Bump versions.

http://archive.skyehawke.com/story.php?no=1234
http://www.skyehawke.com/archive/story.php?no=1234
http://skyehawke.com/archive/story.php?no=1234

app.yaml

@@ -1,6 +1,6 @@
 # ffd-retief-hrd fanfictiondownloader
 application: fanfictiondownloader
-version: 4-4-35
+version: 4-4-43
 runtime: python27
 api_version: 1
 threadsafe: true

calibre-plugin/__init__.py

@@ -27,7 +27,7 @@ class FanFictionDownLoaderBase(InterfaceActionBase):
     description         = 'UI plugin to download FanFiction stories from various sites.'
     supported_platforms = ['windows', 'osx', 'linux']
     author              = 'Jim Miller'
-    version             = (1, 7, 1)
+    version             = (1, 7, 9)
     minimum_calibre_version = (0, 8, 57)
 
     #: This field defines the GUI plugin class that contains all the code

calibre-plugin/config.py

@@ -153,7 +153,7 @@ class RejectURLList:
         self.sync_lock = threading.RLock()
         self.listcache = None
 
-    def _read_list_from_text(self,text):
+    def _read_list_from_text(self,text,addreasontext=None):
         cache = {}
         for line in text.splitlines():
             if ',' in line:
@@ -162,6 +162,10 @@ class RejectURLList:
                 (rejurl,note) = (line,'')
             rejurl = getNormalStoryURL(rejurl)
             if rejurl:
+                if addreasontext and note:
+                    note = note +" - "+addreasontext
+                elif addreasontext:
+                    note = addreasontext
                 cache[rejurl] = note
         return cache
         
@@ -200,8 +204,8 @@ class RejectURLList:
                 del listcache[url]
                 self._save_list(listcache)
 
-    def add_text(self,rejecttext):
-        self.add(self._read_list_from_text(rejecttext).items())
+    def add_text(self,rejecttext,addreasontext):
+        self.add(self._read_list_from_text(rejecttext,addreasontext).items())
             
     def add(self,rejectlist,clear=False):
         # rejectlist=list of (url,note) tuples.
@@ -524,7 +528,8 @@ class BasicTab(QWidget):
                              rejectlist,
                              rejectreasons=rejecturllist.get_reject_reasons(),
                              header="Edit Reject URLs List",
-                             show_delete=False)
+                             show_delete=False,
+                             show_all_reasons=False)
         d.exec_()
         
         if d.result() != d.Accepted:
@@ -552,11 +557,13 @@ class BasicTab(QWidget):
                            "http://example.com?story.php?sid=5,Reason why I rejected it",
                            icon=self.windowIcon(),
                            title="Add Reject URLs",
-                           label="Add Reject URLs. Use: <b>http://...,note</b>",
-                           tooltip="One URL per line, everything after <b>,</b> will be put in the note.")
+                           label="Add Reject URLs. Use: <b>http://...,note</b><br>Invalid story URLs will be ignored.",
+                           tooltip="One URL per line, everything after <b>,</b> will be put in the note.",
+                           rejectreasons=rejecturllist.get_reject_reasons(),
+                           reasonslabel='Add this reason to all URLs added:')
         d.exec_()
         if d.result() == d.Accepted:
-            rejecturllist.add_text(d.get_plain_text())
+            rejecturllist.add_text(d.get_plain_text(),d.get_reason_text())
                 
 class PersonalIniTab(QWidget):
 

calibre-plugin/dialogs.py

@@ -45,6 +45,19 @@ collision_order=[SKIP,
                  OVERWRITEALWAYS,
                  CALIBREONLY,]
         
+# This is a more than slightly kludgey way to get
+# EditWithComplete to *not* alpha-order the reasons, but leave
+# them in the order entered.  If
+# calibre.gui2.complete2.CompleteModel.set_items ever changes,
+# this function will need to also.
+def complete_model_set_items_kludge(self, items):
+    items = [unicode(x.strip()) for x in items]
+    items = [x for x in items if x]
+    items = tuple(items)
+    self.all_items = self.current_items = items
+    self.current_prefix = ''
+    self.reset()
+    
 class NotGoingToDownload(Exception):
     def __init__(self,error,icon='dialog_error.png'):
         self.error=error
@@ -779,19 +792,6 @@ class RejectListTableWidget(QTableWidget):
 
         note_cell = EditWithComplete(self)
 
-        # This is a more than slightly kludgey way to get
-        # EditWithComplete to *not* alpha-order the reasons, but leave
-        # them in the order entered.  If
-        # calibre.gui2.complete2.CompleteModel.set_items ever changes,
-        # this function will need to also.
-        def complete_model_set_items_kludge(self, items):
-            items = [unicode(x.strip()) for x in items]
-            items = [x for x in items if x]
-            items = tuple(items)
-            self.all_items = self.current_items = items
-            self.current_prefix = ''
-            self.reset()
-
         note_cell.lineEdit().mcompleter.model().set_items = \
             partial(complete_model_set_items_kludge,
                     note_cell.lineEdit().mcompleter.model())
@@ -895,6 +895,7 @@ class RejectListDialog(SizePersistedDialog):
                  header="List of Books to Reject",
                  icon='rotate-right.png',
                  show_delete=True,
+                 show_all_reasons=True,
                  save_size_name='ffdl:reject list dialog'):
         SizePersistedDialog.__init__(self, gui, save_size_name)
         self.gui = gui
@@ -935,6 +936,26 @@ class RejectListDialog(SizePersistedDialog):
         spacerItem1 = QtGui.QSpacerItem(20, 40, QtGui.QSizePolicy.Minimum, QtGui.QSizePolicy.Expanding)
         button_layout.addItem(spacerItem1)
 
+        if show_all_reasons:
+            self.reason_edit = EditWithComplete(self)
+            self.reason_edit.lineEdit().mcompleter.model().set_items = \
+                partial(complete_model_set_items_kludge,
+                        self.reason_edit.lineEdit().mcompleter.model())
+            
+            items = ['']+rejectreasons
+            self.reason_edit.update_items_cache(items)
+            self.reason_edit.show_initial_value('')
+            self.reason_edit.set_separator(None)
+            self.reason_edit.setToolTip("This will be added to whatever note you've set for each URL above.")
+            
+            horz = QHBoxLayout()
+            label = QLabel("Add this reason to all URLs added:")
+            label.setToolTip("This will be added to whatever note you've set for each URL above.")
+            horz.addWidget(label)
+            horz.addWidget(self.reason_edit)
+            horz.insertStretch(-1)
+            layout.addLayout(horz)
+                    
         options_layout = QHBoxLayout()
 
         if show_delete:
@@ -960,13 +981,18 @@ class RejectListDialog(SizePersistedDialog):
     def get_reject_list(self):
         return self.rejects_table.get_reject_list()
 
+    def get_reason_text(self):
+        return unicode(self.reason_edit.currentText()).strip()
+    
     def get_deletebooks(self):
         return self.deletebooks.isChecked()
 
 class EditTextDialog(QDialog):
 
     def __init__(self, parent, text,
-                 icon=None, title=None, label=None, tooltip=None):
+                 icon=None, title=None, label=None, tooltip=None,
+                 rejectreasons=[],reasonslabel=None
+                 ):
         QDialog.__init__(self, parent)
         self.resize(600, 500)
         self.l = QVBoxLayout()
@@ -987,6 +1013,29 @@ class EditTextDialog(QDialog):
             self.label.setToolTip(tooltip)
             self.textedit.setToolTip(tooltip)
 
+        if rejectreasons or reasonslabel:
+            self.reason_edit = EditWithComplete(self)
+
+            self.reason_edit.lineEdit().mcompleter.model().set_items = \
+                partial(complete_model_set_items_kludge,
+                        self.reason_edit.lineEdit().mcompleter.model())
+            
+            items = ['']+rejectreasons
+            self.reason_edit.update_items_cache(items)
+            self.reason_edit.show_initial_value('')
+            self.reason_edit.set_separator(None)
+            self.reason_edit.setToolTip(reasonslabel)
+            
+            if reasonslabel:
+                horz = QHBoxLayout()
+                label = QLabel(reasonslabel)
+                label.setToolTip(reasonslabel)
+                horz.addWidget(label)
+                horz.addWidget(self.reason_edit)
+                self.l.addLayout(horz)
+            else:
+                self.l.addWidget(self.reason_edit)
+            
         button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
         button_box.accepted.connect(self.accept)
         button_box.rejected.connect(self.reject)
@@ -994,3 +1043,7 @@ class EditTextDialog(QDialog):
 
     def get_plain_text(self):
         return unicode(self.textedit.toPlainText())
+
+    def get_reason_text(self):
+        return unicode(self.reason_edit.currentText()).strip()
+    

calibre-plugin/ffdl_plugin.py

@@ -290,12 +290,10 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         url_list = get_urls_from_page(url,configuration)
 
         if url_list:
-            d = ViewLog(_("List of URLs"),"\n".join(url_list),parent=self.gui)
-            d.setWindowIcon(get_icon('bookmarks.png'))
-            d.exec_()
+            self.add_dialog("\n".join(url_list))
         else:
-            info_dialog(self.gui, _('List of URLs'),
-                        _('No Valid URLs found on given page.'),
+            info_dialog(self.gui, _('List of Story URLs'),
+                        _('No Valid Story URLs found on given page.'),
                         show=True,
                         show_copy_button=False)
         
@@ -338,12 +336,12 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
     def _finish_get_list_urls(self, book_list):
         url_list = [ x['url'] for x in book_list if x['good'] ]
         if url_list:
-            d = ViewLog(_("List of URLs"),"\n".join(url_list),parent=self.gui)
+            d = ViewLog(_("List of Story URLs"),"\n".join(url_list),parent=self.gui)
             d.setWindowIcon(get_icon('bookmarks.png'))
             d.exec_()
         else:
             info_dialog(self.gui, _('List of URLs'),
-                        _('No URLs found in selected books.'),
+                        _('No Story URLs found in selected books.'),
                         show=True,
                         show_copy_button=False)
                 
@@ -404,8 +402,13 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
 
             bookids=[]
             rejectlist=[]
+            addreasontext=d.get_reason_text()
             for (bookid,url,note) in d.get_reject_list():
                 bookids.append(bookid)
+                if addreasontext and note:
+                    note = note +" - "+addreasontext
+                elif addreasontext:
+                    note = addreasontext
                 rejectlist.append((url,note))
                 print("Adding (%s) to Reject List: %s"%(url,note))
                 
@@ -419,12 +422,13 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             if confirm(message,'fanfictiondownloader_reject_non_fanfiction', self.gui):
                 self.gui.iactions['Remove Books'].delete_books()
                 
-    def add_dialog(self):
+    def add_dialog(self,url_list_text=None):
 
         #print("add_dialog()")
 
-        url_list = self.get_urls_clip()
-        url_list_text = "\n".join(url_list)
+        if not url_list_text:
+            url_list = self.get_urls_clip()
+            url_list_text = "\n".join(url_list)
         
         # self.gui is the main calibre GUI. It acts as the gateway to access
         # all the elements of the calibre user interface, it should also be the
@@ -519,13 +523,14 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         tdir = PersistentTemporaryDirectory(prefix='fanfictiondownloader_')
         options['tdir']=tdir
 
-        self.gui.status_bar.show_message(_('Started fetching metadata for %s stories.'%len(books)), 3000)
-        
         if 0 < len(filter(lambda x : x['good'], books)):
+            self.gui.status_bar.show_message(_('Started fetching metadata for %s stories.'%len(books)), 3000)
             LoopProgressDialog(self.gui,
                                books,
                                partial(self.get_metadata_for_book, options = options),
                                partial(self.start_download_list, options = options))
+        else:
+            self.gui.status_bar.show_message(_('No valid story URLs entered.'), 3000)
         # LoopProgressDialog calls get_metadata_for_book for each 'good' story,
         # get_metadata_for_book updates book for each,
         # LoopProgressDialog calls start_download_list at the end which goes
@@ -870,9 +875,14 @@ make_firstimage_cover:true
         add_ids = [ x['calibre_id'] for x in add_list ]
         update_list = filter(lambda x : x['good'] and not x['added'], book_list)
         update_ids = [ x['calibre_id'] for x in update_list ]
+        all_ids = add_ids
+        all_ids.extend(update_ids)
+
+        if options['collision'] != CALIBREONLY and \
+                (prefs['addtolists'] or prefs['addtoreadlists']):
+            self._update_reading_lists(all_ids,add=True)
         
         if len(add_list):
-            ## even shows up added to searchs.  Nice.
             self.gui.library_view.model().books_added(len(add_list))
             self.gui.library_view.model().refresh_ids(add_ids)
 
@@ -901,8 +911,6 @@ make_firstimage_cover:true
         print("all done, remove temp dir.")
         remove_dir(options['tdir'])
 
-        all_ids = add_ids
-        all_ids.extend(update_ids)
         if 'Count Pages' in self.gui.iactions and len(prefs['countpagesstats']) and len(all_ids):
             cp_plugin = self.gui.iactions['Count Pages']
             cp_plugin.count_statistics(all_ids,prefs['countpagesstats'])
@@ -917,7 +925,8 @@ make_firstimage_cover:true
 
         book_list = job.result
         good_list = filter(lambda x : x['good'], book_list)
-        bad_list = filter(lambda x : x['calibre_id'] and not x['good'], book_list)
+        bad_list = filter(lambda x : not x['good'], book_list)
+        print("book_list:%s"%book_list)
         payload = (good_list, bad_list, options)
         
         msg = '''
@@ -932,14 +941,14 @@ make_firstimage_cover:true
                 status = book['status']
             else:
                 status = 'Good'
-            htmllog = htmllog + '<tr><td>' + '</td><td>'.join([status,book['title'],", ".join(book['author']),book['comment'],book['url']]) + '</td></tr>'
+            htmllog = htmllog + '<tr><td>' + '</td><td>'.join([escapehtml(status),escapehtml(book['title']),escapehtml(", ".join(book['author'])),escapehtml(book['comment']),book['url']]) + '</td></tr>'
         
         for book in bad_list:
             if 'status' in book:
                 status = book['status']
             else:
                 status = 'Bad'
-            htmllog = htmllog + '<tr><td>' + '</td><td>'.join([status,book['title'],", ".join(book['author']),book['comment'],book['url']]) + '</td></tr>'
+            htmllog = htmllog + '<tr><td>' + '</td><td>'.join([escapehtml(status),escapehtml(book['title']),escapehtml(", ".join(book['author'])),escapehtml(book['comment']),book['url']]) + '</td></tr>'
         
         htmllog = htmllog + '</table></body></html>'
         
@@ -948,7 +957,6 @@ make_firstimage_cover:true
                 'FFDL log', 'FFDL download complete', msg,
                 show_copy_button=False)
         
-        
     def _do_download_list_update(self, payload):
         
         (good_list,bad_list,options) = payload
@@ -1012,8 +1020,9 @@ make_firstimage_cover:true
                     print("remove f:"+fmt)
                     db.remove_format(book['calibre_id'], fmt, index_is_id=True)#, notify=False
 
-        if prefs['addtolists'] or prefs['addtoreadlists']:
-            self._update_reading_lists([book_id],add=True)
+        # moved up so whole lists are done at once for efficiency.
+        # if prefs['addtolists'] or prefs['addtoreadlists']:
+        #     self._update_reading_lists([book_id],add=True)
                 
         return book_id
 
@@ -1047,6 +1056,7 @@ make_firstimage_cover:true
         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)
@@ -1418,3 +1428,6 @@ def get_url_list(urls):
     # set removes dups.
     return set(filter(f,urls.strip().splitlines()))
 
+def escapehtml(txt):
+    return txt.replace("&","&amp;").replace(">","&gt;").replace("<","&lt;")
+        

calibre-plugin/jobs.py

@@ -39,11 +39,12 @@ def do_download_worker(book_list, options,
 
     print(options['version'])
     total = 0
+    alreadybad = []
     # Queue all the jobs
     print("Adding jobs for URLs:")
     for book in book_list:
+        print("%s"%book['url'])
         if book['good']:
-            print("%s"%book['url'])
             total += 1
             args = ['calibre_plugins.fanfictiondownloader_plugin.jobs',
                     'do_download_for_worker',
@@ -58,6 +59,9 @@ def do_download_worker(book_list, options,
             # job._modified_date = modified_date
             # job._existing_isbn = existing_isbn
             server.add_job(job)
+        else:
+            # was already bad before the subprocess ever started.
+            alreadybad.append(book)
     
     # This server is an arbitrary_n job, so there is a notifier available.
     # Set the % complete to a small number to avoid the 'unavailable' indicator
@@ -90,11 +94,11 @@ def do_download_worker(book_list, options,
             print("Successfully downloaded:")
             for book in book_list:
                 if book['good']:
-                    print(book['title'])
+                    print("%s %s"%(book['title'],book['url']))
             print("\nUnsuccessful:")
             for book in book_list:
                 if not book['good']:
-                    print(book['title'])
+                    print("%s %s"%(book['title'],book['url']))
             break
 
     server.close()

defaults.ini

@@ -320,12 +320,13 @@ background_color: ffffff
 ## Allow customization of CSS.  Make sure to keep at least one space
 ## at the start of each line and to escape % to %%.  Also need
 ## background_color to be in the same section, if included in CSS.
-## 'adobe-text-layout: optimizeSpeed;' prevents hyphenation on newer Nooks
+## 'adobe-hyphenate: none;' prevents hyphenation on newer Nooks
+## STR(wG) (1.2.1+ for sure)
 output_css: 
  body { background-color: #%(background_color)s;
         text-align: justify;
         margin: 2%%;
-	adobe-text-layout: optimizeSpeed; }
+	adobe-hyphenate: none; }
  pre { font-size: x-small; }
  sml { font-size: small; }
  h1 { text-align: center; }
@@ -469,8 +470,9 @@ extratags: FanFiction,Testing,HTML
 #is_adult:true
 
 ## AO3 adapter defines a few extra metadata entries.
-extra_valid_entries:fandoms,freefromtags,ao3categories,comments,kudos,hits,bookmarks,collections
+extra_valid_entries:fandoms,freeformtags,freefromtags,ao3categories,comments,kudos,hits,bookmarks,collections
 fandoms_label:Fandoms
+freeformtags_label:Freeform Tags
 freefromtags_label:Freeform Tags
 ao3categories_label:AO3 Categories
 comments_label:Comments
@@ -479,11 +481,15 @@ hits_label:Hits
 collections_label:Collections
 bookmarks_label:Bookmarks
 
+## freeformtags was previously typo'ed as freefromtags.  This way,
+## freefromtags will still work for people who've used it.
+include_in_freefromtags:freeformtags
+
 ## adds to titlepage_entries instead of replacing it.
-#extra_titlepage_entries: fandoms,freefromtags,ao3categories,comments,kudos,hits,bookmarks
+#extra_titlepage_entries: fandoms,freeformtags,ao3categories,comments,kudos,hits,bookmarks
 
 ## adds to include_subject_tags instead of replacing it.
-#extra_subject_tags:fandoms,freefromtags,ao3categories
+#extra_subject_tags:fandoms,freeformtags,ao3categories
 
 [ashwinder.sycophanthex.com]
 ## Site dedicated to these categories/characters/ships
@@ -514,6 +520,15 @@ extracategories:Blood Ties
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+[buffynfaith.net]
+## Site dedicated to these categories/characters/ships
+extracategories:Buffy: The Vampire Slayer
+
+## 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
+
 [castlefans.org]
 ## Site dedicated to these categories/characters/ships
 extracategories:Castle
@@ -608,6 +623,10 @@ cliches_label:Character Cliches
 #extra_logpage_entries: themes,timeline,cliches
 #extra_subject_tags: themes,timeline,cliches
 
+[efiction.esteliel.de]
+## Site dedicated to these categories/characters/ships
+extracategories:Lord of the Rings
+
 [erosnsappho.sycophanthex.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
@@ -684,6 +703,19 @@ extracharacters:Hermione Granger
 ## Site dedicated to these categories/characters/ships
 extracategories:Highlander
 
+[imagine.e-fic.com]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## 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
+
 [indeath.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:In Death
@@ -769,6 +801,22 @@ extracategories:One Direction
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+[pommedesang.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Anita Blake Vampire Hunter 
+
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
+#is_adult:true
+
 [ponyfictionarchive.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:My Little Pony: Friendship is Magic
@@ -921,6 +969,14 @@ extracategories:InuYasha
 extracharacters:Sesshoumaru,Kagome
 extraships:Sesshoumaru/Kagome
 
+[www.dotmoon.net]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
 [www.efpfanfic.net]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -1015,6 +1071,10 @@ extracategories:Harry Potter
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[www.henneth-annun.net]
+## Site dedicated to these categories/characters/ships
+extracategories:The Hobbit
+
 [www.hpfandom.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
@@ -1094,10 +1154,23 @@ extraships:Harry Potter/Ginny Weasley
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
 
+[www.potterfics.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 [www.prisonbreakfic.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:Prison Break
 
+[www.psychfic.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Psych
+
+## 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.qaf-fic.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Queer as Folk
@@ -1107,6 +1180,16 @@ extracategories:Queer as Folk
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[www.restrictedsection.org]
+extracategories:Harry Potter
+extragenres:Erotica
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
 [www.scarvesandcoffee.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:Glee
@@ -1256,12 +1339,6 @@ extracategories:Stargate: Atlantis
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
-[www.yourfanfiction.com]
-## Some sites do not require a login, but do require the user to
-## confirm they are adult for adult content.  In commandline version,
-## this should go in your personal.ini, not defaults.ini.
-#is_adult:true
-
 [overrides]
 ## It may sometimes be useful to override all of the specific format,
 ## site and site:format sections in your private configuration.  For

fanficdownloader/adapters/__init__.py

@@ -73,7 +73,6 @@ import adapter_iketernalnet
 import adapter_onedirectionfanfictioncom
 import adapter_prisonbreakficnet
 import adapter_storiesofardacom
-import adapter_yourfanfictioncom
 import adapter_samdeanarchivenu
 import adapter_destinysgatewaycom
 import adapter_ncisfictionnet
@@ -107,6 +106,15 @@ import adapter_indeathnet
 import adapter_jlaunlimitedcom
 import adapter_qafficcom
 import adapter_efpfanficnet
+import adapter_potterficscom
+import adapter_efictionestelielde
+import adapter_dotmoonnet
+import adapter_pommedesangcom
+import adapter_restrictedsectionorg
+import adapter_imagineeficcom
+import adapter_buffynfaithnet
+import adapter_psychficcom
+import adapter_hennethannunnet
 
 ## 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

@@ -82,7 +82,8 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
 
     def getSiteURLPattern(self):
         # http://archiveofourown.org/collections/Smallville_Slash_Archive/works/159770
-        return re.escape("http://")+re.escape(self.getSiteDomain())+r"(/collections/[^/]+)?/works/(?P<id>\d+)"
+        # Discard leading zeros from story ID numbers--AO3 doesn't use them in it's own chapter URLs.
+        return re.escape("http://")+re.escape(self.getSiteDomain())+r"(/collections/[^/]+)?/works/0*(?P<id>\d+)"
         
     ## Login
     def needToLoginCheck(self, data):
@@ -217,7 +218,7 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
         if a != None:
             genres = a.findAll('a',{'class':"tag"})
             for genre in genres:
-                self.story.addToList('freefromtags',genre.string)
+                self.story.addToList('freeformtags',genre.string)
                 self.story.addToList('genre',genre.string)
                 
         a = metasoup.find('dd',{'class':"category tags"})

fanficdownloader/adapters/adapter_archiveskyehawkecom.py

@@ -66,14 +66,16 @@ class ArchiveSkyeHawkeComAdapter(BaseSiteAdapter):
         # The site domain.  Does have www here, if it uses it.
         return 'archive.skyehawke.com'
 
+    @classmethod
+    def getAcceptDomains(cls):
+        # mobile.fimifction.com isn't actually a valid domain, but we can still get the story id from URLs anyway
+        return ['archive.skyehawke.com','www.skyehawke.com']
+
     def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/story.php?no=1234"
+        return "http://archive.skyehawke.com/story.php?no=1234 http://www.skyehawke.com/archive/story.php?no=1234  http://skyehawke.com/archive/story.php?no=1234"
 
     def getSiteURLPattern(self):
-        return re.escape("http://"+self.getSiteDomain()+"/story.php?no=")+r"\d+$"
-
-
-        
+        return re.escape("http://")+r"(archive|www)\.skyehawke\.com/(archive/)?story\.php\?no=\d+$"
 
     ## Getting the chapter list and the meta data, plus 'is adult' checking.
     def extractChapterUrlsAndMetadata(self):

fanficdownloader/adapters/adapter_buffynfaithnet.py

@@ -0,0 +1,290 @@
+# -*- 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
+import cookielib as cl
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+
+# This function is called by the downloader in all adapter_*.py files
+# in this dir to register the adapter class.  So it needs to be
+# updated to reflect the class below it.  That, plus getSiteDomain()
+# take care of 'Registering'.
+def getClass():
+    return BuffyNFaithNetAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class BuffyNFaithNetAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+        
+        self.setHeader()
+        
+        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 correct
+        m = re.match(self.getSiteURLPattern(),url)
+        if m:
+            self.story.setMetadata('storyId',m.group('id'))
+            logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+            # normalized story URL. gets rid of chapter if there, left with ch 1 URL on this site
+            nurl = "http://"+self.getSiteDomain()+"/fanfictions/index.php?act=vie&id="+self.story.getMetadata('storyId')
+            self._setURL(nurl)
+            #argh, this mangles the ampersands I need on metadata['storyUrl']
+            #will set it this way
+            self.story.setMetadata('storyUrl',nurl,condremoveentities=False)
+        else:
+            raise exceptions.InvalidStoryURL(url,
+                                             self.getSiteDomain(),
+                                             self.getSiteExampleURLs())
+        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','bnfnet')
+
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'buffynfaith.net'
+
+    @classmethod
+    def stripURLParameters(cls,url):
+        "Only needs to be overriden if URL contains more than one parameter"
+        ## This adapter needs at least two parameters left on the URL, act and id
+        return re.sub(r"(\?act=(vie|ovr)&id=\d+)&.*$",r"\1",url)
+    
+    def setHeader(self):
+        "buffynfaith.net wants a Referer for images.  Used both above and below(after cookieproc added)"
+        self.opener.addheaders = [('Referer', 'http://'+self.getSiteDomain()+'/')]
+        
+    def getSiteExampleURLs(self):
+        return "http://buffynfaith.net/fanfictions/index.php?act=vie&id=963 http://buffynfaith.net/fanfictions/index.php?act=vie&id=949 http://buffynfaith.net/fanfictions/index.php?act=vie&id=949&ch=2"
+
+    def getSiteURLPattern(self):
+        #http://buffynfaith.net/fanfictions/index.php?act=vie&id=963
+        #http://buffynfaith.net/fanfictions/index.php?act=vie&id=949
+        #http://buffynfaith.net/fanfictions/index.php?act=vie&id=949&ch=2
+        p = re.escape("http://"+self.getSiteDomain()+"/fanfictions/index.php?act=")+\
+            r"(vie|ovr)&id=(?P<id>\d+)(&ch=(?P<ch>\d+))?$"
+        return p
+
+    def extractChapterUrlsAndMetadata(self):
+
+        dateformat = "%d %B %Y"
+        url = self.url
+        logger.debug("URL: "+url)
+        
+        #set a cookie to get past adult check
+        if self.is_adult or self.getConfig("is_adult"):
+            cookieproc = urllib2.HTTPCookieProcessor()
+            cookie = cl.Cookie(version=0, name='my_age', value='yes',
+                               port=None, port_specified=False,
+                               domain=self.getSiteDomain(), domain_specified=False, domain_initial_dot=False,
+                               path='/', path_specified=True,
+                               secure=False,
+                               expires=time.time()+10000,
+                               discard=False,
+                               comment=None,
+                               comment_url=None,
+                               rest={'HttpOnly': None},
+                               rfc2109=False)
+            cookieproc.cookiejar.set_cookie(cookie)
+            self.opener = urllib2.build_opener(cookieproc)        
+            self.setHeader()
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        #print data
+
+        if "ADULT CONTENT WARNING" in data: 
+            raise exceptions.AdultCheckRequired(self.url)
+
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        #stuff in <head>: description
+        svalue = soup.head.find('meta',attrs={'name':'description'})['content']
+        #self.story.setMetadata('description',svalue)
+        self.setDescription(url,svalue)
+        
+        #useful stuff in rest of doc, all contained in this:
+        doc = soup.body.find('div', id='my_wrapper')
+        
+        #first the site category (more of a genre to me, meh) and title, in this element:
+        mt = doc.find('div',attrs={'class':'maintitle'})
+        self.story.addToList('genre',mt.findAll('a')[1].string)
+        self.story.setMetadata('title',mt.findAll('a')[1].nextSibling[len('&nbsp;&raquo;&nbsp;'):])
+        del mt
+
+        #the actual category, for me, is 'Buffy: The Vampire Slayer'
+        #self.story.addToList('category','Buffy: The Vampire Slayer')
+        #No need to do it here, it is better to set it in in plugin-defaults.ini and defaults.ini
+        
+        #then a block that sits in a table cell like so:
+        #(contains a lot of metadata)
+        mblock = doc.find('td', align='left', width = '70%').contents
+        while len(mblock) > 0:
+            i = mblock.pop(0)
+            if 'Author:' in i.string:
+                #drop empty space
+                mblock.pop(0)
+                #get author link
+                a = mblock.pop(0)
+                authre = re.escape('./index.php?act=bio&id=')+'(?P<authid>\d+)'
+                m = re.match(authre,a['href'])
+                self.story.setMetadata('author',a.string)
+                self.story.setMetadata('authorId',m.group('authid'))
+                authurl = u'http://%s/fanfictions/index.php?act=bio&id=%s' % ( self.getSiteDomain(),
+                                            self.story.getMetadata('authorId'))
+                self.story.setMetadata('authorUrl',authurl,condremoveentities=False)
+                #drop empty space
+                mblock.pop(0)
+            if 'Rating:' in i.string:
+                self.story.setMetadata('rating',mblock.pop(0).strip())
+            if 'Published:' in i.string:
+                date = mblock.pop(0).strip()
+                #get rid of 'st', 'nd', 'rd', 'th' after day number
+                date = date[0:2]+date[4:]
+                self.story.setMetadata('datePublished',makeDate(date, dateformat))
+            if 'Last Updated:' in i.string:
+                date = mblock.pop(0).strip()
+                #get rid of 'st', 'nd', 'rd', 'th' after day number
+                date = date[0:2]+date[4:]
+                self.story.setMetadata('dateUpdated',makeDate(date, dateformat))
+            if 'Genre:' in i.string:
+                genres = mblock.pop(0).strip()
+                genres = genres.split('/')
+                for genre in genres: self.story.addToList('genre',genre)
+            #end ifs
+        #end while
+
+        # Find the chapter selector 
+        select = soup.find('select', { 'name' : 'ch' } )
+         
+        if select is None:
+           # no selector found, so it's a one-chapter story.
+           #self.chapterUrls.append((self.story.getMetadata('title'),url))
+           self.chapterUrls.append((self.story.getMetadata('title'),url))
+        else:
+            allOptions = select.findAll('option')
+            for o in allOptions:
+                url = u'http://%s/fanfictions/index.php?act=vie&id=%s&ch=%s' % ( self.getSiteDomain(),
+                                            self.story.getMetadata('storyId'),
+                                            o['value'])
+                title = u"%s" % o
+                title = stripHTML(title)
+                ts = title.split(' ',1)
+                title = ts[0]+'. '+ts[1]
+                self.chapterUrls.append((title,url))
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+        
+        ## Go scrape the rest of the metadata from the author's page.
+        data = self._fetchUrl(self.story.getMetadata('authorUrl'))
+        soup = bs.BeautifulSoup(data)
+        #find the story link and its parent div
+        storya = soup.find('a',{'href':self.story.getMetadata('storyUrl')})
+        storydiv = storya.parent
+        #warnings come under a <spawn> tag. Never seen that before...
+        #appears to just be a line of freeform text, not necessarily a list
+        #optional
+        spawn = storydiv.find('spawn',{'id':'warnings'})
+        if spawn is not None:
+            warns = spawn.nextSibling.strip()
+            self.story.addToList('warnings',warns)
+        #some meta in spans - this should get all, even the ones jammed in a table
+        spans = storydiv.findAll('span')
+        for s in spans:
+            if s.string == 'Ship:':
+                list = s.nextSibling.strip().split()
+                self.story.extendList('ships',list)
+            if s.string == 'Characters:':
+                list = s.nextSibling.strip().split(',')
+                self.story.extendList('characters',list)
+            if s.string == 'Status:':
+                st = s.nextSibling.strip()
+                self.story.setMetadata('status',st)
+            if s.string == 'Words:':
+                st = s.nextSibling.strip()
+                self.story.setMetadata('numWords',st)
+
+        #reviews - is this worth having?
+        #ffnet adapter gathers it, don't know if anything else does
+        #or if it's ever going to be used!
+        a = storydiv.find('a',{'id':'bold-blue'})
+        if a:
+            revs = a.nextSibling.strip()[1:-1]
+            self.story.setMetadata('reviews',st)
+        else:
+            revs = '0'
+            self.story.setMetadata('reviews',st)
+
+    # 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' : 'fanfiction'})
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+        
+        #remove all the unnecessary bookmark tags
+        [s.extract() for s in div('div',{'class':"tiny_box2"})]
+        
+        #is there a review link?
+        r = div.find('a',href=re.compile(re.escape("./index.php?act=irv")+".*$"))
+        if r is not None:
+        #remove the review link and its parent div
+            r.parent.extract()
+        
+        #There might also be a link to the sequel on the last chapter
+        #I'm inclined to keep it in, but the URL needs to be changed from relative to absolute
+        #Shame there isn't proper series metadata available
+        #(I couldn't find it anyway)
+        s = div.find('a',href=re.compile(re.escape("./index.php?act=ovr")+".*$"))
+        if s is not None:
+            s['href'] = 'http://'+self.getSiteDomain()+'/fanfictions'+s['href'][1:]
+
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_dotmoonnet.py

@@ -0,0 +1,216 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2013 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+logger = logging.getLogger(__name__)
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return DotMoonNetAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class DotMoonNetAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL. www.dotmoon.net/library_view.php?storyid=3
+        self._setURL('http://' + self.getSiteDomain() + '/library_view.php?storyid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','dotm')
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%Y-%m-%d"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'www.dotmoon.net'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/library_view.php?storyid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/library_view.php?storyid=")+r"\d+$"
+
+    ## Login seems to be reasonably standard across eFiction sites.
+    def needToLoginCheck(self, data):
+        if 'You must be logged in to read adult-rated stories' in data \
+                or 'Password incorrect' in data \
+                or "That username does not exist" in data:
+            return True
+        else:
+            return False
+        
+    def performLogin(self, url):
+        params = {}
+
+        if self.password:
+            params['user'] = self.username
+            params['passwrd'] = self.password
+        else:
+            params['user'] = self.getConfig("username")
+            params['passwrd'] = self.getConfig("password")
+
+        loginUrl = 'http://' + self.getSiteDomain() + '/board/index.php'
+        
+        logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
+                                                              params['user']))
+    
+        d = self._fetchUrl(loginUrl+'?action=login2&user='+params['user']+'&passwrd='+params['passwrd'])
+        d = self._fetchUrl(loginUrl)
+    
+        if "Show unread posts since last visit" not in d : #Member Account
+            logger.info("Failed to login to URL %s as %s" % (loginUrl,
+                                                              params['user']))
+            raise exceptions.FailedToLogin(url,params['user'])
+            return False
+        else:
+            return True
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        if self.needToLoginCheck(data):
+            # need to log in for this one.
+            self.performLogin(url)
+            data = self._fetchUrl(url)
+            
+        if "Invalid story ID" in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Invalid story ID.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        body=soup.findAll('body')[1]
+        body.find('table').extract()
+        
+        ## Title
+        a = body.find('b')
+        self.story.setMetadata('title',a.string)
+        
+        # Find authorid and URL from... author url. http://www.dotmoon.net/board/index.php?action=profile;u=1'
+        a = body.find('a', href=re.compile(r"index.php\?action=profile;u=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[2])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # Find the chapters: 'library_storyview.php?chapterid=3
+        chapters=body.findAll('a', href=re.compile(r"library_storyview.php\?chapterid=\d+$"))
+        if len(chapters)==0:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: No php/html chapters found.")
+        if len(chapters)==1:
+            self.chapterUrls.append((self.story.getMetadata('title'),'http://'+self.host+'/'+chapters[0]['href']))
+        else:
+            for chapter in chapters:
+                # just in case there's tags, like <i> in chapter titles.
+                self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # other tags
+
+        labels = body.find('table', {'width':'390'}).findAll('td')
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+            
+            if label != None:
+                if 'Fandom' in label:
+                    self.story.addToList('category',value.string)
+                
+                if 'Setting' in label:
+                    self.story.addToList('genre',value.string)
+                
+                if 'Genre' in label:
+                    self.story.addToList('genre',value.string)
+                
+                if 'Style' in label:
+                    self.story.addToList('genre',value.string)
+                
+                if 'Rating' in label:
+                    self.story.addToList('rating',value.string)
+                
+                if 'Created' in label:
+                    self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+                if 'Updated' in label:
+                    self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+        
+                if 'Status' in label:
+                    if 'Completed' in value.string:
+                        self.story.setMetadata('status', 'Completed')
+                    else:
+                        self.story.setMetadata('status', 'In-Progress')
+                        
+        table=body.findAll('table', {'width':'400'})[1].find('td')
+        self.setDescription(url,stripHTML(table).split('Summary: ')[1])
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logger.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('blockquote')
+        div.name='div'
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_efictionestelielde.py

@@ -0,0 +1,221 @@
+# -*- 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 EfictionEstelielDeAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class EfictionEstelielDeAdapter(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.
+        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','eesd')
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%B %d, %Y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'efiction.esteliel.de'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+       
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title and author
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+
+        pagetitle = soup.find('div',{'id':'pagetitle'})
+        ## Title
+        a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',a.string)
+        
+        # Find authorid and URL from... author url.
+        a = 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)
+
+        # 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.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        # utility method
+        def defaultGetattr(d,k):
+            try:
+                return d[k]
+            except:
+                return ""
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        list = soup.find('div', {'class':'listbox'})
+        labelspan=list.find('span',{'class':'label'})
+        value = labelspan.nextSibling
+        label = labelspan.string
+        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)
+        
+        labels = list.findAll('b')
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+
+            if 'Summary' in label:
+                ## Everything until the next span class='label'
+                svalue = ""
+                while 'Rating' not in str(value):
+                    svalue += str(value)
+                    value = value.nextSibling
+                self.setDescription(url,svalue)
+                #self.story.setMetadata('description',stripHTML(svalue))
+
+            if 'Rating' in label:
+                self.story.setMetadata('rating', value)
+
+            if 'Words' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Category' in label:
+                cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+                for cat in cats:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+                for char in chars:
+                    self.story.addToList('characters',char.string)
+
+            if 'Completed' in label:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Updated' in label:
+                # there's a stray [ at the end.
+                #value = value[0:-1]
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+
+        try:
+            if list.find('a', href=re.compile(r"series.php")) != None:
+                for series in asoup.findAll('a', href=re.compile(r"series.php\?seriesid=\d+")):
+                    # Find Series name from series URL.
+                    series_url = 'http://'+self.host+'/'+series['href']
+                    # use BeautifulSoup HTML parser to make everything easier to find.
+                    seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+                    storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+                    i=1
+                    for a in storyas:
+                        if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                            name=seriessoup.find('div', {'id' : 'pagetitle'})
+                            name.find('a').extract()
+                            self.setSeries(name.text.split(' by[')[0], i)
+                            i=0
+                            break
+                        i+=1
+                    if i == 0:
+                        break
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logger.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+                                     
+        div = soup.find('div', {'id' : 'story'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_fimfictionnet.py

@@ -81,8 +81,10 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
             apiResponse = urllib2.urlopen("http://www.fimfiction.net/api/story.php?story=%s" % (self.story.getMetadata("storyId"))).read()
             apiData = json.loads(apiResponse)
             
-            # Unfortunately, we still need to load the story index page to parse the characters
+            # Unfortunately, we still need to load the story index
+            # page to parse the characters.  And chapters, now, too.
             data = self._fetchUrl(self.url)
+            soup = bs.BeautifulSoup(data)
         except urllib2.HTTPError, e:
             if e.code == 404:
                 raise exceptions.StoryDoesNotExist(self.url)
@@ -95,9 +97,6 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
         if "/images/missing_story.png" in data:
             raise exceptions.StoryDoesNotExist(self.url)
         
-        if "Invalid story id" in apiData.values():
-            raise exceptions.StoryDoesNotExist(self.url)
-        
         if "This story has been marked as having adult content." in data:
             raise exceptions.AdultCheckRequired(self.url)
         
@@ -112,18 +111,39 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
             else:
                 raise exceptions.FailedToLogin(self.url,"Story requires individual password",passwdonly=True)
          
+        if "Invalid story id" in apiData.values():
+            raise exceptions.StoryDoesNotExist(self.url)
+        
         storyMetadata = apiData["story"]    
             
-        self.story.setMetadata("title", storyMetadata["title"])
+        ## Title
+        a = soup.find('a', href=re.compile(r'^/story/'+self.story.getMetadata('storyId')))
+        self.story.setMetadata('title',a.string)
+        
+        # self.story.setMetadata("title", storyMetadata["title"])
+        # if not storyMetadata["title"]:
+        #     raise exceptions.FailedToDownload("%s doesn't have a title in the API.  This is a known fimfiction.net bug with titles containing ."%self.url)
+        
         self.story.setMetadata("author", storyMetadata["author"]["name"])
         self.story.setMetadata("authorId", storyMetadata["author"]["id"])
         self.story.setMetadata("authorUrl", "http://%s/user/%s" % (self.getSiteDomain(), storyMetadata["author"]["name"]))
+
+        # chapters = [{"chapterTitle": chapter["title"], "chapterURL": chapter["link"]} for chapter in storyMetadata["chapters"]]
         
-        chapters = [{"chapterTitle": chapter["title"], "chapterURL": chapter["link"]} for chapter in storyMetadata["chapters"]]
-        for chapter in chapters:
-            self.chapterUrls.append((chapter["chapterTitle"], chapter["chapterURL"]))
-        self.story.setMetadata("numChapters", len(self.chapterUrls))
+        # ## this is bit of a kludge based on the assumption all the
+        # ## 'bad' chapters will be at the end.
+        # ## limit down to the number of chapters reported by chapter_count.
+        # chapters = chapters[:storyMetadata["chapter_count"]] 
         
+        # for chapter in chapters:
+        #     self.chapterUrls.append((chapter["chapterTitle"], chapter["chapterURL"]))
+        # self.story.setMetadata("numChapters", len(self.chapterUrls))
+
+        for chapter in soup.findAll('a',{'class':'chapter_link'}):
+            self.chapterUrls.append((stripHTML(chapter), 'http://'+self.host+chapter['href']))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+            
         # In the case of fimfiction.net, possible statuses are 'Completed', 'Incomplete', 'On Hiatus' and 'Cancelled'
         # For the sake of bringing it in line with the other adapters, 'Incomplete' becomes 'In-Progress'
         # and 'Complete' beomes 'Completed'. 'Cancelled' seems an important enough (not to mention more strictly true) 
@@ -133,7 +153,17 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
         status = storyMetadata["status"].replace("Incomplete", "In-Progress").replace("Complete", "Completed")
         self.story.setMetadata("status", status)
         self.story.setMetadata("rating", storyMetadata["content_rating_text"])
-            
+
+        ## Warnings aren't included in the API.
+        bottomli = soup.find('li',{'class':'bottom'})
+        if bottomli:
+            bottomspans = bottomli.findAll('span')
+            # the first span in bottom is the rating, obtained above.
+            if bottomspans and len(bottomspans) > 1:
+                for warning in bottomspans[1:]:
+                    self.story.addToList('warnings',warning.string)
+                
+        
         for category in storyMetadata["categories"]:
             if storyMetadata["categories"][category]:
                 self.story.addToList("genre", category) 
@@ -163,11 +193,11 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
         rawDateUpdated = storyMetadata["date_modified"]
         self.story.setMetadata("dateUpdated", datetime.fromtimestamp(rawDateUpdated))
 
-        soup = bs.BeautifulSoup(data).find("div", {"class":"story"})
+        chars = soup.find("div", {"class":"story"})
         # fimfic stopped putting the char name on or around the char
         # icon now for some reason.  Pull it from the image name with
         # some heuristics.
-        for character in [character_icon["src"] for character_icon in soup.findAll("img", {"class":"character_icon"})]:
+        for character in [character_icon["src"] for character_icon in chars.findAll("img", {"class":"character_icon"})]:
             # //static.fimfiction.net/images/characters/twilight_sparkle.png
             # 5th split /, remove last four, replace _, capitolize every word(title())
             char = character.split('/')[5][:-4].replace('_',' ').title()

fanficdownloader/adapters/adapter_hennethannunnet.py

@@ -0,0 +1,171 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2013 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+logger = logging.getLogger(__name__)
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return HennethAnnunNetAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class HennethAnnunNetAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/stories/chapter.cfm?stid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','htan')
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%m/%d/%y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'www.henneth-annun.net'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/stories/chapter.cfm?stid=1234"
+
+    def getSiteURLPattern(self):
+        return "http://"+self.getSiteDomain()+"/stories/chapter(_view)?.cfm\?stid="+r"\d+$"
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+            
+        if "We're sorry. This story is not available." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: This story is not available.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        a = soup.find('h2', {'id':'page_heading'})
+        self.story.setMetadata('title',a.string)
+
+        # Find the chapters: chapter_view.cfm?stid=6663&spordinal=1" 
+        for chapter in soup.findAll('a', href=re.compile(r'chapter_view.cfm\?stid='+self.story.getMetadata('storyId')+"&spordinal=\d+$")):
+            # just in case there's tags, like <i> in chapter titles.
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/stories/'+chapter['href']))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+        
+        self.story.setMetadata('numWords', soup.find('tr', {'class':'foot'}).findAll('td')[1].text)
+
+        self.setDescription(url,soup.find('div', {'id':'summary'}))
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        info = soup.find('div', {'id':'storyinformation'})
+        labels=info.findAll('b')
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+                
+            if 'Completion' in label:
+                if 'Complete' in value.string:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Rating' in label:
+                self.story.setMetadata('rating', value.string)
+
+            if 'Era:' in label:
+                self.story.addToList('category',value.string)
+
+            if 'Genre' in label:
+                self.story.addToList('genre',value.string)
+                
+        labels=info.findAll('strong')
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+            
+            if 'Author' in label:
+                value=value.nextSibling
+                self.story.setMetadata('authorId',value['href'].split('=')[1])
+                self.story.setMetadata('authorUrl','http://'+self.host+'/'+value['href'])
+                self.story.setMetadata('author',value.string)
+                
+            if 'Post' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Updated:' in label:
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+                
+        for char in soup.findAll('a', href=re.compile(r"/resources/bios_view.cfm\?scid=\d+")):
+            self.story.addToList('characters',stripHTML(char))
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logger.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div', {'class' : 'block chapter'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_imagineeficcom.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.
@@ -28,22 +28,15 @@ from .. import exceptions as exceptions
 from base_adapter import BaseSiteAdapter,  makeDate
 
 def getClass():
-    return YourFanfictionComAdapter
+    return ImagineEFicComAdapter
 
 # Class name has to be unique.  Our convention is camel case the
 # sitename with Adapter at the end.  www is skipped.
-class YourFanfictionComAdapter(BaseSiteAdapter):
+class ImagineEFicComAdapter(BaseSiteAdapter):
 
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
 
-        # yourfanfiction.com blocks the default user-agent.  However,
-        # when asked, they said it was just general anti-spam, not
-        # targeted as us and offered to 'whitelist our IP'.  Clearly,
-        # that wouldn't work, but it does let me do this in good
-        # conscience:
-        self.opener.addheaders = [('User-agent', 'FFDL/1.6')]
-
         self.decode = ["Windows-1252",
                        "utf8"] # 1252 is a superset of iso-8859-1.
                                # Most sites that claim to be
@@ -61,16 +54,16 @@ class YourFanfictionComAdapter(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','yff')
+        self.story.setMetadata('siteabbrev','ime')
 
         # 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 = "%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.yourfanfiction.com'
+        return 'imagine.e-fic.com'
 
     def getSiteExampleURLs(self):
         return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
@@ -78,6 +71,41 @@ class YourFanfictionComAdapter(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):
 
@@ -103,20 +131,12 @@ class YourFanfictionComAdapter(BaseSiteAdapter):
             else:
                 raise e
 
-        # The actual text that is used to announce you need to be an
-        # adult varies from site to site.  Again, print data before
-        # the title search to troubleshoot.
-            
-        # Since the warning text can change by warning level, let's
-        # look for the warning pass url.  ksarchive uses
-        # &warning= -- actually, so do other sites.  Must be an
-        # eFiction book.
-            
-        # viewstory.php?sid=1882&warning=4
-        # viewstory.php?sid=1654&ageconsent=ok&warning=5
-        #print data
-        #m = re.search(r"'viewstory.php\?sid=1882(&warning=4)'",data)
-        m = re.search(r"'viewstory.php\?sid=\d+((&ageconsent=ok)?&warning=\d+)'",data)
+        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"):
                 # We tried the default and still got a warning, so
@@ -124,8 +144,7 @@ class YourFanfictionComAdapter(BaseSiteAdapter):
                 # link and reload data.
                 addurl = m.group(1)
                 # correct stupid & error in url.
-                # explicitly put ageconsent because google appengine regexp doesn't include it for some reason.
-                addurl = addurl.replace("&","&")+'&ageconsent=ok'
+                addurl = addurl.replace("&","&")
                 url = self.url+'&index=1'+addurl
                 logger.debug("URL 2nd try: "+url)
 
@@ -142,17 +161,9 @@ class YourFanfictionComAdapter(BaseSiteAdapter):
         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.")
             
-        # because for some reason, this works while simple 'print data' errors on ascii conversion.
-        # loopdata = data
-        # chklen=5000
-        # while len(loopdata) > 0:
-        #     if len(loopdata) < 5000:
-        #         chklen = len(loopdata)
-        #     logger.info("loopdata: %s" % loopdata[:chklen])
-        #     loopdata = loopdata[chklen:]
-            
         # 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.
         
@@ -182,6 +193,7 @@ class YourFanfictionComAdapter(BaseSiteAdapter):
                 return d[k]
             except:
                 return ""
+                
 
         # <span class="label">Rated:</span> NC-17<br /> etc
         labels = soup.findAll('span',{'class':'label'})
@@ -192,11 +204,9 @@ class YourFanfictionComAdapter(BaseSiteAdapter):
             if 'Summary' in label:
                 ## Everything until the next span class='label'
                 svalue = ""
-                while value and not defaultGetattr(value,'class') == 'label':
+                while not defaultGetattr(value,'class') == 'label':
                     svalue += str(value)
                     value = value.nextSibling
-                # sometimes poorly formated desc (<p> w/o </p>) leads
-                # to all labels being included.
                 self.setDescription(url,svalue)
                 #self.story.setMetadata('description',stripHTML(svalue))
 
@@ -217,17 +227,12 @@ class YourFanfictionComAdapter(BaseSiteAdapter):
                     self.story.addToList('characters',char.string)
 
             if 'Genre' in label:
-                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=5'))
-                for genre in genres:
-                    self.story.addToList('genre',genre.string)
-                    
-            if 'Tags' in label:
-                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=7'))
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
                 for genre in genres:
                     self.story.addToList('genre',genre.string)
 
             if 'Warnings' in label:
-                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=6'))
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
                 for warning in warnings:
                     self.story.addToList('warnings',warning.string)
 
@@ -241,8 +246,6 @@ class YourFanfictionComAdapter(BaseSiteAdapter):
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
             
             if 'Updated' in label:
-                # there's a stray [ at the end.
-                #value = value[0:-1]
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
 
         try:

fanficdownloader/adapters/adapter_pommedesangcom.py

@@ -0,0 +1,298 @@
+# -*- 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 PommeDeSangComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class PommeDeSangComAdapter(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'))
+        
+        # pommedesang.com has two 'sections', shown in URL as
+        # 'efiction' and 'sds' that change how things should be
+        # handled.
+        # http://pommedesang.com/efiction/viewstory.php?sid=1234
+        # http://pommedesang.com/sds/viewstory.php?sid=1234
+        self.section=self.parsedUrl.path.split('/',)[1]
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/'+self.section+'/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','pmds')
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        if 'efiction' in self.section:
+            self.dateformat = "%b %d, %Y"
+        else:
+            self.dateformat = "%m/%d/%y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'pommedesang.com'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/efiction/viewstory.php?sid=1234 http://"+self.getSiteDomain()+"/sds/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return r"http://"+self.getSiteDomain()+"/(efiction|sds)?/viewstory.php\?sid=\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() + '/'+self.section+'/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=5"
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'+addurl
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        if self.needToLoginCheck(data):
+            # need to log in for this one.
+            self.performLogin(url)
+            data = self._fetchUrl(url)
+
+        m = re.search(r"'viewstory.php\?sid=\d+((?:&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.")
+            
+        # 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('viewstory.php\?sid=\d+'))
+        self.story.setMetadata('title',a.string)
+        
+        # Find authorid and URL from... author url.
+        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # Find the chapters:
+        for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
+            # just in case there's tags, like <i> in chapter titles.
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+self.section+'/'+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 ""
+                
+# 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
+            label = labelspan.string
+
+            if 'Summary' in label:
+                ## Everything until the next span class='label'
+                svalue = ""
+                while not defaultGetattr(value,'class') == 'label':
+                    svalue += str(value)
+                    value = value.nextSibling
+                self.setDescription(url,svalue)
+                #self.story.setMetadata('description',stripHTML(svalue))
+
+            if 'Rated' in label:
+                self.story.setMetadata('rating', value)
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Categories' in label:
+                cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+                for cat in cats:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+                for char in chars:
+                    self.story.addToList('characters',char.string)
+
+            if 'Genre' in label:
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1')) # XXX
+                for genre in genres:
+                    self.story.addToList('genre',genre.string)
+
+            if 'Warnings' in label:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
+                for warning in warnings:
+                    self.story.addToList('warnings',warning.string)
+
+            if 'Completed' in label:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Updated' in label:
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/'+self.section+'/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            # can't use ^viewstory...$ in case of higher rated stories with javascript href.
+            storyas = seriessoup.findAll('a', href=re.compile('viewstory.php\?sid=\d+'))
+            i=1
+            for a in storyas:
+                # skip 'report this' and 'TOC' links
+                if 'contact.php' not in a['href'] and 'index' not in a['href']:
+                    if ('viewstory.php?sid='+self.story.getMetadata('storyId')) in a['href']:
+                        self.setSeries(series_name, i)
+                        break
+                    i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logger.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div', {'id' : 'story'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_potterficscom.py

@@ -0,0 +1,247 @@
+# -*- 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 datetime
+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
+
+# This function is called by the downloader in all adapter_*.py files
+# in this dir to register the adapter class.  So it needs to be
+# updated to reflect the class below it.  That, plus getSiteDomain()
+# take care of 'Registering'.
+def getClass():
+    return PotterFicsComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class PotterFicsComAdapter(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 correct
+        m = re.match(self.getSiteURLPattern(),url)
+        if m:
+            self.story.setMetadata('storyId',m.group('id'))
+            logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+            # normalized story URL. gets rid of chapter if there, left with chapter index URL
+            nurl = "http://"+self.getSiteDomain()+"/historias/"+self.story.getMetadata('storyId')
+            self._setURL(nurl)
+        else:
+            raise exceptions.InvalidStoryURL(url,
+                                             self.getSiteDomain(),
+                                             self.getSiteExampleURLs())
+        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','potficscom')
+
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'www.potterfics.com'
+
+    def getSiteExampleURLs(self):
+        return \
+                "http://www.potterfics.com/historias/127583 "\
+                "http://www.potterfics.com/historias/127583/capitulo-1 "\
+                "http://www.potterfics.com/historias/127583/capitulo-4 "\
+                "http://www.potterfics.com/historias/92810 "\
+                "http://www.potterfics.com/historias/111194"
+
+    def getSiteURLPattern(self):
+        #http://www.potterfics.com/historias/127583
+        #http://www.potterfics.com/historias/127583/capitulo-1
+        #http://www.potterfics.com/historias/127583/capitulo-4
+        #http://www.potterfics.com/historias/92810              -> Complete story
+        #http://www.potterfics.com/historias/111194             -> Complete, single chap
+        p = re.escape("http://"+self.getSiteDomain()+"/historias/")+\
+            r"(?P<id>\d+)(/capitulo-(?P<ch>\d+))?/?$"
+        return p
+
+    def extractChapterUrlsAndMetadata(self):
+
+        #this converts '/historias/12345' to 'http://www.potterfics.com/historias/12345'
+        def makeAbsoluteURL(url):
+            if url[0] == '/':
+                url = 'http://'+self.getSiteDomain()+url
+            return url
+
+        #use this to get month numbers from Spanish months
+        SpanishMonths = {
+            'enero'      : '01',
+            'febrero'    : '02',
+            'marzo'      : '03',
+            'abril'      : '04',
+            'mayo'       : '05',
+            'junio'      : '06',
+            'julio'      : '07',
+            'agosto'     : '08',
+            'septiembre' : '09',
+            'octubre'    : '10',
+            'noviembre'  : '11',
+            'diciembre'  : '12'
+            }
+
+        url = self.url
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        #print data
+
+        #deal with adult content warnings - doesn't seem to apply to this site
+
+        #set constant meta for this site:
+        #Set Language = Spanish
+        self.story.setMetadata('language', 'Spanish')
+        #Set Category = Harry Potter
+        #  This is better done in plugin-defaults.ini and defaults.ini
+        #  by adding a section for this site with the line:
+        #  extracategories:Harry Potter
+        #self.story.addToList('category','Harry Potter')
+        
+        #get the rest of the meta
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        #self closing br and img present!
+        soup = bs.BeautifulSoup(data,selfClosingTags=('br','img'))
+    
+        #we want the second table directly under the body, contains all the metadata
+        table = soup.html.body.findAll('table', recursive=False)[1]
+        #within that, we want the second row, first cell
+        cell = table.tr.findNextSibling('tr').td
+
+        #find first metadata block
+        mb = cell.div.findNextSibling('div')
+        #Get meta...
+        self.story.setMetadata('title', mb.b.string)
+        #strip out brackets on rating
+        self.story.setMetadata('rating', mb.span.string[1:-1])
+        #Completion status is denoted by the presence of this image:
+        if mb.find('img',title="Historia terminada"):
+            self.story.setMetadata('status', 'Completed')
+        else:
+            self.story.setMetadata('status', 'In-Progress')
+
+        #find next metadata block
+        #author details
+        mb = mb.findNextSibling('div')
+        self.story.setMetadata('author', mb.b.a.string.strip())
+        self.story.setMetadata('authorUrl', makeAbsoluteURL(mb.b.a['href']))
+        self.story.setMetadata('authorId', self.story.getMetadata('authorUrl').split('/')[4])
+        #dates and times
+        mb = mb.find('span')
+        #posted/published = Escrita
+        date = mb.find(text=re.compile('Escrita el ')).strip().split()
+        year = int(date[7][:-1]) # need to remove the last char from year, it is a comma
+        month = int(SpanishMonths[date[5].lower()])
+        day = int(date[3])
+        time = date[8].split(':')
+        hour = int(time[0])
+        minute = int(time[1])
+        self.story.setMetadata('datePublished', datetime.datetime(year, month, day, hour, minute))
+        #updated = Actualizada
+        date = mb.find(text=re.compile('Actualizada el ')).strip().split()
+        year = int(date[7][:-1]) # need to remove the last char from year, it is a comma
+        month = int(SpanishMonths[date[5].lower()])
+        day = int(date[3])
+        time = date[8].split(':')
+        hour = int(time[0])
+        minute = int(time[1])
+        self.story.setMetadata('dateUpdated', datetime.datetime(year, month, day, hour, minute))
+        
+        mb = mb.span.findNextSibling('span').findNextSibling('span')
+        wc = mb.find(text=re.compile(' palabras en total')).strip()
+        self.story.setMetadata('numWords', wc.split()[0])
+        
+        #then we come to categories and genres. Oh dear. On this site, categories hold everything from genre, to ships, to crossovers.
+        #To make things worse, there is also another genre field, which often holds similar/duplicate info. Links to genre pages do not work
+        #though, so perhaps those will be phased out?
+        #for now, put them all into the genre list
+        links = mb.findAll('a',href=re.compile('/(categorias|generos)/\d+'))
+        genlist = [i.string.strip() for i in links]
+        self.story.extendList('genre',genlist)
+        
+        #get the chapter urls
+        #we can go back to the table cell we found before
+        #get its last element and work backwards to find the last ordered list on the page
+        list = cell.contents[len(cell)-1].findPrevious('ol')
+        chapters = []
+        revs = 0
+        chnum = 0
+        for li in list:
+            chnum += 1
+            chTitle = str(chnum) + '. ' + li.a.b.string.strip()
+            chURL = makeAbsoluteURL(li.a['href'])
+            chapters.append((chTitle,chURL))
+            #Get reviews, add to total
+            revs += int(li.div.a.string.split()[0])
+        
+        self.chapterUrls.extend(chapters)
+        self.story.setMetadata('numChapters', len(chapters))
+        self.story.setMetadata('reviews', revs)
+        
+        #Now for the description... this may be tricky...
+        #if it is there (doesn't have to be), it will be before the chapter list,
+        #separated by a horizontal rule, and after the google ad bar
+        
+        #get list's parent div
+        mb = list.parent
+        #get the div before that, will either be the description, or the google ad bar
+        mb = mb.findPreviousSibling('div')
+        if 'google_ad_client' in str(mb):
+            #couldn't find description, leaving it blank
+            pass
+        else:
+            self.setDescription(url,mb)
+        
+    # 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','img'))
+        
+        div = soup.find('div', {'id' : 'cuerpoHistoria'})
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+        
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_psychficcom.py

@@ -0,0 +1,246 @@
+# -*- 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 PsychFicComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class PsychFicComAdapter(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.
+        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','psyf')
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%B %d, %Y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'www.psychfic.com'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        if self.is_adult or self.getConfig("is_adult"):
+            # Weirdly, different sites use different warning numbers.
+            # If the title search below fails, there's a good chance
+            # you need a different number.  print data at that point
+            # and see what the 'click here to continue' url says.
+            addurl = "&ageconsent=ok&warning=4"
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'+addurl
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        m = re.search(r"'viewstory.php\?sid=\d+((?:&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.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',a.string)
+        
+        # Find authorid and URL from... author url.
+        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # Find the chapters:
+        for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
+            # just in case there's tags, like <i> in chapter titles.
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        # utility method
+        def defaultGetattr(d,k):
+            try:
+                return d[k]
+            except:
+                return ""
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        labels = soup.findAll('span',{'class':'label'})
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.text
+
+            if 'Summary' in label:
+                ## Everything until the next span class='label'
+                svalue = ""
+                while not defaultGetattr(value,'class') == 'label':
+                    svalue += str(value)
+                    value = value.nextSibling
+                self.setDescription(url,svalue)
+                #self.story.setMetadata('description',stripHTML(svalue))
+
+            if 'Rated' in label:
+                self.story.setMetadata('rating', value)
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Categories' in label:
+                cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+                for cat in cats:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+                for char in chars:
+                    self.story.addToList('characters',char.string)
+
+            if 'Genre' in label:
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
+                for genre in genres:
+                    self.story.addToList('genre',genre.string)
+
+            if 'Warnings' in label:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
+                for warning in warnings:
+                    self.story.addToList('warnings',warning.string)
+
+            if 'Completed' in label:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Updated' in label:
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            # 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:
+                # 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)
+                        break
+                    i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logger.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div', {'id' : 'story'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_restrictedsectionorg.py

@@ -0,0 +1,264 @@
+# -*- 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
+import cookielib as cl
+from datetime import datetime
+import json
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return RestrictedSectionOrgSiteAdapter
+
+class RestrictedSectionOrgSiteAdapter(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 = ""
+        
+        # normalized story URL.
+        # get story/file and storyId from url--url validation guarantees query correct
+        m = re.match(self.getSiteURLPattern(),url)
+        if m:
+            self.story.setMetadata('storyId',m.group('id'))
+            logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+            # normalized story URL.
+            self._setURL('http://' + self.getSiteDomain() + '/' + m.group('filestory') + '.php?' + m.group('filestory') + '=' + self.story.getMetadata('storyId'))
+            logger.debug("storyUrl: (%s)"%self.story.getMetadata('storyUrl'))
+        else:
+            raise exceptions.InvalidStoryURL(url,
+                                             self.getSiteDomain(),
+                                             self.getSiteExampleURLs())
+        
+        self.story.setMetadata('siteabbrev','ressec')
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%d %b %Y" # 20 Nov 2005
+        
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        return 'www.restrictedsection.org'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/story.php?story=1234 http://"+self.getSiteDomain()+"/file.php?file=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain())+r"/(?P<filestory>file|story).php\?(file|story)=(?P<id>\d+)$"
+        
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        url = self.url
+        logger.debug("URL: "+url)
+
+        # one-shot stories use file url instead of story.  'Luckily',
+        # we don't have to worry about one-shots becoming
+        # multi-chapter because ressec is frozen.  Still need 'story'
+        # url for metadata, however.
+        try:
+            if 'file' in url:
+                data = self._postUrlUP(url)
+                soup = bs.BeautifulSoup(data)
+                storya = soup.find('a',href=re.compile(r"^story.php\?story=\d+"))
+                url = 'http://'+self.host+'/'+storya['href'].split('&')[0]  # strip rs_session
+
+                fileas = soup.find('a',href=re.compile(r"^file.php\?file=\d+"))
+                if fileas:
+                    for filea in fileas:
+                        if 'Previous Chapter' in filea.string or 'Next Chapter' in filea.string:
+                            raise exceptions.FailedToDownload(self.getSiteDomain() +" Cannot use chapter url with multi-chapter stories on this site.")
+                    
+            logger.debug("metadata URL: "+url)
+            data = self._fetchUrl(url)
+            # print data
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+        if "Story not found" in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Story not found.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+
+        # check user/pass on a chapter for multi-chapter
+        if 'file' not in self.url:
+            self._postUrlUP('http://'+self.host+'/'+soup.find('a', href=re.compile(r"^file.php\?file=\d+"))['href'])
+
+        ## Title
+        h2 = soup.find('h2')
+
+        # Find authorid and URL from... author url.
+        a = h2.find('a')
+        ahref = a['href'].split('&')[0]  # strip rs_session
+        
+        self.story.setMetadata('authorId',ahref.split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+ahref)
+        self.story.setMetadata('author',a.string)
+
+        # title, remove byauthorname.
+        self.story.setMetadata('title',h2.text[:h2.text.index("by"+a.string)])
+
+        dates = soup.findAll('span', {'class':'date'})
+        if dates: # only for multi-chapter
+            self.story.setMetadata('datePublished', makeDate(stripHTML(dates[0]), self.dateformat))
+            self.story.setMetadata('dateUpdated', makeDate(stripHTML(dates[-1]), self.dateformat))
+
+        words = soup.findAll('span', {'class':'size'})
+        wordcount=0
+        for w in words:
+            wordcount = wordcount + int(w.string[:-6].replace(',',''))
+
+        self.story.setMetadata('numWords',"%s"%wordcount)
+
+        self.story.setMetadata('rating', soup.find('a',href=re.compile(r"^rating.php\?rating=\d+")).string)
+        
+        # other tags
+
+        labels = soup.find('table', {'class':'info'}).findAll('th')
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+            
+            if label != None:
+                
+                if 'Categories' in label:
+                    for g in stripHTML(value).split('\n'):
+                        self.story.addToList('genre',g)
+                
+                if 'Pairings' in label:
+                    for g in stripHTML(value).split('\n'):
+                        self.story.addToList('ships',g)
+                
+                if 'Summary' in label:
+                    self.setDescription(url,stripHTML(value).replace("\n"," ").replace("\r",""))
+                    value.extract() # remove summary incase it contains file URLs.
+
+                if 'Updated' in label: # one-shots only.
+                    print "value:%s"%value
+                    value.find('sup').extract() # remove 'st', 'nd', 'th' ordinals
+                    print "value:%s"%value
+                    date = makeDate(stripHTML(value), '%d %B %Y') # full month name
+                    self.story.setMetadata('datePublished', date)
+
+                if 'Length' in label: # one-shots only.
+                    self.story.setMetadata('numWords',value.string[:-6])
+                    
+        # one-shot.
+        if 'file' in self.url:
+            self.chapterUrls.append((self.story.getMetadata('title'),self.url))
+        else: # multi-chapter
+            # Find the chapters: 'library_storyview.php?chapterid=3
+            chapters=soup.findAll('a', href=re.compile(r"^file.php\?file=\d+"))
+            if len(chapters)==0:
+                raise exceptions.FailedToDownload(self.getSiteDomain() +" says: No chapters found.")
+            else:
+                for chapter in chapters:
+                    chhref = chapter['href'].split('&')[0] # strip rs_session
+                    # just in case there's tags, like <i> in chapter titles.
+                    self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chhref))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+
+
+    def _postUrlUP(self, url):
+        params = {}
+        if self.password:
+            params['username'] = self.username
+            params['password'] = self.password
+        else:
+            params['username'] = self.getConfig("username")
+            params['password'] = self.getConfig("password")
+        params['accept.x'] = 1
+        params['accept.y'] = 1
+
+        excpt=None
+        for sleeptime in [0.5, 1.5, 4, 9]:
+            time.sleep(sleeptime)	
+            try:
+                data = self._postUrl(url, params)
+                if data == "Unable to connect to the database":
+                    raise exceptions.FailedToDownload("Site reported 'Unable to connect to the database'")
+                if "I certify that I am over the age of 18 and that accessing the following story will not violate the laws of my country or local ordinances." in data:
+                    raise exceptions.FailedToLogin(url,params['username'])
+                return data
+            except exceptions.FailedToLogin, ftl:
+                # no need to retry these.
+                raise(ftl)
+            except Exception, e:
+                excpt=e
+                logger.warn("Caught an exception reading URL: %s  Exception %s."%(unicode(url),unicode(e)))
+
+        logger.error("Giving up on %s" %url)
+        logger.exception(excpt)
+        raise(excpt)
+        
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logger.debug('Getting chapter text from: %s' % url)
+
+        data = self._postUrlUP(url)
+        #print("data:%s"%data)
+        
+        # some stories have html that confuses the parser.  For story
+        # text we don't care about anything before '<table id="page"'
+        # and seems to clear the issue.
+        data = data[data.index('<table id="page"'):]
+        
+        soup = bs.BeautifulSoup(data)
+        
+        div = soup.find('td',{'id':'page_content'})
+        div.name='div'
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+
+        ## Remove stuff from page_content
+
+        # Remove all tags before the first <hr> after class=info table (including hr)
+        hr = div.find('table',{'class':'info'}).findNext('hr')
+        for tag in hr.findAllPrevious():
+            tag.extract()
+        hr.extract()
+        
+        # Remove all tags after the last <hr> (including hr)
+        hr = div.findAll('hr')[-1]
+        for tag in hr.findAllNext():
+            tag.extract()
+        hr.extract()
+        
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_test1.py

@@ -101,9 +101,10 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
                 }
             self.story.setMetadata('language',langs[idnum%len(langs)])
             self.setSeries('The Great Test',idnum)
-        
+        if idnum == 0:
+            self.setSeries("A Nook Hyphen Test "+self.story.getMetadata('dateCreated'),idnum)
+            
         self.story.setMetadata('rating','Tweenie')
-        
 
         if self.story.getMetadata('storyId') == '673':
             self.story.addToList('author','Author From List')
@@ -205,11 +206,24 @@ 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</p>
-<p>Odd sid's will be In-Progress, evens complete.  sid&lt;10 will be assigned one of four languages and included in a series.</p>
+<p>http://test1.com?sid=672 - Succeeds, quick meta, sleeps 2sec chapters only</p><p>http://test1.com?sid=0 - Succeeds, generates some text specifically for testing hyphenation problems with Nook STR/STRwG</p><p>Odd sid's will be In-Progress, evens complete.  sid&lt;10 will be assigned one of four languages and included in a series.</p>
 </div>
+'''
+        elif self.story.getMetadata('storyId') == '0':
+            text=u'''
+<h3>45. Pronglet Returns to Hogwarts: Chapter 7</h3>
+<br />
+    eyes… but I’m not convinced we should automatically<br />
+<br /><br />
+<b>Thanks to the latest to recommend me: Alastor</b><br />
+<br /><br />
+    “Sure, invite her along. Does she have children?”<br />
+<br />
 '''
         else:
             text=u'''

fanficdownloader/adapters/adapter_thewriterscoffeeshopcom.py

@@ -48,7 +48,7 @@ class TheWritersCoffeeShopComSiteAdapter(BaseSiteAdapter):
         
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/library/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        self.dateformat = "%B %d, %Y"
+        self.dateformat = "%d %b %Y"
 
             
     @staticmethod

fanficdownloader/configurable.py

@@ -74,7 +74,8 @@ class Configuration(ConfigParser.SafeConfigParser):
             # internal stuff.
             'langcode',
             'output_css',
-            'authorHTML'
+            'authorHTML',
+            'lastupdate'
             ]
 
     def addConfigSection(self,section):

fanficdownloader/story.py

@@ -432,8 +432,13 @@ class Story(Configurable):
                                   map(removeAllEntities,retlist) )
 
         if retlist:
-            # remove dups and sort.
-            return sorted(list(set(retlist)))
+            if listname in ('author','authorUrl'):
+                # need to retain order for author & authorUrl so the
+                # two match up.
+                return retlist
+            else:
+                # remove dups and sort.
+                return sorted(list(set(retlist)))
         else:
             return []
 

fanficdownloader/writers/writer_epub.py

@@ -21,6 +21,7 @@ import StringIO
 import zipfile
 from zipfile import ZipFile, ZIP_STORED, ZIP_DEFLATED
 import urllib
+import re
 
 ## XML isn't as forgiving as HTML, so rather than generate as strings,
 ## use DOM to generate the XML files.
@@ -657,7 +658,12 @@ div { margin: 0pt; padding: 0pt; }
                 # as one line.  This causes problems for nook(at
                 # least) when the chapter size starts getting big
                 # (200k+)
-                fullhtml = fullhtml.replace('</p>','</p>\n').replace('<br />','<br />\n')
+                #fullhtml = fullhtml.replace('</p>','</p>\n').replace('<br />','<br />\n')
+                # The replaces above added tons of extra newlines
+                # during *each* epub update.  The regexp version adds
+                # only one and removes any extra.
+                fullhtml = re.sub(r'(</p>|<br />)\n*',r'\1\n',fullhtml)
+
                 outputepub.writestr("OEBPS/file%04d.xhtml"%(index+1),fullhtml.encode('utf-8'))
                 del fullhtml
 

index.html

@@ -54,9 +54,13 @@
 	      much easier. </p>
 	  </div>
 	  <!-- put announcements here, h3 is a good title size. -->
-	  <h3>Fixes:</h3>
+	  <h3>Changes:</h3>
 	  <p>
-	    Set language to Italian for efpfanfic.net, allow replace_metadata to effect language metadata.
+	    <ul>
+	      <li>New site: www.henneth-annun.net -- Thanks Ida!</li>
+	      <li>New site: www.psychfic.com -- Thanks Ida!</li>
+	      <li>Now accepting www.skyehawke.com/archive URLs for  archive.skyehawke.com stories.</li>
+	    </ul>
 	  </p>
 	  <p>
 	    Questions?  Check out our 
@@ -66,7 +70,7 @@
 	    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://4-4-33.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
+	    <a href="http://4-4-42.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
 	  </p>
 	  <div id='error'>
 	    {{ error_message }}
@@ -290,6 +294,8 @@
 	  <dd>
 	    Use the URL of the story's summary, such as
 	    <br /><a href="http://archive.skyehawke.com/story.php?no=17466">http://archive.skyehawke.com/story.php?no=17466</a>.
+	    <br /><a href="http://www.skyehawke.com/archive/story.php?no=17466">http://www.skyehawke.com/archive/story.php?no=17466</a>.
+	    <br /><a href="http://skyehawke.com/archive/story.php?no=17466">http://skyehawke.com/archive/story.php?no=17466</a>.
 	  </dd>
 	  <dt>www.libraryofmoria.com</dt>
 	  <dd>
@@ -389,11 +395,6 @@
 	    Use the URL of the story's first chapter, such as
 	    <br /><a href="http://samdean.archive.nu/viewstory.php?sid=1234">http://samdean.archive.nu/viewstory.php?sid=1234</a>
 	  </dd>
-	  <dt>www.yourfanfiction.com</dt>
-	  <dd>
-	    Use the URL of the story's first chapter, such as
-	    <br /><a href="http://www.yourfanfiction.com/viewstory.php?sid=1234">http://www.yourfanfiction.com/viewstory.php?sid=1234</a>
-	  </dd>
 	  <dt>www.destinysgateway.com</dt>
 	  <dd>
 	    Use the URL of the story's first chapter, such as
@@ -563,6 +564,56 @@
 	    Use the URL of any story chapter, such as
 	    <br /><a href="http://www.efpfanfic.net/viewstory.php?sid=12345">http://www.efpfanfic.net/viewstory.php?sid=12345</a>
 	  </dd>
+	  <dt>www.potterfics.com</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://www.potterfics.com/historias/127583">http://www.potterfics.com/historias/127583</a>
+	  </dd>
+	  <dt>www.dotmoon.net</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://www.dotmoon.net/library_view.php?storyid=1234">http://www.dotmoon.net/library_view.php?storyid=1234</a>
+	  </dd>
+	  <dt>efiction.esteliel.de</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://efiction.esteliel.de/viewstory.php?sid=1234">http://efiction.esteliel.de/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>pommedesang.com</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://pommedesang.com/efiction/viewstory.php?sid=1234">http://pommedesang.com/efiction/viewstory.php?sid=1234</a>
+	    <br /><a href="http://pommedesang.com/sds/viewstory.php?sid=1234">http://pommedesang.com/sds/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>www.restrictedsection.org</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://www.restrictedsection.org/story.php?story=1234">http://www.restrictedsection.org/story.php?story=1234</a>
+	    <br />Or the story URL for one-shots, such as
+	    <br /><a href="http://www.restrictedsection.org/file.php?file=1234">http://www.restrictedsection.org/file.php?file=1234</a>
+	  </dd>
+	  <dt>imagine.e-fic.com</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://imagine.e-fic.com/viewstory.php?sid=1234">http://imagine.e-fic.com/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>buffynfaith.net</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://buffynfaith.net/fanfictions/index.php?act=vie&id=1234">http://buffynfaith.net/fanfictions/index.php?act=vie&amp;id=1234</a>
+	    <br />Or, use the URL of any story chapter, such as
+	    <br /><a href="http://buffynfaith.net/fanfictions/index.php?act=vie&id=1234&ch=2">http://buffynfaith.net/fanfictions/index.php?act=vie&amp;id=1234&amp;ch=2</a>
+	  </dd>
+	  <dt>www.henneth-annun.net</dt>
+	  <dd>
+	    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>
+	  <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>
 	</dl>
 
 	<p>

plugin-defaults.ini

@@ -296,12 +296,13 @@ background_color: ffffff
 ## Allow customization of CSS.  Make sure to keep at least one space
 ## at the start of each line and to escape % to %%.  Also need
 ## background_color to be in the same section, if included in CSS.
-## 'adobe-text-layout: optimizeSpeed;' prevents hyphenation on newer Nooks
+## 'adobe-hyphenate: none;' prevents hyphenation on newer Nooks
+## STR(wG) (1.2.1+ for sure)
 output_css: 
  body { background-color: #%(background_color)s;
         text-align: justify;
         margin: 2%%;
-	adobe-text-layout: optimizeSpeed; }
+	adobe-hyphenate: none; }
  pre { font-size: x-small; }
  sml { font-size: small; }
  h1 { text-align: center; }
@@ -433,8 +434,9 @@ extratags: FanFiction,Testing,HTML
 #is_adult:true
 
 ## AO3 adapter defines a few extra metadata entries.
-extra_valid_entries:fandoms,freefromtags,ao3categories,comments,kudos,hits,bookmarks,collections
+extra_valid_entries:fandoms,freeformtags,freefromtags,ao3categories,comments,kudos,hits,bookmarks,collections
 fandoms_label:Fandoms
+freeformtags_label:Freeform Tags
 freefromtags_label:Freeform Tags
 ao3categories_label:AO3 Categories
 comments_label:Comments
@@ -443,11 +445,15 @@ hits_label:Hits
 collections_label:Collections
 bookmarks_label:Bookmarks
 
+## freeformtags was previously typo'ed as freefromtags.  This way,
+## freefromtags will still work for people who've used it.
+include_in_freefromtags:freeformtags
+
 ## adds to titlepage_entries instead of replacing it.
-#extra_titlepage_entries: fandoms,freefromtags,ao3categories,comments,kudos,hits,bookmarks
+#extra_titlepage_entries: fandoms,freeformtags,ao3categories,comments,kudos,hits,bookmarks
 
 ## adds to include_subject_tags instead of replacing it.
-#extra_subject_tags:fandoms,freefromtags,ao3categories
+#extra_subject_tags:fandoms,freeformtags,ao3categories
 
 [ashwinder.sycophanthex.com]
 ## Site dedicated to these categories/characters/ships
@@ -478,6 +484,15 @@ extracategories:Blood Ties
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+[buffynfaith.net]
+## Site dedicated to these categories/characters/ships
+extracategories:Buffy: The Vampire Slayer
+
+## 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
+
 [castlefans.org]
 ## Site dedicated to these categories/characters/ships
 extracategories:Castle
@@ -588,6 +603,10 @@ cliches_label:Character Cliches
 # themes=>#bcolumn,a
 # timeline=>#ccolumn,n
 
+[efiction.esteliel.de]
+## Site dedicated to these categories/characters/ships
+extracategories:Lord of the Rings
+
 [erosnsappho.sycophanthex.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
@@ -664,6 +683,19 @@ extracharacters:Hermione Granger
 ## Site dedicated to these categories/characters/ships
 extracategories:Highlander
 
+[imagine.e-fic.com]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## 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
+
 [indeath.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:In Death
@@ -749,6 +781,22 @@ extracategories:One Direction
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+[pommedesang.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Anita Blake Vampire Hunter 
+
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
+#is_adult:true
+
 [ponyfictionarchive.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:My Little Pony: Friendship is Magic
@@ -901,6 +949,14 @@ extracategories:InuYasha
 extracharacters:Sesshoumaru,Kagome
 extraships:Sesshoumaru/Kagome
 
+[www.dotmoon.net]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
 [www.efpfanfic.net]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -992,6 +1048,10 @@ extracategories:Harry Potter
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[www.henneth-annun.net]
+## Site dedicated to these categories/characters/ships
+extracategories:The Hobbit
+
 [www.hpfandom.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
@@ -1071,10 +1131,23 @@ extraships:Harry Potter/Ginny Weasley
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
 
+[www.potterfics.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 [www.prisonbreakfic.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:Prison Break
 
+[www.psychfic.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Psych
+
+## 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.qaf-fic.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Queer as Folk
@@ -1084,6 +1157,16 @@ extracategories:Queer as Folk
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[www.restrictedsection.org]
+extracategories:Harry Potter
+extragenres:Erotica
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
 [www.scarvesandcoffee.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:Glee
@@ -1233,12 +1316,6 @@ extracategories:Stargate: Atlantis
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
-[www.yourfanfiction.com]
-## Some sites do not require a login, but do require the user to
-## confirm they are adult for adult content.  In commandline version,
-## this should go in your personal.ini, not defaults.ini.
-#is_adult:true
-
 [overrides]
 ## It may sometimes be useful to override all of the specific format,
 ## site and site:format sections in your private configuration.  For