Compare commits

...
Author SHA1 Message Date
Jim Miller 60dc17c32c Fixes for fanfiction.net's latest changes. 2012-06-05 23:45:03 -05:00
Jim Miller ebd22ff966 Tweak plugin chapter range, bump appspot version. 2012-05-31 18:52:45 -05:00
Ida ddabc4141a Fixed list index out of range error 2012-05-31 16:08:01 -04:00
Jim Miller 530add1771 Plugin: Allow chapter range download on non-update. "URL[begin,end]" 2012-05-31 14:47:01 -05:00
Jim Miller 47cbe5ba5c Default to *not* update cover in epub on update. Add options to force update.
Most of the complexity is just keeping the old cover--FFDL remakes the epub.
Also pass META-INF/calibre_bookmarks.txt.
2012-05-31 13:03:22 -05:00
Jim Miller 1089ea4658 Integrate www.ik-eternal.net--no version bump yet. 2012-05-30 16:48:52 -05:00
Jim Miller 07e9b6da81 Make thehexfiles.net accept www.thehexfiles.net too. 2012-05-30 16:47:56 -05:00
Jim Miller 5d4c8bc44b Minor clean up on ik-eternal.net. 2012-05-30 11:15:24 -05:00
Ida 5f1e7b33b6 First version of the adapter for ik-eternal.net 2012-05-30 00:46:41 -04:00
Jim Miller e823925929 Added tag calibre-plugin-1.5.26 for changeset df4e887cc582 2012-05-29 22:54:24 -05:00
Jim Miller a7eedfd517 Added tag FanFictionDownLoader-4.4.13 for changeset df4e887cc582 2012-05-29 22:54:12 -05:00
Jim Miller e6a32ae300 Forgot to add option to web site announcement. 2012-05-29 22:53:55 -05:00
Jim Miller 60a6d32819 Integrate dokuga.com, bump versions. 2012-05-29 22:30:43 -05:00
Jim Miller 421876743a Merge dokugacom 2012-05-29 20:19:56 -05:00
Ida b39ba3b106 First version of the adapter for the dokuga.com 2012-05-29 21:14:52 -04:00
Jim Miller 46d7305cb3 Make text wrap width an option. 2012-05-28 17:43:18 -05:00
Jim Miller 536e5cf4b9 Added tag FanFictionDownLoader-4.4.12a for changeset 6c79e16c256c 2012-05-27 15:46:50 -05:00
Jim Miller fb3b0f82dd Added tag calibre-plugin-1.5.25 for changeset 6c79e16c256c 2012-05-27 15:46:34 -05:00
Jim Miller 617ba5a149 Fix ffnet genre, characters, status. 2012-05-27 15:46:08 -05:00
Jim Miller ae464a718a Added tag FanFictionDownLoader-4.4.12 for changeset 6ac620498226 2012-05-25 17:04:50 -05:00
Jim Miller ffbf5ec3b5 Added tag calibre-plugin-1.5.24 for changeset 6ac620498226 2012-05-25 17:04:24 -05:00
Jim Miller b337c9aa79 Integrate new adapter for thehexfiles.net, new inject series plugin feature. 2012-05-25 17:03:46 -05:00
Ida 9402cd9076 First version of the adapter for the thehexfiles.net 2012-05-25 15:08:51 -04:00
Jim Miller 5b5e8a3a14 Added tag FanFictionDownLoader-4.4.11 for changeset a09543417484 2012-05-20 10:43:12 -05:00
Jim Miller d5ff2c477a Added tag calibre-plugin-1.5.23 for changeset a09543417484 2012-05-20 10:42:47 -05:00
Jim Miller bc233d527a Integrate 8 new sites from Ida, plus a couple minor fixes. 2012-05-20 10:42:32 -05:00
Ida 2d8c13728d Changed the way title is processed for sycophanthex.com 2012-05-20 10:57:39 -04:00
Ida f680d997ce First version of adapter for sycophanthex.com,
phoenixsong.net, dramione.org, and walkingtheplank.org
Plus a quick correction to checkmated.com
2012-05-19 20:56:43 -04:00
Jim Miller 6040d69bf1 Added tag FanFictionDownLoader-4.4.10 for changeset 24c3362b0f89 2012-05-18 15:46:32 -05:00
Jim Miller f7e276c29c Added tag calibre-plugin-1.5.22 for changeset 24c3362b0f89 2012-05-18 15:46:09 -05:00
Jim Miller 86375876a4 Integrate new adapter www.checkmated.com. 2012-05-18 15:45:44 -05:00
Ida a67e3a7234 Quick change for the summary colleciton in checkmated.com 2012-05-18 16:34:40 -04:00
Ida 73cefeb858 First version of Checkmated.com adapter 2012-05-18 15:37:29 -04:00
Jim Miller d87e79d379 Added tag calibre-plugin-1.5.21 for changeset 831c272dde3a 2012-05-18 12:11:32 -05:00
Jim Miller 5072572f1c Plugin only, optionally search epub text for story URL, option to GC only new. 2012-05-18 12:11:16 -05:00
Jim Miller c4bbf3f072 Added tag FanFictionDownLoader-4.4.9 for changeset 5b585e031b72 2012-05-12 18:49:02 -05:00
Jim Miller 6413c52584 Added tag calibre-plugin-1.5.20 for changeset 5b585e031b72 2012-05-12 18:48:40 -05:00
Jim Miller 37bc1306c9 Integrate new adapters www.wraithbait.com and www.libraryofmoria.com. 2012-05-12 18:47:22 -05:00
Ida 7f8c39227f Fixed dates and rating for WraithBait.com 2012-05-12 18:44:40 -04:00
Jim Miller d4988545b5 Merge 2012-05-12 16:00:28 -05:00
Jim Miller 5ceb96c913 Adding WWOMB(www.squidge.org/peja) adapter. Some infrastructure changes to
allow config section [www.squidge.org/peja].  More needed to support other sites
under www.squidge.org.
2012-05-12 15:58:51 -05:00
Ida 3d735e430d First version of Libraryofmoria.com and Wraithbait.com adapters 2012-05-10 17:38:12 -04:00
Jim Miller 3ccb895c7b Added tag calibre-plugin-1.5.18 for changeset 3beaa4617bd3 2012-05-08 10:43:26 -05:00
Jim Miller f0a1e1d471 Plugin--Add feature to integrate with Generate Cover plugin by kiwidude. 2012-05-08 10:43:02 -05:00
Jim Miller 3719e9860c Added tag CLI-4.4.8a for changeset d38c36148dc4 2012-04-25 21:53:28 -05:00
Jim Miller ea43dffe0c Added tag calibre-plugin-1.5.16 for changeset d38c36148dc4 2012-04-25 21:53:09 -05:00
Jim Miller 0a2cff3469 Yet more fixes for poor parsing of numeric entities--this time, my poor parsing. 2012-04-25 21:52:56 -05:00
Jim Miller 3cb92f48cc Added tag FanFictionDownLoader-4.4.8 for changeset 8fc7a6cc2d87 2012-04-22 10:10:08 -05:00
Jim Miller e5cc4ebbd5 Bump Web/CLI version. 2012-04-22 10:09:44 -05:00
Jim Miller c6c67f99ca Moved tag calibre-plugin-1.5.15 to changeset a1a840bcd4c9 (from changeset bac4028b803d) 2012-04-22 09:55:58 -05:00
Jim Miller c75e62d07e Merge fimfiction changes to trunk. 2012-04-22 09:55:39 -05:00
Jim Miller e9b203eb57 Added tag calibre-plugin-1.5.15 for changeset bac4028b803d 2012-04-21 21:37:27 -05:00
Jim Miller a2eaa9fb22 Fix for ArchiveOfOurOwn site change. 2012-04-21 21:37:16 -05:00
althaine 0cf5ec9880 Updated fimfic.net adapter to use provided API 2012-04-20 20:36:20 +10:00
Jim Miller 465e25d3e6 Added tag FanFictionDownLoader-4.4.7 for changeset c8ab1f6bbd57 2012-04-19 12:19:06 -05:00
Jim Miller 0c85cf1d10 Web- Add list of all downloads feature to web service. 2012-04-19 12:18:40 -05:00
Jim Miller 7f7a1a983c Plugin-Fix setting status column with no status available(fictionalley). 2012-04-19 12:14:51 -05:00
Jim Miller 6f4be261ef Fix Japanese in CLI & web version. Broke it in 443 and didn't notice. 2012-04-18 17:54:42 -05:00
Jim Miller 04eb551d48 Added tag CLI-4.4.6 for changeset b69d6004ae25 2012-04-17 14:07:50 -05:00
Jim Miller 6299fc7582 Added tag calibre-plugin-1.5.14 for changeset b69d6004ae25 2012-04-17 14:07:29 -05:00
Jim Miller c2d7b4ecce Change plugin 'images' checkbox to add to [epubs], kludge for fimfiction images 2012-04-17 14:07:19 -05:00
Jim Miller 01b14701a0 Moved tag calibre-plugin-1.5.13 to changeset b55fabb0b8c9 (from changeset b0720fc31c10) 2012-04-11 11:11:43 -05:00
Jim Miller 08aa677855 Fix for Python GC'ing menu objects with no explicit Python references. 2012-04-11 11:11:25 -05:00
Jim Miller bd477d2696 Added tag FanFictionDownLoader-4.4.5 for changeset b0720fc31c10 2012-04-10 09:43:20 -05:00
Jim Miller 1f3220a221 Added tag calibre-plugin-1.5.13 for changeset b0720fc31c10 2012-04-10 09:42:32 -05:00
Jim Miller b4a8361df9 Package Ida's new archive.skyehawke.com adapter for release. 2012-04-10 09:42:01 -05:00
Ida e647b0e69b First version adapter for archive.skyehawke.com 2012-04-10 01:59:34 -04:00
Jim Miller a5fd8646b7 Added tag calibre-plugin-1.5.12 for changeset 6145294332cd 2012-04-09 11:35:25 -05:00
45 changed files with 4985 additions and 266 deletions
+78
View File
@@ -0,0 +1,78 @@
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN">
<html>
<head>
<link href="/css/index.css" rel="stylesheet" type="text/css">
<title>FanFictionDownLoader (fanfiction.net, fanficauthors, fictionalley, ficwad to epub and HTML)</title>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
<script type="text/javascript">
var _gaq = _gaq || [];
_gaq.push(['_setAccount', 'UA-12136939-1']);
_gaq.push(['_trackPageview']);
(function() {
var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true;
ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s);
})();
</script>
</head>
<body>
<div id='main'>
<h1>
<a href="/" style="text-decoration: none; color: black;">FanFictionDownLoader</a>
</h1>
<script type="text/javascript"><!--
google_ad_client = "ca-pub-0320924304307555";
/* Standard */
google_ad_slot = "8974025478";
google_ad_width = 468;
google_ad_height = 60;
//-->
</script>
<script type="text/javascript"
src="http://pagead2.googlesyndication.com/pagead/show_ads.js">
</script>
<!-- <div id='yourfile'> -->
{{yourfile}}
<!-- </div> -->
<div id='helpbox'>
{% for fic in fics %}
<p>
<a href="{{ fic.url }}" title="Link to original story"><span class="recent"><i>{{ fic.title }}</i></span></a>
by <a href="{{ fic.authorUrl }}">{{ fic.author }}</a> <b>Download Count:</b> {{ fic.count }} <br />
<b>Word Count:</b> {{ fic.numWords }} <b>Chapter Count:</b> {{ fic.numChapters }}<br />
{% if fic.category %} <b>Categories:</b> {{ fic.category }} <br /> {% endif %}
{% if fic.genre %} <b>Genres:</b> {{ fic.genre }} <br /> {% endif %}
{% if fic.language %} <b>Language:</b> {{ fic.language }} <br /> {% endif %}
{% if fic.series %} <b>Series:</b> {{ fic.series }} <br /> {% endif %}
{% if fic.characters %} <b>Characters:</b> {{ fic.characters }} <br /> {% endif %}
{% if fic.status %} <b>Status:</b> {{ fic.status }} <br /> {% endif %}
{% if fic.datePublished %} <b>Published:</b> {{ fic.datePublished }} <br /> {% endif %}
{% if fic.dateUpdated %} <b>Last Updated:</b> {{ fic.dateUpdated }} <br /> {% endif %}
{% if fic.dateCreated %} <b>Last Downloaded:</b> {{ fic.dateCreated }} <br /> {% endif %}
{% if fic.rating %} <b>Rating:</b> {{ fic.rating }} <br /> {% endif %}
{% if fic.warnings %} <b>Warnings:</b> {{ fic.warnings }} <br /> {% endif %}
{% if fic.description %} <b>Summary:</b> {{ fic.description }} <br /> {% endif %}
</p>
{% endfor %}
</div>
<script type="text/javascript"><!--
google_ad_client = "ca-pub-0320924304307555";
/* Standard */
google_ad_slot = "8974025478";
google_ad_width = 468;
google_ad_height = 60;
//-->
</script>
<script type="text/javascript"
src="http://pagead2.googlesyndication.com/pagead/show_ads.js">
</script>
</div>
</body>
</html>
+3 -3
View File
@@ -1,6 +1,6 @@
# ffd-retief-hrd fanfictiondownloader
application: fanfictiondownloader
version: 4-4-4
version: 4-4-14
runtime: python27
api_version: 1
threadsafe: true
@@ -35,8 +35,8 @@ handlers:
- url: /.*
script: main.app
builtins:
- datastore_admin: on
#builtins:
#- datastore_admin: on
libraries:
- name: django
+1 -1
View File
@@ -27,7 +27,7 @@ class FanFictionDownLoaderBase(InterfaceActionBase):
description = 'UI plugin to download FanFiction stories from various sites.'
supported_platforms = ['windows', 'osx', 'linux']
author = 'Jim Miller'
version = (1, 5, 12)
version = (1, 5, 27)
minimum_calibre_version = (0, 8, 30)
#: This field defines the GUI plugin class that contains all the code
+1 -1
View File
@@ -1,6 +1,6 @@
<hr />
<p>Created by Jim Miller, borrowing heavily from Grant Drake's
<p>Plugin created by Jim Miller, borrowing heavily from Grant Drake's
'<a href="http://www.mobileread.com/forums/showthread.php?t=134856">Reading List</a>',
'<a href="http://www.mobileread.com/forums/showthread.php?t=126727">Extract ISBN</a>' and
'<a href="http://www.mobileread.com/forums/showthread.php?t=134000">Count Pages</a>'
+147 -26
View File
@@ -9,16 +9,17 @@ __docformat__ = 'restructuredtext en'
import traceback, copy
from PyQt4.Qt import (QDialog, QWidget, QVBoxLayout, QHBoxLayout, QLabel, QLineEdit, QFont,
QTextEdit, QComboBox, QCheckBox, QPushButton, QTabWidget, QVariant)
from PyQt4.Qt import (QDialog, QWidget, QVBoxLayout, QHBoxLayout, QLabel, QLineEdit, QFont, QWidget,
QTextEdit, QComboBox, QCheckBox, QPushButton, QTabWidget, QVariant, QScrollArea)
from calibre.gui2 import dynamic, info_dialog
from calibre.utils.config import JSONConfig
from calibre.gui2.ui import get_gui
from calibre_plugins.fanfictiondownloader_plugin.dialogs \
import (SKIP, ADDNEW, UPDATE, UPDATEALWAYS, OVERWRITE, OVERWRITEALWAYS,
CALIBREONLY,collision_order)
import (UPDATE, UPDATEALWAYS, OVERWRITE, collision_order)
from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.adapters import getConfigSections
from calibre_plugins.fanfictiondownloader_plugin.common_utils \
import ( get_library_uuid, KeyboardConfigDialog )
@@ -38,6 +39,7 @@ all_prefs.defaults['personal.ini'] = get_resources('plugin-example.ini')
all_prefs.defaults['updatemeta'] = True
all_prefs.defaults['updatecover'] = False
all_prefs.defaults['updateepubcover'] = False
all_prefs.defaults['keeptags'] = False
all_prefs.defaults['urlsfromclip'] = True
all_prefs.defaults['updatedefault'] = True
@@ -46,6 +48,8 @@ all_prefs.defaults['collision'] = OVERWRITE
all_prefs.defaults['deleteotherforms'] = False
all_prefs.defaults['adddialogstaysontop'] = False
all_prefs.defaults['includeimages'] = False
all_prefs.defaults['lookforurlinhtml'] = False
all_prefs.defaults['injectseries'] = False
all_prefs.defaults['send_lists'] = ''
all_prefs.defaults['read_lists'] = ''
@@ -53,6 +57,10 @@ all_prefs.defaults['addtolists'] = False
all_prefs.defaults['addtoreadlists'] = False
all_prefs.defaults['addtolistsonread'] = False
all_prefs.defaults['gcnewonly'] = False
all_prefs.defaults['gc_site_settings'] = {}
all_prefs.defaults['allow_gc_from_ini'] = True
all_prefs.defaults['custom_cols'] = {}
# The list of settings to copy from all_prefs or the previous library
@@ -60,6 +68,7 @@ all_prefs.defaults['custom_cols'] = {}
copylist = ['personal.ini',
'updatemeta',
'updatecover',
'updateepubcover',
'keeptags',
'urlsfromclip',
'updatedefault',
@@ -67,7 +76,12 @@ copylist = ['personal.ini',
'collision',
'deleteotherforms',
'adddialogstaysontop',
'includeimages']
'includeimages',
'lookforurlinhtml',
'injectseries',
'gcnewonly',
'gc_site_settings',
'allow_gc_from_ini']
# fake out so I don't have to change the prefs calls anywhere. The
# Java programmer in me is offended by op-overloading, but it's very
@@ -87,7 +101,8 @@ class PrefsFacade():
self.all_prefs[libraryid] = dict(self._get_copylist_prefs(self.all_prefs))
else:
self.all_prefs[libraryid] = dict(self._get_copylist_prefs(self.all_prefs[self.lastlibid]))
self.lastlibid = libraryid
self.lastlibid = libraryid
return self.all_prefs[libraryid]
@@ -139,10 +154,15 @@ class ConfigWidget(QWidget):
self.personalini_tab = PersonalIniTab(self, plugin_action)
tab_widget.addTab(self.personalini_tab, 'personal.ini')
self.list_tab = ListTab(self, plugin_action)
tab_widget.addTab(self.list_tab, 'Reading Lists')
self.readinglist_tab = ReadingListTab(self, plugin_action)
tab_widget.addTab(self.readinglist_tab, 'Reading Lists')
if 'Reading List' not in plugin_action.gui.iactions:
self.list_tab.setEnabled(False)
self.readinglist_tab.setEnabled(False)
self.generatecover_tab = GenerateCoverTab(self, plugin_action)
tab_widget.addTab(self.generatecover_tab, 'Generate Cover')
if 'Generate Cover' not in plugin_action.gui.iactions:
self.generatecover_tab.setEnabled(False)
self.columns_tab = ColumnsTab(self, plugin_action)
tab_widget.addTab(self.columns_tab, 'Custom Columns')
@@ -158,22 +178,25 @@ class ConfigWidget(QWidget):
prefs['collision'] = unicode(self.basic_tab.collision.currentText())
prefs['updatemeta'] = self.basic_tab.updatemeta.isChecked()
prefs['updatecover'] = self.basic_tab.updatecover.isChecked()
prefs['updateepubcover'] = self.basic_tab.updateepubcover.isChecked()
prefs['keeptags'] = self.basic_tab.keeptags.isChecked()
prefs['urlsfromclip'] = self.basic_tab.urlsfromclip.isChecked()
prefs['updatedefault'] = self.basic_tab.updatedefault.isChecked()
prefs['deleteotherforms'] = self.basic_tab.deleteotherforms.isChecked()
prefs['adddialogstaysontop'] = self.basic_tab.adddialogstaysontop.isChecked()
prefs['includeimages'] = self.basic_tab.includeimages.isChecked()
prefs['lookforurlinhtml'] = self.basic_tab.lookforurlinhtml.isChecked()
prefs['injectseries'] = self.basic_tab.injectseries.isChecked()
if self.list_tab:
if self.readinglist_tab:
# lists
prefs['send_lists'] = ', '.join(map( lambda x : x.strip(), filter( lambda x : x.strip() != '', unicode(self.list_tab.send_lists_box.text()).split(','))))
prefs['read_lists'] = ', '.join(map( lambda x : x.strip(), filter( lambda x : x.strip() != '', unicode(self.list_tab.read_lists_box.text()).split(','))))
prefs['send_lists'] = ', '.join(map( lambda x : x.strip(), filter( lambda x : x.strip() != '', unicode(self.readinglist_tab.send_lists_box.text()).split(','))))
prefs['read_lists'] = ', '.join(map( lambda x : x.strip(), filter( lambda x : x.strip() != '', unicode(self.readinglist_tab.read_lists_box.text()).split(','))))
# print("send_lists: %s"%prefs['send_lists'])
# print("read_lists: %s"%prefs['read_lists'])
prefs['addtolists'] = self.list_tab.addtolists.isChecked()
prefs['addtoreadlists'] = self.list_tab.addtoreadlists.isChecked()
prefs['addtolistsonread'] = self.list_tab.addtolistsonread.isChecked()
prefs['addtolists'] = self.readinglist_tab.addtolists.isChecked()
prefs['addtoreadlists'] = self.readinglist_tab.addtoreadlists.isChecked()
prefs['addtolistsonread'] = self.readinglist_tab.addtolistsonread.isChecked()
# personal.ini
ini = unicode(self.personalini_tab.ini.toPlainText())
@@ -183,6 +206,17 @@ class ConfigWidget(QWidget):
# if they've removed everything, reset to default.
prefs['personal.ini'] = get_resources('plugin-example.ini')
# Generate Covers tab
prefs['gcnewonly'] = self.generatecover_tab.gcnewonly.isChecked()
gc_site_settings = {}
for (site,combo) in self.generatecover_tab.gc_dropdowns.iteritems():
val = unicode(combo.itemData(combo.currentIndex()).toString())
if val != 'none':
gc_site_settings[site] = val
#print("gc_site_settings[%s]:%s"%(site,gc_site_settings[site]))
prefs['gc_site_settings'] = gc_site_settings
prefs['allow_gc_from_ini'] = self.generatecover_tab.allow_gc_from_ini.isChecked()
# Custom Columns tab
colsmap = {}
for (col,combo) in self.columns_tab.custcol_dropdowns.iteritems():
@@ -191,7 +225,7 @@ class ConfigWidget(QWidget):
colsmap[col] = val
#print("colsmap[%s]:%s"%(col,colsmap[col]))
prefs['custom_cols'] = colsmap
def edit_shortcuts(self):
self.save_settings()
# Force the menus to be rebuilt immediately, so we have all our actions registered
@@ -214,9 +248,11 @@ class BasicTab(QWidget):
label.setWordWrap(True)
self.l.addWidget(label)
self.l.addSpacing(5)
tooltip = "On each download, FFDL offers an option to select the output format. <br />This sets what that option will default to."
horz = QHBoxLayout()
label = QLabel('Default Output &Format:')
label.setToolTip(tooltip)
horz.addWidget(label)
self.fileform = QComboBox(self)
self.fileform.addItem('epub')
@@ -224,15 +260,16 @@ class BasicTab(QWidget):
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.')
self.fileform.setToolTip(tooltip)
self.fileform.activated.connect(self.set_collisions)
label.setBuddy(self.fileform)
horz.addWidget(self.fileform)
self.l.addLayout(horz)
tooltip = "On each download, FFDL offers an option of what happens if that story already exists. <br />This sets what that option will default to."
horz = QHBoxLayout()
label = QLabel('Default If Story Already Exists?')
label.setToolTip("What to do if there's already an existing story with the same title and author.")
label.setToolTip(tooltip)
horz.addWidget(label)
self.collision = QComboBox(self)
# add collision options
@@ -240,18 +277,23 @@ class BasicTab(QWidget):
i = self.collision.findText(prefs['collision'])
if i > -1:
self.collision.setCurrentIndex(i)
# self.collision.setToolTip('Overwrite will replace the existing story. Add New will create a new story with the same title and author.')
self.collision.setToolTip(tooltip)
label.setBuddy(self.collision)
horz.addWidget(self.collision)
self.l.addLayout(horz)
self.updatemeta = QCheckBox('Default Update Calibre &Metadata?',self)
self.updatemeta.setToolTip('Update title, author, URL, tags, custom columns, etc for story in Calibre from web site.')
self.updatemeta.setToolTip("On each download, FFDL offers an option to update Calibre's metadata (title, author, URL, tags, custom columns, etc) from the web site. <br />This sets whether that will default to on or off.")
self.updatemeta.setChecked(prefs['updatemeta'])
self.l.addWidget(self.updatemeta)
self.updatecover = QCheckBox('Update Cover when Updating Metadata?',self)
self.updatecover.setToolTip("Update cover image from EPUB when metadata is updated. (EPUB only.)\nDoesn't go looking for new images on 'Update Calibre Metadata Only'.")
self.updateepubcover = QCheckBox('Default Update EPUB Cover when Updating EPUB?',self)
self.updateepubcover.setToolTip("On each download, FFDL offers an option to update the book cover image <i>inside</i> the EPUB from the web site when the EPUB is updated.<br />This sets whether that will default to on or off.")
self.updateepubcover.setChecked(prefs['updateepubcover'])
self.l.addWidget(self.updateepubcover)
self.updatecover = QCheckBox('Update Calibre Cover when Updating Metadata?',self)
self.updatecover.setToolTip("Update calibre book cover image from EPUB when metadata is updated. (EPUB only.)\nDoesn't go looking for new images on 'Update Calibre Metadata Only'.")
self.updatecover.setChecked(prefs['updatecover'])
self.l.addWidget(self.updatecover)
@@ -283,10 +325,20 @@ class BasicTab(QWidget):
# this is a cheat to make it easier for users to realize there's a new include_images features.
self.includeimages = QCheckBox("Include images in EPUBs?",self)
self.includeimages.setToolTip("Download and include images in EPUB stories. This is equivalent to adding:\n\n[defaults]\ninclude_images:true\nkeep_summary_html:true\nmake_firstimage_cover:true\n\n ...to the top of personal.ini. Your settings in personal.ini will override this.")
self.includeimages.setToolTip("Download and include images in EPUB stories. This is equivalent to adding:\n\n[epub]\ninclude_images:true\nkeep_summary_html:true\nmake_firstimage_cover:true\n\n ...to the top of personal.ini. Your settings in personal.ini will override this.")
self.includeimages.setChecked(prefs['includeimages'])
self.l.addWidget(self.includeimages)
self.lookforurlinhtml = QCheckBox("Search EPUB text for Story URL?",self)
self.lookforurlinhtml.setToolTip("Look for first valid story URL inside EPUB text if not found in metadata.\nSomewhat risky, could find wrong URL depending on EPUB content.\nAlso finds and corrects bad ffnet URLs from ficsaver.com files.")
self.lookforurlinhtml.setChecked(prefs['lookforurlinhtml'])
self.l.addWidget(self.lookforurlinhtml)
self.injectseries = QCheckBox("Inject calibre Series when none found?",self)
self.injectseries.setToolTip("If no series is found, inject the calibre series (if there is one) so it appears on the FFDL title page(not cover).")
self.injectseries.setChecked(prefs['injectseries'])
self.l.addWidget(self.injectseries)
self.l.insertStretch(-1)
def set_collisions(self):
@@ -372,7 +424,7 @@ class ShowDefaultsIniDialog(QDialog):
self.ok_button.clicked.connect(self.hide)
self.l.addWidget(self.ok_button)
class ListTab(QWidget):
class ReadingListTab(QWidget):
def __init__(self, parent_dialog, plugin_action):
self.parent_dialog = parent_dialog
@@ -432,6 +484,75 @@ class ListTab(QWidget):
self.l.insertStretch(-1)
class GenerateCoverTab(QWidget):
def __init__(self, parent_dialog, plugin_action):
self.parent_dialog = parent_dialog
self.plugin_action = plugin_action
QWidget.__init__(self)
self.l = QVBoxLayout()
self.setLayout(self.l)
try:
gc_plugin = plugin_action.gui.iactions['Generate Cover']
gc_settings = gc_plugin.get_saved_setting_names()
except KeyError:
gc_settings= []
label = QLabel('The Generate Cover plugin can create cover images for books using various metadata and configurations. If you have GC installed, FFDL can run GC on new downloads and metadata updates. Pick a GC setting by site or Default.')
label.setWordWrap(True)
self.l.addWidget(label)
self.l.addSpacing(5)
scrollable = QScrollArea()
scrollcontent = QWidget()
scrollable.setWidget(scrollcontent)
scrollable.setWidgetResizable(True)
self.l.addWidget(scrollable)
self.sl = QVBoxLayout()
scrollcontent.setLayout(self.sl)
self.gc_dropdowns = {}
sitelist = getConfigSections()
sitelist.sort()
sitelist.insert(0,u"Default")
for site in sitelist:
horz = QHBoxLayout()
label = QLabel(site)
if site == u"Default":
s = "On Metadata update, run Generate Cover with this setting, if not selected for specific site."
else:
s = "On Metadata update, run Generate Cover with this setting for %s stories."%site
label.setToolTip(s)
horz.addWidget(label)
dropdown = QComboBox(self)
dropdown.setToolTip(s)
dropdown.addItem('',QVariant('none'))
for setting in gc_settings:
dropdown.addItem(setting,QVariant(setting))
self.gc_dropdowns[site] = dropdown
if site in prefs['gc_site_settings']:
dropdown.setCurrentIndex(dropdown.findData(QVariant(prefs['gc_site_settings'][site])))
horz.addWidget(dropdown)
self.sl.addLayout(horz)
self.gcnewonly = QCheckBox("Run Generate Cover Only on New Books",self)
self.gcnewonly.setToolTip("Default is to run GC any time the calibre metadata is updated.")
self.gcnewonly.setChecked(prefs['gcnewonly'])
self.l.addWidget(self.gcnewonly)
self.allow_gc_from_ini = QCheckBox('Allow generate_cover_settings from personal.ini to override.',self)
self.allow_gc_from_ini.setToolTip("The personal.ini parameter generate_cover_settings allows you to choose a GC setting based on metadata rather than site, but it's much more complex.<br \>generate_cover_settings is ignored when this is off.")
self.allow_gc_from_ini.setChecked(prefs['allow_gc_from_ini'])
self.l.addWidget(self.allow_gc_from_ini)
self.l.insertStretch(-1)
class OtherTab(QWidget):
def __init__(self, parent_dialog, plugin_action):
+17 -2
View File
@@ -83,7 +83,7 @@ class AddNewDialog(SizePersistedDialog):
self.l.addWidget(QLabel('Story URL(s), one per line:'))
self.url = DroppableQTextEdit(self)
self.url.setToolTip('URLs for stories, one per line.\nWill take URLs from clipboard, but only valid URLs.')
self.url.setToolTip('URLs for stories, one per line.\nWill take URLs from clipboard, but only valid URLs.\nAdd [1,5] after the URL to limit the download to chapters 1-5.')
self.url.setLineWrapMode(QTextEdit.NoWrap)
self.url.setText(url_list_text)
self.l.addWidget(self.url)
@@ -123,10 +123,18 @@ class AddNewDialog(SizePersistedDialog):
horz.addWidget(self.collision)
self.l.addLayout(horz)
horz = QHBoxLayout()
self.updatemeta = QCheckBox('Update Calibre &Metadata?',self)
self.updatemeta.setToolTip('Update metadata for story in Calibre from web site?')
self.updatemeta.setChecked(prefs['updatemeta'])
self.l.addWidget(self.updatemeta)
horz.addWidget(self.updatemeta)
self.updateepubcover = QCheckBox('Update EPUB Cover?',self)
self.updateepubcover.setToolTip('Update book cover image from site or defaults (if found) <i>inside</i> the EPUB when EPUB is updated.')
self.updateepubcover.setChecked(prefs['updateepubcover'])
horz.addWidget(self.updateepubcover)
self.l.addLayout(horz)
button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
button_box.accepted.connect(self.accept)
@@ -155,6 +163,7 @@ class AddNewDialog(SizePersistedDialog):
'fileform': unicode(self.fileform.currentText()),
'collision': unicode(self.collision.currentText()),
'updatemeta': self.updatemeta.isChecked(),
'updateepubcover': self.updateepubcover.isChecked(),
}
def get_urlstext(self):
@@ -402,6 +411,11 @@ class UpdateExistingDialog(SizePersistedDialog):
self.updatemeta.setChecked(prefs['updatemeta'])
options_layout.addWidget(self.updatemeta)
self.updateepubcover = QCheckBox('Update EPUB Cover?',self)
self.updateepubcover.setToolTip('Update book cover image from site or defaults (if found) <i>inside</i> the EPUB when EPUB is updated.')
self.updateepubcover.setChecked(prefs['updateepubcover'])
options_layout.addWidget(self.updateepubcover)
button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
button_box.accepted.connect(self.accept)
button_box.rejected.connect(self.reject)
@@ -435,6 +449,7 @@ class UpdateExistingDialog(SizePersistedDialog):
'fileform': unicode(self.fileform.currentText()),
'collision': unicode(self.collision.currentText()),
'updatemeta': self.updatemeta.isChecked(),
'updateepubcover': self.updateepubcover.isChecked(),
}
def display_story_list(gui, header, prefs, icon, books,
+88 -13
View File
@@ -7,11 +7,12 @@ __license__ = 'GPL v3'
__copyright__ = '2012, Jim Miller'
__docformat__ = 'restructuredtext en'
import time, os, copy, threading
import time, os, copy, threading, re
from ConfigParser import SafeConfigParser
from StringIO import StringIO
from functools import partial
from datetime import datetime
from string import Template
from PyQt4.Qt import (QApplication, QMenu, QToolButton)
@@ -35,7 +36,7 @@ from calibre_plugins.fanfictiondownloader_plugin.common_utils import (set_plugin
from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader import adapters, writers, exceptions
from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.htmlcleanup import stripHTML
from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.epubutils import get_dcsource, get_dcsource_chaptercount
from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.epubutils import get_dcsource, get_dcsource_chaptercount, get_story_url_from_html
from calibre_plugins.fanfictiondownloader_plugin.config import (prefs, permitted_values)
from calibre_plugins.fanfictiondownloader_plugin.dialogs import (
@@ -109,6 +110,9 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
# Assign our menu to this action
self.menu = QMenu(self.gui)
self.old_actions_unique_map = {}
# menu_actions is just to keep a live reference to the menu
# items to prevent GC removing it.
self.menu_actions = []
self.qaction.setMenu(self.menu)
self.menu.aboutToShow.connect(self.about_to_show_menu)
@@ -135,6 +139,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
do_user_config = self.interface_action_base_plugin.do_user_config
self.menu.clear()
self.actions_unique_map = {}
self.menu_actions = []
self.add_action = self.create_menu_item_ex(self.menu, '&Add New from URL(s)', image='plus.png',
unique_name='Add New FanFiction Book(s) from URL(s)',
shortcut_name='Add New FanFiction Book(s) from URL(s)',
@@ -227,6 +232,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
ac = create_menu_action_unique(self, parent_menu, menu_text, image, tooltip,
shortcut, triggered, is_checked, shortcut_name, unique_name)
self.actions_unique_map[ac.calibre_shortcut_unique_name] = ac.calibre_shortcut_unique_name
self.menu_actions.append(ac)
return ac
def plugin_button(self):
@@ -380,7 +386,8 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
def get_metadata_for_book(self,book,
options={'fileform':'epub',
'collision':ADDNEW,
'updatemeta':True}):
'updatemeta':True,
'updateepubcover':True}):
'''
Update passed in book dict with metadata from website and
necessary data. To be called from LoopProgressDialog
@@ -396,6 +403,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
fileform = options['fileform']
collision = options['collision']
updatemeta= options['updatemeta']
updateepubcover= options['updateepubcover']
if not book['good']:
# book has already been flagged bad for whatever reason.
@@ -415,7 +423,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
options['personal.ini'] = prefs['personal.ini']
if prefs['includeimages']:
# this is a cheat to make it easier for users.
options['personal.ini'] = '''[defaults]
options['personal.ini'] = '''[epub]
include_images:true
keep_summary_html:true
make_firstimage_cover:true
@@ -566,7 +574,13 @@ make_firstimage_cover:true
# this behavior matches how epubs come out when imported
# dateCreated == packaged--epub/etc created.
book['timestamp'] = story.getMetadataRaw('dateCreated').replace(tzinfo=local_tz)
if book_id != None and prefs['injectseries']:
mi = db.get_metadata(book_id,index_is_id=True)
if not book['series'] and mi.series != None:
book['calibre_series'] = (mi.series,mi.series_index)
print("calibre_series:%s [%s]"%book['calibre_series'])
if book['good']: # there shouldn't be any !'good' books at this point.
# if still 'good', make a temp file to write the output to.
tmp = PersistentTemporaryFile(prefix='new-%s-'%book['calibre_id'],
@@ -581,7 +595,8 @@ make_firstimage_cover:true
def start_download_list(self,book_list,
options={'fileform':'epub',
'collision':ADDNEW,
'updatemeta':True}):
'updatemeta':True,
'updateepubcover':True}):
'''
Called by LoopProgressDialog to start story downloads BG processing.
adapter_list is a list of tuples of (url,adapter)
@@ -629,7 +644,8 @@ make_firstimage_cover:true
def _update_book(self,book,db=None,
options={'fileform':'epub',
'collision':ADDNEW,
'updatemeta':True}):
'updatemeta':True,
'updateepubcover':True}):
print("add/update %s %s"%(book['title'],book['url']))
mi = self._make_mi_from_book(book)
@@ -767,7 +783,6 @@ make_firstimage_cover:true
epubmi = get_metadata(existingepub,'EPUB')
if epubmi.cover_data[1] is not None:
db.set_cover(book_id, epubmi.cover_data[1])
#mi.cover = epubmi.cover_data[1]
# set author link if found. All current adapters have authorUrl.
if 'authorUrl' in book['all_metadata']:
@@ -788,8 +803,9 @@ make_firstimage_cover:true
print("%s not an existing column, skipping."%col)
continue
coldef = custom_columns[col]
if not meta.startswith('status-') and meta not in book['all_metadata']:
print("No value for %s, skipping."%meta)
if not meta.startswith('status-') and meta not in book['all_metadata'] or \
meta.startswith('status-') and 'status' not in book['all_metadata']:
print("No value for %s, skipping custom column(%s) update."%(meta,coldef['name']))
continue
if meta not in permitted_values[coldef['datatype']]:
print("%s not a valid column type for %s, skipping."%(col,meta))
@@ -806,8 +822,47 @@ make_firstimage_cover:true
if meta == 'status-I':
val = book['all_metadata']['status'] == 'In-Progress'
db.set_custom(book_id, val, label=label, commit=False)
db.commit()
if 'Generate Cover' in self.gui.iactions and (book['added'] or not prefs['gcnewonly']):
gc_plugin = self.gui.iactions['Generate Cover']
setting_name = None
if prefs['allow_gc_from_ini']:
ffdlconfig = SafeConfigParser()
ffdlconfig.readfp(StringIO(get_resources("plugin-defaults.ini")))
ffdlconfig.readfp(StringIO(prefs['personal.ini']))
adapter = adapters.getAdapter(ffdlconfig,book['url'],options['fileform'])
# template => regexp to match => GC Setting to use.
# generate_cover_settings:
# ${category} => Buffy:? the Vampire Slayer => Buffy
for line in adapter.getConfig('generate_cover_settings').splitlines():
if "=>" in line:
(template,regexp,setting) = map( lambda x: x.strip(), line.split("=>") )
value = Template(template).substitute(book['all_metadata']).encode('utf8')
print("%s(%s) => %s => %s"%(template,value,regexp,setting))
if re.search(regexp,value):
setting_name = setting
break
if setting_name:
print("Generate Cover Setting from generate_cover_settings(%s)"%line)
if setting_name not in gc_plugin.get_saved_setting_names():
print("GC Name %s not found, discarding! (check personal.ini for typos)"%setting_name)
setting_name = None
if not setting_name and book['all_metadata']['site'] in prefs['gc_site_settings']:
setting_name = prefs['gc_site_settings'][book['all_metadata']['site']]
if not setting_name and 'Default' in prefs['gc_site_settings']:
setting_name = prefs['gc_site_settings']['Default']
if setting_name:
print("Running Generate Cover with settings %s."%setting_name)
realmi = db.get_metadata(book_id, index_is_id=True)
gc_plugin.generate_cover_for_book(realmi,saved_setting_name=setting_name)
def _get_clean_reading_lists(self,lists):
if lists == None or lists.strip() == "" :
@@ -851,10 +906,18 @@ make_firstimage_cover:true
if len(lists) < 1 :
message="<p>You configured FanFictionDownLoader to automatically update \"Send to Device\" Reading Lists, but you don't have any lists set?</p>"
confirm(message,'fanfictiondownloader_no_send_lists', self.gui)
# Quick demo of how an 'allow send' list might work.
# Issues: allow list per send list? Naming convention? "send(allow)"
# allow_list = rl_plugin.get_book_list("Allow Send to Device")
# # intersection of book_ids & allow_list
# add_book_ids = list(set(book_ids) & set(allow_list))
for l in lists:
if l in rl_plugin.get_list_names():
#print("good send l:(%s)"%l)
rl_plugin.add_books_to_list(l,
#add_book_ids,
book_ids,
display_warnings=False)
else:
@@ -890,7 +953,15 @@ make_firstimage_cover:true
books = []
uniqueurls = set()
for url in urls:
# look here for [\d,\d] at end of url, and remove?
mc = re.match(r"^(?P<url>.*?)(?:\[(?P<begin>\d+)?(?P<comma>,)?(?P<end>\d+)?\])?$",url)
print("url:(%s) begin:(%s) end:(%s)"%(mc.group('url'),mc.group('begin'),mc.group('end')))
url = mc.group('url')
book = self._convert_url_to_book(url)
book['begin'] = mc.group('begin')
book['end'] = mc.group('end')
if book['begin'] and not mc.group('comma'):
book['end'] = book['begin']
if book['url'] in uniqueurls:
book['good'] = False
book['comment'] = "Same story already included."
@@ -972,8 +1043,12 @@ make_firstimage_cover:true
if 'url' in identifiers:
#print("url from epub:"+identifiers['url'].replace('|',':'))
return identifiers['url'].replace('|',':')
# look for dc:source
return get_dcsource(existingepub)
# look for dc:source first, then scan HTML if
link = get_dcsource(existingepub)
if link:
return link
elif prefs['lookforurlinhtml']:
return get_story_url_from_html(existingepub,self._is_good_downloader_url)
return None
def _is_good_downloader_url(self,url):
+15 -2
View File
@@ -107,12 +107,20 @@ def do_download_for_worker(book,options):
ffdlconfig.readfp(StringIO(get_resources("plugin-defaults.ini")))
ffdlconfig.readfp(StringIO(options['personal.ini']))
if not options['updateepubcover'] and 'epub_for_update' in book and options['collision'] in (UPDATE, UPDATEALWAYS):
ffdlconfig.set("overrides","never_make_cover","true")
adapter = adapters.getAdapter(ffdlconfig,book['url'],options['fileform'])
adapter.is_adult = book['is_adult']
adapter.username = book['username']
adapter.password = book['password']
story = adapter.getStoryMetadataOnly()
if 'calibre_series' in book:
print("calibre_series:%s [%d]"%book['calibre_series'])
adapter.setSeries(book['calibre_series'][0],book['calibre_series'][1])
else:
print("no calibre_series")
writer = writers.getWriter(options['fileform'],adapter.config,adapter)
outfile = book['outfile']
@@ -125,19 +133,24 @@ def do_download_for_worker(book,options):
## checks were done earlier, it's new or not dup or newer--just write it.
elif options['collision'] in (ADDNEW, SKIP, OVERWRITE, OVERWRITEALWAYS) or \
('epub_for_update' not in book and options['collision'] in (UPDATE, UPDATEALWAYS)):
adapter.setChaptersRange(book['begin'],book['end'])
print("write to %s"%outfile)
writer.writeStory(outfilename=outfile, forceOverwrite=True)
book['comment'] = 'Download %s completed, %s chapters.'%(options['fileform'],story.getMetadata("numChapters"))
## checks were done earlier, just update it.
elif 'epub_for_update' in book and options['collision'] in (UPDATE, UPDATEALWAYS):
# update now handled by pre-populating the old images and
# chapters in the adapter rather than merging epubs.
urlchaptercount = int(story.getMetadata('numChapters'))
(url,chaptercount,
adapter.oldchapters,
adapter.oldimgs) = get_update_data(book['epub_for_update'])
adapter.oldimgs,
adapter.oldcover,
adapter.calibrebookmark) = get_update_data(book['epub_for_update'])
print("Do update - epub(%d) vs url(%d)" % (chaptercount, urlchaptercount))
print("write to %s"%outfile)
+124 -7
View File
@@ -183,6 +183,9 @@ output_css:
## Add URLs since there aren't links.
titlepage_entries: series,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,storyUrl, authorUrl, description
## Width to word wrap text output. 0 indicates no wrapping.
wrap_width: 78
## use \r\n for line endings, the windows convention. text output only.
windows_eol: true
@@ -306,6 +309,16 @@ extratags: FanFiction,Testing,Text
[test1.com:html]
extratags: FanFiction,Testing,HTML
[archive.skyehawke.com]
[ashwinder.sycophanthex.com]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
## commandline version, this should go in your personal.ini, not
## defaults.ini.
#username:YourName
#password:yourpassword
[castlefans.org]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
@@ -319,6 +332,39 @@ extratags: FanFiction,Testing,HTML
## personal.ini, not defaults.ini.
#is_adult:true
[chaos.sycophanthex.com]
## 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
## some sites include images that we don't ever want becoming the
## cover image. This lets you exclude them.
cover_exclusion_regexp:/images/.*?ribbon.gif
[dramione.org]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
## commandline version, this should go in your personal.ini, not
## defaults.ini.
#username:YourName
#password:yourpassword
## Some sites also require the user to confirm they are adult for
## adult content. In commandline version, this should go in your
## personal.ini, not defaults.ini.
#is_adult:true
[erosnsappho.sycophanthex.com]
## 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
## some sites include images that we don't ever want becoming the
## cover image. This lets you exclude them.
cover_exclusion_regexp:/images/.*?ribbon.gif
[fanfiction.mugglenet.com]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
@@ -346,16 +392,27 @@ extratags: FanFiction,Testing,HTML
#username:YourName
#password:yourpassword
[lumos.sycophanthex.com]
## 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
[nfacommunity.com]
## Some sites do not require a login, but do require the user to
## confirm they are adult for adult content. In commandline version,
## this should go in your personal.ini, not defaults.ini.
#is_adult:true
## Some sites also require the user to confirm they are adult for
## adult content. In commandline version, this should go in your
## personal.ini, not defaults.ini.
#is_adult:true
[occlumency.sycophanthex.com]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
## commandline version, this should go in your personal.ini, not
## defaults.ini.
#username:YourName
#password:yourpassword
[thehexfiles.net]
[thequidditchpitch.org]
## Some sites require login (or login for some rated stories) The
@@ -377,11 +434,21 @@ extratags: FanFiction,Testing,HTML
#is_adult:true
[www.archiveofourown.org]
## Some sites also require the user to confirm they are adult for
## adult content. In commandline version, this should go in your
## personal.ini, not defaults.ini.
## 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
[www.checkmated.com]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
## commandline version, this should go in your personal.ini, not
## defaults.ini.
#username:YourName
#password:yourpassword
[www.dokuga.com]
[www.fanfiction.net]
[www.ficbook.net]
@@ -430,6 +497,25 @@ extratags:
## this should go in your personal.ini, not defaults.ini.
#is_adult:true
[www.ik-eternal.net]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
## commandline version, this should go in your personal.ini, not
## defaults.ini.
#username:YourName
#password:yourpassword
## Some sites also require the user to confirm they are adult for
## adult content. In commandline version, this should go in your
## personal.ini, not defaults.ini.
#is_adult:true
[www.libraryofmoria.com]
## 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
[www.mediaminer.org]
[www.midnightwhispers.ca]
@@ -442,10 +528,29 @@ extratags:
## cover image. This lets you exclude them.
cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
[www.phoenixsong.net]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
## commandline version, this should go in your personal.ini, not
## defaults.ini.
#username:YourName
#password:yourpassword
[www.potionsandsnitches.net]
[www.siye.co.uk]
[www.squidge.org/peja]
# www.squidge.org/peja calls it Fandom <shrug>
category_label:Fandom
# Remove numWords -- www.squidge.org/peja word counts are inaccurate
titlepage_entries: series,category,genre,language,characters,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,description
[www.squidge.org/peja:txt]
## Add URLs since there aren't links.
# Remove numWords -- www.squidge.org/peja word counts are inaccurate
titlepage_entries: series,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,storyUrl, authorUrl, description
[www.thewriterscoffeeshop.com]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
@@ -497,8 +602,20 @@ collect_series: false
## twiwrite.net (ab)uses series as personal reading lists.
collect_series: false
[www.walkingtheplank.org]
## Some sites do not require a login, but do require the user to
## confirm they are adult for adult content. In commandline version,
## this should go in your personal.ini, not defaults.ini.
#is_adult:true
[www.whofic.com]
[www.wraithbait.com]
## 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
+9 -1
View File
@@ -64,6 +64,9 @@ def main():
parser.add_option("-u", "--update-epub",
action="store_true", dest="update",
help="Update an existing epub with new chapter, give epub filename instead of storyurl.",)
parser.add_option("--update-cover",
action="store_true", dest="updatecover",
help="Update cover in an existing epub, otherwise existing cover (if any) is used on update. Only valid with --update-epub.",)
parser.add_option("--force",
action="store_true", dest="force",
help="Force overwrite or update of an existing epub, download and overwrite all chapters.",)
@@ -104,6 +107,9 @@ def main():
if options.force:
config.set("overrides","always_overwrite","true")
if options.update and not options.updatecover:
config.set("overrides","never_make_cover","true")
if options.options:
for opt in options.options:
@@ -167,7 +173,9 @@ def main():
# merging epubs.
(url,chaptercount,
adapter.oldchapters,
adapter.oldimgs) = get_update_data(args[0])
adapter.oldimgs,
adapter.oldcover,
adapter.calibrebookmark) = get_update_data(args[0])
writeStory(config,adapter,"epub")
+20 -1
View File
@@ -51,6 +51,22 @@ import adapter_thequidditchpitchorg
import adapter_nfacommunitycom
import adapter_midnightwhispersca
import adapter_ksarchivecom
import adapter_archiveskyehawkecom
import adapter_squidgeorgpeja
import adapter_libraryofmoriacom
import adapter_wraithbaitcom
import adapter_checkmatedcom
import adapter_chaossycophanthexcom
import adapter_dramioneorg
import adapter_erosnsapphosycophanthexcom
import adapter_lumossycophanthexcom
import adapter_occlumencysycophanthexcom
import adapter_phoenixsongnet
import adapter_walkingtheplankorg
import adapter_ashwindersycophanthexcom
import adapter_thehexfilesnet
import adapter_dokugacom
import adapter_iketernalnet
## This bit of complexity allows adapters to be added by just adding
## importing. It eliminates the long if/else clauses we used to need
@@ -94,11 +110,14 @@ def getAdapter(config,url,fileform=None):
fixedurl = fixedurl.replace("http://","http://www.")
if cls:
adapter = cls(config,fixedurl) # raises InvalidStoryURL
adapter.setSectionOrder(adapter.getSiteDomain(),fileform)
adapter.setSectionOrder(adapter.getConfigSection(),fileform)
return adapter
# No adapter found.
raise exceptions.UnknownSite( url, [cls.getSiteDomain() for cls in __class_list] )
def getConfigSections():
return [cls.getConfigSection() for cls in __class_list]
def getClassFor(domain):
for cls in __class_list:
if cls.matchesSite(domain):
@@ -101,7 +101,7 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
# Now go hunting for all the meta data and the chapter list.
## Title
a = soup.find('a', href=re.compile(r"^/works/\w+"))
a = soup.find('a', href=re.compile(r"^/works/\d+$"))
self.story.setMetadata('title',a.string)
# Find authorid and URL from... author url.
@@ -0,0 +1,190 @@
# -*- 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
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, makeDate
def getClass():
return ArchiveSkyeHawkeComAdapter
# Class name has to be unique. Our convention is camel case the
# sitename with Adapter at the end. www is skipped.
class ArchiveSkyeHawkeComAdapter(BaseSiteAdapter):
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.decode = ["Windows-1252",
"utf8"] # 1252 is a superset of iso-8859-1.
# Most sites that claim to be
# iso-8859-1 (and some that claim to be
# utf8) are really windows-1252.
self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
self.password = ""
self.is_adult=False
# get storyId from url--url validation guarantees query is only sid=1234
self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
# normalized story URL.
self._setURL('http://' + self.getSiteDomain() + '/story.php?no='+self.story.getMetadata('storyId'))
# Each adapter needs to have a unique site abbreviation.
self.story.setMetadata('siteabbrev','ash')
# The date format will vary from site to site.
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
self.dateformat = "%Y-%m-%d"
@staticmethod # must be @staticmethod, don't remove it.
def getSiteDomain():
# The site domain. Does have www here, if it uses it.
return 'archive.skyehawke.com'
def getSiteExampleURLs(self):
return "http://"+self.getSiteDomain()+"/story.php?no=1234"
def getSiteURLPattern(self):
return re.escape("http://"+self.getSiteDomain()+"/story.php?no=")+r"\d+$"
## Getting the chapter list and the meta data, plus 'is adult' checking.
def extractChapterUrlsAndMetadata(self):
url = self.url
logging.debug("URL: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
data = self._fetchUrl(url)
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data)
# print data
# Now go hunting for all the meta data and the chapter list.
## Title
a = soup.find('div', {'class':"story border"}).find('span',{'class':'left'})
title=a.text.split('"')[1]
self.story.setMetadata('title',title)
# Find authorid and URL from... author url.
author = a.find('a')
self.story.setMetadata('authorId',author['href'].split('=')[1])
self.story.setMetadata('authorUrl','http://'+self.host+'/'+author['href'])
self.story.setMetadata('author',author.string)
authorSoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
chapter=soup.find('select',{'name':'chapter'}).findAll('option')
for i in range(1,len(chapter)):
ch=chapter[i]
self.chapterUrls.append((stripHTML(ch),ch['value']))
self.story.setMetadata('numChapters',len(self.chapterUrls))
# eFiction sites don't help us out a lot with their meta data
# formating, so it's a little ugly.
box=soup.find('div', {'class': "container borderridge"})
sum=box.find('span').text
self.setDescription(url,sum)
boxes=soup.findAll('div', {'class': "container bordersolid"})
for box in boxes:
if box.find('b') != None and box.find('b').text == "History and Story Information":
for b in box.findAll('b'):
if "words" in b.nextSibling:
self.story.setMetadata('numWords', b.text)
if "archived" in b.previousSibling:
self.story.setMetadata('datePublished', makeDate(stripHTML(b.text), self.dateformat))
if "updated" in b.previousSibling:
self.story.setMetadata('dateUpdated', makeDate(stripHTML(b.text), self.dateformat))
if "fandom" in b.nextSibling:
self.story.addToList('category', b.text)
for br in box.findAll('br'):
br.replaceWith('split')
genre=box.text.split("Genre:")[1].split("split")[0]
if not "Unspecified" in genre:
self.story.addToList('genre',genre)
if box.find('span') != None and box.find('span').text == "WARNING":
rating=box.findAll('span')[1]
rating.find('br').replaceWith('split')
rating=rating.text.replace("This story is rated",'').split('split')[0]
self.story.setMetadata('rating',rating)
logging.debug(self.story.getMetadata('rating'))
warnings=box.find('ol')
if warnings != None:
warnings=warnings.text.replace(']', '').replace('[', '').split(' ')
for warning in warnings:
self.story.addToList('warnings',warning)
for asoup in authorSoup.findAll('div', {'class':"story bordersolid"}):
if asoup.find('a')['href'] == 'story.php?no='+self.story.getMetadata('storyId'):
if '[ Completed ]' in asoup.text:
self.story.setMetadata('status', 'Completed')
else:
self.story.setMetadata('status', 'In-Progress')
chars=asoup.findNext('div').text.split('Characters')[1].split(']')[0]
for char in chars.split(','):
if not "None" in char:
self.story.addToList('characters',char)
break
# grab the text for an individual chapter.
def getChapterText(self, url):
logging.debug('Getting chapter text from: %s' % url)
soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
div = soup.find('div',{'class':"chapter bordersolid"}).findNext('div').findNext('div')
if None == div:
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
return self.utf8FromSoup(url,div)
@@ -0,0 +1,257 @@
# -*- 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
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, makeDate
def getClass():
return AshwinderSycophantHexComAdapter
# Class name has to be unique. Our convention is camel case the
# sitename with Adapter at the end. www is skipped.
class AshwinderSycophantHexComAdapter(BaseSiteAdapter):
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.decode = ["Windows-1252",
"utf8"] # 1252 is a superset of iso-8859-1.
# Most sites that claim to be
# iso-8859-1 (and some that claim to be
# utf8) are really windows-1252.
self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
self.password = ""
self.is_adult=False
# get storyId from url--url validation guarantees query is only sid=1234
self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
# normalized story URL.
self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
# Each adapter needs to have a unique site abbreviation.
self.story.setMetadata('siteabbrev','asph')
# If all stories from the site fall into the same category,
# the site itself isn't likely to label them as such, so we
# do.
self.story.addToList("category","Harry Potter")
# The date format will vary from site to site.
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
self.dateformat = "%m/%d/%Y"
@staticmethod # must be @staticmethod, don't remove it.
def getSiteDomain():
# The site domain. Does have www here, if it uses it.
return 'ashwinder.sycophanthex.com'
def getSiteExampleURLs(self):
return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
def getSiteURLPattern(self):
return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
## Login seems to be reasonably standard across eFiction sites.
def needToLoginCheck(self, data):
if 'This story contains adult content and/or themes.' in data \
or "That password doesn't match the one in our database" in data:
return True
else:
return False
def performLogin(self, url):
params = {}
if self.password:
params['penname'] = self.username
params['password'] = self.password
else:
params['penname'] = self.getConfig("username")
params['password'] = self.getConfig("password")
params['rememberme'] = '1'
params['sid'] = ''
params['intent'] = ''
params['submit'] = 'Submit'
loginUrl = 'http://' + self.getSiteDomain() + '/user.php'
logging.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
params['penname']))
d = self._fetchUrl(loginUrl, params)
if "User Account Page" 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
## Getting the chapter list and the meta data, plus 'is adult' checking.
def extractChapterUrlsAndMetadata(self):
# index=1 makes sure we see the story chapter index. Some
# sites skip that for one-chapter stories.
url = self.url
logging.debug("URL: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
if self.needToLoginCheck(data):
# need to log in for this one.
self.performLogin(url)
data = self._fetchUrl(url)
if "Access denied. This story has not been validated by the adminstrators of this site." in data:
raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data)
# print data
# Now go hunting for all the meta data and the chapter list.
# Find authorid and URL from... author url.
a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
self.story.setMetadata('authorId',a['href'].split('=')[1])
self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
self.story.setMetadata('author',a.string)
asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
try:
# in case link points somewhere other than the first chapter
a = soup.findAll('option')[1]['value']
self.story.setMetadata('storyId',a.split('=',)[1])
url = 'http://'+self.host+'/'+a
soup = bs.BeautifulSoup(self._fetchUrl(url))
except:
pass
for info in asoup.findAll('table', {'bordercolor' : '#1A1919'}):
a = info.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
if a != None:
self.story.setMetadata('title',a.text)
break
# Find the chapters:
chapters=soup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+&i=1$'))
if len(chapters) == 0:
self.chapterUrls.append((self.story.getMetadata('title'),url))
else:
for chapter in chapters:
# just in case there's tags, like <i> in chapter titles.
self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']))
self.story.setMetadata('numChapters',len(self.chapterUrls))
# eFiction sites don't help us out a lot with their meta data
# formating, so it's a little ugly.
# utility method
def defaultGetattr(d):
try:
return d.name
except:
return ""
cats = info.findAll('a',href=re.compile('categories.php'))
for cat in cats:
self.story.addToList('category',cat.string)
a = info.find('a', href=re.compile(r'reviews.php\?sid='+self.story.getMetadata('storyId')))
val = a.nextSibling
svalue = ""
while not defaultGetattr(val) == 'br':
val = val.nextSibling
val = val.nextSibling
while not defaultGetattr(val) == 'table':
svalue += str(val)
val = val.nextSibling
self.setDescription(url,svalue)
# <span class="label">Rated:</span> NC-17<br /> etc
labels = info.findAll('b')
for labelspan in labels:
value = labelspan.nextSibling
label = stripHTML(labelspan)
if 'Rating' in label:
self.story.setMetadata('rating', value)
if 'Word Count' in label:
self.story.setMetadata('numWords', value)
if 'Genres' in label:
genres = value.string.split(', ')
for genre in genres:
if genre != 'none':
self.story.addToList('genre',genre)
if 'Warnings' in label:
warnings = value.string.split(', ')
for warning in warnings:
if warning != ' none':
self.story.addToList('warnings',warning)
if 'Completed' in label:
if 'Yes' in value:
self.story.setMetadata('status', 'Completed')
else:
self.story.setMetadata('status', 'In-Progress')
if 'Published' in label:
self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
if 'Updated' in label:
# there's a stray [ at the end.
#value = value[0:-1]
self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
# grab the text for an individual chapter.
def getChapterText(self, url):
logging.debug('Getting chapter text from: %s' % url)
data = self._fetchUrl(url)
soup = bs.BeautifulSoup(data, selfClosingTags=('br','hr','span','center')) # some chapters seem to be hanging up on those tags, so it is safer to close them
story = soup.find('div', {"align" : "left"})
if None == story:
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
return self.utf8FromSoup(url,story)
@@ -0,0 +1,239 @@
# -*- 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
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, makeDate
def getClass():
return ChaosSycophantHexComAdapter
# Class name has to be unique. Our convention is camel case the
# sitename with Adapter at the end. www is skipped.
class ChaosSycophantHexComAdapter(BaseSiteAdapter):
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.decode = ["Windows-1252",
"utf8"] # 1252 is a superset of iso-8859-1.
# Most sites that claim to be
# iso-8859-1 (and some that claim to be
# utf8) are really windows-1252.
self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
self.password = ""
self.is_adult=False
# get storyId from url--url validation guarantees query is only sid=1234
self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
# normalized story URL.
self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
# Each adapter needs to have a unique site abbreviation.
self.story.setMetadata('siteabbrev','csph')
# If all stories from the site fall into the same category,
# the site itself isn't likely to label them as such, so we
# do.
#self.story.addToList("category","Harry Potter")
# The date format will vary from site to site.
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
self.dateformat = "%m/%d/%Y"
@staticmethod # must be @staticmethod, don't remove it.
def getSiteDomain():
# The site domain. Does have www here, if it uses it.
return 'chaos.sycophanthex.com'
def getSiteExampleURLs(self):
return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
def getSiteURLPattern(self):
return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
## Getting the chapter list and the meta data, plus 'is adult' checking.
def extractChapterUrlsAndMetadata(self):
if self.is_adult or self.getConfig("is_adult"):
# Weirdly, different sites use different warning numbers.
# If the title search below fails, there's a good chance
# you need a different number. print data at that point
# and see what the 'click here to continue' url says.
addurl = "&ageconsent=ok&warning=19"
else:
addurl=""
# index=1 makes sure we see the story chapter index. Some
# sites skip that for one-chapter stories.
url = self.url+'&index=1'+addurl
logging.debug("URL: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
# The actual text that is used to announce you need to be an
# adult varies from site to site. Again, print data before
# the title search to troubleshoot.
if "Age Consent Required" in data:
raise exceptions.AdultCheckRequired(self.url)
if "Access denied. This story has not been validated by the adminstrators of this site." in data:
raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data)
# print data
# Now go hunting for all the meta data and the chapter list.
## Title
pt = soup.find('div', {'id' : 'pagetitle'})
a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
self.story.setMetadata('title',a.text)
# Find authorid and URL from... author url.
a = pt.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
self.story.setMetadata('authorId',a['href'].split('=')[1])
self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
self.story.setMetadata('author',a.string)
rating=pt.text.split('(')[1].split(')')[0]
self.story.setMetadata('rating', rating)
# Find the chapters:
for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
# just in case there's tags, like <i> in chapter titles.
self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))
self.story.setMetadata('numChapters',len(self.chapterUrls))
# eFiction sites don't help us out a lot with their meta data
# formating, so it's a little ugly.
# utility method
def defaultGetattr(d,k):
try:
return d[k]
except:
return ""
# <span class="label">Rated:</span> NC-17<br /> etc
labels = soup.findAll('span',{'class':'label'})
value = labels[0].previousSibling
svalue = ""
while value != None:
val = value
value = value.previousSibling
while not defaultGetattr(val,'class') == 'label':
svalue += str(val)
val = val.nextSibling
self.setDescription(url,svalue)
for labelspan in labels:
value = labelspan.nextSibling
label = labelspan.string
if 'Word count' in label:
self.story.setMetadata('numWords', value.split(' -')[0])
if 'Categories' in label:
cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
for cat in cats:
self.story.addToList('category',cat.string)
if 'Characters' in label:
chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
for char in chars:
self.story.addToList('characters',char.string)
if 'Genre' in label:
genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
for genre in genres:
self.story.addToList('genre',genre.string)
if 'Warnings' in label:
warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
for warning in warnings:
self.story.addToList('warnings',warning.string)
if 'Complete' in label:
if 'Yes' in value:
self.story.setMetadata('status', 'Completed')
else:
self.story.setMetadata('status', 'In-Progress')
if 'Published' in label:
self.story.setMetadata('datePublished', makeDate(stripHTML(value.split(' -')[0]), self.dateformat))
if 'Updated' in label:
# there's a stray [ at the end.
#value = value[0:-1]
self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
try:
# Find Series name from series URL.
a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
series_name = a.string
series_url = 'http://'+self.host+'/'+a['href']
# use BeautifulSoup HTML parser to make everything easier to find.
seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
i=1
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
break
i+=1
except:
# I find it hard to care if the series parsing fails
pass
# grab the text for an individual chapter.
def getChapterText(self, url):
logging.debug('Getting chapter text from: %s' % url)
soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
div = soup.find('div', {'id' : 'story'})
if None == div:
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
return self.utf8FromSoup(url,div)
@@ -0,0 +1,239 @@
# -*- 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
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, makeDate
def getClass():
return CheckmatedComAdapter
class CheckmatedComAdapter(BaseSiteAdapter):
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.decode = ["Windows-1252",
"utf8"] # 1252 is a superset of iso-8859-1.
# Most sites that claim to be
# iso-8859-1 (and some that claim to be
# utf8) are really windows-1252.
self.username = "" # if left empty, site doesn't return any message at all.
self.password = ""
self.is_adult=False
# get storyId from url--url validation guarantees query is only sid=1234
self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
self._setURL('http://' + self.getSiteDomain() + '/story.php?story='+self.story.getMetadata('storyId'))
# Each adapter needs to have a unique site abbreviation.
self.story.setMetadata('siteabbrev','chm')
# If all stories from the site fall into the same category,
# the site itself isn't likely to label them as such, so we
# do.
self.story.addToList("category","Harry Potter")
# The date format will vary from site to site.
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
self.dateformat = "%b %d, %Y"
@staticmethod # must be @staticmethod, don't remove it.
def getSiteDomain():
# The site domain. Does have www here, if it uses it.
return 'www.checkmated.com'
def getSiteExampleURLs(self):
return "http://"+self.getSiteDomain()+"/story.php?story=1234"
def getSiteURLPattern(self):
return re.escape("http://"+self.getSiteDomain()+"/story.php?story=")+r"\d+$"
## Login seems to be reasonably standard across eFiction sites. This story is in The Bedchamber
def needToLoginCheck(self, data):
if 'This story is in The Bedchamber' in data \
or 'That username is not in our database' in data \
or "That password is not correct, please try again" in data:
return True
else:
return False
def performLogin(self, url):
params = {}
if self.password:
params['name'] = self.username
params['pass'] = self.password
else:
params['name'] = self.getConfig("username")
params['pass'] = self.getConfig("password")
params['login'] = 'yes'
params['submit'] = 'login'
loginUrl = 'http://' + self.getSiteDomain()+'/login.php'
d = self._fetchUrl(loginUrl,params)
e = self._fetchUrl(url)
if "Welcome back," not in d : #Member Account
logging.info("Failed to login to URL %s as %s" % (loginUrl,
params['name']))
raise exceptions.FailedToLogin(url,params['name'])
return False
elif "This story is in The Bedchamber" in e:
raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Your account does not have sufficient priviliges to read this story.")
return False
else:
return True
## Getting the chapter list and the meta data, plus 'is adult' checking.
def extractChapterUrlsAndMetadata(self):
# index=1 makes sure we see the story chapter index. Some
# sites skip that for one-chapter stories.
url = self.url
logging.debug("URL: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
if self.needToLoginCheck(data):
# need to log in for this one.
self.performLogin(url)
data = self._fetchUrl(url)
# The actual text that is used to announce you need to be an
# adult varies from site to site. Again, print data before
# the title search to troubleshoot.
if "Access denied. This story has not been validated by the adminstrators of this site." in data:
raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data)
# print data
# Now go hunting for all the meta data and the chapter list.
## Title
a = soup.findAll('span', {'class' : 'storytitle'})
self.story.setMetadata('title',a[0].string)
# Find authorid and URL from... author url.
a = a[1].find('a', href=re.compile(r"authors.php\?name\=\w+"))
self.story.setMetadata('authorId',a['href'].split('=')[1])
self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
self.story.setMetadata('author',a.string)
a = soup.find('select', {'name' : 'chapter'})
if a == None:
self.chapterUrls.append((self.story.getMetadata('title'),url))
else:
for chapter in a.findAll('option'):
self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/story.php?story='+self.story.getMetadata('storyId')+'&chapter='+chapter['value']))
self.story.setMetadata('numChapters',len(self.chapterUrls))
# eFiction sites don't help us out a lot with their meta data
# formating, so it's a little ugly.
# utility method
def defaultGetattr(d,k):
try:
return d[k]
except:
return ""
# website does not keep track of word count, and there is no convenient way to calculate it
summary = soup.find('fieldset')
summary.find('legend').extract()
summary.name='div'
self.setDescription(url,summary)
# <span class="label">Rated:</span> NC-17<br /> etc
table = soup.findAll('div', {'class' : 'text'})[1]
for labels in table.findAll('tr'):
value = labels.findAll('td')[1]
label = labels.findAll('td')[0]
if 'Rating' in stripHTML(label):
self.story.setMetadata('rating', stripHTML(value))
if 'Ship' in stripHTML(label):
for char in value.string.split('/'):
if char != 'none':
self.story.addToList('characters',char)
if 'Status' in stripHTML(label):
if value.find('img', {'src' : 'img/incomplete.gif'}) == None:
self.story.setMetadata('status', 'Completed')
else:
self.story.setMetadata('status', 'In-Progress')
if 'Published' in stripHTML(label):
self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
if 'Updated' in stripHTML(label):
self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
a = self._fetchUrl(self.story.getMetadata('authorUrl')+'&cat=stories')
for story in bs.BeautifulSoup(a).findAll('table', {'class' : 'storyinfo'}):
a = story.find('a', href=re.compile(r"review.php\?s\="+self.story.getMetadata('storyId')+'&act=view'))
if a != None:
for labels in story.findAll('tr'):
value = labels.findAll('td')[1]
label = labels.findAll('td')[0]
if 'genre' in stripHTML(label):
for genre in value.findAll('img'):
self.story.addToList('genre',genre['title'])
# grab the text for an individual chapter.
def getChapterText(self, url):
logging.debug('Getting chapter text from: %s' % url)
soup = bs.BeautifulSoup(self._fetchUrl(url),
selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
div = soup.find('div', {'id' : 'resizeableText'})
div.find('div', {'class' : 'storyTools'}).extract()
if None == div:
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
return self.utf8FromSoup(url,div)
@@ -0,0 +1,236 @@
# -*- 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
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, makeDate
def getClass():
return DokugaComAdapter
# Class name has to be unique. Our convention is camel case the
# sitename with Adapter at the end. www is skipped.
class DokugaComAdapter(BaseSiteAdapter):
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.decode = ["Windows-1252",
"utf8"] # 1252 is a superset of iso-8859-1.
# Most sites that claim to be
# iso-8859-1 (and some that claim to be
# utf8) are really windows-1252.
self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
self.password = ""
self.is_adult=False
# get storyId from url--url validation guarantees query is only sid=1234
self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[3])
logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
self.story.setMetadata('section',self.parsedUrl.path.split('/',)[1])
# normalized story URL.
self._setURL('http://' + self.getSiteDomain() + '/'+self.parsedUrl.path.split('/',)[1]+'/story/'+self.story.getMetadata('storyId'))
# Each adapter needs to have a unique site abbreviation.
self.story.setMetadata('siteabbrev','dkg')
# If all stories from the site fall into the same category,
# the site itself isn't likely to label them as such, so we
# do.
self.story.addToList("category","InuYasha")
# The date format will vary from site to site.
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
if 'fanfiction' in self.story.getMetadata('section'):
self.dateformat = "%d %b %Y"
else:
self.dateformat = "%m-%d-%y"
@staticmethod # must be @staticmethod, don't remove it.
def getSiteDomain():
# The site domain. Does have www here, if it uses it.
return 'www.dokuga.com'
def getSiteExampleURLs(self):
return "http://"+self.getSiteDomain()+"/fanfiction/story/1234/1 http://"+self.getSiteDomain()+"/spark/story/1234/1"
def getSiteURLPattern(self):
return r"http://"+self.getSiteDomain()+"/(fanfiction|spark)?/story/\d+/?\d+?$"
## Getting the chapter list and the meta data, plus 'is adult' checking.
def extractChapterUrlsAndMetadata(self):
# index=1 makes sure we see the story chapter index. Some
# sites skip that for one-chapter stories.
url = self.url
logging.debug("URL: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
if "Access denied. This story has not been validated by the adminstrators of this site." in data:
raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data)
# print data
# Now go hunting for all the meta data and the chapter list.
## Title and author
a = soup.find('div', {'align' : 'center'}).find('h3')
# Find authorid and URL from... author url.
aut = a.find('a')
self.story.setMetadata('authorId',aut['href'].split('=')[1])
alink='http://'+self.host+aut['href']
self.story.setMetadata('authorUrl','http://'+self.host+aut['href'])
self.story.setMetadata('author',aut.string)
aut.extract()
a = a.string[:(len(a.string)-4)]
self.story.setMetadata('title',a)
# Find the chapters:
chapters = soup.find('select').findAll('option')
if len(chapters)==1:
self.chapterUrls.append((self.story.getMetadata('title'),'http://'+self.host+'/'+self.story.getMetadata('section')+'/story/'+self.story.getMetadata('storyId')+'/1'))
else:
for chapter in chapters:
# just in case there's tags, like <i> in chapter titles. /fanfiction/story/7406/1
self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+self.story.getMetadata('section')+'/story/'+self.story.getMetadata('storyId')+'/'+chapter['value']))
self.story.setMetadata('numChapters',len(self.chapterUrls))
asoup = bs.BeautifulSoup(self._fetchUrl(alink))
if 'fanfiction' in self.story.getMetadata('section'):
asoup=asoup.find('div', {'id' : 'cb_tabid_52'}).find('div')
#grab the rest of the metadata from the author's page
for div in asoup.findAll('div'):
nav=div.find('a', href=re.compile(r'/fanfiction/story/'+self.story.getMetadata('storyId')+"/1$"))
if nav != None:
break
div=div.nextSibling
self.setDescription(url,div)
div=div.nextSibling
a=div.text.split('Rating: ')
if len(a) == 2: self.story.setMetadata('rating', a[1].split('&')[0])
a=div.text.split('Status: ')
if len(a)==2:
iscomp=a[1].split('&')[0]
if 'Complete' in iscomp:
self.story.setMetadata('status', 'Completed')
else:
self.story.setMetadata('status', 'In-Progress')
a=div.text.split('Category: ')
if len(a) == 2: self.story.addToList('category', a[1].split('&')[0])
self.story.addToList('category', 'Fanfiction')
a=div.text.split('Created: ')
if len(a) == 2: self.story.setMetadata('datePublished', makeDate(stripHTML(a[1].split('&')[0]), self.dateformat))
a=div.text.split('Updated: ')
if len(a) == 2: self.story.setMetadata('dateUpdated', makeDate(stripHTML(a[1]), self.dateformat))
div=div.nextSibling.nextSibling
a=div.text.split('Words: ')
if len(a) == 2: self.story.setMetadata('numWords', a[1].split('&')[0])
a=div.text.split('Genre: ')
if len(a) == 2:
for genre in a[1].split('&')[0].split(', '):
self.story.addToList('genre',genre)
else:
asoup=asoup.find('div', {'id' : 'maincol'}).find('div', {'class' : 'padding'})
for div in asoup.findAll('div'):
nav=div.find('a', href=re.compile(r'/spark/story/'+self.story.getMetadata('storyId')+"/1$"))
if nav != None:
break
div=div.nextSibling.nextSibling
self.setDescription(url,div)
self.story.addToList('category', 'Spark')
div=div.nextSibling.nextSibling
a=div.text.split('Rating: ')
if len(a) == 2: self.story.setMetadata('rating', a[1].split(' - ')[0])
a=div.text.split('Status: ')
if len(a)==2:
iscomp=a[1].split(' - ')[0]
if 'Complete' in iscomp:
self.story.setMetadata('status', 'Completed')
else:
self.story.setMetadata('status', 'In-Progress')
a=div.text.split('Genre: ')
if len(a)==2:
for genre in a[1].split(' - ')[0].split('/'):
self.story.addToList('genre',genre)
div=div.nextSibling.nextSibling
a=div.text.split('Updated: ')
if len(a)==2:
date=a[1].split(' -')[0]
self.story.setMetadata('dateUpdated', makeDate(date, self.dateformat))
# does not have published date anywhere
self.story.setMetadata('datePublished', makeDate(date, self.dateformat))
a=div.text.split('Words ')
if len(a)==2: self.story.setMetadata('numWords', a[1])
# grab the text for an individual chapter.
def getChapterText(self, url):
logging.debug('Getting chapter text from: %s' % url)
soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
div = soup.find('div', {'id' : 'chtext'})
if None == div:
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
return self.utf8FromSoup(url,div)
@@ -0,0 +1,271 @@
# -*- 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
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, makeDate
def getClass():
return DramioneOrgAdapter
# Class name has to be unique. Our convention is camel case the
# sitename with Adapter at the end. www is skipped.
class DramioneOrgAdapter(BaseSiteAdapter):
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.decode = ["Windows-1252",
"utf8"] # 1252 is a superset of iso-8859-1.
# Most sites that claim to be
# iso-8859-1 (and some that claim to be
# utf8) are really windows-1252.
self.username = "" # if left empty, site doesn't return any message at all.
self.password = ""
self.is_adult=False
# get storyId from url--url validation guarantees query is only sid=1234
self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
# normalized story URL.
self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
# Each adapter needs to have a unique site abbreviation.
self.story.setMetadata('siteabbrev','drmn')
# If all stories from the site fall into the same category,
# the site itself isn't likely to label them as such, so we
# do.
self.story.addToList("category","Harry Potter")
# The date format will vary from site to site.
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
self.dateformat = "%dth %B %Y"
@staticmethod # must be @staticmethod, don't remove it.
def getSiteDomain():
# The site domain. Does have www here, if it uses it.
return 'dramione.org'
def getSiteExampleURLs(self):
return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
def getSiteURLPattern(self):
return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
## Login seems to be reasonably standard across eFiction sites.
def needToLoginCheck(self, data):
if 'Registered Users Only' in data \
or 'There is no such account on our website' in data \
or "That password doesn't match the one in our database" in data:
return True
else:
return False
def performLogin(self, url):
params = {}
if self.password:
params['penname'] = self.username
params['password'] = self.password
else:
params['penname'] = self.getConfig("username")
params['password'] = self.getConfig("password")
params['cookiecheck'] = '1'
params['submit'] = 'Submit'
loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login'
logging.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
params['penname']))
d = self._fetchUrl(loginUrl, params)
if "Member Account" 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
## Getting the chapter list and the meta data, plus 'is adult' checking.
def extractChapterUrlsAndMetadata(self):
if self.is_adult or self.getConfig("is_adult"):
# Weirdly, different sites use different warning numbers.
# If the title search below fails, there's a good chance
# you need a different number. print data at that point
# and see what the 'click here to continue' url says.
addurl = "&warning=5"
else:
addurl=""
# index=1 makes sure we see the story chapter index. Some
# sites skip that for one-chapter stories.
url = self.url+addurl
logging.debug("URL: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
if self.needToLoginCheck(data):
# need to log in for this one.
self.performLogin(url)
data = self._fetchUrl(url)
# The actual text that is used to announce you need to be an
# adult varies from site to site. Again, print data before
# the title search to troubleshoot.
if "Stories that are suitable for ages 16 and older" in data:
raise exceptions.AdultCheckRequired(self.url)
if "Access denied. This story has not been validated by the adminstrators of this site." in data:
raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data)
# print data
# Now go hunting for all the meta data and the chapter list.
## Title
a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
self.story.setMetadata('title',a.string)
# Find authorid and URL from... author url.
a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
self.story.setMetadata('authorId',a['href'].split('=')[1])
self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
self.story.setMetadata('author',a.string)
# Find the chapters:
for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
# just in case there's tags, like <i> in chapter titles.
self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))
self.story.setMetadata('numChapters',len(self.chapterUrls))
# eFiction sites don't help us out a lot with their meta data
# formating, so it's a little ugly.
genres=soup.findAll('a', {'class' : "tag-1"})
for genre in genres:
self.story.addToList('genre',genre.string)
warnings=soup.findAll('a', {'class' : "tag-2"})
for warning in warnings:
self.story.addToList('warnings',warning.string)
# utility method
def defaultGetattr(d,k):
try:
return d[k]
except:
return ""
# <span class="label">Rated:</span> NC-17<br /> etc
labels = soup.findAll('span',{'class':'label'})
for labelspan in labels:
value = labelspan.nextSibling
label = labelspan.string
if 'Summary' in label:
## Everything until the next span class='label'
svalue = ""
while not defaultGetattr(value,'class') == 'label':
svalue += str(value)
value = value.nextSibling
self.setDescription(url,svalue)
#self.story.setMetadata('description',stripHTML(svalue))
if 'Rated' in label:
self.story.setMetadata('rating', value)
if 'Word count' in label:
self.story.setMetadata('numWords', value)
if 'Categories' in label:
cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
for cat in cats:
self.story.addToList('category',cat.string)
if 'Characters' in label:
chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
for char in chars:
self.story.addToList('characters',char.string)
if 'Completed' in label:
if 'Yes' in value:
self.story.setMetadata('status', 'Completed')
else:
self.story.setMetadata('status', 'In-Progress')
if 'Published' in label:
value=value.replace('st','th').replace('nd','th').replace('rd','th')
self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
if 'Updated' in label:
value=value.replace('st','th').replace('nd','th').replace('rd','th')
self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
try:
# Find Series name from series URL.
a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
series_name = a.string
series_url = 'http://'+self.host+'/'+a['href']
# use BeautifulSoup HTML parser to make everything easier to find.
seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
i=1
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
break
i+=1
except:
# I find it hard to care if the series parsing fails
pass
# grab the text for an individual chapter.
def getChapterText(self, url):
logging.debug('Getting chapter text from: %s' % url)
soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
div = soup.find('div', {'id' : 'story'})
if None == div:
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
return self.utf8FromSoup(url,div)
@@ -0,0 +1,255 @@
# -*- 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
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, makeDate
def getClass():
return ErosnSapphoSycophantHexComAdapter
# Class name has to be unique. Our convention is camel case the
# sitename with Adapter at the end. www is skipped.
class ErosnSapphoSycophantHexComAdapter(BaseSiteAdapter):
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.decode = ["Windows-1252",
"utf8"] # 1252 is a superset of iso-8859-1.
# Most sites that claim to be
# iso-8859-1 (and some that claim to be
# utf8) are really windows-1252.
self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
self.password = ""
self.is_adult=False
# get storyId from url--url validation guarantees query is only sid=1234
self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
# normalized story URL.
self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
# Each adapter needs to have a unique site abbreviation.
self.story.setMetadata('siteabbrev','essph')
# If all stories from the site fall into the same category,
# the site itself isn't likely to label them as such, so we
# do.
self.story.addToList("category","Harry Potter")
# The date format will vary from site to site.
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
self.dateformat = "%d/%m/%y"
@staticmethod # must be @staticmethod, don't remove it.
def getSiteDomain():
# The site domain. Does have www here, if it uses it.
return 'erosnsappho.sycophanthex.com'
def getSiteExampleURLs(self):
return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
def getSiteURLPattern(self):
return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
## Getting the chapter list and the meta data, plus 'is adult' checking.
def extractChapterUrlsAndMetadata(self):
if self.is_adult or self.getConfig("is_adult"):
# Weirdly, different sites use different warning numbers.
# If the title search below fails, there's a good chance
# you need a different number. print data at that point
# and see what the 'click here to continue' url says.
addurl = "&ageconsent=ok&warning=18"
else:
addurl=""
# index=1 makes sure we see the story chapter index. Some
# sites skip that for one-chapter stories.
url = self.url+'&index=1'+addurl
logging.debug("URL: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
m = re.search(r"'viewstory.php\?sid=\d+((?:&amp;ageconsent=ok)?&amp;warning=\d+)'",data)
if m != None:
if self.is_adult or self.getConfig("is_adult"):
# We tried the default and still got a warning, so
# let's pull the warning number from the 'continue'
# link and reload data.
addurl = m.group(1)
# correct stupid &amp; error in url.
addurl = addurl.replace("&amp;","&")
url = self.url+'&index=1'+addurl
logging.debug("URL 2nd try: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
else:
raise exceptions.AdultCheckRequired(self.url)
if "Access denied. This story has not been validated by the adminstrators of this site." in data:
raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data)
# print data
# Now go hunting for all the meta data and the chapter list.
## Title
pt = soup.find('div', {'id' : 'pagetitle'})
a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
self.story.setMetadata('title',a.text)
# Find authorid and URL from... author url.
a = pt.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
self.story.setMetadata('authorId',a['href'].split('=')[1])
self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
self.story.setMetadata('author',a.string)
rating=pt.text.split('(')[1].split(')')[0]
self.story.setMetadata('rating', rating)
# Find the chapters:
for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
# just in case there's tags, like <i> in chapter titles.
self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))
self.story.setMetadata('numChapters',len(self.chapterUrls))
# eFiction sites don't help us out a lot with their meta data
# formating, so it's a little ugly.
# utility method
def defaultGetattr(d,k):
try:
return d[k]
except:
return ""
# <span class="label">Rated:</span> NC-17<br /> etc
labels = soup.findAll('span',{'class':'label'})
value = labels[0].previousSibling
svalue = ""
while value != None:
val = value
value = value.previousSibling
while not defaultGetattr(val,'class') == 'label':
svalue += str(val)
val = val.nextSibling
self.setDescription(url,svalue)
for labelspan in labels:
value = labelspan.nextSibling
label = labelspan.string
if 'Word count' in label:
self.story.setMetadata('numWords', value.split(' -')[0])
if 'Categories' in label:
cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
for cat in cats:
self.story.addToList('category',cat.string)
if 'Characters' in label:
chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
for char in chars:
self.story.addToList('characters',char.string)
if 'Genre' in label:
genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
for genre in genres:
self.story.addToList('genre',genre.string)
if 'Warnings' in label:
warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
for warning in warnings:
self.story.addToList('warnings',warning.string)
if 'Complete' in label:
if 'Yes' in value:
self.story.setMetadata('status', 'Completed')
else:
self.story.setMetadata('status', 'In-Progress')
if 'Published' in label:
self.story.setMetadata('datePublished', makeDate(stripHTML(value.split(' -')[0]), self.dateformat))
if 'Updated' in label:
# there's a stray [ at the end.
#value = value[0:-1]
self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
try:
# Find Series name from series URL.
a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
series_name = a.string
series_url = 'http://'+self.host+'/'+a['href']
# use BeautifulSoup HTML parser to make everything easier to find.
seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
i=1
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
break
i+=1
except:
# I find it hard to care if the series parsing fails
pass
# grab the text for an individual chapter.
def getChapterText(self, url):
logging.debug('Getting chapter text from: %s' % url)
soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
div = soup.find('div', {'id' : 'story'})
if None == div:
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
return self.utf8FromSoup(url,div)
@@ -23,9 +23,14 @@ import time
from .. import BeautifulSoup as bs
from .. import exceptions as exceptions
from ..htmlcleanup import stripHTML
from base_adapter import BaseSiteAdapter, makeDate
ffnetgenres=["Adventure", "Angst", "Crime", "Drama", "Family", "Fantasy", "Friendship", "General",
"Horror", "Humor", "Hurt-Comfort", "Mystery", "Parody", "Poetry", "Romance", "Sci-Fi",
"Spiritual", "Supernatural", "Suspense", "Tragedy", "Western"]
class FanFictionNetSiteAdapter(BaseSiteAdapter):
def __init__(self, config, url):
@@ -198,55 +203,45 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
## Pull some additional data from html. Find Rating and look around it.
a = soup.find('a', href='http://www.fictionratings.com/')
self.story.setMetadata('rating',a.string)
# used below to get correct characters.
metatext = a.findNext(text=re.compile(r' - Reviews:'))
if metatext == None: # indicates there's no Reviews, look for id: instead.
metatext = a.findNext(text=re.compile(r' - id:'))
rating = a.string
if 'Fiction' in rating: # if rating has 'Fiction ', strip that out for consistency with past.
rating = rating[8:]
self.story.setMetadata('rating',rating)
# after Rating, the same bit of text containing id:123456 contains
# Complete--if completed.
if 'Complete' in a.findNext(text=re.compile(r'id:'+self.story.getMetadata('storyId'))):
gui_table1i = soup.find(id="gui_table1i")
metatext = stripHTML(gui_table1i.find('div', {'style':'color:gray;'})).replace('Hurt/Comfort','Hurt-Comfort')
metalist = metatext.split(" - ")
#print("metatext:(%s)"%metalist)
# rating is obtained above more robustly.
if metalist[0].startswith('Rated:'):
metalist=metalist[1:]
# next is assumed to be language.
self.story.setMetadata('language',metalist[0])
metalist=metalist[1:]
# next might be genre.
genrelist = metalist[0].split('/') # Hurt/Comfort already changed above.
goodgenres=True
for g in genrelist:
if g not in ffnetgenres:
goodgenres=False
if goodgenres:
self.story.extendList('genre',genrelist)
metalist=metalist[1:]
# next might be characters, otherwise Reviews, Updated or Published
if not ( metalist[0].startswith('Reviews') or metalist[0].startswith('Updated') or metalist[0].startswith('Published') ):
self.story.extendList('characters',metalist[0].split(' & '))
if 'Status: Complete' in metatext:
self.story.setMetadata('status', 'Completed')
else:
self.story.setMetadata('status', 'In-Progress')
# Parse genre(s) from <meta name="description" content="..."
# <meta name="description" content="A Transformers/Beast Wars - Humor fanfiction with characters Prowl & Sideswipe. Story summary: Sideswipe is bored. Prowl appears to be so, too or at least, Sideswipe thinks he looks bored . So Sideswipe entertains them. After all, what's more fun than a race? Song-fic.">
# <meta name="description" content="Chapter 1 of a Transformers/Beast Wars - Adventure/Friendship fanfiction with characters Bumblebee. TFA: What would you do if you was being abused all you life? Follow NightRunner as she goes through her spark breaking adventure of getting away from her father..">
# (fp)<meta name="description" content="Chapter 1 of a Sci-Fi - Adventure/Humor fiction. Felix Max was just your regular hyperactive kid until he accidently caused his own fathers death. Now he has meta-humans trying to hunt him down with a corrupt goverment to back them up. Oh, and did I mention he has no Powers yet?.">
# <meta name="description" content="Chapter 1 of a Bleach - Adventure/Angst fanfiction with characters Ichigo K. & Neliel T. O./Nel. Time travel with a twist. Time can be a real bi***. Ichigo finds that fact out when he accidentally goes back in time. Is this his second chance or is fate just screwing with him. Not a crack fic.IchixNelXHime.">
# <meta name="description" content="Chapter 1 of a Harry Potter and Transformers - Humor/Adventure crossover fanfiction with characters: Harry P. & Ironhide. ITs one thing to be tossed thru the Veil for something he didnt do. It was quite another to wake in his animigus form in a world not his own. Harry just knew someone was laughing at him somewhere. Mech/Mech pairings inside..">
m = re.match(r"^(?:Chapter \d+ of a|A) (?:.*?) (?:- (?P<genres>.*?) )?(?:crossover )?(?:fan)?fiction(?P<chars>[ ]+with characters)?",
soup.find('meta',{'name':'description'})['content'])
if m != None:
genres=m.group('genres')
if genres != None:
# Hurt/Comfort is one genre.
genres=re.sub('Hurt/Comfort','Hurt-Comfort',genres)
for g in genres.split('/'):
self.story.addToList('genre',g)
if m.group('chars') != None:
# At this point we've proven that there's character(s)
# We can't reliably parse characters out of meta name="description".
# There's no way to tell that "with characters Ichigo K. & Neliel T. O./Nel. " ends at "Nel.", not "T."
# But we can pull them from the reviewstext line, now that we know about existance of chars.
# reviewstext can take form of:
# - English - Shinji H. - Updated: 01-13-12 - Published: 12-20-11 - id:7654123
# - English - Adventure/Angst - Ichigo K. & Neliel T. O./Nel - Reviews:
# - English - Humor/Adventure - Harry P. & Ironhide - Reviews:
mc = re.match(r" - (?P<lang>[^ ]+ - )(?P<genres>[^ ]+ - )? (?P<chars>.+?) - (Reviews|Updated|Published)",
metatext)
chars = mc.group("chars")
for c in chars.split(' & '):
self.story.addToList('characters',c)
m = re.match(r" - (?P<lang>[^ ]+)",metatext)
if m.group('lang') != None:
self.story.setMetadata('language',m.group('lang'))
return
def getChapterText(self, url):
@@ -262,13 +257,11 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
sharediv = soup.find('div', {'class' : 'a2a_kit a2a_default_style'})
if sharediv:
sharediv.extract()
else:
logging.debug('share button div not found')
div = soup.find('div', {'id' : 'storytext'})
div = soup.find('div', {'id' : 'storytextp'})
if None == div:
logging.debug('div id=storytext not found. data:%s'%data)
logging.debug('div id=storytextp not found. data:%s'%data)
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
return self.utf8FromSoup(url,div)
@@ -20,7 +20,8 @@ import logging
import re
import urllib2
import cookielib as cl
import datetime
from datetime import datetime
import json
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
@@ -36,7 +37,7 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.story.setMetadata('siteabbrev','fimficnet')
self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])
self.story.setMetadata('storyId', self.parsedUrl.path.split('/',)[2])
self._setURL("http://"+self.getSiteDomain()+"/story/"+self.story.getMetadata('storyId')+"/")
self.is_adult = False
@@ -74,6 +75,10 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
self.opener = urllib2.build_opener(cookieproc)
try:
apiResponse = urllib2.urlopen("http://www.fimfiction.net/api/story.php?story=%s" % (self.story.getMetadata("storyId"))).read()
apiData = json.loads(apiResponse)
# Unfortunately, we still need to load the story index page to parse the characters
data = self._fetchUrl(self.url)
except urllib2.HTTPError, e:
if e.code == 404:
@@ -87,9 +92,12 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
if "/images/missing_story.png" in data:
raise exceptions.StoryDoesNotExist(self.url)
if "Invalid story id" in apiData.values():
raise exceptions.StoryDoesNotExist(self.url)
if "This story has been marked as having adult content." in data:
raise exceptions.AdultCheckRequired(self.url)
if self.password:
params = {}
params['password'] = self.password
@@ -100,95 +108,56 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
raise exceptions.FailedToDownload("%s requires story password and fail_on_password is true."%self.url)
else:
raise exceptions.FailedToLogin(self.url,"Story requires individual password",passwdonly=True)
storyMetadata = apiData["story"]
self.story.setMetadata("title", storyMetadata["title"])
self.story.setMetadata("author", storyMetadata["author"]["name"])
self.story.setMetadata("authorId", storyMetadata["author"]["id"])
self.story.setMetadata("authorUrl", "http://%s/user/%s" % (self.getSiteDomain(), storyMetadata["author"]["name"]))
soup = bs.BeautifulSoup(data).find("div", {"class":"content_box post_content_box"})
titleheader = soup.find("h2")
title = titleheader.find("a", href=re.compile(r'^/story/')).text
author = titleheader.find("a", href=re.compile(r'^/user/')).text
self.story.setMetadata("title", title)
self.story.setMetadata("author", author)
self.story.setMetadata("authorId", author) # The author's name will be unique
self.story.setMetadata("authorUrl", "http://%s/user/%s" % (self.getSiteDomain(),author))
chapters = [{"chapterTitle": chapter["title"], "chapterURL": chapter["link"]} for chapter in storyMetadata["chapters"]]
for chapter in chapters:
self.chapterUrls.append((chapter["chapterTitle"], chapter["chapterURL"]))
self.story.setMetadata("numChapters", len(self.chapterUrls))
chapterDates = []
for chapter in soup.findAll("a", {"class":"chapter_link"}):
chapterDates.append(chapter.span.extract().text.strip("()"))
self.chapterUrls.append((chapter.text.strip(), "http://"+self.getSiteDomain() + chapter['href']))
self.story.setMetadata('numChapters',len(self.chapterUrls))
for character in [character_icon['title'] for character_icon in soup.findAll("a", {"class":"character_icon"})]:
self.story.addToList("characters", character)
for category in [category.text for category in soup.find("div", {"class":"categories"}).findAll("a")]:
self.story.addToList("genre", category)
self.story.addToList("category", "My Little Pony")
# The very last list element in the list of chapters contains the status, rating and word count e.g.:
#
# <li>
# Incomplete | Rating:
# <span style="color:#c78238;">Teen</span>
# <div class="word_count"><b>5,203</b>words total</div>
# </li>
#
status_bar = soup.findAll('li')[-1]
# In the case of fimfiction.net, possible statuses are 'Completed', 'Incomplete', 'On Hiatus' and 'Cancelled'
# For the sake of bringing it in line with the other adapters, 'Incomplete' and 'On Hiatus' become 'In-Progress'
# and 'Complete' beomes 'Completed'. 'Cancelled' seems an important enough (not to mention more strictly true)
# status to leave unchanged.
status = status_bar.text.split("|")[0].strip().replace("Incomplete", "In-Progress").replace("On Hiatus", "In-Progress").replace("Complete", "Completed")
self.story.setMetadata('status', status)
self.story.setMetadata('rating', status_bar.span.text)
# This way is less elegant, perhaps, but more robust in face of format changes.
numWords = status_bar.find("div",{"class":"word_count"}).b.text
self.story.setMetadata('numWords', numWords)
description_soup = soup.find("div", {"class":"description"})
# Sometimes the description has an expanding element
# This removes the ellipsis and the expand button
try:
description_soup.find('span', {"id":re.compile(r"description_more_elipses_\d+")}).extract() # Web designer can't spell 'ellipsis'
description_soup.find('a', {"class":"more"}).extract()
except:
pass
status = storyMetadata["status"].replace("Incomplete", "In-Progress").replace("On Hiatus", "In-Progress").replace("Complete", "Completed")
self.story.setMetadata("status", status)
self.story.setMetadata("rating", storyMetadata["content_rating_text"])
for category in storyMetadata["categories"]:
if storyMetadata["categories"][category]:
self.story.addToList("genre", category)
self.story.addToList("category", "My Little Pony")
self.story.setMetadata("numWords", str(storyMetadata["words"]))
# fimfic is the first site with an explicit cover image.
story_img = soup.find('img',{'class':'story_image'})
if self.getConfig('include_images') and story_img:
self.story.addImgUrl(self,self.url,story_img['src'],self._fetchUrlRaw,cover=True)
self.setDescription(self.url,description_soup.text)
#self.story.setMetadata('description', description_soup.text)
if self.getConfig('include_images') and "image" in storyMetadata.keys():
coverurl = storyMetadata["image"]
if coverurl.startswith('//static.fimfiction.net'): # fix for img urls missing 'http:'
coverurl = "http:"+coverurl
self.story.addImgUrl(self,self.url,coverurl,self._fetchUrlRaw,cover=True)
self.setDescription(self.url, storyMetadata["description"])
# Unfortunately, nowhere on the page is the year mentioned.
# Best effort to deal with this:
# Use this year, if that's a date in the future, subtract one year.
# Their earliest story is Jun, so they'll probably change the date
# around then.
now = datetime.datetime.now()
# Dates are in Unix time
# Take the publish date from the first chapter posted
rawDatePublished = storyMetadata["chapters"][0]["date_modified"]
self.story.setMetadata("datePublished", datetime.fromtimestamp(rawDatePublished))
rawDateUpdated = storyMetadata["date_modified"]
self.story.setMetadata("dateUpdated", datetime.fromtimestamp(rawDateUpdated))
dateUpdated_soup = bs.BeautifulSoup(data).find("div", {"class":"calendar"})
dateUpdated_soup.find('span').extract()
dateUpdated = makeDate("%s%s"%(now.year,dateUpdated_soup.text), "%Y%b%d")
if dateUpdated > now :
dateUpdated = dateUpdated.replace(year=now.year-1)
self.story.setMetadata("dateUpdated", dateUpdated)
# Get the date of creation from the first chapter
if len(chapterDates) > 0:
datePublished_text = chapterDates[0]
day, month = datePublished_text.split()
day = re.sub(r"[^\d.]+", '', day)
datePublished = makeDate("%s%s%s"%(now.year,month,day), "%Y%b%d")
if datePublished > now :
datePublished = datePublished.replace(year=now.year-1)
self.story.setMetadata("datePublished", datePublished)
else:
self.story.setMetadata("datePublished", dateUpdated)
soup = bs.BeautifulSoup(data).find("div", {"class":"story"})
for character in [character_icon["title"] for character_icon in soup.findAll("a", {"class":"character_icon"})]:
self.story.addToList("characters", character)
def getChapterText(self, url):
logging.debug('Getting chapter text from: %s' % url)
@@ -0,0 +1,285 @@
# -*- 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
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, makeDate
def getClass():
return IkEternalNetAdapter
# Class name has to be unique. Our convention is camel case the
# sitename with Adapter at the end. www is skipped.
class IkEternalNetAdapter(BaseSiteAdapter):
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.decode = ["Windows-1252",
"utf8"] # 1252 is a superset of iso-8859-1.
# Most sites that claim to be
# iso-8859-1 (and some that claim to be
# utf8) are really windows-1252.
self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
self.password = ""
self.is_adult=False
# get storyId from url--url validation guarantees query is only sid=1234
self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
# normalized story URL.
self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
# Each adapter needs to have a unique site abbreviation.
self.story.setMetadata('siteabbrev','ike')
# If all stories from the site fall into the same category,
# the site itself isn't likely to label them as such, so we
# do.
self.story.addToList("category","InuYasha")
# The date format will vary from site to site.
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
self.dateformat = "%B %d, %Y"
@staticmethod # must be @staticmethod, don't remove it.
def getSiteDomain():
# The site domain. Does have www here, if it uses it.
return 'www.ik-eternal.net'
def getSiteExampleURLs(self):
return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
def getSiteURLPattern(self):
return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
## Login seems to be reasonably standard across eFiction sites.
def needToLoginCheck(self, data):
if 'Registered Users Only' in data \
or 'There is no such account on our website' in data \
or "That password doesn't match the one in our database" in data:
return True
else:
return False
def performLogin(self, url):
params = {}
if self.password:
params['penname'] = self.username
params['password'] = self.password
else:
params['penname'] = self.getConfig("username")
params['password'] = self.getConfig("password")
params['cookiecheck'] = '1'
params['submit'] = 'Submit'
loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login'
logging.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
params['penname']))
d = self._fetchUrl(loginUrl, params)
if "Member Account" 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
## Getting the chapter list and the meta data, plus 'is adult' checking.
def extractChapterUrlsAndMetadata(self):
if self.is_adult or self.getConfig("is_adult"):
# Weirdly, different sites use different warning numbers.
# If the title search below fails, there's a good chance
# you need a different number. print data at that point
# and see what the 'click here to continue' url says.
addurl = "&warning=1"
else:
addurl=""
# index=1 makes sure we see the story chapter index. Some
# sites skip that for one-chapter stories.
url = self.url+'&index=1'+addurl
logging.debug("URL: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
if self.needToLoginCheck(data):
# need to log in for this one.
self.performLogin(url)
data = self._fetchUrl(url)
# The actual text that is used to announce you need to be an
# adult varies from site to site. Again, print data before
# the title search to troubleshoot.
# Since the warning text can change by warning level, let's
# look for the warning pass url. ksarchive uses
# &amp;warning= -- actually, so do other sites. Must be an
# eFiction book.
# viewstory.php?sid=1882&amp;warning=4
# viewstory.php?sid=1654&amp;ageconsent=ok&amp;warning=5
#print data
#m = re.search(r"'viewstory.php\?sid=1882(&amp;warning=4)'",data)
m = re.search(r"'viewstory.php\?sid=\d+((?:&amp;ageconsent=ok)?&amp;warning=\d+)'",data)
if m != None:
if self.is_adult or self.getConfig("is_adult"):
# We tried the default and still got a warning, so
# let's pull the warning number from the 'continue'
# link and reload data.
addurl = m.group(1)
# correct stupid &amp; error in url.
addurl = addurl.replace("&amp;","&")
url = self.url+'&index=1'+addurl
logging.debug("URL 2nd try: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
else:
raise exceptions.AdultCheckRequired(self.url)
if "Access denied. This story has not been validated by the adminstrators of this site." in data:
raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data,selfClosingTags=('p')) #poor formatting of the paragraphs in the title page
# print data
# Now go hunting for all the meta data and the chapter list.
## Title
a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
self.story.setMetadata('title',a.string)
# Find authorid and URL from... author url.
a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
self.story.setMetadata('authorId',a['href'].split('=')[1])
self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
self.story.setMetadata('author',a.string)
# Find the chapters:
for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
# just in case there's tags, like <i> in chapter titles.
self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))
self.story.setMetadata('numChapters',len(self.chapterUrls))
# eFiction sites don't help us out a lot with their meta data
# formating, so it's a little ugly.
# utility method
def defaultGetattr(d,k):
try:
return d[k]
except:
return ""
# <span class="label">Rated:</span> NC-17<br /> etc
asoup = soup.find('div', {'class': 'listbox'})
for a in asoup.findAll('p'):
a.name='br'
labels = asoup.findAll('span',{'class':'label'})
for labelspan in labels:
value = labelspan.nextSibling
label = labelspan.string
if 'Summary' in label:
## Everything until the next span class='label'
svalue = ""
while not defaultGetattr(value,'class') == 'label':
svalue += str(value)
value = value.nextSibling
self.setDescription(url,svalue)
#self.story.setMetadata('description',stripHTML(svalue))
if 'Rated' in label:
self.story.setMetadata('rating', value)
if 'Word count' in label:
self.story.setMetadata('numWords', value)
if 'Categories' in label:
cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
for cat in cats:
self.story.addToList('category',cat.string)
if 'Characters' in label:
chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
for char in chars:
self.story.addToList('characters',char.string)
if 'Genre' in label:
genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
for genre in genres:
self.story.addToList('genre',genre.string)
if 'Warnings' in label:
warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
for warning in warnings:
self.story.addToList('warnings',warning.string)
if 'Completed' in label:
if 'Yes' in value:
self.story.setMetadata('status', 'Completed')
else:
self.story.setMetadata('status', 'In-Progress')
if 'Published' in label:
self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
if 'Updated' in label:
# there's a stray [ at the end.
#value = value[0:-1]
self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
# grab the text for an individual chapter.
def getChapterText(self, url):
logging.debug('Getting chapter text from: %s' % url)
soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
div = soup.find('div', {'id' : 'story'})
if None == div:
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
return self.utf8FromSoup(url,div)
@@ -0,0 +1,250 @@
# -*- 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
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, makeDate
def getClass():
return LibraryOfMoriaComAdapter
# Class name has to be unique. Our convention is camel case the
# sitename with Adapter at the end. www is skipped.
class LibraryOfMoriaComAdapter(BaseSiteAdapter):
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.decode = ["Windows-1252",
"utf8"] # 1252 is a superset of iso-8859-1.
# Most sites that claim to be
# iso-8859-1 (and some that claim to be
# utf8) are really windows-1252.
self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
self.password = ""
self.is_adult=False
# get storyId from url--url validation guarantees query is only sid=1234
self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
# normalized story URL.
self._setURL('http://' + self.getSiteDomain() + '/a/viewstory.php?sid='+self.story.getMetadata('storyId'))
# Each adapter needs to have a unique site abbreviation.
self.story.setMetadata('siteabbrev','lom')
# If all stories from the site fall into the same category,
# the site itself isn't likely to label them as such, so we
# do.
self.story.addToList("category","Lord of the Rings")
# The date format will vary from site to site.
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
self.dateformat = "%B %d, %Y"
@staticmethod # must be @staticmethod, don't remove it.
def getSiteDomain():
# The site domain. Does have www here, if it uses it.
return 'www.libraryofmoria.com'
def getSiteExampleURLs(self):
return "http://"+self.getSiteDomain()+"/a/viewstory.php?sid=1234"
def getSiteURLPattern(self):
return re.escape("http://"+self.getSiteDomain()+"/a/viewstory.php?sid=")+r"\d+$"
## Getting the chapter list and the meta data, plus 'is adult' checking.
def extractChapterUrlsAndMetadata(self):
if self.is_adult or self.getConfig("is_adult"):
addurl = "&ageconsent=ok&warning=3"
else:
addurl=""
# index=1 makes sure we see the story chapter index. Some
# sites skip that for one-chapter stories.
url = self.url+addurl
logging.debug("URL: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
m = re.search(r"'viewstory.php\?sid=\d+((?:&amp;ageconsent=ok)?&amp;warning=\d+)'",data)
if m != None:
if self.is_adult or self.getConfig("is_adult"):
# We tried the default and still got a warning, so
# let's pull the warning number from the 'continue'
# link and reload data.
addurl = m.group(1)
# correct stupid &amp; error in url.
addurl = addurl.replace("&amp;","&")
url = self.url+'&index=1'+addurl
logging.debug("URL 2nd try: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
else:
raise exceptions.AdultCheckRequired(self.url)
if "Access denied. This story has not been validated by the adminstrators of this site." in data:
raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data)
# print data
# Now go hunting for all the meta data and the chapter list.
## Title
a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
self.story.setMetadata('title',a.string)
# Find authorid and URL from... author url.
a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
self.story.setMetadata('authorId',a['href'].split('=')[1])
self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
self.story.setMetadata('author',a.string)
# Find the chapters:
for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
# just in case there's tags, like <i> in chapter titles.
self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/a/'+chapter['href']+addurl))
self.story.setMetadata('numChapters',len(self.chapterUrls))
# eFiction sites don't help us out a lot with their meta data
# formating, so it's a little ugly.
# utility method
def defaultGetattr(d,k):
try:
return d[k]
except:
return ""
# <span class="label">Rated:</span> NC-17<br /> etc
labels = soup.findAll('span',{'class':'label'})
for labelspan in labels:
value = labelspan.nextSibling
label = labelspan.string
if 'Summary' in label:
## Everything until the next span class='label'
svalue = ""
while not defaultGetattr(value,'class') == 'label':
svalue += str(value)
value = value.nextSibling
self.setDescription(url,svalue)
#self.story.setMetadata('description',stripHTML(svalue))
if 'Rated' in label:
self.story.setMetadata('rating', value)
if 'Word count' in label:
self.story.setMetadata('numWords', value)
if 'Categories' in label:
cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
catstext = [cat.string for cat in cats]
for cat in catstext:
self.story.addToList('category',cat.string)
if 'Characters' in label:
chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
charstext = [char.string for char in chars]
for char in charstext:
self.story.addToList('characters',char.string)
if 'Type' in label:
genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
for genre in genres:
self.story.addToList('genre',genre.string)
if 'Warning' in label:
warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=5'))
for warning in warnings:
self.story.addToList('warnings',warning.string)
if 'Completed' in label:
if 'Yes' in value:
self.story.setMetadata('status', 'Completed')
else:
self.story.setMetadata('status', 'In-Progress')
if 'Published' in label:
self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
if 'Updated' in label:
# there's a stray [ at the end.
#value = value[0:-1]
self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
try:
# Find Series name from series URL.
a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
series_name = a.string
series_url = 'http://'+self.host+'/a/'+a['href']
# use BeautifulSoup HTML parser to make everything easier to find.
seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
i=1
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
break
i+=1
except:
# I find it hard to care if the series parsing fails
pass
# grab the text for an individual chapter.
def getChapterText(self, url):
logging.debug('Getting chapter text from: %s' % url)
soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
div = soup.find('div', {'id' : 'story'})
if None == div:
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
return self.utf8FromSoup(url,div)
@@ -0,0 +1,239 @@
# -*- 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
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, makeDate
def getClass():
return LumosSycophantHexComAdapter
# Class name has to be unique. Our convention is camel case the
# sitename with Adapter at the end. www is skipped.
class LumosSycophantHexComAdapter(BaseSiteAdapter):
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.decode = ["Windows-1252",
"utf8"] # 1252 is a superset of iso-8859-1.
# Most sites that claim to be
# iso-8859-1 (and some that claim to be
# utf8) are really windows-1252.
self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
self.password = ""
self.is_adult=False
# get storyId from url--url validation guarantees query is only sid=1234
self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
# normalized story URL.
self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
# Each adapter needs to have a unique site abbreviation.
self.story.setMetadata('siteabbrev','lsph')
# If all stories from the site fall into the same category,
# the site itself isn't likely to label them as such, so we
# do.
self.story.addToList("category","Harry Potter")
# The date format will vary from site to site.
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
self.dateformat = "%m/%d/%Y"
@staticmethod # must be @staticmethod, don't remove it.
def getSiteDomain():
# The site domain. Does have www here, if it uses it.
return 'lumos.sycophanthex.com'
def getSiteExampleURLs(self):
return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
def getSiteURLPattern(self):
return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
## Getting the chapter list and the meta data, plus 'is adult' checking.
def extractChapterUrlsAndMetadata(self):
if self.is_adult or self.getConfig("is_adult"):
# Weirdly, different sites use different warning numbers.
# If the title search below fails, there's a good chance
# you need a different number. print data at that point
# and see what the 'click here to continue' url says.
addurl = "&ageconsent=ok&warning=19"
else:
addurl=""
# index=1 makes sure we see the story chapter index. Some
# sites skip that for one-chapter stories.
url = self.url+'&index=1'+addurl
logging.debug("URL: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
# The actual text that is used to announce you need to be an
# adult varies from site to site. Again, print data before
# the title search to troubleshoot.
if "Age Consent Required" in data:
raise exceptions.AdultCheckRequired(self.url)
if "Access denied. This story has not been validated by the adminstrators of this site." in data:
raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data)
# print data
# Now go hunting for all the meta data and the chapter list.
## Title
pt = soup.find('div', {'id' : 'pagetitle'})
a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
self.story.setMetadata('title',a.text)
# Find authorid and URL from... author url.
a = pt.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
self.story.setMetadata('authorId',a['href'].split('=')[1])
self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
self.story.setMetadata('author',a.string)
rating=pt.text.split('(')[1].split(')')[0]
self.story.setMetadata('rating', rating)
# Find the chapters:
for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
# just in case there's tags, like <i> in chapter titles.
self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))
self.story.setMetadata('numChapters',len(self.chapterUrls))
# eFiction sites don't help us out a lot with their meta data
# formating, so it's a little ugly.
# utility method
def defaultGetattr(d,k):
try:
return d[k]
except:
return ""
# <span class="label">Rated:</span> NC-17<br /> etc
labels = soup.findAll('span',{'class':'label'})
value = labels[0].previousSibling
svalue = ""
while value != None:
val = value
value = value.previousSibling
while not defaultGetattr(val,'class') == 'label':
svalue += str(val)
val = val.nextSibling
self.setDescription(url,svalue)
for labelspan in labels:
value = labelspan.nextSibling
label = labelspan.string
if 'Word count' in label:
self.story.setMetadata('numWords', value.split(' -')[0])
if 'Categories' in label:
cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
for cat in cats:
self.story.addToList('category',cat.string)
if 'Characters' in label:
chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
for char in chars:
self.story.addToList('characters',char.string)
if 'Genre' in label:
genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
for genre in genres:
self.story.addToList('genre',genre.string)
if 'Warnings' in label:
warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
for warning in warnings:
self.story.addToList('warnings',warning.string)
if 'Complete' in label:
if 'Yes' in value:
self.story.setMetadata('status', 'Completed')
else:
self.story.setMetadata('status', 'In-Progress')
if 'Published' in label:
self.story.setMetadata('datePublished', makeDate(stripHTML(value.split(' -')[0]), self.dateformat))
if 'Updated' in label:
# there's a stray [ at the end.
#value = value[0:-1]
self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
try:
# Find Series name from series URL.
a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
series_name = a.string
series_url = 'http://'+self.host+'/'+a['href']
# use BeautifulSoup HTML parser to make everything easier to find.
seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
i=1
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
break
i+=1
except:
# I find it hard to care if the series parsing fails
pass
# grab the text for an individual chapter.
def getChapterText(self, url):
logging.debug('Getting chapter text from: %s' % url)
soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
div = soup.find('div', {'id' : 'story'})
if None == div:
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
return self.utf8FromSoup(url,div)
@@ -0,0 +1,265 @@
# -*- 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
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, makeDate
def getClass():
return OcclumencySycophantHexComAdapter
# Class name has to be unique. Our convention is camel case the
# sitename with Adapter at the end. www is skipped.
class OcclumencySycophantHexComAdapter(BaseSiteAdapter):
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.decode = ["Windows-1252",
"utf8"] # 1252 is a superset of iso-8859-1.
# Most sites that claim to be
# iso-8859-1 (and some that claim to be
# utf8) are really windows-1252.
self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
self.password = ""
self.is_adult=False
# get storyId from url--url validation guarantees query is only sid=1234
self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
# normalized story URL.
self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
# Each adapter needs to have a unique site abbreviation.
self.story.setMetadata('siteabbrev','osph')
# If all stories from the site fall into the same category,
# the site itself isn't likely to label them as such, so we
# do.
self.story.addToList("category","Harry Potter")
# The date format will vary from site to site.
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
self.dateformat = "%m/%d/%Y"
@staticmethod # must be @staticmethod, don't remove it.
def getSiteDomain():
# The site domain. Does have www here, if it uses it.
return 'occlumency.sycophanthex.com'
def getSiteExampleURLs(self):
return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
def getSiteURLPattern(self):
return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
## Login seems to be reasonably standard across eFiction sites.
def needToLoginCheck(self, data):
if 'This story contains adult content and/or themes.' in data \
or "That password doesn't match the one in our database" in data:
return True
else:
return False
def performLogin(self, url):
params = {}
if self.password:
params['penname'] = self.username
params['password'] = self.password
else:
params['penname'] = self.getConfig("username")
params['password'] = self.getConfig("password")
params['rememberme'] = '1'
params['sid'] = ''
params['intent'] = ''
params['submit'] = 'Submit'
loginUrl = 'http://' + self.getSiteDomain() + '/user.php'
logging.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
params['penname']))
d = self._fetchUrl(loginUrl, params)
if "Logout" 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
## Getting the chapter list and the meta data, plus 'is adult' checking.
def extractChapterUrlsAndMetadata(self):
# index=1 makes sure we see the story chapter index. Some
# sites skip that for one-chapter stories.
url = self.url
logging.debug("URL: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
if self.needToLoginCheck(data):
# need to log in for this one.
self.performLogin(url)
data = self._fetchUrl(url)
if "Access denied. This story has not been validated by the adminstrators of this site." in data:
raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data)
# print data
# Now go hunting for all the meta data and the chapter list.
# Find authorid and URL from... author url.
a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
self.story.setMetadata('authorId',a['href'].split('=')[1])
self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
self.story.setMetadata('author',a.string)
asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
try:
# in case link points somewhere other than the first chapter
a = soup.findAll('option')[1]['value']
self.story.setMetadata('storyId',a.split('=',)[1])
url = 'http://'+self.host+'/'+a
soup = bs.BeautifulSoup(self._fetchUrl(url))
except:
pass
for info in asoup.findAll('table', {'class' : 'border'}):
a = info.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
if a != None:
self.story.setMetadata('title',a.text)
break
# Find the chapters:
chapters=soup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+&i=1$'))
if len(chapters) == 0:
self.chapterUrls.append((self.story.getMetadata('title'),url))
else:
for chapter in chapters:
# just in case there's tags, like <i> in chapter titles.
self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']))
self.story.setMetadata('numChapters',len(self.chapterUrls))
# eFiction sites don't help us out a lot with their meta data
# formating, so it's a little ugly.
# utility method
def defaultGetattr(d):
try:
return d.name
except:
return ""
cats = info.findAll('a',href=re.compile('categories.php'))
for cat in cats:
self.story.addToList('category',cat.string)
a = info.find('a', href=re.compile(r'reviews.php\?sid='+self.story.getMetadata('storyId')))
val = a.nextSibling
svalue = ""
while not defaultGetattr(val) == 'br':
val = val.nextSibling
val = val.nextSibling
while not defaultGetattr(val) == 'table':
svalue += str(val)
val = val.nextSibling
self.setDescription(url,svalue)
# <span class="label">Rated:</span> NC-17<br /> etc
labels = info.findAll('b')
for labelspan in labels:
value = labelspan.nextSibling
label = stripHTML(labelspan)
if 'Rating' in label:
self.story.setMetadata('rating', value)
if 'Word Count' in label:
self.story.setMetadata('numWords', value)
if 'Genres' in label:
genres = value.string.split(', ')
for genre in genres:
if genre != 'none':
self.story.addToList('genre',genre)
if 'Characters' in label:
chars = value.string.split(', ')
for char in chars:
if char != 'none':
self.story.addToList('characters',char)
if 'Warnings' in label:
warnings = value.string.split(', ')
for warning in warnings:
if warning != ' none':
self.story.addToList('warnings',warning)
if 'Completed' in label:
if 'Yes' in value:
self.story.setMetadata('status', 'Completed')
else:
self.story.setMetadata('status', 'In-Progress')
if 'Published' in label:
self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
if 'Updated' in label:
# there's a stray [ at the end.
#value = value[0:-1]
self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
# grab the text for an individual chapter.
def getChapterText(self, url):
logging.debug('Getting chapter text from: %s' % url)
data = self._fetchUrl(url)
data = data.replace('<div align="left"', '<div align="left">')
soup = bs.BeautifulSoup(data, selfClosingTags=('br','hr'))
story = soup.find('div', {"align" : "left"})
if None == story:
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
return self.utf8FromSoup(url,story)
@@ -0,0 +1,242 @@
# -*- 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, urllib, cookielib
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, makeDate
def getClass():
return PhoenixSongNetAdapter
# Class name has to be unique. Our convention is camel case the
# sitename with Adapter at the end. www is skipped.
class PhoenixSongNetAdapter(BaseSiteAdapter):
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.decode = ["Windows-1252",
"utf8"] # 1252 is a superset of iso-8859-1.
# Most sites that claim to be
# iso-8859-1 (and some that claim to be
# utf8) are really windows-1252.
self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
self.password = ""
self.is_adult=False
# get storyId from url--url validation guarantees query is only sid=1234
self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[3])
logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
# normalized story URL.
self._setURL('http://' + self.getSiteDomain() + '/fanfiction/story/' +self.story.getMetadata('storyId')+'/')
# Each adapter needs to have a unique site abbreviation.
self.story.setMetadata('siteabbrev','phs')
# If all stories from the site fall into the same category,
# the site itself isn't likely to label them as such, so we
# do.
self.story.addToList("category","Harry Potter")
# The date format will vary from site to site.
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
self.dateformat = "%B %d %Y"
@staticmethod # must be @staticmethod, don't remove it.
def getSiteDomain():
# The site domain. Does have www here, if it uses it.
return 'www.phoenixsong.net'
def getSiteExampleURLs(self):
return "http://"+self.getSiteDomain()+"/fanfiction/story/1234/"
def getSiteURLPattern(self):
return re.escape("http://"+self.getSiteDomain()+"/fanfiction/story/")+r"\d+/?$"
## Login seems to be reasonably standard across eFiction sites.
def needToLoginCheck(self, data):
if 'Please login to continue.' in data:
return True
else:
return False
def performLogin(self, url):
params = {}
if self.password:
params['txtusername'] = self.username
params['txtpassword'] = self.password
else:
params['txtusername'] = self.getConfig("username")
params['txtpassword'] = self.getConfig("password")
#params['remember'] = '1'
params['login'] = 'Login'
loginUrl = 'http://' + self.getSiteDomain() + '/users/processlogin.php'
logging.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
params['txtusername']))
d = self._fetchUrl(loginUrl, params)
if 'Please login to continue.' in d : #Member Account
logging.info("Failed to login to URL %s as %s" % (loginUrl,
params['txtusername']))
raise exceptions.FailedToLogin(url,params['txtusername'])
return False
else:
return True
## Getting the chapter list and the meta data, plus 'is adult' checking.
def extractChapterUrlsAndMetadata(self):
# index=1 makes sure we see the story chapter index. Some
# sites skip that for one-chapter stories.
url = self.url
logging.debug("URL: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
if self.needToLoginCheck(data):
# need to log in for this one.
self.performLogin(url)
data = self._fetchUrl(url)
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data)
# print data
# Now go hunting for all the meta data and the chapter list.
## Title
b = soup.find('div', {'id' : 'nav25'})
a = b.find('a', href=re.compile(r'fanfiction/story/'+self.story.getMetadata('storyId')+"/$"))
self.story.setMetadata('title',a.string)
# Find authorid and URL from... author url. /fanfiction/stories.php?psid=125
a = b.find('a', href=re.compile(r"/fanfiction/stories.php\?psid=\d+"))
self.story.setMetadata('authorId',a['href'].split('=')[1])
self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
self.story.setMetadata('author',a.string)
# Find the chapters:
chapters = soup.find('select')
if chapters == None:
self.chapterUrls.append((self.story.getMetadata('title'),url))
for b in soup.findAll('b'):
if b.text == "Updated":
date = b.nextSibling.string.split(': ')[1].split(',')
self.story.setMetadata('datePublished', makeDate(date[0]+date[1], self.dateformat))
self.story.setMetadata('dateUpdated', makeDate(date[0]+date[1], self.dateformat))
else:
i = 0
chapters = chapters.findAll('option')
for chapter in chapters:
self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+chapter['value']))
if i == 0:
self.story.setMetadata('storyId',chapter['value'].split('/')[3])
head = bs.BeautifulSoup(self._fetchUrl('http://'+self.host+chapter['value'])).findAll('b')
for b in head:
if b.text == "Updated":
date = b.nextSibling.string.split(': ')[1].split(',')
self.story.setMetadata('datePublished', makeDate(date[0]+date[1], self.dateformat))
if i == (len(chapters)-1):
head = bs.BeautifulSoup(self._fetchUrl('http://'+self.host+chapter['value'])).findAll('b')
for b in head:
if b.text == "Updated":
date = b.nextSibling.string.split(': ')[1].split(',')
self.story.setMetadata('dateUpdated', makeDate(date[0]+date[1], self.dateformat))
i = i+1
self.story.setMetadata('numChapters',len(self.chapterUrls))
asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
info = asoup.find('a', href=re.compile(r'fanfiction/story/'+self.story.getMetadata('storyId')+"/$"))
while info != None:
info = info.findNext('div')
b = info.find('b')
val = b.nextSibling
if 'Rating' in b.string:
self.story.setMetadata('rating', val.string.split(': ')[1])
if 'Words' in b.string:
self.story.setMetadata('numWords', val.string.split(': ')[1])
if 'Setting' in b.string:
self.story.addToList('category', val.string.split(': ')[1])
if 'Status' in b.string:
if 'Completed' in val:
val = 'Completed'
else:
val = 'In-Progress'
self.story.setMetadata('status', val)
if 'Summary' in b.string:
b.extract()
info.find('br').extract()
self.setDescription(url,info)
break
# grab the text for an individual chapter.
def getChapterText(self, url):
logging.debug('Getting chapter text from: %s' % url)
soup = bs.BeautifulSoup(self._fetchUrl(url),
selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
chapter=bs.BeautifulSoup('<div class="story"></div>')
for p in soup.findAll('p'):
if "This is for problems with the formatting or the layout of the chapter." in stripHTML(p):
break
chapter.append(p)
for a in chapter.findAll('div'):
a.extract()
for a in chapter.findAll('table'):
a.extract()
for a in chapter.findAll('script'):
a.extract()
for a in chapter.findAll('form'):
a.extract()
for a in chapter.findAll('textarea'):
a.extract()
if None == chapter:
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
return self.utf8FromSoup(url,chapter)
@@ -0,0 +1,234 @@
# -*- 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
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, makeDate
def getClass():
return SquidgeOrgPejaAdapter
## XXX IMPORTANT NOTE!! This adapter is for squidge.org/peja ONLY!
## There are lots of other sites and stuff under squidge.org that
## we're not supporting. If/When we ever want to support more
## sections of squidge.org, FFDL will need to be changed more
## fundamentally to find different adapters under the same domain.
##
## For now, I've only implemented the part for ini section names so
## if/when more adapters under squidge.org come along, existing ini
## files will still work correctly.
# Class name has to be unique. Our convention is camel case the
# sitename with Adapter at the end. www is skipped.
class SquidgeOrgPejaAdapter(BaseSiteAdapter):
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.decode = ["utf8",
"Windows-1252"] # 1252 is a superset of iso-8859-1.
# Most sites that claim to be
# iso-8859-1 (and some that claim to be
# utf8) are really windows-1252.
self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
self.password = ""
self.is_adult=False
# get storyId from url--url validation guarantees query is only sid=1234
self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
# normalized story URL.
self._setURL('http://' + self.getSiteDomain() + '/peja/cgi-bin/viewstory.php?sid='+self.story.getMetadata('storyId'))
# Each adapter needs to have a unique site abbreviation.
self.story.setMetadata('siteabbrev','wwomb')
# The date format will vary from site to site.
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
self.dateformat = "%m/%d/%y"
@staticmethod # must be @staticmethod, don't remove it.
def getSiteDomain():
# The site domain. Does have www here, if it uses it.
return 'www.squidge.org'
@classmethod # must be @staticmethod, don't remove it.
def getConfigSection(cls):
# The config section name. Only override if != site domain.
return cls.getSiteDomain()+'/peja'
def getSiteExampleURLs(self):
return "http://"+self.getSiteDomain()+"/peja/cgi-bin/viewstory.php?sid=1234"
def getSiteURLPattern(self):
return re.escape("http://"+self.getSiteDomain()+"/peja/cgi-bin/viewstory.php?sid=")+r"\d+$"
## Getting the chapter list and the meta data, plus 'is adult' checking.
def extractChapterUrlsAndMetadata(self):
url = self.url
logging.debug("URL: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
data = self._fetchUrl(url)
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data)
# print data
# Now go hunting for all the meta data and the chapter list.
# Find authorid and URL from... author url.
author = soup.find('div', {'id':"pagetitle"}).find('a')
self.story.setMetadata('authorId',author['href'].split('=')[1])
self.story.setMetadata('authorUrl','http://'+self.host+'/peja/cgi-bin/'+author['href'])
self.story.setMetadata('author',author.string)
authorSoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
# eFiction sites don't help us out a lot with their meta data
# formating, so it's a little ugly.
title = authorSoup.find('a',{'href':'viewstory.php?sid='+self.story.getMetadata('storyId')})
self.story.setMetadata('title',title.string)
titleblock=title.parent.parent
chapterselect=soup.find('select',{'name':'chapter'})
if chapterselect:
for ch in chapterselect.findAll('option'):
self.chapterUrls.append((stripHTML(ch),'http://'+self.host+'/peja/cgi-bin/viewstory.php?sid='+self.story.getMetadata('storyId')+'&chapter='+ch['value']))
else:
self.chapterUrls.append((title,url))
self.story.setMetadata('numChapters',len(self.chapterUrls))
# utility method
def defaultGetattr(d,k):
try:
return d[k]
except:
return ""
# <span class="classification">Rated:</span> NC-17<br /> etc
labels = titleblock.findAll('span',{'class':'classification'})
for labelspan in labels:
value = labelspan.nextSibling
label = labelspan.string
if 'Summary' in label:
## Everything until the next span class='label'
svalue = ""
while not defaultGetattr(value,'class') == 'classification':
svalue += str(value)
value = value.nextSibling
self.setDescription(url,svalue)
#self.story.setMetadata('description',stripHTML(svalue))
if 'Rated' in label:
self.story.setMetadata('rating', value)
if 'Characters' in label:
for char in value.split(','):
self.story.addToList('characters',char.strip())
if 'Genre' in label:
for genre in value.split(','):
if genre.strip() != "None":
self.story.addToList('genre',genre.strip())
if 'Warnings' in label:
for warning in value.split(','):
if warning.strip() != 'None':
self.story.addToList('warnings',warning.strip())
if 'Word count' in label:
self.story.setMetadata('numWords', value)
if 'Fandoms' in label:
cats = labelspan.parent.findAll('a',href=re.compile(r'categories.php'))
catstext = [cat.string for cat in cats]
for cat in catstext:
self.story.addToList('category',cat.string)
if 'Completed' in label:
if 'Yes' in value:
self.story.setMetadata('status', 'Completed')
else:
self.story.setMetadata('status', 'In-Progress')
if 'Published' in label:
self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
if 'Updated' in label:
# there's a stray [ at the end.
#value = value[0:-1]
self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
try:
# Find Series name from series URL.
# http://www.squidge.org/peja/cgi-bin/series.php?seriesid=254
a = titleblock.find('a', href=re.compile(r"series.php\?seriesid=\d+"))
series_name = a.string
series_url = 'http://'+self.host+'/peja/cgi-bin/'+a['href']
# use BeautifulSoup HTML parser to make everything easier to find.
seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
i=1
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
break
i+=1
except:
# I find it hard to care if the series parsing fails
pass
# grab the text for an individual chapter.
def getChapterText(self, url):
logging.debug('Getting chapter text from: %s' % url)
soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
chaptext = soup.find('div',{'id':"story"}).find('span')
if None == chaptext:
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
return self.utf8FromSoup(url,chaptext)
+14 -15
View File
@@ -90,17 +90,16 @@ Some more longer description. "I suck at summaries!" "Better than it sounds!"
else:
self.story.setMetadata('status','Completed')
langs = {
0:"English",
1:"Russian",
2:"French",
3:"German",
}
# greater than 10, no language or series.
if idnum < 10:
langs = {
0:"English",
1:"Russian",
2:"French",
3:"German",
}
self.story.setMetadata('language',langs[idnum%len(langs)])
# greater than 10, no language.
self.setSeries('The Great Test',idnum)
self.setSeries('The Great Test',idnum)
self.story.setMetadata('rating','Tweenie')
@@ -161,7 +160,7 @@ Some more longer description. "I suck at summaries!" "Better than it sounds!"
text=u'''
<div>
<h3>Prologue</h3>
<p>This is a fake adapter for testing purposes. Different storyId's will give different errors:</p>
<p>This is a fake adapter for testing purposes. Different sid's will give different errors:</p>
<p>http://test1.com?sid=664 - Crazy string title</p>
<p>http://test1.com?sid=665 - raises AdultCheckRequired</p>
<p>http://test1.com?sid=666 - raises StoryDoesNotExist</p>
@@ -171,19 +170,19 @@ Some more longer description. "I suck at summaries!" "Better than it sounds!"
<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>
<p>Odd sid's will be In-Progress, evens complete. sid&lt;10 will be assigned one of four languages and included in a series.</p>
</div>
'''
else:
text=u'''
<div>
<h3>Chapter title from site</h3>
<p><center>Centered text</center></p>
<p>Lorem '''+self.crazystring+''' <i>italics</i>, <b>bold</b>, <u>underline</u> consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.</p>
<p>Lorem '''+self.crazystring+u''' <i>italics</i>, <b>bold</b>, <u>underline</u> consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.</p>
br breaks<br><br>
<a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownLoaderPluginWithReadingList" title="Tilt-a-Whirl by Jim &amp; Sarah, on Flickr"><img src="http://i.imgur.com/bo8eD.png"></a><br/>
Puella Magi Madoka Magica/魔法少女まどか★マギカ
<!-- a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownLoaderPluginWithReadingList" title="Tilt-a-Whirl by Jim &amp; Sarah, on Flickr"><img src="http://i.imgur.com/bo8eD.png"></a --><br/>
br breaks<br><br>
Don't&#8212e;ver&#8212d;o&#8212;that&#8212a;gain, &#27861; &#xE9;
<hr>
horizontal rules
<hr size=1 noshade>
@@ -0,0 +1,201 @@
# -*- 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
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, makeDate
def getClass():
return TheHexFilesNetAdapter
# Class name has to be unique. Our convention is camel case the
# sitename with Adapter at the end. www is skipped.
class TheHexFilesNetAdapter(BaseSiteAdapter):
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.decode = ["Windows-1252",
"utf8"] # 1252 is a superset of iso-8859-1.
# Most sites that claim to be
# iso-8859-1 (and some that claim to be
# utf8) are really windows-1252.
self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
self.password = ""
self.is_adult=False
# get storyId from url--url validation guarantees query is only sid=1234
self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
# normalized story URL.
self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
# Each adapter needs to have a unique site abbreviation.
self.story.setMetadata('siteabbrev','thf')
# If all stories from the site fall into the same category,
# the site itself isn't likely to label them as such, so we
# do.
self.story.addToList("category","Harry Potter")
# The date format will vary from site to site.
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
self.dateformat = "%Y.%m.%d"
@staticmethod # must be @staticmethod, don't remove it.
def getSiteDomain():
# The site domain. Does have www here, if it uses it.
return 'thehexfiles.net'
@classmethod
def getAcceptDomains(cls):
return ['www.thehexfiles.net','thehexfiles.net']
def getSiteExampleURLs(self):
return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
def getSiteURLPattern(self):
return re.escape("http://")+"(www\.)?"+re.escape(self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
## Getting the chapter list and the meta data, plus 'is adult' checking.
def extractChapterUrlsAndMetadata(self):
# index=1 makes sure we see the story chapter index. Some
# sites skip that for one-chapter stories.
url = self.url
logging.debug("URL: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data)
# print data
# Now go hunting for all the meta data and the chapter list.
# Find authorid and URL from... author url.
a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
self.story.setMetadata('authorId',a['href'].split('=')[1])
self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
self.story.setMetadata('author',a.string)
asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
try:
# in case link points somewhere other than the first chapter
a = soup.findAll('option')[1]['value']
self.story.setMetadata('storyId',a.split('=',)[1])
url = 'http://'+self.host+'/'+a
soup = bs.BeautifulSoup(self._fetchUrl(url))
except:
pass
for info in asoup.findAll('table', {'cellspacing' : '4'}):
a = info.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
if a != None:
self.story.setMetadata('title',a.string)
break
# Find the chapters:
chapters=soup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+&i=1$'))
if len(chapters) == 0:
self.chapterUrls.append((self.story.getMetadata('title'),url))
else:
for chapter in chapters:
# just in case there's tags, like <i> in chapter titles.
self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']))
self.story.setMetadata('numChapters',len(self.chapterUrls))
cats = info.findAll('a',href=re.compile('categories.php'))
for cat in cats:
self.story.addToList('category',cat.string)
words = info.find(text=re.compile('Words:')).split('|')[1].split(': ')[1]
self.story.setMetadata('numWords', words)
comp = info.find('span', {'class' : 'completed'}).string.split(': ')[1]
if 'Yes' in comp:
self.story.setMetadata('status', 'Completed')
else:
self.story.setMetadata('status', 'In-Progress')
summary = info.find('td', {'class' : 'summary'})
self.setDescription(url,summary)
rating=stripHTML(info.find('td', {'align' : 'left'})).split('(')[1].split(')')[0]
self.story.setMetadata('rating', rating)
labels = info.findAll('td', {'width' : '10%'})
values = info.findAll('td', {'width' : '40%'})
for i in range(0,len(labels)):
value = stripHTML(values[i])
label = stripHTML(labels[i])
if 'Genres' in label:
genres = value.split(', ')
for genre in genres:
if genre != 'none':
self.story.addToList('genre',genre)
if 'Warnings' in label:
warnings = value.split(', ')
for warning in warnings:
if warning != 'none':
self.story.addToList('warnings',warning)
if 'Published' in label:
self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
if 'Updated' in label:
# there's a stray [ at the end.
#value = value[0:-1]
self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
# grab the text for an individual chapter.
def getChapterText(self, url):
logging.debug('Getting chapter text from: %s' % url)
soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
for a in soup.findAll('table'):
a.extract()
if None == soup:
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
return self.utf8FromSoup(url,soup)
@@ -0,0 +1,233 @@
# -*- 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
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, makeDate
def getClass():
return WalkingThePlankOrgAdapter
class WalkingThePlankOrgAdapter(BaseSiteAdapter):
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.decode = ["Windows-1252",
"utf8"] # 1252 is a superset of iso-8859-1.
# Most sites that claim to be
# iso-8859-1 (and some that claim to be
# utf8) are really windows-1252.
self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
self.password = ""
self.is_adult=False
# get storyId from url--url validation guarantees query is only sid=1234
self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
# normalized story URL.
self._setURL('http://' + self.getSiteDomain() + '/archive/viewstory.php?sid='+self.story.getMetadata('storyId'))
# Each adapter needs to have a unique site abbreviation.
self.story.setMetadata('siteabbrev','wtp')
# If all stories from the site fall into the same category,
# the site itself isn't likely to label them as such, so we
# do.
self.story.addToList("category","Harry Potter")
# The date format will vary from site to site.
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
self.dateformat = "%b %d, %Y"
@staticmethod # must be @staticmethod, don't remove it.
def getSiteDomain():
# The site domain. Does have www here, if it uses it.
return 'www.walkingtheplank.org'
def getSiteExampleURLs(self):
return "http://"+self.getSiteDomain()+"/archive/viewstory.php?sid=1234"
def getSiteURLPattern(self):
return re.escape("http://"+self.getSiteDomain()+"/archive/viewstory.php?sid=")+r"\d+$"
## Getting the chapter list and the meta data, plus 'is adult' checking.
def extractChapterUrlsAndMetadata(self):
if self.is_adult or self.getConfig("is_adult"):
# Weirdly, different sites use different warning numbers.
# If the title search below fails, there's a good chance
# you need a different number. print data at that point
# and see what the 'click here to continue' url says.
addurl = "&warning=4"
else:
addurl=""
# index=1 makes sure we see the story chapter index. Some
# sites skip that for one-chapter stories.
url = self.url+'&index=1'+addurl
logging.debug("URL: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
# The actual text that is used to announce you need to be an
# adult varies from site to site. Again, print data before
# the title search to troubleshoot.
if "By clicking this link, you acknowledge" in data:
raise exceptions.AdultCheckRequired(self.url)
if "Access denied. This story has not been validated by the adminstrators of this site." in data:
raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data)
# print data
# Now go hunting for all the meta data and the chapter list.
## Title
a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
self.story.setMetadata('title',a.string)
# Find authorid and URL from... author url.
a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
self.story.setMetadata('authorId',a['href'].split('=')[1])
self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
self.story.setMetadata('author',a.string)
# Find the chapters:
for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
# just in case there's tags, like <i> in chapter titles.
self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/archive/'+chapter['href']+addurl))
self.story.setMetadata('numChapters',len(self.chapterUrls))
# eFiction sites don't help us out a lot with their meta data
# formating, so it's a little ugly.
# utility method
def defaultGetattr(d,k):
try:
return d[k]
except:
return ""
labels = soup.findAll('span',{'class':'label'})
for labelspan in labels:
value = labelspan.nextSibling
label = labelspan.string
if 'Summary' in label:
## Everything until the next span class='label'
svalue = ""
while not defaultGetattr(value,'class') == 'label':
svalue += str(value)
value = value.nextSibling
self.setDescription(url,svalue)
#self.story.setMetadata('description',stripHTML(svalue))
if 'Rated' in label:
self.story.setMetadata('rating', value)
if 'Word count' in label:
self.story.setMetadata('numWords', value)
if 'Categories' in label:
cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
catstext = [cat.string for cat in cats]
for cat in catstext:
self.story.addToList('category',cat.string)
if 'Characters' in label:
chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
charstext = [char.string for char in chars]
for char in charstext:
self.story.addToList('characters',char.string)
if 'Genre' in label:
genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
for genre in genres:
self.story.addToList('genre',genre.string)
if 'Warnings' in label:
warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
for warning in warnings:
self.story.addToList('warnings',warning.string)
if 'Completed' in label:
if 'Yes' in value:
self.story.setMetadata('status', 'Completed')
else:
self.story.setMetadata('status', 'In-Progress')
if 'Published' in label:
self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
if 'Updated' in label:
self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
try:
# Find Series name from series URL.
a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
series_name = a.string
series_url = 'http://'+self.host+'/archive/'+a['href']
# use BeautifulSoup HTML parser to make everything easier to find.
seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
i=1
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
break
i+=1
except:
# I find it hard to care if the series parsing fails
pass
# grab the text for an individual chapter.
def getChapterText(self, url):
logging.debug('Getting chapter text from: %s' % url)
soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
div = soup.find('div', {'id' : 'story'})
if None == div:
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
return self.utf8FromSoup(url,div)
@@ -0,0 +1,227 @@
# -*- 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
from .. import BeautifulSoup as bs
from ..htmlcleanup import stripHTML
from .. import exceptions as exceptions
from base_adapter import BaseSiteAdapter, makeDate
def getClass():
return WraithBaitComAdapter
# Class name has to be unique. Our convention is camel case the
# sitename with Adapter at the end. www is skipped.
class WraithBaitComAdapter(BaseSiteAdapter):
def __init__(self, config, url):
BaseSiteAdapter.__init__(self, config, url)
self.decode = ["Windows-1252",
"utf8"] # 1252 is a superset of iso-8859-1.
# Most sites that claim to be
# iso-8859-1 (and some that claim to be
# utf8) are really windows-1252.
self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
self.password = ""
self.is_adult=False
# get storyId from url--url validation guarantees query is only sid=1234
self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
# Each adapter needs to have a unique site abbreviation.
self.story.setMetadata('siteabbrev','wb')
# If all stories from the site fall into the same category,
# the site itself isn't likely to label them as such, so we
# do.
self.story.addToList("category","Stargate")
# The date format will vary from site to site.
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
self.dateformat = "%d %b %Y"
@staticmethod # must be @staticmethod, don't remove it.
def getSiteDomain():
# The site domain. Does have www here, if it uses it.
return 'www.wraithbait.com'
def getSiteExampleURLs(self):
return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
def getSiteURLPattern(self):
return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
## Getting the chapter list and the meta data, plus 'is adult' checking.
def extractChapterUrlsAndMetadata(self):
if self.is_adult or self.getConfig("is_adult"):
# Weirdly, different sites use different warning numbers.
# If the title search below fails, there's a good chance
# you need a different number. print data at that point
# and see what the 'click here to continue' url says.
addurl = "&ageconsent=ok&warning=12"
else:
addurl=""
# index=1 makes sure we see the story chapter index. Some
# sites skip that for one-chapter stories.
url = self.url+'&index=1'+addurl
logging.debug("URL: "+url)
try:
data = self._fetchUrl(url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
else:
raise e
if "for adults only" in data:
raise exceptions.AdultCheckRequired(self.url)
if "Access denied. This story has not been validated by the adminstrators of this site." in data:
raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
# use BeautifulSoup HTML parser to make everything easier to find.
soup = bs.BeautifulSoup(data)
# print data
# Now go hunting for all the meta data and the chapter list.
## Title
pt = soup.find('div', {'id' : 'pagetitle'})
a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
self.story.setMetadata('title',a.string)
# Find authorid and URL from... author url.
a = pt.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
self.story.setMetadata('authorId',a['href'].split('=')[1])
self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
self.story.setMetadata('author',a.string)
rating=pt.text.split('[')[1].split(']')[0]
self.story.setMetadata('rating', rating)
# Find the chapters:
for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
# just in case there's tags, like <i> in chapter titles.
self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))
self.story.setMetadata('numChapters',len(self.chapterUrls))
# eFiction sites don't help us out a lot with their meta data
# formating, so it's a little ugly.
# utility method
def defaultGetattr(d,k):
try:
return d[k]
except:
return ""
info = soup.find('div', {'class' : 'small'})
word=info.find(text=re.compile("Word count:")).split(':')
self.story.setMetadata('numWords', word[1])
cats = info.findAll('a',href=re.compile(r'browse.php\?type=categories&id=\d'))
for cat in cats:
if "General" != cat.string:
self.story.addToList('category',cat.string)
chars = info.findAll('a',href=re.compile(r'browse.php\?type=characters&charid=\d'))
for char in chars:
self.story.addToList('characters',char.string)
completed=info.find(text=re.compile("Completed: Yes"))
if completed != None:
self.story.setMetadata('status', 'Completed')
else:
self.story.setMetadata('status', 'In-Progress')
date=soup.find('div',{'class' : 'bottom'})
pd=date.find(text=re.compile("Published:")).string.split(': ')
self.story.setMetadata('datePublished', makeDate(stripHTML(pd[1].split(' U')[0]), self.dateformat))
self.story.setMetadata('dateUpdated', makeDate(stripHTML(pd[2]), self.dateformat))
# <span class="label">Rated:</span> NC-17<br /> etc
labels = soup.findAll('span',{'class':'label'})
pub=0
for labelspan in labels:
value = labelspan.nextSibling
label = labelspan.string
if 'Genres' in label:
genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
for genre in genres:
self.story.addToList('genre',genre.string)
if 'Warnings' in label:
warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
for warning in warnings:
self.story.addToList('warnings',warning.string)
try:
# Find Series name from series URL.
a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
series_name = a.string
series_url = 'http://'+self.host+'/'+a['href']
# use BeautifulSoup HTML parser to make everything easier to find.
seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
i=1
for a in storyas:
if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
self.setSeries(series_name, i)
break
i+=1
except:
# I find it hard to care if the series parsing fails
pass
info.extract()
summary = soup.find('div', {'class' : 'content'})
self.setDescription(url,summary)
# grab the text for an individual chapter.
def getChapterText(self, url):
logging.debug('Getting chapter text from: %s' % url)
soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
div = soup.find('div', {'id' : 'story'})
if None == div:
raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url)
return self.utf8FromSoup(url,div)
+19 -5
View File
@@ -70,9 +70,7 @@ class BaseSiteAdapter(Configurable):
def __init__(self, config, url):
self.config = config
Configurable.__init__(self, config)
self.setSectionOrder(self.getSiteDomain())
# self.addConfigSection(self.getSiteDomain())
# self.addConfigSection("overrides")
self.setSectionOrder(self.getConfigSection())
self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
self.password = ""
@@ -82,13 +80,15 @@ class BaseSiteAdapter(Configurable):
self.storyDone = False
self.metadataDone = False
self.story = Story()
self.story.setMetadata('site',self.getSiteDomain())
self.story.setMetadata('site',self.getConfigSection())
self.story.setMetadata('dateCreated',datetime.datetime.now())
self.chapterUrls = [] # tuples of (chapter title,chapter url)
self.chapterFirst = None
self.chapterLast = None
self.oldchapters = None
self.oldimgs = None
self.oldcover = None # (data of existing cover html, data of existing cover image)
self.calibrebookmark = None
## order of preference for decoding.
self.decode = ["utf8",
"Windows-1252"] # 1252 is a superset of
@@ -220,6 +220,15 @@ class BaseSiteAdapter(Configurable):
self.getConfig('allow_unsafe_filename')),
self._fetchUrlRaw,
cover=True)
# no new cover, set old cover, if there is one.
if not self.story.cover and self.oldcover:
self.story.oldcover = self.oldcover
# cheesy way to carry calibre bookmark file forward across update.
if self.calibrebookmark:
self.story.calibrebookmark = self.calibrebookmark
return self.story
def getStoryMetadataOnly(self):
@@ -235,6 +244,11 @@ class BaseSiteAdapter(Configurable):
"Needs to be overriden in each adapter class."
return 'no such domain'
@classmethod
def getConfigSection(cls):
"Only needs to be overriden if != site domain."
return cls.getSiteDomain()
## URL pattern validation is done *after* picking an adaptor based
## on domain instead of *as* the adaptor selector so we can offer
## the user example(s) for that particular site.
@@ -262,7 +276,7 @@ class BaseSiteAdapter(Configurable):
# Just for series, in case we choose to change how it's stored or represented later.
def setSeries(self,name,num):
if self.getConfig('collect_series'):
self.story.setMetadata('series','%s [%s]'%(name, num))
self.story.setMetadata('series','%s [%s]'%(name, int(num)))
def setDescription(self,url,svalue):
#print("\n\nsvalue:\n%s\n"%svalue)
+88 -2
View File
@@ -40,6 +40,50 @@ def get_update_data(inputio,
## Save the path to the .opf file--hrefs inside it are relative to it.
relpath = get_path_part(rootfilename)
oldcover = None
calibrebookmark = None
# Looking for pre-existing cover.
for item in contentdom.getElementsByTagName("reference"):
if item.getAttribute("type") == "cover":
# there is a cover (x)html file, save the soup for it.
href=relpath+item.getAttribute("href")
oldcoverhtmlhref = href
oldcoverhtmldata = epub.read(href)
oldcoverhtmltype = "application/xhtml+xml"
for item in contentdom.getElementsByTagName("item"):
if( relpath+item.getAttribute("href") == oldcoverhtmlhref ):
oldcoverhtmltype = item.getAttribute("media-type")
break
soup = bs.BeautifulSoup(oldcoverhtmldata.decode("utf-8"))
src = None
# first img or image tag.
imgs = soup.findAll('img')
if imgs:
src = get_path_part(href)+imgs[0]['src']
else:
imgs = soup.findAll('image')
if imgs:
src=get_path_part(href)+imgs[0]['xlink:href']
if not src:
continue
try:
# remove all .. and the path part above it, if present.
# Mostly for epubs edited by Sigil.
src = re.sub(r"([^/]+/\.\./)","",src)
print("epubutils: found pre-existing cover image:%s"%src)
oldcoverimghref = src
oldcoverimgdata = epub.read(src)
for item in contentdom.getElementsByTagName("item"):
if( relpath+item.getAttribute("href") == oldcoverimghref ):
oldcoverimgtype = item.getAttribute("media-type")
break
oldcover = (oldcoverhtmlhref,oldcoverhtmltype,oldcoverhtmldata,oldcoverimghref,oldcoverimgtype,oldcoverimgdata)
except Exception as e:
print("Cover Image %s not found"%src)
print("Exception: %s"%(unicode(e)))
traceback.print_exc()
filecount = 0
soups = [] # list of xhmtl blocks
images = {} # dict() longdesc->data
@@ -61,7 +105,7 @@ def get_update_data(inputio,
try:
newsrc=get_path_part(href)+img['src']
# remove all .. and the path part above it, if present.
# Most for epubs edited by Sigil.
# Mostly for epubs edited by Sigil.
newsrc = re.sub(r"([^/]+/\.\./)","",newsrc)
longdesc=img['longdesc']
data = epub.read(newsrc)
@@ -85,12 +129,54 @@ def get_update_data(inputio,
filecount+=1
try:
calibrebookmark = epub.read("META-INF/calibre_bookmarks.txt")
except:
pass
for k in images.keys():
print("\tlongdesc:%s\n\tData len:%s\n"%(k,len(images[k])))
return (source,filecount,soups,images)
return (source,filecount,soups,images,oldcover,calibrebookmark)
def get_path_part(n):
relpath = os.path.dirname(n)
if( len(relpath) > 0 ):
relpath=relpath+"/"
return relpath
def get_story_url_from_html(inputio,_is_good_url=None):
#print("get_story_url_from_html called")
epub = ZipFile(inputio, 'r')
## Find the .opf file.
container = epub.read("META-INF/container.xml")
containerdom = parseString(container)
rootfilenodelist = containerdom.getElementsByTagName("rootfile")
rootfilename = rootfilenodelist[0].getAttribute("full-path")
contentdom = parseString(epub.read(rootfilename))
#firstmetadom = contentdom.getElementsByTagName("metadata")[0]
## Save the path to the .opf file--hrefs inside it are relative to it.
relpath = get_path_part(rootfilename)
# spin through the manifest--only place there are item tags.
for item in contentdom.getElementsByTagName("item"):
# First, count the 'chapter' files. FFDL uses file0000.xhtml,
# but can also update epubs downloaded from Twisting the
# Hellmouth, which uses chapter0.html.
#print("---- item:%s"%item)
if( item.getAttribute("media-type") == "application/xhtml+xml" ):
filehref=relpath+item.getAttribute("href")
soup = bs.BeautifulSoup(epub.read(filehref).decode("utf-8"))
for link in soup.findAll('a',href=re.compile(r'^http.*')):
ahref=link['href']
#print("href:(%s)"%ahref)
# hack for bad ficsaver ffnet URLs.
m = re.match(r"^http://www.fanfiction.net/s(?P<id>\d+)//$",ahref)
if m != None:
ahref="http://www.fanfiction.net/s/%s/1/"%m.group('id')
if _is_good_url == None or _is_good_url(ahref):
return ahref
return None
+1
View File
@@ -63,6 +63,7 @@ class UnknownSite(Exception):
def __init__(self,url,supported_sites_list):
self.url=url
self.supported_sites_list=supported_sites_list
self.supported_sites_list.sort()
def __str__(self):
return "Unknown Site(%s). Supported sites: (%s)" % (self.url, ", ".join(self.supported_sites_list))
+6 -5
View File
@@ -103,9 +103,10 @@ def onlywhite(line):
return c is ' '
return line
def optwrap(text):
def optwrap(text,wrap_width=BODY_WIDTH):
"""Wrap all paragraphs in the provided text."""
if not BODY_WIDTH:
if not wrap_width:
return text
assert wrap, "Requires Python 2.3."
@@ -114,7 +115,7 @@ def optwrap(text):
for para in text.split("\n"):
if len(para) > 0:
if para[0] is not ' ' and para[0] is not '-' and para[0] is not '*':
for line in wrap(para, BODY_WIDTH):
for line in wrap(para, wrap_width):
result += line + "\n"
result += "\n"
newlines = 2
@@ -423,8 +424,8 @@ def html2text_file(html, out=wrapwrite, baseurl=''):
h.feed("")
return h.close()
def html2text(html, baseurl=''):
return optwrap(html2text_file(html, None, baseurl))
def html2text(html, baseurl='', wrap_width=BODY_WIDTH):
return optwrap(html2text_file(html, None, baseurl),wrap_width)
if __name__ == "__main__":
baseurl = ''
+15 -4
View File
@@ -19,12 +19,21 @@ import re
def _unirepl(match):
"Return the unicode string for a decimal number"
if match.group(1)=='x':
if match.group(1).startswith('x'):
radix=16
s = match.group(1)[1:]
else:
radix=10
value = int(match.group(2), radix)
return "%s%s"%(unichr(value),match.group(3))
s = match.group(1)
try:
value = int(s, radix)
retval = "%s%s"%(unichr(value),match.group(2))
except:
# This way, at least if there's more of entities out there
# that fail, it doesn't blow the entire download.
print "Numeric entity translation failed, skipping: &#x%s%s"%(match.group(1),match.group(2))
retval = ""
return retval
def _replaceNumberEntities(data):
# The same brokenish entity parsing in SGMLParser that inserts ';'
@@ -32,7 +41,9 @@ def _replaceNumberEntities(data):
# entities, including part of the next word if it's a-z.
# "Don't&#8212ever&#8212do&#8212that&#8212again," becomes
# "Don't&#8212e;ver&#8212d;o&#8212;that&#8212a;gain,"
p = re.compile(r'&#(x?)([0-9a-fA-F]{,4})([0-9a-fA-F]*);')
# Also need to allow for 5 digit decimal entities &#27861;
# Last expression didn't allow for 2 digit hex correctly: &#xE9;
p = re.compile(r'&#(x[0-9a-fA-F]{,4}|[0-9]{,5})([0-9a-fA-F]*?);')
return p.sub(_unirepl, data)
def _replaceNotEntities(data):
+15 -7
View File
@@ -197,7 +197,9 @@ class Story:
self.imgurls = []
self.imgtuples = []
self.listables = {} # some items (extratags, category, warnings & genres) are also kept as lists.
self.cover=None
self.cover=None # *href* of new cover image--need to create html.
self.oldcover=None # (oldcoverhtmlhref,oldcoverhtmltype,oldcoverhtmldata,oldcoverimghref,oldcoverimgtype,oldcoverimgdata)
self.calibrebookmark=None # cheesy way to carry calibre bookmark file forward across update.
def setMetadata(self, key, value):
## still keeps &lt; &lt; and &amp;
@@ -218,7 +220,7 @@ class Story:
value = re.sub(p,v,value)
return value
def getMetadata(self, key, removeallentities=False):
def getMetadata(self, key, removeallentities=False, doreplacements=True):
value = None
if self.getLists().has_key(key):
value = ', '.join(self.getList(key))
@@ -232,24 +234,30 @@ class Story:
if key == "datePublished" or key == "dateUpdated":
value = value.strftime("%Y-%m-%d")
value=self.doReplacments(value)
if doreplacements:
value=self.doReplacments(value)
if removeallentities and value != None:
return removeAllEntities(value)
else:
return value
def getAllMetadata(self, removeallentities=False):
def getAllMetadata(self, removeallentities=False, doreplacements=True):
'''
All single value *and* list value metadata as strings.
'''
allmetadata = {}
for k in self.metadata.keys():
allmetadata[k] = self.getMetadata(k, removeallentities)
allmetadata[k] = self.getMetadata(k, removeallentities, doreplacements)
for l in self.listables.keys():
allmetadata[l] = self.getMetadata(l, removeallentities)
allmetadata[l] = self.getMetadata(l, removeallentities, doreplacements)
return allmetadata
# just for less clutter in adapters.
def extendList(self,listname,l):
for v in l:
self.addToList(listname,v)
def addToList(self,listname,value):
if value==None:
return
+1 -5
View File
@@ -38,11 +38,7 @@ class BaseStoryWriter(Configurable):
def __init__(self, config, adapter):
Configurable.__init__(self, config)
self.setSectionOrder(adapter.getSiteDomain(),self.getFormatName())
# self.addConfigSection(adapter.getSiteDomain())
# self.addConfigSection(self.getFormatName())
# self.addConfigSection(adapter.getSiteDomain()+":"+self.getFormatName())
# self.addConfigSection("overrides")
self.setSectionOrder(adapter.getConfigSection(),self.getFormatName())
self.adapter = adapter
self.story = adapter.getStoryMetadataOnly() # only cache the metadata initially.
+36 -5
View File
@@ -262,6 +262,37 @@ ${value}<br />
items.append(("ncx","toc.ncx","application/x-dtbncx+xml",None)) ## we'll generate the toc.ncx file,
## but it needs to be in the items manifest.
guide = None
coverIO = None
imgid = "image0000"
if not self.story.cover and self.story.oldcover:
print("writer_epub: no new cover, has old cover, write image.")
(oldcoverhtmlhref,
oldcoverhtmltype,
oldcoverhtmldata,
oldcoverimghref,
oldcoverimgtype,
oldcoverimgdata) = self.story.oldcover
outputepub.writestr(oldcoverhtmlhref,oldcoverhtmldata)
outputepub.writestr(oldcoverimghref,oldcoverimgdata)
imgid = "image0"
items.append((imgid,
oldcoverimghref,
oldcoverimgtype,
None))
items.append(("cover",oldcoverhtmlhref,oldcoverhtmltype,None))
itemrefs.append("cover")
metadata.appendChild(newTag(contentdom,"meta",{"content":"image0",
"name":"cover"}))
guide = newTag(contentdom,"guide")
guide.appendChild(newTag(contentdom,"reference",attrs={"type":"cover",
"title":"Cover",
"href":oldcoverhtmlhref}))
if self.getConfig('include_images'):
imgcount=0
for imgmap in self.story.getImgUrls():
@@ -276,9 +307,6 @@ ${value}<br />
items.append(("style","OEBPS/stylesheet.css","text/css",None))
guide = None
coverIO = None
if self.story.cover:
# Note that the id of the cover xhmtl *must* be 'cover'
# for it to work on Nook.
@@ -347,8 +375,8 @@ div { margin: 0pt; padding: 0pt; }
contentxml = contentdom.toxml(encoding='utf-8')
# tweak for brain damaged Nook STR. Nook insists on name before content.
contentxml = contentxml.replace('<meta content="image0000" name="cover"/>',
'<meta name="cover" content="image0000"/>')
contentxml = contentxml.replace('<meta content="%s" name="cover"/>'%imgid,
'<meta name="cover" content="%s"/>'%imgid)
outputepub.writestr("content.opf",contentxml)
contentdom.unlink()
@@ -458,6 +486,9 @@ div { margin: 0pt; padding: 0pt; }
outputepub.writestr("OEBPS/file%04d.xhtml"%(index+1),fullhtml.encode('utf-8'))
del fullhtml
if self.story.calibrebookmark:
outputepub.writestr("META-INF/calibre_bookmarks.txt",self.story.calibrebookmark)
# declares all the files created by Windows. otherwise, when
# it runs in appengine, windows unzips the files as 000 perms.
for zf in outputepub.filelist:
+13 -3
View File
@@ -21,7 +21,7 @@ from textwrap import wrap
from base_writer import *
from ..html2text import html2text, BODY_WIDTH
from ..html2text import html2text
## In BaseStoryWriter, we define _write to encode <unicode> objects
## back into <string> for true output. But txt needs to write the
@@ -106,6 +106,12 @@ End file.
def writeStoryImpl(self, out):
self.wrap_width = self.getConfig('wrap_width')
if self.wrap_width == '' or self.wrap_width == '0':
self.wrap_width = None
else:
self.wrap_width = int(self.wrap_width)
wrapout = KludgeStringIO()
wrapout.write(self.TEXT_FILE_START.substitute(self.story.metadata))
@@ -131,15 +137,19 @@ End file.
if html:
logging.debug('Writing chapter text for: %s' % title)
self._write(out,self.lineends(self.wraplines(removeAllEntities(self.TEXT_CHAPTER_START.substitute({'chapter':title, 'index':index+1})))))
self._write(out,self.lineends(html2text(html)))
self._write(out,self.lineends(html2text(html,wrap_width=self.wrap_width)))
self._write(out,self.lineends(self.wraplines(self.TEXT_FILE_END.substitute(self.story.metadata))))
def wraplines(self, text):
if not self.wrap_width:
return text
result=''
for para in text.split("\n"):
first=True
for line in wrap(para, BODY_WIDTH):
for line in wrap(para, self.wrap_width):
if first:
first=False
else:
+24
View File
@@ -13,8 +13,23 @@
# limitations under the License.
#
import pickle, copy
from google.appengine.ext import db
class ObjectProperty(db.Property):
data_type = db.Blob
def get_value_for_datastore(self, model_instance):
value = self.__get__(model_instance, model_instance.__class__)
pickled_val = pickle.dumps(value,protocol=pickle.HIGHEST_PROTOCOL)
if value is not None: return db.Blob(pickled_val)
def make_value_from_datastore(self, value):
if value is not None: return pickle.loads(value)
def default_value(self):
return copy.copy(self.default)
class DownloadMeta(db.Model):
user = db.UserProperty()
url = db.StringProperty()
@@ -37,3 +52,12 @@ class DownloadData(db.Model):
class UserConfig(db.Model):
user = db.UserProperty()
config = db.BlobProperty()
class SavedMeta(db.Model):
url = db.StringProperty()
title = db.StringProperty()
author = db.StringProperty()
date = db.DateTimeProperty(auto_now_add=True)
count = db.IntegerProperty()
meta = ObjectProperty()
+102 -12
View File
@@ -54,19 +54,27 @@
much easier. </p>
</div>
<!-- put announcements here, h3 is a good title size. -->
<h3>New Site Added</h3>
<h3>fanfiction.net fixed</h3>
<p>
Support for ksarchive.com has been added. Thanks for Jade AislinSam implementing this.
I hope. I'm parsing it a different way now that I hope will work in all cases. Story text should be fine, but keep an eye on the metadata.
</p>
<h3>New Sites</h3>
<p>
New sites www.dokuga.com, www.ik-eternal.net added. Thanks, Ida.
</p>
<h3>New Option</h3>
<p>
New configuration option under [txt], wrap_width. Use to control or disable word wrap in text mode.
</p>
<p>
Questions? Check out our new
<a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderFAQs">FAQs</a>. Thanks to Wyndham for writing these.
Questions? Check out our
<a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderFAQs">FAQs</a>.
</p>
<p>
If you have any problems with this application, please
report them in
the <a href="http://groups.google.com/group/fanfic-downloader">FanFictionDownLoader Google Group</a>. The
<a href="http://4-4-3.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
<a href="http://4-4-12.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
</p>
<div id='error'>
{{ error_message }}
@@ -96,6 +104,9 @@
<p>
Or see your personal list of <a href="/recent">previously downloaded fanfics</a>.
</p>
<p>
See a list of downloaded fanfics by all users by <a href="/allrecent">most popular</a> or <a href="/allrecent?bydate=1">most recent</a>.
</p>
</div>
</form>
{% else %}
@@ -248,10 +259,6 @@
<br /><a href="http://ficbook.net/readfic/93626">http://ficbook.net/readfic/93626</a>.
<br /><a href="http://ficbook.net/readfic/93626/246417#part_content">http://ficbook.net/readfic/93626/246417#part_content</a>.
</dd>
<dt>gayauthors.org</dt>
<dd>
Removed following complaints by the site administration.
</dd>
<dt>fanfiction.mugglenet.com</dt>
<dd>
Use the URL of the story's chapter list, such as
@@ -287,18 +294,101 @@
Use the URL of the story's chapter list, such as
<br /><a href="http://ksarchive.com/viewstory.php?sid=1124">http://ksarchive.com/viewstory.php?sid=1124</a>.
</dd>
<dt>archive.skyehawke.com</dt>
<dd>
Use the URL of the story's summary, such as
<br /><a href="http://archive.skyehawke.com/story.php?no=17466">http://archive.skyehawke.com/story.php?no=17466</a>.
</dd>
<dt>www.libraryofmoria.com</dt>
<dd>
Use the URL of the story's summary, such as
<br /><a href="http://www.libraryofmoria.com/a/viewstory.php?sid=434">http://www.libraryofmoria.com/a/viewstory.php?sid=434</a>.
</dd>
<dt>www.wraithbait.com</dt>
<dd>
Use the URL of the story's summary, such as
<br /><a href="http://www.wraithbait.com/viewstory.php?sid=14305">http://www.wraithbait.com/viewstory.php?sid=14305</a>.
</dd>
<dt>www.squidge.org/peja (WWOMB)</dt>
<dd>
Use the URL of the story's summary, such as
<br /><a href="http://www.squidge.org/peja/cgi-bin/viewstory.php?sid=1234">http://www.squidge.org/peja/cgi-bin/viewstory.php?sid=1234</a>.<br />
This is <i>only</i> for squidge.org/peja, not other parts of squidge.org.
</dd>
<dt>www.checkmated.com</dt>
<dd>
Use the URL of the story's first chapter, such as
<br /><a href="http://www.checkmated.com/story.php?story=10898">http://www.checkmated.com/story.php?story=10898</a>.
</dd>
<dt>ashwinder.sycophanthex.com</dt>
<dd>
Use the URL of the story's chapter list, such as
<br /><a href="http://ashwinder.sycophanthex.com/viewstory.php?sid=1234">http://ashwinder.sycophanthex.com/viewstory.php?sid=1234</a>
</dd>
<dt>chaos.sycophanthex.com</dt>
<dd>
Use the URL of the story's chapter list, such as
<br /><a href="http://chaos.sycophanthex.com/viewstory.php?sid=1234">http://chaos.sycophanthex.com/viewstory.php?sid=1234</a>
</dd>
<dt>erosnsappho.sycophanthex.com</dt>
<dd>
Use the URL of the story's chapter list, such as
<br /><a href="http://erosnsappho.sycophanthex.com/viewstory.php?sid=1234">http://erosnsappho.sycophanthex.com/viewstory.php?sid=1234</a>
</dd>
<dt>lumos.sycophanthex.com</dt>
<dd>
Use the URL of the story's chapter list, such as
<br /><a href="http://lumos.sycophanthex.com/viewstory.php?sid=1234">http://lumos.sycophanthex.com/viewstory.php?sid=1234</a>
</dd>
<dt>occlumency.sycophanthex.com</dt>
<dd>
Use the URL of the story's chapter list, such as
<br /><a href="http://occlumency.sycophanthex.com/viewstory.php?sid=1234">http://erosnsappho.sycophanthex.com/viewstory.php?sid=1234</a>
</dd>
<dt>dramione.org</dt>
<dd>
Use the URL of the story's chapter list, such as
<br /><a href="http://dramione.org/viewstory.php?sid=1234">http://dramione.org/viewstory.php?sid=1234</a>
</dd>
<dt>www.phoenixsong.net</dt>
<dd>
Use the URL of any story chapter, such as
<br /><a href="http://www.phoenixsong.net/fanfiction/story/1234/">http://www.phoenixsong.net/fanfiction/story/1234/</a>
</dd>
<dt>www.walkingtheplank.org</dt>
<dd>
Use the URL of the story's first chapter, such as
<br /><a href="http://www.walkingtheplank.org/archive/viewstory.php?sid=1234">http://www.walkingtheplank.org/archive/viewstory.php?sid=1234</a>
</dd>
<dt>thehexfiles.net</dt>
<dd>
Use the URL of the story's chapter list, such as
<br /><a href="http://thehexfiles.net/viewstory.php?sid=1234">http://thehexfiles.net/viewstory.php?sid=1234</a>
</dd>
<dt>www.dokuga.com</dt>
<dd>
Use the URL of any story chapter, such as
<br /><a href="http://www.dokuga.com/fanfiction/story/1234/1">http://www.dokuga.com/fanfiction/story/1234/1</a> or
<br /><a href="http://www.dokuga.com/spark/story/1234/1">http://www.dokuga.com/spark/story/1234/1</a>
</dd>
<dt>www.ik-eternal.net</dt>
<dd>
Use the URL of the story's chapter list, such as
<br /><a href="http://www.ik-eternal.net/viewstory.php?sid=1234">http://www.ik-eternal.net/viewstory.php?sid=1234</a>
</dd>
</dl>
<p>
A few additional things to know, which will make your life substantially easier:
</p>
<ol>
<li>
First thing to know: I do not use your Google login and password. In fact, all I know about it is your ID &ndash; password
First thing to know: We do not use your Google login and password. In fact, all we know about it is your ID &ndash; password
is being verified by Google and is absolutely, totally unknown to anyone but you.
</li>
<li>
Small <a href="http://www.sigizmund.com/reading-fanfiction-off-line-in-stanza-and-oth">post written by me</a>
Small <a href="http://www.sigizmund.com/reading-fanfiction-off-line-in-stanza-and-oth">post written by Roman</a>
&mdash; how to read fiction in Stanza or any other ebook reader.
</li>
<li>
@@ -314,7 +404,7 @@
</li>
<li>
If you think that something that should work in fact doesn't, post a message to
our <a href="http://groups.google.com/group/fanfic-downloader">Google Group</a>. I also encourage you to join it so
our <a href="http://groups.google.com/group/fanfic-downloader">Google Group</a>. we also encourage you to join it so
you will find out about latest updates and fixes as soon as possible
</li>
</ol>
+3 -8
View File
@@ -1,6 +1,6 @@
indexes:
# AUTOGENERATED
# notAUTOGENERATED
# This index.yaml is automatically updated whenever the dev_appserver
# detects that a new type of query is run. If you want to manage the
@@ -21,13 +21,8 @@ indexes:
- name: date
direction: desc
- kind: DownloadedFanfic
- kind: SavedMeta
properties:
- name: cleared
- name: date
- kind: DownloadedFanfic
properties:
- name: user
- name: count
- name: date
direction: desc
+52 -1
View File
@@ -303,6 +303,39 @@ class RecentFilesServer(webapp2.RequestHandler):
path = os.path.join(os.path.dirname(__file__), 'recent.html')
self.response.out.write(template.render(path, template_values))
class AllRecentFilesServer(webapp2.RequestHandler):
def get(self):
user = users.get_current_user()
if not user:
self.redirect(users.create_login_url(self.request.uri))
return
q = SavedMeta.all()
if self.request.get('bydate'):
q.order('-date')
else:
q.order('-count')
fics = q.fetch(200)
logging.info("Recent fetched %d downloads for user %s."%(len(fics),user.nickname()))
sendslugs = []
for fic in fics:
ficslug = FicSlug(fic)
sendslugs.append(ficslug)
template_values = dict(fics = sendslugs, nickname = user.nickname())
path = os.path.join(os.path.dirname(__file__), 'allrecent.html')
self.response.out.write(template.render(path, template_values))
class FicSlug():
def __init__(self,savedmeta):
self.url = savedmeta.url
self.count = savedmeta.count
for k, v in savedmeta.meta.iteritems():
setattr(self,k,v)
class FanfictionDownloader(UserConfigServer):
def get(self):
self.post()
@@ -385,7 +418,7 @@ class FanfictionDownloader(UserConfigServer):
template_values = dict(nickname = user.nickname(),
url = url,
format = format,
site = adapter.getSiteDomain(),
site = adapter.getConfigSection(),
fic = download,
is_login=is_login,
)
@@ -464,6 +497,8 @@ class FanfictionDownloaderTask(UserConfigServer):
download.url = adapter.getStory().getMetadata('storyUrl')
download.put()
allmeta = adapter.getStory().getAllMetadata(removeallentities=True,doreplacements=False)
outbuffer = StringIO()
writer.writeStory(outbuffer)
data = outbuffer.getvalue()
@@ -495,6 +530,21 @@ class FanfictionDownloaderTask(UserConfigServer):
download.completed=True
download.put()
smetal = SavedMeta.all().filter('url =', allmeta['storyUrl'] ).fetch(1)
if smetal and smetal[0]:
smeta = smetal[0]
smeta.count += 1
else:
smeta=SavedMeta()
smeta.count = 1
smeta.url = allmeta['storyUrl']
smeta.title = allmeta['title']
smeta.author = allmeta['author']
smeta.meta = allmeta
smeta.date = datetime.datetime.now()
smeta.put()
logging.info("Download finished OK")
del data
@@ -563,6 +613,7 @@ app = webapp2.WSGIApplication([('/', MainHandler),
('/fdown', FanfictionDownloader),
(r'/file.*', FileServer),
('/status', FileStatusServer),
('/allrecent', AllRecentFilesServer),
('/recent', RecentFilesServer),
('/editconfig', EditConfigServer),
('/clearrecent', ClearRecentServer),
+138 -7
View File
@@ -127,6 +127,20 @@ extratags: FanFiction
## doesn't work on some devices either.)
#replace_hr: false
## If you have the Generate Cover plugin installed, you can use the
## generate_cover_settings parameter to intelligently decide which GC
## setting to run. There are three parts 1) a template of which
## metadata part(s) to look at, 2) a regular expression to match the
## template, and 3) the name of the GC setting to use, which must
## match exactly. Use this parameter in [defaults], or by site eg,
## [www.ficwad.com]
## Make sure to keep at least one space at the start of each line and
## to escape % to %%, if used.
## template => regexp to match => GC Setting to use.
#generate_cover_settings:
# ${category} => Buffy:? [tT]he Vampire Slayer => BuffyCover
# ${category} => Star Trek => StarTrekCover
## Each output format has a section that overrides [defaults]
[html]
@@ -158,6 +172,9 @@ output_css:
## Add URLs since there aren't links.
titlepage_entries: series,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,storyUrl, authorUrl, description
## Width to word wrap text output. 0 indicates no wrapping.
wrap_width: 78
## use \r\n for line endings, the windows convention. text output only.
windows_eol: true
@@ -278,6 +295,16 @@ extratags: FanFiction,Testing,Text
[test1.com:html]
extratags: FanFiction,Testing,HTML
[archive.skyehawke.com]
[ashwinder.sycophanthex.com]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
## commandline version, this should go in your personal.ini, not
## defaults.ini.
#username:YourName
#password:yourpassword
[castlefans.org]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
@@ -291,6 +318,39 @@ extratags: FanFiction,Testing,HTML
## personal.ini, not defaults.ini.
#is_adult:true
[chaos.sycophanthex.com]
## 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
## some sites include images that we don't ever want becoming the
## cover image. This lets you exclude them.
cover_exclusion_regexp:/images/.*?ribbon.gif
[dramione.org]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
## commandline version, this should go in your personal.ini, not
## defaults.ini.
#username:YourName
#password:yourpassword
## Some sites also require the user to confirm they are adult for
## adult content. In commandline version, this should go in your
## personal.ini, not defaults.ini.
#is_adult:true
[erosnsappho.sycophanthex.com]
## 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
## some sites include images that we don't ever want becoming the
## cover image. This lets you exclude them.
cover_exclusion_regexp:/images/.*?ribbon.gif
[fanfiction.mugglenet.com]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
@@ -318,16 +378,27 @@ extratags: FanFiction,Testing,HTML
#username:YourName
#password:yourpassword
[lumos.sycophanthex.com]
## 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
[nfacommunity.com]
## Some sites do not require a login, but do require the user to
## confirm they are adult for adult content. In commandline version,
## this should go in your personal.ini, not defaults.ini.
#is_adult:true
## Some sites also require the user to confirm they are adult for
## adult content. In commandline version, this should go in your
## personal.ini, not defaults.ini.
#is_adult:true
[occlumency.sycophanthex.com]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
## commandline version, this should go in your personal.ini, not
## defaults.ini.
#username:YourName
#password:yourpassword
[thehexfiles.net]
[thequidditchpitch.org]
## Some sites require login (or login for some rated stories) The
@@ -349,11 +420,21 @@ extratags: FanFiction,Testing,HTML
#is_adult:true
[www.archiveofourown.org]
## Some sites also require the user to confirm they are adult for
## adult content. In commandline version, this should go in your
## personal.ini, not defaults.ini.
## 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
[www.checkmated.com]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
## commandline version, this should go in your personal.ini, not
## defaults.ini.
#username:YourName
#password:yourpassword
[www.dokuga.com]
[www.fanfiction.net]
[www.ficbook.net]
@@ -399,6 +480,25 @@ extratags:
## this should go in your personal.ini, not defaults.ini.
#is_adult:true
[www.ik-eternal.net]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
## commandline version, this should go in your personal.ini, not
## defaults.ini.
#username:YourName
#password:yourpassword
## Some sites also require the user to confirm they are adult for
## adult content. In commandline version, this should go in your
## personal.ini, not defaults.ini.
#is_adult:true
[www.libraryofmoria.com]
## 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
[www.mediaminer.org]
[www.midnightwhispers.ca]
@@ -411,10 +511,29 @@ extratags:
## cover image. This lets you exclude them.
cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
[www.phoenixsong.net]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
## commandline version, this should go in your personal.ini, not
## defaults.ini.
#username:YourName
#password:yourpassword
[www.potionsandsnitches.net]
[www.siye.co.uk]
[www.squidge.org/peja]
# www.squidge.org/peja calls it Fandom <shrug>
category_label:Fandom
# Remove numWords -- www.squidge.org/peja word counts are inaccurate
titlepage_entries: series,category,genre,language,characters,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,description
[www.squidge.org/peja:txt]
## Add URLs since there aren't links.
# Remove numWords -- www.squidge.org/peja word counts are inaccurate
titlepage_entries: series,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,storyUrl, authorUrl, description
[www.thewriterscoffeeshop.com]
## Some sites require login (or login for some rated stories) The
## program can prompt you, or you can save it in config. In
@@ -466,8 +585,20 @@ collect_series: false
## twiwrite.net (ab)uses series as personal reading lists.
collect_series: false
[www.walkingtheplank.org]
## Some sites do not require a login, but do require the user to
## confirm they are adult for adult content. In commandline version,
## this should go in your personal.ini, not defaults.ini.
#is_adult:true
[www.whofic.com]
[www.wraithbait.com]
## 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