Bump versions, make ready for release.

and is now removing ASCII character x!0 (whitespace) as it interfered with
  regexp.
base_adapter called replace_br_with_p with two argument, where teh function
  only support one.

app.yaml

@@ -1,6 +1,6 @@
 # ffd-retief-hrd fanfictiondownloader
 application: fanfictiondownloader
-version: 4-4-68
+version: 4-4-80
 runtime: python27
 api_version: 1
 threadsafe: true

calibre-plugin/__init__.py

@@ -7,6 +7,16 @@ __license__   = 'GPL v3'
 __copyright__ = '2013, Jim Miller'
 __docformat__ = 'restructuredtext en'
 
+import sys
+if sys.version_info >= (2, 7):
+    import logging
+    logger = logging.getLogger(__name__)
+    loghandler=logging.StreamHandler()
+    loghandler.setFormatter(logging.Formatter("FFDL:%(levelname)s:%(filename)s(%(lineno)d):%(message)s"))
+    logger.addHandler(loghandler)
+    loghandler.setLevel(logging.DEBUG)
+    logger.setLevel(logging.DEBUG)
+
 # The class that all Interface Action plugin wrappers must inherit from
 from calibre.customize import InterfaceActionBase
 
@@ -26,7 +36,7 @@ class FanFictionDownLoaderBase(InterfaceActionBase):
     description         = 'UI plugin to download FanFiction stories from various sites.'
     supported_platforms = ['windows', 'osx', 'linux']
     author              = 'Jim Miller'
-    version             = (1, 7, 35)
+    version             = (1, 7, 51)
     minimum_calibre_version = (0, 8, 57)
 
     #: This field defines the GUI plugin class that contains all the code

calibre-plugin/config.py

@@ -7,6 +7,9 @@ __license__   = 'GPL v3'
 __copyright__ = '2012, Jim Miller'
 __docformat__ = 'restructuredtext en'
 
+import logging
+logger = logging.getLogger(__name__)
+
 import traceback, copy, threading
 from collections import OrderedDict
 
@@ -126,9 +129,15 @@ class ConfigWidget(QWidget):
         label.setOpenExternalLinks(True)
         self.l.addWidget(label)
 
-        tab_widget = QTabWidget(self)
-        self.l.addWidget(tab_widget)
 
+        self.scroll_area = QScrollArea(self)
+        self.scroll_area.setFrameShape(QScrollArea.NoFrame)
+        self.scroll_area.setWidgetResizable(True)
+        self.l.addWidget(self.scroll_area)
+
+        tab_widget = QTabWidget(self)
+        self.scroll_area.setWidget(tab_widget)
+        
         self.basic_tab = BasicTab(self, plugin_action)
         tab_widget.addTab(self.basic_tab, 'Basic')
 
@@ -169,6 +178,9 @@ class ConfigWidget(QWidget):
         prefs['updatecover'] = self.basic_tab.updatecover.isChecked()
         prefs['updateepubcover'] = self.basic_tab.updateepubcover.isChecked()
         prefs['keeptags'] = self.basic_tab.keeptags.isChecked()
+        prefs['suppressauthorsort'] = self.basic_tab.suppressauthorsort.isChecked()
+        prefs['suppresstitlesort'] = self.basic_tab.suppresstitlesort.isChecked()
+        prefs['mark'] = self.basic_tab.mark.isChecked()
         prefs['showmarked'] = self.basic_tab.showmarked.isChecked()
         prefs['urlsfromclip'] = self.basic_tab.urlsfromclip.isChecked()
         prefs['updatedefault'] = self.basic_tab.updatedefault.isChecked()
@@ -177,6 +189,7 @@ class ConfigWidget(QWidget):
         prefs['includeimages'] = self.basic_tab.includeimages.isChecked()
         prefs['lookforurlinhtml'] = self.basic_tab.lookforurlinhtml.isChecked()
         prefs['checkforseriesurlid'] = self.basic_tab.checkforseriesurlid.isChecked()
+        prefs['checkforurlchange'] = self.basic_tab.checkforurlchange.isChecked()
         prefs['injectseries'] = self.basic_tab.injectseries.isChecked()
         prefs['smarten_punctuation'] = self.basic_tab.smarten_punctuation.isChecked()
 
@@ -347,18 +360,38 @@ class BasicTab(QWidget):
         self.keeptags.setChecked(prefs['keeptags'])
         self.l.addWidget(self.keeptags)
 
+        self.suppressauthorsort = QCheckBox('Force Author into Author Sort?',self)
+        self.suppressauthorsort.setToolTip("If checked, the author(s) as given will be used for the Author Sort, too.\nIf not checked, calibre will apply it's built in algorithm which makes 'Bob Smith' sort as 'Smith, Bob', etc.")
+        self.suppressauthorsort.setChecked(prefs['suppressauthorsort'])
+        self.l.addWidget(self.suppressauthorsort)
+
+        self.suppresstitlesort = QCheckBox('Force Title into Title Sort?',self)
+        self.suppresstitlesort.setToolTip("If checked, the title as given will be used for the Title Sort, too.\nIf not checked, calibre will apply it's built in algorithm which makes 'The Title' sort as 'Title, The', etc.")
+        self.suppresstitlesort.setChecked(prefs['suppresstitlesort'])
+        self.l.addWidget(self.suppresstitlesort)
+
         self.checkforseriesurlid = QCheckBox("Check for existing Series Anthology books?",self)
         self.checkforseriesurlid.setToolTip("Check for existings Series Anthology books using each new story's series URL before downloading.\nOffer to skip downloading if a Series Anthology is found.")
         self.checkforseriesurlid.setChecked(prefs['checkforseriesurlid'])
         self.l.addWidget(self.checkforseriesurlid)
 
+        self.checkforurlchange = QCheckBox("Check for changed Story URL?",self)
+        self.checkforurlchange.setToolTip("Warn you if an update will change the URL of an existing book.")
+        self.checkforurlchange.setChecked(prefs['checkforurlchange'])
+        self.l.addWidget(self.checkforurlchange)
+
         self.lookforurlinhtml = QCheckBox("Search EPUB text for Story URL?",self)
         self.lookforurlinhtml.setToolTip("Look for first valid story URL inside EPUB text if not found in metadata.\nSomewhat risky, could find wrong URL depending on EPUB content.\nAlso finds and corrects bad ffnet URLs from ficsaver.com files.")
         self.lookforurlinhtml.setChecked(prefs['lookforurlinhtml'])
         self.l.addWidget(self.lookforurlinhtml)
 
-        self.showmarked = QCheckBox("Show added/updated books when finished?",self)
-        self.showmarked.setToolTip("Show added/updated books only when finished.\nYou can also manually search for 'marked:ffdl_success'.\n'marked:ffdl_failed' is also available, or search 'marked:ffdl' for both.")
+        self.mark = QCheckBox("Mark added/updated books when finished?",self)
+        self.mark.setToolTip("Mark added/updated books when finished.  Use with option below.\nYou can also manually search for 'marked:ffdl_success'.\n'marked:ffdl_failed' is also available, or search 'marked:ffdl' for both.")
+        self.mark.setChecked(prefs['mark'])
+        self.l.addWidget(self.mark)
+
+        self.showmarked = QCheckBox("Show Marked books when finished?",self)
+        self.showmarked.setToolTip("Show Marked added/updated books only when finished.\nYou can also manually search for 'marked:ffdl_success'.\n'marked:ffdl_failed' is also available, or search 'marked:ffdl' for both.")
         self.showmarked.setChecked(prefs['showmarked'])
         self.l.addWidget(self.showmarked)
 
@@ -419,15 +452,17 @@ class BasicTab(QWidget):
         topl.addWidget(defs_gb)
 
         horz = QHBoxLayout()
-        topl.addLayout(horz)
-        horz.addWidget(cali_gb)
-        horz.addWidget(rej_gb)
-        
-        horz = QHBoxLayout()
-        topl.addLayout(horz)
-        horz.addWidget(gui_gb)
-        horz.addWidget(misc_gb)
 
+        horz.addWidget(cali_gb)
+
+        vert = QVBoxLayout()
+        vert.addWidget(gui_gb)
+        vert.addWidget(misc_gb)
+        vert.addWidget(rej_gb)
+        
+        horz.addLayout(vert)
+        
+        topl.addLayout(horz)
         topl.insertStretch(-1)
         
     def set_collisions(self):
@@ -503,9 +538,9 @@ class PersonalIniTab(QWidget):
         self.ini = QTextEdit(self)
         try:
             self.ini.setFont(QFont("Courier",
-                                   self.plugin_action.gui.font().pointSize()+1));
+                                   self.plugin_action.gui.font().pointSize()+1))
         except Exception as e:
-            print("Couldn't get font: %s"%e)
+            logger.error("Couldn't get font: %s"%e)
         self.ini.setLineWrapMode(QTextEdit.NoWrap)
         self.ini.setText(prefs['personal.ini'])
         self.l.addWidget(self.ini)
@@ -539,9 +574,9 @@ class ShowDefaultsIniDialog(QDialog):
         self.ini.setToolTip("These are all of the plugin's configurable options\nand their default settings.")
         try:
             self.ini.setFont(QFont("Courier",
-                                   get_gui().font().pointSize()+1));
+                                   get_gui().font().pointSize()+1))
         except Exception as e:
-            print("Couldn't get font: %s"%e)
+            logger.error("Couldn't get font: %s"%e)
         self.ini.setLineWrapMode(QTextEdit.NoWrap)
         self.ini.setText(text)
         self.ini.setReadOnly(True)

calibre-plugin/dialogs.py

@@ -7,9 +7,15 @@ __license__   = 'GPL v3'
 __copyright__ = '2011, Jim Miller'
 __docformat__ = 'restructuredtext en'
 
+import logging
+logger = logging.getLogger(__name__)
+
 import traceback, re
 from functools import partial
 
+import logging
+logger = logging.getLogger(__name__)
+
 import urllib
 import email
 
@@ -164,7 +170,7 @@ class DroppableQTextEdit(QTextEdit):
         
     def canInsertFromMimeData(self, source):
         if source.hasUrls():
-            return True;
+            return True
         else:
             return QTextEdit.canInsertFromMimeData(self,source)
 
@@ -207,8 +213,8 @@ class AddNewDialog(SizePersistedDialog):
         self.groupbox.setCheckable(True)
         self.groupbox.setChecked(False)
         self.groupbox.setFlat(True)
-        print("style:%s"%self.groupbox.styleSheet())
-        self.groupbox.setStyleSheet(gpstyle);
+        #print("style:%s"%self.groupbox.styleSheet())
+        self.groupbox.setStyleSheet(gpstyle)
 
         self.gbf = QFrame()
         self.gbl = QVBoxLayout()
@@ -537,7 +543,7 @@ class LoopProgressDialog(QProgressDialog):
     def updateStatus(self):
         self.setLabelText("%s %d of %d"%(self.status_prefix,self.i+1,len(self.book_list)))
         self.setValue(self.i+1)
-        print(self.labelText())
+        #print(self.labelText())
 
     def do_loop(self):
 
@@ -558,7 +564,7 @@ class LoopProgressDialog(QProgressDialog):
         except Exception as e:
             book['good']=False
             book['comment']=unicode(e)
-            print("Exception: %s:%s"%(book,unicode(e)))
+            logger.error("Exception: %s:%s"%(book,unicode(e)))
             traceback.print_exc()
             
         self.updateStatus()

calibre-plugin/ffdl_plugin.py

@@ -7,13 +7,17 @@ __license__   = 'GPL v3'
 __copyright__ = '2012, Jim Miller'
 __docformat__ = 'restructuredtext en'
 
-import time, os, copy, threading, re, platform
+import logging
+logger = logging.getLogger(__name__)
+
+import time, os, copy, threading, re, platform, sys
 from StringIO import StringIO
 from functools import partial
 from datetime import datetime
 from string import Template
 import urllib
 import email
+import traceback
 
 from PyQt4.Qt import (QApplication, QMenu, QToolButton, QTimer)
 
@@ -23,7 +27,7 @@ from PyQt4.QtCore import QBuffer
 from calibre.constants import numeric_version as calibre_version
 
 from calibre.ptempfile import PersistentTemporaryFile, PersistentTemporaryDirectory, remove_dir
-from calibre.ebooks.metadata import MetaInformation, authors_to_string
+from calibre.ebooks.metadata import MetaInformation
 from calibre.ebooks.metadata.meta import get_metadata
 from calibre.gui2 import error_dialog, warning_dialog, question_dialog, info_dialog
 from calibre.gui2.dialogs.message_box import ViewLog
@@ -142,7 +146,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             file_path = os.path.join(calibre_config_dir,
                                      *("plugins/fanfictiondownloader_macmenuhack.txt".split('/')))
             file_path = os.path.abspath(file_path)
-            print("Plugin %s macmenuhack file_path:%s"%(self.name,file_path))
+            logger.debug("Plugin %s macmenuhack file_path:%s"%(self.name,file_path))
             self.macmenuhack = os.access(file_path, os.F_OK)
             return self.macmenuhack
 
@@ -386,7 +390,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                         show_copy_button=False)
 
     def get_urls_from_page(self,url):
-        print("get_urls_from_page URL:%s"%url)
+        logger.debug("get_urls_from_page URL:%s"%url)
         if 'archiveofourown.org' in url:
             configuration = get_ffdl_config(url)
         else:
@@ -540,7 +544,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             return
             
         tdir = PersistentTemporaryDirectory(prefix='ffdl_anthology_')
-        print("tdir:\n%s"%tdir)
+        logger.debug("tdir:\n%s"%tdir)
 
         bookepubio = StringIO(db.format(book_id,'EPUB',index_is_id=True))
         
@@ -616,7 +620,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             '''%(len(urlmapfile),"</li><li>".join(urlmapfile.keys()))
             if not question_dialog(self.gui, 'Stories Removed',
                                text, show_copy_button=False):
-                print("Canceling anthology update due to removed stories.")
+                logger.debug("Canceling anthology update due to removed stories.")
                 return
 
         # Now that we've 
@@ -628,7 +632,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             return
 
         if not id_list:
-            id_list = self.gui.library_view.get_selected_ids();
+            id_list = self.gui.library_view.get_selected_ids()
         
         if len(id_list) == 0:
             self.gui.status_bar.show_message(_('No Selected Books to Update'), 3000)
@@ -695,7 +699,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             books = self.convert_urls_to_books(url_list)
 
         options['version'] = self.version
-        print(self.version)
+        logger.debug(self.version)
         
         #print("prep_downloads:%s"%books)
 
@@ -730,7 +734,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         '''
 
         url = book['url']
-        print("url:%s"%url)
+        logger.debug("url:%s"%url)
         mi = None
 
         if not merge: # skip reject list when merging.
@@ -786,7 +790,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             try:
                 adapter.getStoryMetadataOnly()
             except exceptions.FailedToLogin, f:
-                print("Login Failed, Need Username/Password.")
+                logger.warn("Login Failed, Need Username/Password.")
                 userpass = UserPassDialog(self.gui,url,f)
                 userpass.exec_() # exec_ will make it act modal
                 if userpass.status:
@@ -868,14 +872,14 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             
             if book['calibre_id'] != None:
                 # updating an existing book.  Update mode applies.
-                print("update existing id:%s"%book['calibre_id'])
+                logger.debug("update existing id:%s"%book['calibre_id'])
                 book_id = book['calibre_id']
                 # No handling needed: OVERWRITEALWAYS,CALIBREONLY
                 
             # only care about collisions when not ADDNEW
             elif collision != ADDNEW:
                 # 'new' book from URL.  collision handling applies.
-                print("from URL(%s)"%url)
+                logger.debug("from URL(%s)"%url)
     
                 # try to find by identifier url or uri first.
                 searchstr = 'identifiers:"~ur(i|l):=%s"'%url.replace(":","|")
@@ -888,16 +892,16 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                         ## meantime, if it matches the title *and* first
                         ## 100 authors, I'm prepared to assume it's a
                         ## match.
-                        print("reduce author list to 100 only when calibre < 0.8.61")
+                        logger.debug("reduce author list to 100 only when calibre < 0.8.61")
                         authlist = authlist[:100]
                     mi = MetaInformation(story.getMetadata("title", removeallentities=True),
                                          authlist)
                     identicalbooks = db.find_identical_books(mi)
                     if len(identicalbooks) > 0:
-                        print("existing found by title/author(s)")
+                        logger.debug("existing found by title/author(s)")
     
                 else:
-                    print("existing found by identifier URL")
+                    logger.debug("existing found by identifier URL")
                     
                 if collision == SKIP and identicalbooks:
                     raise NotGoingToDownload("Skipping duplicate story.","list_remove.png")
@@ -918,7 +922,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
     
                 if book_id and mi: # book_id and mi only set if matched by title/author.
                     liburl = self.get_story_url(db,book_id)
-                    if book['url'] != liburl:
+                    if book['url'] != liburl and prefs['checkforurlchange']:
                         if collision in (OVERWRITE,OVERWRITEALWAYS):
                             updat="overwrit"
                         else:
@@ -996,14 +1000,14 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                                                   suffix='.epub',
                                                   dir=options['tdir'])
                     db.copy_format_to(book_id,fileform,tmp,index_is_id=True)
-                    print("existing epub tmp:"+tmp.name)
+                    logger.debug("existing epub tmp:"+tmp.name)
                     book['epub_for_update'] = tmp.name
 
             if book_id != None and prefs['injectseries']:
                 mi = db.get_metadata(book_id,index_is_id=True)
                 if not book['series'] and mi.series != None:
                     book['calibre_series'] = (mi.series,mi.series_index)
-                    print("calibre_series:%s [%s]"%book['calibre_series'])
+                    #print("calibre_series:%s [%s]"%book['calibre_series'])
                 
         if book['good']: # there shouldn't be any !'good' books at this point.
             # if still 'good', make a temp file to write the output to.
@@ -1013,8 +1017,8 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             tmp = PersistentTemporaryFile(prefix=story.formatFileName("${title}-${author}-",allowunsafefilename=False)[:100],
                                           suffix='.'+options['fileform'],
                                           dir=options['tdir'])
-            print("title:"+book['title'])
-            print("outfile:"+tmp.name)
+            logger.debug("title:"+book['title'])
+            logger.debug("outfile:"+tmp.name)
             book['outfile'] = tmp.name            
                 
         return
@@ -1092,7 +1096,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         if book['calibre_id'] and prefs['errorcol'] != '' and prefs['errorcol'] in custom_columns:
             label = custom_columns[prefs['errorcol']]['label']
             if not book['good']:
-                print("record/update error message column %s %s"%(book['title'],book['url']))
+                logger.debug("record/update error message column %s %s"%(book['title'],book['url']))
                 db.set_custom(book['calibre_id'], book['comment'], label=label, commit=True) # book['comment']
             else:
                 db.set_custom(book['calibre_id'], '', label=label, commit=True) # book['comment']
@@ -1100,7 +1104,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         if not book['good']:
             return # only update errorcol on error.
         
-        print("add/update %s %s"%(book['title'],book['url']))
+        logger.debug("add/update %s %s"%(book['title'],book['url']))
         mi = self.make_mi_from_book(book)
                 
         if options['collision'] != CALIBREONLY:
@@ -1108,12 +1112,22 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
 
         if options['collision'] == CALIBREONLY or \
                 ( (options['updatemeta'] or book['added']) and book['good'] ):
-            self.update_metadata(db, book['calibre_id'], book, mi, options)
+            try:
+                self.update_metadata(db, book['calibre_id'], book, mi, options)
+            except:
+                det_msg = "".join(traceback.format_exception(*sys.exc_info()))+"\nStory Details:\n%s"%pretty_book(book)
+                logger.error("Error Updating Metadata:\n%s"%det_msg)
+                error_dialog(self.gui,
+                             "Error Updating Metadata",
+                             "<p>An error has occurred while FFDL was updating calibre's metadata for <a href='%s'>%s</a>.</p>"%(book['url'],book['title'])+
+                             "The ebook has been updated, but the metadata has not.",
+                             det_msg=det_msg,
+                             show=True)
 
     def update_books_finish(self, book_list, options={}, showlist=True):
         '''Notify calibre about updated rows, update external plugins
         (Reading Lists & Count Pages) as configured'''
-        
+
         add_list = filter(lambda x : x['good'] and x['added'], book_list)
         add_ids = [ x['calibre_id'] for x in add_list ]
         update_list = filter(lambda x : x['good'] and not x['added'], book_list)
@@ -1141,7 +1155,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         if self.gui.cover_flow:
             self.gui.cover_flow.dataChanged()
 
-        if showlist: # don't use with anthology
+        if showlist and prefs['mark']: # don't use with anthology
             db = self.gui.current_db
             marked_ids = dict()
             marked_text = "ffdl_success"
@@ -1159,10 +1173,8 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                 self.gui.library_view.sort_by_named_field('marked', True)
                 
         self.gui.status_bar.show_message(_('Finished Adding/Updating %d books.'%(len(update_list) + len(add_list))), 3000)
-            
-        print("all done, remove temp dir.")
         remove_dir(options['tdir'])
-
+        
         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'])
@@ -1256,7 +1268,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         (good_list,bad_list,options) = payload
         total_good = len(good_list)
 
-        print("merge titles:\n%s"%"\n".join([ "%s %s"%(x['title'],x['listorder']) for x in good_list ]))
+        logger.debug("merge titles:\n%s"%"\n".join([ "%s %s"%(x['title'],x['listorder']) for x in good_list ]))
 
         good_list = sorted(good_list,key=lambda x : x['listorder'])
         bad_list = sorted(bad_list,key=lambda x : x['listorder'])
@@ -1282,8 +1294,8 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             # if still 'good', make a temp file to write the output to.
             tmp = PersistentTemporaryFile(suffix='.'+options['fileform'],
                                           dir=options['tdir'])
-            print("title:"+mergebook['title'])
-            print("outfile:"+tmp.name)
+            logger.debug("title:"+mergebook['title'])
+            logger.debug("outfile:"+tmp.name)
             mergebook['outfile'] = tmp.name
 
         self.get_epubmerge_plugin().do_merge(tmp.name,
@@ -1304,7 +1316,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
 
         self.gui.status_bar.show_message(_('FFDL Adding/Updating books.'))
 
-        if good_list or (bad_list and prefs['errorcol'] != '' and prefs['errorcol'] in self.gui.library_view.model().custom_columns):
+        if good_list or prefs['mark'] or (bad_list and prefs['errorcol'] != '' and prefs['errorcol'] in self.gui.library_view.model().custom_columns):
             LoopProgressDialog(self.gui,
                                good_list+bad_list,
                                partial(self.update_books_loop, options=options, db=self.gui.current_db),
@@ -1317,22 +1329,24 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         '''Update custom error column if configured.'''
         (empty_list,book_list,options)=payload
         custom_columns = self.gui.library_view.model().custom_columns
-        if prefs['errorcol'] != '' and prefs['errorcol'] in custom_columns:
+        if prefs['mark'] or (prefs['errorcol'] != '' and prefs['errorcol'] in custom_columns):
             self.previous = self.gui.library_view.currentIndex() # used by update_books_finish.
             self.gui.status_bar.show_message(_('Adding/Updating %s BAD books.'%len(book_list)))
             label = custom_columns[prefs['errorcol']]['label']
             LoopProgressDialog(self.gui,
                                book_list,
                                partial(self.update_error_column_loop, db=self.gui.current_db, label=label),
-                               partial(self.update_books_finish, options=options, showlist=False),
+                               partial(self.update_books_finish, options=options),
                                init_label="Updating calibre for BAD FanFiction stories...",
                                win_title="Update calibre for BAD FanFiction stories",
                                status_prefix="Updated")
 
     def update_error_column_loop(self,book,db=None,label='errorcol'):
         if book['calibre_id']:
-            print("add/update bad %s %s %s"%(book['title'],book['url'],book['comment']))
-            db.set_custom(book['calibre_id'], book['comment'], label=label, commit=True)
+            custom_columns = self.gui.library_view.model().custom_columns
+            if (prefs['errorcol'] != '' and prefs['errorcol'] in custom_columns):
+                logger.debug("add/update bad %s %s %s"%(book['title'],book['url'],book['comment']))
+                db.set_custom(book['calibre_id'], book['comment'], label=label, commit=True)
 
     def add_book_or_update_format(self,book,options,prefs,mi=None):
         db = self.gui.current_db
@@ -1361,7 +1375,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             fmts = db.formats(book['calibre_id'], index_is_id=True).split(',')
             for fmt in fmts:
                 if fmt != formmapping[options['fileform']]:
-                    print("remove f:"+fmt)
+                    logger.debug("remove f:"+fmt)
                     db.remove_format(book['calibre_id'], fmt, index_is_id=True)#, notify=False
 
         return book_id
@@ -1370,14 +1384,23 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         oldmi = db.get_metadata(book_id,index_is_id=True)
         if prefs['keeptags']:
             old_tags = db.get_tags(book_id)
+            #print("old_tags:%s"%old_tags)
+            #print("mi.tags:%s"%mi.tags)
             # remove old Completed/In-Progress only if there's a new one.
             if 'Completed' in mi.tags or 'In-Progress' in mi.tags:
                 old_tags = filter( lambda x : x not in ('Completed', 'In-Progress'), old_tags)
                 # remove old Last Update tags if there are new ones.
             if len(filter( lambda x : not x.startswith("Last Update"), mi.tags)) > 0:
                 old_tags = filter( lambda x : not x.startswith("Last Update"), old_tags)
+                
             # mi.tags needs to be list, but set kills dups.
-            mi.tags = list(set(list(old_tags)+mi.tags))
+            # this way also removes case-mismatched dups, keeping old_tags version.
+            foldedcase_tags = dict()
+            for t in list(mi.tags) + list(old_tags):
+                foldedcase_tags[t.lower()] = t
+
+            mi.tags = foldedcase_tags.values()   
+            #print("mi.tags:%s"%mi.tags)
 
         if book['all_metadata']['langcode']:
             mi.languages=[book['all_metadata']['langcode']]
@@ -1393,7 +1416,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                 try:
                     db.set_cover(book_id, epubmi.cover_data[1])
                 except:
-                    print("Failed to set_cover, skipping")
+                    logger.info("Failed to set_cover, skipping")
 
         # implement 'newonly' flags here by setting to the current
         # value again.
@@ -1406,10 +1429,12 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                         try:
                             mi.__setattr__(col,oldmi.__getattribute__(col))
                         except AttributeError:
-                            print("AttributeError? %s"%col)
+                            logger.warn("AttributeError? %s"%col)
                             pass
 
         db.set_metadata(book_id,mi)
+        # mi.authors gets run through the string_to_authors and split on '&' ',' 'and' and 'with'
+        db.set_authors(book_id,book['author']) # author is a list.
 
         # do configured column updates here.
         #print("all_metadata: %s"%book['all_metadata'])
@@ -1419,25 +1444,26 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         for col, meta in prefs['custom_cols'].iteritems():
             #print("setting %s to %s"%(col,meta))
             if col not in custom_columns:
-                print("%s not an existing column, skipping."%col)
+                logger.debug("%s not an existing column, skipping."%col)
                 continue
             coldef = custom_columns[col]
             if col in prefs['custom_cols_newonly'] and prefs['custom_cols_newonly'][col] and not book['added']:
-                print("Skipping custom column(%s) update, set to New Books Only"%coldef['name'])
+                logger.debug("Skipping custom column(%s) update, set to New Books Only"%coldef['name'])
                 continue
             if not meta.startswith('status-') and meta not in book['all_metadata'] or \
                     meta.startswith('status-') and 'status' not in book['all_metadata']:
-                print("No value for %s, skipping custom column(%s) update."%(meta,coldef['name']))
+                logger.debug("No value for %s, skipping custom column(%s) update."%(meta,coldef['name']))
                 continue
             if meta not in permitted_values[coldef['datatype']]:
-                print("%s not a valid column type for %s, skipping."%(col,meta))
+                logger.debug("%s not a valid column type for %s, skipping."%(col,meta))
                 continue
             label = coldef['label']
             if coldef['datatype'] in ('enumeration','text','comments','datetime','series'):
-                db.set_custom(book_id, book['all_metadata'][meta], label=label, commit=False)
+                db.set_custom(book_id, book['all_metadata'][meta], label, commit=False)
             elif coldef['datatype'] in ('int','float'):
                 num = unicode(book['all_metadata'][meta]).replace(",","")
-                db.set_custom(book_id, num, label=label, commit=False)
+                if num != '':
+                    db.set_custom(book_id, num, label=label, commit=False)
             elif coldef['datatype'] == 'bool' and meta.startswith('status-'):
                 if meta == 'status-C':
                     val = book['all_metadata']['status'] == 'Completed'
@@ -1457,14 +1483,11 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                     if "," in custcol:
                         (custcol,flag) = map( lambda x: x.strip(), custcol.split(",") )
 
-                    print("meta:(%s) => custcol:(%s), flag(%s) "%(meta,custcol,flag))
-                    
                     if meta not in book['all_metadata']:
-                        print("No value for %s, skipping custom column(%s) update."%(meta,custcol))
+                        logger.debug("No value for %s, skipping custom column(%s) update."%(meta,custcol))
                         continue
                     
                     if custcol not in custom_columns:
-                        print("No custom column(%s), skipping."%(custcol))
                         continue
                     else:
                         coldef = custom_columns[custcol]
@@ -1479,7 +1502,8 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                                 val = unicode(book['all_metadata'][meta]).replace(",","")
                         else:
                             val = book['all_metadata'][meta]
-                        db.set_custom(book_id, val, label=label, commit=False)
+                        if val != '':
+                            db.set_custom(book_id, val, label=label, commit=False)
 
                     if flag == 'a':
                         vallist = []
@@ -1501,12 +1525,26 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         # Moved down so author's already in the DB.
         if 'authorUrl' in book['all_metadata']:
             authurls = book['all_metadata']['authorUrl'].split(", ")
-            for i, auth in enumerate(book['author']):
-                #print("===Update author url for %s to %s"%(auth,authurls[i]))
-                autid=db.get_author_id(auth)
-                db.set_link_field_for_author(autid, unicode(authurls[i]),
-                                             commit=False, notify=False)
+            authorlist = [ a.replace('&',';') for a in book['author'] ]
+            if hasattr(db, 'new_api'): # new_api starts in calibre 1.0.0
+                authorids = db.new_api.get_item_ids('authors',authorlist)
+                authordata = db.new_api.author_data(authorids.values())
+                # print("\n\nauthorids:%s"%authorids)
+                # print("authordata:%s"%authordata)
 
+                author_id_to_link_map = dict()
+                for i, author in enumerate(authorlist):
+                    author_id_to_link_map[authorids[author]] = authurls[i]
+
+                # print("author_id_to_link_map:%s\n\n"%author_id_to_link_map)
+                db.new_api.set_link_for_authors(author_id_to_link_map)
+            else:
+                # keep for pre-calibre 1.0.0
+                for i, auth in enumerate(authorlist):
+                    #print("===Update author url for %s to %s"%(auth,authurls[i]))
+                    autid=db.get_author_id(auth)
+                    db.set_link_field_for_author(autid, unicode(authurls[i]),
+                                             commit=False, notify=False)
         db.commit()
 
         if 'Generate Cover' in self.gui.iactions and (book['added'] or not prefs['gcnewonly']):
@@ -1534,9 +1572,9 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                             break
 
                 if setting_name:
-                    print("Generate Cover Setting from generate_cover_settings(%s)"%line)
+                    logger.debug("Generate Cover Setting from generate_cover_settings(%s)"%line)
                     if setting_name not in gc_plugin.get_saved_setting_names():
-                        print("GC Name %s not found, discarding! (check personal.ini for typos)"%setting_name)
+                        logger.info("GC Name %s not found, discarding! (check personal.ini for typos)"%setting_name)
                         setting_name = None
                 
             if not setting_name and book['all_metadata']['site'] in prefs['gc_site_settings']:
@@ -1546,7 +1584,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                 setting_name =  prefs['gc_site_settings']['Default']
                 
             if setting_name:
-                print("Running Generate Cover with settings %s."%setting_name)
+                logger.debug("Running Generate Cover with settings %s."%setting_name)
                 realmi = db.get_metadata(book_id, index_is_id=True)
                 gc_plugin.generate_cover_for_book(realmi,saved_setting_name=setting_name)
 
@@ -1606,6 +1644,14 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
 
     def make_mi_from_book(self,book):
         mi = MetaInformation(book['title'],book['author']) # author is a list.
+        if prefs['suppressauthorsort']:
+            # otherwise author names will have calibre's sort algs
+            # applied automatically.
+            mi.author_sort = ' & '.join(book['author'])
+        if prefs['suppresstitlesort']:
+            # otherwise titles will have calibre's sort algs applied
+            # automatically.
+            mi.title_sort = book['title']
         mi.set_identifiers({'url':book['url']})
         mi.publisher = book['publisher']
         mi.tags = book['tags']
@@ -1852,11 +1898,11 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                 book['title'] = series
                 for sr in serieslist:
                     if series != sr:
-                        book['title'] = deftitle;
+                        book['title'] = deftitle
                         break
             
             configuration = get_ffdl_config(book['url'],fileform)
-            print("anthology_title_pattern:%s"%configuration.getConfig('anthology_title_pattern'))
+            logger.debug("anthology_title_pattern:%s"%configuration.getConfig('anthology_title_pattern'))
             if configuration.getConfig('anthology_title_pattern'):
                 tmplt = Template(configuration.getConfig('anthology_title_pattern'))
                 book['title'] = tmplt.safe_substitute({'title':book['title']}).encode('utf8')
@@ -1891,3 +1937,17 @@ def split_text_to_urls(urls):
 def escapehtml(txt):
     return txt.replace("&","&amp;").replace(">","&gt;").replace("<","&lt;")
         
+def pretty_book(d, indent=0, spacer='     '):
+    kindent = spacer * indent
+
+    # if isinstance(d, list):
+    #     return '\n'.join([(pretty_book(v, indent, spacer)) for v in d])
+
+    if isinstance(d, dict):
+        for k in ('password','username'):
+            if k in d and d[k]:
+                d[k]='<was set, removed for security>'
+        return '\n'.join(['%s%s:\n%s' % (kindent, k, pretty_book(v, indent + 1, spacer)) 
+                          for k, v in d.items()])
+    return "%s%s"%(kindent, d)
+

calibre-plugin/jobs.py

@@ -8,6 +8,9 @@ __copyright__ = '2012, Jim Miller'
 __copyright__ = '2011, Grant Drake <grant.drake@gmail.com>'
 __docformat__ = 'restructuredtext en'
 
+import logging
+logger = logging.getLogger(__name__)
+
 import time, os, traceback
 
 from StringIO import StringIO
@@ -38,13 +41,13 @@ def do_download_worker(book_list, options,
     '''
     server = Server(pool_size=cpus)
 
-    print(options['version'])
+    logger.info(options['version'])
     total = 0
     alreadybad = []
     # Queue all the jobs
-    print("Adding jobs for URLs:")
+    logger.info("Adding jobs for URLs:")
     for book in book_list:
-        print("%s"%book['url'])
+        logger.info("%s"%book['url'])
         if book['good']:
             total += 1
             args = ['calibre_plugins.fanfictiondownloader_plugin.jobs',
@@ -87,19 +90,19 @@ def do_download_worker(book_list, options,
         count = count + 1
         notification(float(count)/total, '%d of %d stories finished downloading'%(count,total))
         # Add this job's output to the current log
-        print('Logfile for book ID %s (%s)'%(book_id, job._book['title']))
-        print(job.details)
+        logger.info('Logfile for book ID %s (%s)'%(book_id, job._book['title']))
+        logger.info(job.details)
 
         if count >= total:
             # All done!  Output some lists for convenience of some users.
-            print("Successfully downloaded:")
+            logger.info("Successfully downloaded:")
             for book in book_list:
                 if book['good']:
-                    print("%s %s"%(book['title'],book['url']))
-            print("\nUnsuccessful:")
+                    logger.info("%s %s"%(book['title'],book['url']))
+            logger.info("\nUnsuccessful:")
             for book in book_list:
                 if not book['good']:
-                    print("%s %s"%(book['title'],book['url']))
+                    logger.info("%s %s"%(book['title'],book['url']))
             break
 
     server.close()
@@ -147,7 +150,7 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
 
         ## No need to download at all.  Shouldn't ever get down here.
         if options['collision'] in (CALIBREONLY):
-            print("Skipping CALIBREONLY 'update' down inside worker--this shouldn't be happening...")
+            logger.info("Skipping CALIBREONLY 'update' down inside worker--this shouldn't be happening...")
             book['comment'] = 'Metadata collected.'
             
         ## checks were done earlier, it's new or not dup or newer--just write it.
@@ -170,7 +173,7 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
                 if adapter.logfile:
                     adapter.logfile = adapter.logfile.replace("span id","span notid")
             
-            print("write to %s"%outfile)
+            logger.info("write to %s"%outfile)
             writer.writeStory(outfilename=outfile, forceOverwrite=True)
             book['comment'] = 'Download %s completed, %s chapters.'%(options['fileform'],story.getMetadata("numChapters"))
             
@@ -198,9 +201,13 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
             # dup handling from ffdl_plugin needed for anthology updates.
             if chaptercount > urlchaptercount:
                 raise NotGoingToDownload("Existing epub contains %d chapters, web site only has %d. Use Overwrite to force update." % (chaptercount,urlchaptercount),'dialog_error.png')
-                            
-            print("Do update - epub(%d) vs url(%d)" % (chaptercount, urlchaptercount))
-            print("write to %s"%outfile)
+
+            if not (options['collision'] == UPDATEALWAYS and chaptercount == urlchaptercount) \
+                    and adapter.getConfig("do_update_hook"):
+                chaptercount = adapter.hookForUpdates(chaptercount)
+
+            logger.info("Do update - epub(%d) vs url(%d)" % (chaptercount, urlchaptercount))
+            logger.info("write to %s"%outfile)
 
             writer.writeStory(outfilename=outfile, forceOverwrite=True)
             
@@ -222,7 +229,7 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
             
             log = Log(level=Log.DEBUG)
             # report = []
-            polish({outfile:outfile}, opts, log, print) # report.append
+            polish({outfile:outfile}, opts, log, logger.info) # report.append
         
     except NotGoingToDownload as d:
         book['good']=False
@@ -234,7 +241,7 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
         book['comment']=unicode(e)
         book['icon']='dialog_error.png'
         book['status'] = 'Error'
-        print("Exception: %s:%s"%(book,unicode(e)))
+        logger.info("Exception: %s:%s"%(book,unicode(e)))
         traceback.print_exc()
         
     #time.sleep(10)

calibre-plugin/prefs.py

@@ -30,6 +30,9 @@ default_prefs['updatemeta'] = True
 default_prefs['updatecover'] = False
 default_prefs['updateepubcover'] = False
 default_prefs['keeptags'] = False
+default_prefs['suppressauthorsort'] = False
+default_prefs['suppresstitlesort'] = False
+default_prefs['mark'] = False
 default_prefs['showmarked'] = False
 default_prefs['urlsfromclip'] = True
 default_prefs['updatedefault'] = True
@@ -40,6 +43,7 @@ default_prefs['adddialogstaysontop'] = False
 default_prefs['includeimages'] = False
 default_prefs['lookforurlinhtml'] = False
 default_prefs['checkforseriesurlid'] = True
+default_prefs['checkforurlchange'] = True
 default_prefs['injectseries'] = False
 default_prefs['smarten_punctuation'] = False
 

defaults.ini

@@ -16,7 +16,22 @@
 [defaults]
 
 ## [defaults] section applies to all formats and sites but may be
-## overridden at several levels
+## overridden at several levels.  Example:
+
+## [defaults]
+## titlepage_entries: category,genre, status
+## [www.whofic.com]
+## # overrides defaults.
+## titlepage_entries: category,genre, status,dateUpdated,rating
+## [epub]
+## # overrides defaults & site section
+## titlepage_entries: category,genre, status,datePublished,dateUpdated,dateCreated
+## [www.whofic.com:epub]
+## # overrides defaults, site section & format section
+## titlepage_entries: category,genre, status,datePublished
+## [overrides]
+## # overrides all other sections
+## titlepage_entries: category
 
 ## Some sites also require the user to confirm they are adult for
 ## adult content.  Uncomment by removing '#' in front of is_adult.
@@ -152,6 +167,17 @@ extratags: FanFiction
 #extraships:
 #extrawarnings:
 
+## Add this to genre if there's more than one category.
+#add_genre_when_multi_category: Crossover
+
+## default_value_(entry) can be used to set the value for a metadata
+## entry when no value has been found on the site.  For example, some
+## sites doesn't have a status metadatum.  If uncommented, this will
+## use 'Unknown' for status when no status is found.
+#default_value_status:Unknown
+## Can also be used for other metadata values
+#default_value_category:FanFiction
+
 ## number of seconds to sleep between calls to the story site.  May by
 ## useful if pulling large numbers of stories or if the site is slow.
 #slow_down_sleep_time:0.5
@@ -194,6 +220,11 @@ extratags: FanFiction
 ## doesn't work on some devices either.)
 #replace_hr: false
 
+## Some sites/authors/stories use br tags instead of p tags for
+## paragraphs.  This feature uses some heuristics to find and replace
+## br paragraphs with p tags while preserving scene breaks.
+#replace_br_with_p: false
+
 ## If set false, the summary will have all html stripped.
 ## Both this and include_images must be true to get images in the
 ## summary.
@@ -259,6 +290,8 @@ sort_ships:false
 ## you added calibre_author: keep_in_order_calibre_author:true
 #keep_in_order_author:true
 
+## User-agent
+user_agent:FFDL/1.7
 
 ## Each output format has a section that overrides [defaults]
 [html]
@@ -447,8 +480,8 @@ nook_img_fix:true
 ## mobi TOC cannot be turned off right now.
 #include_tocpage: true
 
-## Each site has a section that overrides [defaults] *and* the format
-## sections test1.com specifically is not a real story site.  Instead,
+## Each site has a section that overrides [defaults].
+## test1.com specifically is not a real story site.  Instead,
 ## it is a fake site for testing configuration and output.  It uses
 ## URLs like: http://test1.com?sid=12345
 [test1.com]
@@ -505,7 +538,8 @@ extratags: FanFiction,Testing,HTML
 #is_adult:true
 
 ## AO3 adapter defines a few extra metadata entries.
-extra_valid_entries:fandoms,freeformtags,freefromtags,ao3categories,comments,kudos,hits,bookmarks,collections
+## If there's ever more than 4 series, add series04,series04Url etc.
+extra_valid_entries:fandoms,freeformtags,freefromtags,ao3categories,comments,kudos,hits,bookmarks,collections,series00,series01,series02,series03,series00Url,series01Url,series02Url,series03Url
 fandoms_label:Fandoms
 freeformtags_label:Freeform Tags
 freefromtags_label:Freeform Tags
@@ -521,7 +555,7 @@ bookmarks_label:Bookmarks
 include_in_freefromtags:freeformtags
 
 ## adds to titlepage_entries instead of replacing it.
-#extra_titlepage_entries: fandoms,freeformtags,ao3categories,comments,kudos,hits,bookmarks
+#extra_titlepage_entries: fandoms,freeformtags,ao3categories,comments,kudos,hits,bookmarks,series00,series01,series02,series03,series00Url,series01Url,series02Url,series03Url
 
 ## adds to include_subject_tags instead of replacing it.
 #extra_subject_tags:fandoms,freeformtags,ao3categories
@@ -739,6 +773,23 @@ extraships:Harry Potter/Hermione Granger
 #username:YourName
 #password:yourpassword
 
+[fictionpad.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
+
+extra_valid_entries:followers,comments,views,likes,dislikes
+#extra_titlepage_entries:followers,comments,views,likes,dislikes
+
+followers_label:Followers
+comments_label:Comments
+views_label:Views
+likes_label:Likes
+dislikes_label:Dislikes
+
 [finestories.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -747,6 +798,24 @@ extraships:Harry Potter/Hermione Granger
 #username:YourName
 #password:yourpassword
 
+[storiesonline.net]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Clear FanFiction from defaults, site is original fiction.
+extratags:
+
+extra_valid_entries:size,universe,codes
+#extra_titlepage_entries:size,universe,codes
+
+size_label:Size
+universe_label:Universe
+codes_label:Codes
+
 [grangerenchanted.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
@@ -789,6 +858,10 @@ extracategories:Highlander
 ## Site dedicated to these categories/characters/ships
 extracategories:In Death
 
+## some sites include images that we don't ever want becoming the
+## cover image.  This lets you exclude them.
+cover_exclusion_regexp:/public/style_emoticons/.*
+
 [ksarchive.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Star Trek
@@ -1096,6 +1169,7 @@ context_label:Context
 type_label:Type of Couple
 
 [www.fanfiction.net]
+user_agent:
 ## fanfiction.net's 'cover' images are really just tiny thumbnails.
 ## Change this to false to use them anyway.
 never_make_cover: true
@@ -1104,6 +1178,10 @@ never_make_cover: true
 ## for examples of how to use them.
 extra_valid_entries:reviews,favs,follows
 
+## ffnet uses 'Pairings', not 'Relationship', stating they don't have
+## to be romantic pairings.
+ships_label:Pairings
+
 [www.fanfiktion.de]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -1126,7 +1204,12 @@ extracategories:Harry Potter
 ## fictionally.org storyIds are not unique.  Combine with authorId.
 output_filename: ${title}-${siteabbrev}_${authorId}_${storyId}${formatext}
 
+## fictionalley.org doesn't have a status metadatum.  If uncommented,
+## this will be used for status.
+#default_value_status:Unknown
+
 [www.fictionpress.com]
+user_agent:
 ## Clear FanFiction from defaults, fictionpress.com is original fiction.
 extratags:
 
@@ -1148,12 +1231,13 @@ extracategories:My Little Pony: Friendship is Magic
 
 ## Extra metadata that this adapter knows about.  See [dramione.org]
 ## for examples of how to use them.
-extra_valid_entries:likes,dislikes,views,total_views,short_description
+extra_valid_entries:likes,dislikes,views,total_views,short_description,groups
 likes_label:Likes
 dislikes_label:Dislikes
 views_label:Highest Single Chapter Views
 total_views_label:Total Views
 short_description_label:Short Summary
+groups_label:Groups
 
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
@@ -1165,6 +1249,13 @@ short_description_label:Short Summary
 ## when a password is required rather than prompting every time.
 #fail_on_password: false
 
+## fimfiction.net stories allow chapters to be added out of order.  So
+## the newest chapter may not be the last one.  FFDL update doesn't
+## like that.  If do_update_hook is uncommented and set true, the
+## adapter will discard all existing chapters from the newest one on
+## when updating to enforce accurate chapters.
+#do_update_hook:false
+
 [www.harrypotterfanfiction.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter

downloader.py

@@ -270,7 +270,6 @@ def main(argv,
            elif chaptercount == 0:
                print "%s doesn't contain any recognizable chapters, probably from a different source.  Not updating." % (output_filename)
            else:
-               print "Do update - epub(%d) vs url(%d)" % (chaptercount, urlchaptercount)
                if not options.metaonly:
 
                    # update now handled by pre-populating the old
@@ -284,6 +283,12 @@ def main(argv,
                     adapter.calibrebookmark,
                     adapter.logfile) = get_update_data(output_filename)
 
+                   print "Do update - epub(%d) vs url(%d)" % (chaptercount, urlchaptercount)
+
+                   if not (options.update and chaptercount == urlchaptercount) \
+                           and adapter.getConfig("do_update_hook"):
+                       chaptercount = adapter.hookForUpdates(chaptercount)
+
                    writeStory(configuration,adapter,"epub")
                    
        else:

fanficdownloader/__init__.py

@@ -4,13 +4,16 @@ try:
     # just a way to switch between web service and CLI/PI
     import google.appengine.api 
 except:
-    import sys
-    if sys.version_info >= (2, 7):
-        import logging
-        logger = logging.getLogger(__name__)
-        loghandler=logging.StreamHandler()
-        loghandler.setFormatter(logging.Formatter("FFDL:%(levelname)s:%(filename)s(%(lineno)d):%(message)s"))
-        logger.addHandler(loghandler)
-        loghandler.setLevel(logging.DEBUG)
-        logger.setLevel(logging.DEBUG)
+    try: # just a way to switch between CLI and PI
+        import calibre.constants
+    except:
+        import sys
+        if sys.version_info >= (2, 7):
+            import logging
+            logger = logging.getLogger(__name__)
+            loghandler=logging.StreamHandler()
+            loghandler.setFormatter(logging.Formatter("FFDL:%(levelname)s:%(filename)s(%(lineno)d):%(message)s"))
+            logger.addHandler(loghandler)
+            loghandler.setLevel(logging.DEBUG)
+            logger.setLevel(logging.DEBUG)
 

fanficdownloader/adapters/__init__.py

@@ -119,6 +119,8 @@ import adapter_nickandgregnet
 import adapter_potterheadsanonymouscom
 import adapter_simplyundeniablecom
 import adapter_scarheadnet
+import adapter_fictionpadcom
+import adapter_storiesonlinenet
 
 ## 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_adastrafanficcom.py

@@ -90,7 +90,7 @@ class AdAstraFanficComSiteAdapter(BaseSiteAdapter):
 
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php"))

fanficdownloader/adapters/adapter_archiveofourownorg.py

@@ -163,7 +163,7 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r"^/works/\d+$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
 		
         # Find authorid and URL from... author url.
         alist = soup.findAll('a', href=re.compile(r"^/users/\w+/pseuds/\w+"))
@@ -210,10 +210,7 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
         if a != None:
             warnings = a.findAll('a',{'class':"tag"})
             for warning in warnings:
-                if warning.string == "Author Chose Not To Use Archive Warnings":
-                    warning.string = "No Archive Warnings Apply"
-                if warning.string != "No Archive Warnings Apply":
-                    self.story.addToList('warnings',warning.string)
+                self.story.addToList('warnings',warning.string)
 		
         a = metasoup.find('dd',{'class':"freeform tags"})
         if a != None:
@@ -288,25 +285,25 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
 
 		
-        try:
-            # Find Series name from series URL.
-            a = metasoup.find('dd',{'class':"series"})
-            b = a.find('a', href=re.compile(r"/series/\d+"))
-            series_name = b.string
-            series_url = 'http://'+self.host+b['href']
-            series_index = int(a.text.split(' ')[1])
-            self.setSeries(series_name, series_index)
-            self.story.setMetadata('seriesUrl',series_url)
-            
-        except:
-            # I find it hard to care if the series parsing fails
-            pass
+        # Find Series name from series URL.
+        ddseries = metasoup.find('dd',{'class':"series"})
+
+        if ddseries:
+            for i, a in enumerate(ddseries.findAll('a', href=re.compile(r"/series/\d+"))):
+                series_name = stripHTML(a)
+                series_url = 'http://'+self.host+a['href']
+                series_index = int(stripHTML(a.previousSibling).replace(', ','').split(' ')[1]) # "Part # of" or ", Part #"
+                self.story.setMetadata('series%02d'%i,"%s [%s]"%(series_name,series_index))
+                self.story.setMetadata('series%02dUrl'%i,series_url)
+                if i == 0:
+                    self.setSeries(series_name, series_index)
+                    self.story.setMetadata('seriesUrl',series_url)
 
     # grab the text for an individual chapter.
     def getChapterText(self, url):
         logger.debug('Getting chapter text from: %s' % url)
 		
-        chapter=bs.BeautifulSoup('<div class="story"></div>')
+        chapter=bs.BeautifulSoup('<div class="story"></div>').find('div')
         data = self._fetchUrl(url)
         soup = bs.BeautifulSoup(data,selfClosingTags=('br','hr'))
 		

fanficdownloader/adapters/adapter_archiveskyehawkecom.py

@@ -101,7 +101,7 @@ class ArchiveSkyeHawkeComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('div', {'class':"story border"}).find('span',{'class':'left'})
-        title=a.text.split('"')[1]
+        title=stripHTML(a).split('"')[1]
         self.story.setMetadata('title',title)
         
         # Find authorid and URL from... author url.

fanficdownloader/adapters/adapter_ashwindersycophanthexcom.py

@@ -157,7 +157,7 @@ class AshwinderSycophantHexComAdapter(BaseSiteAdapter):
         for info in asoup.findAll('table', {'width' : '100%', 'bordercolor' : re.compile(r'#')}):
             a = info.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
             if a != None:
-                self.story.setMetadata('title',a.string)
+                self.story.setMetadata('title',stripHTML(a))
                 break
 		
 

fanficdownloader/adapters/adapter_asr3slashzoneorg.py

@@ -128,7 +128,7 @@ class Asr3SlashzoneOrgAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_bloodtiesfancom.py

@@ -207,7 +207,7 @@ class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_castlefansorg.py

@@ -180,7 +180,7 @@ class CastleFansOrgAdapter(BaseSiteAdapter): # XXX
         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)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_chaossycophanthexcom.py

@@ -116,7 +116,7 @@ class ChaosSycophantHexComAdapter(BaseSiteAdapter):
         ## Title
         pt = soup.find('div', {'id' : 'pagetitle'})
         a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.text)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = pt.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_checkmatedcom.py

@@ -143,11 +143,11 @@ class CheckmatedComAdapter(BaseSiteAdapter):
         # Now go hunting for all the meta data and the chapter list.
 
         ## Title
-        a = soup.findAll('span', {'class' : 'storytitle'})
-        self.story.setMetadata('title',a[0].string)
+        a = soup.find('span', {'class' : 'storytitle'})
+        self.story.setMetadata('title',stripHTML(a))
 
         # Find authorid and URL from... author url.
-        a = a[1].find('a', href=re.compile(r"authors.php\?name\=\w+"))
+        a = a.parent.find('a', href=re.compile(r"authors.php\?name\=\w+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
         self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
         self.story.setMetadata('author',a.string)

fanficdownloader/adapters/adapter_darksolaceorg.py

@@ -94,11 +94,10 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
         else:
             params['penname'] = self.getConfig("username")
             params['password'] = self.getConfig("password")
-        params['rememberme'] = '1'
         params['action'] = 'login'
         params['submit'] = 'Submit'
     
-        loginUrl = 'http://' + self.getSiteDomain() + '/elysian/user.php'
+        loginUrl = 'http://www.' + self.getSiteDomain() + '/elysian/user.php'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['penname']))
     

fanficdownloader/adapters/adapter_destinysgatewaycom.py

@@ -131,7 +131,7 @@ class DestinysGatewayComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_dokugacom.py

@@ -164,7 +164,7 @@ class DokugaComAdapter(BaseSiteAdapter):
         aut.extract()
         
         a = a.string[:(len(a.string)-4)]
-        self.story.setMetadata('title',a)
+        self.story.setMetadata('title',stripHTML(a))
 
         # Find the chapters:
         chapters = soup.find('select').findAll('option')
@@ -205,7 +205,6 @@ class DokugaComAdapter(BaseSiteAdapter):
             
             a=div.text.split('Category: ')
             if len(a) == 2: self.story.addToList('category', a[1].split('&')[0])
-            self.story.addToList('category', 'Fanfiction')
         
             a=div.text.split('Created: ')
             if len(a) == 2: self.story.setMetadata('datePublished', makeDate(stripHTML(a[1].split('&')[0]), self.dateformat))

fanficdownloader/adapters/adapter_dotmoonnet.py

@@ -141,7 +141,7 @@ class DotMoonNetAdapter(BaseSiteAdapter):
         
         ## Title
         a = body.find('b')
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url. http://www.dotmoon.net/board/index.php?action=profile;u=1'
         a = body.find('a', href=re.compile(r"index.php\?action=profile;u=\d+"))

fanficdownloader/adapters/adapter_dracoandginnycom.py

@@ -170,7 +170,7 @@ class DracoAndGinnyComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_dramioneorg.py

@@ -154,7 +154,7 @@ class DramioneOrgAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_efictionestelielde.py

@@ -104,7 +104,7 @@ class EfictionEstelielDeAdapter(BaseSiteAdapter):
         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)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_erosnsapphosycophanthexcom.py

@@ -132,7 +132,7 @@ class ErosnSapphoSycophantHexComAdapter(BaseSiteAdapter):
         ## Title
         pt = soup.find('div', {'id' : 'pagetitle'})
         a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.text)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = pt.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_fanfictionnet.py

@@ -199,7 +199,7 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         for g in genrelist:
             #logger.debug("g:(%s)"%g)
             if g.strip() not in ffnetgenres:
-                logger.info("g not in ffnetgenres")
+                #logger.info("g not in ffnetgenres")
                 goodgenres=False
         if goodgenres:
             self.story.extendList('genre',genrelist)
@@ -222,14 +222,18 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
             elif  metalist[0].startswith('Words'):
                 self.story.setMetadata('numWords',metalist[0].split(':')[1].strip())
             elif not donechars:
-                self.story.extendList('characters',metalist[0].split('&'))
+                # with 'pairing' support, pairings are bracketed w/o comma after
+                # [Caspian X, Lucy Pevensie] Edmund Pevensie, Peter Pevensie
+                self.story.extendList('characters',metalist[0].replace('[','').replace(']',',').split(','))
+
+                l = metalist[0]
+                while '[' in l:
+                    self.story.addToList('ships',l[l.index('[')+1:l.index(']')].replace(', ','/'))
+                    l = l[l.index(']')+1:]
+
                 donechars = True
             metalist=metalist[1:]
 
-        # next might be characters, otherwise Reviews, Updated, Published, Words
-        # if not ( metalist[0].startswith('Reviews') or metalist[0].startswith('Updated') or metalist[0].startswith('Published') or metalist[0].startswith('Words') or metalist[0].startswith('Chapters') ):
-        #     self.story.extendList('characters',metalist[0].split('&'))
-        
         if 'Status: Complete' in metatext:
             self.story.setMetadata('status', 'Completed')
         else:
@@ -266,11 +270,11 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         return
 
     def getChapterText(self, url):
-        logger.debug('Getting chapter text from: %s' % url)
-        time.sleep(0.5) ## ffnet(and, I assume, fpcom) tends to fail
+        time.sleep(5.0) ## ffnet(and, I assume, fpcom) tends to fail
                         ## more if hit too fast.  This is in
                         ## additional to what ever the
                         ## slow_down_sleep_time setting is.
+        logger.debug('Getting chapter text from: %s' % url)
         data = self._fetchUrl(url)
 
         if "Please email this error message in full to <a href='mailto:support@fanfiction.com'>support@fanfiction.com</a>" in data:
@@ -281,10 +285,11 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         # don't care about anything before "<div class='storytextp"
         # (there's a space after storytextp, so no close quote(')) and
         # this kills any body tags.
-        if "<div class='storytextp" not in data:
+        divstr = "<div role='main'"
+        if divstr not in data:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
         else:
-            data = data[data.index("<div class='storytextp"):]
+            data = data[data.index(divstr):]
         data.replace("<body","<notbody").replace("<BODY","<NOTBODY")
         
         soup = bs.BeautifulSoup(data)

fanficdownloader/adapters/adapter_fictionalleyorg.py

@@ -111,7 +111,7 @@ class FictionAlleyOrgSiteAdapter(BaseSiteAdapter):
             url=self.url
             logger.debug("Normalizing to URL: "+url)
             ## title's right there...
-            self.story.setMetadata('title',storya.string)
+            self.story.setMetadata('title',stripHTML(storya))
             data = self._fetchUrl(url)
             soup = bs.BeautifulSoup(data)
             chapterlinklist = soup.findAll('a',{'class':'chapterlink'})
@@ -121,7 +121,7 @@ class FictionAlleyOrgSiteAdapter(BaseSiteAdapter):
             ## same way.
             chapsoup = bs.BeautifulSoup(chapterdata)
             storya = chapsoup.find('div',{'class':'breadcrumbs'}).findAll('a')[1]
-            self.story.setMetadata('title',storya.string)
+            self.story.setMetadata('title',stripHTML(storya))
             del chapsoup
 
         del chapterdata

fanficdownloader/adapters/adapter_fictionpadcom.py

@@ -0,0 +1,192 @@
+# -*- 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 time
+import json
+
+from .. import BeautifulSoup as bs
+#from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+class FictionPadSiteAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+        self.story.setMetadata('siteabbrev','fpad')
+        self.dateformat = "%Y-%m-%dT%H:%M:%SZ"
+        self.is_adult=False
+        self.username = None
+        self.password = None
+        # get storyId from url--url validation guarantees query correct
+        m = re.match(self.getSiteURLPattern(),url)
+        if m:
+            self.story.setMetadata('storyId',m.group('id'))
+            
+            # normalized story URL.
+            self._setURL("https://"+self.getSiteDomain()
+                         +"/author/"+m.group('author')
+                         +"/stories/"+self.story.getMetadata('storyId'))
+        else:
+            raise exceptions.InvalidStoryURL(url,
+                                             self.getSiteDomain(),
+                                             self.getSiteExampleURLs())
+
+    @staticmethod
+    def getSiteDomain():
+        return 'fictionpad.com'
+
+    @classmethod
+    def getSiteExampleURLs(self):
+        return "https://fictionpad.com/author/Author/stories/1234/Some-Title"
+    
+    def getSiteURLPattern(self):
+        # http://fictionpad.com/author/Serdd/stories/4275
+        return r"http(s)?://(www\.)?fictionpad\.com/author/(?P<author>[^/]+)/stories/(?P<id>\d+)"
+
+# <form method="post" action="/signin">
+#     <input name="authenticity_token" type="hidden" value="u+cfdXh46dRnwVnSlmE2B2BFmHgu760paqgBG6KQeos=" />
+#     <input type="hidden" name="remember" value="1">
+#     <strong class="help-start text-center">or with FictionPad</strong>
+#     <label class="control-label hidden-placeholder">Pseudonym or Email Address</label>
+#     <input name="login" class="input-block-level" type="text" placeholder="Pseudonym or Email Address" maxlength="50" required autofocus>
+#     <label class="control-label hidden-placeholder">Password</label>
+#     <input name="password" class="input-block-level" type="password" placeholder="Password" minlength="6" required>
+#     <button type="submit" class="btn btn-primary btn-block">Sign In</button>
+#     <p class="help-end">
+#         <a href="/passwordreset">Forgot your password?</a>
+#     </p>
+# </form>
+    def performLogin(self):
+        params = {}
+
+        if self.password:
+            params['login'] = self.username
+            params['password'] = self.password
+        else:
+            params['login'] = self.getConfig("username")
+            params['password'] = self.getConfig("password")
+        params['remember'] = '1'
+
+        loginUrl = 'http://' + self.getSiteDomain() + '/signin'
+        logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
+                                                              params['login']))
+
+        ## need to pull empty login page first to get authenticity_token
+        soup = bs.BeautifulSoup(self._fetchUrl(loginUrl))
+        params['authenticity_token']=soup.find('input', {'name':'authenticity_token'})['value']
+        
+        data = self._postUrl(loginUrl, params)
+
+        if "Invalid email/pseudonym and password combination." in data:
+            logger.info("Failed to login to URL %s as %s" % (loginUrl,
+                                                              params['login']))
+            raise exceptions.FailedToLogin(loginUrl,params['login'])
+            
+
+    def extractChapterUrlsAndMetadata(self):
+        # fetch the chapter.  From that we will get almost all the
+        # metadata and chapter list
+
+        url=self.url
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+            if "This is a mature story.  Please sign in to read it." in data:
+                self.performLogin()
+                data = self._fetchUrl(url)
+            
+            find = "wordyarn.config.page = "
+            data = data[data.index(find)+len(find):]
+            data = data[:data.index("</script>")]
+            data = data[:data.rindex(";")]
+            data = data.replace('tables:','"tables":')
+            tables = json.loads(data)['tables']
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(url)
+            else:
+                raise e
+
+        # looks like only one author per story allowed.
+        author = tables['users'][0]
+        story = tables['stories'][0]
+        story_ver = tables['story_versions'][0]
+        
+        self.story.setMetadata('authorId',author['id'])
+        self.story.setMetadata('author',author['display_name'])
+        self.story.setMetadata('authorUrl','https://'+self.host+'/author/'+author['display_name']+'/stories')
+
+        self.story.setMetadata('title',story_ver['title'])
+        self.setDescription(url,story_ver['description'])
+        
+        if not ('assets/story_versions/covers' in story_ver['profile_image_url@2x']):
+            self.setCoverImage(url,story_ver['profile_image_url@2x'])
+
+        self.story.setMetadata('datePublished',makeDate(story['published_at'], self.dateformat))
+        self.story.setMetadata('dateUpdated',makeDate(story['published_at'], self.dateformat))
+
+        self.story.setMetadata('followers',story['followers_count'])
+        self.story.setMetadata('comments',story['comments_count'])
+        self.story.setMetadata('views',story['views_count'])
+        self.story.setMetadata('likes',int(story['likes'])) # no idea why they floated these.
+        self.story.setMetadata('dislikes',int(story['dislikes']))
+
+        if story_ver['is_complete']:
+            self.story.setMetadata('status', 'Completed')
+        else:
+            self.story.setMetadata('status', 'In-Progress')
+
+        self.story.setMetadata('rating', story_ver['maturity_level'])
+        self.story.setMetadata('numWords', unicode(story_ver['word_count']))
+
+        for i in tables['fandoms']:
+            self.story.addToList('category',i['name'])
+        
+        for i in tables['genres']:
+            self.story.addToList('genre',i['name'])
+        
+        for i in tables['characters']:
+            self.story.addToList('characters',i['name'])
+
+        for c in tables['chapters']:
+            chtitle = "Chapter %d"%c['number']
+            if c['title']:
+                chtitle += " - %s"%c['title']
+            self.chapterUrls.append((chtitle,c['body_url']))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+            
+    def getChapterText(self, url):
+        logger.debug('Getting chapter text from: %s' % url)
+        if not url:
+            data = u"<em>This chapter has no text.</em>"
+        else:
+            data = self._fetchUrl(url)
+        soup = bs.BeautifulSoup(u"<div id='story'>"+data+u"</div>")
+        return self.utf8FromSoup(url,soup)
+    
+def getClass():
+    return FictionPadSiteAdapter
+

fanficdownloader/adapters/adapter_ficwadcom.py

@@ -116,7 +116,7 @@ class FicwadComSiteAdapter(BaseSiteAdapter):
 
         # title - first h4 tag will be title.
         titleh4 = soup.find('h4')
-        self.story.setMetadata('title', titleh4.a.string)
+        self.story.setMetadata('title', stripHTML(titleh4.a))
 
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"^/author/\d+"))

fanficdownloader/adapters/adapter_fimfictionnet.py

@@ -21,7 +21,6 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 import cookielib as cl
-from datetime import datetime
 import json
 
 from .. import BeautifulSoup as bs
@@ -42,6 +41,10 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
         self._setURL("http://"+self.getSiteDomain()+"/story/"+self.story.getMetadata('storyId')+"/")
         self.is_adult = False
         
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%d %b %Y"
+            
     @staticmethod
     def getSiteDomain():
         return 'www.fimfiction.net'
@@ -93,8 +96,10 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
         if "Warning: mysql_fetch_array(): supplied argument is not a valid MySQL result resource" in data:
             raise exceptions.StoryDoesNotExist(self.url)
 
-        if "/images/missing_story.png" in data:
-            raise exceptions.StoryDoesNotExist(self.url)
+        # Can cause problems if a missing story is referenced in a comment.
+        # Shouldn't be needed anyway.
+        # if "/images/missing_story.png" in data:
+        #     raise exceptions.StoryDoesNotExist(self.url)
         
         if "This story has been marked as having adult content." in data:
             raise exceptions.AdultCheckRequired(self.url)
@@ -117,7 +122,7 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
             
         ## Title
         a = soup.find('a', href=re.compile(r'^/story/'+self.story.getMetadata('storyId')))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # self.story.setMetadata("title", storyMetadata["title"])
         # if not storyMetadata["title"]:
@@ -185,14 +190,42 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
         hrstr="<hr />"
         descdivstr = '<div class="description">'+descdivstr[descdivstr.index(hrstr)+len(hrstr):]
         self.setDescription(self.url,descdivstr)
-        
+
+        # Can't trust dates from API anymore I'm told.
         # Dates are in Unix time
         # Take the publish date from the first chapter posted
-        rawDatePublished = storyMetadata["chapters"][0]["date_modified"]
-        self.story.setMetadata("datePublished", datetime.fromtimestamp(rawDatePublished))
-        rawDateUpdated = storyMetadata["date_modified"]
-        self.story.setMetadata("dateUpdated", datetime.fromtimestamp(rawDateUpdated))
+        # rawDatePublished = storyMetadata["chapters"][0]["date_modified"]
+        # self.story.setMetadata("datePublished", datetime.fromtimestamp(rawDatePublished))
+        # rawDateUpdated = storyMetadata["date_modified"]
+        # self.story.setMetadata("dateUpdated", datetime.fromtimestamp(rawDateUpdated))
+        
+        oldestChapter = None
+        newestChapter = None
+        self.newestChapterNum = None # save for comparing during update.
+        # Scan all chapters to find the oldest and newest, on
+        # FiMFiction it's possible for authors to insert new chapters
+        # out-of-order or change the dates of earlier ones by editing
+        # them--That WILL break epub update.
+        for index, chapterDate in enumerate(soup.findAll('span', {'class':'date'})):
+            date=re.sub(r"(\d+)(st|nd|rd|th)",r"\1",chapterDate.contents[1].strip())
+            chapterDate = makeDate(date,self.dateformat)
+            if oldestChapter == None or chapterDate < oldestChapter:
+                oldestChapter = chapterDate
+            if newestChapter == None or chapterDate > newestChapter:
+                newestChapter = chapterDate
+                self.newestChapterNum = index
 
+        self.story.setMetadata("dateUpdated", newestChapter)
+        
+        pubdatetag = soup.find('span', {'class':'date_approved'})
+        if pubdatetag is None:
+            self.story.setMetadata("datePublished", oldestChapter)            
+        else:
+            pubdateraw = pubdatetag('span')[1].text
+            datestripped=re.sub(r"(\d+)(st|nd|rd|th)",r"\1",pubdateraw.strip())
+            pubDate = makeDate(datestripped,self.dateformat)
+            self.story.setMetadata("datePublished", pubDate)
+            
         chars = soup.find("div", {"class":"inner_data"})
         # fimfic stopped putting the char name on or around the char
         # icon now for some reason.  Pull it from the image name with
@@ -215,10 +248,22 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
                 if not isinstance(value,basestring):
                     value = unicode(value)
                 self.story.setMetadata(metakey, value)
-        
+
+        rawGroupList = soup.find('ul', {'id':'story_group_list'})
+        if rawGroupList is not None:
+            for groupName in rawGroupList.findAll('a', {'href':re.compile('^/group/')}):
+                self.story.addToList("groups",stripHTML(groupName))
             
+    def hookForUpdates(self,chaptercount):
+        if self.oldchapters and len(self.oldchapters) > self.newestChapterNum:
+            print("Existing epub has %s chapters\nNewest chapter is %s.  Discarding old chapters from there on."%(len(self.oldchapters), self.newestChapterNum+1))
+            self.oldchapters = self.oldchapters[:self.newestChapterNum]
+        return len(self.oldchapters)
+            
+        
     def getChapterText(self, url):
         logger.debug('Getting chapter text from: %s' % url)
+        
         soup = bs.BeautifulSoup(self._fetchUrl(url),selfClosingTags=('br','hr')).find('div', {'class' : 'chapter_content'})
         if soup == None:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)

fanficdownloader/adapters/adapter_finestoriescom.py

@@ -93,7 +93,7 @@ class FineStoriesComAdapter(BaseSiteAdapter):
             params['theusername'] = self.getConfig("username")
             params['thepassword'] = self.getConfig("password")
         params['rememberMe'] = '1'
-        params['page'] = 'http://finestories.com/'
+        params['page'] = 'http://'+self.getSiteDomain()+'/'
         params['submit'] = 'Login'
     
         loginUrl = 'http://' + self.getSiteDomain() + '/login.php'
@@ -142,7 +142,7 @@ class FineStoriesComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'/s/'+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.text)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"/a/\w+"))
@@ -262,8 +262,6 @@ class FineStoriesComAdapter(BaseSiteAdapter):
                 last[len(last)-1]=last[len(last)-1].append(next)
                 div.append(div1)
             
-            
-            
         # removing all the left-over stuff    
         for a in div.findAll('span'):
             a.extract()

fanficdownloader/adapters/adapter_grangerenchantedcom.py

@@ -182,7 +182,7 @@ class GrangerEnchantedCom(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_harrypotterfanfictioncom.py

@@ -92,7 +92,7 @@ class HarryPotterFanFictionComSiteAdapter(BaseSiteAdapter):
 
         ## Title
         a = soup.find('a', href=re.compile(r'\?psid='+self.story.getMetadata('storyId')))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         ## javascript:if (confirm('Please note. This story may contain adult themes. By clicking here you are stating that you are over 17. Click cancel if you do not meet this requirement.')) location = '?psid=290995'
         if "This story may contain adult themes." in a['href'] and not (self.is_adult or self.getConfig("is_adult")):
             raise exceptions.AdultCheckRequired(self.url)
@@ -131,55 +131,55 @@ class HarryPotterFanFictionComSiteAdapter(BaseSiteAdapter):
 
         ## Finding the metadata is a bit of a pain.  Most of the meta
         ## data is in a center.table without a bgcolor.
-        for center in soup.findAll('center'):
-            table = center.find('table',{'bgcolor':None})
-            if table:
-                metastr = stripHTML(str(table)).replace('\n',' ').replace('\t',' ')
-                # Rating: 12+ Story Reviews: 3
-                # Chapters: 3
-                # Characters: Andromeda, Ted, Bellatrix, R. Lestrange, Lucius, Narcissa, OC
-                # Genre(s): Fluff, Romance, Young Adult Era: OtherPairings: Other Pairing, Lucius/Narcissa
-                # Status: Completed
-                # First Published: 2010.09.02
-                # Last Published Chapter: 2010.09.28
-                # Last Updated: 2010.09.28
-                # Favorite Story Of: 1 users
-                # Warnings: Scenes of a Mild Sexual Nature
+        #for center in soup.findAll('center'):
+        table = soup.find('table',{'class':'storymaininfo'})
+        if table:
+            metastr = stripHTML(str(table)).replace('\n',' ').replace('\t',' ')
+            # Rating: 12+ Story Reviews: 3
+            # Chapters: 3
+            # Characters: Andromeda, Ted, Bellatrix, R. Lestrange, Lucius, Narcissa, OC
+            # Genre(s): Fluff, Romance, Young Adult Era: OtherPairings: Other Pairing, Lucius/Narcissa
+            # Status: Completed
+            # First Published: 2010.09.02
+            # Last Published Chapter: 2010.09.28
+            # Last Updated: 2010.09.28
+            # Favorite Story Of: 1 users
+            # Warnings: Scenes of a Mild Sexual Nature
 
-                m = re.match(r".*?Status: Completed.*?",metastr)
-                if m:
-                    self.story.setMetadata('status','Completed')
-                else:
-                    self.story.setMetadata('status','In-Progress')
+            m = re.match(r".*?Status: Completed.*?",metastr)
+            if m:
+                self.story.setMetadata('status','Completed')
+            else:
+                self.story.setMetadata('status','In-Progress')
 
-                m = re.match(r".*?Rating: (.+?) Story Reviews.*?",metastr)
-                if m:
-                    self.story.setMetadata('rating', m.group(1))
+            m = re.match(r".*?Rating: (.+?) Story Reviews.*?",metastr)
+            if m:
+                self.story.setMetadata('rating', m.group(1))
 
-                m = re.match(r".*?Genre\(s\): (.+?) Era.*?",metastr)
-                if m:
-                    for g in m.group(1).split(','):
-                        self.story.addToList('genre',g)
-        
-                m = re.match(r".*?Characters: (.+?) Genre.*?",metastr)
-                if m:
-                    for g in m.group(1).split(','):
-                        self.story.addToList('characters',g)
-        
-                m = re.match(r".*?Warnings: (.+).*?",metastr)
-                if m:
-                    for w in m.group(1).split(','):
-                        if w != 'Now Warnings':
-                            self.story.addToList('warnings',w)
-        
-                m = re.match(r".*?First Published: ([0-9\.]+).*?",metastr)
-                if m:
-                    self.story.setMetadata('datePublished',makeDate(m.group(1), "%Y.%m.%d"))
+            m = re.match(r".*?Genre\(s\): (.+?) Era.*?",metastr)
+            if m:
+                for g in m.group(1).split(','):
+                    self.story.addToList('genre',g)
+    
+            m = re.match(r".*?Characters: (.+?) Genre.*?",metastr)
+            if m:
+                for g in m.group(1).split(','):
+                    self.story.addToList('characters',g)
+    
+            m = re.match(r".*?Warnings: (.+).*?",metastr)
+            if m:
+                for w in m.group(1).split(','):
+                    if w != 'Now Warnings':
+                        self.story.addToList('warnings',w)
+    
+            m = re.match(r".*?First Published: ([0-9\.]+).*?",metastr)
+            if m:
+                self.story.setMetadata('datePublished',makeDate(m.group(1), "%Y.%m.%d"))
 
-                # Updated can have more than one space after it. <shrug>
-                m = re.match(r".*?Last Updated: ([0-9\.]+).*?",metastr)
-                if m:
-                    self.story.setMetadata('dateUpdated',makeDate(m.group(1), "%Y.%m.%d"))
+            # Updated can have more than one space after it. <shrug>
+            m = re.match(r".*?Last Updated: ([0-9\.]+).*?",metastr)
+            if m:
+                self.story.setMetadata('dateUpdated',makeDate(m.group(1), "%Y.%m.%d"))
 
     def getChapterText(self, url):
 

fanficdownloader/adapters/adapter_hennethannunnet.py

@@ -101,7 +101,7 @@ class HennethAnnunNetAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('h2', {'id':'page_heading'})
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
 
         # 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+$")):

fanficdownloader/adapters/adapter_hlfictionnet.py

@@ -106,7 +106,7 @@ class HLFictionNetAdapter(BaseSiteAdapter):
         self.story.setMetadata('author',aut.string)
         aut.extract()
         
-        self.story.setMetadata('title',a.string[:(len(a.string)-3)])
+        self.story.setMetadata('title',stripHTML(a)[:(len(a.string)-3)])
 
         # Find the chapters:
         chapters=soup.find('select')

fanficdownloader/adapters/adapter_hpfanficarchivecom.py

@@ -37,11 +37,6 @@ class HPFanficArchiveComAdapter(BaseSiteAdapter):
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
 
-        # hpfanficarchive.com blocks the default user-agent.  However,
-        # when asked, they said it was just general anti-spam, not
-        # targeted at us.  That lets me do this in good conscience:
-        self.opener.addheaders = [('User-agent', 'FFDL/1.7')]
-        
         self.decode = ["Windows-1252",
                        "utf8"] # 1252 is a superset of iso-8859-1.
                                # Most sites that claim to be
@@ -105,7 +100,7 @@ class HPFanficArchiveComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_iketernalnet.py

@@ -183,7 +183,7 @@ class IkEternalNetAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_imagineeficcom.py

@@ -170,7 +170,7 @@ class ImagineEFicComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_indeathnet.py

@@ -46,8 +46,8 @@ class InDeathNetAdapter(BaseSiteAdapter):
         self.password = ""
         self.is_adult=False
         
-		
-		  # get storyId from url--url validation guarantees query correct
+        
+        # get storyId from url--url validation guarantees query correct
         m = re.match(self.getSiteURLPattern(),url)
         if m:
             self.story.setMetadata('storyId',m.group('id'))
@@ -87,6 +87,34 @@ class InDeathNetAdapter(BaseSiteAdapter):
         postdate = makeDate(d.group('day')+' '+ym.group('mon')+' '+ym.group('year'),self.dateformat)
         return postdate
 
+    def getAuthorData(self):
+        
+        mainUrl = self.url.replace("/archive","")
+        
+        try:
+            maindata = self._fetchUrl(mainUrl)
+            
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.meta)
+            else:
+                raise e
+
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        mainsoup = bs.BeautifulSoup(maindata)
+
+        # find first entry
+        e = mainsoup.find('div',{'class':"entry"})
+        
+        # get post author as author
+        d = e.find('div',{'class':"desc"})
+        a = d.find('strong')
+        self.story.setMetadata('author',a.contents[0].string.strip())
+        
+        # Don't seem to be able to get author pages anymore
+        self.story.setMetadata('authorUrl','http://www.indeath.net/')
+        self.story.setMetadata('authorId','0')
+        
     ## Getting the chapter list and the meta data, plus 'is adult' checking.
     def extractChapterUrlsAndMetadata(self):
 
@@ -109,21 +137,14 @@ class InDeathNetAdapter(BaseSiteAdapter):
         ## Title
         h = soup.find('a', id="blog_title")
         t = h.find('span')
-        self.story.setMetadata('title',t.contents[0].string.strip())
-		
+        self.story.setMetadata('title',stripHTML(t.contents[0]).strip())
+        
         s = t.find('div')        
         if s != None:
             self.setDescription(url,s)
-		
-        # Find authorid and URL from first link in Recent Entries (don't yet reference 'recent entries' - let's see if that is required)
-        a = soup.find('a', href=re.compile(r"http://www.indeath.net/user/\d+\-[a-z0-9]+/$"))		#http://www.indeath.net/user/9083-cyrex/
-        m = re.search('http://www.indeath.net/user/(?P<id>\d+)\-(?P<name>[a-z0-9]*)/$',a['href'])
-        self.story.setMetadata('authorId',m.group('id'))
-        self.story.setMetadata('authorUrl',a['href'])
-        self.story.setMetadata('author',m.group('name'))
-
-
 
+        # Get Author from main blog page since it's not reliably on the archive page
+        self.getAuthorData()
 
         # Find the chapters:
         chapters=soup.findAll('a', title="View entry", href=re.compile(r'http://www.indeath.net/blog/'+self.story.getMetadata('storyId')+"/entry\-(\d+)\-([^/]*)/$"))
@@ -152,21 +173,20 @@ class InDeathNetAdapter(BaseSiteAdapter):
             if len(chapters)==1:
                 self.chapterUrls.append((self.story.getMetadata('title'),chapter['href']))
             else:
-            	ct = stripHTML(chapter)
-            	tnew = re.match("(?i)"+self.story.getMetadata('title')+r" - (?P<newtitle>.*)$",ct)
-            	if tnew:
-            		chaptertitle = tnew.group('newtitle')
-            	else:
-            		chaptertitle = ct
+                ct = stripHTML(chapter)
+                tnew = re.match("(?i)"+self.story.getMetadata('title')+r" - (?P<newtitle>.*)$",ct)
+                if tnew:
+                    chaptertitle = tnew.group('newtitle')
+                else:
+                    chaptertitle = ct
                 self.chapterUrls.append((chaptertitle,chapter['href']))
-	
-		
+
         
         
     # grab the text for an individual chapter.
     def getChapterText(self, url):
         logger.debug('Getting chapter text from: %s' % url)
-		
+        
         #chapter=bs.BeautifulSoup('<div class="story"></div>')
         data = self._fetchUrl(url)
         soup = bs.BeautifulSoup(data,selfClosingTags=('br','hr','span','center'))

fanficdownloader/adapters/adapter_libraryofmoriacom.py

@@ -129,7 +129,7 @@ class LibraryOfMoriaComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_lumossycophanthexcom.py

@@ -116,7 +116,7 @@ class LumosSycophantHexComAdapter(BaseSiteAdapter):
         ## Title
         pt = soup.find('div', {'id' : 'pagetitle'})
         a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.text)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = pt.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_mediaminerorg.py

@@ -107,10 +107,10 @@ class MediaMinerOrgSiteAdapter(BaseSiteAdapter):
         for font in title.findAll('font'):
             font.extract() # removes 'font' tags from inside the td.        
         if title.has_key('colspan'):
-            titlet = title.text
+            titlet = stripHTML(title)
         else:
             ## No colspan, it's part chapter title--even if it's a one-shot.
-            titlet = ':'.join(title.text.split(':')[:-1]) # strip trailing 'Chapter X' or chapter title
+            titlet = ':'.join(stripHTML(title).split(':')[:-1]) # strip trailing 'Chapter X' or chapter title
         self.story.setMetadata('title',titlet)
         ## The story title is difficult to reliably parse from the
         ## story pages.  Getting it from the author page is, but costs

fanficdownloader/adapters/adapter_merlinficdtwinscouk.py

@@ -170,7 +170,7 @@ class MerlinFicDtwinsCoUk(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_mugglenetcom.py

@@ -193,7 +193,7 @@ class MuggleNetComAdapter(BaseSiteAdapter): # XXX
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_nationallibrarynet.py

@@ -104,7 +104,7 @@ class NationalLibraryNetAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('h1')
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"authorresults.php\?author=\d+"))

fanficdownloader/adapters/adapter_ncisficcom.py

@@ -103,7 +103,7 @@ class NCISFicComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('h1')
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"authorresults.php\?author=\d+"))

fanficdownloader/adapters/adapter_ncisfictionnet.py

@@ -37,11 +37,6 @@ class NCISFictionNetAdapter(BaseSiteAdapter):
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
 
-        # ncisfiction.net blocks the default user-agent.  However,
-        # when asked, they said it was just general anti-spam, not
-        # targeted at us.  That lets me do this in good conscience:
-        self.opener.addheaders = [('User-agent', 'FFDL/1.7')]
-        
         self.decode = ["iso-8859-1",
                        "Windows-1252"] # 1252 is a superset of iso-8859-1.
                                # Most sites that claim to be

fanficdownloader/adapters/adapter_netraptororg.py

@@ -97,7 +97,7 @@ class NetRaptorOrgAdapter(BaseSiteAdapter):
         ## Title
         pagetitle = soup.find('div',{'id':'pagetitle'})
         a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_nfacommunitycom.py

@@ -156,7 +156,7 @@ class NfaCommunityComAdapter(BaseSiteAdapter): # XXX
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_nhamagicalworldsus.py

@@ -115,7 +115,7 @@ class NHAMagicalWorldsUsAdapter(BaseSiteAdapter):
             a = info.find('a')
             if 'viewstory.php?sid='+self.story.getMetadata('storyId') == a['href'] or \
                     ('viewstory.php?sid='+self.story.getMetadata('storyId')+'&') in a['href']:
-                self.story.setMetadata('title',a.string)
+                self.story.setMetadata('title',stripHTML(a))
                 break
 		
 

fanficdownloader/adapters/adapter_nickandgregnet.py

@@ -101,7 +101,7 @@ class NickAndGregNetAdapter(BaseSiteAdapter):
 
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
@@ -166,10 +166,11 @@ class NickAndGregNetAdapter(BaseSiteAdapter):
 
         soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
                                      selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
-        div = soup.find('table', {'class' : 'tblborder6'})
 
-        if None == div:
-            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+        # wrap a div around it.
+        divsoup = bs.BeautifulStoneSoup('<div class="story"></div>',
+                                        selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        div = divsoup.find('div')
+        div.append(soup.find('table', {'class' : 'tblborder6'}))
+
         return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_occlumencysycophanthexcom.py

@@ -158,7 +158,7 @@ class OcclumencySycophantHexComAdapter(BaseSiteAdapter):
         for info in asoup.findAll('table', {'class' : 'border'}):
             a = info.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
             if a != None:
-                self.story.setMetadata('title',a.text)
+                self.story.setMetadata('title',stripHTML(a))
                 break
 		
 

fanficdownloader/adapters/adapter_onedirectionfanfictioncom.py

@@ -158,7 +158,7 @@ class OneDirectionFanfictionComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_phoenixsongnet.py

@@ -136,7 +136,7 @@ class PhoenixSongNetAdapter(BaseSiteAdapter):
         ## Title
         b = soup.find('div', {'id' : 'nav25'})
         a = b.find('a', href=re.compile(r'fanfiction/story/'+self.story.getMetadata('storyId')+"/$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.  /fanfiction/stories.php?psid=125
         a = b.find('a', href=re.compile(r"/fanfiction/stories.php\?psid=\d+"))

fanficdownloader/adapters/adapter_pommedesangcom.py

@@ -180,7 +180,7 @@ class PommeDeSangComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile('viewstory.php\?sid=\d+'))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_ponyfictionarchivenet.py

@@ -136,7 +136,7 @@ class PonyFictionArchiveNetAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_portkeyorg.py

@@ -251,8 +251,10 @@ class PortkeyOrgAdapter(BaseSiteAdapter): # XXX
 
         logger.debug('Getting chapter text from: %s' % url)
         data = self._fetchUrl(url)
-        soup = bs.BeautifulStoneSoup(data,
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+
+        data = data.replace("HTML>","div>")
+        
+        soup = bs.BeautifulSoup(data)
 
         #print("soup:%s"%soup)
         tag = soup.find('td', {'class' : 'story'})

fanficdownloader/adapters/adapter_potionsandsnitchesnet.py

@@ -83,7 +83,7 @@ class PotionsAndSnitchesNetSiteAdapter(BaseSiteAdapter):
 
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_potterficscom.py

@@ -147,7 +147,7 @@ class PotterFicsComAdapter(BaseSiteAdapter):
         #find first metadata block
         mb = cell.div.findNextSibling('div')
         #Get meta...
-        self.story.setMetadata('title', mb.b.string)
+        self.story.setMetadata('title', stripHTML(mb.b))
         #strip out brackets on rating
         self.story.setMetadata('rating', mb.span.string[1:-1])
         #Completion status is denoted by the presence of this image:

fanficdownloader/adapters/adapter_potterheadsanonymouscom.py

@@ -181,7 +181,7 @@ class PotterHeadsAnonymousComAdapter(BaseSiteAdapter):
         
         ## Title
         a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_pretendercentrecom.py

@@ -134,7 +134,7 @@ class PretenderCenterComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.text)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_psychficcom.py

@@ -130,7 +130,7 @@ class PsychFicComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_qafficcom.py

@@ -138,7 +138,7 @@ class QafFicComAdapter(BaseSiteAdapter):
         self.story.setMetadata('author',aut.string)
         aut.extract()
         
-        self.story.setMetadata('title',a.string[:(len(a.string)-3)])
+        self.story.setMetadata('title',stripHTML(a)[:(len(a.string)-3)])
 
         # Find the chapters:
         chapters=soup.find('select')

fanficdownloader/adapters/adapter_restrictedsectionorg.py

@@ -22,7 +22,6 @@ import re
 import urllib2
 import cookielib as cl
 from datetime import datetime
-import json
 
 from .. import BeautifulSoup as bs
 from ..htmlcleanup import stripHTML
@@ -126,10 +125,12 @@ class RestrictedSectionOrgSiteAdapter(BaseSiteAdapter):
         
         self.story.setMetadata('authorId',ahref.split('=')[1])
         self.story.setMetadata('authorUrl','http://'+self.host+'/'+ahref)
-        self.story.setMetadata('author',a.string)
+        self.story.setMetadata('author',stripHTML(a))
 
         # title, remove byauthorname.
-        self.story.setMetadata('title',h2.text[:h2.text.index("by"+a.string)])
+        auth=stripHTML(a)
+        title=stripHTML(h2)
+        self.story.setMetadata('title',title[:title.index(" by "+auth)])
 
         dates = soup.findAll('span', {'class':'date'})
         if dates: # only for multi-chapter

fanficdownloader/adapters/adapter_samdeanarchivenu.py

@@ -110,7 +110,7 @@ class SamDeanArchiveNuAdapter(BaseSiteAdapter):
         self.story.setMetadata('author',aut.string)
         aut.extract()
         
-        self.story.setMetadata('title',a.string[:(len(a.string)-3)])
+        self.story.setMetadata('title',stripHTML(a)[:(len(stripHTML(a))-3)])
 
         # Find the chapters:
         chapters=soup.find('select')

fanficdownloader/adapters/adapter_scarheadnet.py

@@ -181,7 +181,7 @@ class ScarHeadNetAdapter(BaseSiteAdapter):
         
         ## Title
         a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_scarvesandcoffeenet.py

@@ -139,7 +139,7 @@ class ScarvesAndCoffeeNetAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('div',{"id":"pagetitle"}).find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_sg1heliopoliscom.py

@@ -140,7 +140,7 @@ class SG1HeliopolisComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_simplyundeniablecom.py

@@ -143,7 +143,7 @@ class SimplyUndeniableComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('h1')
-        self.story.setMetadata('title',a.text)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
@@ -155,7 +155,7 @@ class SimplyUndeniableComAdapter(BaseSiteAdapter):
         for info in asoup.findAll('table', {'cellpadding' : '5'}):
             a = info.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
             if a != None:
-                self.story.setMetadata('title',a.string)
+                self.story.setMetadata('title',stripHTML(a))
                 break
                 
         # Find the chapters:
@@ -214,5 +214,6 @@ class SimplyUndeniableComAdapter(BaseSiteAdapter):
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+        div.name='div'
     
         return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_sinfuldesireorg.py

@@ -130,7 +130,7 @@ class SinfulDesireOrgAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_siyecouk.py

@@ -241,5 +241,6 @@ class SiyeCoUkAdapter(BaseSiteAdapter): # XXX
         
         if None == story:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+        story.name='div'
     
         return self.utf8FromSoup(url,story)

fanficdownloader/adapters/adapter_squidgeorgpeja.py

@@ -122,7 +122,7 @@ class SquidgeOrgPejaAdapter(BaseSiteAdapter):
         # formating, so it's a little ugly.
 
         title = authorSoup.find('a',{'href':'viewstory.php?sid='+self.story.getMetadata('storyId')})
-        self.story.setMetadata('title',title.string)
+        self.story.setMetadata('title',stripHTML(title))
         titleblock=title.parent.parent
         
         chapterselect=soup.find('select',{'name':'chapter'})

fanficdownloader/adapters/adapter_stargateatlantisorg.py

@@ -106,7 +106,7 @@ class StargateAtlantisOrgAdapter(BaseSiteAdapter):
         self.story.setMetadata('author',aut.string)
         aut.extract()
         
-        self.story.setMetadata('title',a.string[:(len(a.string)-3)])
+        self.story.setMetadata('title',stripHTML(a)[:(len(stripHTML(a))-3)])
 
         # Find the chapters:
         chapters=soup.findAll('div', {'class' : 'content'})

fanficdownloader/adapters/adapter_storiesofardacom.py

@@ -104,7 +104,7 @@ class StoriesOfArdaComAdapter(BaseSiteAdapter):
         asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
         
         a.find('em').extract()
-        self.story.setMetadata('title',a.text)
+        self.story.setMetadata('title',stripHTML(a))
 
         # Find the chapters: chapterview.asp?sid=7000&cid=30919
         chapters=soup.findAll('a', href=re.compile(r'chapterview.asp\?sid='+self.story.getMetadata('storyId')+"&cid=\d+$"))

fanficdownloader/adapters/adapter_storiesonlinenet.py

@@ -0,0 +1,305 @@
+# -*- 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 StoriesOnlineNetAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class StoriesOnlineNetAdapter(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
+        self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2].split(':')[0])
+        if 'storyInfo' in self.story.getMetadata('storyId'):
+            self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/s/'+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','strol')
+
+        # 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 'storiesonline.net'
+
+    @classmethod
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/s/1234 http://"+self.getSiteDomain()+"/s/1234:4010"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain())+r"/s/\d+(:\d+)?(;\d+)?$"
+
+    ## Login seems to be reasonably standard across eFiction sites.
+    def needToLoginCheck(self, data):
+        if 'Free Registration' in data \
+                or "Invalid Password!" in data \
+                or "Invalid User Name!" in data \
+                or "Access to unlinked chapters requires" in data:
+            return True
+        else:
+            return False
+        
+    def performLogin(self, url):
+        params = {}
+
+        if self.password:
+            params['theusername'] = self.username
+            params['thepassword'] = self.password
+        else:
+            params['theusername'] = self.getConfig("username")
+            params['thepassword'] = self.getConfig("password")
+        params['rememberMe'] = '1'
+        params['page'] = 'http://'+self.getSiteDomain()+'/'
+        params['submit'] = 'Login'
+    
+        loginUrl = 'http://' + self.getSiteDomain() + '/login.php'
+        logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
+                                                              params['theusername']))
+    
+        d = self._fetchUrl(loginUrl, params)
+    
+        if "My Account" not in d : #Member Account
+            logger.info("Failed to login to URL %s as %s" % (loginUrl,
+                                                              params['theusername']))
+            raise exceptions.FailedToLogin(url,params['theusername'])
+            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 "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('h1')
+        self.story.setMetadata('title',stripHTML(a))
+        
+        # Find authorid and URL from... author url.
+        a = soup.find('a', href=re.compile(r"/a/\w+"))
+        self.story.setMetadata('authorId',a['href'].split('/')[2])
+        self.story.setMetadata('authorUrl','http://'+self.host+a['href'])
+        self.story.setMetadata('author',stripHTML(a).replace("'s Page",""))
+
+        # Find the chapters:
+        chapters = soup.findAll('a', href=re.compile(r'/s/'+self.story.getMetadata('storyId')+":\d+$"))
+        if len(chapters) != 0:
+            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']))
+        else:
+            self.chapterUrls.append((self.story.getMetadata('title'),'http://'+self.host+'/s/'+self.story.getMetadata('storyId')))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # surprisingly, the detailed page does not give enough details, so go to author's page
+        skip=0
+        i=0
+        while i == 0:
+            asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')+"&skip="+str(skip)))
+        
+            a = asoup.findAll('td', {'class' : 'lc2'})
+            for lc2 in a:
+                if lc2.find('a')['href'] == '/s/'+self.story.getMetadata('storyId'):
+                    i=1
+                    break
+                if a[len(a)-1] == lc2:
+                    skip=skip+10
+        
+        for cat in lc2.findAll('div', {'class' : 'typediv'}):
+            self.story.addToList('genre',cat.text)
+
+        # in lieu of word count.
+        self.story.setMetadata('size', lc2.findNext('td', {'class' : 'num'}).text)
+        
+        lc4 = lc2.findNext('td', {'class' : 'lc4'})        
+        
+        try:
+            a = lc4.find('a', href=re.compile(r"/library/show_series.php\?id=\d+"))
+            i = a.parent.text.split('(')[1].split(')')[0]
+            self.setSeries(stripHTML(a), i)
+            self.story.setMetadata('seriesUrl','http://'+self.host+a['href'])
+        except:
+            pass
+        try:
+            a = lc4.find('a', href=re.compile(r"/library/universe.php\?id=\d+"))
+            if a:
+                self.story.setMetadata("universe",stripHTML(a))
+        except:
+            pass
+            
+        for a in lc4.findAll('span', {'class' : 'help'}):
+            a.extract()
+        for a in lc4.findAll('br'):
+            a.extract()
+
+        desc = "%s"%lc4
+        desc = desc[desc.index(">")+1:]
+        desc = desc[:desc.index("<")]
+        self.setDescription('http://'+self.host+'/s/'+self.story.getMetadata('storyId'),desc)
+            
+        for b in lc4.findAll('b'):
+            #logger.debug('Getting metadata: "%s"' % b)
+            label = b.text
+            if label in ['Posted:', 'Concluded:', 'Updated:']:
+                value = b.findNext('noscript').text
+                #logger.debug('Have a date field label: "%s", value: "%s"' % (label, value))
+            else:
+                value = b.nextSibling
+            #logger.debug('label: "%s", value: "%s"' % (label, value))
+            
+            if 'Sex' in label:
+                self.story.setMetadata('rating', value)
+                
+            if 'Codes' in label:
+                for code in value.split(' '):
+                    self.story.addToList('codes',code)
+                    
+            if 'Posted' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+                
+            if 'Concluded' in label:
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+                
+            if 'Updated' in label:
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+#                
+        status = lc4.find('span', {'class' : 'ab'})
+        if  status != None:
+            self.story.setMetadata('status', 'In-Progress')
+            if "Last Activity" in status.text:
+                self.story.setMetadata('dateUpdated', makeDate(status.text.split('Activity: ')[1].split(')')[0], self.dateformat))
+        else:
+            self.story.setMetadata('status', 'Completed')
+
+            
+    # 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'})
+        
+        # some big chapters are split over several pages
+        pager = div.find('span', {'class' : 'pager'})
+        if pager != None:
+            urls=pager.findAll('a')
+            urls=urls[:len(urls)-1]
+            
+            
+            for ur in urls:
+                soup = bs.BeautifulSoup(self._fetchUrl("http://"+self.getSiteDomain()+ur['href']),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+                div1 = soup.find('div', {'id' : 'story'})
+                
+                # appending next section
+                last=div.findAll('p')
+                next=div1.find('span', {'class' : 'conTag'}).nextSibling
+            
+                last[len(last)-1]=last[len(last)-1].append(next)
+                div.append(div1)
+            
+        # removing all the left-over stuff    
+        for a in div.findAll('span'):
+            a.extract() 
+            
+        for a in div.findAll('h1'):
+            a.extract()
+        for a in div.findAll('h2'):
+            a.extract()
+        for a in div.findAll('h3'):
+            a.extract()
+        for a in div.findAll('h4'):
+            a.extract()
+        for a in div.findAll('br'):
+            a.extract()
+        for a in div.findAll('div', {'class' : 'date'}):
+            a.extract()
+            
+        a = div.find('form')
+        if a != None:
+            b = a.nextSibling
+            while b != None:
+                a.extract()
+                a=b
+                b=b.nextSibling
+        
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_tenhawkpresentscom.py

@@ -133,7 +133,7 @@ class TenhawkPresentsComSiteAdapter(BaseSiteAdapter):
 
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_test1.py

@@ -323,7 +323,7 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
 </div>
 '''
         elif self.story.getMetadata('storyId') == '0':
-            text=u'''
+            text=u'''<div>
 <h3>45. Pronglet Returns to Hogwarts: Chapter 7</h3>
 <br />
     eyes… but I’m not convinced we should automatically<br />
@@ -332,6 +332,7 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
 <br /><br />
     “Sure, invite her along. Does she have children?”<br />
 <br />
+</div>
 '''
         else:
             if self.story.getMetadata('storyId') == '667':

fanficdownloader/adapters/adapter_thealphagatecom.py

@@ -99,7 +99,7 @@ class TheAlphaGateComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_thehookupzonenet.py

@@ -179,7 +179,7 @@ class TheHookupZoneNetAdapter(BaseSiteAdapter): # XXX
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_themasquenet.py

@@ -177,7 +177,7 @@ class TheMasqueNetAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_thepetulantpoetesscom.py

@@ -165,7 +165,7 @@ class ThePetulantPoetessComAdapter(BaseSiteAdapter):
             for info in asoup.findAll('td', {'class' : 'highlightcolor1'}):
                 a = info.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
                 if a != None:
-                    self.story.setMetadata('title',a.text)                
+                    self.story.setMetadata('title',stripHTML(a))
                     found = 1
                     break
             index=index+1

fanficdownloader/adapters/adapter_thequidditchpitchorg.py

@@ -165,7 +165,7 @@ class TheQuidditchPitchOrgAdapter(BaseSiteAdapter): # XXX
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_tokrafandomnetcom.py

@@ -131,7 +131,7 @@ class TokraFandomnetComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_tthfanficorg.py

@@ -231,10 +231,10 @@ class TwistingTheHellmouthSiteAdapter(BaseSiteAdapter):
         BtVS = True
         BtVSNonX = False
         for cat in verticaltable.findAll('a', href=re.compile(r"^/Category-")):
-            if cat.string not in ['General', 'Non-BtVS/AtS Stories', 'BtVS/AtS Non-Crossover', 'Non-BtVS Crossovers']:
+            if cat.string not in ['General', 'Non-BtVS/AtS Stories', 'Non-BTVS/AtS Stories', 'BtVS/AtS Non-Crossover', 'Non-BtVS Crossovers']:
                 self.story.addToList('category',cat.string)
             else:
-                if 'Non-BtVS' in cat.string:
+                if 'Non-BtVS' in cat.string or 'Non-BTVS' in cat.string:
                     BtVS = False
                 if 'BtVS/AtS Non-Crossover' == cat.string:
                     BtVSNonX = True

fanficdownloader/adapters/adapter_twilightarchivescom.py

@@ -100,7 +100,7 @@ class TwilightArchivesComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('h1')
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find the chapters:
         chapters=soup.find('ol', {'class' : 'chapters'})

fanficdownloader/adapters/adapter_twilightednet.py

@@ -130,7 +130,7 @@ class TwilightedNetSiteAdapter(BaseSiteAdapter):
 
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php"))

fanficdownloader/adapters/adapter_twiwritenet.py

@@ -144,7 +144,7 @@ class TwiwriteNetSiteAdapter(BaseSiteAdapter):
         
         ## Title
         a = pagetitlediv.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = pagetitlediv.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_walkingtheplankorg.py

@@ -115,7 +115,7 @@ class WalkingThePlankOrgAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_whoficcom.py

@@ -22,6 +22,7 @@ import re
 import urllib2
 
 from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
 from base_adapter import BaseSiteAdapter,  makeDate
@@ -70,7 +71,7 @@ class WhoficComSiteAdapter(BaseSiteAdapter):
                 raise e
 
         # pull title(title) and author from the HTML title.
-        title = soup.find('title').string
+        title = stripHTML(soup.find('title'))
         logger.debug('Title: %s' % title)
         title = title.split('::')[1].strip()
         self.story.setMetadata('title',title.split(' by ')[0].strip())
@@ -227,7 +228,8 @@ class WhoficComSiteAdapter(BaseSiteAdapter):
 
         if None == span:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
+        span.name='div'
         return self.utf8FromSoup(url,span)
 
 def getClass():

fanficdownloader/adapters/adapter_wizardtalesnet.py

@@ -171,7 +171,7 @@ class WizardTalesNetAdapter(BaseSiteAdapter):
         ## Title
         pt = soup.find('div', {'id' : 'pagetitle'})
         a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.text)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = pt.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_wolverineandroguecom.py

@@ -101,7 +101,7 @@ class WolverineAndRogueComAdapter(BaseSiteAdapter):
         ## Title
         pt = soup.find('div', {'id' : 'pagetitle'})
         a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.text)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = pt.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_wraithbaitcom.py

@@ -113,7 +113,7 @@ class WraithBaitComAdapter(BaseSiteAdapter):
         ## Title
         pt = soup.find('div', {'id' : 'pagetitle'})
         a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         alist = pt.findAll('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/base_adapter.py

@@ -26,6 +26,7 @@ from functools import partial
 
 from .. import BeautifulSoup as bs
 from ..htmlcleanup import stripHTML
+from ..htmlheuristics import replace_br_with_p
 
 logger = logging.getLogger(__name__)
 
@@ -77,6 +78,8 @@ class BaseSiteAdapter(Configurable):
         self.is_adult=False
         
         self.opener = u2.build_opener(u2.HTTPCookieProcessor(),GZipProcessor())
+        ## Specific UA because too many sites are blocking the default python UA.
+        self.opener.addheaders = [('User-agent', self.getConfig('user_agent'))]
         self.storyDone = False
         self.metadataDone = False
         self.story = Story(configuration)
@@ -245,6 +248,10 @@ class BaseSiteAdapter(Configurable):
             self.metadataDone = True
         return self.story
 
+    def hookForUpdates(self,chaptercount):
+        "Usually not needed."
+        return chaptercount
+
     ###############################
     
     @staticmethod
@@ -348,13 +355,8 @@ class BaseSiteAdapter(Configurable):
 	    # removes paired, but empty tags.
             if t.string != None and len(t.string.strip()) == 0 :
                 t.extract()
-                
-        retval = soup.__str__('utf8').decode('utf-8')
 
-        if self.getConfig('replace_hr'):
-            # replacing a self-closing tag with a container tag in the
-            # soup is more difficult than it first appears.  So cheat.
-            retval = retval.replace("<hr />","<div class='center'>* * *</div>")
+        retval = soup.__str__('utf8').decode('utf-8')
 
         if self.getConfig('nook_img_fix'):
             # if the <img> tag doesn't have a div or a p around it,
@@ -365,7 +367,19 @@ class BaseSiteAdapter(Configurable):
             
         # Don't want body tags in chapter html--writers add them.
         # This is primarily for epub updates.
-        return re.sub(r"</?body>\r?\n?","",retval)
+        retval = re.sub(r"</?body>\r?\n?","",retval)
+        
+        if self.getConfig("replace_br_with_p"):
+            # Apply heuristic processing to replace <br> paragraph
+            # breaks with <p> tags.
+            retval = replace_br_with_p(retval)
+            
+        if self.getConfig('replace_hr'):
+            # replacing a self-closing tag with a container tag in the
+            # soup is more difficult than it first appears.  So cheat.
+            retval = retval.replace("<hr />","<div class='center'>* * *</div>")
+
+        return retval
 
 def cachedfetch(realfetch,cache,url):
     if url in cache:
@@ -377,7 +391,7 @@ fullmon = {"January":"01", "February":"02", "March":"03", "April":"04", "May":"0
            "June":"06","July":"07", "August":"08", "September":"09", "October":"10",
            "November":"11", "December":"12" }
 
-def makeDate(string,format):
+def makeDate(string,dateform):
     # Surprise!  Abstracting this turned out to be more useful than
     # just saving bytes.
 
@@ -386,10 +400,10 @@ def makeDate(string,format):
     # there's non-english content. -- ficbook.net now makes that a
     # lie.  It has to do something even more complicated to get
     # Russian month names correct everywhere.
-    do_abbrev = "%b" in format
+    do_abbrev = "%b" in dateform
         
-    if "%B" in format or do_abbrev:
-        format = format.replace("%B","%m").replace("%b","%m")
+    if "%B" in dateform or do_abbrev:
+        dateform = dateform.replace("%B","%m").replace("%b","%m")
         for (name,num) in fullmon.items():
             if do_abbrev:
                 name = name[:3] # first three for abbrev
@@ -397,5 +411,5 @@ def makeDate(string,format):
                 string = string.replace(name,num)
                 break
             
-    return datetime.datetime.strptime(string,format)
+    return datetime.datetime.strptime(string,dateform)
 

fanficdownloader/epubutils.py

@@ -7,6 +7,9 @@ __license__   = 'GPL v3'
 __copyright__ = '2012, Jim Miller'
 __docformat__ = 'restructuredtext en'
 
+import logging
+logger = logging.getLogger(__name__)
+
 import re, os, traceback
 from zipfile import ZipFile
 from xml.dom.minidom import parseString
@@ -72,7 +75,7 @@ def get_update_data(inputio,
                 # remove all .. and the path part above it, if present.
                 # Mostly for epubs edited by Sigil.
                 src = re.sub(r"([^/]+/\.\./)","",src)
-                print("epubutils: found pre-existing cover image:%s"%src)
+                #print("epubutils: found pre-existing cover image:%s"%src)
                 oldcoverimghref = src
                 oldcoverimgdata = epub.read(src)
                 for item in contentdom.getElementsByTagName("item"):
@@ -81,8 +84,8 @@ def get_update_data(inputio,
                         break
                 oldcover = (oldcoverhtmlhref,oldcoverhtmltype,oldcoverhtmldata,oldcoverimghref,oldcoverimgtype,oldcoverimgdata)
             except Exception as e:
-                print("Cover Image %s not found"%src)
-                print("Exception: %s"%(unicode(e)))
+                logger.warn("Cover Image %s not found"%src)
+                logger.warn("Exception: %s"%(unicode(e)))
                 traceback.print_exc()
 
     filecount = 0
@@ -118,8 +121,8 @@ def get_update_data(inputio,
                                 images[longdesc] = data
                                 img['src'] = img['longdesc']
                             except Exception as e:
-                                print("Image %s not found!\n(originally:%s)"%(newsrc,longdesc))
-                                print("Exception: %s"%(unicode(e)))
+                                logger.warn("Image %s not found!\n(originally:%s)"%(newsrc,longdesc))
+                                logger.warn("Exception: %s"%(unicode(e)))
                                 traceback.print_exc()
                         soup = soup.find('body')
                         # ffdl epubs have chapter title h3
@@ -143,8 +146,8 @@ def get_update_data(inputio,
     except:
         pass
                     
-    for k in images.keys():
-        print("\tlongdesc:%s\n\tData len:%s\n"%(k,len(images[k])))
+    #for k in images.keys():
+        #print("\tlongdesc:%s\n\tData len:%s\n"%(k,len(images[k])))
     return (source,filecount,soups,images,oldcover,calibrebookmark,logfile)
 
 def get_path_part(n):

fanficdownloader/htmlcleanup.py

@@ -15,6 +15,9 @@
 # limitations under the License.
 #
 
+import logging
+logger = logging.getLogger(__name__)
+
 import re
 
 def _unirepl(match):
@@ -31,7 +34,7 @@ def _unirepl(match):
     except:
         # This way, at least if there's more of entities out there
         # that fail, it doesn't blow the entire download.
-        print "Numeric entity translation failed, skipping: &#x%s%s"%(match.group(1),match.group(2))
+        logger.warn("Numeric entity translation failed, skipping: &#x%s%s"%(match.group(1),match.group(2)))
         retval = ""
     return retval
 
@@ -69,8 +72,9 @@ def removeEntities(text):
     
     if text is None:
         return ""
-    if not (isinstance(text,str) or isinstance(text,unicode)):
-        return str(text)
+    
+    if not isinstance(text,basestring):
+        return unicode(text)
     
     try:
         t = text.decode('utf-8')

fanficdownloader/htmlheuristics.py

@@ -0,0 +1,127 @@
+# -*- 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 logging
+logger = logging.getLogger(__name__)
+import re
+
+from . import exceptions as exceptions
+
+def replace_br_with_p(body):
+
+    # Ascii character (and Unicode as well) xA0 is a non-breaking space, ascii code 160.
+    # However, Python Regex does not recognize it as a whitespace, so we'll be changing it to a reagular space.
+    body = body.replace(u'\xa0', u' ')
+
+    if body.find('>') == -1 or body.rfind("<") == -1:
+        return body
+
+    # change surrounding div to a p and remove attrs Top surrounding
+    # tag in all cases now should be div, to just strip the first and
+    # last tags.
+    body = u'<p>'+body[body.index('>')+1:body.rindex("<")]+u'</p>'
+
+    # So many people add formatting to their HR tags, and ePub does not allow those, we are supposed to use css.
+    # This nukes the hr tag attributes.
+    body = re.sub(r'\s*<hr[^>]+>\s*', r'\n<hr />\n', body)
+
+    # Need to look at BeautifulSoup to see if it'll even return breaks that aren't properly formatted (<br />).
+    body = re.sub(r'\s*<br[^>]*>\s*', r'<br />', body)
+
+    # Remove leading and trailing breaks from HR tags
+    body = re.sub(r'\s*(<br\ \/>)*\s*<hr\ \/>\s*(<br\ \/>)*\s*', r'\n<hr />\n', body)
+    # Nuking breaks leading paragraps that may be in the body. They are eventually treated as <p><br /></p>
+    body = re.sub(r'\s*(<br\ \/>)+\s*<p', r'\n<p></p>\n<p', body)
+    # Nuking breaks trailing paragraps that may be in the body. They are eventually treated as <p><br /></p>
+    body = re.sub(r'</p>\s*(<br\ \/>)+\s*', r'</p>\n<p></p>\n', body)
+
+    # Because a leading or trailing non break tag will break the following code, we have to mess around rather badly for a few lines.
+    body = body.replace(u'[',u'&squareBracketStart;')
+    body = body.replace(u']',u'&squareBracketEnd;')
+    body = body.replace(u'<br />',u'[br /]')
+
+    breaksRegexp = [
+        re.compile(r'([^\]])(\[br\ \/\])([^\[])'),
+        re.compile(r'([^\]])(\[br\ \/\]){2}([^\[])'),
+        re.compile(r'([^\]])(\[br\ \/\]){3}([^\[])'),
+        re.compile(r'([^\]])(\[br\ \/\]){4}([^\[])'),
+        re.compile(r'([^\]])(\[br\ \/\]){5}([^\[])'),
+        re.compile(r'([^\]])(\[br\ \/\]){6}([^\[])'),
+        re.compile(r'([^\]])(\[br\ \/\]){7}([^\[])'),
+        re.compile(r'([^\]])(\[br\ \/\]){8}([^\[])'),
+        re.compile(r'(\[br\ \/\]){9,}')]
+
+    breaksCount = [
+        len(breaksRegexp[0].findall(body)),
+        len(breaksRegexp[1].findall(body)),
+        len(breaksRegexp[2].findall(body)),
+        len(breaksRegexp[3].findall(body)),
+        len(breaksRegexp[4].findall(body)),
+        len(breaksRegexp[5].findall(body)),
+        len(breaksRegexp[6].findall(body)),
+        len(breaksRegexp[7].findall(body))]
+
+    breaksMax = 0
+    breaksMaxIndex = 0;
+
+    for i in range(len(breaksCount)):
+        if breaksCount[i] > breaksMax:
+            breaksMax = breaksCount[i]
+            breaksMaxIndex = i
+
+    # Find all instances of consecutive breaks less than otr equal to the max count use most often
+    #  replase those tags to inverted p tag pairs, those with more connsecutive breaks are replaced them with a horisontal line
+    for i in range(len(breaksCount)):
+        if i <= breaksMaxIndex:
+            body = breaksRegexp[i].sub(r'\1</p>\n<p>\3', body)
+        else:
+            body = breaksRegexp[i].sub(r'\1</p>\n<hr />\n<p>\3', body)
+
+    body = breaksRegexp[8].sub(r'</p>\n<hr />\n<p>', body)
+
+    # Reverting the square brackets
+    body = body.replace(u'[', u'<')
+    body = body.replace(u']', u'>')
+    body = body.replace(u'&squareBracketStart;', u'[')
+    body = body.replace(u'&squareBracketEnd;', u']')
+
+    # If for some reason, a third break makes its way inside the paragraph, preplace that with the empty paragraph for the additional linespaing.
+    body = re.sub(r'<p>\s*(<br\ \/>)+', r'<p><br /></p>\n<p>', body)
+
+    # change empty p tags to include a br to force spacing.
+    body = re.sub(r'<p>\s*</p>', r'<p><br/></p>', body)
+
+    # Clean up hr tags, and add inverted p tag pairs
+    body = re.sub(r'\s*<hr\ \/>\s*', r'</p>\n<hr />\n<p>', body)
+
+    # Because the previous regexp may cause trouble if the hr tag already had a p tag pair around it, w nee dot repair that.
+    # Repeated opening p tags are condenced to one. As we added the extra leading opening p tags, we can safely assume that
+    #  the last in such a chain must be the original. Lets keep its attributes if they are there.
+    body = re.sub(r'\s*(<p[^>]*>\s*)+<p([^>]*)>\s*', r'\n<p\2>', body)
+    # Repeated closing p tags are condenced to one
+    body = re.sub(r'\s*(<\/\s*p>\s*){2,}', r'</p>\n', body)
+
+    # superflous cleaning, remove whitespaces traling opening p tags. These does affect formatting.
+    body = re.sub(r'<p([^>]*)>\s*', r'<p\1>', body)
+    # superflous cleaning, remove whitespaces leading closing p tags. These does not affect formatting.
+    body = re.sub(r'\s*</p>', r'</p>', body)
+
+    # re-wrap in div tag.
+    body = u'<div>\n' + body + u'\n</div>'
+
+    return body 
+

fanficdownloader/story.py

@@ -349,6 +349,8 @@ class Story(Configurable):
                 return removeAllEntities(value)
             else:
                 return value
+        else: #if self.getConfig("default_value_"+key):
+            return self.getConfig("default_value_"+key)
         
     def getAllMetadata(self,
                        removeallentities=False,
@@ -411,6 +413,9 @@ class Story(Configurable):
         if not value in self.metadata[listname]:
             self.metadata[listname].append(value)
 
+        if listname == 'category' and self.getConfig('add_genre_when_multi_category') and len(self.metadata[listname]) > 1:
+            self.addToList('genre',self.getConfig('add_genre_when_multi_category'))
+
     def isList(self,listname):
         'Everything set with an include_in_* is considered a list.'
         return self.hasConfig("include_in_"+listname) or \
@@ -482,6 +487,8 @@ class Story(Configurable):
 
         if None in subjectset:
             subjectset.remove(None)
+        if '' in subjectset:
+            subjectset.remove('')
 
         return list(subjectset | set(self.getConfigList("extratags")))
             
@@ -624,7 +631,7 @@ class Story(Configurable):
                     ext)
                 self.imgtuples.append({'newsrc':newsrc,'mime':mime,'data':data})
                 
-            logger.debug("\nimgurl:%s\nnewsrc:%s\nimage size:%d\n"%(imgurl,newsrc,len(data)))
+            #logger.debug("\nimgurl:%s\nnewsrc:%s\nimage size:%d\n"%(imgurl,newsrc,len(data)))
         else:
             newsrc = self.imgtuples[self.imgurls.index(imgurl)]['newsrc']