Compare commits

..
Author SHA1 Message Date
Jim Miller 8fb62499cd Remove 'aa' from plugin name, create a new icon. 2011-12-21 18:08:36 -06:00
Jim Miller dbda2f96a6 Plugin improvements: options, copy clipboard as url, save options, etc. 2011-12-21 15:01:18 -06:00
Jim Miller c9a69ff3c8 TTH won't send you future updates if you aren't 'caught up' on the story.
Login isn't required for F21, but logging in will mark stories you've
downloaded as 'read' on tth.
2011-12-20 14:40:05 -06:00
Jim Miller 56ac912706 Rename some files, further improvements--just about usable for new stories only. 2011-12-19 21:18:55 -06:00
Jim Miller b75c9d4946 Refactoring and cleaning up. 2011-12-19 18:04:47 -06:00
Jim Miller cbc8cadd91 First calibre-plugin version with working background downloading. 2011-12-19 14:59:20 -06:00
Jim Miller f634629b98 Check for existing duplicate, other minor improvements. 2011-12-18 19:09:08 -06:00
Jim Miller c0ea637aef Fill calibre metadata directly(vs read from epub), allow other output formats. 2011-12-17 14:56:46 -06:00
Jim Miller 5511b4fd28 Store/use personal.ini, is_adult and user/pass dialogs when needed. 2011-12-16 23:01:18 -06:00
Jim Miller a9fa06fd4d Collect URL, first 'useful' version. Borrowing from GPL v3 code, so not Apache License. 2011-12-16 11:29:36 -06:00
Jim Miller d5c38927fb Add initial version of plugin code--proof of concept stage. 2011-12-16 10:57:40 -06:00
Jim Miller 97e257d22a Begin on a calibre plugin of FFDL while still sharing code with CLI & web. 2011-12-16 10:55:08 -06:00
Jim Miller 6c2f025ca1 Correct post_process_cmd to use shell so it can parse args. 2011-12-16 10:23:17 -06:00
Jim Miller 71981c157f Remove 'use new version' texts. Automerge didn't do what I intended. 2011-12-15 17:50:45 -06:00
Jim Miller 68c9e3cb8e Added tag last_python25 for changeset f41bce05c6ba 2011-12-15 16:58:23 -06:00
Jim Miller dc0a4c2b25 Merging python27 branch back into default(trunk) branch. 2011-12-15 16:56:59 -06:00
Jim Miller 33b15fe7c1 Fix for (past)contrib author in tthfanficorg. Tweak meaning of --force in CLI. 2011-12-15 16:48:24 -06:00
Jim Miller 63faea59d8 Fix for fimfiction.net 'too many values to unpack' error 2011-12-14 15:27:46 -06:00
Jim Miller 8905a08862 Added tag fanficdownloader-4.1.0 for changeset ac4f9f370ee4 2011-12-14 12:49:52 -06:00
Jim Miller 1d1e0899ee Added tag fanficdownloader-4.1.1 for changeset 2d69c1a21b37 2011-12-14 12:49:40 -06:00
Jim Miller 18f26de557 Add post_process_cmd feature for CLI only. 2011-12-14 12:47:03 -06:00
Jim Miller 32bae4c47b Add tthfanfic.org. They have their own ebook downloads, but lack metadata. 2011-12-14 12:07:13 -06:00
Jim Miller 6e41e5d59a Add background_color for html/epub, change notice, bump to 4-1-1. 2011-12-14 11:54:28 -06:00
Jim Miller f9f7c6ea2a Twisting the Hellmouth epubs are .html, not .xhtml. Bump stored version to 4.1. 2011-12-14 11:08:26 -06:00
Jim Miller 9b98cb8cce Warning that AppEngine Python2.7 has a bug fetching large reqs. 2011-11-21 14:07:49 -06:00
Jim Miller 5ba3a36518 Tweak to index now that we have new new URL. 2011-11-15 17:33:09 -06:00
Jim Miller 672cc09b0d Disable r3m0v3rOrphans cron. There's a Python 2.7 runtime bug effecting it. 2011-11-15 11:52:09 -06:00
Jim Miller fed75f6684 Couple tweaks to multithreaded. 2011-11-15 11:28:56 -06:00
Jim Miller be645e012b First attempt at multithreaded python 2.7 version of downloader. 2011-11-09 17:41:15 -06:00
Jim Miller 1cf87eae3a Reduce story save time, increase status check time, add notice about quotas. 2011-11-08 12:50:45 -06:00
althaine 2cd89b2e55 Brought fimfiction.net published date parsing into line with new site layout 2011-11-06 18:59:33 +11:00
Jim Miller a3402170ad whoficcom only - viewstory.php url can appear descs, look for reviews.php. 2011-10-31 11:08:25 -05:00
Jim Miller 141ed90d74 Work around for poorly formatted desc on adastra. Saw error in logs. 2011-10-27 15:00:33 -05:00
Jim Miller 33e520fef1 Added tag fanficdownloader-4.0.6 for changeset c6f4e3562a86 2011-09-25 16:34:57 -05:00
Jim Miller 7e6963bbaf Bump version, add notice about fimfiction.net. 2011-09-25 16:32:56 -05:00
althaine 4a4ec3863d Brought fimfiction.net fic status in line with other adapters 2011-09-26 07:18:06 +10:00
althaine 070096e9cb Added fimfiction.net to index.html
Added fimfiction.net to defaults.ini
Add mature fic handling to fimfiction.net
More robust handling of story descriptions from fimfiction.net
Added 'characters' list
2011-09-25 15:23:06 +10:00
althaine 88bfd4ec58 Added fimfiction.net 2011-09-25 10:39:58 +10:00
Jim Miller c96381a0b4 Added tag fanficdownloader-4.0.5 for changeset ead54adcc041 2011-09-19 17:04:39 -05:00
Jim Miller f9466ef491 Improve CLI config file specification, CLI only. Issue 19. 2011-09-19 17:04:20 -05:00
Jim Miller 8e02856b55 Added tag fanficdownloader-4.0.5 for changeset 61d72dfc9f63 2011-09-15 14:50:06 -05:00
Jim Miller 8d0a29270a Add website_encodings option to change encoding list, add 'auto' as encoding type.
'auto' uses Universal Encoding Detector(http://chardet.feedparser.org/) to
derive encoding.  It spots utf-8 fairly well, but not iso8859-1/windows-1252,
so we require 90+% confidence before using it.
2011-09-15 14:43:12 -05:00
Jim Miller 06920119db Change hpcom to BeautifulSoup vs BeautifulStoneSoup to allow nested div tags. 2011-08-14 19:42:37 -05:00
Jim Miller 75fb648ace Annotate adapter_fanficcastletvnet.py for ease of copying for new sites. 2011-08-12 17:22:29 -05:00
Jim Miller e4ad7edb48 Added tag fanficdownloader-4.0.4 for changeset 8e70741ae507 2011-07-24 11:10:19 -05:00
Jim Miller ca0082797c AppEngine Version 4-0-4. 2011-07-24 11:10:05 -05:00
Jim Miller fe684926b1 Added tag fanficdownloader-4.0.4 for changeset ddec88fac578 2011-07-24 11:08:25 -05:00
Jim Miller f920f505c6 Fix for mediaminer.org genre. 2011-07-24 11:08:04 -05:00
Jim Miller 3ca4447279 Some tweaks for CLI only update feature. Doesn't force file extension anymore. 2011-07-22 17:14:25 -05:00
Jim Miller ac11984c97 Change abbrev for fanfic.castletv.net. 2011-07-14 19:54:27 -05:00
Jim Miller 09f3f62792 Add fanfic.castletv.net to index.html. 2011-07-14 19:41:48 -05:00
Jim Miller eefdaf8518 Add fanfic.castletv.net. 2011-07-14 18:13:24 -05:00
Jim Miller 0e7a211ce9 Running at 94% of available space used. Decrease save time to 6 days. 2011-07-04 12:20:02 -05:00
Jim Miller 9863616eae Improve ffnet error checking. 2011-06-20 14:24:21 -05:00
Jim Miller 5afd7b8c06 Check for and report errors in User Configuration. 2011-06-15 13:07:48 -05:00
Jim Miller 0e7ef6d804 Different Age Consent text in tenhawkpresents.com 2011-06-14 15:15:56 -05:00
Jim Miller 2a154c13ac Add fanfiction.tenhawkpresents.com. 2011-06-14 15:11:00 -05:00
Jim Miller 24120a73e7 Added tag fanficdownloader-4.0.3 for changeset efa536795df8 2011-06-12 16:26:22 -05:00
Jim Miller fddd146b39 Refactorings/tweaks from Update Feature work that are worthwhile even without it. 2011-06-12 16:26:05 -05:00
Jim Miller 8bf22729fe CLI downloader can update existing epubs, pull only metadata or chapter range.
epubmerge provides a lot of the grunt work for updates.
2011-06-09 19:07:43 -05:00
sigizmund e202105248 Adding Google +1 button to see how it goes. Minor static fixes. 2011-06-08 22:18:25 +01:00
Jim Miller 4f0ce05006 Added tag fanficdownloader-4.0.2 for changeset fbf33a024a38 2011-06-07 20:12:32 -05:00
Jim Miller 57534c26c5 My fix for ffnet latest update chapters broke m. mobile support. Fixed. 2011-06-07 20:12:11 -05:00
Jim Miller df3b95aa6f Added tag fanficdownloader-4.0.2 for changeset 2d6980d864a9 2011-06-07 19:50:01 -05:00
Jim Miller fd2d4a935d Bump to 4-0-2 primarily for new download version for ffnet/fpcom fix. 2011-06-07 19:49:49 -05:00
Jim Miller 71ae63e1ea Update index, remove new version notice, put ffnet/fpcom notice. 2011-06-07 14:26:31 -05:00
Jim Miller 2a353a74f9 Make ffnet/fpcom use BeautifulSoup (not Stone) for nested divs. 2011-06-07 14:19:25 -05:00
Jim Miller aa629c2c39 Merge ffnet/fpcom, make both use URL given to pull meta/chap list to avoid
missing latest chapter due to out of date servers.
2011-06-07 13:00:39 -05:00
Jim Miller 520a295f88 Try both utf8 and windows-1252 (order depends on adapter), then strip non-ascii
characters entirely if both fail.
2011-06-05 16:49:35 -05:00
Jim Miller 951bc3b030 Put orphan search in cron--it works now. Not that there were any. 2011-06-03 22:38:30 -05:00
Jim Miller 09d37c4426 Use cursor saved in memcache to search for orphan chunks. Smaller, ordered
search doesn't work because ids are not increasing.
2011-06-03 22:09:59 -05:00
Jim Miller b76e812eaa Orphan search exceeds queued task DB timeout as well. Use smaller search
like the regular cleanup and leave manual instead of cron.
2011-06-03 21:07:02 -05:00
Jim Miller ecabbd3af2 Use task queue for orphan chunk clean up. 2011-06-03 20:40:40 -05:00
Jim Miller 152ee61ed4 Now I remember why cleanup was limited--task timeout. Basic reverted to 100
each time, but still by time not day, orphan search will have to become a queue
task--unscheduled for now.
2011-06-03 20:12:04 -05:00
Jim Miller f2283a2052 Improve download cleanup, add orphan chunk cleanup, add recent list clear,
improve mediaminer no such story detect.
2011-06-03 20:03:14 -05:00
Jim Miller fb5740c549 Install hook to make urlfetch deadline 10s, add limited retry on fetch error. 2011-06-02 16:10:19 -05:00
Jim Miller 7133189601 Added tag fanficdownloader-4.0.1 for changeset 265d84461442 2011-06-02 12:35:37 -05:00
Jim Miller 6d24caee1e Tweak status.html and test1.com. 2011-06-02 12:35:13 -05:00
Jim Miller 583275f037 Added tag fanficdownloader-4.0.1 for changeset 01d49b13cc3c 2011-05-30 23:02:16 -05:00
Jim Miller 50b80b6d68 4-0-1 Add mobi back in, changes to recent&status appearance, more reliability. 2011-05-30 23:02:00 -05:00
Jim Miller f7857ad6dc Suppress warnings about Django version. 2011-05-30 15:48:35 -05:00
Jim Miller a3f75cb3eb Improve error handling/reporting, make redownloads appear at top of recent list. 2011-05-30 15:05:00 -05:00
Jim Miller 94063d478c Pass normalized URL to queue task, not original url. 2011-05-30 09:59:37 -05:00
Jim Miller f25eae83d3 Save corrected URL in DownloadMeta record so status & recent have good URL. 2011-05-29 21:21:02 -05:00
Jim Miller 433e371b74 Enable (www|m). for fictionpress.com, like ff.net. 2011-05-29 17:03:02 -05:00
Jim Miller def2937327 Save appengine version in DownloadMeta to aid troubleshooting. 2011-05-29 13:07:12 -05:00
Jim Miller e99adf3fa9 Allow trailing / after /Story_Title on ff.net, fp.com urls. 2011-05-29 10:44:46 -05:00
Jim Miller a05bf24ed3 Fix typo that prevented some proper fictionpress.com urls from working. 2011-05-28 21:28:54 -05:00
Jim Miller aa58f1c1ee Make much more forgiving of inexact URLs--that's most of our errors now. 2011-05-28 16:09:34 -05:00
Jim Miller 35aeae59f2 Tweaking logging slightly. 2011-05-27 20:43:36 -05:00
Jim Miller 6d5785a5ac Added tag fanficdownloader-4.0.0 for changeset 3dbb4938aead 2011-05-23 18:33:56 -05:00
Jim Miller 07fbb8c5d5 Bring 4.0.0 branch into trunk. 2011-05-23 18:26:24 -05:00
Jim Miller ac74918005 Make this default appengine version, downloader.py honors -f, remove extratags from default title page. 2011-05-23 17:36:56 -05:00
Jim Miller b85a5ab95b Include announcement of new version. 2011-05-23 17:35:24 -05:00
Jim Miller 215552af00 Strip html tags and entities from epub chapter titles. 2011-05-20 09:56:53 -05:00
Jim Miller 7f0c989319 Reduce logging level of normal system exceptions. 2011-05-19 20:36:19 -05:00
Jim Miller d38360be6b Fix zip output file name. 2011-05-19 17:30:41 -05:00
Jim Miller bf52020876 Bump html output title size back up to h1. 2011-05-19 10:35:41 -05:00
Jim Miller 58b95af0da Fixes for various problems found during testing, remove old files. Beta ready. 2011-05-16 12:38:42 -05:00
Jim Miller df9e877865 Fixes to various from first round testing and some code clean up. 2011-05-13 21:34:58 -05:00
Jim Miller a88d4cac50 Support for fictionalley.org, add feature to not overwrite files newer than last
update, fix to config section precedence, consolidate date parsing a bit.
2011-05-11 22:44:18 -05:00
Jim Miller 756b6944fc Support for mediaminer.org, update copyrights. 2011-05-11 12:29:59 -05:00
Jim Miller 6d2f657729 Support for thewriterscoffeeshop.com, allow both login/pass and Are Adult in one site. 2011-05-10 13:26:34 -05:00
Jim Miller 9b2450a609 Support for twiwrite.net, potionsandsnitches.com & harrypotterfanfiction.com. 2011-05-09 21:20:06 -05:00
Jim Miller 36d4b9afcf Add adastrafanfic.com support and support to confirm adult w/o login/pass. 2011-05-09 14:46:05 -05:00
Jim Miller d90c9ebced Support for ficwad.com. Further tweaks/improvments, especially to user config.
(I'm getting a bit carried away with making things configurable, honestly.)
2011-05-08 21:53:06 -05:00
Jim Miller ecd1690b70 Add fictionpress.com adapter, some more tweak/fixes. 2011-05-07 15:14:46 -05:00
Jim Miller 87a57cc286 Add (partial) CLI options, fixes to site editconfig. 2011-05-07 12:51:03 -05:00
Jim Miller d91f2e74fd Only ask for Login/Password when required. Save and use user configuration. 2011-05-06 20:33:54 -05:00
Jim Miller d3b1ddcda9 Added tag fanficdownloader-3.0.2 for changeset 564ada569d46 2011-05-06 19:59:04 -05:00
Jim Miller a7b80388dd Merge changes from trunk to 4-0 branch. 2011-05-06 13:00:32 -05:00
Jim Miller 9515ff00be Tweak output a bit, allow any 'entry' as epub subject. 2011-05-06 12:42:20 -05:00
sigizmund 605c4c40fc Mis-aligned ad block 2011-05-06 12:00:50 +01:00
sigizmund 3e1f0dd53b Fixing screwed Google Analytics tracking code. I don't know how, but it nearly disappeared and our impressions went down from 250+ a day to around 30. 2011-05-06 11:24:27 +01:00
Jim Miller 0e28d86a7b Fix for zip files, status in epub. 2011-05-05 20:47:39 -05:00
Jim Miller 94669a2179 Fix up exception handling, first working appengine(SDK) version. 2011-05-04 17:54:36 -05:00
Jim Miller 547411666d Move CLI up a level to match appengine, change module packaging to suit.
Change mechanism for loading adapters to avoid problems with module init.
Move adapter exceptions to own file.
2011-05-04 14:29:24 -05:00
Jim Miller 150316f460 Commit first version of reorg/rewrite. Currently CLI only. 2011-05-03 11:27:58 -05:00
Jim Miller f75abaad72 3-0-2 Add convert link feature. Remove title page table(for convert). Make favicon.ico work. 2011-05-02 13:54:48 -05:00
Jim Miller bdaea79875 Previous change to elim newlines in debug sometimes output breaks download.
Cheap fix, comment out debugs.
2011-05-02 13:12:16 -05:00
Jim Miller 7420d27652 More log clean up, better handling of bad URL in ficwad, missing story in ffnet. 2011-04-26 17:22:51 -05:00
Jim Miller 1426626d0a Strip leading newline so it doesn't (falsely) show up in appengine logs as error. 2011-04-25 19:57:40 -05:00
Jim Miller 666e9666cd Attempting to help with ffnet failures. Increase fetch deadline, add retries with backoff, 1/2 sleep.
Also remove <> from error message--HTML eats it.
2011-04-22 17:03:43 -05:00
Jim Miller 1c2c1a5d62 Add support for twiwrite.net. Requires User/Pass like twilighted.net. 2011-04-20 22:34:59 -05:00
Jim Miller 7c5aaa36d5 Save recent downloads longer(5 days, was 2). Fix some redirects.
Reduces log errors and makes auto-re-login more transparent.
2011-04-20 17:32:30 -05:00
sigizmund 13b96946d1 Improving logging, can dump the data which was downloaded if download fails. 2011-04-19 12:49:37 +01:00
sigizmund 1119ba52a0 Replaced ad block 2011-04-18 11:07:56 +01:00
Jim Miller b058477b97 Fix so recent, but pre-compress mobis will still download. 2011-04-03 16:55:51 -05:00
Jim Miller 1f303013bd Fix to allow retrying, compress mobi chunks, Working/Finished/Failed in status.html title, keep 3 days worth. 2011-04-03 16:47:08 -05:00
Jim Miller 302a8f12a3 Removing storage for old version. Fixes for whofic meta data. 2011-04-01 22:14:05 -05:00
retiefjimm 3e381dd33f Still tweaking the clean up cron. 2011-03-24 22:09:11 -05:00
retiefjimm bd82311d51 Mobi improvements: Mark TOC so reader can find it, don't let reader eat every 4096th char, don't prettify. Remove debug outputs from whofic. Increase fetch size of remover. 2011-03-24 12:57:38 -05:00
retiefjimm efb521c829 Added tag fanficdownloader-0.5 for changeset 0f08ff79de17 2011-03-22 19:45:47 -05:00
retiefjimm 925324bd13 Improved (but not perfected) mobi file output. Reduce cron clean up time to 2 days. 2011-03-22 19:17:41 -05:00
retiefjimm 1d1ed1ef71 Add support for www.whofic.com. 2011-03-22 19:11:17 -05:00
retiefjimm 389fc010f2 After merging QueueProc changes, tweaks clean up cron times and change appspot instance name. 2011-03-22 12:59:12 -05:00
Jim Miller 5ab5991d6e Merging QueueProc changes to trunk. 2011-03-22 12:48:17 -05:00
retiefjimm 8c606e45fd Remove 2 sec sleep before making live version. 2011-03-17 17:03:25 -05:00
retiefjimm e645c054d8 adastrafanfic can have chapters with tags (<i>) in them. Allow get as well as post. 2011-03-15 14:49:16 -05:00
retiefjimm e6ebd956f8 Datastore max size is 1,000,000, not 1M(=2^20). 2011-03-10 14:30:42 -06:00
retiefjimm ef5e7700b9 Back out some changes I didn't actually mean to commit. Just some custom stuff. 2011-03-10 13:14:51 -06:00
retiefjimm 53e2a0f204 First version with background queue processing and support for stories >1M. 2011-03-10 13:00:11 -06:00
retiefjimm 0e9d992e13 Make Branch for conversion to Queue Processing. 2011-03-04 11:58:53 -06:00
retiefjimm 790aca39da Add epubmerge.py, a standalone CLI program to merge multiple epubs together into one. 2011-02-24 18:02:49 -06:00
retiefjimm 7064873b4e Put title, author and publisher into mobi files properly as meta data. Also strips non-ascii chars from t,a,p--caused problems with mobi gen.
Calibre's book reader cannot read the mobi files produced from fanficdownloader, either before or after these changes.
2011-01-23 13:37:29 -06:00
retiefjimm 95e7ba636d Add commas to word counts. 2011-01-15 10:41:28 -06:00
sigizmund fe557bbce5 Fixed downloading mobi from fdown 2011-01-03 20:35:15 +00:00
retiefjimm 783a614345 Enable collection of user's own user/password again. Only used by twilighted.net. 2010-12-27 11:29:12 -06:00
retiefjimm a32ccf7dac Work around an SGMLParser/BeautifulStoneSoup entity bug--incorrectly inserts (;) when it shouldn't, "AT&T" becomes "AT&T;". Also update to latest BeautifulSoup: has one minor, unrelated change. 2010-12-19 12:21:55 -06:00
retiefjimm d3abfbf5d6 Add Star Trek fanfic site adastrafanfic.com, plus add filename(linenum) to logger output for CLI. 2010-12-13 23:31:35 -06:00
retiefjimm d95c72f447 Split info line in ffnet by ' - ' instead of just '-' so Sci-Fi doesn't become just 'Sci'. fpcom already does. 2010-12-08 17:40:10 -06:00
retiefjimm e05749678e Move status->subject into output.py as per Bill's suggestion. 2010-12-06 15:03:07 -06:00
retiefjimm f7d94105ee Correct example URL. 2010-12-05 21:40:04 -06:00
retiefjimm 50b0573033 Add status (In-Progress or Completed) to metadata as a Subject tag. 2010-12-05 21:38:16 -06:00
wsuetholz 48b882c745 2 second sleep was in Mediaminer as well. 2010-12-05 21:21:44 -06:00
wsuetholz 3fdd079b97 Merge with 8d1772310e5c4ad1772a92b1f0408952b0b370e2 2010-12-05 20:58:38 -06:00
wsuetholz e674f7c7df There was still a 2 second sleep between chapters for the fictonpress adapter.. Keep in mind that if you do a lot of downloading from fanfiction.net or fictionpress.com it is possible that your IP address could be locked without the sleep in place. 2010-12-05 20:52:13 -06:00
retiefjimm 8f58164dde Added tag fanficdownloader-0.4 for changeset f23fd0e4cbc3 2010-12-02 17:36:52 -06:00
wsuetholz 4c99fdbcc1 Removed some leftover functions that were left from using ffnet.py as a base for fpcom.py and mediaminer.py. 2010-11-30 15:17:00 -06:00
wsuetholz c6b79cb57b Changed the "Title Page" reference in the TOC and CONTENT epub files to be title_page instead. 2010-11-30 15:11:20 -06:00
wsuetholz f114a2438e This one might be controversial..
Since none of the EBook readers are really for update-able stories I added tags/subjects in for Last Update Year/Month and Last Update, which at least in FBReader I can order by, and see all stories updated for a certain month, or a certain date.  This will let you know to reread the story.
2010-11-30 14:06:12 -06:00
wsuetholz 2f0bb31e24 Take out adding the id: field as a subject. 2010-11-30 13:56:18 -06:00
wsuetholz 30455bfda2 Updated the processing for fictionpress.com of the information line to correctly extract the Updated and Published dates, and the Completion status 2010-11-30 12:13:00 -06:00
wsuetholz cfb218f21e Moved the check for a completed story higher in the code, this makes the continue's that are in that portion of the if statement not skip that check. 2010-11-29 18:45:47 -06:00
retiefjimm 617dc21eb9 Kludge fix for uniode in story descs in appengine. 2010-11-27 17:32:31 -06:00
retiefjimm 2d7f6c2e5c Correct story status for ficwad, change story status for fictionalley to 'Unknown' (site doesn't tell us status), change mobi file output mode to 'wb'(binary) so it works on windows. 2010-11-26 19:36:53 -06:00
sigizmund 719aed32a9 Tiny static changes - preparing for doing some SEO 2010-11-26 15:55:04 +00:00
retiefjimm ccef466090 Change no-class div tags to p tags in mediaminer stories to get paragraph breaks. 2010-11-24 12:36:38 -06:00
sigizmund 708f750bab Added Mobipocket support to the Web UI 2010-11-24 09:37:49 +00:00
retiefjimm 3b0a2639e7 Merge because Hg is insistent. 2010-11-23 12:53:27 -06:00
retiefjimm edb4f5a3bd Change a couple of the example story URLs. 2010-11-23 12:49:57 -06:00
retiefjimm f3571959df Change a couple of the example story URLs. 2010-11-23 12:42:33 -06:00
sigizmund ebcce7e42d Adding Mobi format and making final configuration changes before uploading a beta version. 2010-11-23 07:15:18 +00:00
retiefjimm cf0d1bf09b Change output names for web version, make html & text output work for CLI version. 2010-11-22 20:05:58 -06:00
retiefjimm ecdeef4b3b Add new adapters to main.py, update verbiage on index, replace a couple prints with logging.debug. 2010-11-22 15:00:00 -06:00
retiefjimm dd483db783 Move books directory down into sub dir next to CLI. 2010-11-22 13:24:50 -06:00
sigizmund 348786f073 cvreating a special tag so we can quickly restore to previous version 2010-11-22 07:06:29 +00:00
sigizmund 5549786946 Adding AppEngine files under the source control, moving downloaded code one directory deeper. 2010-11-22 07:04:17 +00:00
retiefjimm f584b3f1e8 Change calls for str() to unicode(). Default CL type to epub if not given. 2010-11-21 11:52:11 -06:00
retiefjimm df6b85b723 Fix desc escaping. <sigh> 2010-11-18 23:34:25 -06:00
wsuetholz 26f6ddabd9 The with call is not an automatic in python 2.5, you need to import with_statement for it to work.
the from __future__ import with_statement needs to be the first import statment as well.
2010-11-18 20:08:55 -06:00
wsuetholz 22d0989d0a Raise exceptions instead of an exit when errors are detected.
Added static functions to the writer classes that contain the type name and type extension to use when writing out the destination file.
Added a function to the zipdir that will check the date the fic was last updated in the current archive of a fic against the current last updated date and return whether the fic is newer then the archive file.  This is not useful at this time for when this is running under appEngine.
Added a flag to indicate if the program is running from appEngine or not.
2010-11-18 16:07:58 -06:00
retiefjimm 9b6fdb4540 Fix numeric entities--correctly this time. Reduce margins slightly, tweak description escaping slightly. 2010-11-18 14:26:16 -06:00
wsuetholz e3b4769bfb Misspelled the return variable from getOutputFileName. 2010-11-16 09:09:26 -06:00
wsuetholz 5618d8036b MediaMiner was not sending the date with the correct timezone info, so strip it off. We don't need the time anyways. 2010-11-13 23:30:47 -06:00
wsuetholz dbec6c95b2 Changed to deal with somebody putting in the mobile url for fanfiction.net... ie <http://m.fanfiction.net/s/11> will get changed to <http://www.fanfiction.net/s/11> 2010-11-12 21:51:46 -06:00
wsuetholz c77498e6ea Some changes in order to allow the refactoring of functions to work from within the appEngine. 2010-11-12 21:28:25 -06:00
wsuetholz 99ba1b48aa The getSubjects function was returning the author. 2010-11-12 20:27:17 -06:00
wsuetholz bdf429b41c Added in mediaminer.org adapter. Still has problems becaue mm seems to use the &#8820; type character encoding, and I couldn't manage to replace them. 2010-11-12 20:25:55 -06:00
wsuetholz 981a922d00 Deal with being passed in the first chapter as the url. 2010-11-11 13:53:48 -06:00
wsuetholz b51dd549f5 self.numChapters was one too many. 2010-11-11 13:22:30 -06:00
wsuetholz 35065593af Refactored source code to remove redundant code.. Moved most of the adapter get and set functions for variables into the adapter.py. Define all the adapter variables in adapter.py. Remove the unneeded functions from the various adapter sources.
Fix a couple of problems with fpcom.py.  Rearrange the Genre and Category for some of the adapters.
2010-11-11 13:14:15 -06:00
wsuetholz 696223a456 Added in an adapter for FictionPress.com. This started out as a copy of ffnet.py, but the extractIndividualUrls rapidly became completly different. I have not found a field that says total number of words for the story. 2010-11-11 09:55:37 -06:00
wsuetholz 30b914788c Add a new adapter for the potionsandsnitches web site. Once we started looking for the additional information for the title page, things were sufficiently different from the twilighted adapter that it couldn't be used anymore. 2010-11-10 23:11:08 -06:00
wsuetholz ed4ff4b6ab Trying to fix outputting some utf-8 text. Added the utf-8 header to all the source code.
Ended up modifying the removeEntities function to do a weird decode/encode step on the text passed in.  This seems to at least stop things from crashing..
2010-11-10 13:47:13 -06:00
wsuetholz 3f40df82dd Change to allow a chapter url to be passed in, yet still get the information it needs from the story index page. This will get the chapter links from the passed in url. 2010-11-10 12:36:21 -06:00
wsuetholz 7c252e83a1 It seems that self.numWords and self.numChapters can on occasion be numeric instead of string, so use the str() function when building the string for the title page. 2010-11-10 12:34:25 -06:00
wsuetholz d4c18fe1a8 Changed all references to downaloder.py to downloader.py. 2010-11-10 11:29:17 -06:00
wsuetholz b2ea9c3e73 Changed the title page generation to allow for easily adding and removing entries from the table of information shown.
Modified ffnet.py to use the mangled story title if given instead of the name portion of the URL.  As part of this, the Name and chapter number are now optional in the URL passed in.
2010-11-10 11:18:48 -06:00
wsuetholz 33d1fabd11 Changeset Tag Branch User Date Summary
53:c93e07566456			wsuetholz	2010-11-10 10:11	Ficwad wants you to login in order to view some stories..  They old ficwad.py got around that by starting with the first chapter instead of the story index page.  Since I needed the story index page I had changed it to switch to that page, and then scrape the chapter information from there, which doesn't work if the chapters are blocked.  While it still won't work if you pass in the URL for the story index page, I now switch back to the page that you passed in originally when looking for the chapters to download..  The one problem I have with this, is I change the self.url to the story index page, which should probably remain so that we have a consistent self.url even if the user starts with chapter 9 this time instead of chapter 1.
2010-11-10 10:18:46 -06:00
retiefjimm c326aa47b0 Need to reverse sort entities list to get entities with ';' ahead of versions without. Like '&quot;' and '&quot'. Otherwise '&quot;' becomes '";'. 2010-11-09 23:02:33 -06:00
wsuetholz d67668de23 Changes to the format of the title page. Tried to fix the description field on the title page and the contents.opf page. 2010-11-09 18:20:37 -06:00
wsuetholz 363c211401 Had left in a debugging statements that should have been removed.. 2010-11-09 18:18:42 -06:00
wsuetholz 379efc34f1 Add a title page to the resulting EPUB file. This required scraping more information from the web pages in order to populate the new fields. This change includes a change to the way that the output.py uses the adapters. It now gets passed in the adapter and then calls functions from the adapter in order to retrieve the scraped information. This will make it easier down the road when adding more information, or even pictures. 2010-11-09 16:35:46 -06:00
retiefjimm 778deaea00 Replace the haphazardly collected set of html entities with a list of known (browser) supported entities. Will now preserve right/left quotes. 2010-10-28 17:29:00 -05:00
retiefjimm 33c3f0b4fd Added tag fanficdownloader-0.2 for changeset 3eff15bceebe 2010-10-20 15:02:11 -05:00
retiefjimm 5bca3106df Adding a twipassword.py and a quick readme.txt. 2010-10-20 14:58:48 -05:00
retiefjimm c056ed0740 Fix zip routine so it checks for file mimetype doesn't just assume it exists. 2010-10-16 11:30:09 -05:00
retiefjimm 25cbab225c potionsandsnitches.net doesn't require login. Indeed, it doesn't even have the same login URL. 2010-10-14 12:42:29 -05:00
retiefjimm 4e53481d7d Somewhat kludgey fix for the kludgey way we extract the story text from fictionalley for stories with poor html. 2010-10-13 00:01:24 -05:00
retiefjimm b9a72d372d Add &#x0000; entity support, fix "<authorname> aa" from testing, add potionsandsnitches.net. 2010-10-11 20:44:19 -05:00
retiefjimm 7f8d7a7dbb Add '\n' after each </p> and <br /> tag. Extremely long(200k+) single line chapters (like ffnet gives) causes problems for nook.
Also removed a little dead code from ffnet.py.
2010-10-11 14:05:57 -05:00
retiefjimm dafa33c64e Generalize handling of &#<number>; entities. Generalize method to create a valid filename.
Remove print from fictionalley.py that was causing the output-before-302-header issue.
Some changes to chapter URL formation due to apparent differences in handling '//' in URLs in appengine vs downalod.py in 2.5.2.
2010-10-10 12:54:41 -05:00
retiefjimm 275a1dd6ad Add &#039;->'\'' to entity translation list. 2010-10-08 21:54:35 -05:00
retiefjimm f8701a9e8d Fix to force mimetype file to be uncompressed and first in epub. Tested on Python 2.5.2. 2010-10-08 18:46:03 -05:00
retiefjimm 466d5f4ee3 Remove Entities, fix bar ampersands in story & author names. 2010-10-06 14:31:21 -05:00
retiefjimm ca4b09d69d Fixes for some obscure encoding errors. UTF8 versions of apostrophe and dash in story titles & chapter titles could cause problems in a few places. 2010-10-03 19:23:39 -05:00
retiefjimm f75910ce7d Stop doing prettify on the HTML, it sometimes introduces extraneous white space. Change the chapter file names and ids inside the metadata to sequential chapter0001 rather than base64 of the chapter title. Replace invalid center & u tags with div styled centered and span styled underlined. Remove dead ffa.py file. Change downloda.py to not call ffa.py, but do call fictionalley. 2010-09-30 21:33:58 -05:00
retiefjimm 773ff3c03c Improved metadata for epubcheck, fixed a problem I introduced with &gt;/&lt;. 2010-09-29 21:32:04 -05:00
retiefjimm 9434431c7b Add twilighted.net(not com) to downaloder.py so it actually *works*. Add one-shot support for twilighted.net. 2010-09-28 19:52:30 -05:00
retiefjimm 3be9b3331e Replace &#XXX; entities in file names, allow BR tags--some stories use multiple BRs are section breaks. 2010-09-28 19:26:19 -05:00
retiefjimm 84fea5b896 Fictionalley.com working, also add twilighted.com to downaloder.py. 2010-09-28 19:26:06 -05:00
retiefjimm fe67201f95 Fix up code for harrypotterfanfiction.com so it works and add one-shot support. Add &nbsp; &lt; and &gt; to entities list. 2010-09-28 13:26:49 -05:00
retiefjimm ccb3fb36c5 Allow '&amp;' and '&pound;'. Allow single chapter/one-shot stories from FicWad. Correct story names from FicWad. Stop creating empty 'Story Index' chapter in stories from FicWad. Exit on chapter d/l error from FicWad. 2010-09-26 19:08:49 -05:00
Jimm 31c68ff796 Exit on ff.net error downloading chapter. Replace ':' with '_' in file name for html output, too. 2010-09-25 11:55:31 -05:00
retiefjimm 950807747c Replace ':' in filename with '_' for Windoze. appspot version appears to already do this. 2010-09-25 00:44:56 -05:00
retiefjimm b22d961e73 Allow one-shot fics for ffnet.
Write epub files as mode 'b' binary so it works on Windows.
Allow hr tags in epub output.
Don't compress file mimetype in epub file--required by standard.
2010-09-24 23:36:05 -05:00
sigizmund 2b2e7d52ec Starting to use source control again after a long break :-) 2010-07-17 14:44:14 +01:00
sigizmund 48d561de1a Fixed multiline ff.net 2009-12-21 13:40:11 +00:00
sigizmund 1740e0da48 Changes while moving to AJAX service 2009-12-21 13:12:47 +00:00
sigizmund ed9e2992c0 hpfiction added - not yet working 2009-12-18 18:57:53 +00:00
sigizmund c123e77221 somemerges 2009-12-18 18:56:44 +00:00
sigizmund 5143a2187a fictionpress.com support added 2009-12-18 18:55:57 +00:00
sigizmund 1f897843e0 Whole lot of fixes related to appengine 2009-12-18 14:51:53 +00:00
sigizmund ef97755ed3 AppEngine version. Not quite clear is it working or n ot 2009-12-18 12:26:23 +00:00
sigizmund 33855b7877 zipdir with in-memory stuff added 2009-12-18 11:40:29 +00:00
sigizmund 615228a2ac changed slightly to make it work with AppEngine 2009-12-18 11:23:37 +00:00
sigizmund 028c2df521 Fixed a problem with &#[digits]; for fanfiction.net. Just why BeautifulSoup cannot handle them? 2009-12-17 15:32:05 +00:00
sigizmund 2352ba6dfc forgot about html_constants 2009-12-17 15:18:31 +00:00
sigizmund 59697f1a75 Added adapter.py, now all working adapters must implement FanfictionSiteAdapter interface 2009-12-17 15:16:51 +00:00
sigizmund a01e0e2ed6 Fixed few problems, including the slash in filename 2009-12-17 14:37:31 +00:00
sigizmund 8c621d6a59 Small bug in ff.net parsing was fixed 2009-12-17 13:44:07 +00:00
sigizmund f55e6d3c05 epub zip is now produced correctly, also TOC works with Stanza now 2009-12-17 13:37:13 +00:00
sigizmund d2d183430d small changes to make work on other machines. why there's no Python 2.6 on Ubuntu? 2009-12-17 12:53:59 +00:00
sigizmund 6e73e5dc11 login_password again 2009-12-17 12:46:06 +00:00
sigizmund fd2ccb30ff login_password 2009-12-17 12:45:12 +00:00
sigizmund 41caae6226 fanfiction.net support added 2009-12-17 12:38:34 +00:00
kirillov 5adcf131b3 fanfiction.net support added 2009-12-17 12:38:15 +00:00
sigizmund bcf82e2632 zipdir added 2009-12-17 11:34:15 +00:00
sigizmund 259c0f3650 sample change 2009-12-17 11:30:23 +00:00
sigizmund 861d1561d9 test change 2009-12-17 11:29:10 +00:00
sigizmund 6ef95c634d FFA changed, architecture changed, not quite ready yet 2009-12-17 11:26:55 +00:00
sigizmund a9748061f0 minor changes 2009-12-15 15:26:45 +00:00
sigizmund c0459faa43 added 2009-12-15 15:23:48 +00:00
43 changed files with 1232 additions and 216 deletions
+17 -8
View File
@@ -1,20 +1,22 @@
# fanfictionloader ffd-retief
application: fanfictionloader
version: 4-0-7
runtime: python
# ffd-retief-hrd fanfictiondownloader
application: ffd-retief-hrd
version: 4-1-1
runtime: python27
api_version: 1
threadsafe: true
handlers:
- url: /r3m0v3r.*
script: utils/remover.py
script: utils.remover.app
login: admin
- url: /tally.*
script: utils/tally.py
script: utils.tally.app
login: admin
- url: /fdownloadtask
script: main.py
script: main.app
login: admin
- url: /css
@@ -31,7 +33,14 @@ handlers:
upload: static/favicon\.ico
- url: /.*
script: main.py
script: main.app
builtins:
- datastore_admin: on
libraries:
- name: django
version: "1.2"
- name: PIL
version: "1.1.7"
+90
View File
@@ -0,0 +1,90 @@
#!/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, Jim Miller'
__docformat__ = 'restructuredtext en'
# The class that all Interface Action plugin wrappers must inherit from
from calibre.customize import InterfaceActionBase
class InterfacePluginDemo(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
specified in the actual_plugin field below.
The reason for having two classes is that it allows the command line
calibre utilities to run without needing to load the GUI libraries.
'''
name = 'FanFictionDownLoader Plugin'
description = 'UI plugin to download FanFiction stories from various sites.'
supported_platforms = ['windows', 'osx', 'linux']
author = 'Jim Miller'
version = (1, 0, 0)
minimum_calibre_version = (0, 7, 53)
# action_menu_clone_qaction = True
#: 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.fanfictiondownloader_plugin.ffdl_plugin:FanFictionDownLoaderPlugin'
def is_customizable(self):
'''
This method must return True to enable customization via
Preferences->Plugins
'''
return True
def config_widget(self):
'''
Implement this method and :meth:`save_settings` in your plugin to
use a custom configuration dialog.
This method, if implemented, must return a QWidget. The widget can have
an optional method validate() that takes no arguments and is called
immediately after the user clicks OK. Changes are applied if and only
if the method returns True.
If for some reason you cannot perform the configuration at this time,
return a tuple of two strings (message, details), these will be
displayed as a warning dialog to the user and the process will be
aborted.
The base class implementation of this method raises NotImplementedError
so by default no user configuration is possible.
'''
# It is important to put this import statement here rather than at the
# top of the module as importing the config class will also cause the
# GUI libraries to be loaded, which we do not want when using calibre
# from the command line
from calibre_plugins.fanfictiondownloader_plugin.config import ConfigWidget
return ConfigWidget()
def save_settings(self, config_widget):
'''
Save the settings specified by the user with config_widget.
:param config_widget: The widget returned by :meth:`config_widget`.
'''
config_widget.save_settings()
# Apply the changes
ac = self.actual_plugin_
if ac is not None:
ac.apply_settings()
# For testing, run from command line with this:
# calibre-debug -e __init__.py
#
if __name__ == '__main__':
from PyQt4.Qt import QApplication
from calibre.gui2.preferences import test_widget
app = QApplication([])
test_widget('Advanced', 'Plugins')
+11
View File
@@ -0,0 +1,11 @@
FanFictionDownLoader Plugin
===========================
http://code.google.com/p/fanficdownloader/
Created by Jim Miller, borrowing heavily from
Kovid Goyal's 'The InterfacePlugin Demo' and
Grant Drake's 'Count Pages' plugins.
Requires calibre >= 0.7.53
+95
View File
@@ -0,0 +1,95 @@
#!/usr/bin/env python
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from __future__ import (unicode_literals, division, absolute_import,
print_function)
__license__ = 'GPL v3'
__copyright__ = '2011, Jim Miller'
__docformat__ = 'restructuredtext en'
from PyQt4.Qt import (QWidget, QVBoxLayout, QHBoxLayout, QLabel, QLineEdit, QTextEdit,
QComboBox, QCheckBox)
from calibre.utils.config import JSONConfig
from calibre_plugins.fanfictiondownloader_plugin.dialogs import (OVERWRITE, ADDNEW, SKIP)
# This is where all preferences for this plugin will be 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
prefs = JSONConfig('plugins/fanfictiondownloader_plugin')
# Set defaults
prefs.defaults['personal.ini'] = get_resources('example.ini')
prefs.defaults['updatemeta'] = True
prefs.defaults['fileform'] = 'epub'
prefs.defaults['collision'] = OVERWRITE
class ConfigWidget(QWidget):
def __init__(self):
QWidget.__init__(self)
self.l = QVBoxLayout()
self.setLayout(self.l)
horz = QHBoxLayout()
label = QLabel('Default Output &Format:')
horz.addWidget(label)
self.fileform = QComboBox(self)
self.fileform.addItem('epub')
self.fileform.addItem('mobi')
self.fileform.addItem('html')
self.fileform.addItem('txt')
self.fileform.setCurrentIndex(self.fileform.findText(prefs['fileform']))
self.fileform.setToolTip('Choose output format to create. May set default from plugin configuration.')
label.setBuddy(self.fileform)
horz.addWidget(self.fileform)
self.l.addLayout(horz)
horz = QHBoxLayout()
label = QLabel('Default On &Collision?')
label.setToolTip("What to do if there's already an existing story with the same title and author.")
horz.addWidget(label)
self.collision = QComboBox(self)
self.collision.addItem(OVERWRITE)
self.collision.addItem(ADDNEW)
self.collision.addItem(SKIP)
self.collision.setCurrentIndex(self.collision.findText(prefs['collision']))
self.collision.setToolTip('Overwrite will replace the existing story. Add New will create a new story with the same title and author.')
label.setBuddy(self.collision)
horz.addWidget(self.collision)
self.l.addLayout(horz)
horz = QHBoxLayout()
horz.addStretch(1)
self.updatemeta = QCheckBox('Default Update &Metadata?',self)
self.updatemeta.setToolTip('Update metadata for story in Calibre from web site?')
horz.addWidget(self.updatemeta)
self.updatemeta.setChecked(prefs['updatemeta'])
self.l.addLayout(horz)
self.label = QLabel('personal.ini:')
self.l.addWidget(self.label)
self.ini = QTextEdit(self)
self.ini.setLineWrapMode(QTextEdit.NoWrap)
self.ini.setText(prefs['personal.ini'])
self.l.addWidget(self.ini)
def save_settings(self):
prefs['fileform'] = unicode(self.fileform.currentText())
prefs['collision'] = unicode(self.collision.currentText())
prefs['updatemeta'] = self.updatemeta.isChecked()
ini = unicode(self.ini.toPlainText())
if ini:
prefs['personal.ini'] = ini
else:
# if they've removed everything, clear it so they get the
# default next time.
del prefs['personal.ini']
+253
View File
@@ -0,0 +1,253 @@
#!/usr/bin/env python
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from __future__ import (unicode_literals, division,
print_function)
__license__ = 'GPL v3'
__copyright__ = '2011, Jim Miller'
__docformat__ = 'restructuredtext en'
from PyQt4.Qt import (QDialog, QMessageBox, QVBoxLayout, QHBoxLayout, QGridLayout,
QPushButton, QProgressDialog, QString, QLabel, QCheckBox,
QTextEdit, QLineEdit, QInputDialog, QComboBox, QClipboard,
QProgressDialog, QTimer, QApplication )
from calibre.gui2 import error_dialog, warning_dialog, question_dialog, info_dialog
from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader import adapters,writers,exceptions
OVERWRITE='Overwrite'
ADDNEW='Add New'
SKIP='Skip'
class DownloadDialog(QDialog):
def __init__(self, gui, prefs, icon, do_user_config, start_downloads):
QDialog.__init__(self, gui)
self.gui = gui
self.do_user_config = do_user_config
self.start_downloads = start_downloads
self.setMinimumWidth(300)
self.l = QVBoxLayout()
self.setLayout(self.l)
self.setWindowTitle('FanFictionDownLoader')
self.setWindowIcon(icon)
self.l.addWidget(QLabel('Story URL(s), one per line:'))
self.url = QTextEdit(self)
self.url.setToolTip('URLs for stories, one per line.')
self.url.setLineWrapMode(QTextEdit.NoWrap)
clipboard = QApplication.instance().clipboard()
self.url.setText(clipboard.text())
#'''http://test1.com?sid=6
#''')
# http://test1.com?sid=6701
# http://test1.com?sid=6702
# http://test1.com?sid=6703
# http://test1.com?sid=6704
# http://test1.com?sid=6705
# http://test1.com?sid=6706
# http://test1.com?sid=6707
# http://test1.com?sid=6708
# http://test1.com?sid=6709
self.l.addWidget(self.url)
# self.url = QLineEdit(self)
# self.url.setText('http://test1.com?sid=12345')
# self.l.addWidget(self.url)
self.ffdl_button = QPushButton(
'Download Stories', self)
self.ffdl_button.setToolTip('Start download(s).')
self.ffdl_button.clicked.connect(self.ffdl)
self.l.addWidget(self.ffdl_button)
horz = QHBoxLayout()
label = QLabel('Output &Format:')
horz.addWidget(label)
self.fileform = QComboBox(self)
self.fileform.addItem('epub')
self.fileform.addItem('mobi')
self.fileform.addItem('html')
self.fileform.addItem('txt')
self.fileform.setCurrentIndex(self.fileform.findText(prefs['fileform']))
self.fileform.setToolTip('Choose output format to create. May set default from plugin configuration.')
label.setBuddy(self.fileform)
horz.addWidget(self.fileform)
self.l.addLayout(horz)
horz = QHBoxLayout()
label = QLabel('On &Collision?')
label.setToolTip("What to do if there's already an existing story with the same title and author.")
horz.addWidget(label)
self.collision = QComboBox(self)
self.collision.addItem(OVERWRITE)
self.collision.addItem(ADDNEW)
self.collision.addItem(SKIP)
self.collision.setCurrentIndex(self.collision.findText(prefs['collision']))
self.collision.setToolTip('Overwrite will replace the existing story. Add New will create a new story with the same title and author.')
label.setBuddy(self.collision)
horz.addWidget(self.collision)
self.l.addLayout(horz)
horz = QHBoxLayout()
horz.addStretch(1)
self.updatemeta = QCheckBox('Update &Metadata?',self)
self.updatemeta.setChecked(prefs['updatemeta'])
self.updatemeta.setToolTip('Update metadata for story in Calibre from web site?')
horz.addWidget(self.updatemeta)
self.l.addLayout(horz)
horz = QHBoxLayout()
self.about_button = QPushButton('About', self)
self.about_button.clicked.connect(self.about)
horz.addWidget(self.about_button)
self.conf_button = QPushButton(
'Configure this plugin', self)
self.conf_button.clicked.connect(self.config)
horz.addWidget(self.conf_button)
self.l.addLayout(horz)
self.resize(self.sizeHint())
def about(self):
# Get the about text from a file inside the plugin zip file
# The get_resources function is a builtin function defined for all your
# plugin code. It loads files from the plugin zip file. It returns
# the bytes from the specified file.
#
# Note that if you are loading more than one file, for performance, you
# should pass a list of names to get_resources. In this case,
# get_resources will return a dictionary mapping names to bytes. Names that
# are not found in the zip file will not be in the returned dictionary.
text = get_resources('about.txt')
QMessageBox.about(self, 'About the FanFictionDownLoader Plugin',
text.decode('utf-8'))
def ffdl(self):
self.start_downloads(unicode(self.url.toPlainText()),
unicode(self.fileform.currentText()),
unicode(self.collision.currentText()),
self.updatemeta.isChecked())
self.hide()
def config(self):
self.do_user_config(parent=self)
class UserPassDialog(QDialog):
'''
Need to collect User/Pass for some sites.
'''
def __init__(self, gui, site):
QDialog.__init__(self, gui)
self.gui = gui
self.status=False
self.setWindowTitle('User/Password')
self.l = QGridLayout()
self.setLayout(self.l)
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.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)
self.cancel_button = QPushButton('Cancel', self)
self.cancel_button.clicked.connect(self.cancel)
self.l.addWidget(self.cancel_button,3,1)
self.resize(self.sizeHint())
def ok(self):
self.status=True
self.hide()
def cancel(self):
self.status=False
self.hide()
class MetadataProgressDialog(QProgressDialog):
'''
ProgressDialog displayed while fetching metadata for each story.
'''
def __init__(self, gui, loop_list, fileform, getadapter_function, download_list_function, db):
QProgressDialog.__init__(self,
"Fetching metadata for stories...",
QString(), 0, len(loop_list), gui)
self.setWindowTitle("Downloading metadata for stories")
self.setMinimumWidth(500)
self.gui = gui
self.db = db
self.loop_list = loop_list
self.fileform = fileform
self.getadapter_function = getadapter_function
self.download_list_function = download_list_function
self.i, self.loop_bad, self.loop_good = 0, [], []
## 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)
self.exec_()
def updateStatus(self):
self.setLabelText("Fetched metadata for %d of %d"%(self.i+1,len(self.loop_list)))
self.setValue(self.i+1)
print(self.labelText())
def do_loop(self):
print("self.i:%d"%self.i)
if self.i == 0:
self.setValue(0)
if self.i >= len(self.loop_list) or self.wasCanceled():
return self.do_when_finished()
else:
current = self.loop_list[self.i]
try:
retval = self.getadapter_function(current,self.fileform)
if retval:
self.loop_good.append((current,retval))
else:
self.loop_bad.append((current,'Duplicate--skipped.'))
except Exception as e:
self.loop_bad.append((current,e))
self.updateStatus()
self.i += 1
QTimer.singleShot(0, self.do_loop)
def do_when_finished(self):
self.hide()
# Queues a job to process these ePub/Mobi books in the background.
self.download_list_function(self.loop_good,self.fileform)
if self.loop_bad != []:
res = []
for j in self.loop_bad:
res.append('%s : %s'%j)
msg = '%s' % '\n'.join(res)
warning_dialog(self.gui, _('Could not get metadata for some stories'),
_('Could not get metadata for %d of %d stories.') %
(len(self.loop_bad), len(self.loop_list)),
msg).exec_()
# else:
# info_dialog(self.gui, "Starting Downloads",
# "Got metadata and started download for %d stories."%len(self.loop_good),
# show_copy_button=False).exec_()
self.gui = None
+290
View File
@@ -0,0 +1,290 @@
#!/usr/bin/env python
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from __future__ import (unicode_literals, division, absolute_import,
print_function)
__license__ = 'GPL v3'
__copyright__ = '2011, Jim Miller'
__docformat__ = 'restructuredtext en'
from StringIO import StringIO
import ConfigParser
from functools import partial
# The class that all interface action plugins must inherit from
from calibre.ptempfile import PersistentTemporaryFile
from calibre.ebooks.metadata import MetaInformation
from calibre.gui2 import error_dialog, warning_dialog, question_dialog, info_dialog
from calibre.gui2.actions import InterfaceAction
from calibre.gui2.threaded_jobs import ThreadedJob
from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader import adapters, writers, exceptions
from calibre_plugins.fanfictiondownloader_plugin.config import prefs
from calibre_plugins.fanfictiondownloader_plugin.dialogs import (
DownloadDialog, MetadataProgressDialog, UserPassDialog, OVERWRITE, ADDNEW, SKIP)
# because calibre immediately transforms html into zip and don't want
# to have an 'if html'. db.has_format is cool with the case mismatch,
# but if I'm doing it anyway...
formmapping = {
'epub':'EPUB',
'mobi':'MOBI',
'html':'ZIP',
'txt':'TXT'
}
class FanFictionDownLoaderPlugin(InterfaceAction):
name = 'FanFictionDownLoader'
# Declare the main action associated with this plugin
# The keyboard shortcut can be None if you dont want to use a keyboard
# shortcut. Remember that currently calibre has no central management for
# keyboard shortcuts, so try to use an unusual/unused shortcut.
# (text, icon_path, tooltip, keyboard shortcut)
# icon_path isn't in the zip--icon loaded below.
action_spec = ('FanFictionDownLoader', None,
'Download FanFiction stories from various web sites', None)
action_type = 'global'
def genesis(self):
# This method is called once per plugin, do initial setup here
# Set the icon for this interface action
# The get_icons function is a builtin function defined for all your
# plugin code. It loads icons from the plugin zip file. It returns
# QIcon objects, if you want the actual data, use the analogous
# get_resources builtin function.
#
# Note that if you are loading more than one icon, for performance, you
# should pass a list of names to get_icons. In this case, get_icons
# will return a dictionary mapping names to QIcons. Names that
# are not found in the zip file will result in null QIcons.
icon = get_icons('images/icon.png')
# The qaction is automatically created from the action_spec defined
# above
self.qaction.setIcon(icon)
# Call function when plugin triggered.
self.qaction.triggered.connect(self.show_dialog)
def show_dialog(self):
# The base plugin object defined in __init__.py
base_plugin_object = self.interface_action_base_plugin
# Show the config dialog
# The config dialog can also be shown from within
# Preferences->Plugins, which is why the do_user_config
# method is defined on the base plugin class
do_user_config = base_plugin_object.do_user_config
# The current database shown in the GUI
# db is an instance of the class LibraryDatabase2 from database.py
# This class has many, many methods that allow you to do a lot of
# things.
self.db = self.gui.current_db
rows = self.gui.library_view.selectionModel().selectedRows()
if rows:
book_ids = self.gui.library_view.get_selected_ids()
print("book_ids: %s"%book_ids)
row = self.gui.library_view.currentIndex()
if row.isValid():
print("current id:%d"%self.gui.library_view.model().id(row))
#self.db.get_identifiers()['url']
# self.gui is the main calibre GUI. It acts as the gateway to access
# all the elements of the calibre user interface, it should also be the
# parent of the dialog
# DownloadDialog just collects URLs, format and presents buttons.
d = DownloadDialog(self.gui,
prefs,
self.qaction.icon(),
do_user_config, # method for config button
self.start_downloads, # method to start downloads
)
d.show()
def apply_settings(self):
# No need to do anything with perfs here, but we could.
prefs
def start_downloads(self,urls,fileform,
collision,updatemeta):
self.ffdlconfig = ConfigParser.SafeConfigParser()
self.ffdlconfig.readfp(StringIO(get_resources("defaults.ini")))
self.ffdlconfig.readfp(StringIO(prefs['personal.ini']))
url_list = get_url_list(urls)
self.fetchmeta_qpd = \
MetadataProgressDialog(self.gui,
url_list,
fileform,
partial(self.get_adapter_for_story, collision=collision),
partial(self.download_list,collision=collision,updatemeta=updatemeta),
self.db)
def get_adapter_for_story(self,url,fileform,collision=SKIP):
'''
Returns adapter object for story at URL. To be called from
MetadataProgressDialog 'loop' to build up list of adapters. Also
pops dialogs for is adult, user/pass, duplicate
'''
print("URL:"+url)
adapter = adapters.getAdapter(self.ffdlconfig,url)
try:
adapter.getStoryMetadataOnly()
except exceptions.FailedToLogin:
print("Login Failed, Need Username/Password.")
userpass = UserPassDialog(self.gui,url)
userpass.exec_() # exec_ will make it act modal
if userpass.status:
adapter.username = userpass.user.text()
adapter.password = userpass.passwd.text()
# else:
# del adapter
# return
except exceptions.AdultCheckRequired:
if question_dialog(self.gui, 'Are You Adult?', '<p>'+
"%s requires that you be an adult. Please confirm you are an adult in your locale:"%url,
show_copy_button=False):
adapter.is_adult=True
# else:
# del adapter
# return
# let exceptions percolate up.
story = adapter.getStoryMetadataOnly()
add=True
if collision != ADDNEW:
mi = MetaInformation(story.getMetadata("title"),
(story.getMetadata("author"),)) # author is a list.
identicalbooks = self.db.find_identical_books(mi)
print(identicalbooks)
## more than one match will need to be handled differently.
if identicalbooks and collision == SKIP:
add=False
# book_id = identicalbooks.pop()
# print("formats:"+self.db.formats(book_id,index_is_id=True))
# print("has format:%s"%self.db.has_format(book_id,formmapping[fileform],index_is_id=True))
# if self.db.has_format(book_id,formmapping[fileform],index_is_id=True):
# if question_dialog(self.gui, 'Update?', '<p>'+
# "%s by %s is already in your library more than once. Add/Replace this format?"%
# (story.getMetadata("title"),story.getMetadata("author")),
# show_copy_button=False):
# add=True
if add:
return adapter
else:
return None
def download_list(self,adaptertuple_list,fileform,
collision=ADDNEW,
updatemeta=True):
'''
Called by MetadataProgressDialog to start story downloads BG processing.
adapter_list is a list of tuples of (url,adapter)
'''
print("download_list")
job = ThreadedJob('FanFictionDownload',
'Downloading FanFiction Stories',
func=self.do_story_downloads,
args=(adaptertuple_list, fileform, self.db),
kwargs={'collision':collision,'updatemeta':updatemeta},
callback=self._get_stories_completed)
self.gui.job_manager.run_threaded_job(job)
self.gui.status_bar.show_message('Downloading %d stories'%len(adaptertuple_list))
def _get_stories_completed(self, job):
print("_get_stories_completed")
def do_story_downloads(self, adaptertuple_list, fileform, db,
**kwargs): # lambda x,y:x lambda makes small anonymous function.
# abort=None, log=None,
'''
Master job, loop to download this list of stories
'''
print("do_story_downloads")
abort = kwargs['abort']
notifications=kwargs['notifications']
log = kwargs['log']
notifications.put((0.01, 'Start Downloading Stories'))
count = 0.01
total = len(adaptertuple_list)
# Queue all the jobs
for (url,adapter) in adaptertuple_list:
if abort.is_set():
notifications.put(1.0,'Aborting...')
return
notifications.put((float(count)/total,
'Downloading %s'%adapter.getStoryMetadataOnly().getMetadata("title")))
log.prints(log.INFO,'Downloading %s'%adapter.getStoryMetadataOnly().getMetadata("title"))
try:
self.do_story_download(adapter,fileform,db,kwargs['collision'],kwargs['updatemeta'])
except Exception as e:
log.prints(log.ERROR,'Failed Downloading %s: %s'%
(adapter.getStoryMetadataOnly().getMetadata("title"),e))
count = count + 1
return
def do_story_download(self,adapter,fileform,db,collision,updatemeta):
print("do_story_download")
story = adapter.getStoryMetadataOnly()
mi = MetaInformation(story.getMetadata("title"),
(story.getMetadata("author"),)) # author is a list.
writer = writers.getWriter(fileform,adapter.config,adapter)
tmp = PersistentTemporaryFile("."+fileform)
print("%s by %s"%(story.getMetadata("title"), story.getMetadata("author")))
print("tmp: "+tmp.name)
writer.writeStory(tmp)
mi.set_identifiers({'url':story.getMetadata("storyUrl")})
mi.publisher = story.getMetadata("site")
mi.tags = writer.getTags()
mi.languages = ['en']
mi.pubdate = story.getMetadataRaw('datePublished').strftime("%Y-%m-%d")
mi.timestamp = story.getMetadataRaw('dateCreated').strftime("%Y-%m-%d")
mi.comments = story.getMetadata("description")
identicalbooks = self.db.find_identical_books(mi)
print(identicalbooks)
addedcount=0
if identicalbooks and collision == OVERWRITE:
## more than one match? add to first off the list.
book_id = identicalbooks.pop()
if updatemeta:
db.set_metadata(book_id,mi)
db.add_format_with_hooks(book_id, fileform, tmp, index_is_id=True)
else:
(notadded,addedcount)=db.add_books([tmp],[fileform],[mi], add_duplicates=True)
# Otherwise list of books doesn't update right away.
if addedcount:
self.gui.library_view.model().books_added(addedcount)
del adapter
del writer
def f(x):
if x.strip(): return True
else: return False
def get_url_list(urls):
return filter(f,urls.strip().splitlines())
Binary file not shown.

After

Width:  |  Height:  |  Size: 23 KiB

+5 -3
View File
@@ -3,6 +3,8 @@ cron:
url: /r3m0v3r
schedule: every 2 hours
- description: orphan cleanup job
url: /r3m0v3rOrphans
schedule: every 4 hours
# There's a bug in the Python 2.7 runtime that prevents this from
# working properly. In theory, there should never be orphans anyway.
#- description: orphan cleanup job
# url: /r3m0v3rOrphans
# schedule: every 4 hours
+19 -4
View File
@@ -105,6 +105,10 @@ zip_filename: ${title}-${siteabbrev}_${storyId}${formatext}.zip
## zip_filename.
allow_unsafe_filename: false
## entries to make epub subjects and calibre tags
## lastupdate creates two tags: "Last Update Year/Month: %Y/%m" and "Last Update: %Y/%m/%d"
include_subject_tags: extratags, genre, category, characters, lastupdate, status
## extra tags (comma separated) to include, primarily for epub.
extratags: FanFiction
@@ -113,6 +117,15 @@ extratags: FanFiction
## Primarily for commandline.
#slow_down_sleep_time:0.5
## output background color--only used by html and epub (and ignored in
## epub by many readers). Must be hex code, # will be added.
background_color: ffffff
## For use only with stand-alone CLI version--run a command on the
## generated file after it's produced. All of the titlepage_entries
## values are available, plus output_filename.
#post_process_cmd: addbook -f "${output_filename}" -t "${title}"
## Each output format has a section that overrides [defaults]
[html]
@@ -128,10 +141,6 @@ windows_eol: true
## epub is already a zip file.
zip_output: false
## entries to make epub subject tags
## lastupdate creates two tags: "Last Update Year/Month: %Y/%m" and "Last Update: %Y/%m/%d"
include_subject_tags: extratags, genre, category, characters, lastupdate, status
## epub carries the TOC in metadata.
## mobi generated from epub will have a TOC at the end.
include_tocpage: false
@@ -245,6 +254,12 @@ output_filename: ${title}-${siteabbrev}_${authorId}_${storyId}${formatext}
## this should go in your personal.ini, not defaults.ini.
#is_adult:true
[www.tthfanfic.org]
## 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
[overrides]
## It may sometimes be useful to override all of the specific format,
## site and site:format sections in your private configuration. For
+18 -11
View File
@@ -24,6 +24,9 @@ from os.path import normpath, expanduser, isfile, join
from StringIO import StringIO
from optparse import OptionParser
import getpass
import string
from subprocess import call
from epubmerge import doMerge
@@ -38,7 +41,9 @@ import ConfigParser
def writeStory(config,adapter,writeformat,metaonly=False,outstream=None):
writer = writers.getWriter(writeformat,config,adapter)
writer.writeStory(outstream=outstream,metaonly=metaonly)
output_filename=writer.getOutputFileName()
del writer
return output_filename
def main():
@@ -65,7 +70,7 @@ def main():
help="Update an existing epub with new chapter, give epub filename instead of storyurl. Not compatible with inserted TOC.",)
parser.add_option("--force",
action="store_true", dest="force",
help="Force update of an existing epub, download and overwrite all chapters.",)
help="Force overwrite or update of an existing epub, download and overwrite all chapters.",)
(options, args) = parser.parse_args()
@@ -97,6 +102,10 @@ def main():
config.add_section("overrides")
except ConfigParser.DuplicateSectionError:
pass
if options.force:
config.set("overrides","always_overwrite","true")
if options.options:
for opt in options.options:
(var,val) = opt.split('=')
@@ -112,7 +121,7 @@ def main():
striptitletoc=True,
forceunique=False)
print "Updating %s, URL: %s" % (args[0],url)
filename = args[0]
output_filename = args[0]
config.set("overrides","output_filename",args[0])
else:
url = args[0]
@@ -184,16 +193,14 @@ def main():
adapter.setChaptersRange(options.begin,options.end)
if options.format == "all":
## For testing. Doing all three formats actually causes
## some interesting config issues with format-specific
## sections. But it should rarely be an issue.
writeStory(config,adapter,"epub",options.metaonly)
writeStory(config,adapter,"html",options.metaonly)
writeStory(config,adapter,"txt",options.metaonly)
else:
writeStory(config,adapter,options.format,options.metaonly)
output_filename=writeStory(config,adapter,options.format,options.metaonly)
if not options.metaonly and adapter.getConfig("post_process_cmd"):
metadata = adapter.story.metadata
metadata['output_filename']=output_filename
call(string.Template(adapter.getConfig("post_process_cmd"))
.substitute(metadata), shell=True)
del adapter
except exceptions.InvalidStoryURL, isu:
+1 -1
View File
@@ -216,7 +216,7 @@ def doMerge(outputio,files,authoropts=[],titleopt=None,descopt=None,
try:
outputepub.writestr(href,
epub.read(relpath+item.getAttribute("href")))
if re.match(r'.*/(file|chapter)\d+\.xhtml',href):
if re.match(r'.*/(file|chapter)\d+\.x?html',href):
filecount+=1
items.append((id,href,item.getAttribute("media-type")))
filelist.append(href)
+35 -18
View File
@@ -15,21 +15,51 @@
# limitations under the License.
#
import os, re, sys, glob
import os, re, sys, glob, types
from os.path import dirname, basename, normpath
import logging
import urlparse as up
import fanficdownloader.exceptions as exceptions
from .. import exceptions as exceptions
## must import each adapter here.
import adapter_test1
import adapter_fanfictionnet
import adapter_fanficcastletvnet
import adapter_fanfictionnet
import adapter_fictionalleyorg
import adapter_fictionpresscom
import adapter_ficwadcom
import adapter_fimfictionnet
import adapter_harrypotterfanfictioncom
import adapter_mediaminerorg
import adapter_potionsandsnitchesnet
import adapter_tenhawkpresentscom
import adapter_adastrafanficcom
import adapter_thewriterscoffeeshopcom
import adapter_tthfanficorg
import adapter_twilightednet
import adapter_twiwritenet
import adapter_whoficcom
## This bit of complexity allows adapters to be added by just adding
## the source file. It eliminates the long if/else clauses we used to
## need to pick out the adapter.
## importing. It eliminates the long if/else clauses we used to need
## to pick out the adapter.
## List of registered site adapters.
__class_list = []
def imports():
for name, val in globals().items():
if isinstance(val, types.ModuleType):
yield val.__name__
for x in imports():
if "fanficdownloader.adapters.adapter_" in x:
#print x
__class_list.append(sys.modules[x].getClass())
def getAdapter(config,url):
## fix up leading protocol.
fixedurl = re.sub(r"(?i)^[htp]+[:/]+","http://",url.strip())
@@ -63,16 +93,3 @@ def getClassFor(domain):
for cls in __class_list:
if cls.matchesSite(domain):
return cls
## Automatically import each adapter_*.py file.
## Each implement getClass() to their class
filelist = glob.glob(dirname(__file__)+'/adapter_*.py')
sys.path.insert(0,normpath(dirname(__file__)))
for file in filelist:
#print "file: "+basename(file)[:-3]
module = __import__(basename(file)[:-3])
__class_list.append(module.getClass())
del sys.path[0]
@@ -21,9 +21,9 @@ import re
import urllib
import urllib2
import fanficdownloader.BeautifulSoup as bs
from fanficdownloader.htmlcleanup import stripHTML
import fanficdownloader.exceptions as exceptions
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, utf8FromSoup, makeDate
@@ -20,9 +20,9 @@ import logging
import re
import urllib2
import fanficdownloader.BeautifulSoup as bs
from fanficdownloader.htmlcleanup import stripHTML
import fanficdownloader.exceptions as exceptions
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, utf8FromSoup, makeDate
@@ -21,8 +21,8 @@ import re
import urllib2
import time
import fanficdownloader.BeautifulSoup as bs
import fanficdownloader.exceptions as exceptions
from .. import BeautifulSoup as bs
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, utf8FromSoup, makeDate
@@ -21,9 +21,9 @@ import re
import urllib
import urllib2
import fanficdownloader.BeautifulSoup as bs
from fanficdownloader.htmlcleanup import stripHTML
import fanficdownloader.exceptions as exceptions
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, utf8FromSoup, makeDate
@@ -22,9 +22,9 @@ import urllib2
import time
import httplib, urllib
import fanficdownloader.BeautifulSoup as bs
import fanficdownloader.exceptions as exceptions
from fanficdownloader.htmlcleanup import stripHTML
from .. import BeautifulSoup as bs
from .. import exceptions as exceptions
from ..htmlcleanup import stripHTML
from base_adapter import BaseSiteAdapter, utf8FromSoup, makeDate
@@ -21,9 +21,9 @@ import re
import urllib2
import cookielib as cl
import fanficdownloader.BeautifulSoup as bs
from fanficdownloader.htmlcleanup import stripHTML
import fanficdownloader.exceptions as exceptions
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, utf8FromSoup, makeDate
@@ -21,9 +21,9 @@ import re
import urllib
import urllib2
import fanficdownloader.BeautifulSoup as bs
from fanficdownloader.htmlcleanup import stripHTML
import fanficdownloader.exceptions as exceptions
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, utf8FromSoup, makeDate
@@ -21,9 +21,9 @@ import re
import urllib
import urllib2
import fanficdownloader.BeautifulSoup as bs
from fanficdownloader.htmlcleanup import stripHTML
import fanficdownloader.exceptions as exceptions
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, utf8FromSoup, makeDate
@@ -21,9 +21,9 @@ import re
import urllib
import urllib2
import fanficdownloader.BeautifulSoup as bs
from fanficdownloader.htmlcleanup import stripHTML
import fanficdownloader.exceptions as exceptions
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, utf8FromSoup, makeDate
@@ -21,9 +21,9 @@ import re
import urllib
import urllib2
import fanficdownloader.BeautifulSoup as bs
from fanficdownloader.htmlcleanup import stripHTML
import fanficdownloader.exceptions as exceptions
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, utf8FromSoup, makeDate
+14 -5
View File
@@ -19,8 +19,8 @@ import datetime
import time
import logging
import fanficdownloader.BeautifulSoup as bs
import fanficdownloader.exceptions as exceptions
from .. import BeautifulSoup as bs
from .. import exceptions
from base_adapter import BaseSiteAdapter, utf8FromSoup, makeDate
@@ -54,6 +54,12 @@ class TestSiteAdapter(BaseSiteAdapter):
if self.story.getMetadata('storyId') == '666':
raise exceptions.StoryDoesNotExist(self.url)
if self.story.getMetadata('storyId').startswith('670'):
time.sleep(1.0)
if self.story.getMetadata('storyId').startswith('671'):
time.sleep(1.0)
if self.getConfig("username"):
self.username = self.getConfig("username")
@@ -63,7 +69,7 @@ class TestSiteAdapter(BaseSiteAdapter):
if self.story.getMetadata('storyId') == '664':
self.story.setMetadata(u'title',"Test Story Title "+self.crazystring)
else:
self.story.setMetadata(u'title',"Test Story Title")
self.story.setMetadata(u'title',"Test Story Title "+self.story.getMetadata('storyId'))
self.story.setMetadata('storyUrl',self.url)
self.story.setMetadata('description',u'Description '+self.crazystring+u''' Done
@@ -128,8 +134,9 @@ Some more longer description. "I suck at summaries!" "Better than it sounds!"
if self.story.getMetadata('storyId') == '667':
raise exceptions.FailedToDownload("Error downloading Chapter: %s!" % url)
if self.story.getMetadata('storyId') == '670':
time.sleep(2.0)
if self.story.getMetadata('storyId').startswith('670') or \
self.story.getMetadata('storyId').startswith('672'):
time.sleep(1.0)
if "chapter=1" in url :
text=u'''
@@ -143,6 +150,8 @@ Some more longer description. "I suck at summaries!" "Better than it sounds!"
<p>http://test1.com?sid=668 - raises FailedToLogin unless username='Me'</p>
<p>http://test1.com?sid=669 - Succeeds with Updated Date=now</p>
<p>http://test1.com?sid=670 - Succeeds, but sleeps 2sec on each chapter</p>
<p>http://test1.com?sid=671 - Succeeds, but sleeps 2sec metadata only</p>
<p>http://test1.com?sid=672 - Succeeds, quick meta, sleeps 2sec chapters only</p>
<p>And other storyId will succeed with the same output.</p>
</div>
'''
@@ -21,9 +21,9 @@ import re
import urllib
import urllib2
import fanficdownloader.BeautifulSoup as bs
from fanficdownloader.htmlcleanup import stripHTML
import fanficdownloader.exceptions as exceptions
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, utf8FromSoup, makeDate
@@ -0,0 +1,238 @@
# -*- 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
import re
import urllib2
import time
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, utf8FromSoup, makeDate
class TwistingTheHellmouthSiteAdapter(BaseSiteAdapter):
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.story.setMetadata('siteabbrev','tth')
self.dateformat = "%d %b %y"
self.is_adult=False
self.username = None
self.password = None
# get storyId from url--url validation guarantees query correct
m = re.match(self.getSiteURLPattern(),url)
if m:
self.story.setMetadata('storyId',m.group('id'))
logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
# normalized story URL.
self._setURL("http://"+self.getSiteDomain()\
+"/Story-"+self.story.getMetadata('storyId'))
else:
raise exceptions.InvalidStoryURL(url,
self.getSiteDomain(),
self.getSiteExampleURLs())
@staticmethod
def getSiteDomain():
return 'www.tthfanfic.org'
def getSiteExampleURLs(self):
return "http://www.tthfanfic.org/Story-5583 http://www.tthfanfic.org/Story-5583/Greywizard+Marked+By+Kane.htm ttp://www.tthfanfic.org/T-526321777890480578489880055880/Story-26448-15/batzulger+Willow+Rosenberg+and+the+Mind+Riders.htm"
# http://www.tthfanfic.org/T-526321777848988007890480555880/Story-26448-15/batzulger+Willow+Rosenberg+and+the+Mind+Riders.htm
# http://www.tthfanfic.org/Story-5583
# http://www.tthfanfic.org/Story-5583/Greywizard+Marked+By+Kane.htm
def getSiteURLPattern(self):
return r"http://www.tthfanfic.org/(T-\d+/)?Story-(?P<id>\d+)(-\d+)?(/.*)?$"
# tth won't send you future updates if you aren't 'caught up'
# on the story. Login isn't required for F21, but logging in will
# mark stories you've downloaded as 'read' on tth.
def performLogin(self):
params = {}
if self.password:
params['urealname'] = self.username
params['password'] = self.password
else:
params['urealname'] = self.getConfig("username")
params['password'] = self.getConfig("password")
params['loginsubmit'] = 'Login'
if not params['password']:
return
loginUrl = 'http://' + self.getSiteDomain() + '/login.php'
logging.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
params['urealname']))
## need to pull empty login page first to get ctkn and
## password name, which are BUSs
# <form method='post' action='/login.php' accept-charset="utf-8">
# <input type='hidden' name='ctkn' value='4bdf761f5bea06bf4477072afcbd0f8d721d1a4f989c09945a9e87afb7a66de1'/>
# <input type='text' id='urealname' name='urealname' value=''/>
# <input type='password' id='password' name='6bb3fcd148d148629223690bf19733b8'/>
# <input type='submit' value='Login' name='loginsubmit'/>
soup = bs.BeautifulSoup(self._fetchUrl(loginUrl))
params['ctkn']=soup.find('input', {'name':'ctkn'})['value']
params[soup.find('input', {'id':'password'})['name']] = params['password']
d = self._fetchUrl(loginUrl, params)
if "Stories Published" not in d : #Member Account
logging.info("Failed to login to URL %s as %s" % (loginUrl,
params['penname']))
raise exceptions.FailedToLogin(url,params['penname'])
return False
else:
return True
def extractChapterUrlsAndMetadata(self):
# fetch the chapter. From that we will get almost all the
# metadata and chapter list
url=self.url
logging.debug("URL: "+url)
# tth won't send you future updates if you aren't 'caught up'
# on the story. Login isn't required for F21, but logging in will
# mark stories you've downloaded as 'read' on tth.
self.performLogin()
# use BeautifulSoup HTML parser to make everything easier to find.
try:
data = self._fetchUrl(url)
soup = bs.BeautifulSoup(data)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(url)
else:
raise e
if "<h2>Story Not Found</h2>" in data:
raise exceptions.StoryDoesNotExist(url)
if "NOTE: This story is rated FR21 which is above your chosen filter level." in data:
if self.is_adult or self.getConfig("is_adult"):
form = soup.find('form', {'id':'sitemaxratingform'})
params={'ctkn':form.find('input', {'name':'ctkn'})['value'],
'sitemaxrating':'5'}
logging.info("Attempting to get rating cookie for %s" % url)
data = self._postUrl("http://"+self.getSiteDomain()+'/setmaxrating.php',params)
# refetch story page.
data = self._fetchUrl(url)
soup = bs.BeautifulSoup(data)
else:
raise exceptions.AdultCheckRequired(self.url)
# http://www.tthfanfic.org/AuthorStories-3449/Greywizard.htm
# Find authorid and URL from... author url.
a = soup.find('a', href=re.compile(r"^/AuthorStories-\d+"))
self.story.setMetadata('authorId',a['href'].split('/')[1].split('-')[1])
self.story.setMetadata('authorUrl','http://'+self.host+a['href'])
self.story.setMetadata('author',stripHTML(a))
try:
# going to pull part of the meta data from author list page.
logging.debug("author URL: "+self.story.getMetadata('authorUrl'))
authordata = self._fetchUrl(self.story.getMetadata('authorUrl'))
authorsoup = bs.BeautifulSoup(authordata)
# author can have several pages, scan until we find it.
while( not authorsoup.find('a', href=re.compile(r"^/Story-"+self.story.getMetadata('storyId'))) ):
nextpage = 'http://'+self.host+authorsoup.find('a', {'class':'arrowf'})['href']
logging.debug("author nextpage URL: "+nextpage)
authordata = self._fetchUrl(nextpage)
authorsoup = bs.BeautifulSoup(authordata)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(url)
else:
raise e
storydiv = authorsoup.find('div', {'id':'st'+self.story.getMetadata('storyId'), 'class':re.compile(r"storylistitem")})
self.story.setMetadata('description',stripHTML(storydiv.find('div',{'class':'storydesc'})))
self.story.setMetadata('title',stripHTML(storydiv.find('a',{'class':'storylink'})))
verticaltable = soup.find('table', {'class':'verticaltable'})
BtVS = True
for cat in verticaltable.findAll('a', href=re.compile(r"^/Category-")):
if cat.string not in ['General', 'Non-BtVS/AtS Stories', 'BtVS/AtS Non-Crossover', 'Non-BtVS Crossovers']:
self.story.addToList('category',cat.string)
else:
if 'Non-BtVS' in cat.string:
BtVS = False
if BtVS:
self.story.addToList('category','Buffy: The Vampire Slayer')
verticaltabletds = verticaltable.findAll('td')
self.story.setMetadata('rating', verticaltabletds[2].string)
self.story.setMetadata('numWords', verticaltabletds[4].string)
# Complete--if completed.
if 'Yes' in verticaltabletds[10].string:
self.story.setMetadata('status', 'Completed')
else:
self.story.setMetadata('status', 'In-Progress')
self.story.setMetadata('datePublished',makeDate(stripHTML(verticaltabletds[8].string), self.dateformat))
self.story.setMetadata('dateUpdated',makeDate(stripHTML(verticaltabletds[9].string), self.dateformat))
for icon in storydiv.find('span',{'class':'storyicons'}).findAll('img'):
if( icon['title'] not in ['Non-Crossover'] ) :
self.story.addToList('genre',icon['title'])
# Find the chapter selector
select = soup.find('select', { 'name' : 'chapnav' } )
if select is None:
# no selector found, so it's a one-chapter story.
self.chapterUrls.append((self.story.getMetadata('title'),url))
else:
allOptions = select.findAll('option')
for o in allOptions:
url = "http://"+self.host+o['value']
# just in case there's tags, like <i> in chapter titles.
self.chapterUrls.append((stripHTML(o),url))
self.story.setMetadata('numChapters',len(self.chapterUrls))
return
def getChapterText(self, url):
logging.debug('Getting chapter text from: %s' % url)
soup = bs.BeautifulSoup(self._fetchUrl(url))
div = soup.find('div', {'id' : 'storyinnerbody'})
if None == div:
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
# strip out included chapter title, if present, to avoid doubling up.
try:
div.find('h3').extract()
except:
pass
return utf8FromSoup(div)
def getClass():
return TwistingTheHellmouthSiteAdapter
@@ -21,9 +21,9 @@ import re
import urllib
import urllib2
import fanficdownloader.BeautifulSoup as bs
from fanficdownloader.htmlcleanup import stripHTML
import fanficdownloader.exceptions as exceptions
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, utf8FromSoup, makeDate
@@ -21,9 +21,9 @@ import re
import urllib
import urllib2
import fanficdownloader.BeautifulSoup as bs
from fanficdownloader.htmlcleanup import stripHTML
import fanficdownloader.exceptions as exceptions
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, utf8FromSoup, makeDate
@@ -20,8 +20,8 @@ import logging
import re
import urllib2
import fanficdownloader.BeautifulSoup as bs
import fanficdownloader.exceptions as exceptions
from .. import BeautifulSoup as bs
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, utf8FromSoup, makeDate
+6 -5
View File
@@ -39,13 +39,13 @@ except:
pass
#logging.info("Hook to make default deadline 10.0 NOT installed--not using appengine")
from fanficdownloader.story import Story
from fanficdownloader.configurable import Configurable
from fanficdownloader.htmlcleanup import removeEntities, removeAllEntities, stripHTML
from fanficdownloader.exceptions import InvalidStoryURL
from ..story import Story
from ..configurable import Configurable
from ..htmlcleanup import removeEntities, removeAllEntities, stripHTML
from ..exceptions import InvalidStoryURL
try:
import fanficdownloader.chardet as chardet
from .. import chardet as chardet
except ImportError:
chardet = None
@@ -63,6 +63,7 @@ class BaseSiteAdapter(Configurable):
return re.match(self.getSiteURLPattern(), self.url)
def __init__(self, config, url):
self.config = config
Configurable.__init__(self, config)
self.addConfigSection(self.getSiteDomain())
self.addConfigSection("overrides")
+1 -1
View File
@@ -25,7 +25,7 @@ class Story:
try:
self.metadata = {'version':os.environ['CURRENT_VERSION_ID']}
except:
self.metadata = {'version':'4.0'}
self.metadata = {'version':'4.1'}
self.chapters = [] # chapters will be tuples of (title,html)
self.listables = {} # some items (extratags, category, warnings & genres) are also kept as lists.
+1 -1
View File
@@ -18,7 +18,7 @@
## This could (should?) use a dynamic loader like adapters, but for
## now, it's static, since there's so few of them.
from fanficdownloader.exceptions import FailedToDownload
from ..exceptions import FailedToDownload
from writer_html import HTMLWriter
from writer_txt import TextWriter
+21 -2
View File
@@ -24,8 +24,8 @@ import zipfile
from zipfile import ZipFile, ZIP_DEFLATED
import logging
from fanficdownloader.configurable import Configurable
from fanficdownloader.htmlcleanup import removeEntities, removeAllEntities, stripHTML
from ..configurable import Configurable
from ..htmlcleanup import removeEntities, removeAllEntities, stripHTML
class BaseStoryWriter(Configurable):
@@ -102,6 +102,9 @@ class BaseStoryWriter(Configurable):
self.story.setMetadata('formatname',self.getFormatName())
self.story.setMetadata('formatext',self.getFormatExt())
def getMetadata(self,key):
return stripHTML(self.story.getMetadata(key))
def getOutputFileName(self):
if self.getConfig('zip_output'):
return self.getZipFileName()
@@ -242,6 +245,22 @@ class BaseStoryWriter(Configurable):
if close:
outstream.close()
def getTags(self):
# set to avoid duplicates subject tags.
subjectset = set()
for entry in self.validEntries:
if entry in self.getConfigList("include_subject_tags") and \
entry not in self.story.getLists() and \
self.story.getMetadata(entry):
subjectset.add(self.getMetadata(entry))
# listables all go into dc:subject tags, but only if they are configured.
for (name,lst) in self.story.getLists().iteritems():
if name in self.getConfigList("include_subject_tags"):
for tag in lst:
subjectset.add(tag)
return subjectset
def writeStoryImpl(self, out):
"Must be overriden by sub classes."
pass
+8 -20
View File
@@ -26,7 +26,7 @@ from zipfile import ZipFile, ZIP_STORED, ZIP_DEFLATED
from xml.dom.minidom import parse, parseString, getDOMImplementation
from base_writer import *
from fanficdownloader.htmlcleanup import stripHTML
from ..htmlcleanup import stripHTML
class EpubWriter(BaseStoryWriter):
@@ -41,7 +41,10 @@ class EpubWriter(BaseStoryWriter):
def __init__(self, config, story):
BaseStoryWriter.__init__(self, config, story)
self.EPUB_CSS='''body { margin-left: 2%; margin-right: 2%; margin-top: 2%; margin-bottom: 2%; text-align: justify; }
self.EPUB_CSS = string.Template('''
body { margin: 2%;
text-align: justify;
background-color: #${background_color}; }
pre { font-size: x-small; }
sml { font-size: small; }
h1 { text-align: center; }
@@ -63,7 +66,7 @@ h6 { text-align: center; }
.smcap {font-variant: small-caps;}
.u {text-decoration: underline;}
.bold {font-weight: bold;}
'''
''')
self.EPUB_TITLE_PAGE_START = string.Template('''<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
@@ -153,9 +156,6 @@ h6 { text-align: center; }
</html>
''')
def getMetadata(self,key):
return stripHTML(self.story.getMetadata(key))
def writeStoryImpl(self, out):
## Python 2.5 ZipFile is rather more primative than later
@@ -257,19 +257,7 @@ h6 { text-align: center; }
metadata.appendChild(newTag(contentdom,"dc:description",text=
self.getMetadata('description')))
# set to avoid duplicates subject tags.
subjectset = set()
for entry in self.validEntries:
if entry in self.getConfigList("include_subject_tags") and \
entry not in self.story.getLists() and \
self.story.getMetadata(entry):
subjectset.add(self.getMetadata(entry))
# listables all go into dc:subject tags, but only if they are configured.
for (name,lst) in self.story.getLists().iteritems():
if name in self.getConfigList("include_subject_tags"):
for tag in lst:
subjectset.add(tag)
for subject in subjectset:
for subject in self.getTags():
metadata.appendChild(newTag(contentdom,"dc:subject",text=subject))
@@ -376,7 +364,7 @@ h6 { text-align: center; }
del tocncxdom
# write stylesheet.css file.
outputepub.writestr("OEBPS/stylesheet.css",self.EPUB_CSS)
outputepub.writestr("OEBPS/stylesheet.css",self.EPUB_CSS.substitute({"background_color":self.getConfig("background_color")}))
# write title page.
if self.getConfig("titlepage_use_table"):
+4
View File
@@ -39,6 +39,7 @@ class HTMLWriter(BaseStoryWriter):
<head>
<title>${title} by ${author}</title>
<style type="text/css">
body { background-color: #${background_color}; }
.CI {
text-align:center;
margin-top:0px;
@@ -94,6 +95,9 @@ class HTMLWriter(BaseStoryWriter):
def writeStoryImpl(self, out):
# minor cheat, tucking bg into metadata.
if self.getConfig("background_color"):
self.story.metadata["background_color"] = self.getConfig("background_color")
self._write(out,self.HTML_FILE_START.substitute(self.story.metadata))
self.writeTitlePage(out,
+2 -5
View File
@@ -20,8 +20,8 @@ import string
import StringIO
from base_writer import *
from fanficdownloader.htmlcleanup import stripHTML
from fanficdownloader.mobi import Converter
from ..htmlcleanup import stripHTML
from ..mobi import Converter
class MobiWriter(BaseStoryWriter):
@@ -124,9 +124,6 @@ class MobiWriter(BaseStoryWriter):
</html>
''')
def getMetadata(self,key):
return stripHTML(self.story.getMetadata(key))
def writeStoryImpl(self, out):
files = []
+1 -1
View File
@@ -21,7 +21,7 @@ from textwrap import wrap
from base_writer import *
from fanficdownloader.html2text import html2text, BODY_WIDTH
from ..html2text import html2text, BODY_WIDTH
## In BaseStoryWriter, we define _write to encode <unicode> objects
## back into <string> for true output. But txt needs to write the
+20 -18
View File
@@ -54,33 +54,28 @@
much easier. </p>
</div>
<!-- put announcements here, h3 is a good title size. -->
<h3>Please Switch to <a href="http://fanfictiondownloader.appspot.com/">New Version</a></h3>
<h3>This is the Official Multithreading Version</h3>
<p>
We have a new, more efficient, version of the system up now. Please start using the
<a href="http://fanfictiondownloader.appspot.com/">New
Version here</a>. If for some reason, the new version
doesn't work for you, please let us know on
the <a href="http://groups.google.com/group/fanfic-downloader">Fanfiction
Downloader Google Group</a>.
</p>
<h3>New Google Quotas</h3>
<p>
Google has changed their quota limits for free
applications using their AppEngine system, like this one.
We expect that there will be times when the
system exceeds it's permitted processing quota.
This version of the application uses Python 2.7 and
multithreading to try and reduce our usage. Google
considers Python 2.7 Experimental still, so there may be issues.
</p>
<p>
You also have the option of running the downloader on your
own computer if you have Python available.
<a href="http://code.google.com/p/fanficdownloader/downloads/list">Download here.</a>
<b>Good news!</b><br />
The issue that was causing problems with downloading large stories
has been fixed.
</p>
<p>
<b>New Feature</b><br /> You can now set a custom
parameter for background_color that will be used with html
and epub output. (Note: many epub readers ignore the bg color.)
</p>
<p>
If you have any problems with this application, please
report them in
the <a href="http://groups.google.com/group/fanfic-downloader">Fanfiction
Downloader Google Group</a>. The
<a href="http://4-0-6.fanfictionloader.appspot.com">Previous
<a href="http://4-0-7.fanfictiondownloader.appspot.com">Previous
Version</a> is also available for you to use if necessary.
</p>
<div id='error'>
@@ -213,6 +208,13 @@
<br /> or the URL of any chapter, such as
<br /><a href="http://www.fimfiction.com/story/123/1/">http://www.fimfiction.com/story/123/1/</a>.
</dd>
<dt>tthfanfic.org</dt>
<dd>
Use the URL of any story, with or without chapter, title and notice, such as
<br /><a href="http://www.tthfanfic.org/Story-5583">http://www.tthfanfic.org/Story-5583</a>
<br /><a href="http://www.tthfanfic.org/Story-5583/Greywizard+Marked+By+Kane.htm">http://www.tthfanfic.org/Story-5583/Greywizard+Marked+By+Kane.htm</a>.
<br /><a href="http://www.tthfanfic.org/T-99999999/Story-26448-15/batzulger+Willow+Rosenberg+and+the+Mind+Riders.htm">http://www.tthfanfic.org/T-99999999/Story-26448-15/batzulger+Willow+Rosenberg+and+the+Mind+Riders.htm</a>.
</dd>
</dl>
+23 -28
View File
@@ -41,23 +41,24 @@ import ConfigParser
## Console page first, you will get a django version mismatch error when you
## to go hit one of the application pages. Just change a file again, and
## make sure to hit an app page before the SDK page to clear it.
os.environ['DJANGO_SETTINGS_MODULE'] = 'settings'
from google.appengine.dist import use_library
use_library('django', '1.2')
#os.environ['DJANGO_SETTINGS_MODULE'] = 'settings'
#from google.appengine.dist import use_library
#use_library('django', '1.2')
from google.appengine.ext import db
from google.appengine.api import taskqueue
from google.appengine.api import users
from google.appengine.ext import webapp
#from google.appengine.ext import webapp
import webapp2
from google.appengine.ext.webapp import template
from google.appengine.ext.webapp import util
#from google.appengine.ext.webapp2 import util
from google.appengine.runtime import DeadlineExceededError
from ffstorage import *
from fanficdownloader import adapters, writers, exceptions
class UserConfigServer(webapp.RequestHandler):
class UserConfigServer(webapp2.RequestHandler):
def getUserConfig(self,user):
config = ConfigParser.SafeConfigParser()
@@ -73,7 +74,7 @@ class UserConfigServer(webapp.RequestHandler):
return config
class MainHandler(webapp.RequestHandler):
class MainHandler(webapp2.RequestHandler):
def get(self):
user = users.get_current_user()
if user:
@@ -160,7 +161,7 @@ class EditConfigServer(UserConfigServer):
self.response.out.write(template.render(path, template_values))
class FileServer(webapp.RequestHandler):
class FileServer(webapp2.RequestHandler):
def get(self):
fileId = self.request.get('id')
@@ -221,7 +222,7 @@ class FileServer(webapp.RequestHandler):
path = os.path.join(os.path.dirname(__file__), 'status.html')
self.response.out.write(template.render(path, template_values))
class FileStatusServer(webapp.RequestHandler):
class FileStatusServer(webapp2.RequestHandler):
def get(self):
user = users.get_current_user()
if not user:
@@ -257,7 +258,7 @@ class FileStatusServer(webapp.RequestHandler):
path = os.path.join(os.path.dirname(__file__), 'status.html')
self.response.out.write(template.render(path, template_values))
class ClearRecentServer(webapp.RequestHandler):
class ClearRecentServer(webapp2.RequestHandler):
def get(self):
user = users.get_current_user()
if not user:
@@ -282,7 +283,7 @@ class ClearRecentServer(webapp.RequestHandler):
logging.info('Deleted %d instances download.' % num)
self.redirect("/?error=recentcleared")
class RecentFilesServer(webapp.RequestHandler):
class RecentFilesServer(webapp2.RequestHandler):
def get(self):
user = users.get_current_user()
if not user:
@@ -556,20 +557,14 @@ def urlEscape(data):
p = re.compile(r'([^\w])')
return p.sub(toPercentDecimal, data.encode("utf-8"))
def main():
application = webapp.WSGIApplication([('/', MainHandler),
('/fdowntask', FanfictionDownloaderTask),
('/fdown', FanfictionDownloader),
(r'/file.*', FileServer),
('/status', FileStatusServer),
('/recent', RecentFilesServer),
('/editconfig', EditConfigServer),
('/clearrecent', ClearRecentServer),
],
debug=False)
util.run_wsgi_app(application)
if __name__ == '__main__':
logging.getLogger().setLevel(logging.DEBUG)
main()
logging.getLogger().setLevel(logging.DEBUG)
app = webapp2.WSGIApplication([('/', MainHandler),
('/fdowntask', FanfictionDownloaderTask),
('/fdown', FanfictionDownloader),
(r'/file.*', FileServer),
('/status', FileStatusServer),
('/recent', RecentFilesServer),
('/editconfig', EditConfigServer),
('/clearrecent', ClearRecentServer),
],
debug=False)
-9
View File
@@ -43,15 +43,6 @@
<div id='greeting'>
<p>Hi, {{ nickname }}! These are the fanfics you've recently requested.</p>
<p><a href="/clearrecent">Clear your Recent Downloads List</a></p>
<h3>Please Switch to <a href="http://fanfictiondownloader.appspot.com/">New Version</a></h3>
<p>
We have a new, more efficient, version of the system up now. Please start using the
<a href="http://fanfictiondownloader.appspot.com/">New
Version here</a>. If for some reason, the new version
doesn't work for you, please let us know on
the <a href="http://groups.google.com/group/fanfic-downloader">Fanfiction
Downloader Google Group</a>.
</p>
</div>
</div>
-9
View File
@@ -66,15 +66,6 @@
</div>
{% endif %}
<p>See your personal list of <a href="/recent">previously downloaded fanfics</a>.</p>
<h3>Please Switch to <a href="http://fanfictiondownloader.appspot.com/">New Version</a></h3>
<p>
We have a new, more efficient, version of the system up now. Please start using the
<a href="http://fanfictiondownloader.appspot.com/">New
Version here</a>. If for some reason, the new version
doesn't work for you, please let us know on
the <a href="http://groups.google.com/group/fanfic-downloader">Fanfiction
Downloader Google Group</a>.
</p>
</div>
<div style='text-align: center'>
<img src="http://code.google.com/appengine/images/appengine-silver-120x30.gif"
+11 -14
View File
@@ -25,15 +25,16 @@ Copyright 2011 Fanficdownloader team
import datetime
import logging
from google.appengine.ext.webapp import util
from google.appengine.ext import webapp
#from google.appengine.ext.webapp import util
import webapp2
#from google.appengine.ext import webapp
from google.appengine.api import users
from google.appengine.api import taskqueue
from google.appengine.api import memcache
from ffstorage import *
class Remover(webapp.RequestHandler):
class Remover(webapp2.RequestHandler):
def get(self):
logging.debug("Starting r3m0v3r")
user = users.get_current_user()
@@ -56,9 +57,10 @@ class Remover(webapp.RequestHandler):
logging.debug('Delete '+d.url)
logging.info('Deleted instances: %d' % num)
self.response.headers['Content-Type'] = 'text/html'
self.response.out.write('Deleted instances: %d<br>' % num)
class RemoveOrphanDataChunks(webapp.RequestHandler):
class RemoveOrphanDataChunks(webapp2.RequestHandler):
def get(self):
logging.debug("Starting RemoveOrphanDataChunks")
@@ -98,15 +100,10 @@ class RemoveOrphanDataChunks(webapp.RequestHandler):
memcache.set('orphan_search_cursor',chunks.cursor())
logging.info('Deleted %d orphan chunks from %d total.' % (deleted,num))
self.response.headers['Content-Type'] = 'text/html'
self.response.out.write('Deleted %d orphan chunks from %d total.' % (deleted,num))
def main():
application = webapp.WSGIApplication([('/r3m0v3r', Remover),
('/r3m0v3rOrphans', RemoveOrphanDataChunks)],
debug=False)
util.run_wsgi_app(application)
if __name__ == '__main__':
logging.getLogger().setLevel(logging.DEBUG)
main()
logging.getLogger().setLevel(logging.DEBUG)
app = webapp2.WSGIApplication([('/r3m0v3r', Remover),
('/r3m0v3rOrphans', RemoveOrphanDataChunks)],
debug=False)
+8 -13
View File
@@ -18,15 +18,16 @@
import datetime
import logging
from google.appengine.ext.webapp import util
from google.appengine.ext import webapp
#from google.appengine.ext.webapp import util
import webapp2
#from google.appengine.ext import webapp
from google.appengine.api import users
from google.appengine.api import taskqueue
from google.appengine.api import memcache
from ffstorage import *
class Tally(webapp.RequestHandler):
class Tally(webapp2.RequestHandler):
def get(self):
logging.debug("Starting Tally")
user = users.get_current_user()
@@ -57,13 +58,7 @@ class Tally(webapp.RequestHandler):
logging.info('Tallied %d fics.' % num)
self.response.out.write('<br/>Tallied %d fics.<br/>' % num)
def main():
application = webapp.WSGIApplication([('/tally', Tally),
],
debug=False)
util.run_wsgi_app(application)
if __name__ == '__main__':
logging.getLogger().setLevel(logging.DEBUG)
main()
logging.getLogger().setLevel(logging.DEBUG)
app = webapp2.WSGIApplication([('/tally', Tally),
],
debug=False)