Compare commits

...
248 Commits
Author SHA1 Message Date
Jim Miller f181ff2c03 Bump versions 2015-09-17 10:50:46 -05:00
Jim Miller 389a04ce81 Update example URLs for mediaminer.org. 2015-09-17 10:46:56 -05:00
Jim Miller 787ebbdb53 Allow forum.questionablequesting.com now as well as questionablequesting.com. 2015-09-16 11:35:06 -05:00
Jim Miller cc6b31427e Update for mediaminer.org story URL changes. 2015-09-14 12:33:06 -05:00
Jim Miller af9679a290 Update translation files. 2015-09-14 10:22:20 -05:00
Jim Miller c18a972b12 Set 0/N as initial LoopProgressDialog display. 2015-09-09 09:02:18 -05:00
Jim Miller 10d297d77f Change plugin to deal adapters that can change story URL due to being given chapter url. 2015-09-09 08:44:57 -05:00
Jim Miller df10e539a9 Add test cases that change story URL. 2015-09-09 08:21:39 -05:00
Jim Miller 16a090c019 Change story URL when given chapter URL instead of story start URL. 2015-09-09 08:18:29 -05:00
Jim Miller 5472b21447 Fix mediaminer.org for site changes. 2015-09-08 09:31:59 -05:00
Jim Miller 0e17e15466 Stop logging a common html parsing error that we're ignoring anyway. 2015-09-08 09:31:06 -05:00
Jim Miller e30bd1adcc Add forumtags to [base_xenforoforum], include in title page, but not subjects by default. 2015-09-08 09:30:05 -05:00
Jim Miller c47bf27689 Skip output_filename_safepattern on formatext so .epub doesn't become _epub. 2015-09-08 08:47:25 -05:00
Jim Miller 84a308289c Change output_filename_safepattern to replace leading '.' for benefit of *nix OSes. 2015-09-08 08:03:10 -05:00
Jim Miller 94b44c9519 Record forum thread tags in base_xenforoforum. 2015-09-04 12:30:59 -05:00
Jim Miller 1c431cd972 Fix eFiction Base Author URLs. 2015-09-03 11:50:58 -05:00
Jim Miller 0233404429 Remove some debug output from epubutils.py 2015-09-02 08:36:21 -05:00
Jim Miller ca2d2ff0be Fix fall back for FimF cover image when there's a 'medium' but not a 'large' available. 2015-09-02 08:35:59 -05:00
Jim Miller 0b4fc8b138 On UnNew of an anthology, also update individiual toc.ncx files used for EpubMerge UnMerge. 2015-08-31 15:20:25 -05:00
Jim Miller 29598b1306 Convert dark-solace.org to eFiction Base adapter to fix user login problem. 2015-08-31 13:52:47 -05:00
Jim Miller 4990368ac5 Switch chapter #post-12345 URLs to permalinks. 2015-08-31 10:46:33 -05:00
Jim Miller ef3969b33b Merge pull request #106 from cryzed/master
Added adapter for quotev.com - thanks cryzed!
2015-08-31 08:34:00 -05:00
cryzed 4cb69a0a3c Parse additional metadata with the quotev adapter 2015-08-31 14:18:06 +02:00
cryzed 3488c54f3d Added adapter for quotev.com 2015-08-31 06:05:25 +02:00
Jim Miller ee211a362a Fix missing , so mark_new_chapters doesn't show red editing personal.ini. 2015-08-29 08:31:18 -05:00
Jim Miller ddc957d1b7 Explicitly set publisher=None to avoid occasional problems. 2015-08-29 08:30:37 -05:00
Jim Miller e677dc063d Update translations, bump versions. 2015-08-17 13:31:56 -05:00
Jim Miller 1079713432 Add another tweak to xenforum title/tag processing. 2015-08-17 13:27:14 -05:00
Jim Miller ff0ed8c9a2 Tweak xenforum tagsfromtitle 2015-08-11 11:09:43 -05:00
Jim Miller a5c731e471 Add additional check for check_next_chapter on ffnet when site it down. 2015-08-11 10:52:54 -05:00
Jim Miller dafbac5c9b Add minor fix for portkey.org chapter parsing. 2015-08-09 16:24:27 -05:00
Jim Miller 668fca6f6e Add DESCRIPTION.rst explicitly to pip package. Was in whl file, but not source zip. 2015-08-05 09:05:57 -05:00
Jim Miller e97f03a680 Add DESCRIPTION.rst explicitly to pip package. Was in whl file, but not source zip. 2015-08-05 09:03:16 -05:00
Jim Miller 0c272bcf36 Change dramione.org default encoding to utf8. 2015-08-05 08:58:24 -05:00
Jim Miller 58eca7efff Don't require trailing slash on base_xenforoforum. 2015-08-03 17:07:14 -05:00
Jim Miller 5b31f55b18 Add questionablequesting.com as another base_xenforoforum adapter. 2015-08-03 10:17:23 -05:00
Jim Miller e071b0de4e Update translations, bump versions. 2015-07-31 11:10:30 -05:00
Jim Miller 49c899df5d Add chapter range to title if used. Can be disabled in ini. 2015-07-29 08:42:44 -05:00
Jim Miller cfbe3610af Update translations 2015-07-27 13:00:03 -05:00
Jim Miller 2e8d942057 Update translations 2015-07-27 12:58:42 -05:00
Jim Miller 457b0f6fc3 Merge pull request #103 from PlushBeaver/masseffect2in
Add MassEffect2.in Adapter
2015-07-27 12:53:42 -05:00
Dmitry Kozliuk 0ec1e8b779 Switch MassEffect2.in adapter to BeautifulSoup 4.3. 2015-07-27 20:05:54 +03:00
Dmitry Kozliuk 1ad45299db Fix mistakes and typos in configuration per JimmXinu's suggestion.
See GitHub PR comments:
    https://github.com/JimmXinu/FanFicFare/pull/103#discussion_r35535523
    https://github.com/JimmXinu/FanFicFare/pull/103#discussion_r35535396
2015-07-27 20:03:22 +03:00
Dmitry Kozliuk 3ff24b8543 Merge branch 'master' into masseffect2in 2015-07-27 20:03:04 +03:00
Dmitry Kozliuk db1cf8587c Set lifted `slow_down_sleep_time' to prevent IP ban for excessive requests. 2015-07-27 20:02:20 +03:00
Dmitry Kozliuk 13dde78139 Append warnings to story metadata. 2015-07-27 20:01:51 +03:00
Jim Miller 03d3938876 Force CLI/web service config file reads to use utf-8. Needed for incoming masseffect2in adapter. 2015-07-27 08:33:21 -05:00
Jim Miller 60f90850cb Don't need to check file existance ourselves for configparser. 2015-07-27 08:31:54 -05:00
Dmitry Kozliuk 9d5c64b5db Remove development and debugging facilities. 2015-07-26 22:00:08 +03:00
Dmitry Kozliuk acc0048ef0 Merge branch 'master' into masseffect2in 2015-07-26 21:42:22 +03:00
Dmitry Kozliuk 5b01eef495 Add documentation strings, make some methods private (__*). 2015-07-26 21:38:15 +03:00
Dmitry Kozliuk b8710eba97 Collect story-wide metadata across all chapters.
* Support multiple authors for story and no author for chapter.
    * Make chapter rating optional.
    * Detect chapter (and thus, story) "adultness" by either rating or
      editor warning, whichever is present.
    * Add first chapter summary as story summary, parse as summary
      either a dedicated attribute or freestanding text.
2015-07-26 21:31:16 +03:00
Dmitry Kozliuk e2e4590f1d Consider story in progress if the last, not any, chapter is in progress. 2015-07-26 21:31:16 +03:00
Dmitry Kozliuk fb6a8fc931 Support more variants of chapter and story attribute formats.
Collaterally, parse characters and pairings to separate lists.
2015-07-26 21:31:16 +03:00
Dmitry Kozliuk 9c84c7201c Replace intricate numbering parsing with simpler approach.
Instead of locating numbering elements in headings, extracting titles
and indices and then combining them into chapter titles, we employ a
much simpler approach:
    * The longest common prefix of all headings is story title.
    * Everithing after it in every prefix is chapter title.
    * If `chapter X' is found in heading, prefix length is corrected.
    * If chapter title contains numbering prefix, chapter index is
      extracted (but not part index and not chapter title separately).
2015-07-26 20:45:36 +03:00
Jim Miller 19c6b241fe Tweak forum back tagsfromtitle. 2015-07-24 12:54:05 -05:00
Dmitry Kozliuk 2516e617e4 Remove more stop-words variants. 2015-07-24 03:37:58 +03:00
Dmitry Kozliuk d91d4b8c3c Refactor and improve heading parsing.
Now several (relatively) simple REs are used instead of a complex one.
New heading variants are supported:
    * Story title. Chapter X. Chapter title (part Y)
    * Story title. Chapter X (continued)
    * Story title. First chapter
Potentially overridable method `Chapter._extractHeading()' extracted.
2015-07-24 03:33:39 +03:00
Jim Miller 2b0d2fc5c1 Add 'Download from Email Immediately' optional feature to plugin. 2015-07-23 08:19:41 -05:00
Dmitry Kozliuk d809ac9f6c Prevent capturing chapters from related stories.
When prequel or sequel is posted, editors sometimes make `Next/Previous
chapter' links between them.  Since it is the only mechanism for chapter
detection, additional title check was added.  It is heuristical and may
need improvement one day.
2015-07-23 02:47:49 +03:00
Dmitry Kozliuk a8ce9d5711 Add editor signature removal capability.
All chapters have editor signature in the end.  Users wishing to remove
it can switch `exclude_editor_signature' option in `personal.ini'.
2015-07-23 02:44:50 +03:00
Dmitry Kozliuk 79b56c872f Refactor MassEffect2.in adapter and improve it.
Refactoring:
    * New `Chapter' class extracted to separate HTML parsing from
      adapter output preparation and story-wide metadata collection.
    * Lazy-parsing and fragments caching is done at Chapter level.

Improvements:
    * Rating "adultness" and label-to-title mapping made configurable.
    * Fix chapter number detection when title contains large numbers
      (ex.: http://www.masseffect2.in/publ/19-1-0-2934).
    * Add mechanism for detecting series-like stories with no chapter
      numbering and extracting correct titles.
    * Fix number format for generated chapter titles.
2015-07-23 02:44:03 +03:00
Dmitry Kozliuk 6a13323c92 Improved configuration per JimmXinu's suggestion.
https://github.com/PlushBeaver/FanFicFare/commit/707f7a347bfffd80a12e806c255c4b4e24f29dfa#commitcomment-12298782
2015-07-22 19:33:28 +03:00
Dmitry Kozliuk d5d2a28d85 Merge branch 'master' into masseffect2in 2015-07-22 17:29:33 +03:00
Jim Miller f72ac3c979 Add site ninelives.dark-solace.org as Base eFiction adapter. 2015-07-22 08:42:47 -05:00
Dmitry Kozliuk aa93d4bb2d Set site-specific language and category correctly. 2015-07-22 14:31:06 +03:00
Dmitry Kozliuk 707f7a347b Add rudimentary support for `www.masseffect2.in'.
Status: usable, but needs various enhancements and refactoring.

Implemented:
    * Downloading of whole stories given a chapter URL.
    * Automatic chapter numbering extraction and title generation.
    * Author identification.
    * Word and chapter (not chapter parts) counting.
    * Genre, character, and rating detection (in basic cases).
2015-07-22 01:12:13 +03:00
Jim Miller 0e59651635 Fix issue with series excluded becoming 'None' instead of ''. 2015-07-21 10:51:16 -05:00
Jim Miller 61accdff32 Add chapter limits with URL (like [3-4]) for web service. 2015-07-17 13:26:37 -05:00
Jim Miller ee0817faba Add chapter limits with URL (like [3-4]) for web service. 2015-07-17 13:11:38 -05:00
Jim Miller 5849f7cbbf Fix base_xenforoforum_adapter for redirected URLs with #fragments--happens if thread title changed. 2015-07-17 12:15:33 -05:00
Jim Miller fe8e5a641c Fixes for spikeluver.com 2015-07-17 10:58:30 -05:00
Jim Miller 48749cfc2e Update messages.pot for translations. 2015-07-14 13:46:11 -05:00
Jim Miller fd561c0d74 Merge branch 'master' into spacebattles 2015-07-14 13:43:52 -05:00
Jim Miller cae4a74578 Bump version to v2.2.10 2015-07-14 13:33:05 -05:00
Jim Miller 3839bba182 Update translations. 2015-07-14 13:30:31 -05:00
Jim Miller d633f70ce7 Tweak forums title replace_metadata 2015-07-14 13:27:22 -05:00
Jim Miller 19109bfb4e Improved comment. 2015-07-12 15:41:43 -05:00
Jim Miller b2cc7053ee Minor tweak fixes. 2015-07-10 17:58:01 -05:00
Jim Miller 50a725d74a Merge branch 'master' into spacebattles 2015-07-10 17:00:52 -05:00
Jim Miller 4338f4e550 Fix 'kludgey text find for older mediaminer story'. 2015-07-10 16:56:39 -05:00
Jim Miller 883f9e22cc Yet more tweaks to mediaminer.org URL detection. 2015-07-10 16:44:10 -05:00
Jim Miller fbf409ccc5 Add ini chapter title patterns for default, add, new and addnew. 2015-07-10 16:38:08 -05:00
Jim Miller 58f093072a Keep existing (new) chapter marks when updating epub. 2015-07-10 12:40:54 -05:00
Jim Miller 66768f617e Merge branch 'master' into spacebattles 2015-07-10 12:20:26 -05:00
Jim Miller 9b468da598 Make mediaminer.org URLs more flexible. 2015-07-10 12:19:27 -05:00
Jim Miller 26e54b3fcb Remove unneeded vim & #! comments. 2015-07-10 10:55:46 -05:00
Jim Miller d065ae56d2 Make UnNew on 'mark read' optional, add '--unnew' option to CLI. 2015-07-10 10:40:17 -05:00
Jim Miller 6dbe797bba Merge branch 'master' into spacebattles 2015-07-08 20:30:31 -05:00
Jim Miller fa90a3f23c Updates for mediaminer.org changes. 2015-07-08 12:04:29 -05:00
Jim Miller e3c5d97e5e Merge branch 'master' into spacebattles 2015-07-07 23:19:04 -05:00
Jim Miller 4f7fd93b64 Make searching for existing books by title/author(s) optional. 2015-07-07 23:18:46 -05:00
Jim Miller e637b4b073 Save first version of UnNew feature for removing '(new)' marks on chapters. 2015-07-03 11:16:47 -05:00
Jim Miller 21872601db Allow https links from SV forum stories, too. 2015-07-03 11:15:46 -05:00
Jim Miller d5403e2705 Merge branch 'master' into spacebattles 2015-06-30 22:56:27 -05:00
Jim Miller d37dadf972 Update translations. 2015-06-30 22:49:22 -05:00
Jim Miller a84c5dea19 Remove outdated comment. 2015-06-30 22:44:06 -05:00
Jim Miller ce2476d3a8 Add [base_efiction] and [base_xenforoforum] sections, add base_xenforoforum_adapter, document new options. 2015-06-29 13:07:38 -05:00
Jim Miller 4dcfd6e4be Add [base_efiction] and [base_xenforoforum] sections, add base_xenforoforum_adapter, document new options. 2015-06-29 13:07:21 -05:00
Jim Miller b2c1d485b9 Merge branch 'master' into spacebattles 2015-06-29 10:29:37 -05:00
Jim Miller 5dbbc2efe5 Strip imap config options of lead/trail spaces. 2015-06-29 10:29:28 -05:00
Jim Miller 1de8755d36 Add more forums tweaks and '(new)' chapter mark option. 2015-06-29 10:28:53 -05:00
Jim Miller 972cbffbaf Merge branch 'master' into spacebattles 2015-06-26 12:51:26 -05:00
Jim Miller c442feeb26 Add feature - make it optional to set the Calibre Author URL (on Standard Columns tab) 2015-06-26 12:47:01 -05:00
Jim Miller 17b0800242 Add feature - make it optional to set the Calibre Author URL (on Standard Columns tab) 2015-06-26 12:46:14 -05:00
Jim Miller dfae104674 forum adapters - Fixes 2015-06-26 12:18:55 -05:00
Jim Miller ddc3607df6 forum adapters - Take pub/update dates from index post if not from threadmarks. 2015-06-25 18:19:38 -05:00
Jim Miller ce5869313d Merge v2.2.9 2015-06-25 13:54:33 -05:00
Jim Miller 3c6a60f001 Bump version to v2.2.9 2015-06-25 13:39:02 -05:00
Jim Miller 96529571b2 Update translations. 2015-06-25 13:22:06 -05:00
Jim Miller ea2f64a7fb Add additional features to/for forums(SB&SV) adapters. 2015-06-25 13:18:47 -05:00
Jim Miller 78f1760857 Merge branch 'master' into spacebattles 2015-06-22 09:46:57 -05:00
Jim Miller ab2eb447e2 Exclude doReplacements on add_genre_when_multi_category call to getList('category'). 2015-06-22 09:46:33 -05:00
Jim Miller b4bfdd5914 Merge branch 'master' into spacebattles 2015-06-20 13:08:45 -05:00
Jim Miller 71a44e4e64 Default bulk_load true for all adapters. 2015-06-20 12:50:18 -05:00
Jim Miller ff42cd86e2 Update translations, bulk_load for NHA, Rated==Rating in eFiction base. 2015-06-20 12:48:16 -05:00
Jim Miller fd2a4a1ee4 Merge branch 'master' into spacebattles 2015-06-16 07:19:01 -05:00
Jim Miller e2c34eaea1 Update adapter_nhamagicalworldsus, make a Base eFiction adapter. 2015-06-16 07:13:12 -05:00
Jim Miller aaf32dee67 Merge branch 'master' into spacebattles 2015-06-12 19:56:53 -05:00
Jim Miller 78e5d8427b Make passing Calibre Columns in optional and only pass savemetacol data when column is configured to reduce data passed to/from BG processes. 2015-06-12 19:39:30 -05:00
Jim Miller c3c4fb8344 Allow forums URLs to point to non-first posts for index. 2015-06-10 23:44:36 -05:00
Jim Miller 92a60b5583 Merge branch 'master' into spacebattles 2015-06-09 18:07:56 -05:00
Jim Miller c0adf8e027 Bump version to v2.2.8 2015-06-09 17:56:11 -05:00
Jim Miller 69d1ce6c01 Preserve order of URLs fetched from page--especially important for anthologies. 2015-06-09 13:08:56 -05:00
Jim Miller 390c661a88 Preserve order of URLs fetched from page--especially important for anthologies. 2015-06-09 13:00:43 -05:00
Jim Miller b72889efdf Merge branch 'master' into spacebattles 2015-06-08 20:23:34 -05:00
Jim Miller 6ff1ed4ba9 Correct index.html change list. 2015-06-08 20:16:23 -05:00
Jim Miller ea1bbc0be0 Update translations. 2015-06-08 20:00:38 -05:00
Jim Miller 6b45689377 Bump version to v2.2.7 2015-06-08 19:58:57 -05:00
Jim Miller d2535ef12b Exclude iframe tags in forums stories. 2015-06-08 11:13:17 -05:00
Jim Miller 0246ecafcf Handle dup chapter URLs with redirect better in cache. 2015-06-05 10:55:19 -05:00
Jim Miller 3428c18c47 Fix for hardcoded http:// urls being redirected to https:// urls on SB 2015-06-04 09:26:38 -05:00
Jim Miller a9aa7ba505 Add forums.sufficientvelocity.com as a child of SB adapter. 2015-06-04 08:53:22 -05:00
Jim Miller fcc5c1424d Change forums.spacebattles.com to https. 2015-06-01 09:31:00 -05:00
Jim Miller 9b8599ffff Merge branch 'master' into spacebattles 2015-05-30 16:23:21 -05:00
Jim Miller 2a174f1762 Normalize story URLs from email before comparing to Reject List. 2015-05-30 16:23:12 -05:00
Jim Miller 69ae58686e Normalize story URLs from email before comparing to Reject List. 2015-05-30 16:18:36 -05:00
Jim Miller 542685be93 Merge branch 'master' into spacebattles 2015-05-30 10:36:33 -05:00
Jim Miller 50095a3b74 Merge pull request #102 from cryzed/master
Prevent duplicated story URLs even without normalization
2015-05-30 10:29:13 -05:00
Jim Miller 495bfb36b3 Fix dump_html_metadata for non-string values. 2015-05-30 10:16:16 -05:00
Jim Miller d6d08345b7 Fix add_genre_when_multi_category when genre is empty. 2015-05-30 09:30:41 -05:00
cryzed f9573e2061 Prevent duplicated story URLs even without normalization 2015-05-30 15:27:05 +02:00
Jim Miller dd73420412 Merge branch 'master' into spacebattles 2015-05-29 11:59:13 -05:00
Jim Miller 7b9edf9f6f Bump version to v2.2.6 2015-05-29 10:44:29 -05:00
Jim Miller bf5b88b88b Update Translations. 2015-05-29 10:33:26 -05:00
Jim Miller cf0e47dd29 Merge branch 'master' into spacebattles 2015-05-28 19:39:38 -05:00
Jim Miller 280b89dc51 Add support for specific story covers on storiesonline.net -- Thanks, davidfor 2015-05-28 19:35:38 -05:00
Jim Miller a11d4729bd Add update chapters by remembered URLs feature. 2015-05-28 19:34:19 -05:00
Jim Miller 8e8bb93f72 Merge branch 'master' into spacebattles 2015-05-27 10:44:34 -05:00
Jim Miller be2160158c Fix add_genre_when_multi_category for AO3 changes to genre/category. 2015-05-27 10:41:13 -05:00
Jim Miller a2f461475d Merge branch 'master' into spacebattles 2015-05-26 16:27:01 -05:00
Jim Miller 9658a2552b Don't flag ini error on do_update_hook in [archiveofourown.org]. 2015-05-25 19:59:15 -05:00
Jim Miller 3306b11a4f Change AO3 genre & category to fill with freeformtags, ao3categories & fandoms from defaults.ini instead of by hardcode. 2015-05-25 15:47:57 -05:00
Jim Miller f62172b40a Add semi-support for forums.spacebattles.com. 2015-05-25 14:19:59 -05:00
Jim Miller 86a134f883 Fix for storiesonline universe parsing (from davidfor). 2015-05-21 12:21:17 -05:00
Jim Miller 4490edfa36 Update translations messages. 2015-05-21 10:13:37 -05:00
Jim Miller a822b60069 Fix get_update_data call when overwriting with logfile. 2015-05-21 10:11:27 -05:00
Jim Miller e81e2655fc Merge remote-tracking branch '2FanFicFare/master' into metadata 2015-05-18 12:01:57 -05:00
Jim Miller 8d517ccf27 Fix for Reject always on Fetch from Email. 2015-05-18 12:01:12 -05:00
Jim Miller a80b9d1114 Merge remote-tracking branch '2FanFicFare/master' into metadata 2015-05-15 17:47:16 -05:00
Jim Miller 9fb3c72d3f Polish Series/Anthology update, busy cursor. 2015-05-15 17:46:54 -05:00
Jim Miller 5b57571367 Fix and Tweak Saved Metadata and Calibre Metadata-into-ebooks features. 2015-05-15 11:49:46 -05:00
Jim Miller 2b81623936 Merge remote-tracking branch '2FanFicFare/master' into metadata 2015-05-14 22:54:42 -05:00
Jim Miller 3a120e6a0e Polish Fetch from Page, busy cursor. 2015-05-14 22:54:32 -05:00
Jim Miller aaf366f22a Merge remote-tracking branch '2FanFicFare/master' into metadata 2015-05-14 22:52:39 -05:00
Jim Miller e5edb7b945 Polish Fetch from Page, busy cursor. 2015-05-14 22:52:33 -05:00
Jim Miller dfa46a14cb Merge remote-tracking branch '2FanFicFare/master' into metadata 2015-05-14 22:28:24 -05:00
Jim Miller a5b162b187 Polish Fetch from Email, add auto-reject feature. 2015-05-14 22:28:10 -05:00
Jim Miller d9b5b4bfe3 Merge remote-tracking branch '2FanFicFare/master' into metadata 2015-05-14 22:16:06 -05:00
Jim Miller beef2ebadc Polish Fetch from Email, add auto-reject feature. 2015-05-14 22:15:30 -05:00
Jim Miller 44e3d07195 Tweak metadata save/reuse. 2015-05-13 12:59:42 -05:00
Jim Miller b2411d5888 Suppress display of 'Update from Saved' when savemetacol not set, other fixes. 2015-05-13 12:27:24 -05:00
Jim Miller e61371d5c4 Merge remote-tracking branch 'origin' into metadata 2015-05-12 17:54:38 -05:00
Jim Miller d59a1bda1a Add exception catch for possible corner case on Linux 2015-05-12 15:57:01 -05:00
Jim Miller ef52acd5b3 Save and use metadata from a custom column, and pass cal cols into fff on updates. 2015-05-08 16:36:08 -05:00
Jim Miller 29185ec574 Merge remote-tracking branch '2FanFicFare/master' into metadata 2015-05-07 12:08:15 -05:00
Jim Miller 989f3c2c80 Update html5lib to 0.99999. 2015-05-07 12:06:51 -05:00
Jim Miller 7e8f72e234 Merge branch 'master' of https://github.com/JimmXinu/FanFicFare into metadata 2015-05-07 11:21:58 -05:00
Jim Miller 872f00087e Update translations. 2015-05-07 11:13:10 -05:00
Jim Miller 5433633888 Bump version v2.2.5 2015-05-07 11:05:56 -05:00
Jim Miller d93e4a152d Remove metadata saved in epub code, keep stubs for metadata saved elsewhere. Calibre User Categories into metadata isn't working right. 2015-05-05 17:33:59 -05:00
Jim Miller 52487456d7 Save more partial code for metadata saved in epubs and existing cal columns passed into update. Epub metadata version. 2015-05-05 16:13:27 -05:00
Jim Miller cf826b3e36 Merge remote-tracking branch 'origin/master' into metadata 2015-05-05 13:41:14 -05:00
Jim Miller 2bc30444c8 Fix for grangerenchanted.com bad HTML summary causing crash. 2015-05-05 13:38:57 -05:00
Jim Miller f36aac7362 Merge remote-tracking branch 'origin/master' into metadata 2015-05-05 13:18:37 -05:00
Jim Miller 4a2df36443 Fix ponyfictionarchive.net stories without status. 2015-05-05 13:15:04 -05:00
Jim Miller 67f9fc12b9 Merge remote-tracking branch 'origin' into metadata 2015-05-01 10:00:41 -05:00
Jim Miller 5dd2959eb0 Fix ficwad.com changing author URLs. 2015-05-01 09:57:35 -05:00
Jim Miller 5ff7660b67 Merge branch 'master' into metadata 2015-04-30 16:07:06 -05:00
Jim Miller 3d07257f7c Bump version v2.2.4 2015-04-29 11:03:06 -05:00
Jim Miller b7d2fdba81 Update translations. 2015-04-29 11:02:23 -05:00
Jim Miller 41cf8dff09 Save partial code for metadata saved in epubs and existing cal columns passed into update. 2015-04-29 10:54:57 -05:00
Jim Miller b2fbe6ea09 Update strings for translation. 2015-04-27 11:56:07 -05:00
Jim Miller 0415f3bd6c Improve Reject list 2015-04-24 13:42:16 -05:00
Jim Miller bad9a0ea36 Merge branch 'master' into calibre_cover_generate 2015-04-24 12:12:37 -05:00
Jim Miller d51bb8373f Fix multi-page chapters on storiesonline.net. 2015-04-24 12:11:39 -05:00
Jim Miller 138b751519 Enhance Cover Generation settings, including option to use Cal's built-in cover gen. 2015-04-23 20:07:34 -05:00
Jim Miller 53e9030a61 Remove 'Include images in EPUBs?' config option from plugin--default to always include images. 2015-04-23 17:56:04 -05:00
Jim Miller 3ab60a9808 Add ini notes about cover_image with generate_cover_settings 2015-04-23 17:46:56 -05:00
Jim Miller bdf5d45a3c Update Calibre Cover settings only--not function yet. 2015-04-23 17:46:07 -05:00
Jim Miller f91aa5ba3f Merge remote-tracking branch 'origin/master' into calibre_cover_generate 2015-04-22 22:27:57 -05:00
Jim Miller 4980dd8027 Fix Spanish(es) %(pini)s--fixed in Transifex 2015-04-22 17:23:54 -05:00
Jim Miller ca6bc7f88e Detect and reject animated gifs in Calibre because they come out so poorly. 2015-04-22 16:50:56 -05:00
Jim Miller 53ca251a49 Add to FimF cover_exclusion_regexp and smaller cover when href not found. 2015-04-22 15:48:24 -05:00
Jim Miller dda8360044 Improve error reporting when only one URL vs list. 2015-04-22 15:40:46 -05:00
Jim Miller f51b21cfeb Add to FimF cover_exclusion_regexp and smaller cover when href not found. 2015-04-22 14:04:25 -05:00
Jim Miller e07bd0653b Add to FimF cover_exclusion_regexp and smaller cover when href not found. 2015-04-22 14:03:58 -05:00
Jim Miller b16aee27a1 More fix for storiesonline.net change 2015-04-21 13:28:20 -05:00
Jim Miller 17a631dc79 More fix for storiesonline.net change 2015-04-21 10:44:49 -05:00
Jim Miller 808b44cf9b Pass allmetadata back out from jobs.py to have cover_image. 2015-04-20 21:19:10 -05:00
Jim Miller 62db815781 Merge branch 'master' into calibre_cover_generate 2015-04-20 21:16:07 -05:00
Jim Miller d2aa6c1774 Save come defaults.ini comment changes. 2015-04-20 21:12:35 -05:00
Jim Miller 48e1bc7aa4 Add cover_image meta-metadata for source of cover image: specific, first, old or default. 2015-04-20 20:32:34 -05:00
Jim Miller f6b1529c27 Add Readme for translation dir 2015-04-20 20:16:02 -05:00
Jim Miller 84b0070d2c Translation updates. 2015-04-18 13:28:31 -05:00
Jim Miller 37e80cb63b Bump version v2.2.3 2015-04-18 13:21:02 -05:00
Jim Miller c82a157bad Add site it-could-happen.net. 2015-04-17 14:09:57 -05:00
Jim Miller 555fa7678f Change code.google link. 2015-04-16 18:09:41 -05:00
Jim Miller eeccde995f Merge branch 'master' of https://github.com/JimmXinu/FanFicFare 2015-04-16 17:11:31 -05:00
Jim Miller e82a21e303 Fix wiki link. 2015-04-16 17:09:03 -05:00
Jim Miller 64d147910d Update README.md 2015-04-16 17:08:10 -05:00
Jim Miller 04e0bde07b Update PI about box. 2015-04-16 13:30:13 -05:00
Jim Miller 0a07ebc8b2 Fix storiesonline.net site changes 2015-04-16 13:24:52 -05:00
Jim Miller c4c4ff152f Add tgstorytime.com to allowed list for bulk_load param. 2015-04-15 19:52:19 -05:00
Jim Miller bc82d35c92 Update for PI forum thread. 2015-04-15 18:50:44 -05:00
Jim Miller 28b9fa511f Bump versions -- v2.2.2 2015-04-15 16:39:27 -05:00
Jim Miller 9cf75c4774 Bump versions -- v2.2.1 2015-04-15 16:36:59 -05:00
Jim Miller 2e1bb8139a Bump versions -- v2.2.1 2015-04-15 16:33:41 -05:00
Jim Miller 1c1b6a25c4 Bump versions -- v2.2.1 2015-04-15 16:25:45 -05:00
Jim Miller 6569c87060 Fix for anthology from URLs immediately after making non-EPUB single book. 2015-04-15 15:55:09 -05:00
Jim Miller d26298042c Add -i/--infile option for CLI to do lists of URLs (and/or EPUBs with -u) 2015-04-15 15:42:27 -05:00
Jim Miller 90baa68695 Add eFiction Base adapter for tgstorytime.com. 2015-04-15 13:44:54 -05:00
Jim Miller 2b289c6c93 Remove unnecessary commented code. 2015-04-15 13:43:35 -05:00
Jim Miller edf4039115 Yet more renaming, plus a few ini tweaks. 2015-04-15 12:07:10 -05:00
Jim Miller 819dc06d8f Updates to translations for name change. Now include all languages with +25% strings vs +90% before. 2015-04-15 12:06:21 -05:00
Jim Miller 3ecfdd568e Add option to checking ffnet auth img vs cover img, fix new ini params. 2015-04-12 23:17:07 -05:00
Jim Miller 853295bcf9 Switch to real pypi, still need '--pre' flag while beta. 2015-04-12 17:28:12 -05:00
Jim Miller d95401116e Remove defunct sites. 2015-04-12 17:27:36 -05:00
Jim Miller fad5d6837d Fix problems found during trawl through all sites. 2015-04-11 16:51:18 -05:00
Jim Miller 01d9c79a67 Yet more name/url changes. 2015-04-11 16:41:53 -05:00
Jim Miller b4b6f6924c Fix for ffnet's latest change to story/cover image. 2015-04-11 16:18:26 -05:00
Jim Miller 6b744216ab More renaming, update POT for translations. 2015-04-11 11:18:35 -05:00
Jim Miller be1f541da9 Change some menu & gui details to be clearer, more renaming. 2015-04-11 11:10:27 -05:00
Jim Miller f8fd109873 Change FFF icon more (green) 2015-04-09 21:46:04 -05:00
Jim Miller c48346f0ec Fix PI CLI. 2015-04-09 21:44:42 -05:00
Jim Miller 48df00fdef Update copyrights, partial changes to about.txt 2015-04-08 17:45:04 -05:00
Jim Miller 6b36cb29b9 Additional Renaming from FFDL to FFF, plugin copyright/LICENSE updates. 2015-04-08 17:28:25 -05:00
Jim Miller ff647d488b Bump and sync version numbers for alpha test. 2015-04-08 14:31:41 -05:00
188 changed files with 15433 additions and 8780 deletions
+1
View File
@@ -25,3 +25,4 @@ output
build
dist
FanFicFare.egg-info
personal.ini
+682
View File
@@ -1,3 +1,8 @@
The code in fanficfare and webservice are under the Apache License.
The code in calibre-plugin, because it derives from other GPLv3 code,
is also GPLv3. GPLv3 follows the Apache License.
Apache License
Version 2.0, January 2004
@@ -200,3 +205,680 @@
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
GNU GENERAL PUBLIC LICENSE
Version 3, 29 June 2007
Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The GNU General Public License is a free, copyleft license for
software and other kinds of works.
The licenses for most software and other practical works are designed
to take away your freedom to share and change the works. By contrast,
the GNU General Public License is intended to guarantee your freedom to
share and change all versions of a program--to make sure it remains free
software for all its users. We, the Free Software Foundation, use the
GNU General Public License for most of our software; it applies also to
any other work released this way by its authors. You can apply it to
your programs, too.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
them if you wish), that you receive source code or can get it if you
want it, that you can change the software or use pieces of it in new
free programs, and that you know you can do these things.
To protect your rights, we need to prevent others from denying you
these rights or asking you to surrender the rights. Therefore, you have
certain responsibilities if you distribute copies of the software, or if
you modify it: responsibilities to respect the freedom of others.
For example, if you distribute copies of such a program, whether
gratis or for a fee, you must pass on to the recipients the same
freedoms that you received. You must make sure that they, too, receive
or can get the source code. And you must show them these terms so they
know their rights.
Developers that use the GNU GPL protect your rights with two steps:
(1) assert copyright on the software, and (2) offer you this License
giving you legal permission to copy, distribute and/or modify it.
For the developers' and authors' protection, the GPL clearly explains
that there is no warranty for this free software. For both users' and
authors' sake, the GPL requires that modified versions be marked as
changed, so that their problems will not be attributed erroneously to
authors of previous versions.
Some devices are designed to deny users access to install or run
modified versions of the software inside them, although the manufacturer
can do so. This is fundamentally incompatible with the aim of
protecting users' freedom to change the software. The systematic
pattern of such abuse occurs in the area of products for individuals to
use, which is precisely where it is most unacceptable. Therefore, we
have designed this version of the GPL to prohibit the practice for those
products. If such problems arise substantially in other domains, we
stand ready to extend this provision to those domains in future versions
of the GPL, as needed to protect the freedom of users.
Finally, every program is threatened constantly by software patents.
States should not allow patents to restrict development and use of
software on general-purpose computers, but in those that do, we wish to
avoid the special danger that patents applied to a free program could
make it effectively proprietary. To prevent this, the GPL assures that
patents cannot be used to render the program non-free.
The precise terms and conditions for copying, distribution and
modification follow.
TERMS AND CONDITIONS
0. Definitions.
"This License" refers to version 3 of the GNU General Public License.
"Copyright" also means copyright-like laws that apply to other kinds of
works, such as semiconductor masks.
"The Program" refers to any copyrightable work licensed under this
License. Each licensee is addressed as "you". "Licensees" and
"recipients" may be individuals or organizations.
To "modify" a work means to copy from or adapt all or part of the work
in a fashion requiring copyright permission, other than the making of an
exact copy. The resulting work is called a "modified version" of the
earlier work or a work "based on" the earlier work.
A "covered work" means either the unmodified Program or a work based
on the Program.
To "propagate" a work means to do anything with it that, without
permission, would make you directly or secondarily liable for
infringement under applicable copyright law, except executing it on a
computer or modifying a private copy. Propagation includes copying,
distribution (with or without modification), making available to the
public, and in some countries other activities as well.
To "convey" a work means any kind of propagation that enables other
parties to make or receive copies. Mere interaction with a user through
a computer network, with no transfer of a copy, is not conveying.
An interactive user interface displays "Appropriate Legal Notices"
to the extent that it includes a convenient and prominently visible
feature that (1) displays an appropriate copyright notice, and (2)
tells the user that there is no warranty for the work (except to the
extent that warranties are provided), that licensees may convey the
work under this License, and how to view a copy of this License. If
the interface presents a list of user commands or options, such as a
menu, a prominent item in the list meets this criterion.
1. Source Code.
The "source code" for a work means the preferred form of the work
for making modifications to it. "Object code" means any non-source
form of a work.
A "Standard Interface" means an interface that either is an official
standard defined by a recognized standards body, or, in the case of
interfaces specified for a particular programming language, one that
is widely used among developers working in that language.
The "System Libraries" of an executable work include anything, other
than the work as a whole, that (a) is included in the normal form of
packaging a Major Component, but which is not part of that Major
Component, and (b) serves only to enable use of the work with that
Major Component, or to implement a Standard Interface for which an
implementation is available to the public in source code form. A
"Major Component", in this context, means a major essential component
(kernel, window system, and so on) of the specific operating system
(if any) on which the executable work runs, or a compiler used to
produce the work, or an object code interpreter used to run it.
The "Corresponding Source" for a work in object code form means all
the source code needed to generate, install, and (for an executable
work) run the object code and to modify the work, including scripts to
control those activities. However, it does not include the work's
System Libraries, or general-purpose tools or generally available free
programs which are used unmodified in performing those activities but
which are not part of the work. For example, Corresponding Source
includes interface definition files associated with source files for
the work, and the source code for shared libraries and dynamically
linked subprograms that the work is specifically designed to require,
such as by intimate data communication or control flow between those
subprograms and other parts of the work.
The Corresponding Source need not include anything that users
can regenerate automatically from other parts of the Corresponding
Source.
The Corresponding Source for a work in source code form is that
same work.
2. Basic Permissions.
All rights granted under this License are granted for the term of
copyright on the Program, and are irrevocable provided the stated
conditions are met. This License explicitly affirms your unlimited
permission to run the unmodified Program. The output from running a
covered work is covered by this License only if the output, given its
content, constitutes a covered work. This License acknowledges your
rights of fair use or other equivalent, as provided by copyright law.
You may make, run and propagate covered works that you do not
convey, without conditions so long as your license otherwise remains
in force. You may convey covered works to others for the sole purpose
of having them make modifications exclusively for you, or provide you
with facilities for running those works, provided that you comply with
the terms of this License in conveying all material for which you do
not control copyright. Those thus making or running the covered works
for you must do so exclusively on your behalf, under your direction
and control, on terms that prohibit them from making any copies of
your copyrighted material outside their relationship with you.
Conveying under any other circumstances is permitted solely under
the conditions stated below. Sublicensing is not allowed; section 10
makes it unnecessary.
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
No covered work shall be deemed part of an effective technological
measure under any applicable law fulfilling obligations under article
11 of the WIPO copyright treaty adopted on 20 December 1996, or
similar laws prohibiting or restricting circumvention of such
measures.
When you convey a covered work, you waive any legal power to forbid
circumvention of technological measures to the extent such circumvention
is effected by exercising rights under this License with respect to
the covered work, and you disclaim any intention to limit operation or
modification of the work as a means of enforcing, against the work's
users, your or third parties' legal rights to forbid circumvention of
technological measures.
4. Conveying Verbatim Copies.
You may convey verbatim copies of the Program's source code as you
receive it, in any medium, provided that you conspicuously and
appropriately publish on each copy an appropriate copyright notice;
keep intact all notices stating that this License and any
non-permissive terms added in accord with section 7 apply to the code;
keep intact all notices of the absence of any warranty; and give all
recipients a copy of this License along with the Program.
You may charge any price or no price for each copy that you convey,
and you may offer support or warranty protection for a fee.
5. Conveying Modified Source Versions.
You may convey a work based on the Program, or the modifications to
produce it from the Program, in the form of source code under the
terms of section 4, provided that you also meet all of these conditions:
a) The work must carry prominent notices stating that you modified
it, and giving a relevant date.
b) The work must carry prominent notices stating that it is
released under this License and any conditions added under section
7. This requirement modifies the requirement in section 4 to
"keep intact all notices".
c) You must license the entire work, as a whole, under this
License to anyone who comes into possession of a copy. This
License will therefore apply, along with any applicable section 7
additional terms, to the whole of the work, and all its parts,
regardless of how they are packaged. This License gives no
permission to license the work in any other way, but it does not
invalidate such permission if you have separately received it.
d) If the work has interactive user interfaces, each must display
Appropriate Legal Notices; however, if the Program has interactive
interfaces that do not display Appropriate Legal Notices, your
work need not make them do so.
A compilation of a covered work with other separate and independent
works, which are not by their nature extensions of the covered work,
and which are not combined with it such as to form a larger program,
in or on a volume of a storage or distribution medium, is called an
"aggregate" if the compilation and its resulting copyright are not
used to limit the access or legal rights of the compilation's users
beyond what the individual works permit. Inclusion of a covered work
in an aggregate does not cause this License to apply to the other
parts of the aggregate.
6. Conveying Non-Source Forms.
You may convey a covered work in object code form under the terms
of sections 4 and 5, provided that you also convey the
machine-readable Corresponding Source under the terms of this License,
in one of these ways:
a) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by the
Corresponding Source fixed on a durable physical medium
customarily used for software interchange.
b) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by a
written offer, valid for at least three years and valid for as
long as you offer spare parts or customer support for that product
model, to give anyone who possesses the object code either (1) a
copy of the Corresponding Source for all the software in the
product that is covered by this License, on a durable physical
medium customarily used for software interchange, for a price no
more than your reasonable cost of physically performing this
conveying of source, or (2) access to copy the
Corresponding Source from a network server at no charge.
c) Convey individual copies of the object code with a copy of the
written offer to provide the Corresponding Source. This
alternative is allowed only occasionally and noncommercially, and
only if you received the object code with such an offer, in accord
with subsection 6b.
d) Convey the object code by offering access from a designated
place (gratis or for a charge), and offer equivalent access to the
Corresponding Source in the same way through the same place at no
further charge. You need not require recipients to copy the
Corresponding Source along with the object code. If the place to
copy the object code is a network server, the Corresponding Source
may be on a different server (operated by you or a third party)
that supports equivalent copying facilities, provided you maintain
clear directions next to the object code saying where to find the
Corresponding Source. Regardless of what server hosts the
Corresponding Source, you remain obligated to ensure that it is
available for as long as needed to satisfy these requirements.
e) Convey the object code using peer-to-peer transmission, provided
you inform other peers where the object code and Corresponding
Source of the work are being offered to the general public at no
charge under subsection 6d.
A separable portion of the object code, whose source code is excluded
from the Corresponding Source as a System Library, need not be
included in conveying the object code work.
A "User Product" is either (1) a "consumer product", which means any
tangible personal property which is normally used for personal, family,
or household purposes, or (2) anything designed or sold for incorporation
into a dwelling. In determining whether a product is a consumer product,
doubtful cases shall be resolved in favor of coverage. For a particular
product received by a particular user, "normally used" refers to a
typical or common use of that class of product, regardless of the status
of the particular user or of the way in which the particular user
actually uses, or expects or is expected to use, the product. A product
is a consumer product regardless of whether the product has substantial
commercial, industrial or non-consumer uses, unless such uses represent
the only significant mode of use of the product.
"Installation Information" for a User Product means any methods,
procedures, authorization keys, or other information required to install
and execute modified versions of a covered work in that User Product from
a modified version of its Corresponding Source. The information must
suffice to ensure that the continued functioning of the modified object
code is in no case prevented or interfered with solely because
modification has been made.
If you convey an object code work under this section in, or with, or
specifically for use in, a User Product, and the conveying occurs as
part of a transaction in which the right of possession and use of the
User Product is transferred to the recipient in perpetuity or for a
fixed term (regardless of how the transaction is characterized), the
Corresponding Source conveyed under this section must be accompanied
by the Installation Information. But this requirement does not apply
if neither you nor any third party retains the ability to install
modified object code on the User Product (for example, the work has
been installed in ROM).
The requirement to provide Installation Information does not include a
requirement to continue to provide support service, warranty, or updates
for a work that has been modified or installed by the recipient, or for
the User Product in which it has been modified or installed. Access to a
network may be denied when the modification itself materially and
adversely affects the operation of the network or violates the rules and
protocols for communication across the network.
Corresponding Source conveyed, and Installation Information provided,
in accord with this section must be in a format that is publicly
documented (and with an implementation available to the public in
source code form), and must require no special password or key for
unpacking, reading or copying.
7. Additional Terms.
"Additional permissions" are terms that supplement the terms of this
License by making exceptions from one or more of its conditions.
Additional permissions that are applicable to the entire Program shall
be treated as though they were included in this License, to the extent
that they are valid under applicable law. If additional permissions
apply only to part of the Program, that part may be used separately
under those permissions, but the entire Program remains governed by
this License without regard to the additional permissions.
When you convey a copy of a covered work, you may at your option
remove any additional permissions from that copy, or from any part of
it. (Additional permissions may be written to require their own
removal in certain cases when you modify the work.) You may place
additional permissions on material, added by you to a covered work,
for which you have or can give appropriate copyright permission.
Notwithstanding any other provision of this License, for material you
add to a covered work, you may (if authorized by the copyright holders of
that material) supplement the terms of this License with terms:
a) Disclaiming warranty or limiting liability differently from the
terms of sections 15 and 16 of this License; or
b) Requiring preservation of specified reasonable legal notices or
author attributions in that material or in the Appropriate Legal
Notices displayed by works containing it; or
c) Prohibiting misrepresentation of the origin of that material, or
requiring that modified versions of such material be marked in
reasonable ways as different from the original version; or
d) Limiting the use for publicity purposes of names of licensors or
authors of the material; or
e) Declining to grant rights under trademark law for use of some
trade names, trademarks, or service marks; or
f) Requiring indemnification of licensors and authors of that
material by anyone who conveys the material (or modified versions of
it) with contractual assumptions of liability to the recipient, for
any liability that these contractual assumptions directly impose on
those licensors and authors.
All other non-permissive additional terms are considered "further
restrictions" within the meaning of section 10. If the Program as you
received it, or any part of it, contains a notice stating that it is
governed by this License along with a term that is a further
restriction, you may remove that term. If a license document contains
a further restriction but permits relicensing or conveying under this
License, you may add to a covered work material governed by the terms
of that license document, provided that the further restriction does
not survive such relicensing or conveying.
If you add terms to a covered work in accord with this section, you
must place, in the relevant source files, a statement of the
additional terms that apply to those files, or a notice indicating
where to find the applicable terms.
Additional terms, permissive or non-permissive, may be stated in the
form of a separately written license, or stated as exceptions;
the above requirements apply either way.
8. Termination.
You may not propagate or modify a covered work except as expressly
provided under this License. Any attempt otherwise to propagate or
modify it is void, and will automatically terminate your rights under
this License (including any patent licenses granted under the third
paragraph of section 11).
However, if you cease all violation of this License, then your
license from a particular copyright holder is reinstated (a)
provisionally, unless and until the copyright holder explicitly and
finally terminates your license, and (b) permanently, if the copyright
holder fails to notify you of the violation by some reasonable means
prior to 60 days after the cessation.
Moreover, your license from a particular copyright holder is
reinstated permanently if the copyright holder notifies you of the
violation by some reasonable means, this is the first time you have
received notice of violation of this License (for any work) from that
copyright holder, and you cure the violation prior to 30 days after
your receipt of the notice.
Termination of your rights under this section does not terminate the
licenses of parties who have received copies or rights from you under
this License. If your rights have been terminated and not permanently
reinstated, you do not qualify to receive new licenses for the same
material under section 10.
9. Acceptance Not Required for Having Copies.
You are not required to accept this License in order to receive or
run a copy of the Program. Ancillary propagation of a covered work
occurring solely as a consequence of using peer-to-peer transmission
to receive a copy likewise does not require acceptance. However,
nothing other than this License grants you permission to propagate or
modify any covered work. These actions infringe copyright if you do
not accept this License. Therefore, by modifying or propagating a
covered work, you indicate your acceptance of this License to do so.
10. Automatic Licensing of Downstream Recipients.
Each time you convey a covered work, the recipient automatically
receives a license from the original licensors, to run, modify and
propagate that work, subject to this License. You are not responsible
for enforcing compliance by third parties with this License.
An "entity transaction" is a transaction transferring control of an
organization, or substantially all assets of one, or subdividing an
organization, or merging organizations. If propagation of a covered
work results from an entity transaction, each party to that
transaction who receives a copy of the work also receives whatever
licenses to the work the party's predecessor in interest had or could
give under the previous paragraph, plus a right to possession of the
Corresponding Source of the work from the predecessor in interest, if
the predecessor has it or can get it with reasonable efforts.
You may not impose any further restrictions on the exercise of the
rights granted or affirmed under this License. For example, you may
not impose a license fee, royalty, or other charge for exercise of
rights granted under this License, and you may not initiate litigation
(including a cross-claim or counterclaim in a lawsuit) alleging that
any patent claim is infringed by making, using, selling, offering for
sale, or importing the Program or any portion of it.
11. Patents.
A "contributor" is a copyright holder who authorizes use under this
License of the Program or a work on which the Program is based. The
work thus licensed is called the contributor's "contributor version".
A contributor's "essential patent claims" are all patent claims
owned or controlled by the contributor, whether already acquired or
hereafter acquired, that would be infringed by some manner, permitted
by this License, of making, using, or selling its contributor version,
but do not include claims that would be infringed only as a
consequence of further modification of the contributor version. For
purposes of this definition, "control" includes the right to grant
patent sublicenses in a manner consistent with the requirements of
this License.
Each contributor grants you a non-exclusive, worldwide, royalty-free
patent license under the contributor's essential patent claims, to
make, use, sell, offer for sale, import and otherwise run, modify and
propagate the contents of its contributor version.
In the following three paragraphs, a "patent license" is any express
agreement or commitment, however denominated, not to enforce a patent
(such as an express permission to practice a patent or covenant not to
sue for patent infringement). To "grant" such a patent license to a
party means to make such an agreement or commitment not to enforce a
patent against the party.
If you convey a covered work, knowingly relying on a patent license,
and the Corresponding Source of the work is not available for anyone
to copy, free of charge and under the terms of this License, through a
publicly available network server or other readily accessible means,
then you must either (1) cause the Corresponding Source to be so
available, or (2) arrange to deprive yourself of the benefit of the
patent license for this particular work, or (3) arrange, in a manner
consistent with the requirements of this License, to extend the patent
license to downstream recipients. "Knowingly relying" means you have
actual knowledge that, but for the patent license, your conveying the
covered work in a country, or your recipient's use of the covered work
in a country, would infringe one or more identifiable patents in that
country that you have reason to believe are valid.
If, pursuant to or in connection with a single transaction or
arrangement, you convey, or propagate by procuring conveyance of, a
covered work, and grant a patent license to some of the parties
receiving the covered work authorizing them to use, propagate, modify
or convey a specific copy of the covered work, then the patent license
you grant is automatically extended to all recipients of the covered
work and works based on it.
A patent license is "discriminatory" if it does not include within
the scope of its coverage, prohibits the exercise of, or is
conditioned on the non-exercise of one or more of the rights that are
specifically granted under this License. You may not convey a covered
work if you are a party to an arrangement with a third party that is
in the business of distributing software, under which you make payment
to the third party based on the extent of your activity of conveying
the work, and under which the third party grants, to any of the
parties who would receive the covered work from you, a discriminatory
patent license (a) in connection with copies of the covered work
conveyed by you (or copies made from those copies), or (b) primarily
for and in connection with specific products or compilations that
contain the covered work, unless you entered into that arrangement,
or that patent license was granted, prior to 28 March 2007.
Nothing in this License shall be construed as excluding or limiting
any implied license or other defenses to infringement that may
otherwise be available to you under applicable patent law.
12. No Surrender of Others' Freedom.
If conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot convey a
covered work so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you may
not convey it at all. For example, if you agree to terms that obligate you
to collect a royalty for further conveying from those to whom you convey
the Program, the only way you could satisfy both those terms and this
License would be to refrain entirely from conveying the Program.
13. Use with the GNU Affero General Public License.
Notwithstanding any other provision of this License, you have
permission to link or combine any covered work with a work licensed
under version 3 of the GNU Affero General Public License into a single
combined work, and to convey the resulting work. The terms of this
License will continue to apply to the part which is the covered work,
but the special requirements of the GNU Affero General Public License,
section 13, concerning interaction through a network will apply to the
combination as such.
14. Revised Versions of this License.
The Free Software Foundation may publish revised and/or new versions of
the GNU General Public License from time to time. Such new versions will
be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the
Program specifies that a certain numbered version of the GNU General
Public License "or any later version" applies to it, you have the
option of following the terms and conditions either of that numbered
version or of any later version published by the Free Software
Foundation. If the Program does not specify a version number of the
GNU General Public License, you may choose any version ever published
by the Free Software Foundation.
If the Program specifies that a proxy can decide which future
versions of the GNU General Public License can be used, that proxy's
public statement of acceptance of a version permanently authorizes you
to choose that version for the Program.
Later license versions may give you additional or different
permissions. However, no additional obligations are imposed on any
author or copyright holder as a result of your choosing to follow a
later version.
15. Disclaimer of Warranty.
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. Limitation of Liability.
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
SUCH DAMAGES.
17. Interpretation of Sections 15 and 16.
If the disclaimer of warranty and limitation of liability provided
above cannot be given local legal effect according to their terms,
reviewing courts shall apply local law that most closely approximates
an absolute waiver of all civil liability in connection with the
Program, unless a warranty or assumption of liability accompanies a
copy of the Program in return for a fee.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
state the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
Also add information on how to contact you by electronic and paper mail.
If the program does terminal interaction, make it output a short
notice like this when it starts in an interactive mode:
<program> Copyright (C) <year> <name of author>
This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
This is free software, and you are welcome to redistribute it
under certain conditions; type `show c' for details.
The hypothetical commands `show w' and `show c' should show the appropriate
parts of the General Public License. Of course, your program's commands
might be different; for a GUI interface, you would use an "about box".
You should also get your employer (if you work as a programmer) or school,
if any, to sign a "copyright disclaimer" for the program, if necessary.
For more information on this, and how to apply and follow the GNU GPL, see
<http://www.gnu.org/licenses/>.
The GNU General Public License does not permit incorporating your program
into proprietary programs. If your program is a subroutine library, you
may consider it more useful to permit linking proprietary applications with
the library. If this is what you want to do, use the GNU Lesser General
Public License instead of this License. But first, please read
<http://www.gnu.org/philosophy/why-not-lgpl.html>.
+1
View File
@@ -0,0 +1 @@
include DESCRIPTION.rst
+6 -4
View File
@@ -10,8 +10,10 @@ FFDL, AKA fanficdownloader) project previously hosted as a
This program is available as a calibre plugin, a command-line
interface, and a web service.
*Currently, the project is the middle of being moved from code.google
to GitHub and being renamed. For now, continue to use
FanFictionDownLoader(FFDL).*
FanFicFare has now been launched. New versions, features and updates
will all be in FanFicFare.
[code.google project]: https://code.google.com/p/fanficdownloader/
There's additional info in the project [wiki] pages.
[code.google project]: http://google-opensource.blogspot.com/2015/03/farewell-to-google-code.html
[wiki]: https://github.com/JimmXinu/FanFicFare/wiki
+9 -9
View File
@@ -4,7 +4,7 @@ from __future__ import (unicode_literals, division, absolute_import,
print_function)
__license__ = 'GPL v3'
__copyright__ = '2014, Jim Miller'
__copyright__ = '2015, Jim Miller'
__docformat__ = 'restructuredtext en'
import sys
@@ -32,7 +32,7 @@ class FanFicFareBase(InterfaceActionBase):
'''
This class is a simple wrapper that provides information about the
actual plugin class. The actual interface plugin class is called
InterfacePlugin and is defined in the ffdl_plugin.py file, as
InterfacePlugin and is defined in the fff_plugin.py file, as
specified in the actual_plugin field below.
The reason for having two classes is that it allows the command line
@@ -42,13 +42,13 @@ class FanFicFareBase(InterfaceActionBase):
description = _('UI plugin to download FanFiction stories from various sites.')
supported_platforms = ['windows', 'osx', 'linux']
author = 'Jim Miller'
version = (2, 1, 5)
version = (2, 2, 13)
minimum_calibre_version = (1, 48, 0)
#: This field defines the GUI plugin class that contains all the code
#: that actually does something. Its format is module_path:class_name
#: The specified class must be defined in the specified module.
actual_plugin = 'calibre_plugins.fanficfare_plugin.ffdl_plugin:FanFicFarePlugin'
actual_plugin = 'calibre_plugins.fanficfare_plugin.fff_plugin:FanFicFarePlugin'
def is_customizable(self):
'''
@@ -107,7 +107,7 @@ class FanFicFareBase(InterfaceActionBase):
# CLI--it would load everytime anyway.
from StringIO import StringIO
from calibre.library import db
from calibre_plugins.fanficfare_plugin.downloader import main as ffdl_main
from calibre_plugins.fanficfare_plugin.fanficfare.cli import main as fff_main
from calibre_plugins.fanficfare_plugin.prefs import PrefsFacade
from calibre.utils.config import prefs as calibre_prefs
from optparse import OptionParser
@@ -122,10 +122,10 @@ class FanFicFareBase(InterfaceActionBase):
or not x.startswith('-')]
opts, args = parser.parse_args(pargs)
ffdl_prefs = PrefsFacade(db(path=opts.library_path,
fff_prefs = PrefsFacade(db(path=opts.library_path,
read_only=True))
ffdl_main(argv[1:],
fff_main(argv[1:],
parser=parser,
passed_defaultsini=StringIO(get_resources("defaults.ini")),
passed_personalini=StringIO(ffdl_prefs["personal.ini"]))
passed_defaultsini=StringIO(get_resources("fanficfare/defaults.ini")),
passed_personalini=StringIO(fff_prefs["personal.ini"]))
+32
View File
@@ -0,0 +1,32 @@
<hr />
<p>Plugin created by Jim Miller, borrowing heavily from Grant Drake's
'<a href="http://www.mobileread.com/forums/showthread.php?t=134856">Reading List</a>',
'<a href="http://www.mobileread.com/forums/showthread.php?t=126727">Extract ISBN</a>' and
'<a href="http://www.mobileread.com/forums/showthread.php?t=134000">Count Pages</a>'
plugins.</p>
<p>
Calibre officially distributes plugins from the mobileread.com forum site.
The official distro channel for this plugin is there: <a href="http://www.mobileread.com/forums/showthread.php?t=259221">FanFicFare</a>
</p>
<p> I also monitor the
<a href="http://groups.google.com/group/fanfic-downloader">general users
group</a> for the downloader. That covers the web application and CLI, too.
</p>
<p>
The source for this plugin is available at it's
<a href="https://github.com/JimmXinu/FanFicFare">project home</a>.
</p>
<hr />
<p>
See the <a href="https://github.com/JimmXinu/FanFicFare/wiki/Supportedsites">list of supported sites</a>.
</p>
<p>
Read the <a href="https://github.com/JimmXinu/FanFicFare/wiki/FAQs">FAQs</a>.
</p>
-28
View File
@@ -1,28 +0,0 @@
<hr />
<p>Plugin created by Jim Miller, borrowing heavily from Grant Drake's
'<a href="http://www.mobileread.com/forums/showthread.php?t=134856">Reading List</a>',
'<a href="http://www.mobileread.com/forums/showthread.php?t=126727">Extract ISBN</a>' and
'<a href="http://www.mobileread.com/forums/showthread.php?t=134000">Count Pages</a>'
plugins.</p>
<p>
Calibre officially distributes plugins from the mobileread.com forum site.
The official distro channel for this plugin is there: <a href="http://www.mobileread.com/forums/showthread.php?t=163261">FanFictionDownLoader</a>
</p>
<p> I also monitor the
<a href="http://groups.google.com/group/fanfic-downloader">general users
group</a> for the downloader. That covers the web application and CLI, too.
</p>
The source for this plugin is available at it's
<a href="http://code.google.com/p/fanficdownloader">project home</a>.
<hr />
<p>
See the <a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderSupportedsites">list of supported sites</a>.
</p>
<p>
Read the <a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderFAQs">FAQs</a>.
</p>
+3 -3
View File
@@ -1,10 +1,10 @@
#!/usr/bin/env python
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
# -*- coding: utf-8 -*-
from __future__ import (unicode_literals, division,
print_function)
__license__ = 'GPL v3'
__copyright__ = '2014, Jim Miller'
__copyright__ = '2015, Jim Miller'
__docformat__ = 'restructuredtext en'
import re
+3 -3
View File
@@ -1,10 +1,10 @@
#!/usr/bin/env python
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
# -*- coding: utf-8 -*-
from __future__ import (unicode_literals, division, absolute_import,
print_function)
__license__ = 'GPL v3'
__copyright__ = '2011, Grant Drake <grant.drake@gmail.com>'
__copyright__ = '2011, Grant Drake <grant.drake@gmail.com>, 2015, Jim Miller'
__docformat__ = 'restructuredtext en'
import os
+323 -97
View File
@@ -1,5 +1,5 @@
#!/usr/bin/env python
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
# -*- coding: utf-8 -*-
from __future__ import (unicode_literals, division, absolute_import,
print_function)
@@ -17,12 +17,12 @@ try:
from PyQt5.Qt import (QDialog, QWidget, QVBoxLayout, QHBoxLayout, QGridLayout,
QLabel, QLineEdit, QFont, QWidget, QTextEdit, QComboBox,
QCheckBox, QPushButton, QTabWidget, QScrollArea,
QDialogButtonBox, QGroupBox, Qt )
QDialogButtonBox, QGroupBox, QButtonGroup, QRadioButton, Qt)
except ImportError as e:
from PyQt4.Qt import (QDialog, QWidget, QVBoxLayout, QHBoxLayout, QGridLayout,
QLabel, QLineEdit, QFont, QWidget, QTextEdit, QComboBox,
QCheckBox, QPushButton, QTabWidget, QScrollArea,
QDialogButtonBox, QGroupBox, Qt )
QDialogButtonBox, QGroupBox, QButtonGroup, QRadioButton, Qt)
try:
from calibre.gui2 import QVariant
del QVariant
@@ -39,9 +39,15 @@ else:
return [convert_qvariant(i) for i in x.toList()]
return x.toPyObject()
from calibre.gui2.ui import get_gui
from calibre.gui2 import dynamic, info_dialog, question_dialog
from calibre.constants import numeric_version as calibre_version
from calibre.gui2.ui import get_gui
from calibre.gui2.complete2 import EditWithComplete
try:
from calibre.ebooks.covers import generate_cover as cal_generate_cover
HAS_CALGC=True
except:
HAS_CALGC=False
# pulls in translation files for _() strings
try:
@@ -49,12 +55,14 @@ try:
except NameError:
pass # load_translations() added in calibre 1.9
from calibre.library.field_metadata import FieldMetadata
field_metadata = FieldMetadata()
# There are a number of things used several times that shouldn't be
# translated. This is just a way to make that easier by keeping them
# out of the _() strings.
# I'm tempted to override _() to include them...
no_trans = { 'pini':'personal.ini',
'imgset':'\n\n[epub]\ninclude_images:true\nkeep_summary_html:true\nmake_firstimage_cover:true\n\n',
'gcset':'generate_cover_settings',
'ccset':'custom_columns_settings',
'gc':'Generate Cover',
@@ -70,22 +78,25 @@ no_trans = { 'pini':'personal.ini',
'p':'password',
}
from calibre_plugins.fanficfare_plugin.prefs import prefs, PREFS_NAMESPACE
STD_COLS_SKIP = ['size','cover','news','ondevice','path','series_sort','sort']
from calibre_plugins.fanficfare_plugin.prefs \
import (prefs, PREFS_NAMESPACE, updatecalcover_order, calcover_save_options,
gencalcover_order, SAVE_YES, SAVE_NO)
from calibre_plugins.fanficfare_plugin.dialogs \
import (UPDATE, UPDATEALWAYS, collision_order, save_collisions, RejectListDialog,
EditTextDialog, IniTextDialog, RejectUrlEntry)
from calibre_plugins.fanficfare_plugin.fanficfare.adapters \
import getConfigSections
import getSiteSections
from calibre_plugins.fanficfare_plugin.common_utils \
import ( KeyboardConfigDialog, PrefsViewerDialog )
from calibre_plugins.fanficfare_plugin.ffdl_util \
from calibre_plugins.fanficfare_plugin.fff_util \
import (test_config)
from calibre.gui2.complete2 import EditWithComplete #MultiCompleteLineEdit
class RejectURLList:
def __init__(self,prefs):
self.prefs = prefs
@@ -176,7 +187,12 @@ class ConfigWidget(QWidget):
self.l = QVBoxLayout()
self.setLayout(self.l)
label = QLabel('<a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderSupportedsites">'+_('List of Supported Sites')+'</a> -- <a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderFAQs">'+_('FAQs')+'</a>')
label = QLabel('<a href="'\
+'https://github.com/JimmXinu/FanFicFare/wiki/Supportedsites">'\
+_('List of Supported Sites')+'</a> -- <a href="'\
+'https://github.com/JimmXinu/FanFicFare/wiki/FAQs">'\
+_('FAQs')+'</a>')
label.setOpenExternalLinks(True)
self.l.addWidget(label)
@@ -200,10 +216,8 @@ class ConfigWidget(QWidget):
if 'Reading List' not in plugin_action.gui.iactions:
self.readinglist_tab.setEnabled(False)
self.generatecover_tab = GenerateCoverTab(self, plugin_action)
tab_widget.addTab(self.generatecover_tab, 'Generate Cover')
if 'Generate Cover' not in plugin_action.gui.iactions:
self.generatecover_tab.setEnabled(False)
self.calibrecover_tab = CalibreCoverTab(self, plugin_action)
tab_widget.addTab(self.calibrecover_tab, _('Calibre Cover'))
self.countpages_tab = CountPagesTab(self, plugin_action)
tab_widget.addTab(self.countpages_tab, 'Count Pages')
@@ -229,7 +243,6 @@ class ConfigWidget(QWidget):
prefs['fileform'] = unicode(self.basic_tab.fileform.currentText())
prefs['collision'] = save_collisions[unicode(self.basic_tab.collision.currentText())]
prefs['updatemeta'] = self.basic_tab.updatemeta.isChecked()
prefs['updatecover'] = self.basic_tab.updatecover.isChecked()
prefs['updateepubcover'] = self.basic_tab.updateepubcover.isChecked()
prefs['keeptags'] = self.basic_tab.keeptags.isChecked()
prefs['suppressauthorsort'] = self.basic_tab.suppressauthorsort.isChecked()
@@ -242,11 +255,11 @@ class ConfigWidget(QWidget):
prefs['updatedefault'] = self.basic_tab.updatedefault.isChecked()
prefs['deleteotherforms'] = self.basic_tab.deleteotherforms.isChecked()
prefs['adddialogstaysontop'] = self.basic_tab.adddialogstaysontop.isChecked()
prefs['includeimages'] = self.basic_tab.includeimages.isChecked()
prefs['lookforurlinhtml'] = self.basic_tab.lookforurlinhtml.isChecked()
prefs['checkforseriesurlid'] = self.basic_tab.checkforseriesurlid.isChecked()
prefs['checkforurlchange'] = self.basic_tab.checkforurlchange.isChecked()
prefs['injectseries'] = self.basic_tab.injectseries.isChecked()
prefs['matchtitleauth'] = self.basic_tab.matchtitleauth.isChecked()
prefs['smarten_punctuation'] = self.basic_tab.smarten_punctuation.isChecked()
prefs['reject_always'] = self.basic_tab.reject_always.isChecked()
@@ -259,6 +272,7 @@ class ConfigWidget(QWidget):
prefs['addtolists'] = self.readinglist_tab.addtolists.isChecked()
prefs['addtoreadlists'] = self.readinglist_tab.addtoreadlists.isChecked()
prefs['addtolistsonread'] = self.readinglist_tab.addtolistsonread.isChecked()
prefs['autounnew'] = self.readinglist_tab.autounnew.isChecked()
# personal.ini
ini = self.personalini_tab.personalini
@@ -268,17 +282,25 @@ class ConfigWidget(QWidget):
# if they've removed everything, reset to default.
prefs['personal.ini'] = get_resources('plugin-example.ini')
# Generate Covers tab
prefs['gcnewonly'] = self.generatecover_tab.gcnewonly.isChecked()
prefs['cal_cols_pass_in'] = self.personalini_tab.cal_cols_pass_in.isChecked()
# Covers tab
prefs['updatecalcover'] = calcover_save_options[unicode(self.calibrecover_tab.updatecalcover.currentText())]
# for backward compatibility:
prefs['updatecover'] = prefs['updatecalcover'] == SAVE_YES
prefs['gencalcover'] = calcover_save_options[unicode(self.calibrecover_tab.gencalcover.currentText())]
prefs['calibre_gen_cover'] = self.calibrecover_tab.calibre_gen_cover.isChecked()
prefs['plugin_gen_cover'] = self.calibrecover_tab.plugin_gen_cover.isChecked()
prefs['gcnewonly'] = self.calibrecover_tab.gcnewonly.isChecked()
gc_site_settings = {}
for (site,combo) in self.generatecover_tab.gc_dropdowns.iteritems():
for (site,combo) in self.calibrecover_tab.gc_dropdowns.iteritems():
val = unicode(convert_qvariant(combo.itemData(combo.currentIndex())))
if val != 'none':
gc_site_settings[site] = val
#print("gc_site_settings[%s]:%s"%(site,gc_site_settings[site]))
prefs['gc_site_settings'] = gc_site_settings
prefs['allow_gc_from_ini'] = self.generatecover_tab.allow_gc_from_ini.isChecked()
prefs['gc_polish_cover'] = self.generatecover_tab.gc_polish_cover.isChecked()
prefs['allow_gc_from_ini'] = self.calibrecover_tab.allow_gc_from_ini.isChecked()
prefs['gc_polish_cover'] = self.calibrecover_tab.gc_polish_cover.isChecked()
# Count Pages tab
countpagesstats = []
@@ -303,10 +325,15 @@ class ConfigWidget(QWidget):
colsnewonly[col] = checkbox.isChecked()
prefs['std_cols_newonly'] = colsnewonly
prefs['set_author_url'] =self.std_columns_tab.set_author_url.isChecked()
# Custom Columns tab
# error column
prefs['errorcol'] = unicode(convert_qvariant(self.cust_columns_tab.errorcol.itemData(self.cust_columns_tab.errorcol.currentIndex())))
# metadata column
prefs['savemetacol'] = unicode(convert_qvariant(self.cust_columns_tab.savemetacol.itemData(self.cust_columns_tab.savemetacol.currentIndex())))
# cust cols tab
colsmap = {}
for (col,combo) in self.cust_columns_tab.custcol_dropdowns.iteritems():
@@ -323,12 +350,14 @@ class ConfigWidget(QWidget):
prefs['allow_custcol_from_ini'] = self.cust_columns_tab.allow_custcol_from_ini.isChecked()
prefs['imapserver'] = unicode(self.imap_tab.imapserver.text())
prefs['imapuser'] = unicode(self.imap_tab.imapuser.text())
prefs['imappass'] = unicode(self.imap_tab.imappass.text())
prefs['imapfolder'] = unicode(self.imap_tab.imapfolder.text())
prefs['imapserver'] = unicode(self.imap_tab.imapserver.text()).strip()
prefs['imapuser'] = unicode(self.imap_tab.imapuser.text()).strip()
prefs['imappass'] = unicode(self.imap_tab.imappass.text()).strip()
prefs['imapfolder'] = unicode(self.imap_tab.imapfolder.text()).strip()
prefs['imapmarkread'] = self.imap_tab.imapmarkread.isChecked()
prefs['imapsessionpass'] = self.imap_tab.imapsessionpass.isChecked()
prefs['auto_reject_from_email'] = self.imap_tab.auto_reject_from_email.isChecked()
prefs['download_from_email_immediately'] = self.imap_tab.download_from_email_immediately.isChecked()
prefs.save_to_db()
@@ -358,7 +387,7 @@ class BasicTab(QWidget):
self.l = QVBoxLayout()
groupbox.setLayout(self.l)
tooltip = _("On each download, FFF offers an option to select the output format. <br />This sets what that option will default to.")
tooltip = _("On each download, FanFicFare offers an option to select the output format. <br />This sets what that option will default to.")
horz = QHBoxLayout()
label = QLabel(_('Default Output &Format:'))
label.setToolTip(tooltip)
@@ -375,7 +404,7 @@ class BasicTab(QWidget):
horz.addWidget(self.fileform)
self.l.addLayout(horz)
tooltip = _("On each download, FFF offers an option of what happens if that story already exists. <br />This sets what that option will default to.")
tooltip = _("On each download, FanFicFare offers an option of what happens if that story already exists. <br />This sets what that option will default to.")
horz = QHBoxLayout()
label = QLabel(_('Default If Story Already Exists?'))
label.setToolTip(tooltip)
@@ -391,21 +420,17 @@ class BasicTab(QWidget):
horz.addWidget(self.collision)
self.l.addLayout(horz)
horz = QHBoxLayout()
self.updatemeta = QCheckBox(_('Default Update Calibre &Metadata?'),self)
self.updatemeta.setToolTip(_("On each download, FFF offers an option to update Calibre's metadata (title, author, URL, tags, custom columns, etc) from the web site. <br />This sets whether that will default to on or off. <br />Columns set to 'New Only' in the column tabs will only be set for new books."))
self.updatemeta.setToolTip(_("On each download, FanFicFare offers an option to update Calibre's metadata (title, author, URL, tags, custom columns, etc) from the web site. <br />This sets whether that will default to on or off. <br />Columns set to 'New Only' in the column tabs will only be set for new books."))
self.updatemeta.setChecked(prefs['updatemeta'])
self.l.addWidget(self.updatemeta)
horz.addWidget(self.updatemeta)
self.updateepubcover = QCheckBox(_('Default Update EPUB Cover when Updating EPUB?'),self)
self.updateepubcover.setToolTip(_("On each download, FFF offers an option to update the book cover image <i>inside</i> the EPUB from the web site when the EPUB is updated.<br />This sets whether that will default to on or off."))
self.updateepubcover.setToolTip(_("On each download, FanFicFare offers an option to update the book cover image <i>inside</i> the EPUB from the web site when the EPUB is updated.<br />This sets whether that will default to on or off."))
self.updateepubcover.setChecked(prefs['updateepubcover'])
self.l.addWidget(self.updateepubcover)
self.smarten_punctuation = QCheckBox(_('Smarten Punctuation (EPUB only)'),self)
self.smarten_punctuation.setToolTip(_("Run Smarten Punctuation from Calibre's Polish Book feature on each EPUB download and update."))
self.smarten_punctuation.setChecked(prefs['smarten_punctuation'])
if calibre_version >= (0, 9, 39):
self.l.addWidget(self.smarten_punctuation)
horz.addWidget(self.updateepubcover)
self.l.addLayout(horz)
cali_gb = groupbox = QGroupBox(_("Updating Calibre Options"))
self.l = QVBoxLayout()
@@ -416,11 +441,6 @@ class BasicTab(QWidget):
self.deleteotherforms.setChecked(prefs['deleteotherforms'])
self.l.addWidget(self.deleteotherforms)
self.updatecover = QCheckBox(_('Update Calibre Cover when Updating Metadata?'),self)
self.updatecover.setToolTip(_("Update calibre book cover image from EPUB when metadata is updated. (EPUB only.)\nDoesn't go looking for new images on 'Update Calibre Metadata Only'."))
self.updatecover.setChecked(prefs['updatecover'])
self.l.addWidget(self.updatecover)
self.keeptags = QCheckBox(_('Keep Existing Tags when Updating Metadata?'),self)
self.keeptags.setToolTip(_("Existing tags will be kept and any new tags added.\n%(cmplt)s and %(inprog)s tags will be still be updated, if known.\n%(lul)s tags will be updated if %(lus)s in %(is)s.\n(If Tags is set to 'New Only' in the Standard Columns tab, this has no effect.)")%no_trans)
self.keeptags.setChecked(prefs['keeptags'])
@@ -452,25 +472,25 @@ class BasicTab(QWidget):
self.l.addWidget(self.lookforurlinhtml)
self.mark = QCheckBox(_("Mark added/updated books when finished?"),self)
self.mark.setToolTip(_("Mark added/updated books when finished. Use with option below.\nYou can also manually search for 'marked:ffdl_success'.\n'marked:ffdl_failed' is also available, or search 'marked:ffdl' for both."))
self.mark.setToolTip(_("Mark added/updated books when finished. Use with option below.\nYou can also manually search for 'marked:fff_success'.\n'marked:fff_failed' is also available, or search 'marked:fff' for both."))
self.mark.setChecked(prefs['mark'])
self.l.addWidget(self.mark)
self.showmarked = QCheckBox(_("Show Marked books when finished?"),self)
self.showmarked.setToolTip(_("Show Marked added/updated books only when finished.\nYou can also manually search for 'marked:ffdl_success'.\n'marked:ffdl_failed' is also available, or search 'marked:ffdl' for both."))
self.showmarked.setToolTip(_("Show Marked added/updated books only when finished.\nYou can also manually search for 'marked:fff_success'.\n'marked:fff_failed' is also available, or search 'marked:fff' for both."))
self.showmarked.setChecked(prefs['showmarked'])
self.l.addWidget(self.showmarked)
self.smarten_punctuation = QCheckBox(_('Smarten Punctuation (EPUB only)'),self)
self.smarten_punctuation.setToolTip(_("Run Smarten Punctuation from Calibre's Polish Book feature on each EPUB download and update."))
self.smarten_punctuation.setChecked(prefs['smarten_punctuation'])
self.l.addWidget(self.smarten_punctuation)
self.autoconvert = QCheckBox(_("Automatically Convert new/update books?"),self)
self.autoconvert.setToolTip(_("Automatically call calibre's Convert for new/update books.\nConverts to the current output format as chosen in calibre's\nPreferences->Behavior settings."))
self.autoconvert.setChecked(prefs['autoconvert'])
self.l.addWidget(self.autoconvert)
self.show_est_time = QCheckBox(_("Show estimated time left?"),self)
self.show_est_time.setToolTip(_("When a Progress Bar is shown, show a rough estimate of the time left."))
self.show_est_time.setChecked(prefs['show_est_time'])
self.l.addWidget(self.show_est_time)
gui_gb = groupbox = QGroupBox(_("GUI Options"))
self.l = QVBoxLayout()
groupbox.setLayout(self.l)
@@ -481,7 +501,7 @@ class BasicTab(QWidget):
self.l.addWidget(self.urlsfromclip)
self.updatedefault = QCheckBox(_('Default to Update when books selected?'),self)
self.updatedefault.setToolTip(_('The top FanFictionDownLoader plugin button will start Update if\nbooks are selected. If unchecked, it will always bring up \'Add New\'.'))
self.updatedefault.setToolTip(_('The top FanFicFare plugin button will start Update if\nbooks are selected. If unchecked, it will always bring up \'Add New\'.'))
self.updatedefault.setChecked(prefs['updatedefault'])
self.l.addWidget(self.updatedefault)
@@ -490,27 +510,31 @@ class BasicTab(QWidget):
self.adddialogstaysontop.setChecked(prefs['adddialogstaysontop'])
self.l.addWidget(self.adddialogstaysontop)
self.show_est_time = QCheckBox(_("Show estimated time left?"),self)
self.show_est_time.setToolTip(_("When a Progress Bar is shown, show a rough estimate of the time left."))
self.show_est_time.setChecked(prefs['show_est_time'])
self.l.addWidget(self.show_est_time)
misc_gb = groupbox = QGroupBox(_("Misc Options"))
self.l = QVBoxLayout()
groupbox.setLayout(self.l)
# this is a cheat to make it easier for users to realize there's a new include_images features.
self.includeimages = QCheckBox(_("Include images in EPUBs?"),self)
self.includeimages.setToolTip(_("Download and include images in EPUB stories. This is equivalent to adding:%(imgset)s ...to the top of %(pini)s. Your settings in %(pini)s will override this.")%no_trans)
self.includeimages.setChecked(prefs['includeimages'])
self.l.addWidget(self.includeimages)
self.injectseries = QCheckBox(_("Inject calibre Series when none found?"),self)
self.injectseries.setToolTip(_("If no series is found, inject the calibre series (if there is one) so it appears on the FFF title page(not cover)."))
self.injectseries.setToolTip(_("If no series is found, inject the calibre series (if there is one) so \nit appears on the FanFicFare title page(not cover)."))
self.injectseries.setChecked(prefs['injectseries'])
self.l.addWidget(self.injectseries)
self.matchtitleauth = QCheckBox(_("Search by Title/Author(s) for If Story Already Exists?"),self)
self.matchtitleauth.setToolTip(_("When checking <i>If Story Already Exists</i> FanFicFare will first match by URL Identifier. But if not found, it can also search existing books by Title and Author(s)."))
self.matchtitleauth.setChecked(prefs['matchtitleauth'])
self.l.addWidget(self.matchtitleauth)
rej_gb = groupbox = QGroupBox(_("Reject List"))
self.l = QVBoxLayout()
groupbox.setLayout(self.l)
self.rejectlist = QPushButton(_('Edit Reject URL List'), self)
self.rejectlist.setToolTip(_("Edit list of URLs FFF will automatically Reject."))
self.rejectlist.setToolTip(_("Edit list of URLs FanFicFare will automatically Reject."))
self.rejectlist.clicked.connect(self.show_rejectlist)
self.l.addWidget(self.rejectlist)
@@ -576,7 +600,7 @@ class BasicTab(QWidget):
title=_("Reject Reasons"),
label=_("Customize Reject List Reasons"),
tooltip=_("Customize the Reasons presented when Rejecting URLs"),
save_size_name='ffdl:Reject List Reasons')
save_size_name='fff:Reject List Reasons')
d.exec_()
if d.result() == d.Accepted:
prefs['rejectreasons'] = d.get_plain_text()
@@ -590,7 +614,7 @@ class BasicTab(QWidget):
tooltip=_("One URL per line:\n<b>http://...,note</b>\n<b>http://...,title by author - note</b>"),
rejectreasons=rejecturllist.get_reject_reasons(),
reasonslabel=_('Add this reason to all URLs added:'),
save_size_name='ffdl:Add Reject List')
save_size_name='fff:Add Reject List')
d.exec_()
if d.result() == d.Accepted:
rejecturllist.add_text(d.get_plain_text(),d.get_reason_text())
@@ -610,7 +634,7 @@ class PersonalIniTab(QWidget):
self.l.addWidget(label)
# self.l.addSpacing(5)
label = QLabel(_("<b>New:</b>")+" "+_("FFF now includes find, color coding, and error checking for personal.ini editing. Red generally indicates errors."))
label = QLabel(_("FanFicFare now includes find, color coding, and error checking for personal.ini editing. Red generally indicates errors."))
label.setWordWrap(True)
self.l.addWidget(label)
@@ -634,15 +658,25 @@ class PersonalIniTab(QWidget):
self.ini_button.clicked.connect(self.add_ini_button)
self.l.addWidget(self.ini_button)
label = QLabel(_("Changes will only be saved if you click 'OK' to leave Customize FanFicFare."))
label.setWordWrap(True)
self.l.addWidget(label)
self.defaults = QPushButton(_('View Defaults')+' (plugin-defaults.ini)', self)
self.defaults.setToolTip(_("View all of the plugin's configurable settings\nand their default settings."))
self.defaults.clicked.connect(self.show_defaults)
self.l.addWidget(self.defaults)
label = QLabel(_("Changes will only be saved if you click 'OK' to leave Customize FFF."))
label.setWordWrap(True)
self.l.addWidget(label)
self.cal_cols_pass_in = QCheckBox(_('Pass Calibre Columns into FanFicFare on Update/Overwrite')%no_trans,self)
self.cal_cols_pass_in.setToolTip(_("If checked, when updating/overwriting an existing book, FanFicFare will have the Calibre Columns available to use in replace_metadata, title_page, etc.<br>Click the button below to see the Calibre Column namess.")%no_trans)
self.cal_cols_pass_in.setChecked(prefs['cal_cols_pass_in'])
self.l.addWidget(self.cal_cols_pass_in)
self.showcalcols = QPushButton(_('Show Calibre Column Names'), self)
self.showcalcols.setToolTip(_("FanFicFare can pass the Calibre Columns into the download/update process.<br>This will show you the columns available by name."))
self.showcalcols.clicked.connect(self.show_showcalcols)
self.l.addWidget(self.showcalcols)
self.l.insertStretch(-1)
# let edit box fill the space.
@@ -654,7 +688,7 @@ class PersonalIniTab(QWidget):
label=_("Plugin Defaults (%s) (Read-Only)")%'plugin-defaults.ini',
use_find=True,
read_only=True,
save_size_name='ffdl:defaults.ini').exec_()
save_size_name='fff:defaults.ini').exec_()
def add_ini_button(self):
d = IniTextDialog(self,
@@ -663,11 +697,32 @@ class PersonalIniTab(QWidget):
title=_("Edit personal.ini"),
label=_("Edit personal.ini"),
use_find=True,
save_size_name='ffdl:personal.ini')
save_size_name='fff:personal.ini')
d.exec_()
if d.result() == d.Accepted:
self.personalini = d.get_plain_text()
def show_showcalcols(self):
lines=[]#[('calibre_std_user_categories',_('User Categories'))]
for k,f in field_metadata.iteritems():
if f['name'] and k not in STD_COLS_SKIP: # only if it has a human readable name.
lines.append(('calibre_std_'+k,f['name']))
for k, column in self.plugin_action.gui.library_view.model().custom_columns.iteritems():
if k != prefs['savemetacol']:
# custom always have name.
lines.append(('calibre_cust_'+k[1:],column['name']))
lines.sort() # sort by key.
EditTextDialog(self,
'\n'.join(['%s (%s)'%(l,k) for (k,l) in lines]),
icon=self.windowIcon(),
title=_('Calibre Column Entry Names'),
label=_('Label (entry_name)'),
read_only=True,
save_size_name='fff:showcalcols').exec_()
class ReadingListTab(QWidget):
def __init__(self, parent_dialog, plugin_action):
@@ -703,6 +758,7 @@ class ReadingListTab(QWidget):
self.send_lists_box.update_items_cache(reading_lists)
self.send_lists_box.setText(prefs['send_lists'])
horz.addWidget(self.send_lists_box)
self.send_lists_box.setCursorPosition(0)
self.l.addLayout(horz)
self.addtoreadlists = QCheckBox(_('Add new/updated stories to "To Read" Reading List(s).'),self)
@@ -719,6 +775,7 @@ class ReadingListTab(QWidget):
self.read_lists_box.update_items_cache(reading_lists)
self.read_lists_box.setText(prefs['read_lists'])
horz.addWidget(self.read_lists_box)
self.read_lists_box.setCursorPosition(0)
self.l.addLayout(horz)
self.addtolistsonread = QCheckBox(_('Add stories back to "Send to Device" Reading List(s) when marked "Read".'),self)
@@ -726,16 +783,26 @@ class ReadingListTab(QWidget):
self.addtolistsonread.setChecked(prefs['addtolistsonread'])
self.l.addWidget(self.addtolistsonread)
self.autounnew = QCheckBox(_('Automatically run Remove "New" Chapter Marks when marking books "Read".'),self)
self.autounnew.setToolTip(_('Menu option to remove from "To Read" lists will also remove "(new)" chapter marks created by personal.ini <i>mark_new_chapters</i> setting.'))
self.autounnew.setChecked(prefs['autounnew'])
self.l.addWidget(self.autounnew)
self.l.insertStretch(-1)
class GenerateCoverTab(QWidget):
class CalibreCoverTab(QWidget):
def __init__(self, parent_dialog, plugin_action):
self.parent_dialog = parent_dialog
self.plugin_action = plugin_action
QWidget.__init__(self)
self.l = QVBoxLayout()
self.gencov_elements=[] ## used to disable/enable when gen
## cover is off/on. This is more
## about being a visual que than real
## necessary function.
topl = self.l = QVBoxLayout()
self.setLayout(self.l)
try:
@@ -743,8 +810,116 @@ class GenerateCoverTab(QWidget):
gc_settings = gc_plugin.get_saved_setting_names()
except KeyError:
gc_settings= []
label = QLabel(_('The %(gc)s plugin can create cover images for books using various metadata and configurations. If you have GC installed, FFF can run GC on new downloads and metadata updates. Pick a GC setting by site or Default.')%no_trans)
label = QLabel(_("The Calibre cover image for a downloaded book can come"
" from the story site(if EPUB and images are enabled), or"
" from either Calibre's built-in random cover generator or"
" the %(gc)s plugin.")%no_trans)
label.setWordWrap(True)
self.l.addWidget(label)
self.l.addSpacing(5)
tooltip = _("Update Calibre book cover image from EPUB when Calibre metadata is updated.\n"
"Doesn't go looking for new images on 'Update Calibre Metadata Only'.\n"
"Cover in EPUB could be from site or previously injected into the EPUB.\n"
"This comes before Generate Cover so %(gc)s(Plugin) use the image if configured to.")%no_trans
horz = QHBoxLayout()
label = QLabel(_('Update Calibre Cover (from EPUB):'))
label.setToolTip(tooltip)
horz.addWidget(label)
self.updatecalcover = QComboBox(self)
for i in updatecalcover_order:
self.updatecalcover.addItem(i)
# back compat. If has own value, use.
if prefs['updatecalcover']:
self.updatecalcover.setCurrentIndex(self.updatecalcover.findText(calcover_save_options[prefs['updatecalcover']]))
elif prefs['updatecover']: # doesn't have own val, set YES if old value set.
self.updatecalcover.setCurrentIndex(self.updatecalcover.findText(calcover_save_options[SAVE_YES]))
else: # doesn't have own value, old value not set, NO.
self.updatecalcover.setCurrentIndex(self.updatecalcover.findText(calcover_save_options[SAVE_NO]))
self.updatecalcover.setToolTip(tooltip)
label.setBuddy(self.updatecalcover)
horz.addWidget(self.updatecalcover)
self.l.addLayout(horz)
tooltip = _("Generate a Calibre book cover image when Calibre metadata is updated.<br />"
"Defaults to 'Yes, Always' for backward compatibility and because %(gc)s(Plugin)"
" will only run if configured for Default or site.")%no_trans
horz = QHBoxLayout()
label = QLabel(_('Generate Calibre Cover:'))
label.setToolTip(tooltip)
horz.addWidget(label)
self.gencalcover = QComboBox(self)
for i in gencalcover_order:
self.gencalcover.addItem(i)
# back compat. If has own value, use.
# if prefs['gencalcover']:
self.gencalcover.setCurrentIndex(self.gencalcover.findText(calcover_save_options[prefs['gencalcover']]))
# elif prefs['gencover']: # doesn't have own val, set YES if old value set.
# self.gencalcover.setCurrentIndex(self.gencalcover.findText(calcover_save_options[SAVE_YES]))
# else: # doesn't have own value, old value not set, NO.
# self.gencalcover.setCurrentIndex(self.gencalcover.findText(calcover_save_options[SAVE_NO]))
self.gencalcover.setToolTip(tooltip)
label.setBuddy(self.gencalcover)
horz.addWidget(self.gencalcover)
self.l.addLayout(horz)
self.gencalcover.currentIndexChanged.connect(self.endisable_elements)
# can't be local or it's destroyed when __init__ is done and
# connected things don't fire.
self.gencov_rdgrp = QButtonGroup()
self.gencov_gb = QGroupBox()
horz = QHBoxLayout()
self.gencov_gb.setLayout(horz)
self.plugin_gen_cover = QRadioButton(_('Plugin %(gc)s')%no_trans,self)
self.plugin_gen_cover.setToolTip(_("Use plugin to create covers. Additional settings are below."))
self.gencov_rdgrp.addButton(self.plugin_gen_cover)
# always, new only, when no cover from site, inject yes/no...
self.plugin_gen_cover.setChecked(prefs['plugin_gen_cover'])
horz.addWidget(self.plugin_gen_cover)
self.gencov_elements.append(self.plugin_gen_cover)
self.calibre_gen_cover = QRadioButton(_('Calibre Generate Cover'),self)
self.calibre_gen_cover.setToolTip(_("Call Calibre's Edit Metadata Generate cover"
" feature to create a random cover each time"
" a story is downloaded or updated.<br />"
"Right click or long click the 'Generate cover'"
" button in Calibre's Edit Metadata to customize."))
self.gencov_rdgrp.addButton(self.calibre_gen_cover)
# always, new only, when no cover from site, inject yes/no...
self.calibre_gen_cover.setChecked(prefs['calibre_gen_cover'])
horz.addWidget(self.calibre_gen_cover)
self.gencov_elements.append(self.calibre_gen_cover)
#self.l.addLayout(horz)
self.l.addWidget(self.gencov_gb)
self.gcnewonly = QCheckBox(_("Generate Covers Only for New Books")%no_trans,self)
self.gcnewonly.setToolTip(_("Default is to generate a cover any time the calibre metadata is"
" updated.<br \>Used for both Calibre and Plugin generated covers."))
self.gcnewonly.setChecked(prefs['gcnewonly'])
self.l.addWidget(self.gcnewonly)
self.gencov_elements.append(self.gcnewonly)
self.gc_polish_cover = QCheckBox(_("Inject/update the cover inside EPUB"),self)
self.gc_polish_cover.setToolTip(_("Calibre's Polish feature will be used to inject or update the generated"
" cover into the EPUB ebook file.<br \>Used for both Calibre and Plugin generated covers."))
self.gc_polish_cover.setChecked(prefs['gc_polish_cover'])
self.l.addWidget(self.gc_polish_cover)
self.gencov_elements.append(self.gc_polish_cover)
self.gcp_gb = QGroupBox(_("%(gc)s(Plugin) Settings")%no_trans)
topl.addWidget(self.gcp_gb)
self.l = QVBoxLayout()
self.gcp_gb.setLayout(self.l)
self.gencov_elements.append(self.gcp_gb)
self.gencov_rdgrp.buttonClicked.connect(self.endisable_elements)
label = QLabel(_('The %(gc)s plugin can create cover images for books using various metadata (including existing cover image). If you have %(gc)s installed, FanFicFare can run %(gc)s on new downloads and metadata updates. Pick a %(gc)s setting by site and/or one to use by Default.')%no_trans)
label.setWordWrap(True)
self.l.addWidget(label)
self.l.addSpacing(5)
@@ -760,14 +935,14 @@ class GenerateCoverTab(QWidget):
self.gc_dropdowns = {}
sitelist = getConfigSections()
sitelist = getSiteSections()
sitelist.sort()
sitelist.insert(0,_("Default"))
for site in sitelist:
horz = QHBoxLayout()
label = QLabel(site)
if site == _("Default"):
s = _("On Metadata update, run %(gc)s with this setting, if not selected for specific site.")%no_trans
s = _("On Metadata update, run %(gc)s with this setting, if there isn't a more specific setting below.")%no_trans
else:
no_trans['site']=site # not ideal, but, meh.
s = _("On Metadata update, run %(gc)s with this setting for %(site)s stories.")%no_trans
@@ -793,20 +968,34 @@ class GenerateCoverTab(QWidget):
self.sl.insertStretch(-1)
self.gcnewonly = QCheckBox(_("Run %(gc)s Only on New Books")%no_trans,self)
self.gcnewonly.setToolTip(_("Default is to run GC any time the calibre metadata is updated."))
self.gcnewonly.setChecked(prefs['gcnewonly'])
self.l.addWidget(self.gcnewonly)
self.allow_gc_from_ini = QCheckBox(_('Allow %(gcset)s from %(pini)s to override')%no_trans,self)
self.allow_gc_from_ini.setToolTip(_("The %(pini)s parameter %(gcset)s allows you to choose a GC setting based on metadata rather than site, but it's much more complex.<br \>%(gcset)s is ignored when this is off.")%no_trans)
self.allow_gc_from_ini.setToolTip(_("The %(pini)s parameter %(gcset)s allows you to choose a %(gc)s setting based on metadata"
" rather than site, but it's much more complex.<br \>%(gcset)s is ignored when this is off.")%no_trans)
self.allow_gc_from_ini.setChecked(prefs['allow_gc_from_ini'])
self.l.addWidget(self.allow_gc_from_ini)
self.gc_polish_cover = QCheckBox(_("Use calibre's Polish feature to inject/update the cover"),self)
self.gc_polish_cover.setToolTip(_("Calibre's Polish feature will be used to inject or update the generated cover into the ebook, EPUB only."))
self.gc_polish_cover.setChecked(prefs['gc_polish_cover'])
self.l.addWidget(self.gc_polish_cover)
# keep at end.
self.endisable_elements()
def endisable_elements(self,button=None):
"Clearing house function for setting elements of Calibre"
"Cover tab enabled/disabled depending on all factors."
## First, cover gen on/off
for e in self.gencov_elements:
e.setEnabled(calcover_save_options[unicode(self.gencalcover.currentText())] != SAVE_NO)
# next, disable plugin settings when using calibre gen cov.
if not self.plugin_gen_cover.isChecked():
self.gcp_gb.setEnabled(False)
# disable (but not enable) unsupported options.
if not HAS_CALGC:
self.calibre_gen_cover.setEnabled(False)
if not 'Generate Cover' in self.plugin_action.gui.iactions:
self.plugin_gen_cover.setEnabled(False)
self.gcp_gb.setEnabled(False)
class CountPagesTab(QWidget):
@@ -839,12 +1028,12 @@ class CountPagesTab(QWidget):
horz = QHBoxLayout()
self.wordcount = QCheckBox('Word Count',self)
self.wordcount.setToolTip(tooltip+"\n"+_('Will overwrite word count from FFF metadata if set to update the same custom column.'))
self.wordcount.setToolTip(tooltip+"\n"+_('Will overwrite word count from FanFicFare metadata if set to update the same custom column.'))
self.wordcount.setChecked('WordCount' in prefs['countpagesstats'])
horz.addWidget(self.wordcount)
self.wordcountmissing = QCheckBox('Only if Word Count is Missing in FFF Metadata',self)
self.wordcountmissing.setToolTip(_("Only run Count Page's Word Count if checked <i>and</i> FFF metadata doesn't already have a word count. If this is used with one of the other Page Counts, the Page Count plugin will be called twice."))
self.wordcountmissing = QCheckBox('Only if Word Count is Missing in FanFicFare Metadata',self)
self.wordcountmissing.setToolTip(_("Only run Count Page's Word Count if checked <i>and</i> FanFicFare metadata doesn't already have a word count. If this is used with one of the other Page Counts, the Page Count plugin will be called twice."))
self.wordcountmissing.setChecked(prefs['wordcountmissing'])
self.wordcountmissing.setEnabled(self.wordcount.isChecked())
horz.addWidget(self.wordcountmissing)
@@ -880,7 +1069,7 @@ class OtherTab(QWidget):
self.l = QVBoxLayout()
self.setLayout(self.l)
label = QLabel(_("These controls aren't plugin settings as such, but convenience buttons for setting Keyboard shortcuts and getting all the FanFictionDownLoader confirmation dialogs back again."))
label = QLabel(_("These controls aren't plugin settings as such, but convenience buttons for setting Keyboard shortcuts and getting all the FanFicFare confirmation dialogs back again."))
label.setWordWrap(True)
self.l.addWidget(label)
self.l.addSpacing(5)
@@ -891,7 +1080,7 @@ class OtherTab(QWidget):
self.l.addWidget(keyboard_shortcuts_button)
reset_confirmation_button = QPushButton(_('Reset disabled &confirmation dialogs'), self)
reset_confirmation_button.setToolTip(_('Reset all show me again dialogs for the FanFictionDownLoader plugin'))
reset_confirmation_button.setToolTip(_('Reset all show me again dialogs for the FanFicFare plugin'))
reset_confirmation_button.clicked.connect(self.reset_dialogs)
self.l.addWidget(reset_confirmation_button)
@@ -984,7 +1173,7 @@ titleLabels = {
'formatname':_('File Format'),
'formatext':_('File Extension'),
'siteabbrev':_('Site Abbrev'),
'version':_('FFF Version')
'version':_('FanFicFare Version')
}
class CustomColumnsTab(QWidget):
@@ -1056,7 +1245,6 @@ class CustomColumnsTab(QWidget):
self.allow_custcol_from_ini.setChecked(prefs['allow_custcol_from_ini'])
self.l.addWidget(self.allow_custcol_from_ini)
self.l.addSpacing(5)
label = QLabel(_("Special column:"))
label.setWordWrap(True)
self.l.addWidget(label)
@@ -1075,6 +1263,21 @@ class CustomColumnsTab(QWidget):
self.errorcol.setCurrentIndex(self.errorcol.findData(prefs['errorcol']))
horz.addWidget(self.errorcol)
self.l.addLayout(horz)
horz = QHBoxLayout()
label = QLabel(_("Saved Metadata Column:"))
tooltip=_("If set, FanFicFare will save a copy of all its metadata in this column when the book is downloaded or updated.<br/>The metadata from this column can later be used to update custom columns without having to request the metadata from the server again.<br/>(Long Text columns only.)")
label.setToolTip(tooltip)
horz.addWidget(label)
self.savemetacol = QComboBox(self)
self.savemetacol.setToolTip(tooltip)
self.savemetacol.addItem('','')
for key, column in custom_columns.iteritems():
if column['datatype'] in ('comments'):
self.savemetacol.addItem(column['name'],key)
self.savemetacol.setCurrentIndex(self.savemetacol.findData(prefs['savemetacol']))
horz.addWidget(self.savemetacol)
self.l.addLayout(horz)
#print("prefs['custom_cols'] %s"%prefs['custom_cols'])
@@ -1102,7 +1305,7 @@ class StandardColumnsTab(QWidget):
self.l = QVBoxLayout()
self.setLayout(self.l)
label = QLabel(_("The standard calibre metadata columns are listed below. You may choose whether FFF will fill each column automatically on updates or only for new books."))
label = QLabel(_("The standard calibre metadata columns are listed below. You may choose whether FanFicFare will fill each column automatically on updates or only for new books."))
label.setWordWrap(True)
self.l.addWidget(label)
self.l.addSpacing(5)
@@ -1123,6 +1326,17 @@ class StandardColumnsTab(QWidget):
horz.addWidget(newonlycheck)
self.l.addLayout(horz)
self.l.addSpacing(5)
label = QLabel(_("Other Standard Column Options"))
label.setWordWrap(True)
self.l.addWidget(label)
self.l.addSpacing(5)
self.set_author_url = QCheckBox(_('Set Calibre Author URL'),self)
self.set_author_url.setToolTip(_("Set Calibre Author URL to Author's URL on story site."))
self.set_author_url.setChecked(prefs['set_author_url'])
self.l.addWidget(self.set_author_url)
self.l.insertStretch(-1)
@@ -1137,7 +1351,7 @@ class ImapTab(QWidget):
self.setLayout(self.l)
row=0
label = QLabel(_('These settings will allow FFF to fetch story URLs from your email account. It will only look for story URLs in unread emails in the folder specified below.'))
label = QLabel(_('These settings will allow FanFicFare to fetch story URLs from your email account. It will only look for story URLs in unread emails in the folder specified below.'))
label.setWordWrap(True)
self.l.addWidget(label,row,0,1,-1)
row+=1
@@ -1163,7 +1377,7 @@ class ImapTab(QWidget):
row+=1
label = QLabel(_('IMAP User Password'))
tooltip = _("IMAP password. If left empty, FFF will ask you for your password when you use the feature.")
tooltip = _("IMAP password. If left empty, FanFicFare will ask you for your password when you use the feature.")
label.setToolTip(tooltip)
self.l.addWidget(label,row,0)
self.imappass = QLineEdit(self)
@@ -1174,7 +1388,7 @@ class ImapTab(QWidget):
row+=1
self.imapsessionpass = QCheckBox(_('Remember Password for Session (when not saved above)'),self)
self.imapsessionpass.setToolTip(_('If checked, and no password is entered above, FFF will remember your password until you close calibre or change Libraries.'))
self.imapsessionpass.setToolTip(_('If checked, and no password is entered above, FanFicFare will remember your password until you close calibre or change Libraries.'))
self.imapsessionpass.setChecked(prefs['imapsessionpass'])
self.l.addWidget(self.imapsessionpass,row,0,1,-1)
row+=1
@@ -1195,8 +1409,20 @@ class ImapTab(QWidget):
self.l.addWidget(self.imapmarkread,row,0,1,-1)
row+=1
self.auto_reject_from_email = QCheckBox(_('Discard URLs on Reject List'),self)
self.auto_reject_from_email.setToolTip(_('If checked, FanFicFare will silently discard story URLs from emails that are on your Reject URL List.<br>Otherwise they will appear and you will see the normal Reject URL dialog.<br>The Emails will still be marked Read if configured to.'))
self.auto_reject_from_email.setChecked(prefs['auto_reject_from_email'])
self.l.addWidget(self.auto_reject_from_email,row,0,1,-1)
row+=1
self.download_from_email_immediately = QCheckBox(_('Download from Email Immediately'),self)
self.download_from_email_immediately.setToolTip(_('If checked, FanFicFare will start downloading story URLs from emails immediately.<br>Otherwise the usual Download from URLs dialog will appear.'))
self.download_from_email_immediately.setChecked(prefs['download_from_email_immediately'])
self.l.addWidget(self.download_from_email_immediately,row,0,1,-1)
row+=1
label = QLabel(_("<b>It's safest if you create a separate email account that you use only "
"for your story update notices. FFF and calibre cannot guarantee that "
"for your story update notices. FanFicFare and calibre cannot guarantee that "
"malicious code cannot get your email password once you've entered it. "
"<br>Use this feature at your own risk. </b>"))
label.setWordWrap(True)
+192 -151
View File
@@ -1,5 +1,5 @@
#!/usr/bin/env python
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
# -*- coding: utf-8 -*-
from __future__ import (unicode_literals, division,
print_function)
@@ -79,14 +79,16 @@ UPDATE=_('Update EPUB if New Chapters')
UPDATEALWAYS=_('Update EPUB Always')
OVERWRITE=_('Overwrite if Newer')
OVERWRITEALWAYS=_('Overwrite Always')
CALIBREONLY=_('Update Calibre Metadata Only')
CALIBREONLY=_('Update Calibre Metadata from Web Site')
CALIBREONLYSAVECOL=_('Update Calibre Metadata from Saved Metadata Column')
collision_order=[SKIP,
ADDNEW,
UPDATE,
UPDATEALWAYS,
OVERWRITE,
OVERWRITEALWAYS,
CALIBREONLY,]
CALIBREONLY,
CALIBREONLYSAVECOL,]
# best idea I've had for how to deal with config/pref saving the
# collision name in english.
@@ -97,6 +99,7 @@ SAVE_UPDATEALWAYS='Update EPUB Always'
SAVE_OVERWRITE='Overwrite if Newer'
SAVE_OVERWRITEALWAYS='Overwrite Always'
SAVE_CALIBREONLY='Update Calibre Metadata Only'
SAVE_CALIBREONLYSAVECOL='Update Calibre Metadata Only(Saved Column)'
save_collisions={
SKIP:SAVE_SKIP,
ADDNEW:SAVE_ADDNEW,
@@ -112,8 +115,9 @@ save_collisions={
SAVE_OVERWRITE:OVERWRITE,
SAVE_OVERWRITEALWAYS:OVERWRITEALWAYS,
SAVE_CALIBREONLY:CALIBREONLY,
SAVE_CALIBREONLYSAVECOL:CALIBREONLYSAVECOL,
}
anthology_collision_order=[UPDATE,
UPDATEALWAYS,
OVERWRITEALWAYS]
@@ -122,8 +126,8 @@ gpstyle='QGroupBox {border:0; padding-top:10px; padding-bottom:0px; margin-botto
class RejectUrlEntry:
matchpat=re.compile(r"^(?P<url>[^,]+)(,(?P<fullnote>(((?P<title>.+) by (?P<auth>.+?)( - (?P<note>.+))?)|.*)))?$")
matchpat=re.compile(r"^(?P<url>[^,]+?)(,(?P<fullnote>(((?P<title>.+?) by (?P<auth>.+?)( - (?P<note>.+))?)|.*)))?$")
def __init__(self,url_or_line,note=None,title=None,auth=None,
addreasontext=None,fromline=False,book_id=None):
@@ -147,7 +151,7 @@ class RejectUrlEntry:
self.note=note
self.title=title
self.auth=auth
if not self.note:
if addreasontext:
self.note = addreasontext
@@ -156,14 +160,14 @@ class RejectUrlEntry:
else:
if addreasontext:
self.note = self.note + ' - ' + addreasontext
self.url = getNormalStoryURL(self.url)
self.valid = self.url != None
def to_line(self):
# always 'url,'
return self.url+","+self.fullnote()
def fullnote(self):
retval = ""
if self.title and self.auth:
@@ -171,10 +175,10 @@ class RejectUrlEntry:
retval = retval + "%s by %s"%(self.title,self.auth)
if self.note:
retval = retval + " - "
if self.note:
retval = retval + self.note
return retval
class NotGoingToDownload(Exception):
@@ -218,7 +222,7 @@ class DroppableQTextEdit(QTextEdit):
self.append("\n".join(urllist))
return None
return QTextEdit.dropEvent(self,event)
def canInsertFromMimeData(self, source):
if source.hasUrls():
return True
@@ -230,15 +234,15 @@ class DroppableQTextEdit(QTextEdit):
self.append(source.text())
else:
return QTextEdit.insertFromMimeData(self, source)
class AddNewDialog(SizePersistedDialog):
go_signal = pyqtSignal(object, object, object, object)
def __init__(self, gui, prefs, icon):
SizePersistedDialog.__init__(self, gui, 'FanFictionDownLoader plugin:add new dialog')
SizePersistedDialog.__init__(self, gui, 'fff:add new dialog')
self.prefs = prefs
self.setMinimumWidth(300)
self.l = QVBoxLayout()
self.setLayout(self.l)
@@ -254,7 +258,8 @@ class AddNewDialog(SizePersistedDialog):
self.l.addWidget(self.url)
self.merge = self.newmerge = False
self.extraoptions = {}
# elements to hide when doing merge.
self.mergehide = []
# elements to show again when doing *update* merge
@@ -277,11 +282,11 @@ class AddNewDialog(SizePersistedDialog):
self.gbf.setVisible(False)
self.groupbox.toggled.connect(self.gbf.setVisible)
horz = QHBoxLayout()
label = QLabel(_('Output &Format:'))
self.mergehide.append(label)
self.fileform = QComboBox(self)
self.fileform.addItem('epub')
self.fileform.addItem('mobi')
@@ -289,7 +294,7 @@ class AddNewDialog(SizePersistedDialog):
self.fileform.addItem('txt')
self.fileform.setToolTip(_('Choose output format to create. May set default from plugin configuration.'))
self.fileform.activated.connect(self.set_collisions)
horz.addWidget(label)
label.setBuddy(self.fileform)
horz.addWidget(self.fileform)
@@ -303,7 +308,7 @@ class AddNewDialog(SizePersistedDialog):
self.collision.setToolTip("CollisionToolTip")
# add collision options
self.set_collisions()
i = self.collision.findText(save_collisions[prefs['collision']])
i = self.collision.findText(save_collisions[self.prefs['collision']])
if i > -1:
self.collision.setCurrentIndex(i)
self.collisionlabel.setBuddy(self.collision)
@@ -317,17 +322,17 @@ class AddNewDialog(SizePersistedDialog):
horz = QHBoxLayout()
self.updatemeta = QCheckBox(_('Update Calibre &Metadata?'),self)
self.updatemeta.setToolTip(_("Update metadata for existing stories in Calibre from web site?\n(Columns set to 'New Only' in the column tabs will only be set for new books.)"))
self.updatemeta.setChecked(prefs['updatemeta'])
self.updatemeta.setChecked(self.prefs['updatemeta'])
horz.addWidget(self.updatemeta)
self.mergehide.append(self.updatemeta)
self.mergeupdateshow.append(self.updatemeta)
self.updateepubcover = QCheckBox(_('Update EPUB Cover?'),self)
self.updateepubcover.setToolTip(_('Update book cover image from site or defaults (if found) <i>inside</i> the EPUB when EPUB is updated.'))
self.updateepubcover.setChecked(prefs['updateepubcover'])
self.updateepubcover.setChecked(self.prefs['updateepubcover'])
horz.addWidget(self.updateepubcover)
self.mergehide.append(self.updateepubcover)
self.gbl.addLayout(horz)
self.button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
@@ -335,11 +340,11 @@ class AddNewDialog(SizePersistedDialog):
self.button_box.rejected.connect(self.reject)
self.l.addWidget(self.button_box)
# invoke the
# invoke the
def ok_clicked(self):
self.dialog_closing(None) # save persistent size.
self.hide()
self.go_signal.emit( self.get_ffdl_options(),
self.go_signal.emit( self.get_fff_options(),
self.get_urlstext(),
self.merge,
self.extrapayload )
@@ -352,9 +357,12 @@ class AddNewDialog(SizePersistedDialog):
newmerge=True,
extraoptions={},
extrapayload=None):
# rather than mutex in ffdl_plugin, just bail here if it's
# rather than mutex in fff_plugin, just bail here if it's
# already in use.
if self.isVisible(): return
if self.isVisible():
if url_list_text: # add to open box.
self.url.setText( '\n'.join([self.get_urlstext(), url_list_text]) )
return
try:
self.go_signal.disconnect()
@@ -368,9 +376,9 @@ class AddNewDialog(SizePersistedDialog):
self.extrapayload = extrapayload
self.groupbox.setVisible(not(self.merge and self.newmerge))
if self.merge:
self.toplabel.setText(_('Story URL(s) for anthology, one per line:'))
self.toplabel.setText(_('Story URLs for anthology, one per line:'))
self.url.setToolTip(_('URLs for stories to include in the anthology, one per line.\nWill take URLs from clipboard, but only valid URLs.'))
self.collisionlabel.setText(_('If Story Already Exists in Anthology?'))
self.collision.setToolTip(_("What to do if there's already an existing story with the same URL in the anthology."))
@@ -382,7 +390,7 @@ class AddNewDialog(SizePersistedDialog):
else:
for widget in self.mergehide:
widget.setVisible(True)
self.toplabel.setText(_('Story URL(s), one per line:'))
self.toplabel.setText(_('Story URLs, one per line:'))
self.url.setToolTip(_('URLs for stories, one per line.\nWill take URLs from clipboard, but only valid URLs.\nAdd [1,5] after the URL to limit the download to chapters 1-5.'))
self.collisionlabel.setText(_('If Story Already Exists?'))
self.collision.setToolTip(_("What to do if there's already an existing story with the same URL or title and author."))
@@ -390,7 +398,7 @@ class AddNewDialog(SizePersistedDialog):
# Need to re-able after hiding/showing
self.setAcceptDrops(True)
self.url.setFocus()
if self.prefs['adddialogstaysontop']:
QDialog.setWindowFlags ( self, Qt.Dialog | Qt.WindowStaysOnTopHint )
else:
@@ -398,24 +406,27 @@ class AddNewDialog(SizePersistedDialog):
if not self.merge:
self.fileform.setCurrentIndex(self.fileform.findText(self.prefs['fileform']))
else:
# always epub on self.merge (anthology)
self.fileform.setCurrentIndex(self.fileform.findText('epub'))
# add collision options
self.set_collisions()
i = self.collision.findText(save_collisions[self.prefs['collision']])
if i > -1:
self.collision.setCurrentIndex(i)
self.updatemeta.setChecked(self.prefs['updatemeta'])
if not self.merge:
self.updateepubcover.setChecked(self.prefs['updateepubcover'])
self.url.setText(url_list_text)
if url_list_text:
self.button_box.button(QDialogButtonBox.Ok).setFocus()
# restore saved size.
self.resize_dialog()
if show: # so anthology update can be modal still.
self.show()
#self.resize(self.sizeHint())
@@ -424,17 +435,24 @@ class AddNewDialog(SizePersistedDialog):
prev=self.collision.currentText()
self.collision.clear()
if self.merge:
order = anthology_collision_order
order = list(anthology_collision_order)
else:
order = collision_order
order = list(collision_order)
## Remove options that aren't valid.
if self.fileform.currentText() != 'epub':
order.remove(UPDATE)
order.remove(UPDATEALWAYS)
if self.prefs['savemetacol'] == '':
order.remove(CALIBREONLYSAVECOL)
for o in order:
if self.merge or self.fileform.currentText() == 'epub' or o not in [UPDATE,UPDATEALWAYS]:
self.collision.addItem(o)
self.collision.addItem(o)
i = self.collision.findText(prev)
if i > -1:
self.collision.setCurrentIndex(i)
def get_ffdl_options(self):
def get_fff_options(self):
retval = {
'fileform': unicode(self.fileform.currentText()),
'collision': unicode(self.collision.currentText()),
@@ -442,14 +460,14 @@ class AddNewDialog(SizePersistedDialog):
'updateepubcover': self.updateepubcover.isChecked(),
'smarten_punctuation':self.prefs['smarten_punctuation']
}
if self.merge:
retval['fileform']=='epub'
retval['updateepubcover']=True
if self.newmerge:
retval['updatemeta']=True
retval['collision']=ADDNEW
return dict(retval.items() + self.extraoptions.items() )
def get_urlstext(self):
@@ -459,46 +477,53 @@ class AddNewDialog(SizePersistedDialog):
class FakeLineEdit():
def __init__(self):
pass
def text(self):
pass
class CollectURLDialog(SizePersistedDialog):
'''
Collect single url for get urls.
'''
def __init__(self, gui, title, url_text, epubmerge_plugin=None):
SizePersistedDialog.__init__(self, gui, 'FanFictionDownLoader plugin:get story urls')
def __init__(self, gui, title, url_text, anthology=False, indiv=True):
SizePersistedDialog.__init__(self, gui, 'fff:get story urls')
self.status=False
self.anthology=False
self.setMinimumWidth(300)
self.l = QGridLayout()
self.l = QVBoxLayout()
self.setLayout(self.l)
self.setWindowTitle(title)
self.l.addWidget(QLabel(title),0,0,1,3)
self.l.addWidget(QLabel("URL:"),1,0)
self.l.addWidget(QLabel(title))
horz = QHBoxLayout()
self.l.addLayout(horz)
horz.addWidget(QLabel("URL:"))
self.url = QLineEdit(self)
self.url.setText(url_text)
self.l.addWidget(self.url,1,1,1,2)
self.indiv_button = QPushButton(_('For Individual Books'), self)
self.indiv_button.setToolTip(_('Get URLs and go to dialog for individual story downloads.'))
self.indiv_button.clicked.connect(self.indiv)
self.l.addWidget(self.indiv_button,2,0)
horz.addWidget(self.url)
self.merge_button = QPushButton(_('For Anthology Epub'), self)
self.merge_button.setToolTip(_('Get URLs and go to dialog for Anthology download.\nRequires %s plugin.')%'EpubMerge 1.3.1+')
self.merge_button.clicked.connect(self.merge)
self.l.addWidget(self.merge_button,2,1)
self.merge_button.setEnabled(epubmerge_plugin!=None)
horz = QHBoxLayout()
self.l.addLayout(horz)
if indiv:
self.indiv_button = QPushButton(_('For Individual Books'), self)
self.indiv_button.setToolTip(_('Get URLs and go to dialog for individual story downloads.'))
self.indiv_button.clicked.connect(self.indiv)
horz.addWidget(self.indiv_button)
if anthology:
self.merge_button = QPushButton(_('For Anthology Epub'), self)
self.merge_button.setToolTip(_('Get URLs and go to dialog for Anthology download.\nRequires %s plugin.')%'EpubMerge 1.3.1+')
self.merge_button.clicked.connect(self.merge)
horz.addWidget(self.merge_button)
self.cancel_button = QPushButton(_('Cancel'), self)
self.cancel_button.clicked.connect(self.cancel)
self.l.addWidget(self.cancel_button,2,2)
horz.addWidget(self.cancel_button)
# restore saved size.
self.resize_dialog()
@@ -536,16 +561,16 @@ class UserPassDialog(QDialog):
else:
self.setWindowTitle(_('User/Password'))
self.l.addWidget(QLabel(_("%s requires you to login to download this story.")%site),0,0,1,2)
self.l.addWidget(QLabel(_("User:")),1,0)
self.user = QLineEdit(self)
self.l.addWidget(self.user,1,1)
self.l.addWidget(QLabel(_("Password:")),2,0)
self.passwd = QLineEdit(self)
self.passwd.setEchoMode(QLineEdit.Password)
self.l.addWidget(self.passwd,2,1)
self.ok_button = QPushButton(_('OK'), self)
self.ok_button.clicked.connect(self.ok)
self.l.addWidget(self.ok_button,3,0)
@@ -591,6 +616,9 @@ class LoopProgressDialog(QProgressDialog):
from calibre_plugins.fanficfare_plugin.prefs import prefs
self.show_est_time = prefs['show_est_time']
self.setLabelText('%s %d / %d' % (self.status_prefix, self.i, len(self.book_list)))
self.setValue(self.i)
## self.do_loop does QTimer.singleShot on self.do_loop also.
## A weird way to do a loop, but that was the example I had.
QTimer.singleShot(0, self.do_loop)
@@ -614,10 +642,10 @@ class LoopProgressDialog(QProgressDialog):
book = self.book_list[self.i]
try:
## collision spec passed into getadapter by partial from ffdl_plugin
## collision spec passed into getadapter by partial from fff_plugin
## no retval only if it exists, but collision is SKIP
self.foreach_function(book)
except NotGoingToDownload as d:
book['good']=False
book['comment']=unicode(d)
@@ -628,10 +656,10 @@ class LoopProgressDialog(QProgressDialog):
book['comment']=unicode(e)
logger.error("Exception: %s:%s"%(book,unicode(e)))
traceback.print_exc()
self.updateStatus()
self.i += 1
if self.i >= len(self.book_list) or self.wasCanceled():
return self.do_when_finished()
else:
@@ -677,7 +705,7 @@ class AboutDialog(QDialog):
def __init__(self, parent, icon, text):
QDialog.__init__(self, parent)
self.resize(400, 250)
#self.resize(400, 250)
self.l = QGridLayout()
self.setLayout(self.l)
self.logo = QLabel()
@@ -716,13 +744,13 @@ class AuthorTableWidgetItem(ReadOnlyTableWidgetItem):
class UpdateExistingDialog(SizePersistedDialog):
def __init__(self, gui, header, prefs, icon, books,
save_size_name='fanfictiondownloader_plugin:update list dialog'):
save_size_name='fff:update list dialog'):
SizePersistedDialog.__init__(self, gui, save_size_name)
self.prefs = prefs
self.setWindowTitle(header)
self.setWindowIcon(icon)
layout = QVBoxLayout(self)
self.setLayout(layout)
title_layout = ImageTitleLayout(self, 'images/icon.png',
@@ -765,7 +793,7 @@ class UpdateExistingDialog(SizePersistedDialog):
gbf.setVisible(False)
groupbox.toggled.connect(gbf.setVisible)
label = QLabel(_('Output &Format:'))
gbl.addWidget(label)
self.fileform = QComboBox(self)
@@ -773,19 +801,19 @@ class UpdateExistingDialog(SizePersistedDialog):
self.fileform.addItem('mobi')
self.fileform.addItem('html')
self.fileform.addItem('txt')
self.fileform.setCurrentIndex(self.fileform.findText(prefs['fileform']))
self.fileform.setCurrentIndex(self.fileform.findText(self.prefs['fileform']))
self.fileform.setToolTip(_('Choose output format to create. May set default from plugin configuration.'))
self.fileform.activated.connect(self.set_collisions)
label.setBuddy(self.fileform)
gbl.addWidget(self.fileform)
label = QLabel(_('Update Mode:'))
gbl.addWidget(label)
self.collision = QComboBox(self)
self.collision.setToolTip(_("What sort of update to perform. May set default from plugin configuration."))
# add collision options
self.set_collisions()
i = self.collision.findText(save_collisions[prefs['collision']])
i = self.collision.findText(save_collisions[self.prefs['collision']])
if i > -1:
self.collision.setCurrentIndex(i)
label.setBuddy(self.collision)
@@ -793,23 +821,23 @@ class UpdateExistingDialog(SizePersistedDialog):
self.updatemeta = QCheckBox(_('Update Calibre &Metadata?'),self)
self.updatemeta.setToolTip(_("Update metadata for existing stories in Calibre from web site?\n(Columns set to 'New Only' in the column tabs will only be set for new books.)"))
self.updatemeta.setChecked(prefs['updatemeta'])
self.updatemeta.setChecked(self.prefs['updatemeta'])
gbl.addWidget(self.updatemeta)
self.updateepubcover = QCheckBox(_('Update EPUB Cover?'),self)
self.updateepubcover.setToolTip(_('Update book cover image from site or defaults (if found) <i>inside</i> the EPUB when EPUB is updated.'))
self.updateepubcover.setChecked(prefs['updateepubcover'])
self.updateepubcover.setChecked(self.prefs['updateepubcover'])
gbl.addWidget(self.updateepubcover)
button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
button_box.accepted.connect(self.accept)
button_box.rejected.connect(self.reject)
options_layout.addWidget(button_box)
layout.addLayout(options_layout)
# Cause our dialog size to be restored from prefs or created on first usage
self.resize_dialog()
self.books_table.populate_table(books)
@@ -817,21 +845,29 @@ class UpdateExistingDialog(SizePersistedDialog):
def set_collisions(self):
prev=self.collision.currentText()
self.collision.clear()
for o in collision_order:
if o not in [ADDNEW,SKIP] and \
(self.fileform.currentText() == 'epub' or o not in [UPDATE,UPDATEALWAYS]):
self.collision.addItem(o)
order = list(collision_order)
order.remove(ADDNEW)
order.remove(SKIP)
if self.fileform.currentText() != 'epub':
order.remove(UPDATE)
order.remove(UPDATEALWAYS)
if self.prefs['savemetacol'] == '':
order.remove(CALIBREONLYSAVECOL)
for o in order:
self.collision.addItem(o)
i = self.collision.findText(prev)
if i > -1:
self.collision.setCurrentIndex(i)
def remove_from_list(self):
self.books_table.remove_selected_rows()
def get_books(self):
return self.books_table.get_books()
def get_ffdl_options(self):
def get_fff_options(self):
return {
'fileform': unicode(self.fileform.currentText()),
'collision': unicode(self.collision.currentText()),
@@ -891,16 +927,16 @@ class StoryListTableWidget(QTableWidget):
status_cell = IconWidgetItem(None,icon,val)
status_cell.setData(Qt.UserRole, val)
self.setItem(row, 0, status_cell)
title_cell = ReadOnlyTableWidgetItem(book['title'])
title_cell.setData(Qt.UserRole, row)
self.setItem(row, 1, title_cell)
self.setItem(row, 2, AuthorTableWidgetItem(", ".join(book['author']), ", ".join(book['author_sort'])))
url_cell = ReadOnlyTableWidgetItem(book['url'])
self.setItem(row, 3, url_cell)
comment_cell = ReadOnlyTableWidgetItem(book['comment'])
self.setItem(row, 4, comment_cell)
@@ -921,7 +957,7 @@ class StoryListTableWidget(QTableWidget):
message = '<p>'+_('Are you sure you want to remove this book from the list?')
if len(rows) > 1:
message = '<p>'+_('Are you sure you want to remove the selected %d books from the list?')%len(rows)
if not confirm(message,'fanfictiondownloader_delete_item', self):
if not confirm(message,'fff_delete_item', self):
return
first_sel_row = self.currentRow()
for selrow in reversed(rows):
@@ -978,16 +1014,17 @@ class RejectListTableWidget(QTableWidget):
self.setItem(row, 0, url_cell)
self.setItem(row, 1, ReadOnlyTableWidgetItem(rej.title))
self.setItem(row, 2, ReadOnlyTableWidgetItem(rej.auth))
note_cell = EditWithComplete(self,sort_func=lambda x:1)
items = [rej.note]+self.rejectreasons
note_cell.update_items_cache(items)
note_cell.show_initial_value(rej.note)
note_cell.set_separator(None)
note_cell.setToolTip(_('Select or Edit Reject Note.'))
self.setCellWidget(row, 3, note_cell)
note_cell.setCursorPosition(0)
def remove_selected_rows(self):
self.setFocus()
rows = self.selectionModel().selectedRows()
@@ -996,7 +1033,7 @@ class RejectListTableWidget(QTableWidget):
message = '<p>'+_('Are you sure you want to remove this URL from the list?')
if len(rows) > 1:
message = '<p>'+_('Are you sure you want to remove the %d selected URLs from the list?')%len(rows)
if not confirm(message,'ffdl_rejectlist_delete_item_again', self):
if not confirm(message,'fff_rejectlist_delete_item_again', self):
return
first_sel_row = self.currentRow()
for selrow in reversed(rows):
@@ -1017,12 +1054,12 @@ class RejectListDialog(SizePersistedDialog):
icon='rotate-right.png',
show_delete=True,
show_all_reasons=True,
save_size_name='ffdl:reject list dialog'):
save_size_name='fff:reject list dialog'):
SizePersistedDialog.__init__(self, gui, save_size_name)
self.setWindowTitle(header)
self.setWindowIcon(get_icon(icon))
layout = QVBoxLayout(self)
self.setLayout(layout)
title_layout = ImageTitleLayout(self, icon, header,
@@ -1038,9 +1075,9 @@ class RejectListDialog(SizePersistedDialog):
rejects_layout.addLayout(button_layout)
spacerItem = QtGui.QSpacerItem(20, 40, QtGui.QSizePolicy.Minimum, QtGui.QSizePolicy.Expanding)
button_layout.addItem(spacerItem)
self.remove_button = QtGui.QToolButton(self)
self.remove_button.setToolTip(_('Remove selected URL(s) from the list'))
self.remove_button.setToolTip(_('Remove selected URLs from the list'))
self.remove_button.setIcon(get_icon('list_remove.png'))
self.remove_button.clicked.connect(self.remove_from_list)
button_layout.addWidget(self.remove_button)
@@ -1050,21 +1087,22 @@ class RejectListDialog(SizePersistedDialog):
if show_all_reasons:
self.reason_edit = EditWithComplete(self,sort_func=lambda x:1)
items = ['']+rejectreasons
self.reason_edit.update_items_cache(items)
self.reason_edit.show_initial_value('')
self.reason_edit.set_separator(None)
self.reason_edit.setToolTip(_("This will be added to whatever note you've set for each URL above."))
horz = QHBoxLayout()
label = QLabel(_("Add this reason to all URLs added:"))
label.setToolTip(_("This will be added to whatever note you've set for each URL above."))
horz.addWidget(label)
horz.addWidget(self.reason_edit)
self.reason_edit.setCursorPosition(0)
horz.insertStretch(-1)
layout.addLayout(horz)
options_layout = QHBoxLayout()
if show_delete:
@@ -1072,14 +1110,14 @@ class RejectListDialog(SizePersistedDialog):
self.deletebooks.setToolTip(_("Delete the selected books after adding them to the Rejected URLs list."))
self.deletebooks.setChecked(True)
options_layout.addWidget(self.deletebooks)
button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
button_box.accepted.connect(self.accept)
button_box.rejected.connect(self.reject)
options_layout.addWidget(button_box)
layout.addLayout(options_layout)
# Cause our dialog size to be restored from prefs or created on first usage
self.resize_dialog()
self.rejects_table.populate_table(reject_list)
@@ -1112,7 +1150,7 @@ class RejectListDialog(SizePersistedDialog):
except:
# doesn't have self.reason_edit when editing existing list.
return None
def get_deletebooks(self):
return self.deletebooks.isChecked()
@@ -1120,8 +1158,9 @@ class EditTextDialog(SizePersistedDialog):
def __init__(self, parent, text,
icon=None, title=None, label=None, tooltip=None,
read_only=False,
rejectreasons=[],reasonslabel=None,
save_size_name='ffdl:edit text dialog',
save_size_name='fff:edit text dialog',
):
SizePersistedDialog.__init__(self, parent, save_size_name)
@@ -1133,9 +1172,10 @@ class EditTextDialog(SizePersistedDialog):
if icon:
self.setWindowIcon(icon)
self.l.addWidget(self.label)
self.textedit = QTextEdit(self)
self.textedit.setLineWrapMode(QTextEdit.NoWrap)
self.textedit.setReadOnly(read_only)
self.textedit.setText(text)
self.l.addWidget(self.textedit)
@@ -1145,13 +1185,13 @@ class EditTextDialog(SizePersistedDialog):
if rejectreasons or reasonslabel:
self.reason_edit = EditWithComplete(self,sort_func=lambda x:1)
items = ['']+rejectreasons
self.reason_edit.update_items_cache(items)
self.reason_edit.show_initial_value('')
self.reason_edit.set_separator(None)
self.reason_edit.setToolTip(reasonslabel)
if reasonslabel:
horz = QHBoxLayout()
label = QLabel(reasonslabel)
@@ -1161,12 +1201,13 @@ class EditTextDialog(SizePersistedDialog):
self.l.addLayout(horz)
else:
self.l.addWidget(self.reason_edit)
self.reason_edit.setCursorPosition(0)
button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
button_box.accepted.connect(self.accept)
button_box.rejected.connect(self.reject)
self.l.addWidget(button_box)
# Cause our dialog size to be restored from prefs or created on first usage
self.resize_dialog()
@@ -1175,19 +1216,19 @@ class EditTextDialog(SizePersistedDialog):
def get_reason_text(self):
return unicode(self.reason_edit.currentText()).strip()
class IniTextDialog(SizePersistedDialog):
def __init__(self, parent, text,
icon=None, title=None, label=None,
use_find=False,
read_only=False,
save_size_name='ffdl:ini text dialog',
save_size_name='fff:ini text dialog',
):
SizePersistedDialog.__init__(self, parent, save_size_name)
self.keys=dict()
self.l = QVBoxLayout()
self.setLayout(self.l)
self.label = QLabel(label)
@@ -1196,7 +1237,7 @@ class IniTextDialog(SizePersistedDialog):
if icon:
self.setWindowIcon(icon)
self.l.addWidget(self.label)
self.textedit = QTextEdit(self)
highlighter = IniHighlighter(self.textedit,
@@ -1205,7 +1246,7 @@ class IniTextDialog(SizePersistedDialog):
entries=get_valid_entries(),
entry_keywords=get_valid_entry_keywords(),
)
self.textedit.setLineWrapMode(QTextEdit.NoWrap)
try:
self.textedit.setFont(QFont("Courier",
@@ -1223,46 +1264,46 @@ class IniTextDialog(SizePersistedDialog):
if use_find:
findtooltip=_('Search for string in edit box.')
horz = QHBoxLayout()
label = QLabel(_('Find:'))
label.setToolTip(findtooltip)
# Button to search the document for something
self.findButton = QtGui.QPushButton(_('Find'),self)
self.findButton.clicked.connect(self.find)
self.findButton.setToolTip(findtooltip)
# The field into which to type the query
self.findField = QLineEdit(self)
self.findField.setToolTip(findtooltip)
self.findField.returnPressed.connect(self.findButton.setFocus)
# Case Sensitivity option
self.caseSens = QtGui.QCheckBox(_('Case sensitive'),self)
self.caseSens.setToolTip(_("Search for case sensitive string; don't treat Harry, HARRY and harry all the same."))
horz.addWidget(label)
horz.addWidget(self.findField)
horz.addWidget(self.findButton)
horz.addWidget(self.caseSens)
self.l.addLayout(horz)
self.addCtrlKeyPress(QtCore.Qt.Key_F,self.findFocus)
self.addCtrlKeyPress(QtCore.Qt.Key_G,self.find)
button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
button_box.accepted.connect(self.accept)
button_box.rejected.connect(self.reject)
self.l.addWidget(button_box)
# Cause our dialog size to be restored from prefs or created on first usage
self.resize_dialog()
def accept(self):
from ffdl_util import test_config
from fff_util import test_config
# print("in accept")
errors = test_config(self.get_plain_text())
@@ -1273,9 +1314,9 @@ class IniTextDialog(SizePersistedDialog):
_('Go back to fix errors?'),
errors)
retry = d.exec_() == d.Accepted
# print("retry:%s"%retry)
if retry:
lineno=d.get_lineno()
if lineno:
@@ -1297,19 +1338,19 @@ class IniTextDialog(SizePersistedDialog):
return func()
else:
return SizePersistedDialog.keyPressEvent(self, event)
def get_plain_text(self):
return unicode(self.textedit.toPlainText())
def findFocus(self):
# print("findFocus called")
self.findField.setFocus()
self.findField.selectAll()
self.findField.selectAll()
def find(self):
#print("find self.lastStart:%s"%self.lastStart)
# Grab the parent's text
text = self.textedit.toPlainText()
@@ -1324,7 +1365,7 @@ class IniTextDialog(SizePersistedDialog):
# last starting position
self.lastStart = text.find(query,self.lastStart + 1)
# If the find() method didn't return -1 (not found)
if self.lastStart >= 0:
end = self.lastStart + len(query)
self.moveCursor(self.lastStart,end)
@@ -1332,7 +1373,7 @@ class IniTextDialog(SizePersistedDialog):
# Make the next search start from the begining again
self.lastStart = 0
self.textedit.moveCursor(self.textedit.textCursor().Start)
def moveCursor(self,start,end):
# We retrieve the QTextCursor object from the parent's QTextEdit
@@ -1349,7 +1390,7 @@ class IniTextDialog(SizePersistedDialog):
self.textedit.setTextCursor(cursor)
def select_line(self,lineno):
# We retrieve the QTextCursor object from the parent's QTextEdit
cursor = self.textedit.textCursor()
@@ -1375,9 +1416,9 @@ class ViewLog(SizePersistedDialog):
def get_lineno(self):
return self.lineno
def __init__(self, parent, title, errors,
save_size_name='ffdl:view log dialog',):
def __init__(self, parent, title, errors,
save_size_name='fff:view log dialog',):
SizePersistedDialog.__init__(self, parent,save_size_name)
self.l = l = QVBoxLayout()
self.setLayout(l)
@@ -1397,9 +1438,9 @@ class ViewLog(SizePersistedDialog):
label.setToolTip(_('Click to go to line %s')%lineno)
label.mouseReleaseEvent = partial(self.label_clicked, lineno=lineno)
self.l.addWidget(label)
# html='<p>'+'</p><p>'.join([ '(lineno: %s) %s'%e for e in errors ])+'</p>'
# self.tb = QTextBrowser(self)
# self.tb.setFont(QFont("Courier",
# parent.font().pointSize()+1))
@@ -1417,13 +1458,13 @@ class ViewLog(SizePersistedDialog):
saveanyway = QPushButton(_('Save Anyway'), self)
saveanyway.clicked.connect(self.reject)
horz.addWidget(saveanyway)
l.addLayout(horz)
self.setModal(False)
self.setWindowTitle(title)
self.setWindowIcon(QIcon(I('debug.png')))
#self.show()
# Cause our dialog size to be restored from prefs or created on first usage
self.resize_dialog()
@@ -1444,7 +1485,7 @@ class EmailPassDialog(QDialog):
self.setWindowTitle(_('Password'))
self.l.addWidget(QLabel(_("Enter Email Password for %s:")%user),0,0,1,2)
# self.l.addWidget(QLabel(_("Password:")),1,0)
self.passwd = QLineEdit(self)
self.passwd.setEchoMode(QLineEdit.Password)
File diff suppressed because it is too large Load Diff
@@ -1,10 +1,10 @@
#!/usr/bin/env python
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
# -*- coding: utf-8 -*-
from __future__ import (unicode_literals, division, absolute_import,
print_function)
__license__ = 'GPL v3'
__copyright__ = '2013, Jim Miller'
__copyright__ = '2015, Jim Miller'
__docformat__ = 'restructuredtext en'
from StringIO import StringIO
@@ -17,37 +17,29 @@ from calibre_plugins.fanficfare_plugin.fanficfare import adapters, exceptions
from calibre_plugins.fanficfare_plugin.fanficfare.configurable import Configuration
from calibre_plugins.fanficfare_plugin.prefs import prefs
def get_ffdl_personalini():
if prefs['includeimages']:
# this is a cheat to make it easier for users.
return '''[epub]
include_images:true
keep_summary_html:true
make_firstimage_cover:true
''' + prefs['personal.ini']
else:
return prefs['personal.ini']
def get_fff_personalini():
return prefs['personal.ini']
def get_ffdl_config(url,fileform="epub",personalini=None):
def get_fff_config(url,fileform="epub",personalini=None):
if not personalini:
personalini = get_ffdl_personalini()
site='unknown'
personalini = get_fff_personalini()
sections=['unknown']
try:
site = adapters.getConfigSectionFor(url)
sections = adapters.getConfigSectionsFor(url)
except Exception as e:
logger.debug("Failed trying to get ini config for url(%s): %s, using section [%s] instead"%(url,e,site))
configuration = Configuration(site,fileform)
logger.debug("Failed trying to get ini config for url(%s): %s, using section %s instead"%(url,e,sections))
configuration = Configuration(sections,fileform)
configuration.readfp(StringIO(get_resources("plugin-defaults.ini")))
configuration.readfp(StringIO(personalini))
return configuration
def get_ffdl_adapter(url,fileform="epub",personalini=None):
return adapters.getAdapter(get_ffdl_config(url,fileform,personalini),url)
def get_fff_adapter(url,fileform="epub",personalini=None):
return adapters.getAdapter(get_fff_config(url,fileform,personalini),url)
def test_config(initext):
try:
configini = get_ffdl_config("test1.com?sid=555",
configini = get_fff_config("test1.com?sid=555",
personalini=initext)
errors = configini.test_config()
except ParsingError as pe:
Binary file not shown.

Before

Width:  |  Height:  |  Size: 22 KiB

After

Width:  |  Height:  |  Size: 23 KiB

Binary file not shown.
+3 -3
View File
@@ -1,10 +1,10 @@
#!/usr/bin/env python
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
# -*- coding: utf-8 -*-
from __future__ import (unicode_literals, division,
print_function)
__license__ = 'GPL v3'
__copyright__ = '2014, Jim Miller'
__copyright__ = '2015, Jim Miller'
__docformat__ = 'restructuredtext en'
import re
+52 -24
View File
@@ -1,17 +1,17 @@
#!/usr/bin/env python
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
# -*- coding: utf-8 -*-
from __future__ import (unicode_literals, division, absolute_import,
print_function)
__license__ = 'GPL v3'
__copyright__ = '2015, Jim Miller'
__copyright__ = '2011, Grant Drake <grant.drake@gmail.com>'
__copyright__ = '2015, Jim Miller, 2011, Grant Drake <grant.drake@gmail.com>'
__docformat__ = 'restructuredtext en'
import logging
logger = logging.getLogger(__name__)
import time, traceback
from StringIO import StringIO
from calibre.utils.ipc.server import Server
from calibre.utils.ipc.job import ParallelJob
@@ -96,26 +96,26 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
'''
from calibre_plugins.fanficfare_plugin import FanFicFareBase
ffdlbase = FanFicFareBase(options['plugin_path'])
with ffdlbase:
fffbase = FanFicFareBase(options['plugin_path'])
with fffbase:
from calibre_plugins.fanficfare_plugin.dialogs import (NotGoingToDownload,
OVERWRITE, OVERWRITEALWAYS, UPDATE, UPDATEALWAYS, ADDNEW, SKIP, CALIBREONLY)
OVERWRITE, OVERWRITEALWAYS, UPDATE, UPDATEALWAYS, ADDNEW, SKIP, CALIBREONLY, CALIBREONLYSAVECOL)
from calibre_plugins.fanficfare_plugin.fanficfare import adapters, writers, exceptions
from calibre_plugins.fanficfare_plugin.fanficfare.epubutils import get_update_data
from calibre_plugins.fanficfare_plugin.ffdl_util import (get_ffdl_adapter, get_ffdl_config)
from calibre_plugins.fanficfare_plugin.fff_util import (get_fff_adapter, get_fff_config)
try:
book['comment'] = _('Download started...')
configuration = get_ffdl_config(book['url'],
configuration = get_fff_config(book['url'],
options['fileform'],
options['personal.ini'])
if configuration.getConfig('use_ssl_unverified_context'):
## monkey patch to avoid SSL bug. dupliated from
## ffdl_plugin.py because bg jobs run in own process
## fff_plugin.py because bg jobs run in own process
## space.
import ssl
if hasattr(ssl, '_create_unverified_context'):
@@ -152,9 +152,12 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
outfile = book['outfile']
## No need to download at all. Shouldn't ever get down here.
if options['collision'] in (CALIBREONLY):
if options['collision'] in (CALIBREONLY, CALIBREONLYSAVECOL):
logger.info("Skipping CALIBREONLY 'update' down inside worker--this shouldn't be happening...")
book['comment'] = 'Metadata collected.'
book['all_metadata'] = story.getAllMetadata(removeallentities=True)
if options['savemetacol'] != '':
book['savemetacol'] = story.dump_html_metadata()
## checks were done earlier, it's new or not dup or newer--just write it.
elif options['collision'] in (ADDNEW, SKIP, OVERWRITE, OVERWRITEALWAYS) or \
@@ -162,23 +165,20 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
# preserve logfile even on overwrite.
if 'epub_for_update' in book:
(urlignore,
chaptercountignore,
oldchaptersignore,
oldimgsignore,
oldcoverignore,
calibrebookmarkignore,
# only logfile set in adapter, so others aren't used.
adapter.logfile) = get_update_data(book['epub_for_update'])
adapter.logfile = get_update_data(book['epub_for_update'])[6]
# change the existing entries id to notid so
# write_epub writes a whole new set to indicate overwrite.
if adapter.logfile:
adapter.logfile = adapter.logfile.replace("span id","span notid")
logger.info("write to %s"%outfile)
inject_cal_cols(book,story,configuration)
writer.writeStory(outfilename=outfile, forceOverwrite=True)
book['comment'] = 'Download %s completed, %s chapters.'%(options['fileform'],story.getMetadata("numChapters"))
book['all_metadata'] = story.getAllMetadata(removeallentities=True)
if options['savemetacol'] != '':
book['savemetacol'] = story.dump_html_metadata()
## checks were done earlier, just update it.
elif 'epub_for_update' in book and options['collision'] in (UPDATE, UPDATEALWAYS):
@@ -192,16 +192,21 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
adapter.oldimgs,
adapter.oldcover,
adapter.calibrebookmark,
adapter.logfile) = get_update_data(book['epub_for_update'])
adapter.logfile,
adapter.oldchaptersmap,
adapter.oldchaptersdata) = get_update_data(book['epub_for_update'])[0:9]
# dup handling from ffdl_plugin needed for anthology updates.
# dup handling from fff_plugin needed for anthology updates.
if options['collision'] == UPDATE:
if chaptercount == urlchaptercount:
book['comment']=_("Already contains %d chapters. Reuse as is.")%chaptercount
book['all_metadata'] = story.getAllMetadata(removeallentities=True)
if options['savemetacol'] != '':
book['savemetacol'] = story.dump_html_metadata()
book['outfile'] = book['epub_for_update'] # for anthology merge ops.
return book
# dup handling from ffdl_plugin needed for anthology updates.
# dup handling from fff_plugin needed for anthology updates.
if chaptercount > urlchaptercount:
raise NotGoingToDownload(_("Existing epub contains %d chapters, web site only has %d. Use Overwrite to force update.") % (chaptercount,urlchaptercount),'dialog_error.png')
@@ -212,11 +217,15 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
logger.info("Do update - epub(%d) vs url(%d)" % (chaptercount, urlchaptercount))
logger.info("write to %s"%outfile)
inject_cal_cols(book,story,configuration)
writer.writeStory(outfilename=outfile, forceOverwrite=True)
book['comment'] = _('Update %s completed, added %s chapters for %s total.')%\
(options['fileform'],(urlchaptercount-chaptercount),urlchaptercount)
book['all_metadata'] = story.getAllMetadata(removeallentities=True)
if options['savemetacol'] != '':
book['savemetacol'] = story.dump_html_metadata()
if options['smarten_punctuation'] and options['fileform'] == "epub" \
and calibre_version >= (0, 9, 39):
# for smarten punc
@@ -250,3 +259,22 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
#time.sleep(10)
return book
## calibre's columns for an existing book are pased in and injected
## into the story's metadata. For convenience, we also add labels and
## valid_entries for them in a special [injected] section that has
## even less precedence than [defaults]
def inject_cal_cols(book,story,configuration):
configuration.remove_section('injected')
if 'calibre_columns' in book:
injectini = ['[injected]']
extra_valid = []
for k, v in book['calibre_columns'].iteritems():
story.setMetadata(k,v['val'])
injectini.append('%s_label:%s'%(k,v['label']))
extra_valid.append(k)
if extra_valid: # if empty, there's nothing to add.
injectini.append("add_to_extra_valid_entries:,"+','.join(extra_valid))
configuration.readfp(StringIO('\n'.join(injectini)))
#print("added:\n%s\n"%('\n'.join(injectini)))
+260 -109
View File
@@ -1,4 +1,4 @@
# Copyright 2013 Fanficdownloader team
# Copyright 2015 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -85,9 +85,9 @@ authorId_label:Author ID
## show up in Calibre as tags. Also carried into mobi when converted.
extratags_label:Extra Tags
## The version of fanficdownloader
version_label:FFDL Version
version_label:Downloader Version
## Date formats used by FFDL. Published and Update don't have time.
## Date formats used by FanFicFare. Published and Update don't have time.
## See http://docs.python.org/library/datetime.html#strftime-strptime-behavior
## Note that ini format requires % to be escaped as %%.
dateCreated_format:%%Y-%%m-%%d %%H:%%M:%%S
@@ -172,7 +172,7 @@ connect_timeout:60.0
## Note that if metakey == conditionalkey the conditional is ignored.
## You can use \s in the replacement to add explicit spaces. (The config parser
## tends to discard trailing spaces.)
## replace_metadata <entry>_LIST options: FFDL replace_metadata lines
## replace_metadata <entry>_LIST options: FanFicFare replace_metadata lines
## operate on individual list items for list entries. But if you
## want to do a replacement on the joined string for the whole list,
## you can by using <entry>_LIST. Example, if you added
@@ -232,12 +232,21 @@ connect_timeout:60.0
## Make sure to keep at least one space at the start of each line and
## to escape % to %%, if used.
## template => regexp to match => GC Setting to use.
## To use this, make sure you go to the Generate Cover tab in FFDL
## To use this, make sure you go to the Generate Cover tab in FanFicFare
## config and check 'Allow generate_cover_settings from personal.ini
## to override'
## You can check for an existing cover image in the metadata
## cover_image. cover_image can be:
## specific -- The site has an image that is specifically this story's cover
## first -- The first image in the story or story desc is used as cover
## default -- A default_cover_image was used
## old -- There was already a cover image in the epub.
## This is useful because GC plugin can use the existing image.
#generate_cover_settings:
# ${category} => Buffy:? [tT]he Vampire Slayer => BuffyCover
# ${category} => Star Trek => StarTrekCover
# ${cover_image} => => CompleteCover
# ${cover_image} => (specific|first|default) => CoverWithOrigImage
## If set false, the summary will have all html stripped.
## Both this and include_images must be true to get images in the
@@ -252,6 +261,11 @@ keep_summary_html:true
## kept. Some sites(AO3) use <a title="Translation">Foreign language</a>
#keep_title_attr: false
## If a chapter range was given, use this pattern for the book title.
## replace_metadata and include/exclude will be applied *after* this.
## Set to empty value to disable.
title_chapter_range_pattern:${title} (Ch ${first}-${last})
## Don't like the numbers at the start of chapter titles on some
## sites? You can use strip_chapter_numbers to strip them off. Just
## want to make them all look the same? Strip them off, then add them
@@ -284,12 +298,31 @@ chapter_title_strip_pattern:^[0-9]+[\.: -]+
## etc
#chapter_title_strip_pattern:^([0-9]+[\.: -]+)?(Chapter *[0-9]+[\.:, -]*)?
## Uses a python template substitution. The ${index} is the 'chapter'
## number and ${title} is the chapter title, after applying
## chapter_title_strip_pattern. Those are the only variables available.
## "The Beginning" => "1. The Beginning"
## If true, when updating an epub that already has old chapters, new
## chapters will be marked in the TOC and chapter header by using
## chapter_title_new_pattern and chapter_title_addnew_pattern to set the chapter.
mark_new_chapters:false
## chapter title patterns use python template substitution. The
## ${index} is the 'chapter' number and ${title} is the chapter title,
## after applying chapter_title_strip_pattern. Those are the only
## variables available.
## The basic pattern used when not using add_chapter_numbers or
## mark_new_chapters
chapter_title_def_pattern:${title}
## Pattern used with add_chapter_numbers, but not mark_new_chapters
chapter_title_add_pattern:${index}. ${title}
## Pattern used with mark_new_chapters, but not add_chapter_numbers
## (new) is just text and can be changed.
chapter_title_new_pattern:(new) ${title}
## Pattern used with add_chapter_numbers and mark_new_chapters
## (new) is just text and can be changed.
chapter_title_addnew_pattern:${index}. (new) ${title}
## Uses a python template substitution. The ${title} is the default
## title of a new anthology, <series name> in the case of a series, or
## the first book title otherwise. This is only applied to new
@@ -306,20 +339,91 @@ anthology_tags:Anthology
## ships_LIST to change the / back to something else if you want.
sort_ships:false
## join_string_<entry> options -- FFDL list entries are comma
## join_string_<entry> options -- FanFicFare list entries are comma
## separated by default. You can use this to change that. For example,
## if you want authors separated with ' & ' instead, use
## join_string_calibre_author:\s&\s. (\s == space)
#join_string_author:,\s
## keep_in_order_<entry> options: FFDL sorts list entries by default
## keep_in_order_<entry> options: FanFicFare sorts list entries by default
## (except for author/authorUrl/authorId). But if you want to use an
## extra entry derived from author, it ends up sorted. For example, if
## you added calibre_author: keep_in_order_calibre_author:true
#keep_in_order_author:true
## User-agent
user_agent:FFDL/2.0
user_agent:FFF/2.X
## Added for [base_xenforoforum], but can be used with other sites,
## too. Limit the 'description' to the first X *characters*
## collected. Character count includes HTML tags, so it can be
## non-intuitive.
#description_limit:1000
[base_efiction]
## At the time of writing, eFiction Base adapters allow downloading
## the whole story in bulk using the 'Print' feature. If 'bulk_load'
## is set to 'true', both metadata and chapters can be loaded in one
## step
bulk_load:true
[base_xenforoforum]
## Currently only forums.spacebattles.com and forums.sufficientvelocity.com
cover_exclusion_regexp:/clear.png
## I saw lots of chapters name simply '1.1' etc during testing.
strip_chapter_numbers:false
## Copy title to tagsfromtitle for parsing tags.
add_to_extra_valid_entries:,tagsfromtitle,forumtags
## '.NOREPL' tells the system to *not* apply title's
## in/exclude/replace_metadata -- Only works on include_in_ lines.
include_in_tagsfromtitle:title.NOREPL
tagsfromtitle_label:Tags from Title
forumtags_label:Tags from Forum
## might want to do this, maybe not. Will often include category, but
## also often include non-category stuff.
# include_in_category:tagsfromtitle
add_to_include_metadata_pre:
# only keep tagsfromtitle with ( or [ in.
tagsfromtitle=~[\[\(]
add_to_replace_metadata:
# remove anything outside () or []
tagsfromtitle=>^.*?([\(\[]([^\]\)]+)[\)\]]).*?$=>\1
# remove () []
tagsfromtitle=>[\(\)\[\]]=>
# change (spaces)slash(or semicolon)(spaces) to comma
tagsfromtitle=> *[/;] *=>,
tagsfromtitle=> [xX] =>,
# remove [] or () blocks and leading/trailing spaces/dashes/colons
title=>[-: ]*[\(\[]([^\]\)]+)[\)\]][-: ]*=>
# remove 'Thread' and the next word, usually "Thread 2", "Thread
# four", "Thread iv", etc
title,tagsfromtitle=>[-: ]*[Tt]hread [^ ]+[-: ]*=>
add_to_extra_titlepage_entries:,tagsfromtitle,forumtags
## '.SPLIT' tells the system to split by ','
add_to_include_subject_tags:,tagsfromtitle.SPLIT
## Or to also include forumtags add this to personal.ini:
#add_to_include_subject_tags:,forumtags
## base_xenforoforum reads Published and Updated datetimes from
## Threadmarks if used, or from the posted & updated times of the
## 'first' post if no threadmarks.
datePublished_format:%%Y-%%m-%%d %%H:%%M:%%S
dateUpdated_format:%%Y-%%m-%%d %%H:%%M:%%S
## Only take the first X characters of the 'first' post to use as
## the description.
description_limit:500
## Each output format has a section that overrides [defaults]
[html]
@@ -330,7 +434,7 @@ user_agent:FFDL/2.0
## include_images is *not* available in the web service in any format.
#include_images:false
## This switch prevents FFDL from doing any processing on the images.
## This switch prevents FanFicFare from doing any processing on the images.
## Usually they would be converted to jpg, resized and optionally made
## grayscale.
no_image_processing: true
@@ -442,12 +546,12 @@ output_css:
## include images from img tags in the body and summary of
## stories. Images will be converted to jpg for size if possible.
## include_images is *only* available in epub and html output format.
#include_images:false
include_images:true
## If set, the first image found will be made the cover image. If
## keep_summary_html is true, any images in summary will be before any
## in chapters.
#make_firstimage_cover: false
make_firstimage_cover: true
## If set, the epub will never have a cover, even include_images is on
## and the site has specific cover images.
@@ -479,6 +583,22 @@ image_max_size: 580, 725
## space.
#grayscale_images: false
## jpg or png
## -- jpg produces smaller images, and may be supported by more
## readers, but it's older and doesn't allow transparency.
## Transparency removed as if remove_transparency: true
## -- png is newer but does allow transparency, but only in CLI.
## It doesn't work in calibre PI due to limitations of the API.
convert_images_to: jpg
## Remove transparency and fill with background_color if true.
remove_transparency: true
## This switch prevents FanFicFare from doing any processing on the images.
## Usually they would be converted to jpg, resized and optionally made
## grayscale.
#no_image_processing: false
## if the <img> tag doesn't have a div or a p around it, nook gets
## confused and displays it on every page after that under the text
## for the rest of the chapter. I doubt adding a div around the img
@@ -549,10 +669,12 @@ extratags: FanFiction,Testing,HTML
#is_adult:true
## archiveofourown.org stories allow chapters to be added out of
## order. So the newest chapter may not be the last one. FFDL update
## order. So the newest chapter may not be the last one. FanFicFare update
## doesn't like that. If do_update_hook is uncommented and set true,
## the adapter will discard all existing chapters from the newest one
## on when updating to enforce accurate chapters.
## Starting July 2015, FFF stores chapter URLs in the chapter files.
## Stories downloaded after that shouldn't need this setting anymore.
#do_update_hook:false
## AO3 adapter defines a few extra metadata entries.
@@ -568,6 +690,18 @@ hits_label:Hits
collections_label:Collections
bookmarks_label:Bookmarks
## AO3 doesn't have anything it calls 'genre'. The adapter used to be
## hardcoded to include the site specific metadata freeformtags &
## ao3categories in the standard metadata field genre. By making it
## configurable, users can change it.
include_in_genre: freeformtags, ao3categories
## AO3 uses the word 'category' differently than most sites. The
## adapter used to be hardcoded to include the site specific metadata
## fandom in the standard metadata field category. By making it
## configurable, users can change it.
include_in_category:fandoms
## freeformtags was previously typo'ed as freefromtags. This way,
## freefromtags will still work for people who've used it.
include_in_freefromtags:freeformtags
@@ -579,7 +713,7 @@ include_in_freefromtags:freeformtags
#extra_subject_tags:fandoms,freeformtags,ao3categories
## AO3 chapters can include several different types of notes. We've
## traditional included them all in the chapter text, but this allows
## traditionally included them all in the chapter text, but this allows
## you to customize which you include. Copy this parameter to your
## personal.ini and list the ones you don't want.
#exclude_notes:authorheadnotes,chaptersummary,chapterheadnotes,chapterfootnotes,authorfootnotes
@@ -729,11 +863,6 @@ extraships:Spike/Buffy
## this should go in your personal.ini, not defaults.ini.
#is_adult:true
## Virtually all eFiction-based sites allow downloading the whole story in
## bulk using the 'Print' feature. If 'bulk_load' is set to 'true', both
## metadata and chapters can be loaded in one step
bulk_load:true
[dramione.org]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
@@ -758,7 +887,7 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
## Some adapters collect additional meta information beyond the
## standard ones. They need to be defined in extra_valid_entries to
## tell the rest of the FFDL system about them. They can be used in
## tell the rest of the FanFicFare system about them. They can be used in
## include_subject_tags, titlepage_entries, extra_titlepage_entries,
## logpage_entries, extra_logpage_entries, and include_in_* config
## items. You can also add additional entries here to build up
@@ -914,11 +1043,6 @@ extraships:Harry Potter/Hermione Granger
#username:YourName
#password:yourpassword
## Virtually all eFiction-based sites allow downloading the whole story in
## bulk using the 'Print' feature. If 'bulk_load' is set to 'true', both
## metadata and chapters can be loaded in one step
bulk_load:true
extra_valid_entries: readings,romance
extra_titlepage_entries: readings,romance
readings_label: Readings
@@ -1002,6 +1126,18 @@ dislikes_label:Dislikes
#username:YourName
#password:yourpassword
# shows size as "10 KB", not word count
extra_valid_entries:size
# don't show twitter icon.
cover_exclusion_regexp:/res/css/bir.png
[forums.spacebattles.com]
## see [base_xenforoforum]
[forums.sufficientvelocity.com]
## see [base_xenforoforum]
[grangerenchanted.com]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
@@ -1048,6 +1184,18 @@ extracategories:In Death
## cover image. This lets you exclude them.
cover_exclusion_regexp:/public/style_emoticons/.*
[it-could-happen.net]
## Some sites do not require a login, but do require the user to
## confirm they are adult for adult content. In commandline version,
## this should go in your personal.ini, not defaults.ini.
#is_adult:true
## RPF == http://en.wikipedia.org/wiki/Real_person_fiction
## Site dedicated to these categories/characters/ships
extracategories:Glee RPF
extracharacters:Darren Criss, Chris Colfer
extraships:Darren Criss/Chris Colfer
[ksarchive.com]
## Site dedicated to these categories/characters/ships
extracategories:Star Trek
@@ -1067,11 +1215,6 @@ eroticatags_label:Erotica Tags
extra_titlepage_entries: eroticatags
[lotrfanfiction.com]
## Virtually all eFiction-based sites allow downloading the whole story in
## bulk using the 'Print' feature. If 'bulk_load' is set to 'true', both
## metadata and chapters can be loaded in one step
bulk_load:true
extra_valid_entries: readings
readings_label: Readings
@@ -1111,8 +1254,6 @@ extracategories:West Wing
## Site dedicated to these categories/characters/ships
extracategories:NCIS
[netraptor.org]
[nfacommunity.com]
## Some sites do not require a login, but do require the user to
## confirm they are adult for adult content. In commandline version,
@@ -1127,6 +1268,12 @@ extracategories:NCIS
extracategories:Buffy: The Vampire Slayer
extracharacters:Willow
[ninelives.dark-solace.org]
## Site dedicated to these categories/characters/ships
extracategories:The Walking Dead
extracharacters:Carol,Daryl
extraships:Carol/Daryl
[nocturnal-light.net]
## Extra metadata that this adapter knows about. See [dramione.org]
## for examples of how to use them.
@@ -1274,10 +1421,6 @@ reviews_label:Reviews
extracharacters:Spike,Buffy
extracategories:Buffy the Vampire Slayer
[stargate-atlantis.org]
## Site dedicated to these categories/characters/ships
extracategories:Stargate: Atlantis
[storiesonline.net]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
@@ -1319,6 +1462,14 @@ universe_as_series: true
## cover image. This lets you exclude them.
cover_exclusion_regexp:/css/bir.png
[tgstorytime.com]
## Site dedicated to these categories/characters/ships
extracategories:Transgender
## Some sites do not require a login, but do require the user to
## confirm they are adult for adult content.
#is_adult:true
[thehexfiles.net]
## Site dedicated to these categories/characters/ships
extracategories:Harry Potter
@@ -1347,11 +1498,6 @@ extracategories:Criminal Minds
## personal.ini, not defaults.ini.
#is_adult:true
## Virtually all eFiction-based sites allow downloading the whole story in
## bulk using the 'Print' feature. If 'bulk_load' is set to 'true', both
## metadata and chapters can be loaded in one step
bulk_load:true
extra_valid_entries: readings,challenge
extra_titlepage_entries: readings,challenge
challenge_label: Challenge
@@ -1420,6 +1566,8 @@ extra_titlepage_entries:readings,awards
awards_label:Awards
readings_label:Readings
## some sites include images that we don't ever want becoming the
## cover image. This lets you exclude them.
cover_exclusion_regexp:art/.*Awards.jpg
[voracity2.e-fic.com]
@@ -1460,17 +1608,6 @@ extraships:Draco Malfoy/Ginny Weasley
## Site dedicated to these categories/characters/ships
extracategories:Stargate: SG-1
[www.checkmated.com]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
## commandline version, this should go in your personal.ini, not
## defaults.ini.
#username:YourName
#password:yourpassword
## Site dedicated to these categories/characters/ships
extracategories:Harry Potter
[www.destinysgateway.com]
## Some sites do not require a login, but do require the user to
## confirm they are adult for adult content. In commandline version,
@@ -1490,14 +1627,6 @@ extracategories:InuYasha
extracharacters:Sesshoumaru,Kagome
extraships:Sesshoumaru/Kagome
[www.dotmoon.net]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
## commandline version, this should go in your personal.ini, not
## defaults.ini.
#username:YourName
#password:yourpassword
[www.efpfanfic.net]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
@@ -1519,9 +1648,15 @@ user_agent:
## Set this to true to never use them.
#never_make_cover: false
## fanfiction.net shows the user's
## exclude fanfiction.net imageu (old user vs story detect) and
## default user (d_60_90)
cover_exclusion_regexp:(/imageu/|d_60_90\.jpg)
## April 2015, ffnet changed their story and user pictures urls to be
## the same. Now the only way to know if the story image is really
## the author image is to go get the author image and check.
skip_author_cover:true
## fanfiction.net is blocking people more aggressively. If you
## download fewer stories less often you can likely get by with
## reducing this sleep.
@@ -1544,7 +1679,7 @@ extra_valid_entries:reviews,favs,follows
## to be romantic pairings.
ships_label:Pairings
## Date formats used by FFDL. Published and Update don't usually have
## Date formats used by FanFicFare. Published and Update don't usually have
## time, but they do now on ffnet.
## See http://docs.python.org/library/datetime.html#strftime-strptime-behavior
## Note that ini format requires % to be escaped as %%.
@@ -1590,6 +1725,22 @@ extratags:
## for examples of how to use them.
extra_valid_entries:reviews,favs,follows
## fanfiction.net shows the user's
cover_exclusion_regexp:(/imageu/|d_60_90\.jpg)
## fanfiction.net is blocking people more aggressively. If you
## download fewer stories less often you can likely get by with
## reducing this sleep.
slow_down_sleep_time:4
## Date formats used by FanFicFare. Published and Update don't usually have
## time, but they do now on ffnet.
## See http://docs.python.org/library/datetime.html#strftime-strptime-behavior
## Note that ini format requires % to be escaped as %%.
#dateCreated_format:%%Y-%%m-%%d %%H:%%M:%%S
datePublished_format:%%Y-%%m-%%d %%H:%%M:%%S
dateUpdated_format:%%Y-%%m-%%d %%H:%%M:%%S
[www.fimfiction.net]
## Some sites do not require a login, but do require the user to
## confirm they are adult for adult content. In commandline version,
@@ -1602,7 +1753,7 @@ extra_valid_entries:reviews,favs,follows
#fail_on_password: false
## fimfiction.net stories allow chapters to be added out of order. So
## the newest chapter may not be the last one. FFDL update doesn't
## the newest chapter may not be the last one. FanFicFare update doesn't
## like that. If do_update_hook is uncommented and set true, the
## adapter will discard all existing chapters from the newest one on
## when updating to enforce accurate chapters.
@@ -1613,6 +1764,10 @@ extra_valid_entries:reviews,favs,follows
## to on, but can be switched off if it is found to cause problems.
fix_fimf_blockquotes:true
## some sites include images that we don't ever want becoming the
## cover image. This lets you exclude them.
cover_exclusion_regexp:/images/emoticons/
## Site dedicated to these categories/characters/ships
extracategories:My Little Pony: Friendship is Magic
@@ -1656,10 +1811,6 @@ make_linkhtml_entries:prequel,sequels,groups,coverSource
## Site dedicated to these categories/characters/ships
extracategories:Harry Potter
[www.henneth-annun.net]
## Site dedicated to these categories/characters/ships
extracategories:The Hobbit
[www.hpfandom.net]
## Some sites do not require a login, but do require the user to
## confirm they are adult for adult content. In commandline version,
@@ -1700,7 +1851,38 @@ extraships:InuYasha/Kagome
## Site dedicated to these categories/characters/ships
extracategories:Lord of the Rings
[www.masseffect2.in]
## Site dedicated to this fandom.
extracategories: Mass Effect
## Ucoz.com engine, upon which MassEffect2.in is based, imposes an unspecified limit on request frequency.
## Reports vary from `5 requests per second' to `2 requests per second for more than 10 per minute'.
## With default settings, a several-hours IP ban may follow, so set it higher.
slow_down_sleep_time: 2
## Whether to exclude editor signature from the bottom of chapter text.
exclude_editor_signature: false
## Stories on the site almost never have cover image, and for the stories which do,
## this may be adjusted in `personal.ini' before downloading.
never_make_cover: true
## Titles for ratings identified by 1- or 2-letter codes from `ERATING system'
## (`система Р.Е.Й.Т.И.Н.Г.'). MassEffect2.in and some other sites adopted it,
## but changed titles and update them occasionally.
rating_titles: R=RESTRICTED (16+), E=EXEMPT (18+), I=ART HOUSE, T=To every, A=IN=Иной мир, Nn=Новый мир, G=О\, Господи!
adult_ratings: E,R
[www.mediaminer.org]
dateUpdated_format:%%Y-%%m-%%d %%H:%%M:%%S
## Note that mediaminer doesn't give datePublished on the story's
## index page--it's collected from the earliest uploaded chapter. So
## it's not available when only fetching metadata.
datePublished_format:%%Y-%%m-%%d %%H:%%M:%%S
## some sites include images that we don't ever want becoming the
## cover image. This lets you exclude them.
cover_exclusion_regexp:/img/rss.png
[www.midnightwhispers.ca]
## Some sites do not require a login, but do require the user to
@@ -1734,7 +1916,7 @@ extraships:Nick Stokes/Greg Sanders
## phoenixsong.net, oddly, can have high rated chapters (login
## required) in the middle of a lower rated story. Use this to force
## FFDL to always login to phoenixsong.net so those stories download
## FanFicFare to always login to phoenixsong.net so those stories download
## correctly. If you have a login, this is recommended.
#force_login:true
@@ -1768,6 +1950,13 @@ extracategories:Psych
## Site dedicated to these categories/characters/ships
extracategories:Queer as Folk
[quotev.com]
extra_valid_entries:pages,readers,reads,favorites
pages_label:Pages
readers_label:Readers
reads_label:Reads
favorites_label:Favorites
[www.restrictedsection.org]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
@@ -1790,17 +1979,6 @@ extragenres:Erotica
extracategories:Glee
extracharacters:Kurt Hummel,Blaine Anderson
[www.simplyundeniable.com]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
## commandline version, this should go in your personal.ini, not
## defaults.ini.
#username:YourName
#password:yourpassword
## Site dedicated to these categories/characters/ships
extracategories:Harry Potter
[www.sinful-desire.org]
## Some sites do not require a login, but do require the user to
## confirm they are adult for adult content. In commandline version,
@@ -1892,20 +2070,6 @@ extracategories:Twilight
## twilighted.net (ab)uses series as personal reading lists.
collect_series: false
[www.twiwrite.net]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
## commandline version, this should go in your personal.ini, not
## defaults.ini.
#username:YourName
#password:yourpassword
## Site dedicated to these categories/characters/ships
extracategories:Twilight
## twiwrite.net (ab)uses series as personal reading lists.
collect_series: false
[www.walkingtheplank.org]
## Some sites do not require a login, but do require the user to
## confirm they are adult for adult content. In commandline version,
@@ -1919,19 +2083,6 @@ extraships:Severus Snape/Harry Potter
[www.whofic.com]
[www.wizardtales.net]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
## commandline version, this should go in your personal.ini, not
## defaults.ini.
#username:YourName
#password:yourpassword
## Some sites also require the user to confirm they are adult for
## adult content. In commandline version, this should go in your
## personal.ini, not defaults.ini.
#is_adult:true
[www.wolverineandrogue.com]
## Site dedicated to these categories/characters/ships
extracategories:X-Men Movie
-6
View File
@@ -76,12 +76,6 @@
#username:YourUsername
#password:YourPassword
[www.twiwrite.net]
#username:YourName
#password:yourpassword
## default is false
#collect_series: true
[www.adastrafanfic.com]
## Some sites do not require a login, but do require the user to
## confirm they are adult for adult content.
+61 -24
View File
@@ -1,5 +1,5 @@
#!/usr/bin/env python
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
# -*- coding: utf-8 -*-
from __future__ import (unicode_literals, division, absolute_import,
print_function)
@@ -7,20 +7,51 @@ __license__ = 'GPL v3'
__copyright__ = '2015, Jim Miller'
__docformat__ = 'restructuredtext en'
import logging
logger = logging.getLogger(__name__)
import copy
from calibre.utils.config import JSONConfig
from calibre.gui2.ui import get_gui
from calibre_plugins.fanficfare_plugin.dialogs import OVERWRITE
from calibre_plugins.fanficfare_plugin.dialogs import SAVE_UPDATE
from calibre_plugins.fanficfare_plugin.common_utils import get_library_uuid
PREFS_NAMESPACE = 'FanFictionDownLoaderPlugin'
# Show translated strings, but save the same string in prefs so your
# prefs are the same in different languages.
YES=_('Yes, Always')
SAVE_YES='Yes'
YES_IF_IMG=_('Yes, if EPUB has a cover image')
SAVE_YES_IF_IMG='Yes, if img'
YES_UNLESS_IMG=_('Yes, unless FanFicFare found a cover image')
SAVE_YES_UNLESS_IMG='Yes, unless img'
NO=_('No')
SAVE_NO='No'
calcover_save_options = {
YES:SAVE_YES,
SAVE_YES:YES,
YES_IF_IMG:SAVE_YES_IF_IMG,
SAVE_YES_IF_IMG:YES_IF_IMG,
YES_UNLESS_IMG:SAVE_YES_UNLESS_IMG,
SAVE_YES_UNLESS_IMG:YES_UNLESS_IMG,
NO:SAVE_NO,
SAVE_NO:NO,
}
updatecalcover_order=[YES,YES_IF_IMG,NO]
gencalcover_order=[YES,YES_UNLESS_IMG,NO]
# if don't have any settings for FanFicFarePlugin, copy from
# predecessor FanFictionDownLoaderPlugin.
FFDL_PREFS_NAMESPACE = 'FanFictionDownLoaderPlugin'
PREFS_NAMESPACE = 'FanFicFarePlugin'
PREFS_KEY_SETTINGS = 'settings'
# Set defaults used by all. Library specific settings continue to
# take from here.
default_prefs = {}
default_prefs['personal.ini'] = get_resources('plugin-example.ini')
default_prefs['cal_cols_pass_in'] = False
default_prefs['rejecturls'] = ''
default_prefs['rejectreasons'] = '''Sucked
Boring
@@ -28,7 +59,6 @@ Dup from another site'''
default_prefs['reject_always'] = False
default_prefs['updatemeta'] = True
default_prefs['updatecover'] = False
default_prefs['updateepubcover'] = False
default_prefs['keeptags'] = False
default_prefs['suppressauthorsort'] = False
@@ -39,14 +69,14 @@ default_prefs['autoconvert'] = False
default_prefs['urlsfromclip'] = True
default_prefs['updatedefault'] = True
default_prefs['fileform'] = 'epub'
default_prefs['collision'] = OVERWRITE
default_prefs['collision'] = SAVE_UPDATE
default_prefs['deleteotherforms'] = False
default_prefs['adddialogstaysontop'] = False
default_prefs['includeimages'] = False
default_prefs['lookforurlinhtml'] = False
default_prefs['checkforseriesurlid'] = True
default_prefs['checkforurlchange'] = True
default_prefs['injectseries'] = False
default_prefs['matchtitleauth'] = True
default_prefs['smarten_punctuation'] = False
default_prefs['show_est_time'] = False
@@ -55,7 +85,13 @@ default_prefs['read_lists'] = ''
default_prefs['addtolists'] = False
default_prefs['addtoreadlists'] = False
default_prefs['addtolistsonread'] = False
default_prefs['autounnew'] = False
default_prefs['updatecalcover'] = None
default_prefs['gencalcover'] = SAVE_YES
default_prefs['updatecover'] = False
default_prefs['calibre_gen_cover'] = False
default_prefs['plugin_gen_cover'] = True
default_prefs['gcnewonly'] = False
default_prefs['gc_site_settings'] = {}
default_prefs['allow_gc_from_ini'] = True
@@ -65,11 +101,13 @@ default_prefs['countpagesstats'] = []
default_prefs['wordcountmissing'] = False
default_prefs['errorcol'] = ''
default_prefs['savemetacol'] = ''
default_prefs['custom_cols'] = {}
default_prefs['custom_cols_newonly'] = {}
default_prefs['allow_custcol_from_ini'] = True
default_prefs['std_cols_newonly'] = {}
default_prefs['set_author_url'] = True
default_prefs['imapserver'] = ''
default_prefs['imapuser'] = ''
@@ -77,13 +115,8 @@ default_prefs['imappass'] = ''
default_prefs['imapsessionpass'] = False
default_prefs['imapfolder'] = 'INBOX'
default_prefs['imapmarkread'] = True
# This is where all preferences for this plugin *were* stored
# Remember that this name (i.e. plugins/fanfictiondownloader_plugin) is also
# in a global namespace, so make it as unique as possible.
# You should always prefix your config file name with plugins/,
# so as to ensure you dont accidentally clobber a calibre config file
old_prefs = JSONConfig('plugins/fanfictiondownloader_plugin')
default_prefs['auto_reject_from_email'] = False
default_prefs['download_from_email_immediately'] = False
def set_library_config(library_config,db):
db.prefs.set_namespaced(PREFS_NAMESPACE,
@@ -93,19 +126,23 @@ def set_library_config(library_config,db):
def get_library_config(db):
library_id = get_library_uuid(db)
library_config = None
# Check whether this is a configuration needing to be migrated
# from json into database. If so: get it, set it, rename it in json.
if library_id in old_prefs:
#print("get prefs from old_prefs")
library_config = old_prefs[library_id]
set_library_config(library_config,db)
old_prefs["migrated to library db %s"%library_id] = old_prefs[library_id]
del old_prefs[library_id]
if library_config is None:
#print("get prefs from db")
library_config = db.prefs.get_namespaced(PREFS_NAMESPACE, PREFS_KEY_SETTINGS,
copy.deepcopy(default_prefs))
library_config = db.prefs.get_namespaced(PREFS_NAMESPACE,
PREFS_KEY_SETTINGS)
# if don't have any settings for FanFicFarePlugin, copy from
# predecessor FanFictionDownLoaderPlugin.
if library_config is None:
logger.info("Attempting to read settings from predecessor--FFDL")
library_config = db.prefs.get_namespaced(FFDL_PREFS_NAMESPACE,
PREFS_KEY_SETTINGS)
if library_config is None:
# defaults.
logger.info("Using default settings")
library_config = copy.deepcopy(default_prefs)
return library_config
# fake out so I don't have to change the prefs calls anywhere. The
+6
View File
@@ -0,0 +1,6 @@
# Translations
If you're interested in helping provide translations for this project,
please use the
[Transifex](https://www.transifex.com/projects/p/calibre-plugins/resources/)
website to add translations to this, or other calibre plugins that support it.
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
+15
View File
@@ -1,5 +1,20 @@
# -*- coding: utf-8 -*-
# Copyright 2015 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the 'License');
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an 'AS IS' BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
try:
# just a way to switch between web service and CLI/PI
import google.appengine.api
+28 -12
View File
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -42,7 +42,6 @@ import adapter_adastrafanficcom
import adapter_twcslibrarynet
import adapter_tthfanficorg
import adapter_twilightednet
import adapter_twiwritenet
import adapter_whoficcom
import adapter_siyecouk
import adapter_archiveofourownorg
@@ -58,7 +57,6 @@ import adapter_archiveskyehawkecom
import adapter_squidgeorgpeja
import adapter_libraryofmoriacom
import adapter_wraithbaitcom
import adapter_checkmatedcom
import adapter_chaossycophanthexcom
import adapter_dramioneorg
import adapter_erosnsapphosycophanthexcom
@@ -75,7 +73,6 @@ import adapter_storiesofardacom
import adapter_samdeanarchivenu
import adapter_destinysgatewaycom
import adapter_ncisfictionnet
import adapter_stargateatlantisorg
import adapter_thealphagatecom
import adapter_fanfiktionde
import adapter_ponyfictionarchivenet
@@ -88,7 +85,6 @@ import adapter_darksolaceorg
import adapter_finestoriescom
import adapter_hpfanficarchivecom
import adapter_twilightarchivescom
import adapter_wizardtalesnet
import adapter_nhamagicalworldsus
import adapter_hlfictionnet
import adapter_grangerenchantedcom
@@ -105,19 +101,15 @@ import adapter_qafficcom
import adapter_efpfanficnet
import adapter_potterficscom
import adapter_efictionestelielde
import adapter_dotmoonnet
import adapter_pommedesangcom
import adapter_restrictedsectionorg
import adapter_imagineeficcom
import adapter_buffynfaithnet
import adapter_psychficcom
import adapter_hennethannunnet
import adapter_tokrafandomnetcom
import adapter_netraptororg
import adapter_asr3slashzoneorg
import adapter_nickandgregnet
import adapter_potterheadsanonymouscom
import adapter_simplyundeniablecom
import adapter_scarheadnet
import adapter_fictionpadcom
import adapter_storiesonlinenet
@@ -141,6 +133,14 @@ import adapter_lotrfanfictioncom
import adapter_fhsarchivecom
import adapter_fanfictionjunkiesde
import adapter_devianthearts
import adapter_tgstorytimecom
import adapter_itcouldhappennet
import adapter_forumsspacebattlescom
import adapter_forumssufficientvelocitycom
import adapter_questionablequestingcom
import adapter_ninelivesdarksolaceorg
import adapter_masseffect2in
import adapter_quotevcom
## This bit of complexity allows adapters to be added by just adding
## importing. It eliminates the long if/else clauses we used to need
@@ -200,19 +200,35 @@ def getAdapter(config,url,anyurl=False):
# No adapter found.
raise exceptions.UnknownSite( url, [cls.getSiteDomain() for cls in __class_list] )
def getConfigSections():
def getSiteSections():
# doesn't include base sections. Sections rather than site DNS because of squidge/peja
return [cls.getConfigSection() for cls in __class_list]
def getConfigSections():
# does include base sections.
sections = set()
for cls in __class_list:
sections.update(cls.getConfigSections())
return sections
def get_bulk_load_sites():
# for now, all eFiction Base adapters are assumed to allow bulk_load.
sections = set()
for cls in filter( lambda x : issubclass(x,base_efiction_adapter.BaseEfictionAdapter),
__class_list):
sections.update( [ x.replace('www.','') for x in cls.getConfigSections() ] )
return sections
def getSiteExamples():
l=[]
for cls in sorted(__class_list, key=lambda x : x.getConfigSection()):
l.append((cls.getConfigSection(),cls.getSiteExampleURLs().split()))
return l
def getConfigSectionFor(url):
def getConfigSectionsFor(url):
(cls,fixedurl) = getClassFor(url)
if cls:
return cls.getConfigSection()
return cls.getConfigSections()
# No adapter found.
raise exceptions.UnknownSite( url, [cls.getSiteDomain() for cls in __class_list] )
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2014 Fanficdownloader team
# Copyright 2014 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -230,7 +230,6 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
fandoms = a.findAll('a',{'class':"tag"})
for fandom in fandoms:
self.story.addToList('fandoms',fandom.string)
self.story.addToList('category',fandom.string)
a = metasoup.find('dd',{'class':"warning tags"})
if a != None:
@@ -243,7 +242,6 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
genres = a.findAll('a',{'class':"tag"})
for genre in genres:
self.story.addToList('freeformtags',genre.string)
self.story.addToList('genre',genre.string)
a = metasoup.find('dd',{'class':"category tags"})
if a != None:
@@ -251,7 +249,6 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
for genre in genres:
if genre != "Gen":
self.story.addToList('ao3categories',genre.string)
self.story.addToList('genre',genre.string)
a = metasoup.find('dd',{'class':"character tags"})
if a != None:
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2013 Fanficdownloader team
# Copyright 2013 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2014 Fanficdownloader team
# Copyright 2014 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
+24 -30
View File
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -82,7 +82,7 @@ class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX
# The date format will vary from site to site.
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
self.dateformat = "%b %d, %Y" # XXX
self.dateformat = "%d %b %Y" # XXX
@staticmethod # must be @staticmethod, don't remove it.
def getSiteDomain():
@@ -233,25 +233,27 @@ class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX
except:
return ""
# <span class="label">Rated:</span> NC-17<br /> etc
labels = soup.findAll('span',{'class':'label'})
listbox = soup.find('div',{'class':'listbox'})
# <strong>Rating:</strong> M<br /> etc
labels = listbox.findAll('strong')
for labelspan in labels:
value = labelspan.nextSibling
label = labelspan.string
if 'Summary' in label:
## Everything until the next span class='label'
## Everything until the next strong tag.
svalue = ""
while not defaultGetattr(value,'class') == 'label':
while not isinstance(value,bs.Tag) or value.name != 'strong':
svalue += str(value)
value = value.nextSibling
self.setDescription(url,svalue)
#self.story.setMetadata('description',stripHTML(svalue))
if 'Rated' in label:
if 'Rating' in label:
self.story.setMetadata('rating', value)
if 'Word count' in label:
if 'Words' in label:
value=re.sub(r"\|",r"",value)
self.story.setMetadata('numWords', value)
if 'Categories' in label:
@@ -266,26 +268,6 @@ class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX
for char in charstext:
self.story.addToList('characters',char.string)
## Not all sites use Genre, but there's no harm to
## leaving it in. Check to make sure the type_id number
## is correct, though--it's site specific.
if 'Genre' in label:
genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
genrestext = [genre.string for genre in genres]
self.genre = ', '.join(genrestext)
for genre in genrestext:
self.story.addToList('genre',genre.string)
## Not all sites use Warnings, but there's no harm to
## leaving it in. Check to make sure the type_id number
## is correct, though--it's site specific.
if 'Warnings' in label:
warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
warningstext = [warning.string for warning in warnings]
self.warning = ', '.join(warningstext)
for warning in warningstext:
self.story.addToList('warnings',warning.string)
if 'Completed' in label:
if 'Yes' in value:
self.story.setMetadata('status', 'Completed')
@@ -293,13 +275,25 @@ class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX
self.story.setMetadata('status', 'In-Progress')
if 'Published' in label:
value=re.sub(r"\|",r"",value)
self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
if 'Updated' in label:
# there's a stray [ at the end.
#value = value[0:-1]
value=re.sub(r"\|",r"",value)
self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
# moved outside because they changed *most*, but not *all* labels to <strong>
ships = listbox.findAll('a',href=re.compile(r'browse.php.type=class&(amp;)?type_id=2')) # crappy html: & vs &amp; in url.
shipstext = [ship.string for ship in ships]
for ship in shipstext:
self.story.addToList('ships',ship.string)
genres = listbox.findAll('a',href=re.compile(r'browse.php\?type=class&(amp;)?type_id=1')) # crappy html: & vs &amp; in url.
genrestext = [genre.string for genre in genres]
for genre in genrestext:
self.story.addToList('genre',genre.string)
try:
# Find Series name from series URL.
a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2013 Fanficdownloader team
# Copyright 2013 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -1,238 +0,0 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
import time
import logging
logger = logging.getLogger(__name__)
import re
import urllib2
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, makeDate
def getClass():
return CheckmatedComAdapter
class CheckmatedComAdapter(BaseSiteAdapter):
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.decode = ["Windows-1252",
"utf8"] # 1252 is a superset of iso-8859-1.
# Most sites that claim to be
# iso-8859-1 (and some that claim to be
# utf8) are really windows-1252.
self.username = "" # if left empty, site doesn't return any message at all.
self.password = ""
self.is_adult=False
# get storyId from url--url validation guarantees query is only sid=1234
self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
self._setURL('http://' + self.getSiteDomain() + '/story.php?story='+self.story.getMetadata('storyId'))
# Each adapter needs to have a unique site abbreviation.
self.story.setMetadata('siteabbrev','chm')
# The date format will vary from site to site.
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
self.dateformat = "%b %d, %Y"
@staticmethod # must be @staticmethod, don't remove it.
def getSiteDomain():
# The site domain. Does have www here, if it uses it.
return 'www.checkmated.com'
@classmethod
def getSiteExampleURLs(cls):
return "http://"+cls.getSiteDomain()+"/story.php?story=1234"
def getSiteURLPattern(self):
return re.escape("http://"+self.getSiteDomain()+"/story.php?story=")+r"\d+$"
## Login seems to be reasonably standard across eFiction sites. This story is in The Bedchamber
def needToLoginCheck(self, data):
if 'This story is in The Bedchamber' in data \
or 'That username is not in our database' in data \
or "That password is not correct, please try again" in data:
return True
else:
return False
def performLogin(self, url):
params = {}
if self.password:
params['name'] = self.username
params['pass'] = self.password
else:
params['name'] = self.getConfig("username")
params['pass'] = self.getConfig("password")
params['login'] = 'yes'
params['submit'] = 'login'
loginUrl = 'http://' + self.getSiteDomain()+'/login.php'
d = self._fetchUrl(loginUrl,params)
e = self._fetchUrl(url)
if "Welcome back," not in d : #Member Account
logger.info("Failed to login to URL %s as %s" % (loginUrl,
params['name']))
raise exceptions.FailedToLogin(url,params['name'])
return False
elif "This story is in The Bedchamber" in e:
raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Your account does not have sufficient priviliges to read this story.")
return False
else:
return True
## Getting the chapter list and the meta data, plus 'is adult' checking.
def extractChapterUrlsAndMetadata(self):
# index=1 makes sure we see the story chapter index. Some
# sites skip that for one-chapter stories.
url = self.url
logger.debug("URL: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
if self.needToLoginCheck(data):
# need to log in for this one.
self.performLogin(url)
data = self._fetchUrl(url)
# The actual text that is used to announce you need to be an
# adult varies from site to site. Again, print data before
# the title search to troubleshoot.
if "Access denied. This story has not been validated by the adminstrators of this site." in data:
raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data)
# print data
# Now go hunting for all the meta data and the chapter list.
## Title
a = soup.find('span', {'class' : 'storytitle'})
self.story.setMetadata('title',stripHTML(a))
# Find authorid and URL from... author url.
a = a.parent.find('a', href=re.compile(r"authors.php\?name\=\w+"))
self.story.setMetadata('authorId',a['href'].split('=')[1])
self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
self.story.setMetadata('author',a.string)
a = soup.find('select', {'name' : 'chapter'})
if a == None:
self.chapterUrls.append((self.story.getMetadata('title'),url))
else:
for chapter in a.findAll('option'):
self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/story.php?story='+self.story.getMetadata('storyId')+'&chapter='+chapter['value']))
self.story.setMetadata('numChapters',len(self.chapterUrls))
# eFiction sites don't help us out a lot with their meta data
# formating, so it's a little ugly.
# utility method
def defaultGetattr(d,k):
try:
return d[k]
except:
return ""
# website does not keep track of word count, and there is no convenient way to calculate it
summary = soup.find('fieldset')
summary.find('legend').extract()
summary.name='div'
self.setDescription(url,summary)
# <span class="label">Rated:</span> NC-17<br /> etc
table = soup.findAll('div', {'class' : 'text'})[1]
for labels in table.findAll('tr'):
value = labels.findAll('td')[1]
label = labels.findAll('td')[0]
if 'Rating' in stripHTML(label):
self.story.setMetadata('rating', stripHTML(value))
if 'Ship' in stripHTML(label):
if value.string != "none/none":
self.story.addToList('ships',value.string)
for char in value.string.split('/'):
if char != 'none':
self.story.addToList('characters',char)
if 'Status' in stripHTML(label):
if value.find('img', {'src' : 'img/incomplete.gif'}) == None:
self.story.setMetadata('status', 'Completed')
else:
self.story.setMetadata('status', 'In-Progress')
if 'Published' in stripHTML(label):
self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
if 'Updated' in stripHTML(label):
self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
a = self._fetchUrl(self.story.getMetadata('authorUrl')+'&cat=stories')
for story in bs.BeautifulSoup(a).findAll('table', {'class' : 'storyinfo'}):
a = story.find('a', href=re.compile(r"review.php\?s\="+self.story.getMetadata('storyId')+'&act=view'))
if a != None:
for labels in story.findAll('tr'):
value = labels.findAll('td')[1]
label = labels.findAll('td')[0]
if 'genre' in stripHTML(label):
for genre in value.findAll('img'):
self.story.addToList('genre',genre['title'])
# grab the text for an individual chapter.
def getChapterText(self, url):
logger.debug('Getting chapter text from: %s' % url)
soup = bs.BeautifulSoup(self._fetchUrl(url),
selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
div = soup.find('div', {'id' : 'resizeableText'})
div.find('div', {'class' : 'storyTools'}).extract()
if None == div:
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
return self.utf8FromSoup(url,div)
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
+18 -313
View File
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -16,321 +16,26 @@
#
# Software: eFiction
import time
import logging
logger = logging.getLogger(__name__)
import re
import urllib2
from base_efiction_adapter import BaseEfictionAdapter
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
class DarkSolaceOrgAdapter(BaseEfictionAdapter):
from base_adapter import BaseSiteAdapter, makeDate
@staticmethod
def getSiteDomain():
return 'dark-solace.org'
@classmethod
def getPathToArchive(self):
return '/elysian'
@classmethod
def getSiteAbbrev(self):
return 'dksl'
@classmethod
def getDateFormat(self):
return "%B %d, %Y"
def getClass():
return DarkSolaceOrgAdapter
# Class name has to be unique. Our convention is camel case the
# sitename with Adapter at the end. www is skipped.
class DarkSolaceOrgAdapter(BaseSiteAdapter):
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.decode = ["Windows-1252",
"utf8"] # 1252 is a superset of iso-8859-1.
# Most sites that claim to be
# iso-8859-1 (and some that claim to be
# utf8) are really windows-1252.
self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
self.password = ""
self.is_adult=False
# get storyId from url--url validation guarantees query is only sid=1234
self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
# normalized story URL.
self._setURL('http://' + self.getSiteDomain() + '/elysian/viewstory.php?sid='+self.story.getMetadata('storyId'))
# Each adapter needs to have a unique site abbreviation.
self.story.setMetadata('siteabbrev','dksl')
# The date format will vary from site to site.
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
self.dateformat = "%B %d, %Y"
@staticmethod # must be @staticmethod, don't remove it.
def getSiteDomain():
# The site domain. Does have www here, if it uses it.
return 'dark-solace.org'
@classmethod
def getAcceptDomains(cls):
return ['www.dark-solace.org','dark-solace.org']
@classmethod
def getSiteExampleURLs(cls):
return "http://"+cls.getSiteDomain()+"/elysian/viewstory.php?sid=1234"
def getSiteURLPattern(self):
return re.escape("http://")+"(www\.)?"+re.escape(self.getSiteDomain()+"/elysian/viewstory.php?sid=")+r"\d+$"
## Login seems to be reasonably standard across eFiction sites.
def needToLoginCheck(self, data):
if 'This story contains adult content not suitable for children' in data \
or "That password doesn't match the one in our database" in data \
or "Registered Users Only" in data:
return True
else:
return False
def performLogin(self, url):
params = {}
if self.password:
params['penname'] = self.username
params['password'] = self.password
else:
params['penname'] = self.getConfig("username")
params['password'] = self.getConfig("password")
params['action'] = 'login'
params['submit'] = 'Submit'
loginUrl = 'http://www.' + self.getSiteDomain() + '/elysian/user.php'
logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
params['penname']))
d = self._postUrl(loginUrl, params)
if "Member Account" not in d : #User Account Page
logger.info("Failed to login to URL %s as %s, or have no authorization to access the story" % (loginUrl, params['penname']))
raise exceptions.FailedToLogin(url,params['penname'])
return False
else:
return True
## Getting the chapter list and the meta data, plus 'is adult' checking.
def extractChapterUrlsAndMetadata(self):
if self.is_adult or self.getConfig("is_adult"):
# Weirdly, different sites use different warning numbers.
# If the title search below fails, there's a good chance
# you need a different number. print data at that point
# and see what the 'click here to continue' url says.
addurl = "&ageconsent=ok&warning=5"
else:
addurl=""
# index=1 makes sure we see the story chapter index. Some
# sites skip that for one-chapter stories.
url = self.url+'&index=1'+addurl
logger.debug("URL: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
if self.needToLoginCheck(data):
# need to log in for this one.
self.performLogin(url)
data = self._fetchUrl(url)
m = re.search(r"'viewstory.php\?sid=\d+((?:&amp;ageconsent=ok)?&amp;warning=\d+)'",data)
if m != None:
if self.is_adult or self.getConfig("is_adult"):
# We tried the default and still got a warning, so
# let's pull the warning number from the 'continue'
# link and reload data.
addurl = m.group(1)
# correct stupid &amp; error in url.
addurl = addurl.replace("&amp;","&")
url = self.url+'&index=1'+addurl
logger.debug("URL 2nd try: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
else:
raise exceptions.AdultCheckRequired(self.url)
if "Access denied. This story has not been validated by the adminstrators of this site." in data:
raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data)
# print data
# Now go hunting for all the meta data and the chapter list.
## Title and author
div = soup.find('div', {'id' : 'pagetitle'})
aut = div.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
self.story.setMetadata('authorId',aut['href'].split('=')[1])
self.story.setMetadata('authorUrl','http://'+self.host+'/elysian/'+aut['href'])
self.story.setMetadata('author',aut.string)
aut.extract()
# first a tag in pagetitle is title
self.story.setMetadata('title',stripHTML(div.find('a')))
div.find('a').extract()
# only thing left in div(pagetitle) now should be 'by' and rating.
rating = stripHTML(div)
if '[' in rating:
self.story.setMetadata('rating', rating[rating.index('[')+1:-1])
for chapa in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+
self.story.getMetadata('storyId')+'&chapter=\d+')):
self.chapterUrls.append((stripHTML(chapa),'http://'+self.host+'/elysian/'+chapa['href']))
self.story.setMetadata('numChapters',len(self.chapterUrls))
asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
storylink = asoup.find('a', href=re.compile(r'viewstory.php\?sid='+
self.story.getMetadata('storyId')+'($|[^\d])'))
# author's story list is paginated if there's a pagelinks div.
# Only need to look in it if the story wasn't on the first page.
pagelinks = asoup.find('div',{'id':'pagelinks'})
if pagelinks and storylink==None:
authpageslist = pagelinks.findAll('a',href=re.compile(r'action=storiesby'))
for page in authpageslist[1:]: # skip first, already checked above.
asoup = bs.BeautifulSoup(self._fetchUrl('http://'+self.host+'/elysian/'+page['href']))
storylink = asoup.find('a', href=re.compile(r'viewstory.php\?sid='+
self.story.getMetadata('storyId')+'($|[^\d])'))
if storylink:
break
if not storylink:
raise exceptions.FailedToDownload("Unable to find story metadata on author's page(s)")
metalist = storylink.parent.parent
# eFiction sites don't help us out a lot with their meta data
# formating, so it's a little ugly.
# utility method
def defaultGetattr(d,k):
try:
return d[k]
except:
return ""
# <span class="label">Rated:</span> NC-17<br /> etc
labels = metalist.findAll('span', {'class' : 'label'})
for labelspan in labels:
label = labelspan.text
value = labelspan.nextSibling
if 'Summary' in label:
## Everything until the next span class='label'
svalue = ""
while value and not (defaultGetattr(value,'class') == 'label' or "Chapters: " in stripHTML(value)):
svalue += str(value)
value = value.nextSibling
self.setDescription(url,svalue)
#self.story.setMetadata('description',stripHTML(svalue))
if 'Word count' in label:
self.story.setMetadata('numWords', value)
if 'Categories' in label:
cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
for cat in cats:
self.story.addToList('category',cat.string)
if 'Characters' in label:
chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
for char in chars:
self.story.addToList('characters',char.string)
if 'Genre' in label:
genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
for genre in genres:
self.story.addToList('genre',genre.string)
if 'Warnings' in label:
warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
for warning in warnings:
self.story.addToList('warnings',warning.string)
if 'Completed' in label:
if 'Yes' in value:
self.story.setMetadata('status', 'Completed')
else:
self.story.setMetadata('status', 'In-Progress')
if 'Published' in label:
self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
if 'Updated' in label:
# there's a stray [ at the end.
#value = value[0:-1]
self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
try:
# Find Series name from series URL.
a = metalist.find('a', href=re.compile(r"series.php\?seriesid=\d+"))
series_name = a.string
series_url = 'http://'+self.host+'/elysian/'+a['href']
# use BeautifulSoup HTML parser to make everything easier to find.
seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
# can't use ^viewstory...$ in case of higher rated stories with javascript href.
storylink = seriessoup.find('a', href=re.compile(r'viewstory.php\?sid='+
self.story.getMetadata('storyId')+'($|[^\d])'))
if storylink and storylink.parent and storylink.parent['class'] != 'title': # in case of links inside story summaries.
storylink = None
offset = 0
# series story list is paginated if there's a pagelinks div.
# Only need to look in it if the story wasn't on the first page.
pagelinks = seriessoup.find('div',{'id':'pagelinks'})
if pagelinks and storylink==None:
authpageslist = pagelinks.findAll('a',href=re.compile(r'offset='))
for page in authpageslist[1:]: # skip first, already checked above.
seriessoup = bs.BeautifulSoup(self._fetchUrl('http://'+self.host+'/elysian/'+page['href']))
storylink = seriessoup.find('a', href=re.compile(r'viewstory.php\?sid='+
self.story.getMetadata('storyId')+'($|[^\d])'))
if storylink and storylink.parent and storylink.parent['class'] != 'title': # in case of links inside story summaries.
storylink = None
if storylink:
offset = int(page['href'].split('=')[-1]) # offset is last.
break
# for reasons I don't understand, searching for story
# links by regex wasn't working reliably. It was missing
# the javascript links sometimes. This is cleaner anyway.
for i, div in enumerate(seriessoup.findAll('div', {'class':'title'})):
a = div.find('a') # first a is story link.
# skip 'report this' and 'TOC' links
if a == storylink:
self.setSeries(series_name, 1+i+offset)
self.story.setMetadata('seriesUrl',series_url)
break
except Exception, e:
logger.debug("Series parsing failed: %s"%e)
# grab the text for an individual chapter.
def getChapterText(self, url):
logger.debug('Getting chapter text from: %s' % url)
soup = bs.BeautifulSoup(self._fetchUrl(url))
div = soup.find('div', {'id' : 'story'})
if None == div:
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
return self.utf8FromSoup(url,div)
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2012 Fanficdownloader team
# Copyright 2012 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
+1 -16
View File
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2015 Fanficdownloader team
# Copyright 2015 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -32,21 +32,6 @@ class DeviantHeartsAdapter(BaseEfictionAdapter):
@classmethod
def getDateFormat(self):
return "%m/%d/%y"
# def handleMetadataPair(self, key, value):
# if key == 'Warnings':
# for val in re.split("\s*,\s*", value):
# if value == 'None':
# return
# else:
# # toss numbers only.
# self.story.addToList('warnings', filter(lambda x : not x.isdigit() , val))
# # elif 'Categories' in key:
# # for val in re.split("\s*>\s*", value):
# # self.story.addToList('category', val)
# else:
# super(FHSArchiveComAdapter, self).handleMetadataPair(key, value)
def getClass():
return DeviantHeartsAdapter
+1 -1
View File
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
-217
View File
@@ -1,217 +0,0 @@
# -*- coding: utf-8 -*-
# Copyright 2013 Fanficdownloader team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
import time
import logging
logger = logging.getLogger(__name__)
import re
import urllib2
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, makeDate
def getClass():
return DotMoonNetAdapter
# Class name has to be unique. Our convention is camel case the
# sitename with Adapter at the end. www is skipped.
class DotMoonNetAdapter(BaseSiteAdapter):
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.decode = ["Windows-1252",
"utf8"] # 1252 is a superset of iso-8859-1.
# Most sites that claim to be
# iso-8859-1 (and some that claim to be
# utf8) are really windows-1252.
self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
self.password = ""
self.is_adult=False
# get storyId from url--url validation guarantees query is only sid=1234
self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
# normalized story URL. www.dotmoon.net/library_view.php?storyid=3
self._setURL('http://' + self.getSiteDomain() + '/library_view.php?storyid='+self.story.getMetadata('storyId'))
# Each adapter needs to have a unique site abbreviation.
self.story.setMetadata('siteabbrev','dotm')
# The date format will vary from site to site.
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
self.dateformat = "%Y-%m-%d"
@staticmethod # must be @staticmethod, don't remove it.
def getSiteDomain():
# The site domain. Does have www here, if it uses it.
return 'www.dotmoon.net'
@classmethod
def getSiteExampleURLs(cls):
return "http://"+cls.getSiteDomain()+"/library_view.php?storyid=1234"
def getSiteURLPattern(self):
return re.escape("http://"+self.getSiteDomain()+"/library_view.php?storyid=")+r"\d+$"
## Login seems to be reasonably standard across eFiction sites.
def needToLoginCheck(self, data):
if 'You must be logged in to read adult-rated stories' in data \
or 'Password incorrect' in data \
or "That username does not exist" in data:
return True
else:
return False
def performLogin(self, url):
params = {}
if self.password:
params['user'] = self.username
params['passwrd'] = self.password
else:
params['user'] = self.getConfig("username")
params['passwrd'] = self.getConfig("password")
loginUrl = 'http://' + self.getSiteDomain() + '/board/index.php'
logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
params['user']))
d = self._fetchUrl(loginUrl+'?action=login2&user='+params['user']+'&passwrd='+params['passwrd'])
d = self._fetchUrl(loginUrl)
if "Show unread posts since last visit" not in d : #Member Account
logger.info("Failed to login to URL %s as %s" % (loginUrl,
params['user']))
raise exceptions.FailedToLogin(url,params['user'])
return False
else:
return True
## Getting the chapter list and the meta data, plus 'is adult' checking.
def extractChapterUrlsAndMetadata(self):
# index=1 makes sure we see the story chapter index. Some
# sites skip that for one-chapter stories.
url = self.url
logger.debug("URL: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
if self.needToLoginCheck(data):
# need to log in for this one.
self.performLogin(url)
data = self._fetchUrl(url)
if "Invalid story ID" in data:
raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Invalid story ID.")
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data)
# print data
# Now go hunting for all the meta data and the chapter list.
body=soup.findAll('body')[1]
body.find('table').extract()
## Title
a = body.find('b')
self.story.setMetadata('title',stripHTML(a))
# Find authorid and URL from... author url. http://www.dotmoon.net/board/index.php?action=profile;u=1'
a = body.find('a', href=re.compile(r"index.php\?action=profile;u=\d+"))
self.story.setMetadata('authorId',a['href'].split('=')[2])
self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
self.story.setMetadata('author',a.string)
# Find the chapters: 'library_storyview.php?chapterid=3
chapters=body.findAll('a', href=re.compile(r"library_storyview.php\?chapterid=\d+$"))
if len(chapters)==0:
raise exceptions.FailedToDownload(self.getSiteDomain() +" says: No php/html chapters found.")
if len(chapters)==1:
self.chapterUrls.append((self.story.getMetadata('title'),'http://'+self.host+'/'+chapters[0]['href']))
else:
for chapter in chapters:
# just in case there's tags, like <i> in chapter titles.
self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']))
self.story.setMetadata('numChapters',len(self.chapterUrls))
# other tags
labels = body.find('table', {'width':'390'}).findAll('td')
for labelspan in labels:
value = labelspan.nextSibling
label = labelspan.string
if label != None:
if 'Fandom' in label:
self.story.addToList('category',value.string)
if 'Setting' in label:
self.story.addToList('genre',value.string)
if 'Genre' in label:
self.story.addToList('genre',value.string)
if 'Style' in label:
self.story.addToList('genre',value.string)
if 'Rating' in label:
self.story.addToList('rating',value.string)
if 'Created' in label:
self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
if 'Updated' in label:
self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
if 'Status' in label:
if 'Completed' in value.string:
self.story.setMetadata('status', 'Completed')
else:
self.story.setMetadata('status', 'In-Progress')
table=body.findAll('table', {'width':'400'})[1].find('td')
self.setDescription(url,stripHTML(table).split('Summary: ')[1])
# grab the text for an individual chapter.
def getChapterText(self, url):
logger.debug('Getting chapter text from: %s' % url)
soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
div = soup.find('blockquote')
div.name='div'
if None == div:
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
return self.utf8FromSoup(url,div)
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2012 Fanficdownloader team
# Copyright 2012 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
+9 -8
View File
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -38,8 +38,9 @@ class DramioneOrgAdapter(BaseSiteAdapter):
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.decode = ["Windows-1252",
"utf8"] # 1252 is a superset of iso-8859-1.
self.decode = ["utf8",
"Windows-1252",]
# 1252 is a superset of iso-8859-1.
# Most sites that claim to be
# iso-8859-1 (and some that claim to be
# utf8) are really windows-1252.
@@ -218,20 +219,20 @@ class DramioneOrgAdapter(BaseSiteAdapter):
except:
return ""
# <span class="label">Rated:</span> NC-17<br /> etc
labels = soup.findAll('span',{'class':'label'})
listbox = soup.find('div',{'class':'listbox'})
# <strong>Rated:</strong> M<br /> etc
labels = listbox.findAll('strong')
for labelspan in labels:
value = labelspan.nextSibling
label = labelspan.string
if 'Summary' in label:
## Everything until the next span class='label'
## Everything until the next strong tag.
svalue = ""
while not defaultGetattr(value,'class') == 'label':
while not isinstance(value,bs.Tag) or value.name != 'strong':
svalue += str(value)
value = value.nextSibling
self.setDescription(url,svalue)
#self.story.setMetadata('description',stripHTML(svalue))
if 'Rated' in label:
self.story.setMetadata('rating', value)
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2013 Fanficdownloader team
# Copyright 2013 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
+1 -1
View File
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2012 Fanficdownloader team
# Copyright 2012 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2014 Fanficdownloader team
# Copyright 2014 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
+48 -9
View File
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -104,7 +104,7 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
data = self._fetchUrl(url)
#logger.debug("\n===================\n%s\n===================\n"%data)
soup = self.make_soup(data)
except urllib2.HTTPError, e:
except urllib2.HTTPError as e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(url)
else:
@@ -135,11 +135,15 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
chapcount+1)
logger.debug('=Trying newer chapter: %s' % tryurl)
newdata = self._fetchUrl(tryurl)
if "not found. Please check to see you are not using an outdated url." \
not in newdata:
if "not found. Please check to see you are not using an outdated url." not in newdata \
and "This request takes too long to process, it is timed out by the server." not in newdata:
logger.debug('=======Found newer chapter: %s' % tryurl)
soup = self.make_soup(newdata)
except:
except urllib2.HTTPError as e:
if e.code == 503:
raise e
except e:
logger.warn("Caught an exception reading URL: %s sleeptime(%s) Exception %s."%(unicode(url),sleeptime,unicode(e)))
pass
# Find authorid and URL from... author url.
@@ -268,14 +272,49 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
if get_cover:
# Try the larger image first.
cover_url = ""
try:
img = soup.find('img',{'class':'lazy cimage'})
self.setCoverImage(url,img['data-original'])
img = soup.select('img.lazy.cimage')
cover_url=img[0]['data-original']
except:
img = soup.find('img',{'class':'cimage'})
img = soup.select('img.cimage')
if img:
self.setCoverImage(url,img['src'])
cover_url=img[0]['src']
logger.debug("cover_url:%s"%cover_url)
authimg_url = ""
if cover_url and self.getConfig('skip_author_cover'):
authsoup = self.make_soup(self._fetchUrl(self.story.getMetadata('authorUrl')))
try:
img = authsoup.select('img.lazy.cimage')
authimg_url=img[0]['data-original']
except:
img = authsoup.select('img.cimage')
if img:
authimg_url=img[0]['src']
logger.debug("authimg_url:%s"%authimg_url)
## ffnet uses different sizes on auth & story pages, but same id.
## //ffcdn2012t-fictionpressllc.netdna-ssl.com/image/1936929/150/
## //ffcdn2012t-fictionpressllc.netdna-ssl.com/image/1936929/180/
try:
cover_id = cover_url.split('/')[4]
except:
cover_id = None
try:
authimg_id = authimg_url.split('/')[4]
except:
authimg_id = None
## don't use cover if it matches the auth image.
if cover_id and authimg_id and cover_id == authimg_id:
cover_url = None
if cover_url:
self.setCoverImage(url,cover_url)
# Find the chapter selector
select = soup.find('select', { 'name' : 'chapter' } )
+1 -1
View File
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2012 Fanficdownloader team
# Copyright 2012 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
+1 -1
View File
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2014 Fanficdownloader team
# Copyright 2014 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
+1 -1
View File
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2014 Fanficdownloader team
# Copyright 2014 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
+1 -1
View File
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
+1 -1
View File
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2013 Fanficdownloader team
# Copyright 2013 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
+2 -2
View File
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -135,7 +135,7 @@ class FicwadComSiteAdapter(BaseSiteAdapter):
self.story.setMetadata('title', stripHTML(titleh4.a))
# Find authorid and URL from... author url.
a = soup.find('span',{'class':'author'}).find('a', href=re.compile(r"^/author/\d+"))
a = soup.find('span',{'class':'author'}).find('a', href=re.compile(r"^/a/"))
self.story.setMetadata('authorId',a['href'].split('/')[2])
self.story.setMetadata('authorUrl','http://'+self.host+a['href'])
self.story.setMetadata('author',a.string)
+8 -2
View File
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -176,7 +176,13 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
if coverurl.startswith('//'): # fix for img urls missing 'http:'
coverurl = "http:"+coverurl
if get_cover:
self.setCoverImage(self.url,coverurl)
# try setting from href, if fails, try using the img src
if self.setCoverImage(self.url,coverurl)[0] == "failedtoload":
img = storyImage.find('img')
# try src, then data-src, then leave None.
coverurl = img.get('src',img.get('data-src',None))
if coverurl:
self.setCoverImage(self.url,coverurl)
coverSource = storyImage.find('a', {'class':'source'})
if coverSource:
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2013 Fanficdownloader team
# Copyright 2013 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -173,7 +173,7 @@ class FineStoriesComAdapter(BaseSiteAdapter):
for cat in lc2.findAll('div', {'class' : 'typediv'}):
self.story.addToList('category',cat.text)
self.story.setMetadata('numWords', lc2.findNext('td', {'class' : 'num'}).text)
self.story.setMetadata('size', lc2.findNext('td', {'class' : 'num'}).text)
lc4 = lc2.findNext('td', {'class' : 'lc4'})
@@ -0,0 +1,35 @@
# -*- coding: utf-8 -*-
# Copyright 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
from base_xenforoforum_adapter import BaseXenForoForumAdapter
def getClass():
return ForumsSpacebattlesComAdapter
class ForumsSpacebattlesComAdapter(BaseXenForoForumAdapter):
def __init__(self, config, url):
BaseXenForoForumAdapter.__init__(self, config, url)
# Each adapter needs to have a unique site abbreviation.
self.story.setMetadata('siteabbrev','fsb')
@staticmethod # must be @staticmethod, don't remove it.
def getSiteDomain():
# The site domain. Does have www here, if it uses it.
return 'forums.spacebattles.com'
@@ -0,0 +1,34 @@
# -*- coding: utf-8 -*-
# Copyright 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
from base_xenforoforum_adapter import BaseXenForoForumAdapter
def getClass():
return ForumsSufficientVelocityComAdapter
class ForumsSufficientVelocityComAdapter(BaseXenForoForumAdapter):
def __init__(self, config, url):
BaseXenForoForumAdapter.__init__(self, config, url)
# Each adapter needs to have a unique site abbreviation.
self.story.setMetadata('siteabbrev','fsv')
@staticmethod # must be @staticmethod, don't remove it.
def getSiteDomain():
# The site domain. Does have www here, if it uses it.
return 'forums.sufficientvelocity.com'
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2012 Fanficdownloader team
# Copyright 2012 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -176,7 +176,7 @@ class GrangerEnchantedCom(BaseSiteAdapter):
raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data)
soup = self.make_soup(data)
# print data
# Now go hunting for all the meta data and the chapter list.
@@ -217,11 +217,10 @@ class GrangerEnchantedCom(BaseSiteAdapter):
if 'Summary' in label:
## Everything until the next span class='label'
svalue = ""
while not defaultGetattr(value,'class') == 'label':
svalue += str(value)
while value and not defaultGetattr(value,'class') == 'label' and '<span class="label">' not in unicode(value):
svalue += unicode(value)
value = value.nextSibling
self.setDescription(url,svalue)
#self.story.setMetadata('description',stripHTML(svalue))
if 'Rated' in label:
self.story.setMetadata('rating', value)
@@ -271,7 +270,7 @@ class GrangerEnchantedCom(BaseSiteAdapter):
series_url = 'http://'+self.host+'/'+self.section+'/'+a['href']
# use BeautifulSoup HTML parser to make everything easier to find.
seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
seriessoup = self.make_soup(self._fetchUrl(series_url))
# can't use ^viewstory...$ in case of higher rated stories with javascript href.
storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
i=1
@@ -300,8 +299,7 @@ class GrangerEnchantedCom(BaseSiteAdapter):
logger.debug('Getting chapter text from: %s' % url)
soup = bs.BeautifulSoup(self._fetchUrl(url),
selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
soup = self.make_soup(self._fetchUrl(url))
div = soup.find('div', {'id' : 'story1'})
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -1,172 +0,0 @@
# -*- coding: utf-8 -*-
# Copyright 2013 Fanficdownloader team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
import time
import logging
logger = logging.getLogger(__name__)
import re
import urllib2
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, makeDate
def getClass():
return HennethAnnunNetAdapter
# Class name has to be unique. Our convention is camel case the
# sitename with Adapter at the end. www is skipped.
class HennethAnnunNetAdapter(BaseSiteAdapter):
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.decode = ["Windows-1252",
"utf8"] # 1252 is a superset of iso-8859-1.
# Most sites that claim to be
# iso-8859-1 (and some that claim to be
# utf8) are really windows-1252.
self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
self.password = ""
self.is_adult=False
# get storyId from url--url validation guarantees query is only sid=1234
self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
# normalized story URL.
self._setURL('http://' + self.getSiteDomain() + '/stories/chapter.cfm?stid='+self.story.getMetadata('storyId'))
# Each adapter needs to have a unique site abbreviation.
self.story.setMetadata('siteabbrev','htan')
# The date format will vary from site to site.
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
self.dateformat = "%m/%d/%y"
@staticmethod # must be @staticmethod, don't remove it.
def getSiteDomain():
# The site domain. Does have www here, if it uses it.
return 'www.henneth-annun.net'
@classmethod
def getSiteExampleURLs(cls):
return "http://"+cls.getSiteDomain()+"/stories/chapter.cfm?stid=1234"
def getSiteURLPattern(self):
return "http://"+self.getSiteDomain()+"/stories/chapter(_view)?.cfm\?stid="+r"\d+$"
## Getting the chapter list and the meta data, plus 'is adult' checking.
def extractChapterUrlsAndMetadata(self):
# index=1 makes sure we see the story chapter index. Some
# sites skip that for one-chapter stories.
url = self.url
logger.debug("URL: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
if "We're sorry. This story is not available." in data:
raise exceptions.FailedToDownload(self.getSiteDomain() +" says: This story is not available.")
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data)
# print data
# Now go hunting for all the meta data and the chapter list.
## Title
a = soup.find('h2', {'id':'page_heading'})
self.story.setMetadata('title',stripHTML(a))
# Find the chapters: chapter_view.cfm?stid=6663&amp;spordinal=1"
for chapter in soup.findAll('a', href=re.compile(r'chapter_view.cfm\?stid='+self.story.getMetadata('storyId')+"&spordinal=\d+$")):
# just in case there's tags, like <i> in chapter titles.
self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/stories/'+chapter['href']))
self.story.setMetadata('numChapters',len(self.chapterUrls))
self.story.setMetadata('numWords', soup.find('tr', {'class':'foot'}).findAll('td')[1].text)
self.setDescription(url,soup.find('div', {'id':'summary'}))
# <span class="label">Rated:</span> NC-17<br /> etc
info = soup.find('div', {'id':'storyinformation'})
labels=info.findAll('b')
for labelspan in labels:
value = labelspan.nextSibling
label = labelspan.string
if 'Completion' in label:
if 'Complete' in value.string:
self.story.setMetadata('status', 'Completed')
else:
self.story.setMetadata('status', 'In-Progress')
if 'Rating' in label:
self.story.setMetadata('rating', value.string)
if 'Era:' in label:
self.story.addToList('category',value.string)
if 'Genre' in label:
self.story.addToList('genre',value.string)
labels=info.findAll('strong')
for labelspan in labels:
value = labelspan.nextSibling
label = labelspan.string
if 'Author' in label:
value=value.nextSibling
self.story.setMetadata('authorId',value['href'].split('=')[1])
self.story.setMetadata('authorUrl','http://'+self.host+'/'+value['href'])
self.story.setMetadata('author',value.string)
if 'Post' in label:
self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
if 'Updated:' in label:
self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
for char in soup.findAll('a', href=re.compile(r"/resources/bios_view.cfm\?scid=\d+")):
self.story.addToList('characters',stripHTML(char))
# grab the text for an individual chapter.
def getChapterText(self, url):
logger.debug('Getting chapter text from: %s' % url)
soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
div = soup.find('div', {'class' : 'block chapter'})
if None == div:
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
return self.utf8FromSoup(url,div)
+1 -1
View File
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2012 Fanficdownloader team
# Copyright 2012 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
+21 -1
View File
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -98,6 +98,26 @@ class HPFandomNetAdapterAdapter(BaseSiteAdapter): # XXX
# Now go hunting for all the meta data and the chapter list.
# set first URL
a = soup.find('a', href=re.compile(r"viewstory.php\?sid=\d+"))
self._setURL('http://' + self.getSiteDomain() + '/eff/'+a['href'])
if self.parsedUrl.query.split('=',)[1] != self.story.getMetadata('storyId'):
self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
url = self.url
logger.debug("reset URL: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data)
# self.story.setMetadata('storyId', re.compile(self.getSiteURLPattern()).match(a).group('storyId'))
# Find authorid and URL from... author url.
a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
self.story.setMetadata('authorId',a['href'].split('=')[1])
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2012 Fanficdownloader team
# Copyright 2012 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
+1 -1
View File
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2013 Fanficdownloader team
# Copyright 2013 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
+1 -1
View File
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2012 Fanficdownloader team
# Copyright 2012 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -0,0 +1,46 @@
# -*- coding: utf-8 -*-
# Copyright 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
# Software: eFiction
import re
from base_efiction_adapter import BaseEfictionAdapter
class ItCouldHappenNetSiteAdapter(BaseEfictionAdapter):
@staticmethod
def getSiteDomain():
return 'it-could-happen.net'
@classmethod
def getSiteAbbrev(seluuf):
return 'ich'
@classmethod
def getDateFormat(self):
return "%B %d, %Y"
def handleMetadataPair(self, key, value):
# This site is all one 'category' as it's usually defined and
# uses Category for what is usually genre.
if key == 'Categories':
for val in re.split("\s*,\s*", value):
self.story.addToList('genre', val)
else:
super(ItCouldHappenNetSiteAdapter, self).handleMetadataPair(key, value)
def getClass():
return ItCouldHappenNetSiteAdapter
+1 -1
View File
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
+14 -225
View File
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -16,236 +16,25 @@
#
# Software: eFiction
import time
import logging
logger = logging.getLogger(__name__)
import re
import urllib2
from base_efiction_adapter import BaseEfictionAdapter
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
class LibraryOfMoriaComAdapter(BaseEfictionAdapter):
from base_adapter import BaseSiteAdapter, makeDate
def getClass():
return LibraryOfMoriaComAdapter
# Class name has to be unique. Our convention is camel case the
# sitename with Adapter at the end. www is skipped.
class LibraryOfMoriaComAdapter(BaseSiteAdapter):
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.decode = ["Windows-1252",
"utf8"] # 1252 is a superset of iso-8859-1.
# Most sites that claim to be
# iso-8859-1 (and some that claim to be
# utf8) are really windows-1252.
self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
self.password = ""
self.is_adult=False
# get storyId from url--url validation guarantees query is only sid=1234
self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
# normalized story URL.
self._setURL('http://' + self.getSiteDomain() + '/a/viewstory.php?sid='+self.story.getMetadata('storyId'))
# Each adapter needs to have a unique site abbreviation.
self.story.setMetadata('siteabbrev','lom')
# The date format will vary from site to site.
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
self.dateformat = "%B %d, %Y"
@staticmethod # must be @staticmethod, don't remove it.
@staticmethod
def getSiteDomain():
# The site domain. Does have www here, if it uses it.
return 'www.libraryofmoria.com'
@classmethod
def getSiteExampleURLs(cls):
return "http://"+cls.getSiteDomain()+"/a/viewstory.php?sid=1234"
def getPathToArchive(self):
return '/a'
def getSiteURLPattern(self):
return re.escape("http://"+self.getSiteDomain()+"/a/viewstory.php?sid=")+r"\d+$"
@classmethod
def getSiteAbbrev(seluuf):
return 'lom'
@classmethod
def getDateFormat(self):
return "%B %d, %Y"
## Getting the chapter list and the meta data, plus 'is adult' checking.
def extractChapterUrlsAndMetadata(self):
if self.is_adult or self.getConfig("is_adult"):
addurl = "&ageconsent=ok&warning=3"
else:
addurl=""
# index=1 makes sure we see the story chapter index. Some
# sites skip that for one-chapter stories.
url = self.url+addurl
logger.debug("URL: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
m = re.search(r"'viewstory.php\?sid=\d+((?:&amp;ageconsent=ok)?&amp;warning=\d+)'",data)
if m != None:
if self.is_adult or self.getConfig("is_adult"):
# We tried the default and still got a warning, so
# let's pull the warning number from the 'continue'
# link and reload data.
addurl = m.group(1)
# correct stupid &amp; error in url.
addurl = addurl.replace("&amp;","&")
url = self.url+'&index=1'+addurl
logger.debug("URL 2nd try: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
else:
raise exceptions.AdultCheckRequired(self.url)
if "Access denied. This story has not been validated by the adminstrators of this site." in data:
raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data)
# print data
# Now go hunting for all the meta data and the chapter list.
## Title
a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
self.story.setMetadata('title',stripHTML(a))
# Find authorid and URL from... author url.
a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
self.story.setMetadata('authorId',a['href'].split('=')[1])
self.story.setMetadata('authorUrl','http://'+self.host+'/a/'+a['href'])
self.story.setMetadata('author',a.string)
# Find the chapters:
for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
# just in case there's tags, like <i> in chapter titles.
self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/a/'+chapter['href']+addurl))
self.story.setMetadata('numChapters',len(self.chapterUrls))
# eFiction sites don't help us out a lot with their meta data
# formating, so it's a little ugly.
# utility method
def defaultGetattr(d,k):
try:
return d[k]
except:
return ""
# <span class="label">Rated:</span> NC-17<br /> etc
labels = soup.findAll('span',{'class':'label'})
for labelspan in labels:
value = labelspan.nextSibling
label = labelspan.string
if 'Summary' in label:
## Everything until the next span class='label'
svalue = ""
while not defaultGetattr(value,'class') == 'label':
svalue += str(value)
value = value.nextSibling
self.setDescription(url,svalue)
#self.story.setMetadata('description',stripHTML(svalue))
if 'Rated' in label:
self.story.setMetadata('rating', value)
if 'Word count' in label:
self.story.setMetadata('numWords', value)
if 'Categories' in label:
cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
catstext = [cat.string for cat in cats]
for cat in catstext:
self.story.addToList('category',cat.string)
if 'Characters' in label:
chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
charstext = [char.string for char in chars]
for char in charstext:
self.story.addToList('characters',char.string)
if 'Type' in label:
genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
for genre in genres:
self.story.addToList('genre',genre.string)
if 'Warning' in label:
warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=5'))
for warning in warnings:
self.story.addToList('warnings',warning.string)
if 'Completed' in label:
if 'Yes' in value:
self.story.setMetadata('status', 'Completed')
else:
self.story.setMetadata('status', 'In-Progress')
if 'Published' in label:
self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
if 'Updated' in label:
# there's a stray [ at the end.
#value = value[0:-1]
self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
try:
# Find Series name from series URL.
a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
series_name = a.string
series_url = 'http://'+self.host+'/a/'+a['href']
# use BeautifulSoup HTML parser to make everything easier to find.
seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
i=1
for a in storyas:
# skip 'report this' and 'TOC' links
if 'contact.php' not in a['href'] and 'index' not in a['href']:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
except:
# I find it hard to care if the series parsing fails
pass
# grab the text for an individual chapter.
def getChapterText(self, url):
logger.debug('Getting chapter text from: %s' % url)
soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
div = soup.find('div', {'id' : 'story'})
if None == div:
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
return self.utf8FromSoup(url,div)
def getClass():
return LibraryOfMoriaComAdapter
+1 -1
View File
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2013 Fanficdownloader team
# Copyright 2013 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2014 Fanficdownloader team
# Copyright 2014 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -0,0 +1,719 @@
# -*- coding: utf-8 -*-
# Copyright 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
import bs4
import datetime
import logging
import re
import urllib2
from ..htmlcleanup import removeEntities, stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, makeDate
_logger = logging.getLogger(__name__)
def getClass():
"""Returns adapter class defined in this module."""
return MassEffect2InAdapter
class ParsingError(Exception):
"""Indicates an error while parsing web page content."""
def __init__(self, message):
Exception.__init__(self)
self.message = message
def __str__(self):
return self.message
class MassEffect2InAdapter(BaseSiteAdapter):
"""
Provides support for MassEffect2.in site as story source.
Can be used as a template for sites build upon Ucoz.com engine (until no base class extracted).
Specializations:
1) Russian content (date format, genre names, etc.);
2) original `E.R.A.T.I.N.G.' rating scale, used by masseffect2.in
and some affiliated sites, denoted with images;
3) editor signatures an an option to remove them.
"""
WORD_PATTERN = re.compile(u'\w+', re.UNICODE)
DOCUMENT_ID_PATTERN = re.compile(u'\d+-\d+-\d+-\d+')
SITE_LANGUAGE = u'Russian'
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.decode = ["utf8"]
self.story.setMetadata('siteabbrev', 'me2in')
self.story.setMetadata('storyId', self._getDocumentId(self.url))
self._setURL(self._makeDocumentUrl(self.story.getMetadata('storyId')))
self._chapters = {}
self._parsingConfiguration = None
# Must be @staticmethod, not @classmethod!
@staticmethod
def getSiteDomain():
return 'www.masseffect2.in'
@classmethod
def getSiteExampleURLs(cls):
return u' '.join([cls._makeDocumentUrl('19-1-0-1234'),
cls._makeDocumentUrl('24-1-0-4321')])
def getSiteURLPattern(self):
return re.escape(self._makeDocumentUrl('')) + self.DOCUMENT_ID_PATTERN.pattern
def use_pagecache(self):
"""Allows use of downloaded page cache. It is essential for this
adapter, because the site does not offers chapter URL list, and many
pages have to be fetched and parsed repeatedly."""
return True
def extractChapterUrlsAndMetadata(self):
"""Extracts chapter URLs and story metadata. Actually downloads all
chapters, which is not exactly right, but necessary due to technical
limitations of the site."""
def followChapters(starting, forward=True):
if forward:
url = starting.getNextChapterUrl()
else:
url = starting.getPreviousChapterUrl()
if url:
url = self._makeDocumentUrl(self._getDocumentId(url))
following = self._makeChapter(url)
# Do not follow links to related, but different stories (prequels or sequels).
if not following.isFromStory(starting.getHeading()):
return
if forward:
yield following
for chapter in followChapters(following, forward):
yield chapter
if not forward:
yield following
try:
startingChapter = self._makeChapter(self.url)
except urllib2.HTTPError, error:
if error.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
raise
# We only have one date for each chapter and assume the oldest one
# to be publication date and the most recent one to be update date.
datePublished = datetime.datetime.max
dateUpdated = datetime.datetime.min
wordCount = 0
# We aim at counting chapters, not chapter parts.
chapterCount = 0
storyInProgress = False
chapters = \
list(followChapters(startingChapter, forward=False)) + \
[startingChapter] + \
list(followChapters(startingChapter, forward=True))
headings = [chapter.getHeading() for chapter in chapters]
largestCommonPrefix = _getLargestCommonPrefix(*headings)
prefixLength = len(largestCommonPrefix)
storyTitleEnd, chapterTitleStart = prefixLength, prefixLength
match = re.search(u'[:\.\s]*(?P<chapter>глава\s+)?$', largestCommonPrefix, re.IGNORECASE | re.UNICODE)
if match:
storyTitleEnd -= len(match.group())
label = match.group('chapter')
if label:
chapterTitleStart -= len(label)
storyTitle = largestCommonPrefix[:storyTitleEnd]
self.story.setMetadata('title', storyTitle)
garbagePattern = re.compile(u'(?P<start>^)?[:\.\s]*(?(start)|$)', re.UNICODE)
indexPattern = re.compile(u'(?:глава\s)?(?:(?<!\d)(?P<index>\d{1,3})(?=\D|$))', re.IGNORECASE | re.UNICODE)
for chapter in chapters:
url = chapter.getUrl()
self._chapters[url] = chapter
_logger.debug(u"Processing chapter `%s'.", url)
try:
authorName = chapter.getAuthorName()
if authorName:
self.story.extendList('author', [authorName])
authorId = chapter.getAuthorId()
if authorId:
authorUrl = 'http://%s/index/%s' % (self.getSiteDomain(), authorId)
else:
authorId = u''
authorUrl = u''
self.story.extendList('authorId', [authorId])
self.story.extendList('authorUrl', [authorUrl])
if not self.story.getMetadata('rating'):
ratingTitle = chapter.getRatingTitle()
if ratingTitle:
self.story.setMetadata('rating', ratingTitle)
if not self.story.getMetadata('description'):
summary = chapter.getSummary()
if summary:
self.story.setMetadata('description', summary)
datePublished = min(datePublished, chapter.getDate())
dateUpdated = max(dateUpdated, chapter.getDate())
self.story.extendList('genre', chapter.getGenres())
self.story.extendList('characters', chapter.getCharacters())
self.story.extendList('ships', chapter.getPairings())
wordCount += self._getWordCount(chapter.getTextElement())
# Chapter status usually represents the story status, so we want the last chapter status.
# Some chapters may have no status attribute.
chapterInProgress = chapter.isInProgress()
if chapterInProgress is not None:
storyInProgress = chapterInProgress
# If any chapter is adult, consider the whole story adult.
if chapter.isAdult():
self.story.setMetadata('is_adult', True)
warning = chapter.getWarning()
if warning:
self.story.extendList('warnings', [warning])
chapterTitle = re.sub(garbagePattern, u'', chapter.getHeading()[chapterTitleStart:])
match = re.search(indexPattern, chapterTitle)
if match:
index = int(match.group('index'))
chapterCount = max(chapterCount, index)
else:
chapterCount += 1
self.chapterUrls.append((chapterTitle, url))
except ParsingError, error:
raise exceptions.FailedToDownload(u"Failed to download chapter `%s': %s" % (url, error))
# Some metadata are handled separately due to format conversions.
self.story.setMetadata('status', 'In Progress' if storyInProgress else 'Completed')
self.story.setMetadata('datePublished', datePublished)
self.story.setMetadata('dateUpdated', dateUpdated)
self.story.setMetadata('numWords', str(wordCount))
self.story.setMetadata('numChapters', chapterCount)
# Site-specific metadata.
self.story.setMetadata('language', self.SITE_LANGUAGE)
def getChapterText(self, url):
"""Grabs the text for an individual chapter."""
if url not in self._chapters:
raise exceptions.FailedToDownload(u"No chapter `%s' present!" % url)
chapter = self._chapters[url]
return self.utf8FromSoup(url, chapter.getTextElement())
def _makeChapter(self, url):
"""Creates a chapter object given a URL."""
document = self.make_soup(self._fetchUrl(url))
chapter = Chapter(self._getParsingConfiguration(), url, document)
return chapter
def _getWordCount(self, element):
"""Returns word count in plain text extracted from chapter body."""
text = stripHTML(element)
count = len(re.findall(self.WORD_PATTERN, text))
return count
def _getParsingConfiguration(self):
if not self._parsingConfiguration:
self._parsingConfiguration = {}
adultRatings = self.getConfigList('adult_ratings')
if not adultRatings:
raise exceptions.PersonalIniFailed(
u"Missing `adult_ratings' setting", u"MassEffect2.in", u"?")
adultRatings = set(adultRatings)
self._parsingConfiguration['adultRatings'] = adultRatings
ratingTitleDescriptions = self.getConfigList('rating_titles')
if ratingTitleDescriptions:
ratingTitles = {}
for ratingDescription in ratingTitleDescriptions:
parts = ratingDescription.split(u'=')
if len(parts) < 2:
_logger.warning(
u"Invalid `rating_titles' setting, missing `=' in `%s'."
% ratingDescription)
continue
labels = parts[:-1]
title = parts[-1]
for label in labels:
ratingTitles[label] = title
# Duplicate label aliasing in adult rating set.
if label in adultRatings:
adultRatings.add(*labels)
self._parsingConfiguration['adultRatings'] = list(adultRatings)
self._parsingConfiguration['ratingTitles'] = ratingTitles
else:
raise exceptions.PersonalIniFailed(
u"Missing `rating_titles' setting", u"MassEffect2.in", u"?")
self._parsingConfiguration['excludeEditorSignature'] = \
self.getConfig('exclude_editor_signature', False)
return self._parsingConfiguration
def _getDocumentId(self, url):
"""Extract document ID from MassEffect2.in URL."""
match = re.search(self.DOCUMENT_ID_PATTERN, url)
if not match:
raise ValueError(u"Failed to extract document ID from `'" % url)
documentId = url[match.start():match.end()]
return documentId
@classmethod
def _makeDocumentUrl(cls, documentId):
"""Make a chapter URL given a document ID."""
return 'http://%s/publ/%s' % (cls.getSiteDomain(), documentId)
class Chapter(object):
"""Represents a lazily-parsed chapter of a story."""
def __init__(self, configuration, url, document):
self._configuration = configuration
self._url = url
self._document = document
# Lazy-loaded:
self._heading = None
self._date = None
self._author = None
self._attributes = None
self._textElement = None
self._infoBar = None
def getHeading(self):
return self._extractHeading()
def getSummary(self):
attributes = self.__getAttributes()
if 'summary' in attributes:
return attributes['summary']
def getAuthorId(self):
author = self._getAuthor()
if author:
return author['id']
def getAuthorName(self):
author = self._getAuthor()
if author:
return author['name']
def getDate(self):
return self.__getDate()
def getRatingTitle(self):
attributes = self.__getAttributes()
if 'rating' in attributes:
return attributes['rating']['title']
def isAdult(self):
attributes = self.__getAttributes()
if 'rating' in attributes and attributes['rating']['isAdult']:
return True
if 'warning' in attributes:
return True
return False
def getWarning(self):
attributes = self.__getAttributes()
if 'warning' in attributes:
return attributes['warning']
def getCharacters(self):
return self._getListAttribute('characters')
def getPairings(self):
return self._getListAttribute('pairings')
def getGenres(self):
return self._getListAttribute('genres')
def isInProgress(self):
attributes = self.__getAttributes()
if 'isInProgress' in attributes:
return attributes['isInProgress']
def getUrl(self):
return self._url
def getTextElement(self):
return self._getTextElement()
def getPreviousChapterUrl(self):
"""Download chapters following `Previous chapter' links.
Returns a list of chapters' URLs."""
return self._getSiblingChapterUrl({'class': 'fl tal'})
def getNextChapterUrl(self):
"""Download chapters following `Next chapter' links.
Returns a list of chapters' URLs."""
return self._getSiblingChapterUrl({'class': 'tar fr'})
def isFromStory(self, storyTitle, prefixThreshold=-1):
"""Check if this chapter is from a story different from the given one.
Prefix threshold specifies how long common story title prefix shall be
for chapters from one story: negative value means implementation-defined
optimum, zero inhibits the check, and positive value adjusts threshold."""
def getFirstWord(string):
match = re.search(u'^\s*\w+', string, re.UNICODE)
return string[match.start():match.end()]
thisStoryTitle = self.getHeading()
if prefixThreshold != 0:
if prefixThreshold < 0:
prefixThreshold = min(
len(getFirstWord(storyTitle)), len(getFirstWord(thisStoryTitle)))
else:
prefixThreshold = min(
prefixThreshold, len(storyTitle), len(thisStoryTitle))
result = len(_getLargestCommonPrefix(storyTitle, thisStoryTitle)) >= prefixThreshold
return result
else:
return storyTitle != thisStoryTitle
def _getListAttribute(self, name):
"""Return an attribute value as a list or an empty list if the attribute is absent."""
attributes = self.__getAttributes()
if name in attributes:
return attributes[name]
return []
def _extractHeading(self):
"""Extract header text from the document."""
return stripHTML(
self._document.find('div', {'class': 'eTitle'}).string)
def __getHeading(self):
"""Lazily parse and return heading."""
if not self._heading:
self._heading = self._extractHeading()
return self._heading
def _getAuthor(self):
"""Lazily parse and return author's information."""
if not self._author:
self._author = self._parseAuthor()
return self._author
def _parseAuthor(self):
"""Locate and parse chapter author's information to a dictionary with author's `id' and `name'."""
try:
authorLink = self._getInfoBarElement() \
.find('i', {'class': 'icon-user'}) \
.findNextSibling('a')
except AttributeError:
raise ParsingError(u'Failed to locate author link.')
match = re.search(u'(8-\d+)', authorLink['onclick'])
if not match:
raise ParsingError(u'Failed to extract author ID.')
authorId = match.group(0)
authorName = stripHTML(authorLink.text)
return {
'id': authorId,
'name': authorName
}
def __getDate(self):
"""Lazily parse chapter date."""
if not self._date:
self._date = self._parseDate()
return self._date
def _parseDate(self):
"""Locate and parse chapter date."""
try:
dateText = self._getInfoBarElement() \
.find('i', {'class': 'icon-eye'}) \
.findPreviousSibling(text=True) \
.strip(u'| \n')
except AttributeError:
raise ParsingError(u'Failed to locate date.')
date = makeDate(dateText, '%d.%m.%Y')
return date
def _getInfoBarElement(self):
"""Locate informational bar element, containing chapter date and author, on the page."""
if not self._infoBar:
self._infoBar = self._document.find('td', {'class': 'eDetails2'})
if not self._infoBar:
raise ParsingError(u'No informational bar found.')
return self._infoBar
def __getAttributes(self):
"""Lazily parse attributes."""
if not self._attributes:
self._attributes = self._parseAttributes()
return self._attributes
def _parseAttributes(self):
"""Parse chapter attribute block and return it as a dictionary with standard entries."""
attributes = {}
attributesText = u''
try:
starter = self._document \
.find('div', {'class': 'comm-div'}) \
.findNextSibling('div', {'class': 'cb'})
bound = starter.findNextSibling('div', {'class': 'cb'})
def processElement(element):
"""Return textual representation an *inline* element of chapter attribute block."""
result = u''
if isinstance(element, bs4.Tag):
if element.name in ('b', 'strong', 'font', 'br'):
result += u"\n"
if element.name == 's':
result += u"<s>%s</s>" % stripHTML(element)
else:
result += stripHTML(element)
else:
result += removeEntities(element)
return result
elements = starter.nextSiblingGenerator()
for element in elements:
if isinstance(element, bs4.Tag):
if element == bound:
break
else:
if element.name in ('div', 'p'):
attributesText += u"\n"
for child in element.childGenerator():
attributesText += processElement(child)
continue
attributesText += processElement(element)
elements = starter.nextGenerator()
for element in elements:
if isinstance(element, bs4.Tag):
if element == bound:
break
elif element.name == 'img':
rating = self._parseRatingFromImage(element)
if rating:
attributes['rating'] = rating
break
except AttributeError or TypeError:
raise ParsingError(u'Failed to locate and collect attributes.')
separators = u"\r\n :;."
freestandingText = u''
for line in attributesText.split(u'\n'):
if line.count(u':') != 1:
freestandingText += line
continue
key, value = line.split(u':', 1)
key = key.strip(separators).lower()
value = value.strip().strip(separators)
parsed = self._parseAttribute(key, value)
for parsedKey, parsedValue in parsed.iteritems():
attributes[parsedKey] = parsedValue
freestandingText = freestandingText.strip()
if 'summary' not in attributes and freestandingText:
attributes['summary'] = freestandingText
if 'rating' not in attributes:
_logger.warning(u"Failed to locate or recognize rating for `%s'!", self.getUrl())
return attributes
# Most, but not all, URLs of rating icons match this.
RATING_LABEL_PATTERN = re.compile(u'/(?P<rating>[ERATINnG]+)\.png$')
def _parseRatingFromImage(self, element):
"""Given an image element, try to parse story rating from it."""
# Although deprecated, `has_key()' is required here.
if not element.has_attr('src'):
return
source = element['src']
if 'REITiNG' in source:
match = re.search(self.RATING_LABEL_PATTERN, source)
if not match:
return
label = match.group('rating')
if label in self._configuration['ratingTitles']:
return {
'label': label,
'title': self._configuration['ratingTitles'][label],
'isAdult': label in self._configuration['adultRatings']
}
else:
_logger.warning(u"No title found for rating label `%s'!" % label)
# TODO: conduct a research on such abnormal URLs.
elif source == 'http://www.masseffect2.in/_fr/10/1360399.png':
label = 'Nn'
return {
'label': 'Nn',
'title': self._configuration['ratingTitles'][label],
'isAdult': label in self._configuration['adultRatings']
}
# Various `et cetera' and `et al' forms in Russian texts.
# Intended to be used with whole strings!
ETC_PATTERN = re.compile(
u'''[и&]\s(?:
(?:т\.?\s?[пд]?\.?)|
(?:др(?:угие|\.)?)|
(?:пр(?:очие|\.)?)|
# Note: identically looking letters `K' and `o'
# below are from Latin and Cyrillic alphabets.
(?:ко(?:мпания)?|[KК][oо°])
)$
''',
re.IGNORECASE + re.UNICODE + re.VERBOSE)
# `Author's Notes' and its variants in Russian.
ANNOTATION_PATTERN = re.compile(u'аннотация|описание|(?:(?:за|при)мечание\s)?(?:от\s)?автора', re.UNICODE)
def _parseAttribute(self, key, value):
"""
Parse a single a single record in chapter attributes for chapter metadata.
Return a dictionary of canonical attributes and values (i. e. multiple attributes may be discovered).
"""
def refineCharacter(name):
"""Refines character name from stop-words and distortions."""
strippedName = name.strip()
nameOnly = re.sub(self.ETC_PATTERN, u'', strippedName)
# TODO: extract canonical name (even ME-specific?).
canonicalName = nameOnly
return canonicalName
if re.match(u'жанры?', key, re.UNICODE):
genres = filter(bool, map(unicode.strip, re.split(u'[,;/]', value)))
return {'genres': genres}
elif key == u'статус':
isInProgress = value == u'в процессе'
return {'isInProgress': isInProgress}
elif key == u'персонажи':
participants = map(refineCharacter, re.split(u'[,;]', value))
characters = []
pairings = []
for participant in participants:
if u'/' in participant:
pairings.append(participant)
else:
characters.append(participant)
return {
'characters': characters,
'pairings': pairings
}
elif key == u'предупреждение':
return {'warning': value}
elif re.match(self.ANNOTATION_PATTERN, key):
if not value.endswith(u'.'):
value += u'.'
# Capitalize would make value[1:] lowercase, which we don't want.
value = value[:1].upper() + value[1:]
return {'summary': value}
else:
_logger.info(u"Unrecognized attribute `%s' ignored.", key)
return {}
def _getTextElement(self):
"""Locate chapter body text element on the page."""
if not self._textElement:
self._textElement = self.__collectTextElements()
return self._textElement
def __collectTextElements(self):
"""Return all elements containing parts of chapter text (which may be
<p>aragraphs, <div>isions or plain text nodes) under a single root."""
starter = self._document.find('div', {'id': u'article'})
if starter is None:
# FIXME: This will occur if the method is called more than once.
# The reason is elements appended to `root' are removed from the document.
# BS 4.4 implements cloning via `copy.copy()', but supporting it for BS 4.3
# would be error-prone (due to relying on BS internals) and is not needed.
if self._textElement:
_logger.debug(u"You may not call this function more than once!")
raise ParsingError(u'Failed to locate text.')
collection = [starter]
for element in starter.nextSiblingGenerator():
if element is None:
break
if isinstance(element, bs4.Tag) and element.name == 'tr':
break
collection.append(element)
root = bs4.Tag(name='td')
for element in collection:
root.append(element)
if self._configuration['excludeEditorSignature']:
root = self._excludeEditorSignature(root)
return root
def _getSiblingChapterUrl(self, selector):
"""Locate a link to a sibling chapter, either previous or next one, and return its URL."""
block = self._document \
.find('td', {'class': 'eDetails1'}) \
.find('div', selector)
if not block:
return
link = block.find('a')
if not link:
return
return link['href']
# Editor signature always starts with something like this.
SIGNED_PATTERN = re.compile(u'отредактирова(?:но|ла?)[:.\s]', re.IGNORECASE + re.UNICODE)
def _excludeEditorSignature(self, root):
"""Exclude editor signature from within `root' element."""
for textNode in root.findAll(text=True):
if re.match(self.SIGNED_PATTERN, textNode.string):
editorLink = textNode.findNext('a')
if editorLink:
editorLink.extract()
# Seldom editor link has inner formatting, which is sibling DOM-wise.
editorName = textNode.findNext('i')
if editorName:
editorName.extract()
textNode.extract()
# We could try removing container element, but there is a risk
# of removing text ending with it. Better play safe here.
break
return root
def _getLargestCommonPrefix(*args):
"""Returns largest common prefix of all unicode arguments, ignoring case.
:rtype : unicode
"""
from itertools import takewhile, izip
toLower = lambda xs: map(lambda x: x.lower(), xs)
allSame = lambda xs: len(set(toLower(xs))) == 1
return u''.join([i[0] for i in takewhile(allSame, izip(*args))])
+113 -97
View File
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -22,7 +22,6 @@ import re
import urllib
import urllib2
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
@@ -41,29 +40,57 @@ class MediaMinerOrgSiteAdapter(BaseSiteAdapter):
# get storyId from url--url validation guarantees query correct
m = re.match(self.getSiteURLPattern(),url)
urltitle='urltitle'
if m:
self.story.setMetadata('storyId',m.group('id'))
if m.group('id1'):
self.story.setMetadata('storyId',m.group('id1'))
urltitle=m.group('urltitle1')
elif m.group('id2'):
self.story.setMetadata('storyId',m.group('id2'))
urltitle=m.group('urltitle2')
elif m.group('id3'):
self.story.setMetadata('storyId',m.group('id3'))
else:
raise InvalidStoryURL(url,
self.getSiteDomain(),
self.getSiteExampleURLs())
# normalized story URL.
self._setURL('http://' + self.getSiteDomain() + '/fanfic/view_st.php/'+self.story.getMetadata('storyId'))
self._setURL('http://' + self.getSiteDomain() + '/fanfic/s/'+urltitle+'/'+self.story.getMetadata('storyId'))
else:
raise exceptions.InvalidStoryURL(url,
self.getSiteDomain(),
self.getSiteExampleURLs())
# The date format will vary from site to site.
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
self.dateformat = "%B %d, %Y %H:%M"
@staticmethod
def getSiteDomain():
return 'www.mediaminer.org'
@classmethod
def getSiteExampleURLs(cls):
return "http://"+cls.getSiteDomain()+"/fanfic/view_st.php/123456 http://"+cls.getSiteDomain()+"/fanfic/view_ch.php/1234123/123444#fic_c"
return "http://"+cls.getSiteDomain()+"/fanfic/s/story-title/123456 http://"+cls.getSiteDomain()+"/fanfic/c/story-title/chapter-title/123456/987612"
def getSiteURLPattern(self):
## http://www.mediaminer.org/fanfic/view_st.php/76882
## http://www.mediaminer.org/fanfic/view_ch.php/167618/594087#fic_c
return re.escape("http://"+self.getSiteDomain())+\
"/fanfic/view_(st|ch)\.php/"+r"(?P<id>\d+)(/\d+(#fic_c)?)?$"
## old urls
## http://www.mediaminer.org/fanfic/view_st.php/76882
## new urls
## http://www.mediaminer.org/fanfic/s/ghosts-from-the-past/72
## http://www.mediaminer.org/fanfic/c/ghosts-from-the-past/chapter-2/72/174
## http://www.mediaminer.org/fanfic/s/robtech-final-missions/61553
## http://www.mediaminer.org/fanfic/c/robtech-final-missions/robotech-final-missions-oneshot/61553/189830
return re.escape("http://"+self.getSiteDomain())+r"/fanfic/"+\
r"((s/(?P<urltitle1>[^/]+)/(?P<id1>\d+))|"+\
r"((c/(?P<urltitle2>[^/]+)/[^/]+/(?P<id2>\d+))/\d+)|"+\
r"(view_st\.php/(?P<id3>\d+)))"
# Override stripURLParameters so the id parameter won't get stripped
@classmethod
def stripURLParameters(cls, url):
return url
def extractChapterUrlsAndMetadata(self):
@@ -71,23 +98,26 @@ class MediaMinerOrgSiteAdapter(BaseSiteAdapter):
logger.debug("URL: "+url)
try:
data = self._fetchUrl(url)
data = self._fetchUrl(url) # w/o trailing / gets 'chapter list' page even for one-shots.
except urllib2.HTTPError, e:
if e.code == 404:
logger.error("404 on %s"%url)
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data)
soup = self.make_soup(data)
# [ A - All Readers ], strip '[' ']'
## Above title because we remove the smtxt font to get title.
smtxt = soup.find("font",{"class":"smtxt"})
smtxt = soup.find("h3",{"id":"post-rating"})
if not smtxt:
logger.error("can't find rating")
raise exceptions.StoryDoesNotExist(self.url)
rating = smtxt.string[1:-1]
self.story.setMetadata('rating',rating)
else:
rating = smtxt.string[1:-1]
self.story.setMetadata('rating',rating)
# Find authorid and URL from... author url.
a = soup.find('a', href=re.compile(r"/fanfic/src.php/u/\d+"))
@@ -103,41 +133,24 @@ class MediaMinerOrgSiteAdapter(BaseSiteAdapter):
## <td class="ffh">The Kraut, The Bartender, and The Drunkard: Chapter 1</b> <font class="smtxt">[ P - Pre-Teen ]</font></td>
## <td class="ffh">Betrayal and Justice: A Cold Heart</b> <font size="-1">( Chapter 1 )</font> <font class="smtxt">[ A - All Readers ]</font></td>
## <td class="ffh">Question and Answer: Question and Answer</b> <font size="-1">( One-Shot )</font> <font class="smtxt">[ A - All Readers ]</font></td>
title = soup.find('td',{'class':'ffh'})
for font in title.findAll('font'):
font.extract() # removes 'font' tags from inside the td.
if title.has_key('colspan'):
titlet = stripHTML(title)
else:
## No colspan, it's part chapter title--even if it's a one-shot.
titlet = ':'.join(stripHTML(title).split(':')[:-1]) # strip trailing 'Chapter X' or chapter title
self.story.setMetadata('title',titlet)
## The story title is difficult to reliably parse from the
## story pages. Getting it from the author page is, but costs
## another fetch.
# authsoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
# titlea = authsoup.find('a',{'href':'/fanfic/view_st.php/'+self.story.getMetadata('storyId')})
# self.story.setMetadata('title',titlea.text)
# title = soup.find('td',{'class':'ffh'})
# for font in title.findAll('font'):
# font.extract() # removes 'font' tags from inside the td.
# if title.has_attr('colspan'):
# titlet = stripHTML(title)
# else:
# ## No colspan, it's part chapter title--even if it's a one-shot.
# titlet = ':'.join(stripHTML(title).split(':')[:-1]) # strip trailing 'Chapter X' or chapter title
self.story.setMetadata('title',stripHTML(soup.find('h1',{'id':'post-title'})))
# save date from first for later.
firstdate=None
# Find the chapters
select = soup.find('select',{'name':'cid'})
if not select:
self.chapterUrls.append(( self.story.getMetadata('title'),self.url))
else:
for option in select.findAll("option"):
chapter = stripHTML(option.string)
## chapter can be: Chapter 7 [Jan 23, 2011]
## or: Vigilant Moonlight ( Chapter 1 ) [Jan 30, 2004]
## or even: Prologue ( Prologue ) [Jul 31, 2010]
m = re.match(r'^(.*?) (\( .*? \) )?\[(.*?)\]$',chapter)
chapter = m.group(1)
# save date from first for later.
if not firstdate:
firstdate = m.group(3)
self.chapterUrls.append((chapter,'http://'+self.host+'/fanfic/view_ch.php/'+self.story.getMetadata('storyId')+'/'+option['value']))
# Find the chapters - one-shot now have chapter list, too.
chap_p = soup.find('p',{'style':'margin-left:10px;'})
for (atag,aurl,name) in [ (x,x['href'],stripHTML(x)) for x in chap_p.find_all('a') ]:
self.chapterUrls.append((name,'http://'+self.host+aurl))
self.story.setMetadata('numChapters',len(self.chapterUrls))
# category
@@ -146,27 +159,20 @@ class MediaMinerOrgSiteAdapter(BaseSiteAdapter):
self.story.addToList('category',a.string)
# genre
# <a href="/fanfic/src.php/a/567">Ranma 1/2</a>
# <a href="/fanfic/src.php/g/567">Ranma 1/2</a>
for a in soup.findAll('a',href=re.compile(r"^/fanfic/src.php/g/")):
self.story.addToList('genre',a.string)
# if firstdate, then the block below will only have last updated.
if firstdate:
self.story.setMetadata('datePublished', makeDate(firstdate, "%b %d, %Y"))
# Everything else is in <tr bgcolor="#EEEED4">
metastr = stripHTML(soup.find("tr",{"bgcolor":"#EEEED4"})).replace('\n',' ').replace('\r',' ').replace('\t',' ')
# Latest Revision: August 03, 2010
m = re.match(r".*?(?:Latest Revision|Uploaded On): ([a-zA-Z]+ \d\d, \d\d\d\d)",metastr)
metastr = stripHTML(soup.find("div",{"class":"post-meta"}))
# Latest Revision: February 07, 2015 15:21 PST
m = re.match(r".*?(?:Latest Revision|Uploaded On): ([a-zA-Z]+ \d\d, \d\d\d\d \d\d:\d\d)",metastr)
if m:
self.story.setMetadata('dateUpdated', makeDate(m.group(1), "%B %d, %Y"))
if not firstdate:
self.story.setMetadata('datePublished',
self.story.getMetadataRaw('dateUpdated'))
else:
self.story.setMetadata('dateUpdated',
self.story.getMetadataRaw('datePublished'))
self.story.setMetadata('dateUpdated', makeDate(m.group(1), self.dateformat))
# site doesn't give date published on index page.
# set to updated, change in chapters below.
# self.story.setMetadata('datePublished',
# self.story.getMetadataRaw('dateUpdated'))
# Words: 123456
m = re.match(r".*?\| Words: (\d+) \|",metastr)
@@ -192,44 +198,54 @@ class MediaMinerOrgSiteAdapter(BaseSiteAdapter):
logger.debug('Getting chapter text from: %s' % url)
data=self._fetchUrl(url)
soup = bs.BeautifulStoneSoup(data,
selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
data = self._fetchUrl(url)
soup = self.make_soup(data)
anchor = soup.find('a',{'name':'fic_c'})
headerstr = stripHTML(soup.find('div',{'class':'post-meta clearfix '}))
# print("data:%s"%data)
#header.extract()
if None == anchor:
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
## find divs with align=left, those are paragraphs in newer stories.
divlist = anchor.findAllNext('div',{'align':'left'})
if divlist:
for div in divlist:
div.name='p' # convert to <p> mediaminer uses div with
# a margin for paragraphs.
anchor.append(div) # cheat! stuff all the content
# divs into anchor just as a
# holder.
del div['style']
del div['align']
anchor.name='div'
return self.utf8FromSoup(url,anchor)
else:
logger.debug('Using kludgey text find for older mediaminer story.')
## Some older mediaminer stories are unparsable with BeautifulSoup.
## Really nasty formatting. Sooo... Cheat! Parse it ourselves a bit first.
## Story stuff falls between:
data = "<div id='HERE'>" + data[data.find('<a name="fic_c">'):] +"</div>"
soup = bs.BeautifulStoneSoup(data,
selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
for tag in soup.findAll('td',{'class':'ffh'}) + \
soup.findAll('div',{'class':'acl'}) + \
soup.findAll('div',{'class':'footer smtxt'}) + \
soup.findAll('table',{'class':'tbbrdr'}):
tag.extract() # remove tag from soup.
m = re.match(r".*?Uploaded On: ([a-zA-Z]+ \d\d, \d\d\d\d \d\d:\d\d)",headerstr)
if m:
date = makeDate(m.group(1), self.dateformat)
if not self.story.getMetadataRaw('datePublished') or date < self.story.getMetadataRaw('datePublished'):
self.story.setMetadata('datePublished', date)
return self.utf8FromSoup(url,soup)
chapter = soup.find('div',{'id':'fanfic-text'})
return self.utf8FromSoup(url,chapter)
# chapter=self.make_soup('<div class="story"></div>').find('div')
# if None == header:
# raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
# ## find divs with align=left, those are paragraphs in newer stories.
# divlist = header.findAllNext('div',{'align':'left'})
# if divlist:
# for div in divlist:
# div.name='p' # convert to <p> mediaminer uses div with
# # a margin for paragraphs.
# chapter.append(div)
# del div['style']
# del div['align']
# return self.utf8FromSoup(url,chapter)
# else:
# logger.debug('Using kludgey text find for older mediaminer story.')
# ## Some older mediaminer stories are unparsable with BeautifulSoup.
# ## Really nasty formatting. Sooo... Cheat! Parse it ourselves a bit first.
# ## Story stuff falls between:
# data = "<div id='HERE'>" + data[data.find('<div class="adWrap">'):data.find('<div class="addthis_sharing_toolbox">')] +"</div>"
# soup = self.make_soup(data)
# for tag in soup.findAll('td',{'class':'ffh'}) + \
# soup.findAll('div',{'class':'acl'}) + \
# soup.findAll('div',{'class':'adWrap'}) + \
# soup.findAll('div',{'class':'footer smtxt'}) + \
# soup.findAll('table',{'class':'tbbrdr'}):
# tag.extract() # remove tag from soup.
# return self.utf8FromSoup(url,soup)
def getClass():
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2012 Fanficdownloader team
# Copyright 2012 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
+1 -1
View File
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2012 Fanficdownloader team
# Copyright 2012 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
+1 -1
View File
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2012 Fanficdownloader team
# Copyright 2012 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2012 Fanficdownloader team
# Copyright 2012 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
-213
View File
@@ -1,213 +0,0 @@
# -*- coding: utf-8 -*-
# Copyright 2013 Fanficdownloader team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
# Software: eFiction
import time
import logging
logger = logging.getLogger(__name__)
import re
import urllib2
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, makeDate
def getClass():
return NetRaptorOrgAdapter
class NetRaptorOrgAdapter(BaseSiteAdapter):
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.decode = ["Windows-1252",
"utf8"] # 1252 is a superset of iso-8859-1.
# Most sites that claim to be
# iso-8859-1 (and some that claim to be
# utf8) are really windows-1252.
self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
self.password = ""
self.is_adult=False
# get storyId from url--url validation guarantees query is only sid=1234
self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
# normalized story URL.
self._setURL('http://' + self.getSiteDomain() + '/fanfiction/viewstory.php?sid='+self.story.getMetadata('storyId'))
# Each adapter needs to have a unique site abbreviation.
self.story.setMetadata('siteabbrev','netrap')
# The date format will vary from site to site.
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
self.dateformat = "%d/%m/%y"
@staticmethod # must be @staticmethod, don't remove it.
def getSiteDomain():
# The site domain. Does have www here, if it uses it.
return 'netraptor.org'
@classmethod
def getSiteExampleURLs(cls):
return "http://"+cls.getSiteDomain()+"/fanfiction/viewstory.php?sid=1234"
def getSiteURLPattern(self):
return re.escape("http://"+self.getSiteDomain()+"/fanfiction/viewstory.php?sid=")+r"\d+$"
## Getting the chapter list and the meta data, plus 'is adult' checking.
def extractChapterUrlsAndMetadata(self):
url = self.url+'&index=1'
logger.debug("URL: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
if "Access denied. This story has not been validated by the adminstrators of this site." in data:
raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data)
# print data
# Now go hunting for all the meta data and the chapter list.
## Title
pagetitle = soup.find('div',{'id':'pagetitle'})
a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
self.story.setMetadata('title',stripHTML(a))
# Find authorid and URL from... author url.
a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
self.story.setMetadata('authorId',a['href'].split('=')[1])
self.story.setMetadata('authorUrl','http://'+self.host+'/fanfiction/'+a['href'])
self.story.setMetadata('author',a.string)
# Find the chapters:
for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
# just in case there's tags, like <i> in chapter titles.
self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/fanfiction/'+chapter['href']))
self.story.setMetadata('numChapters',len(self.chapterUrls))
# eFiction sites don't help us out a lot with their meta data
# formating, so it's a little ugly.
# utility method
def defaultGetattr(d,k):
try:
return d[k]
except:
return ""
labels = soup.findAll('span',{'class':'label'})
for labelspan in labels:
value = labelspan.nextSibling
label = labelspan.string
if 'Summary' in label:
## Everything until the next span class='label'
svalue = ""
while not defaultGetattr(value,'class') == 'label':
svalue += str(value)
value = value.nextSibling
self.setDescription(url,svalue)
#self.story.setMetadata('description',stripHTML(svalue))
if 'Rated' in label:
self.story.setMetadata('rating', value)
if 'Word count' in label:
self.story.setMetadata('numWords', value)
if 'Categories' in label:
cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
catstext = [cat.string for cat in cats]
for cat in catstext:
self.story.addToList('category',cat.string)
if 'Characters' in label:
chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
charstext = [char.string for char in chars]
for char in charstext:
self.story.addToList('characters',char.string)
if 'Genre' in label:
genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
for genre in genres:
self.story.addToList('genre',genre.string)
if 'Warnings' in label:
warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
for warning in warnings:
self.story.addToList('warnings',warning.string)
if 'Completed' in label:
if 'Yes' in value:
self.story.setMetadata('status', 'Completed')
else:
self.story.setMetadata('status', 'In-Progress')
if 'Published' in label:
self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
if 'Updated' in label:
self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
try:
# Find Series name from series URL.
a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
series_name = a.string
series_url = 'http://'+self.host+'/fanfiction/'+a['href']
# use BeautifulSoup HTML parser to make everything easier to find.
seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
i=1
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
self.story.setMetadata('seriesUrl',series_url)
break
i+=1
except:
# I find it hard to care if the series parsing fails
pass
# grab the text for an individual chapter.
def getChapterText(self, url):
logger.debug('Getting chapter text from: %s' % url)
soup = bs.BeautifulSoup(self._fetchUrl(url))
div = soup.find('div', {'id' : 'story'})
if None == div:
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
return self.utf8FromSoup(url,div)
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
+12 -210
View File
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2012 Fanficdownloader team
# Copyright 2012 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -16,222 +16,24 @@
#
# Software: eFiction
import time
import logging
logger = logging.getLogger(__name__)
import re
import urllib2
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, makeDate
def getClass():
return NHAMagicalWorldsUsAdapter
from base_efiction_adapter import BaseEfictionAdapter
# Class name has to be unique. Our convention is camel case the
# sitename with Adapter at the end. www is skipped.
class NHAMagicalWorldsUsAdapter(BaseSiteAdapter):
class NHAMagicalWorldsUsAdapter(BaseEfictionAdapter):
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.decode = ["Windows-1252",
"utf8"] # 1252 is a superset of iso-8859-1.
# Most sites that claim to be
# iso-8859-1 (and some that claim to be
# utf8) are really windows-1252.
self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
self.password = ""
self.is_adult=False
# get storyId from url--url validation guarantees query is only sid=1234
self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
# normalized story URL.
self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
# Each adapter needs to have a unique site abbreviation.
self.story.setMetadata('siteabbrev','nha')
# The date format will vary from site to site.
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
self.dateformat = " %d/%m/%y"
@staticmethod # must be @staticmethod, don't remove it.
@staticmethod
def getSiteDomain():
# The site domain. Does have www here, if it uses it.
return 'nha.magical-worlds.us'
@classmethod
def getSiteExampleURLs(cls):
return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
def getSiteURLPattern(self):
return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
## Getting the chapter list and the meta data, plus 'is adult' checking.
def extractChapterUrlsAndMetadata(self):
url = self.url
logger.debug("URL: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
m = re.search(r"'viewstory.php\?sid=\d+((?:&amp;ageconsent=ok)?&amp;warning=\d+)'",data)
if m != None:
if self.is_adult or self.getConfig("is_adult"):
# We tried the default and still got a warning, so
# let's pull the warning number from the 'continue'
# link and reload data.
addurl = m.group(1)
# correct stupid &amp; error in url.
addurl = addurl.replace("&amp;","&")
url = self.url+'&index=1'+addurl
logger.debug("URL 2nd try: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
else:
raise exceptions.AdultCheckRequired(self.url)
if "Access denied. This story has not been validated by the adminstrators of this site." in data:
raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data)
# print data
# Now go hunting for all the meta data and the chapter list.
# Find authorid and URL from... author url.
a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
self.story.setMetadata('authorId',a['href'].split('=')[1])
self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
self.story.setMetadata('author',a.string)
asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
try:
# in case link points somewhere other than the first chapter
a = soup.findAll('option')[1]['value']
self.story.setMetadata('storyId',a.split('=',)[1])
url = 'http://'+self.host+'/'+a
soup = bs.BeautifulSoup(self._fetchUrl(url))
except:
pass
for info in asoup.findAll('table', {'width' : '100%', 'bordercolor' : re.compile(r'#')}):
a = info.find('a')
if 'viewstory.php?sid='+self.story.getMetadata('storyId') == a['href'] or \
('viewstory.php?sid='+self.story.getMetadata('storyId')+'&') in a['href']:
self.story.setMetadata('title',stripHTML(a))
break
# Find the chapters:
chapters=soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+'&chapter=\d+$'))
if len(chapters) == 0:
self.chapterUrls.append((self.story.getMetadata('title'),url))
else:
for chapter in chapters:
# just in case there's tags, like <i> in chapter titles.
self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']))
self.story.setMetadata('numChapters',len(self.chapterUrls))
# eFiction sites don't help us out a lot with their meta data
# formating, so it's a little ugly.
# utility method
def defaultGetattr(d):
try:
return d.name
except:
return ""
cats = info.findAll('a',href=re.compile('categories.php'))
for cat in cats:
self.story.addToList('category',cat.string)
a = info.find('a', href=re.compile(r'viewuser.php'))
val = a.nextSibling
svalue = ""
while not defaultGetattr(val) == 'br':
val = val.nextSibling
val = val.nextSibling
while not defaultGetattr(val) == 'br':
svalue += unicode(val)
val = val.nextSibling
self.setDescription(url,svalue)
def getSiteAbbrev(self):
return 'nha'
#does not provide convenient way to get word count
labels = info.findAll('i')
for labelspan in labels:
value = labelspan.nextSibling
label = stripHTML(labelspan)
if 'Rating' in label:
self.story.setMetadata('rating', value.split(' -')[0])
if 'Genres' in label:
genres = value.string.split(', ')
for genre in genres:
if 'None' not in genre:
self.story.addToList('genre',genre.split(' -')[0])
if 'Characters' in label:
chars = value.string.split(', ')
for char in chars:
if 'None' not in char:
self.story.addToList('characters',char.split(' -')[0])
if 'Warnings' in label:
warnings = value.string.split(', ')
for warning in warnings:
if 'None' not in warning:
self.story.addToList('warnings',warning.split(' -')[0])
if 'Completed' in label:
if 'Yes' in value:
self.story.setMetadata('status', 'Completed')
else:
self.story.setMetadata('status', 'In-Progress')
if 'Published' in label:
self.story.setMetadata('datePublished', makeDate(value.split(' -')[0], self.dateformat))
if 'Updated' in label:
# there's a stray [ at the end.
#value = value[0:-1]
self.story.setMetadata('dateUpdated', makeDate(value.split(' -')[0], self.dateformat))
# grab the text for an individual chapter.
def getChapterText(self, url):
logger.debug('Getting chapter text from: %s' % url)
data = self._fetchUrl(url)
soup = bs.BeautifulSoup(data, selfClosingTags=('br','hr','span','center')) # some chapters seem to be hanging up on those tags, so it is safer to close them
story = soup.find('div', {"id" : "story"})
if None == story:
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
@classmethod
def getDateFormat(self):
return "%d/%m/%y"
def getClass():
return NHAMagicalWorldsUsAdapter
return self.utf8FromSoup(url,story)
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2013 Fanficdownloader team
# Copyright 2013 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -0,0 +1,38 @@
# -*- coding: utf-8 -*-
# Copyright 2015 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
# Software: eFiction
import re
from base_efiction_adapter import BaseEfictionAdapter
class NineLivesDarkSolaceAdapter(BaseEfictionAdapter):
@staticmethod
def getSiteDomain():
return 'ninelives.dark-solace.org'
@classmethod
def getSiteAbbrev(self):
return '9lvs'
@classmethod
def getDateFormat(self):
return "%B %d, %Y"
def getClass():
return NineLivesDarkSolaceAdapter
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2012 Fanficdownloader team
# Copyright 2012 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2011 Fanficdownloader team
# Copyright 2011 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2013 Fanficdownloader team
# Copyright 2013 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
# Copyright 2012 Fanficdownloader team
# Copyright 2012 Fanficdownloader team, 2015 FanFicFare team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
@@ -171,7 +171,8 @@ class PonyFictionArchiveNetAdapter(BaseSiteAdapter):
self.story.addToList('warnings',warning.string)
status = soup.find('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
self.story.setMetadata('status',status.string)
if status: # apparently this site can have stories with neither In-Progress or Complete.
self.story.setMetadata('status',status.string)
section = soup.findAll('span', {'class' : 'General'})[1]

Some files were not shown because too many files have changed in this diff Show More