Fix for siye.co.uk stories with HTML in the title, bump versions.

meta section, fix highbyte chars in description.

app.yaml

@@ -1,6 +1,6 @@
 # ffd-retief-hrd fanfictiondownloader
 application: fanfictiondownloader
-version: 4-4-53
+version: 4-4-61
 runtime: python27
 api_version: 1
 threadsafe: true

calibre-plugin/__init__.py

@@ -1,11 +1,10 @@
 #!/usr/bin/env python
-# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
 # -*- coding: utf-8 -*-
 from __future__ import (unicode_literals, division, absolute_import,
                         print_function)
 
 __license__   = 'GPL v3'
-__copyright__ = '2011, Jim Miller'
+__copyright__ = '2013, Jim Miller'
 __docformat__ = 'restructuredtext en'
 
 # The class that all Interface Action plugin wrappers must inherit from
@@ -27,7 +26,7 @@ class FanFictionDownLoaderBase(InterfaceActionBase):
     description         = 'UI plugin to download FanFiction stories from various sites.'
     supported_platforms = ['windows', 'osx', 'linux']
     author              = 'Jim Miller'
-    version             = (1, 7, 20)
+    version             = (1, 7, 28)
     minimum_calibre_version = (0, 8, 57)
 
     #: This field defines the GUI plugin class that contains all the code

calibre-plugin/common_utils.py

@@ -239,8 +239,8 @@ class SizePersistedDialog(QDialog):
             self.restoreGeometry(self.geom)
 
     def dialog_closing(self, result):
-        geom = bytearray(self.saveGeometry())
-        gprefs[self.unique_pref_name] = geom
+        self.geom = bytearray(self.saveGeometry())
+        gprefs[self.unique_pref_name] = self.geom
 
 
 class ReadOnlyTableWidgetItem(QTableWidgetItem):

calibre-plugin/config.py

@@ -15,8 +15,8 @@ from PyQt4.Qt import (QDialog, QWidget, QVBoxLayout, QHBoxLayout, QLabel,
                       QCheckBox, QPushButton, QTabWidget, QVariant, QScrollArea,
                       QDialogButtonBox )
 
-from calibre.utils.config import JSONConfig
 from calibre.gui2.ui import get_gui
+from calibre.gui2 import dynamic, info_dialog
 
 from calibre_plugins.fanfictiondownloader_plugin.prefs import prefs, PREFS_NAMESPACE
 from calibre_plugins.fanfictiondownloader_plugin.dialogs \

calibre-plugin/dialogs.py

@@ -53,13 +53,14 @@ class RejectUrlEntry:
     matchpat=re.compile(r"^(?P<url>[^,]+)(,(?P<fullnote>(((?P<title>.+) by (?P<auth>.+?)( - (?P<note>.+))?)|.*)))?$")
     
     def __init__(self,url_or_line,note=None,title=None,auth=None,
-                 addreasontext=None,fromline=False):
-        
+                 addreasontext=None,fromline=False,book_id=None):
+
         self.url=url_or_line
         self.note=note
         self.title=title
         self.auth=auth
         self.valid=False
+        self.book_id=book_id
 
         if fromline:
             mc = re.match(self.matchpat,url_or_line)
@@ -258,8 +259,8 @@ class AddNewDialog(SizePersistedDialog):
 
     # invoke the 
     def ok_clicked(self):
+        self.dialog_closing(None) # save persistent size.
         self.hide()
-        print("ok_clicked called")
         self.go_signal.emit( self.get_ffdl_options(),
                              self.get_urlstext(),
                              self.merge,
@@ -828,7 +829,9 @@ class RejectListTableWidget(QTableWidget):
 
     def populate_table_row(self, row, rej):
 
-        self.setItem(row, 0, ReadOnlyTableWidgetItem(rej.url))
+        url_cell = ReadOnlyTableWidgetItem(rej.url)
+        url_cell.setData(Qt.UserRole, QVariant(rej.book_id))
+        self.setItem(row, 0, url_cell)
         self.setItem(row, 1, ReadOnlyTableWidgetItem(rej.title))
         self.setItem(row, 2, ReadOnlyTableWidgetItem(rej.auth))
         
@@ -950,10 +953,19 @@ class RejectListDialog(SizePersistedDialog):
         rejectrows = []
         for row in range(self.rejects_table.rowCount()):
             url = unicode(self.rejects_table.item(row, 0).text()).strip()
+            book_id = self.rejects_table.item(row, 0).data(Qt.UserRole).toPyObject()
             title = unicode(self.rejects_table.item(row, 1).text()).strip()
             auth = unicode(self.rejects_table.item(row, 2).text()).strip()
             note = unicode(self.rejects_table.cellWidget(row, 3).currentText()).strip()
-            rejectrows.append(RejectUrlEntry(url,note,title,auth,self.get_reason_text()))
+            rejectrows.append(RejectUrlEntry(url,note,title,auth,self.get_reason_text(),book_id=book_id))
+        return rejectrows
+
+    def get_reject_list_ids(self):
+        rejectrows = []
+        for row in range(self.rejects_table.rowCount()):
+            book_id = self.rejects_table.item(row, 0).data(Qt.UserRole).toPyObject()
+            if book_id:
+                rejectrows.append(book_id)
         return rejectrows
 
     def get_reason_text(self):

calibre-plugin/ffdl_plugin.py

@@ -408,12 +408,12 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             
     def reject_list_urls_finish(self, book_list):
 
-        # construct reject list of tuples:
-        # (calibre_id, url, "title, authors", old reject note).
+        # construct reject list of objects
         reject_list = [ RejectUrlEntry(x['url'],
                                        x['oldrejnote'],
                                        x['title'],
-                                       ', '.join(x['author']))
+                                       ', '.join(x['author']),
+                                       book_id=x['calibre_id'])
                         for x in book_list if x['good'] ]
         if reject_list:
             d = RejectListDialog(self.gui,reject_list,
@@ -426,7 +426,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             rejecturllist.add(d.get_reject_list())
 
             if d.get_deletebooks():
-                self.gui.iactions['Remove Books'].delete_books()
+                self.gui.iactions['Remove Books'].do_library_delete(d.get_reject_list_ids())
             
         else:
             message="<p>Rejecting FFDL URLs: None of the books selected have FanFiction URLs.</p><p>Proceed to Remove?</p>"
@@ -661,6 +661,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
 
         url = book['url']
         print("url:%s"%url)
+        mi = None
 
         if not merge: # skip reject list when merging.
             if rejecturllist.check(url):
@@ -845,6 +846,42 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                     book['icon'] = 'edit-redo.png'
                     book['status'] = 'Update'
     
+                if book_id and mi: # book_id and mi only set if matched by title/author.
+                    liburl = self.get_story_url(db,book_id)
+                    if book['url'] != liburl:
+                        if collision in (OVERWRITE,OVERWRITEALWAYS):
+                            updat="overwrit"
+                        else:
+                            updat="updat"
+                        if not question_dialog(self.gui, 'Change Story URL?',
+                                               '<h3>Change Story URL?</h3>'+
+                                               '<p><b>%s</b> by <b>%s</b> is already in your library with a different source URL:</p>'%
+                                                   (mi.title,', '.join(mi.author))+
+                                               '<p>In library: <a href="%(liburl)s">%(liburl)s</a></p><p>New URL: <a href="%(newurl)s">%(newurl)s</a></p>'%
+                                                   {'liburl':liburl,'newurl':book['url']}+
+                                               "<p>Click '<b>Yes</b>' to %se book with new URL.</p>"%updat+
+                                               "<p>Click '<b>No</b>' to skip %sing this book.</p>"%updat,
+                                               show_copy_button=False):
+                            if question_dialog(self.gui, 'Download as New Book?',
+                                               '<h3>Download as New Book?</h3>'+
+                                               '<p><b>%s</b> by <b>%s</b> is already in your library with a different source URL.</p>'%
+                                               (mi.title,', '.join(mi.author))+
+                                               '<p>You chose not to update the existing book.  Do you want to add a new book for this URL?</p>'+
+                                               '<p>New URL: <a href="%(newurl)s">%(newurl)s</a></p>'%
+                                               {'newurl':book['url']}+
+                                               "<p>Click '<b>Yes</b>' to a new book with new URL.</p>"+
+                                               "<p>Click '<b>No</b>' to skip URL.</p>",
+                                               show_copy_button=False):
+                                book_id = None
+                                mi = None
+                                book['calibre_id'] = None
+                            else:
+                                book['comment'] = "Update declined by user due to differing story URL(%s)"%liburl
+                                book['good']=False
+                                book['icon']='rotate-right.png'
+                                book['status'] = 'Different URL'
+                                return
+        
             if book_id != None and collision != ADDNEW:
                 if collision in (CALIBREONLY):
                     book['comment'] = 'Metadata collected.'
@@ -889,7 +926,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                     db.copy_format_to(book_id,fileform,tmp,index_is_id=True)
                     print("existing epub tmp:"+tmp.name)
                     book['epub_for_update'] = tmp.name
-    
+
             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:
@@ -1159,7 +1196,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         if 'mergebook' in options:
             existingbook = options['mergebook']
         #print("existingbook:\n%s"%existingbook)
-        mergebook = self.merge_meta_books(existingbook,good_list)
+        mergebook = self.merge_meta_books(existingbook,good_list,options['fileform'])
 
         if 'mergebook' in options:
             mergebook['calibre_id'] = options['mergebook']['calibre_id']
@@ -1281,16 +1318,10 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             existingepub = db.format(book_id,'EPUB',index_is_id=True, as_file=True)
             epubmi = get_metadata(existingepub,'EPUB')
             if epubmi.cover_data[1] is not None:
-                db.set_cover(book_id, epubmi.cover_data[1])
-
-        # set author link if found.  All current adapters have authorUrl, except anonymous on AO3.
-        if 'authorUrl' in book['all_metadata']:
-            authurls = book['all_metadata']['authorUrl'].split(", ")
-            for i, auth in enumerate(book['author']):
-                #print("===Update author url for %s to %s"%(auth,authurls[i]))
-                autid=db.get_author_id(auth)
-                db.set_link_field_for_author(autid, unicode(authurls[i]),
-                                             commit=False, notify=False)
+                try:
+                    db.set_cover(book_id, epubmi.cover_data[1])
+                except:
+                    print("Failed to set_cover, skipping")
 
         # implement 'newonly' flags here by setting to the current
         # value again.
@@ -1369,7 +1400,11 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
 
                     if flag == 'r' or book['added']: # flag 'n' isn't actually needed--*always* set if configured and new book.
                         if coldef['datatype'] in ('int','float'): # for favs, etc--site specific metadata.
-                            val = unicode(book['all_metadata'][meta]).replace(",","")
+                            if 'anthology_meta_list' in book and meta in book['anthology_meta_list']:
+                                # re-split list, strip commas, convert to floats, sum up.
+                                val = sum([ float(x.replace(",","")) for x in book['all_metadata'][meta].split(", ") ])
+                            else:
+                                val = unicode(book['all_metadata'][meta]).replace(",","")
                         else:
                             val = book['all_metadata'][meta]
                         db.set_custom(book_id, val, label=label, commit=False)
@@ -1390,6 +1425,16 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                             
                         db.set_custom(book_id, ", ".join(vallist), label=label, commit=False)
 
+        # set author link if found.  All current adapters have authorUrl, except anonymous on AO3.
+        # Moved down so author's already in the DB.
+        if 'authorUrl' in book['all_metadata']:
+            authurls = book['all_metadata']['authorUrl'].split(", ")
+            for i, auth in enumerate(book['author']):
+                #print("===Update author url for %s to %s"%(auth,authurls[i]))
+                autid=db.get_author_id(auth)
+                db.set_link_field_for_author(autid, unicode(authurls[i]),
+                                             commit=False, notify=False)
+
         db.commit()
 
         if 'Generate Cover' in self.gui.iactions and (book['added'] or not prefs['gcnewonly']):
@@ -1623,7 +1668,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                     # identifiers have :->| in uri.
                     # print("uri from ident uri:%s"%identifiers['uri'].replace('|',':'))
                     return identifiers['uri'].replace('|',':')
-            elif path.lower().endswith('.epub'):
+            elif path and path.lower().endswith('.epub'):
                 existingepub = path
                 
             ## only epub has URL in it--at least where I can easily find it.
@@ -1642,12 +1687,13 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
     def is_good_downloader_url(self,url):
         return adapters.getNormalStoryURL(url)
 
-    def merge_meta_books(self,existingbook,book_list):
+    def merge_meta_books(self,existingbook,book_list,fileform):
         book = self.make_book()
         book['author'] = []
         book['tags'] = []
         book['url'] = ''
         book['all_metadata'] = {}
+        book['anthology_meta_list'] = {}
         book['comment'] = ''
         book['added'] = True
         book['good'] = True
@@ -1714,12 +1760,16 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                         book['all_metadata'][k]=book['all_metadata'][k]+"\n\n"+v
                     else:
                         book['all_metadata'][k]=book['all_metadata'][k]+", "+v
+                        # flag psuedo list element.  Used so numeric
+                        # cust cols can convert back to numbers and
+                        # add.
+                        book['anthology_meta_list'][k]=True
     
         if existingbook:
             book['title'] = deftitle = existingbook['title']
             book['comments'] = existingbook['comments']
         else:
-            book['title'] = deftitle = book_list[0]['title']+" Anthology"
+            book['title'] = deftitle = book_list[0]['title']
             book['comments'] = "Anthology containing:\n" + \
                 "\n".join([ "%s by %s"%(b['title'],', '.join(b['author'])) for b in book_list ])
             # book['all_metadata']['description']
@@ -1727,12 +1777,22 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             # if all same series, use series for name.  But only if all and not previous named
             if len(serieslist) == len(book_list):
                 series = serieslist[0]
-                book['title'] = series+" Anthology"
+                book['title'] = series
                 for sr in serieslist:
                     if series != sr:
                         book['title'] = deftitle;
                         break
             
+            configuration = get_ffdl_config(book['url'],fileform)
+            print("anthology_title_pattern:%s"%configuration.getConfig('anthology_title_pattern'))
+            if configuration.getConfig('anthology_title_pattern'):
+                tmplt = Template(configuration.getConfig('anthology_title_pattern'))
+                book['title'] = tmplt.safe_substitute({'title':book['title']}).encode('utf8')
+            else:
+                # No setting, do fall back default.  Shouldn't happen,
+                # should always have a version in defaults.
+                book['title'] = book['title']+" Anthology"
+        
         book['all_metadata']['title'] = book['title'] # because custom columns are set from all_metadata
         book['all_metadata']['author'] = ", ".join(book['author'])
         book['author_sort']=book['author']
@@ -1741,6 +1801,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                 book['tags'].remove(v)
         book['tags'].append('Anthology')
         book['all_metadata']['anthology'] = "true"
+        
         return book
 
 def split_text_to_urls(urls):

defaults.ini

@@ -1,4 +1,4 @@
-# Copyright 2012 Fanficdownloader team
+# Copyright 2013 Fanficdownloader team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -169,6 +169,8 @@ extratags: FanFiction
 ## *Five* part lines.  Effect only when trailing conditional key=>regexp matches
 ## metakey[,metakey]=>pattern=>replacement[&&conditionalkey=>regexp]
 ## Note that if metakey == conditionalkey the conditional is ignored.
+## You can use \s in the replacement to add explicit spaces.  (The config parser
+## tends to discard trailing spaces.)
 #replace_metadata:
 # genre,category=>Sci-Fi=>SF
 # Puella Magi Madoka Magica.* => Madoka
@@ -189,6 +191,10 @@ extratags: FanFiction
 ## summary.
 keep_summary_html:true
 
+## If set true, any style attributes on tags in the story HTML will be
+## kept.  Useful for keeping extra colors & formatting from original.
+#keep_style_attr: false
+
 ## Don't like the numbers at the start of chapter titles on some
 ## sites?  You can use strip_chapter_numbers to strip them off.  Just
 ## want to make them all look the same?  Strip them off, then add them
@@ -273,7 +279,7 @@ output_css:
 
 [txt]
 ## Add URLs since there aren't links.
-titlepage_entries: series,seriesUrl,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,storyUrl, authorUrl, description
+titlepage_entries: series,seriesUrl,category,genre,language,characters,ships,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
@@ -507,6 +513,15 @@ extraships:Severus Snape/Hermione Granger
 #username:YourName
 #password:yourpassword
 
+[asr3.slashzone.org]
+## Site dedicated to these categories/characters/ships
+extracategories:The Sentinel
+
+## 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
+
 [bloodties-fans.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Blood Ties
@@ -571,6 +586,11 @@ extraships:Spike/Buffy
 #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
+
 [dramione.org]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
@@ -602,7 +622,7 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 ## composite metadata entries.  dramione.org, for example, adds
 ## 'cliches' and then defines as the composite of hermiones,dracos in
 ## include_in_cliches.
-extra_valid_entries:themes,hermiones,dracos,timeline,cliches
+extra_valid_entries:themes,hermiones,dracos,timeline,cliches,read,reviews
 include_in_cliches:hermiones,dracos
 
 ## For another example, you could, by uncommenting this line, include
@@ -702,6 +722,10 @@ extracharacters:Hermione Granger
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+## Extra metadata that this adapter knows about.  See [dramione.org]
+## for examples of how to use them.
+extra_valid_entries:read,reviews
+
 [hlfiction.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:Highlander
@@ -762,6 +786,8 @@ extracategories:West Wing
 ## Site dedicated to these categories/characters/ships
 extracategories:NCIS
 
+[netraptor.org]
+
 [nfacommunity.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:NCIS
@@ -918,6 +944,15 @@ extracategories:Harry Potter
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+[tokra.fandomnet.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Stargate: SG-1
+
+## 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.adastrafanfic.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Star Trek
@@ -1148,6 +1183,11 @@ cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
 ## Site dedicated to these categories/characters/ships
 extracategories:NCIS
 
+[www.nickandgreg.net]
+## Site dedicated to these categories/characters/ships
+extracategories:CSI
+extraships:Nick Stokes/Greg Sanders
+
 [www.phoenixsong.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
@@ -1356,3 +1396,47 @@ extracategories:Stargate: Atlantis
 ## extratags params in all other sections.  Only commandline options
 ## beat overrides.
 #extratags:fanficdownloader
+
+
+[teststory:defaults]
+valid_entries:title,author_list,authorId_list,authorUrl_list,storyUrl,
+ datePublished,dateUpdated,numWords,status,language,series,seriesUrl,
+ rating,category_list,genre_list,warnings_list,characters_list
+
+# {{storyId}} is a special case--it's the only one that works.
+title:Test Story Title {{storyId}}
+author_list:Test Author aa
+authorId_list:1
+authorUrl_list:http://test1.com?authid=1
+storyUrl:http://test1.com?sid={{storyId}}
+datePublished:1975-03-15
+dateUpdated:1975-04-15
+numWords:123,456
+status:In-Progress
+language:English
+
+chaptertitles:Prologue
+
+## Add additional sections with different numbers to get different
+## parameters for different story urls.
+## test1.com?sid=1000
+[teststory:1000]
+# note the leading commas when doing add_to_ with valid_entries and *_list
+add_to_valid_entries:,favs
+title:Testing New Feature {{storyId}}
+author_list:Bob Smith
+authorId_list:45
+authorUrl_list:http://test1.com?authid=45
+datePublished:2013-03-15
+dateUpdated:2013-04-15
+numWords:1456
+favs:56
+series:The Great Test [4]
+seriesUrl:http://test1.com?seriesid=1
+rating:Tweenie
+category_list:Harry Potter,Furbie,Crossover,Puella Magi Madoka Magica/魔法少女まどか★マギカ,Magical Girl Lyrical Nanoha
+genre_list:Fantasy,Comedy,Sci-Fi,Noir
+warnings_list:Swearing,Violence
+characters_list:Bob Smith,George Johnson,Fred Smythe
+
+chaptertitles:Prologue,Chapter 1\, Xenos on Cinnabar,Chapter 2\, Sinmay on Kintikin,3. Chapter 3

downloader.py

@@ -33,16 +33,24 @@ if sys.version_info >= (2, 7):
     rootlogger.addHandler(loghandler)
 
 try:
-    from fanficdownloader import adapters,writers,exceptions
-    from fanficdownloader.configurable import Configuration
-    from fanficdownloader.epubutils import get_dcsource_chaptercount, get_update_data
-    from fanficdownloader.geturls import get_urls_from_page
+    from calibre.constants import numeric_version as calibre_version
+    is_calibre = True
 except:
+    is_calibre = False
+
+# using try/except directly was masking errors during development.
+if is_calibre:
     # running under calibre
     from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader import adapters,writers,exceptions
     from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.configurable import Configuration
     from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.epubutils import get_dcsource_chaptercount, get_update_data
     from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.geturls import get_urls_from_page
+else:
+    from fanficdownloader import adapters,writers,exceptions
+    from fanficdownloader.configurable import Configuration
+    from fanficdownloader.epubutils import get_dcsource_chaptercount, get_update_data
+    from fanficdownloader.geturls import get_urls_from_page
+    
 
 if sys.version_info < (2, 5):
     print "This program requires Python 2.5 or newer."

fanficdownloader/adapters/__init__.py

@@ -71,7 +71,6 @@ import adapter_thehexfilesnet
 import adapter_dokugacom
 import adapter_iketernalnet
 import adapter_onedirectionfanfictioncom
-import adapter_prisonbreakficnet
 import adapter_storiesofardacom
 import adapter_samdeanarchivenu
 import adapter_destinysgatewaycom
@@ -88,7 +87,6 @@ import adapter_pretendercentrecom
 import adapter_darksolaceorg
 import adapter_finestoriescom
 import adapter_hpfanficarchivecom
-import adapter_svufictioncom
 import adapter_twilightarchivescom
 import adapter_wizardtalesnet
 import adapter_nhamagicalworldsus
@@ -103,7 +101,6 @@ import adapter_merlinficdtwinscouk
 import adapter_thehookupzonenet
 import adapter_bloodtiesfancom
 import adapter_indeathnet
-import adapter_jlaunlimitedcom
 import adapter_qafficcom
 import adapter_efpfanficnet
 import adapter_potterficscom
@@ -115,6 +112,10 @@ import adapter_imagineeficcom
 import adapter_buffynfaithnet
 import adapter_psychficcom
 import adapter_hennethannunnet
+import adapter_tokrafandomnetcom
+import adapter_netraptororg
+import adapter_asr3slashzoneorg
+import adapter_nickandgregnet
 
 ## This bit of complexity allows adapters to be added by just adding
 ## importing.  It eliminates the long if/else clauses we used to need

fanficdownloader/adapters/adapter_archiveofourownorg.py

@@ -1,4 +1,4 @@
-# -*- coding: utf-8 -*-
+#  -*- coding: utf-8 -*-
 
 # Copyright 2011 Fanficdownloader team
 #
@@ -292,7 +292,7 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
             a = metasoup.find('dd',{'class':"series"})
             b = a.find('a', href=re.compile(r"/series/\d+"))
             series_name = b.string
-            series_url = 'http://'+self.host+'/fanfic/'+b['href']
+            series_url = 'http://'+self.host+b['href']
             series_index = int(a.text.split(' ')[1])
             self.setSeries(series_name, series_index)
             self.story.setMetadata('seriesUrl',series_url)

fanficdownloader/adapters/adapter_asr3slashzoneorg.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2011 Fanficdownloader team
+# Copyright 2013 Fanficdownloader team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -27,12 +27,10 @@ from .. import exceptions as exceptions
 
 from base_adapter import BaseSiteAdapter,  makeDate
 
-
 def getClass():
-    return JLAUnlimitedComAdapter
+    return Asr3SlashzoneOrgAdapter
 
-
-class JLAUnlimitedComAdapter(BaseSiteAdapter):
+class Asr3SlashzoneOrgAdapter(BaseSiteAdapter):
 
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
@@ -42,36 +40,34 @@ class JLAUnlimitedComAdapter(BaseSiteAdapter):
                                # 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.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])
         logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
-
-        self._setURL('http://' + self.getSiteDomain() + '/eFiction1.1/viewstory.php?sid='+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','jla')
+        self.story.setMetadata('siteabbrev','asr3')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%m/%d/%y"
-
+        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 'www.jlaunlimited.com'
+        return 'asr3.slashzone.org'
 
     def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/eFiction1.1/viewstory.php?sid=1234"
+        return "http://"+self.getSiteDomain()+"/archive/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
-        return re.escape("http://"+self.getSiteDomain()+"/eFiction1.1/viewstory.php?sid=")+r"\d+$"
-
-
-
+        return re.escape("http://"+self.getSiteDomain()+"/archive/viewstory.php?sid=")+r"\d+$"
 
     ## Getting the chapter list and the meta data, plus 'is adult' checking.
     def extractChapterUrlsAndMetadata(self):
@@ -81,7 +77,7 @@ class JLAUnlimitedComAdapter(BaseSiteAdapter):
             # 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=4" # XXX
+            addurl = "&ageconsent=ok&warning=3"
         else:
             addurl=""
 
@@ -98,8 +94,7 @@ class JLAUnlimitedComAdapter(BaseSiteAdapter):
             else:
                 raise e
 
-        # Assume that if there is a url with 'warning=#' in the page then it is a 'check' page
-        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)",data)
+        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&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
@@ -120,141 +115,111 @@ class JLAUnlimitedComAdapter(BaseSiteAdapter):
                         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
+        #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')))
+        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('authorUrl','http://'+self.host+'/archive/'+a['href'])
         self.story.setMetadata('author',a.string)
 
+        # Rating
+        rate = stripHTML(soup.find('div',{'id':'pagetitle'}))
+        rate = rate[rate.rindex('[')+1:rate.rindex(']')]
+        self.story.setMetadata('rating', rate)
+
         # Find the chapters:
-        for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+")):
+        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+'/eFiction1.1/'+chapter['href']+addurl))
+            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 ""
+        metadiv = soup.find('div',{'class':'content'})
+        smalldiv = metadiv.find('div',{'class':'small'})
 
-        # <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
+        categorys = smalldiv.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+        for category in categorys:
+            self.story.addToList('category',category.string)
+        
+        chars = smalldiv.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+        for char in chars:
+            self.story.addToList('characters',char.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))
+        ships = smalldiv.parent.findAll('a',href=re.compile(r'browse\.php\?type=class&type_id=2&classid=1'))
+        for ship in ships:
+            self.story.addToList('ships',ship.string)
 
-            if 'Rated' in label:
-                self.story.setMetadata('rating', value)
+        metatext = stripHTML(smalldiv)
 
-            if 'Word count' in label:
-                self.story.setMetadata('numWords', value)
+        if 'Completed: Yes' in metatext:
+            self.story.setMetadata('status', 'Completed')
+        else:
+            self.story.setMetadata('status', 'In-Progress')
 
-            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)
+        wordstart=metatext.rindex('Word count:')+12
+        words = metatext[wordstart:metatext.index(' ',wordstart)]
+        self.story.setMetadata('numWords', words)
 
-            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)
-
-            ## Not all sites use Genre, but there's no harm to
-            ## leaving it in.  Check to make sure the type_id number
-            ## is correct, though--it's site specific.
-            if 'Genre' in label:
-                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1')) # XXX
-                genrestext = [genre.string for genre in genres]
-                self.genre = ', '.join(genrestext)
-                for genre in genrestext:
-                    self.story.addToList('genre',genre.string)
-
-            ## Not all sites use Warnings, but there's no harm to
-            ## leaving it in.  Check to make sure the type_id number
-            ## is correct, though--it's site specific.
-            if 'Warnings' in label:
-                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
-                warningstext = [warning.string for warning in warnings]
-                self.warning = ', '.join(warningstext)
-                for warning in warningstext:
-                    self.story.addToList('warnings',warning.string)
-
-            if 'Completed' in label:
-                if 'Yes' in value:
-                    self.story.setMetadata('status', 'Completed')
-                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))
+        datesdiv = soup.find('div',{'class':'bottom'})
+        dates = stripHTML(datesdiv).split()
+        # Published: 04/26/2011 Updated: 03/06/2013
+        self.story.setMetadata('datePublished', makeDate(dates[1], self.dateformat))
+        self.story.setMetadata('dateUpdated', makeDate(dates[3], 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+'/fanfic/'+a['href']
+            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+$'))
+            # can't use ^viewstory...$ in case of higher rated stories with javascript href.
+            storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
             i=1
             for a in storyas:
-                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
-                    self.setSeries(series_name, i)
-                    self.story.setMetadata('seriesUrl',series_url)
-                    break
-                i+=1
+                # skip 'report this' and 'TOC' links
+                if 'contact.php' not in a['href'] and 'index' not in a['href']:
+                    if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                        self.setSeries(series_name, i)
+                        self.story.setMetadata('seriesUrl',series_url)
+                        break
+                    i+=1
             
         except:
             # I find it hard to care if the series parsing fails
             pass
-
-
+            
+        # remove 'small' leaving only summary.
+        smalldiv.extract()
+        self.setDescription(url,metadiv)
+        
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-
-        div = soup.find('div', {'id' : 'story'})
+        soup = bs.BeautifulSoup(self._fetchUrl(url))
         
+        div = soup.find('div', {'id' : 'story'})
+
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-
+    
         return self.utf8FromSoup(url,div)
-

fanficdownloader/adapters/adapter_bloodtiesfancom.py

@@ -211,7 +211,7 @@ class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX
         # 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('authorUrl','http://'+self.host+'/fiction/'+a['href'])
         self.story.setMetadata('author',a.string)
 
         # Find the chapters:

fanficdownloader/adapters/adapter_castlefansorg.py

@@ -184,7 +184,7 @@ class CastleFansOrgAdapter(BaseSiteAdapter): # XXX
         # Find authorid and URL from... author url.
         a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
-        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/fanfic/'+a['href'])
         self.story.setMetadata('author',a.string)
 
         # Find the chapters:

fanficdownloader/adapters/adapter_darksolaceorg.py

@@ -49,7 +49,6 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
         logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
-		
         
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/elysian/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -59,7 +58,7 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%d %B %Y"
+        self.dateformat = "%B %d, %Y"
             
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
@@ -79,7 +78,8 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
     ## Login seems to be reasonably standard across eFiction sites.
     def needToLoginCheck(self, data):
         if 'This story contains adult content not suitable for children' in data \
-                or "That password doesn't match the one in our database" in data:
+                or "That password doesn't match the one in our database" in data \
+                or "Registered Users Only" in data:
             return True
         else:
             return False
@@ -94,17 +94,16 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
             params['penname'] = self.getConfig("username")
             params['password'] = self.getConfig("password")
         params['rememberme'] = '1'
-        params['sid'] = ''
-        params['intent'] = ''
+        params['action'] = 'login'
         params['submit'] = 'Submit'
     
         loginUrl = 'http://' + self.getSiteDomain() + '/elysian/user.php'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['penname']))
     
-        d = self._fetchUrl(loginUrl, params)
+        d = self._postUrl(loginUrl, params)
     
-        if "User Account Page" not in d : #Member Account
+        if "Member Account" not in d : #User Account Page
             logger.info("Failed to login to URL %s as %s, or have no authorization to access the story" % (loginUrl, params['penname']))
             raise exceptions.FailedToLogin(url,params['penname'])
             return False
@@ -113,9 +112,19 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
 
     ## Getting the chapter list and the meta data, plus 'is adult' checking.
     def extractChapterUrlsAndMetadata(self):
+        
+        if self.is_adult or self.getConfig("is_adult"):
+            # Weirdly, different sites use different warning numbers.
+            # If the title search below fails, there's a good chance
+            # you need a different number.  print data at that point
+            # and see what the 'click here to continue' url says.
+            addurl = "&ageconsent=ok&warning=5"
+        else:
+            addurl=""
+
         # index=1 makes sure we see the story chapter index.  Some
         # sites skip that for one-chapter stories.
-        url = self.url
+        url = self.url+'&index=1'+addurl
         logger.debug("URL: "+url)
 
         try:
@@ -128,9 +137,30 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
 
         if self.needToLoginCheck(data):
             # need to log in for this one.
-            addurl="&ageconsent=ok"
             self.performLogin(url)
-            data = self._fetchUrl(url+addurl)
+            data = self._fetchUrl(url)
+            
+        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&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 & error in url.
+                addurl = addurl.replace("&","&")
+                url = self.url+'&index=1'+addurl
+                logger.debug("URL 2nd try: "+url)
+
+                try:
+                    data = self._fetchUrl(url)
+                except urllib2.HTTPError, e:
+                    if e.code == 404:
+                        raise exceptions.StoryDoesNotExist(self.url)
+                    else:
+                        raise e    
+            else:
+                raise exceptions.AdultCheckRequired(self.url)
             
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
             raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
@@ -142,33 +172,41 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
         # Now go hunting for all the meta data and the chapter list.
         
         ## Title and author
-        a = soup.find('div', {'id' : 'pagetitle'})
+        div = soup.find('div', {'id' : 'pagetitle'})
         
-        aut = a.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        aut = div.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',aut['href'].split('=')[1])
         self.story.setMetadata('authorUrl','http://'+self.host+'/elysian/'+aut['href'])
         self.story.setMetadata('author',aut.string)
         aut.extract()
-        
-        self.story.setMetadata('title',a.string[:(len(a.string)-3)])
+
+        # first a tag in pagetitle is title
+        self.story.setMetadata('title',stripHTML(div.find('a')))
 
         # Find the chapters:
-        chapters=soup.find('select', {'name' : 'chapter'})
-        if chapters != None:
-            for chapter in chapters.findAll('option'):
-                self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/elysian/viewstory.php?sid='+self.story.getMetadata('storyId')+'&chapter='+chapter['value']))
-        else:
-            self.chapterUrls.append((self.story.getMetadata('title'),url))
+        # chapters=soup.find('select', {'name' : 'chapter'})
+        # if chapters != None:
+        #     for chapter in chapters.findAll('option'):
+        #         self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/elysian/viewstory.php?sid='+self.story.getMetadata('storyId')+'&chapter='+chapter['value']))
+        # else:
+        #     self.chapterUrls.append((self.story.getMetadata('title'),url+"&chapter=1"))
 
+        for chapa in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+
+                                                       self.story.getMetadata('storyId')+'&chapter=\d+')):
+            self.chapterUrls.append((stripHTML(chapa),'http://'+self.host+'/elysian/'+chapa['href']))
+        
         self.story.setMetadata('numChapters',len(self.chapterUrls))
         
         asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
         
-        for list in asoup.findAll('div', {'class' : re.compile('listbox\s+')}):
-            a = list.find('a', href=re.compile(r'viewstory.php\?sid='))
-            if a != None:
-                if 'viewstory.php?sid='+self.story.getMetadata('storyId') in a['href']:
-                    break
+        # for metalist in asoup.findAll('div', {'class' : re.compile('listbox\s+')}):
+        #     a = metalist.find('a', href=re.compile(r'viewstory.php\?sid='))
+        #     if a != None:
+        #         if 'viewstory.php?sid='+self.story.getMetadata('storyId') in a['href']:
+        #             break
+
+        metalist = asoup.find('a', href=re.compile(r'viewstory.php\?sid='+
+                                                   self.story.getMetadata('storyId')+'($|[^\d])')).parent.parent
 
         # eFiction sites don't help us out a lot with their meta data
         # formating, so it's a little ugly.
@@ -182,7 +220,7 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
                 
 
         # <span class="label">Rated:</span> NC-17<br /> etc
-        labels = list.findAll('span', {'class' : 'classification'})
+        labels = metalist.findAll('span', {'class' : 'label'})
         for labelspan in labels:
             label = labelspan.text
             value = labelspan.nextSibling
@@ -190,7 +228,7 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
             if 'Summary' in label:
                 ## Everything until the next span class='label'
                 svalue = ""
-                while not (defaultGetattr(value,'class') == 'classification' or "Chapters: " in stripHTML(value)):
+                while not (defaultGetattr(value,'class') == 'label' or "Chapters: " in stripHTML(value)):
                     svalue += str(value)
                     value = value.nextSibling
                 self.setDescription(url,svalue)
@@ -238,7 +276,7 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
 
         try:
             # Find Series name from series URL.
-            a = list.find('a', href=re.compile(r"series.php\?seriesid=\d+"))
+            a = metalist.find('a', href=re.compile(r"series.php\?seriesid=\d+"))
             series_name = a.string
             series_url = 'http://'+self.host+'/elysian/'+a['href']
 
@@ -265,8 +303,7 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        soup = bs.BeautifulSoup(self._fetchUrl(url))
         
         div = soup.find('div', {'id' : 'story'})
 

fanficdownloader/adapters/adapter_dramioneorg.py

@@ -237,6 +237,9 @@ class DramioneOrgAdapter(BaseSiteAdapter):
             if 'Word count' in label:
                 self.story.setMetadata('numWords', value)
 
+            if 'Read' in label:
+                self.story.setMetadata('read', value)
+
             if 'Categories' in label:
                 cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
                 for cat in cats:
@@ -282,6 +285,14 @@ class DramioneOrgAdapter(BaseSiteAdapter):
             # I find it hard to care if the series parsing fails
             pass
             
+        try:
+            self.story.setMetadata('reviews',
+                                   stripHTML(soup.find('h2',{'id':'pagetitle'}).
+                                             findAll('a', href=re.compile(r'^reviews.php'))[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):
 

fanficdownloader/adapters/adapter_fanfictionnet.py

@@ -135,12 +135,25 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         categories = soup.find('div',{'id':'pre_story_links'}).findAll('a',{'class':'xcontrast_txt'})
         #print("xcontrast_txt a:%s"%categories)
         if len(categories) > 1:
+            # Strangely, the ones with *two* links are the
+            # non-crossover categories.  Each is in a category itself
+            # of Book, Movie, etc.
             self.story.addToList('category',stripHTML(categories[1]))
         elif 'Crossover' in categories[0]['href']:
             caturl = "http://%s%s"%(self.getSiteDomain(),categories[0]['href'])
             catsoup = bs.BeautifulSoup(self._fetchUrl(caturl))
             for a in catsoup.findAll('a',href=re.compile(r"^/crossovers/")):
                 self.story.addToList('category',stripHTML(a))
+            else:
+                # Fall back.  I ran across a story with a Crossver
+                # category link to a broken page once.
+                # http://www.fanfiction.net/s/2622060/1/
+                # Naruto + Harry Potter Crossover
+                logger.info("Fall back category collection")
+                for c in stripHTML(categories[0]).replace(" Crossover","").split(' + '):
+                    self.story.addToList('category',c)
+                
+                
             
         a = soup.find('a', href='http://www.fictionratings.com/')
         rating = a.string

fanficdownloader/adapters/adapter_grangerenchantedcom.py

@@ -227,6 +227,9 @@ class GrangerEnchantedCom(BaseSiteAdapter):
             if 'Word count' in label:
                 self.story.setMetadata('numWords', value)
 
+            if 'Read' in label:
+                self.story.setMetadata('read', value)
+
             if 'Categories' in label:
                 cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
                 for cat in cats:
@@ -278,7 +281,14 @@ class GrangerEnchantedCom(BaseSiteAdapter):
                         self.story.setMetadata('seriesUrl',series_url)
                         break
                     i+=1
-            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+
+        try:
+            self.story.setMetadata('reviews',
+                                   stripHTML(soup.find('div',{'id':'sort'}).
+                                             findAll('a', href=re.compile(r'^reviews.php'))[1]))
         except:
             # I find it hard to care if the series parsing fails
             pass

fanficdownloader/adapters/adapter_libraryofmoriacom.py

@@ -133,7 +133,7 @@ class LibraryOfMoriaComAdapter(BaseSiteAdapter):
         # 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('authorUrl','http://'+self.host+'/a/'+a['href'])
         self.story.setMetadata('author',a.string)
 
         # Find the chapters:

fanficdownloader/adapters/adapter_netraptororg.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2012 Fanficdownloader team
+# Copyright 2013 Fanficdownloader team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -28,11 +28,9 @@ from .. import exceptions as exceptions
 from base_adapter import BaseSiteAdapter,  makeDate
 
 def getClass():
-    return PrisonBreakFicNetAdapter
+    return NetRaptorOrgAdapter
 
-# Class name has to be unique.  Our convention is camel case the
-# sitename with Adapter at the end.  www is skipped.
-class PrisonBreakFicNetAdapter(BaseSiteAdapter):
+class NetRaptorOrgAdapter(BaseSiteAdapter):
 
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
@@ -51,31 +49,29 @@ class PrisonBreakFicNetAdapter(BaseSiteAdapter):
         logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
         
         # normalized story URL.
-        self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        self._setURL('http://' + self.getSiteDomain() + '/fanfiction/viewstory.php?sid='+self.story.getMetadata('storyId'))
         
         # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','pbf')
+        self.story.setMetadata('siteabbrev','netrap')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%B %d, %Y"
+        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 'www.prisonbreakfic.net'
+        return 'netraptor.org'
 
     def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+        return "http://"+self.getSiteDomain()+"/fanfiction/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
-        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+        return re.escape("http://"+self.getSiteDomain()+"/fanfiction/viewstory.php?sid=")+r"\d+$"
 
     ## Getting the chapter list and the meta data, plus 'is adult' checking.
     def extractChapterUrlsAndMetadata(self):
 
-        # index=1 makes sure we see the story chapter index.  Some
-        # sites skip that for one-chapter stories.
         url = self.url+'&index=1'
         logger.debug("URL: "+url)
 
@@ -86,6 +82,10 @@ class PrisonBreakFicNetAdapter(BaseSiteAdapter):
                 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)
@@ -94,19 +94,20 @@ class PrisonBreakFicNetAdapter(BaseSiteAdapter):
         # 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')+"$"))
+        pagetitle = soup.find('div',{'id':'pagetitle'})
+        a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',a.string)
         
         # Find authorid and URL from... author url.
-        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
-        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/fanfiction/'+a['href'])
         self.story.setMetadata('author',a.string)
 
         # Find the chapters:
         for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
             # just in case there's tags, like <i> in chapter titles.
-            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']))
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/fanfiction/'+chapter['href']))
 
         self.story.setMetadata('numChapters',len(self.chapterUrls))
 
@@ -119,10 +120,7 @@ class PrisonBreakFicNetAdapter(BaseSiteAdapter):
                 return d[k]
             except:
                 return ""
-                
-# summary, rated, word count, categories, characters, genre, warnings, completed, published, updated, seires
-
-        # <span class="label">Rated:</span> NC-17<br /> etc
+				
         labels = soup.findAll('span',{'class':'label'})
         for labelspan in labels:
             value = labelspan.nextSibling
@@ -145,21 +143,18 @@ class PrisonBreakFicNetAdapter(BaseSiteAdapter):
 
             if 'Categories' in label:
                 cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
-                for cat in cats:
+                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'))
-                for char in chars:
+                charstext = [char.string for char in chars]
+                for char in charstext:
                     self.story.addToList('characters',char.string)
 
-            if 'Pairing' in label:
-                ships = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=3')) # XXX
-                for ship in ships:
-                    self.story.addToList('ships',ship.string.replace(" and ","/"))
-
             if 'Genre' in label:
-                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1')) # XXX
+                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)
 
@@ -184,7 +179,7 @@ class PrisonBreakFicNetAdapter(BaseSiteAdapter):
             # 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']
+            series_url = 'http://'+self.host+'/fanfiction/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
             seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
@@ -206,8 +201,7 @@ class PrisonBreakFicNetAdapter(BaseSiteAdapter):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        soup = bs.BeautifulSoup(self._fetchUrl(url))
         
         div = soup.find('div', {'id' : 'story'})
 

fanficdownloader/adapters/adapter_nhamagicalworldsus.py

@@ -112,7 +112,8 @@ class NHAMagicalWorldsUsAdapter(BaseSiteAdapter):
 		
         for info in asoup.findAll('table', {'width' : '100%', 'bordercolor' : re.compile(r'#')}):
             a = info.find('a')
-            if ('viewstory.php?sid='+self.story.getMetadata('storyId')) in a['href']:
+            if 'viewstory.php?sid='+self.story.getMetadata('storyId') == a['href'] or \
+                    ('viewstory.php?sid='+self.story.getMetadata('storyId')+'&') in a['href']:
                 self.story.setMetadata('title',a.string)
                 break
 		
@@ -142,14 +143,14 @@ class NHAMagicalWorldsUsAdapter(BaseSiteAdapter):
         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')))
+        a = info.find('a', href=re.compile(r'viewuser.php'))
         val = a.nextSibling
         svalue = ""
         while not defaultGetattr(val) == 'br':
             val = val.nextSibling
         val = val.nextSibling
         while not defaultGetattr(val) == 'br':
-            svalue += str(val)
+            svalue += unicode(val)
             val = val.nextSibling
         self.setDescription(url,svalue)
         

fanficdownloader/adapters/adapter_nickandgregnet.py

@@ -0,0 +1,174 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2013 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+logger = logging.getLogger(__name__)
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return NickAndGregNetAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class NickAndGregNetAdapter(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])
+        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        # XXX Most sites don't have the /fanfic part.  Replace all to remove it usually.
+        self._setURL('http://' + self.getSiteDomain() + '/desert_archive/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','nag')
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%Y/%m/%d"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'www.nickandgreg.net'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/desert_archive/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/desert_archive/viewstory.php?sid=")+r"\d+$"
+    
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&i=1'
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+
+        ## Title
+        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        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+'/desert_archive/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # Find the chapters:
+        chapters = soup.find('select')
+        for chapter in chapters.findAll('option'):
+            if chapter.text != 'Story Index' and chapter.text != 'Chapters':
+                self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/desert_archive/'+chapter['value']))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+        
+        asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
+        
+        for div in asoup.findAll('td', {'class' : 'tblborder6'}):
+            a = div.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+            if a != None:
+                break
+        
+        self.setDescription(url,div.find('br').nextSibling)
+        
+        a=div.text.split('Rating:')
+        if len(a) == 2: self.story.setMetadata('rating', a[1].split(' -')[0])
+        
+        a=div.text.split('Characters:')
+        if len(a) == 2: 
+        	for char in a[1].split(' -')[0].split(', '):
+        	    self.story.addToList('characters',char)
+        	    
+        a=div.text.split('Genres:')
+        if len(a) == 2: 
+        	for genre in a[1].split(' -')[0].split(', '):
+        	    self.story.addToList('genre',genre)
+        	    
+        a=div.text.split('Warnings:')
+        if len(a) == 2: 
+        	for warn in a[1].split(' -')[0].split(', '):
+        	    if 'none' not in warn:
+        	        self.story.addToList('warnings',warn)
+        	    
+        a=div.text.split('Completed:')
+        if len(a) ==2:
+            if 'Yes' in a[1]:
+                self.story.setMetadata('status', 'Completed')
+            else:
+                self.story.setMetadata('status', 'In-Progress')
+                
+        a=div.text.split('Published:')
+        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].split(' -')[0]), self.dateformat))
+
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logger.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('table', {'class' : 'tblborder6'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_scarvesandcoffeenet.py

@@ -141,7 +141,7 @@ class ScarvesAndCoffeeNetAdapter(BaseSiteAdapter):
         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+"))
+        a = soup.find('div',{"id":"pagetitle"}).find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
         self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
         self.story.setMetadata('author',a.string)

fanficdownloader/adapters/adapter_siyecouk.py

@@ -110,7 +110,7 @@ class SiyeCoUkAdapter(BaseSiteAdapter): # XXX
 
         ## Title
         titlea = authsoup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',titlea.string)
+        self.story.setMetadata('title',stripHTML(titlea))
         
         # Find the chapters (from soup, not authsoup):
         for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):

fanficdownloader/adapters/adapter_test1.py

@@ -47,31 +47,63 @@ class TestSiteAdapter(BaseSiteAdapter):
         return BaseSiteAdapter.getSiteURLPattern(self)+r'/?\?sid=\d+$'
 
     def extractChapterUrlsAndMetadata(self):
+        idstr = self.story.getMetadata('storyId')
+        idnum = int(idstr)
 
-        if self.story.getMetadata('storyId') == '665' and not (self.is_adult or self.getConfig("is_adult")):
+        if idnum >= 1000:
+            logger.warn("storyId:%s - Custom INI data will be used."%idstr)
+
+            sections = ['teststory:%s'%idstr,'teststory:defaults']
+            #print("self.get_config_list(sections,'valid_entries'):%s"%self.get_config_list(sections,'valid_entries'))
+            for key in self.get_config_list(sections,'valid_entries'):
+                if key.endswith("_list"):
+                    nkey = key[:-len("_list")]
+                    #print("addList:%s"%(nkey))
+                    for val in self.get_config_list(sections,key):
+                        #print("addList:%s->%s"%(nkey,val))
+                        self.story.addToList(nkey,val.decode('utf-8').replace('{{storyId}}',idstr))
+                else:
+                    # Special cases:
+                    if key in ['datePublished','dateUpdated']:
+                        self.story.setMetadata(key,makeDate(self.get_config(sections,key),"%Y-%m-%d"))
+                    else:
+                        self.story.setMetadata(key,self.get_config(sections,key).decode('utf-8').replace('{{storyId}}',idstr))
+                    #print("set:%s->%s"%(key,self.story.getMetadata(key)))
+
+            self.chapterUrls = []
+            for (j,chap) in enumerate(self.get_config_list(sections,'chaptertitles'),start=1):
+                self.chapterUrls.append( (chap,self.url+"&chapter=%d"%j) )
+            # self.chapterUrls = [(u'Prologue '+self.crazystring,self.url+"&chapter=1"),
+            #                 ('Chapter 1, Xenos on Cinnabar',self.url+"&chapter=2"),
+            #                 ]
+            self.story.setMetadata('numChapters',len(self.chapterUrls))
+            
+            return
+
+        if idstr == '665' and not (self.is_adult or self.getConfig("is_adult")):
             logger.warn("self.is_adult:%s"%self.is_adult)
             raise exceptions.AdultCheckRequired(self.url)
 
-        if self.story.getMetadata('storyId') == '666':
+        if idstr == '666':
             raise exceptions.StoryDoesNotExist(self.url)
 
-        if self.story.getMetadata('storyId').startswith('670'):
+        if idstr.startswith('670'):
             time.sleep(1.0)
             
-        if self.story.getMetadata('storyId').startswith('671'):
+        if idstr.startswith('671'):
             time.sleep(1.0)
             
         if self.getConfig("username"):
             self.username = self.getConfig("username")
         
-        if self.story.getMetadata('storyId') == '668' and self.username != "Me" :
+        if idstr == '668' and self.username != "Me" :
             raise exceptions.FailedToLogin(self.url,self.username)
 
-        if self.story.getMetadata('storyId') == '664':
-            self.story.setMetadata(u'title',"Test Story Title "+self.story.getMetadata('storyId')+self.crazystring)
+        if idstr == '664':
+            self.story.setMetadata(u'title',"Test Story Title "+idstr+self.crazystring)
             self.story.setMetadata('author','Test Author aa bare amp(&) quote(') amp(&)')
         else:
-            self.story.setMetadata(u'title',"Test Story Title "+self.story.getMetadata('storyId'))
+            self.story.setMetadata(u'title',"Test Story Title "+idstr)
             self.story.setMetadata('author','Test Author aa')
         self.story.setMetadata('storyUrl',self.url)
         self.setDescription(self.url,u'Description '+self.crazystring+u''' Done
@@ -79,13 +111,12 @@ class TestSiteAdapter(BaseSiteAdapter):
 Some more longer description.  "I suck at summaries!"  "Better than it sounds!"  "My first fic"
 ''')
         self.story.setMetadata('datePublished',makeDate("1975-03-15","%Y-%m-%d"))
-        if self.story.getMetadata('storyId') == '669':
+        if idstr == '669':
             self.story.setMetadata('dateUpdated',datetime.datetime.now())
         else:
             self.story.setMetadata('dateUpdated',makeDate("1975-04-15","%Y-%m-%d"))
         self.story.setMetadata('numWords','123456')
 
-        idnum = int(self.story.getMetadata('storyId'))
         if idnum % 2 == 1:
             self.story.setMetadata('status','In-Progress')
         else:
@@ -108,7 +139,7 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
             
         self.story.setMetadata('rating','Tweenie')
 
-        if self.story.getMetadata('storyId') == '673':
+        if idstr == '673':
             self.story.addToList('author','Author From List')
             self.story.addToList('author','Author From List 2')
         
@@ -128,18 +159,19 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
         self.story.addToList('warnings','Swearing')
         self.story.addToList('warnings','Violence')
 
-        if self.story.getMetadata('storyId') == '80':
+        if idstr == '80':
             self.story.addToList('category',u'Rizzoli & Isles')
             self.story.addToList('characters','J. Rizzoli')
-        elif self.story.getMetadata('storyId') == '81':
+        elif idstr == '81':
             self.story.addToList('category',u'Pitch Perfect')
             self.story.addToList('characters','Chloe B.')
-        elif self.story.getMetadata('storyId') == '83':
+        elif idstr == '83':
             self.story.addToList('category',u'Rizzoli & Isles')
             self.story.addToList('characters','J. Rizzoli')
             self.story.addToList('category',u'Pitch Perfect')
             self.story.addToList('characters','Chloe B.')
-        elif self.story.getMetadata('storyId') == '82':
+            self.story.addToList('ships','Chloe B. & J. Rizzoli')
+        elif idstr == '82':
             self.story.addToList('characters','Henry (Once Upon a Time)')        
             self.story.addToList('category',u'Once Upon a Time (TV)')
         else:
@@ -217,6 +249,9 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
 <div>
 <h3>Prologue</h3>
 <p>This is a fake adapter for testing purposes.  Different sid's will give different errors:</p>
+<h4>Config(personal.ini)</h4>
+<p>sid&gt;=1000 will use custom test story data from your configuration(personal.ini)</p>
+<p>Hard coded ids:</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>
@@ -224,10 +259,6 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
 <p>http://test1.com?sid=668 - raises FailedToLogin unless username='Me'</p>
 <p>http://test1.com?sid=669 - Succeeds with Updated Date=now</p>
 <p>http://test1.com?sid=670 - Succeeds, but sleeps 2sec on each chapter</p>
-
-
-
-
 <p>http://test1.com?sid=671 - Succeeds, but sleeps 2sec metadata only</p>
 <p>http://test1.com?sid=672 - Succeeds, quick meta, sleeps 2sec chapters only</p>
 <p>http://test1.com?sid=673 - Succeeds, multiple authors, extra categories, genres</p>

fanficdownloader/adapters/adapter_thehookupzonenet.py

@@ -183,7 +183,7 @@ class TheHookupZoneNetAdapter(BaseSiteAdapter): # XXX
         # 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('authorUrl','http://'+self.host+'/CriminalMinds/'+a['href'])
         self.story.setMetadata('author',a.string)
 
         # Find the chapters:

fanficdownloader/adapters/adapter_thewriterscoffeeshopcom.py

@@ -244,16 +244,23 @@ class TheWritersCoffeeShopComSiteAdapter(BaseSiteAdapter):
         # issues with different SGML parsers in python.  This is a
         # nasty hack, but it works.
         data = data[data.index("<body"):]
-        
-        soup = bs.BeautifulStoneSoup(data,
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
-        span = soup.find('div', {'id' : 'story'})
 
-        if None == span:
+        chapter=bs.BeautifulSoup('<div class="story"></div>')
+        
+        soup = bs.BeautifulSoup(data)
+
+        found=False
+        for div in soup.findAll('div'):
+            if div.has_key('class') and div['class'] == 'notes':
+                chapter.append(div)
+            if div.has_key('id') and div['id'] == 'story':
+                chapter.append(div)
+                found=True
+
+        if not found:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
-        return self.utf8FromSoup(url,span)
+
+        return self.utf8FromSoup(url,chapter)
 
 def getClass():
     return TheWritersCoffeeShopComSiteAdapter

fanficdownloader/adapters/adapter_tokrafandomnetcom.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2012 Fanficdownloader team
+# Copyright 2013 Fanficdownloader team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -28,11 +28,11 @@ from .. import exceptions as exceptions
 from base_adapter import BaseSiteAdapter,  makeDate
 
 def getClass():
-    return SVUFictionComAdapter
+    return TokraFandomnetComAdapter
 
 # Class name has to be unique.  Our convention is camel case the
 # sitename with Adapter at the end.  www is skipped.
-class SVUFictionComAdapter(BaseSiteAdapter):
+class TokraFandomnetComAdapter(BaseSiteAdapter): 
 
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
@@ -54,16 +54,17 @@ class SVUFictionComAdapter(BaseSiteAdapter):
         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','svuf')
+        self.story.setMetadata('siteabbrev','tokra')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%b %d, %Y"
+        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 'svufiction.com'
+        # The site domain.  Does have www here, if it uses it.  But it
+        # doesn't matter too much anymore.
+        return 'tokra.fandomnet.com'
 
     def getSiteExampleURLs(self):
         return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
@@ -71,50 +72,15 @@ class SVUFictionComAdapter(BaseSiteAdapter):
     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'
-        logger.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
-            logger.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 = "&ageconsent=ok&warning=6"
+            addurl = "&ageconsent=ok&warning=3"
         else:
             addurl=""
 
@@ -130,12 +96,7 @@ class SVUFictionComAdapter(BaseSiteAdapter):
                 raise exceptions.StoryDoesNotExist(self.url)
             else:
                 raise e
-                
-        if self.needToLoginCheck(data):
-            # need to log in for this one.
-            self.performLogin(url)
-            data = self._fetchUrl(url)
-                
+
         m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
         if m != None:
             if self.is_adult or self.getConfig("is_adult"):
@@ -163,26 +124,24 @@ class SVUFictionComAdapter(BaseSiteAdapter):
             
         # use BeautifulSoup HTML parser to make everything easier to find.
         soup = bs.BeautifulSoup(data)
-        # print data
+        #print data
 
         # Now go hunting for all the meta data and the chapter list.
         
         ## Title
-        pt = soup.find('div', {'class' : 'title'})
-        a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        if a.text != "":
-            self.story.setMetadata('title',a.text)
-        else:
-            self.story.setMetadata('title','Banner')
+        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',a.string)
         
         # Find authorid and URL from... author url.
-        a = pt.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        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)
 
-        rating=pt.text.split('[')[1].split(']')[0]
-        self.story.setMetadata('rating', rating)
+        # Rating
+        rate = stripHTML(soup.find('div',{'id':'pagetitle'}))
+        rate = rate[rate.rindex('[')+1:rate.rindex(']')]
+        self.story.setMetadata('rating', rate)
 
         # Find the chapters:
         for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
@@ -194,45 +153,36 @@ class SVUFictionComAdapter(BaseSiteAdapter):
         # 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 ""
+        metadiv = soup.find('div',{'class':'content'})
+        smalldiv = metadiv.find('div',{'class':'small'})
 
-        bottom=soup.find('div', {'class' : 'bottom'}).text
-        self.story.setMetadata('numWords', bottom.split('Word count: ')[1].split(' Read:')[0])
-        self.story.setMetadata('datePublished', makeDate(bottom.split('Published: ')[1].split(' Updated:')[0], self.dateformat))
-        self.story.setMetadata('dateUpdated', makeDate(bottom.split('Updated: ')[1], self.dateformat))
+        # tokra categories -> genre
+        # categories will be filled from ini.
+        genres = smalldiv.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+        for genre in genres:
+            self.story.addToList('genre',genre.string)
+        
+        chars = smalldiv.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+        for char in chars:
+            self.story.addToList('characters',char.string)
 
-        
-        content=soup.find('div', {'class' : 'content'})
-        value=content.find('h1').nextSibling
-        svalue = ""
-        while not defaultGetattr(value,'class') == 'smaller':
-            svalue += str(value)
-            value = value.nextSibling
-        self.setDescription(url,svalue)
-        
-        status = content.text.split('Completed: ')[1]
-        if 'Yes' in status:
+        metatext = stripHTML(smalldiv)
+
+        if 'Completed: Yes' in metatext:
             self.story.setMetadata('status', 'Completed')
         else:
             self.story.setMetadata('status', 'In-Progress')
-        
-        cats = content.findAll('a',href=re.compile(r'browse.php\?type=categories'))
-        for cat in cats:
-            self.story.addToList('category',cat.string)
-            
-        chars = content.findAll('a',href=re.compile(r'browse.php\?type=characters'))
-        for char in chars:
-            self.story.addToList('characters',char.string)
-            
-        genres = content.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
-        for genre in genres:
-            self.story.addToList('genre',genre.string)
-            
+
+        wordstart=metatext.rindex('Word count:')+12
+        words = metatext[wordstart:metatext.index(' ',wordstart)]
+        self.story.setMetadata('numWords', words)
+
+        datesdiv = soup.find('div',{'class':'bottom'})
+        dates = stripHTML(datesdiv).split()
+        # Published: 04/26/2011 Updated: 03/06/2013
+        self.story.setMetadata('datePublished', makeDate(dates[1], self.dateformat))
+        self.story.setMetadata('dateUpdated', makeDate(dates[3], self.dateformat))
+
         try:
             # Find Series name from series URL.
             a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
@@ -257,17 +207,30 @@ class SVUFictionComAdapter(BaseSiteAdapter):
             # I find it hard to care if the series parsing fails
             pass
             
+        # remove 'small' leaving only summary.
+        smalldiv.extract()
+        self.setDescription(url,metadiv)
+        
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        soup = bs.BeautifulSoup(self._fetchUrl(url))
         
-        div = soup.find('div', {'id' : 'story'})
+        div = soup.find('div', {'class' : 'content'})
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+
+        # remove some decorations while keeping notes.
+        remove = div.find('div', {'id' : 'pagetitle'})
+        remove.extract()
+    
+        for remove in div.findAll('div', {'class' : 'right'}):
+            remove.extract()
+    
+        for remove in div.findAll('div', {'class' : 'left'}):
+            remove.extract()
     
         return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_tthfanficorg.py

@@ -154,6 +154,30 @@ class TwistingTheHellmouthSiteAdapter(BaseSiteAdapter):
         self.story.setMetadata('author',stripHTML(a))
         authorurl = 'http://'+self.host+a['href']
 
+        try:
+            # going to pull part of the meta data from *primary* author list page.
+            logger.debug("**AUTHOR** URL: "+authorurl)
+            authordata = self._fetchUrl(authorurl)
+            descurl=authorurl
+            authorsoup = bs.BeautifulSoup(authordata)
+            # author can have several pages, scan until we find it.
+            while( not authorsoup.find('a', href=re.compile(r"^/Story-"+self.story.getMetadata('storyId'))) ):
+                nextpage = 'http://'+self.host+authorsoup.find('a', {'class':'arrowf'})['href']
+                logger.debug("**AUTHOR** nextpage URL: "+nextpage)
+                authordata = self._fetchUrl(nextpage)
+                descurl=nextpage
+                authorsoup = bs.BeautifulSoup(authordata)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(url)
+            else:
+                raise e
+
+        storydiv = authorsoup.find('div', {'id':'st'+self.story.getMetadata('storyId'), 'class':re.compile(r"storylistitem")})
+        self.setDescription(descurl,storydiv.find('div',{'class':'storydesc'}))
+        #self.story.setMetadata('description',stripHTML(storydiv.find('div',{'class':'storydesc'})))
+        self.story.setMetadata('title',stripHTML(storydiv.find('a',{'class':'storylink'})))
+
         ainfo = soup.find('a', href='/StoryInfo-%s-1'%self.story.getMetadata('storyId'))
         if ainfo != None: # indicates multiple authors/contributors.
             try:
@@ -201,30 +225,6 @@ class TwistingTheHellmouthSiteAdapter(BaseSiteAdapter):
     
         self.story.setMetadata('numChapters',len(self.chapterUrls))
 
-        try:
-            # going to pull part of the meta data from *primary* author list page.
-            logger.debug("**AUTHOR** URL: "+authorurl)
-            authordata = self._fetchUrl(authorurl)
-            descurl=authorurl
-            authorsoup = bs.BeautifulSoup(authordata)
-            # author can have several pages, scan until we find it.
-            while( not authorsoup.find('a', href=re.compile(r"^/Story-"+self.story.getMetadata('storyId'))) ):
-                nextpage = 'http://'+self.host+authorsoup.find('a', {'class':'arrowf'})['href']
-                logger.debug("**AUTHOR** nextpage URL: "+nextpage)
-                authordata = self._fetchUrl(nextpage)
-                descurl=nextpage
-                authorsoup = bs.BeautifulSoup(authordata)
-        except urllib2.HTTPError, e:
-            if e.code == 404:
-                raise exceptions.StoryDoesNotExist(url)
-            else:
-                raise e
-
-        storydiv = authorsoup.find('div', {'id':'st'+self.story.getMetadata('storyId'), 'class':re.compile(r"storylistitem")})
-        self.setDescription(descurl,storydiv.find('div',{'class':'storydesc'}))
-        #self.story.setMetadata('description',stripHTML(storydiv.find('div',{'class':'storydesc'})))
-        self.story.setMetadata('title',stripHTML(storydiv.find('a',{'class':'storylink'})))
-
         verticaltable = soup.find('table', {'class':'verticaltable'})
 
         BtVS = True

fanficdownloader/adapters/adapter_walkingtheplankorg.py

@@ -119,7 +119,7 @@ class WalkingThePlankOrgAdapter(BaseSiteAdapter):
         # 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('authorUrl','http://'+self.host+'/archive/'+a['href'])
         self.story.setMetadata('author',a.string)
 
         # Find the chapters:

fanficdownloader/adapters/base_adapter.py

@@ -197,7 +197,8 @@ class BaseSiteAdapter(Configurable):
             for index, (title,url) in enumerate(self.chapterUrls):
                 if (self.chapterFirst!=None and index < self.chapterFirst) or \
                         (self.chapterLast!=None and index > self.chapterLast):
-                    self.story.addChapter(removeEntities(title),
+                    self.story.addChapter(url,
+                                          removeEntities(title),
                                           None)
                 else:
                     if self.oldchapters and index < len(self.oldchapters):
@@ -206,7 +207,8 @@ class BaseSiteAdapter(Configurable):
                                                  partial(cachedfetch,self._fetchUrlRaw,self.oldimgs))
                     else:
                         data = self.getChapterText(url)
-                    self.story.addChapter(removeEntities(title),
+                    self.story.addChapter(url,
+                                          removeEntities(title),
                                           removeEntities(data))
             self.storyDone = True
             
@@ -313,6 +315,8 @@ class BaseSiteAdapter(Configurable):
             fetch=self._fetchUrlRaw
 
         acceptable_attributes = ['href','name','class','id']
+        if self.getConfig("keep_style_attr"):
+            acceptable_attributes.append('style')
         #print("include_images:"+self.getConfig('include_images'))
         if self.getConfig('include_images'):
             acceptable_attributes.extend(('src','alt','longdesc'))

fanficdownloader/configurable.py

@@ -15,7 +15,7 @@
 # limitations under the License.
 #
 
-import ConfigParser
+import ConfigParser, re
 
 # All of the writers(epub,html,txt) and adapters(ffnet,twlt,etc)
 # inherit from Configurable.  The config file(s) uses ini format:
@@ -37,10 +37,20 @@ class Configuration(ConfigParser.SafeConfigParser):
     def __init__(self, site, fileform):
         ConfigParser.SafeConfigParser.__init__(self)
         self.sectionslist = ['defaults']
-        self.addConfigSection(site)
+
+        if site.startswith("www."):
+            sitewith = site
+            sitewithout = site.replace("www.","")
+        else:
+            sitewith = "www."+site
+            sitewithout = site
+        
+        self.addConfigSection(sitewith)
+        self.addConfigSection(sitewithout)
         if fileform:
             self.addConfigSection(fileform)
-            self.addConfigSection(site+":"+fileform)
+            self.addConfigSection(sitewith+":"+fileform)
+            self.addConfigSection(sitewithout+":"+fileform)
         self.addConfigSection("overrides")
         
         self.validEntries = [
@@ -89,8 +99,12 @@ class Configuration(ConfigParser.SafeConfigParser):
     def getValidMetaList(self):
         return self.validEntries + self.getConfigList("extra_valid_entries")
 
+    # used by adapters & writers, non-convention naming style
     def hasConfig(self, key):
-        for section in self.sectionslist:
+        return self.has_config(self.sectionslist, key)
+
+    def has_config(self, sections, key):
+        for section in sections:
             try:
                 self.get(section,key)
                 #print("found %s in section [%s]"%(key,section))
@@ -104,10 +118,14 @@ class Configuration(ConfigParser.SafeConfigParser):
                     pass
 
         return False
-        
+
+    # used by adapters & writers, non-convention naming style
     def getConfig(self, key, default=""):
+        return self.get_config(self.sectionslist,key,default)
+    
+    def get_config(self, sections, key, default=""):        
         val = default
-        for section in self.sectionslist:
+        for section in sections:
             try:
                 val = self.get(section,key)
                 if val and val.lower() == "false":
@@ -117,7 +135,7 @@ class Configuration(ConfigParser.SafeConfigParser):
             except (ConfigParser.NoOptionError, ConfigParser.NoSectionError), e:
                 pass
 
-        for section in self.sectionslist[::-1]:
+        for section in sections[::-1]:
             # 'martian smiley' [::-1] reverses list by slicing whole list with -1 step.
             try:
                 val = val + self.get(section,"add_to_"+key)
@@ -128,11 +146,15 @@ class Configuration(ConfigParser.SafeConfigParser):
         return val
 
     # split and strip each.
-    def getConfigList(self, key):
-        vlist = self.getConfig(key).split(',')
-        vlist = filter( lambda x : x !='', [ v.strip() for v in vlist ])
+    def get_config_list(self, sections, key):
+        vlist = re.split(r'(?<!\\),',self.get_config(sections,key)) # don't split on \,
+        vlist = filter( lambda x : x !='', [ v.strip().replace('\,',',') for v in vlist ])
         #print "vlist("+key+"):"+str(vlist)
         return vlist        
+    
+    # used by adapters & writers, non-convention naming style
+    def getConfigList(self, key):
+        return self.get_config_list(self.sectionslist, key)
 
 # extended by adapter, writer and story for ease of calling configuration.
 class Configurable(object):
@@ -147,11 +169,19 @@ class Configurable(object):
         return self.configuration.getValidMetaList()
     
     def hasConfig(self, key):
-        return self.configuration.hasConfig(key)
+        return self.configuration.hasConfig(key)        
         
+    def has_config(self, sections, key):
+        return self.configuration.has_config(sections, key)
+
     def getConfig(self, key, default=""):
         return self.configuration.getConfig(key,default)
 
+    def get_config(self, sections, key, default=""):
+        return self.configuration.get_config(sections,key,default)
+
     def getConfigList(self, key):
         return self.configuration.getConfigList(key)
-        
+
+    def get_config_list(self, sections, key):
+        return self.configuration.get_config_list(sections,key)

fanficdownloader/epubutils.py

@@ -130,6 +130,9 @@ def get_update_data(inputio,
                         h2 = soup.find('h2')
                         if h2:
                             h2.extract()
+
+                        for skip in soup.findAll(attrs={'class':'skip_on_ffdl_update'}):
+                            skip.extract()
                             
                         soups.append(soup)
                         

fanficdownloader/exceptions.py

@@ -68,3 +68,10 @@ class UnknownSite(Exception):
     def __str__(self):
         return "Unknown Site(%s).  Supported sites: (%s)" % (self.url, ", ".join(self.supported_sites_list))
 
+class FailedToWriteOutput(Exception):
+    def __init__(self,error):
+        self.error=error
+
+    def __str__(self):
+        return self.error
+

fanficdownloader/geturls.py

@@ -54,9 +54,14 @@ def get_urls_from_page(url,configuration=None,normalize=False):
         opener = u2.build_opener(u2.HTTPCookieProcessor(),GZipProcessor())
         data = opener.open(url).read()
 
-    return get_urls_from_html(data,url,configuration,normalize)
+    # kludge because I don't see it on enough sites to be worth generalizing yet.
+    restrictsearch=None
+    if 'scarvesandcoffee.net' in url:
+        restrictsearch=('div',{'id':'mainpage'})
 
-def get_urls_from_html(data,url=None,configuration=None,normalize=False):
+    return get_urls_from_html(data,url,configuration,normalize,restrictsearch)
+
+def get_urls_from_html(data,url=None,configuration=None,normalize=False,restrictsearch=None):
 
     normalized = [] # normalized url
     retlist = [] # orig urls.
@@ -65,6 +70,9 @@ def get_urls_from_html(data,url=None,configuration=None,normalize=False):
         configuration = Configuration("test1.com","EPUB")
 
     soup = BeautifulSoup(data)
+    if restrictsearch:
+        soup = soup.find(*restrictsearch)
+        print("restrict search:%s"%soup)
     
     for a in soup.findAll('a'):
         if a.has_key('href'):
@@ -105,9 +113,9 @@ def get_urls_from_text(data,configuration=None,normalize=False):
         # 'are you old enough' links, and 'Report This' links.
         # The 'normalized' set prevents duplicates.
         if 'story.php' in href:
-            m = re.search(r"(?P<sid>(view)?story\.php\?(sid|psid|no|story|stid)=\d+)",a['href'])
+            m = re.search(r"(?P<sid>(view)?story\.php\?(sid|psid|no|story|stid)=\d+)",href)
             if m != None:
-                href = form_url(None,m.group('sid'))
+                href = form_url(href,m.group('sid'))
         try:
             href = href.replace('&index=1','')
             adapter = adapters.getAdapter(configuration,href)

fanficdownloader/html.py

@@ -17,7 +17,7 @@ class HtmlProcessor:
     self.unfill = unfill
     html = self._ProcessRawHtml(html)
     self._soup = BeautifulSoup(html)
-    if self._soup.title:
+    if self._soup.title.contents:
       self.title = self._soup.title.contents[0]
     else:
       self.title = None

fanficdownloader/mobi.py

@@ -8,6 +8,8 @@ import time
 import random
 import logging
 
+logger = logging.getLogger(__name__)
+
 from html import HtmlProcessor
 
 # http://wiki.mobileread.com/wiki/MOBI
@@ -124,8 +126,8 @@ class Converter:
       tmp = self.MakeOneHTML(html_strs)
       self._ConvertStringToFile(tmp, out_file)
     except Exception, e:
-      logging.error('Error %s', e)
-      logging.debug('Details: %s' % html_strs)
+      logger.error('Error %s', e)
+      #logger.debug('Details: %s' % html_strs)
 
   def _ConvertStringToFile(self, html_data, out):
     html = HtmlProcessor(html_data)

fanficdownloader/story.py

@@ -280,10 +280,10 @@ class Story(Configurable):
         for line in replace.splitlines():
             (metakeys,regexp,replacement,condkey,condregexp)=(None,None,None,None,None)
             if "&&" in line:
-                (line,conditional) = map( lambda x: x.strip(), line.split("&&") )
-                (condkey,condregexp) = map( lambda x: x.strip(), conditional.split("=>") )
+                (line,conditional) = line.split("&&")
+                (condkey,condregexp) = conditional.split("=>")
             if "=>" in line:
-                parts = map( lambda x: x.strip(), line.split("=>") )
+                parts = line.split("=>")
                 if len(parts) > 2:
                     metakeys = map( lambda x: x.strip(), parts[0].split(",") )
                     (regexp,replacement)=parts[1:]
@@ -294,9 +294,13 @@ class Story(Configurable):
                 regexp = re.compile(regexp)
                 if condregexp:
                     condregexp = re.compile(condregexp)
+                # A way to explicitly include spaces in the
+                # replacement string.  The .ini parser eats any
+                # trailing spaces.
+                replacement=replacement.replace('\s',' ') 
                 self.replacements.append([metakeys,regexp,replacement,condkey,condregexp])
     
-    def doReplacments(self,value,key):
+    def doReplacements(self,value,key):
         for (metakeys,regexp,replacement,condkey,condregexp) in self.replacements:
             if (metakeys == None or key in metakeys) \
                     and isinstance(value,basestring) \
@@ -336,7 +340,7 @@ class Story(Configurable):
                     value = value.strftime(self.getConfig(key+"_format","%Y-%m-%d"))
 
             if doreplacements:
-                value=self.doReplacments(value,key)
+                value=self.doReplacements(value,key)
             if removeallentities and value != None:
                 return removeAllEntities(value)
             else:
@@ -360,8 +364,8 @@ class Story(Configurable):
                 auth = v
                 # make sure doreplacements & removeallentities are honored.
                 if doreplacements:
-                    aurl=self.doReplacments(aurl,'authorUrl')
-                    auth=self.doReplacments(auth,'author')
+                    aurl=self.doReplacements(aurl,'authorUrl')
+                    auth=self.doReplacements(auth,'author')
                 if removeallentities:
                     aurl=removeAllEntities(aurl)
                     auth=removeAllEntities(auth)
@@ -434,7 +438,7 @@ class Story(Configurable):
         if retlist:
             if doreplacements:
                 retlist = filter( lambda x : x!=None and x!='' ,
-                                  map(partial(self.doReplacments,key=listname),retlist) )
+                                  map(partial(self.doReplacements,key=listname),retlist) )
             if removeallentities:
                 retlist = filter( lambda x : x!=None and x!='' ,
                                   map(removeAllEntities,retlist) )
@@ -470,11 +474,11 @@ class Story(Configurable):
 
         return list(subjectset | set(self.getConfigList("extratags")))
             
-    def addChapter(self, title, html):
+    def addChapter(self, url, title, html):
         if self.getConfig('strip_chapter_numbers') and \
                 self.getConfig('chapter_title_strip_pattern'):
             title = re.sub(self.getConfig('chapter_title_strip_pattern'),"",title)
-        self.chapters.append( (title,html) )
+        self.chapters.append( (url,title,html) )
 
     def getChapters(self,fortoc=False):
         "Chapters will be tuples of (title,html)"
@@ -484,8 +488,10 @@ class Story(Configurable):
                 (self.getConfig('add_chapter_numbers') == "true" \
                      or (self.getConfig('add_chapter_numbers') == "toconly" and fortoc)) \
                      and self.getConfig('chapter_title_add_pattern'):
-            for index, (title,html) in enumerate(self.chapters):
-                retval.append( (string.Template(self.getConfig('chapter_title_add_pattern')).substitute({'index':index+1,'title':title}),html) ) 
+            for index, (url,title,html) in enumerate(self.chapters):
+                retval.append( (url,
+                                string.Template(self.getConfig('chapter_title_add_pattern')).substitute({'index':index+1,'title':title}),
+                                html) )
         else:
             retval = self.chapters
             

fanficdownloader/writers/base_writer.py

@@ -177,11 +177,12 @@ class BaseStoryWriter(Configurable):
             
             self._write(out,START.substitute(self.story.getAllMetadata()))
 
-            for index, (title,html) in enumerate(self.story.getChapters(fortoc=True)):
+            for index, (url,title,html) in enumerate(self.story.getChapters(fortoc=True)):
                 if html:
                     self._write(out,ENTRY.substitute({'chapter':title,
                                                       'number':index+1,
-                                                      'index':"%04d"%(index+1)}))
+                                                      'index':"%04d"%(index+1),
+                                                      'url':url}))
 
             self._write(out,END.substitute(self.story.getAllMetadata()))
 

fanficdownloader/writers/writer_epub.py

@@ -501,7 +501,7 @@ div { margin: 0pt; padding: 0pt; }
             items.append(("log_page","OEBPS/log_page.xhtml","application/xhtml+xml","Update Log"))
             itemrefs.append("log_page")
             
-        for index, (title,html) in enumerate(self.story.getChapters(fortoc=True)):
+        for index, (url,title,html) in enumerate(self.story.getChapters(fortoc=True)):
             if html:
                 i=index+1
                 items.append(("file%04d"%i,
@@ -649,10 +649,10 @@ div { margin: 0pt; padding: 0pt; }
         else:
             CHAPTER_END = self.EPUB_CHAPTER_END
         
-        for index, (title,html) in enumerate(self.story.getChapters()):
+        for index, (url,title,html) in enumerate(self.story.getChapters()):
             if html:
                 logger.debug('Writing chapter text for: %s' % title)
-                vals={'chapter':title, 'index':"%04d"%(index+1), 'number':index+1}
+                vals={'url':url, 'chapter':title, 'index':"%04d"%(index+1), 'number':index+1}
                 fullhtml = CHAPTER_START.substitute(vals) + html + CHAPTER_END.substitute(vals)
                 # ffnet(& maybe others) gives the whole chapter text
                 # as one line.  This causes problems for nook(at

fanficdownloader/writers/writer_html.py

@@ -128,10 +128,10 @@ ${output_css}
         else:
             CHAPTER_END = self.HTML_CHAPTER_END
         
-        for index, (title,html) in enumerate(self.story.getChapters()):
+        for index, (url,title,html) in enumerate(self.story.getChapters()):
             if html:
                 logging.debug('Writing chapter text for: %s' % title)
-                vals={'chapter':title, 'index':"%04d"%(index+1), 'number':index+1}
+                vals={'url':url, 'chapter':title, 'index':"%04d"%(index+1), 'number':index+1}
                 self._write(out,CHAPTER_START.substitute(vals))
                 self._write(out,html)
                 self._write(out,CHAPTER_END.substitute(vals))

fanficdownloader/writers/writer_mobi.py

@@ -22,6 +22,9 @@ import StringIO
 from base_writer import *
 from ..htmlcleanup import stripHTML
 from ..mobi import Converter
+from ..exceptions import FailedToWriteOutput
+
+logger = logging.getLogger(__name__)
 
 class MobiWriter(BaseStoryWriter):
 
@@ -158,10 +161,10 @@ ${value}<br />
         else:
             CHAPTER_END = self.MOBI_CHAPTER_END
         
-        for index, (title,html) in enumerate(self.story.getChapters()):
+        for index, (url,title,html) in enumerate(self.story.getChapters()):
             if html:
-                logging.debug('Writing chapter text for: %s' % title)
-                vals={'chapter':title, 'index':"%04d"%(index+1), 'number':index+1}
+                logger.debug('Writing chapter text for: %s' % title)
+                vals={'url':url, 'chapter':title, 'index':"%04d"%(index+1), 'number':index+1}
                 fullhtml = CHAPTER_START.substitute(vals) + html + CHAPTER_END.substitute(vals)
                 # ffnet(& maybe others) gives the whole chapter text
                 # as one line.  This causes problems for nook(at
@@ -175,6 +178,8 @@ ${value}<br />
                       author=self.getMetadata('author'),
                       publisher=self.getMetadata('site'))
         mobidata = c.ConvertStrings(files)
+        if len(mobidata) < 1:
+            raise FailedToWriteOutput("Zero length mobi output")
         out.write(mobidata)
         
         del files

fanficdownloader/writers/writer_txt.py

@@ -154,10 +154,10 @@ End file.
         else:
             CHAPTER_END = self.TEXT_CHAPTER_END
         
-        for index, (title,html) in enumerate(self.story.getChapters()):
+        for index, (url, title,html) in enumerate(self.story.getChapters()):
             if html:
                 logging.debug('Writing chapter text for: %s' % title)
-                vals={'chapter':title, 'index':"%04d"%(index+1), 'number':index+1}
+                vals={'url':url, 'chapter':title, 'index':"%04d"%(index+1), 'number':index+1}
                 self._write(out,self.lineends(self.wraplines(removeAllEntities(CHAPTER_START.substitute(vals)))))
                 self._write(out,self.lineends(html2text(html,wrap_width=self.wrap_width)))
                 self._write(out,self.lineends(self.wraplines(removeAllEntities(CHAPTER_END.substitute(vals)))))

index.html

@@ -53,13 +53,14 @@
 	    <p>Hi, {{ nickname }}! This is FanFictionDownLoader, which makes reading stories from various websites
 	      much easier. </p>
 	  </div>
-	  <!-- put announcements here, h3 is a good title size. -->
+	  <!-- put announcements here, h3 is a good title size.
 	  <h3>Changes:</h3>
 	  <p>
 	    <ul>
-	      <li>Yet another fix for fanfiction.net changes.</li>
+	      <li></li>
 	    </ul>
 	  </p>
+	   -->
 	  <p>
 	    Questions?  Check out our 
 	    <a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderFAQs">FAQs</a>.
@@ -68,7 +69,7 @@
 	    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://4-4-52.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
+	    <a href="http://4-4-59.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
 	  </p>
 	  <div id='error'>
 	    {{ error_message }}
@@ -378,11 +379,6 @@
 	    Use the URL of the story's first chapter, such as
 	    <br /><a href="http://onedirectionfanfiction.com/viewstory.php?sid=1234">http://onedirectionfanfiction.com/viewstory.php?sid=1234</a>
 	  </dd>
-	  <dt>www.prisonbreakfic.net</dt>
-	  <dd>
-	    Use the URL of the story's first chapter, such as
-	    <br /><a href="http://www.prisonbreakfic.net/viewstory.php?sid=1234">http://www.prisonbreakfic.net/viewstory.php?sid=1234</a>
-	  </dd>
 	  <dt>www.storiesofarda.com</dt>
 	  <dd>
 	    Use the URL of the story's chapter list, such as
@@ -471,11 +467,6 @@
 	    Use the URL of the story's first chapter, such as
 	    <br /><a href="http://www.hpfanficarchive.com/stories/viewstory.php?sid=1234">http://www.hpfanficarchive.com/stories/viewstory.php?sid=1234</a>
 	  </dd>
-	  <dt>svufiction.com</dt>
-	  <dd>
-	    Use the URL of the story's first chapter, such as
-	    <br /><a href="http://svufiction.com/viewstory.php?sid=1234">http://svufiction.com/viewstory.php?sid=1234</a>
-	  </dd>
 	  <dt>www.twilightarchives.com</dt>
 	  <dd>
 	    Use the URL of the story's first chapter, such as
@@ -552,11 +543,6 @@
 	    Use the URL of the story's chapter list, such as
 	    <br /><a href="http://www.indeath.net/blog/25-nightmare-in-death/">http://www.indeath.net/blog/25-nightmare-in-death/</a>
 	  </dd>
-	  <dt>www.jlaunlimited.com</dt>
-	  <dd>
-	    Use the URL of the story's first chapter, such as
-	    <br /><a href="http://www.jlaunlimited.com/eFiction1.1/viewstory.php?sid=1234">http://www.jlaunlimited.com/eFiction1.1/viewstory.php?sid=1234</a>
-	  </dd>
 	  <dt>www.efpfanfic.net</dt>
 	  <dd>
 	    Use the URL of any story chapter, such as
@@ -607,11 +593,31 @@
 	    Use the URL of the story's chapter list, such as
 	    <br /><a href="http://www.henneth-annun.net/stories/chapter.cfm?stid=1234">http://www.henneth-annun.net/stories/chapter.cfm?stid=1234</a>
 	  </dd>
-	  <dt>http://www.psychfic.com</dt>
+	  <dt>www.psychfic.com</dt>
 	  <dd>
 	    Use the URL of the story's chapter list, such as
 	    <br /><a href="http://www.psychfic.com/viewstory.php?sid=1234">http://www.psychfic.com/viewstory.php?sid=1234</a>
 	  </dd>
+	  <dt>tokra.fandomnet.com</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://tokra.fandomnet.com/viewstory.php?sid=1234">http://tokra.fandomnet.com/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>asr3.slashzone.org</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://asr3.slashzone.org/archive/viewstory.php?sid=1234">http://asr3.slashzone.org/archive/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>netraptor.org</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://netraptor.org/archive/viewstory.php?sid=1234">http://netraptor.org/archive/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>nickandgreg.net</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://www.nickandgreg.net/desert_archive/viewstory.php?sid=1234">http://www.nickandgreg.net/desert_archive/viewstory.php?sid=1234</a>
+	  </dd>
 	</dl>
 
 	<p>