Turn on ficbook.net and allow chapter URLs in fbn.

Many(most?) of the sites ignore gzip because of our User-Agent. ffnet honors it.
Add progress bar while getting URLs or getting URLs for update.

app.yaml

@@ -1,6 +1,6 @@
 # ffd-retief-hrd fanfictiondownloader
 application: fanfictiondownloader
-version: 4-2-1
+version: 4-3-2
 runtime: python27
 api_version: 1
 threadsafe: true

calibre-plugin/__init__.py

@@ -27,7 +27,7 @@ class FanFictionDownLoaderBase(InterfaceActionBase):
     description         = 'UI plugin to download FanFiction stories from various sites.'
     supported_platforms = ['windows', 'osx', 'linux']
     author              = 'Jim Miller'
-    version             = (1, 2, 2)
+    version             = (1, 4, 3)
     minimum_calibre_version = (0, 8, 30)
 
     #: This field defines the GUI plugin class that contains all the code

calibre-plugin/config.py

@@ -9,8 +9,8 @@ __docformat__ = 'restructuredtext en'
 
 import traceback, copy
 
-from PyQt4.Qt import (QDialog, QWidget, QVBoxLayout, QHBoxLayout, QLabel, QLineEdit,
-                      QTextEdit, QComboBox, QCheckBox, QPushButton, QTabWidget)
+from PyQt4.Qt import (QDialog, QWidget, QVBoxLayout, QHBoxLayout, QLabel, QLineEdit, QFont,
+                      QTextEdit, QComboBox, QCheckBox, QPushButton, QTabWidget, QVariant)
 
 from calibre.gui2 import dynamic, info_dialog
 from calibre.utils.config import JSONConfig
@@ -47,6 +47,7 @@ all_prefs.defaults['read_lists'] = ''
 all_prefs.defaults['addtolists'] = False
 all_prefs.defaults['addtoreadlists'] = False
 all_prefs.defaults['addtolistsonread'] = False
+all_prefs.defaults['custom_cols'] = {}
 
 # The list of settings to copy from all_prefs or the previous library
 # when config is called for the first time on a library.
@@ -57,10 +58,7 @@ copylist = ['personal.ini',
             'updatedefault',
             'fileform',
             'collision',
-            'deleteotherforms',
-            'addtolists',
-            'addtoreadlists',
-            'addtolistsonread']
+            'deleteotherforms']
 
 # fake out so I don't have to change the prefs calls anywhere.  The
 # Java programmer in me is offended by op-overloading, but it's very
@@ -132,10 +130,14 @@ class ConfigWidget(QWidget):
         tab_widget.addTab(self.list_tab, 'Reading Lists')
         if 'Reading List' not in plugin_action.gui.iactions:
             self.list_tab.setEnabled(False)
-            
+
+        self.columns_tab = ColumnsTab(self, plugin_action)
+        tab_widget.addTab(self.columns_tab, 'Custom Columns')
+
         self.other_tab = OtherTab(self, plugin_action)
         tab_widget.addTab(self.other_tab, 'Other')
 
+
     def save_settings(self):
 
         # basic
@@ -164,6 +166,15 @@ class ConfigWidget(QWidget):
         else:
             # if they've removed everything, reset to default.
             prefs['personal.ini'] = get_resources('plugin-example.ini')
+
+        # Custom Columns tab
+        colsmap = {}
+        for (col,combo) in self.columns_tab.custcol_dropdowns.iteritems():
+            val = unicode(combo.itemData(combo.currentIndex()).toString())
+            if val != 'none':
+                colsmap[col] = val
+                #print("colsmap[%s]:%s"%(col,colsmap[col]))
+        prefs['custom_cols'] = colsmap
         
     def edit_shortcuts(self):
         self.save_settings()
@@ -183,6 +194,11 @@ class BasicTab(QWidget):
         self.l = QVBoxLayout()
         self.setLayout(self.l)
 
+        label = QLabel('These settings control the basic features of the plugin--downloading FanFiction.')
+        label.setWordWrap(True)
+        self.l.addWidget(label)
+        self.l.addSpacing(5)
+        
         horz = QHBoxLayout()
         label = QLabel('Default Output &Format:')
         horz.addWidget(label)
@@ -214,7 +230,7 @@ class BasicTab(QWidget):
         self.l.addLayout(horz)
 
         self.updatemeta = QCheckBox('Default Update Calibre &Metadata?',self)
-        self.updatemeta.setToolTip('Update title, author, URL, tags, etc for story in Calibre from web site.')
+        self.updatemeta.setToolTip('Update title, author, URL, tags, custom columns, etc for story in Calibre from web site.')
         self.updatemeta.setChecked(prefs['updatemeta'])
         self.l.addWidget(self.updatemeta)
 
@@ -265,10 +281,20 @@ class PersonalIniTab(QWidget):
         self.l = QVBoxLayout()
         self.setLayout(self.l)
 
+        label = QLabel('These settings provide more detailed control over what metadata will be displayed inside the ebook as well as let you set is_adult and user/password for different sites.')
+        label.setWordWrap(True)
+        self.l.addWidget(label)
+        self.l.addSpacing(5)
+        
         self.label = QLabel('personal.ini:')
         self.l.addWidget(self.label)
 
         self.ini = QTextEdit(self)
+        try:
+            self.ini.setFont(QFont("Courier",
+                                   self.plugin_action.gui.font().pointSize()+1));
+        except Exception as e:
+            print("Couldn't get font: %s"%e)
         self.ini.setLineWrapMode(QTextEdit.NoWrap)
         self.ini.setText(prefs['personal.ini'])
         self.l.addWidget(self.ini)
@@ -293,13 +319,18 @@ class ShowDefaultsIniDialog(QDialog):
         self.l = QVBoxLayout()
         self.setLayout(self.l)
         self.label = QLabel("Plugin Defaults (Read-Only)")
-        self.label.setToolTip("These all of the plugin's configurable settings\nand their default settings.")
+        self.label.setToolTip("These are all of the plugin's configurable options\nand their default settings.")
         self.setWindowTitle(_('Plugin Defaults'))
         self.setWindowIcon(icon)
         self.l.addWidget(self.label)
         
         self.ini = QTextEdit(self)
-        self.ini.setToolTip("These all of the plugin's configurable settings\nand their default settings.")
+        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));
+        except Exception as e:
+            print("Couldn't get font: %s"%e)
         self.ini.setLineWrapMode(QTextEdit.NoWrap)
         self.ini.setText(text)
         self.ini.setReadOnly(True)
@@ -379,6 +410,11 @@ class OtherTab(QWidget):
         self.l = QVBoxLayout()
         self.setLayout(self.l)
 
+        label = QLabel("These controls aren't plugin settings as such, but convenience buttons for setting Keyboard shortcuts and getting all the FanFictionDownLoader confirmation dialogs back again.")
+        label.setWordWrap(True)
+        self.l.addWidget(label)
+        self.l.addSpacing(5)
+        
         keyboard_shortcuts_button = QPushButton('Keyboard shortcuts...', self)
         keyboard_shortcuts_button.setToolTip(_(
                     'Edit the keyboard shortcuts associated with this plugin'))
@@ -401,3 +437,119 @@ class OtherTab(QWidget):
         info_dialog(self, _('Done'),
                 _('Confirmation dialogs have all been reset'), show=True)
 
+permitted_values = {
+    'int' : ['numWords','numChapters'],
+    'float' : ['numWords','numChapters'],
+    'bool' : ['status-C','status-I'],
+    'datetime' : ['datePublished', 'dateUpdated', 'dateCreated'],
+    'series' : ['series'],
+    'enumeration' : ['category',
+                     'genre',
+                     'language',
+                     'series',
+                     'characters',
+                     'status',
+                     'datePublished',
+                     'dateUpdated',
+                     'dateCreated',
+                     'rating',
+                     'warnings',
+                     'numChapters',
+                     'numWords',
+                     'site',
+                     'storyId',
+                     'authorId',
+                     'extratags',
+                     'title',
+                     'storyUrl',
+                     'description',
+                     'author',
+                     'authorUrl',
+                     'formatname'
+                     #,'formatext'   # not useful information.
+                     #,'siteabbrev'
+                     #,'version'
+                     ]
+    }
+# no point copying the whole list.
+permitted_values['text'] = permitted_values['enumeration']
+permitted_values['comments'] = permitted_values['enumeration']
+
+titleLabels = {
+    'category':'Category',
+    'genre':'Genre',
+    'language':'Language',
+    'status':'Status',
+    'status-C':'Status:Completed',
+    'status-I':'Status:In-Progress',
+    'series':'Series',
+    'characters':'Characters',
+    'datePublished':'Published',
+    'dateUpdated':'Updated',
+    'dateCreated':'Packaged',
+    'rating':'Rating',
+    'warnings':'Warnings',
+    'numChapters':'Chapters',
+    'numWords':'Words',
+    'site':'Site',
+    'storyId':'Story ID',
+    'authorId':'Author ID',
+    'extratags':'Extra Tags',
+    'title':'Title',
+    'storyUrl':'Story URL',
+    'description':'Summary',
+    'author':'Author',
+    'authorUrl':'Author URL',
+    'formatname':'File Format',
+    'formatext':'File Extension',
+    'siteabbrev':'Site Abbrev',
+    'version':'FFDL Version'
+    }
+
+class ColumnsTab(QWidget):
+
+    def __init__(self, parent_dialog, plugin_action):
+        self.parent_dialog = parent_dialog
+        self.plugin_action = plugin_action
+        QWidget.__init__(self)
+        
+        self.l = QVBoxLayout()
+        self.setLayout(self.l)
+
+        label = QLabel("If you have custom columns defined, they will be listed below.  Choose a metadata value type to fill your columns automatically.")
+        label.setWordWrap(True)
+        self.l.addWidget(label)
+        self.l.addSpacing(5)
+        
+        self.custcol_dropdowns = {}
+
+        custom_columns = self.plugin_action.gui.library_view.model().custom_columns
+
+        for key, column in custom_columns.iteritems():
+
+            if column['datatype'] in permitted_values:
+                # print("\n============== %s ===========\n"%key)
+                # for (k,v) in column.iteritems():
+                #     print("column['%s'] => %s"%(k,v))
+                horz = QHBoxLayout()
+                label = QLabel('%s(%s)'%(column['name'],key))
+                label.setToolTip("Update this %s column with..."%column['datatype'])
+                horz.addWidget(label)
+                dropdown = QComboBox(self)
+                dropdown.addItem('',QVariant('none'))
+                for md in permitted_values[column['datatype']]:
+                    dropdown.addItem(titleLabels[md],QVariant(md))
+                self.custcol_dropdowns[key] = dropdown
+                if key in prefs['custom_cols']:
+                    dropdown.setCurrentIndex(dropdown.findData(QVariant(prefs['custom_cols'][key])))
+                if column['datatype'] == 'enumeration':
+                    dropdown.setToolTip("Metadata values valid for this type of column.\nValues that aren't valid for this enumeration column will be ignored.")
+                else:
+                    dropdown.setToolTip("Metadata values valid for this type of column.")
+
+                horz.addWidget(dropdown)
+                self.l.addLayout(horz)
+        
+        self.l.insertStretch(-1)
+
+        #print("prefs['custom_cols'] %s"%prefs['custom_cols'])

calibre-plugin/dialogs.py

@@ -11,13 +11,16 @@ import traceback
 
 from PyQt4 import QtGui
 from PyQt4.Qt import (QDialog, QTableWidget, QMessageBox, QVBoxLayout, QHBoxLayout, QGridLayout,
-                      QPushButton, QProgressDialog, QString, QLabel, QCheckBox, QIcon,
+                      QPushButton, QProgressDialog, QString, QLabel, QCheckBox, QIcon, QTextCursor,
                       QTextEdit, QLineEdit, QInputDialog, QComboBox, QClipboard, QVariant,
                       QProgressDialog, QTimer, QDialogButtonBox, QPixmap, Qt,QAbstractItemView )
 
 from calibre.gui2 import error_dialog, warning_dialog, question_dialog, info_dialog
 from calibre.gui2.dialogs.confirm_delete import confirm
 
+from calibre import confirm_config_name
+from calibre.gui2 import dynamic
+
 from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader import adapters,writers,exceptions
 from calibre_plugins.fanfictiondownloader_plugin.common_utils \
     import (ReadOnlyTableWidgetItem, ReadOnlyTextIconWidgetItem, SizePersistedDialog,
@@ -45,7 +48,24 @@ class NotGoingToDownload(Exception):
 
     def __str__(self):
         return self.error
-    
+
+class DroppableQTextEdit(QTextEdit):
+    def __init__(self,parent):
+        QTextEdit.__init__(self,parent)
+        
+    def canInsertFromMimeData(self, source):
+        if source.hasUrls():
+            return True;
+        else:
+            return QTextEdit.canInsertFromMimeData(self,source)
+
+    def insertFromMimeData(self, source):
+        if source.hasUrls():
+            for u in source.urls():
+                self.append(u.toString())
+        else:
+            return QTextEdit.insertFromMimeData(self, source)
+                            
 class AddNewDialog(SizePersistedDialog):
 
     def __init__(self, gui, prefs, icon, url_list_text):
@@ -60,7 +80,7 @@ class AddNewDialog(SizePersistedDialog):
         self.setWindowIcon(icon)
 
         self.l.addWidget(QLabel('Story URL(s), one per line:'))
-        self.url = QTextEdit(self)
+        self.url = DroppableQTextEdit(self)
         self.url.setToolTip('URLs for stories, one per line.\nWill take URLs from clipboard, but only valid URLs.')
         self.url.setLineWrapMode(QTextEdit.NoWrap)
         self.url.setText(url_list_text)
@@ -132,7 +152,7 @@ class AddNewDialog(SizePersistedDialog):
         return {
             'fileform': unicode(self.fileform.currentText()),
             'collision': unicode(self.collision.currentText()),
-            'updatemeta': unicode(self.updatemeta.isChecked()),
+            'updatemeta': self.updatemeta.isChecked(),
             }
 
     def get_urlstext(self):
@@ -180,25 +200,27 @@ class UserPassDialog(QDialog):
         self.status=False
         self.hide()
 
-class MetadataProgressDialog(QProgressDialog):
+class LoopProgressDialog(QProgressDialog):
     '''
     ProgressDialog displayed while fetching metadata for each story.
     '''
     def __init__(self, gui,
                  book_list,
-                 options,
-                 metadata_function,
-                 startdownload_function):
+                 foreach_function,
+                 finish_function,
+                 init_label="Fetching metadata for stories...",
+                 win_title="Downloading metadata for stories",
+                 status_prefix="Fetched metadata for"):
         QProgressDialog.__init__(self,
-                                 "Fetching metadata for stories...",
+                                 init_label,
                                  QString(), 0, len(book_list), gui)
-        self.setWindowTitle("Downloading metadata for stories")
+        self.setWindowTitle(win_title)
         self.setMinimumWidth(500)
         self.gui = gui
         self.book_list = book_list
-        self.options = options
-        self.metadata_function = metadata_function
-        self.startdownload_function = startdownload_function
+        self.foreach_function = foreach_function
+        self.finish_function = finish_function
+        self.status_prefix = status_prefix
         self.i = 0
         
         ## self.do_loop does QTimer.singleShot on self.do_loop also.
@@ -207,7 +229,7 @@ class MetadataProgressDialog(QProgressDialog):
         self.exec_()
 
     def updateStatus(self):
-        self.setLabelText("Fetched metadata for %d of %d"%(self.i+1,len(self.book_list)))
+        self.setLabelText("%s %d of %d"%(self.status_prefix,self.i+1,len(self.book_list)))
         self.setValue(self.i+1)
         print(self.labelText())
 
@@ -220,7 +242,7 @@ class MetadataProgressDialog(QProgressDialog):
         try:
             ## collision spec passed into getadapter by partial from ffdl_plugin
             ## no retval only if it exists, but collision is SKIP
-            self.metadata_function(book)
+            self.foreach_function(book)
             
         except NotGoingToDownload as d:
             book['good']=False
@@ -245,7 +267,7 @@ class MetadataProgressDialog(QProgressDialog):
         self.hide()
         self.gui = None        
         # Queues a job to process these books in the background.
-        self.startdownload_function(self.book_list)
+        self.finish_function(self.book_list)
 
 class AboutDialog(QDialog):
 
@@ -290,7 +312,7 @@ class AuthorTableWidgetItem(ReadOnlyTableWidgetItem):
 
 class UpdateExistingDialog(SizePersistedDialog):
     def __init__(self, gui, header, prefs, icon, books,
-                 save_size_name='FanFictionDownLoader plugin:update list dialog'):
+                 save_size_name='fanfictiondownloader_plugin:update list dialog'):
         SizePersistedDialog.__init__(self, gui, save_size_name)
         self.gui = gui
         
@@ -395,17 +417,38 @@ class UpdateExistingDialog(SizePersistedDialog):
         return {
             'fileform': unicode(self.fileform.currentText()),
             'collision': unicode(self.collision.currentText()),
-            'updatemeta': unicode(self.updatemeta.isChecked()),
+            'updatemeta': self.updatemeta.isChecked(),
             }
 
+def display_story_list(gui, header, prefs, icon, books,
+                       label_text='',
+                       save_size_name='fanfictiondownloader_plugin:display list dialog',
+                       offer_skip=False):
+    all_good = True
+    for b in books:
+        if not b['good']:
+            all_good=False
+            break
+        
+    ## 
+    if all_good and not dynamic.get(confirm_config_name(save_size_name), True):
+        return True
+        pass
+            ## fake accept?
+    d = DisplayStoryListDialog(gui, header, prefs, icon, books,
+                               label_text,
+                               save_size_name,
+                               offer_skip and all_good)
+    d.exec_()
+    return d.result() == d.Accepted
+
 class DisplayStoryListDialog(SizePersistedDialog):
     def __init__(self, gui, header, prefs, icon, books,
                  label_text='',
-                 save_size_name='FanFictionDownLoader plugin:display list dialog'):
+                 save_size_name='fanfictiondownloader_plugin:display list dialog',
+                 offer_skip=False):
         SizePersistedDialog.__init__(self, gui, save_size_name)
-        # UpdateExistingDialog.__init__(self, gui, header, prefs, icon, books,
-        #                               save_size_name='FanFictionDownLoader plugin:display list dialog')
-
+        self.name = save_size_name
         self.gui = gui
         
         self.setWindowTitle(header)
@@ -426,6 +469,15 @@ class DisplayStoryListDialog(SizePersistedDialog):
         #self.label.setWordWrap(True)
         options_layout.addWidget(self.label)
         
+        if offer_skip:
+            spacerItem1 = QtGui.QSpacerItem(2, 4, QtGui.QSizePolicy.Expanding, QtGui.QSizePolicy.Minimum)
+            options_layout.addItem(spacerItem1)
+            self.again = QCheckBox('Show this again?',self)
+            self.again.setChecked(True)
+            self.again.stateChanged.connect(self.toggle)
+            self.again.setToolTip('Uncheck to skip review and update stories immediately when no problems.')
+            options_layout.addWidget(self.again)
+        
         button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
         button_box.accepted.connect(self.accept)
         button_box.rejected.connect(self.reject)
@@ -437,10 +489,15 @@ class DisplayStoryListDialog(SizePersistedDialog):
         # Cause our dialog size to be restored from prefs or created on first usage
         self.resize_dialog()
         self.books_table.populate_table(books)
-        
+
     def get_books(self):
         return self.books_table.get_books()
 
+    def toggle(self, *args):
+        dynamic[confirm_config_name(self.name)] = self.again.isChecked()
+
+    
+
 class StoryListTableWidget(QTableWidget):
 
     def __init__(self, parent):

calibre-plugin/ffdl_plugin.py

@@ -21,6 +21,7 @@ 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
 from calibre.gui2.dialogs.confirm_delete import confirm
+from calibre.utils.date import local_tz
 
 # The class that all interface action plugins must inherit from
 from calibre.gui2.actions import InterfaceAction
@@ -32,10 +33,10 @@ from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader import adapter
 from calibre_plugins.fanfictiondownloader_plugin.epubmerge import doMerge
 from calibre_plugins.fanfictiondownloader_plugin.dcsource import get_dcsource
 
-from calibre_plugins.fanfictiondownloader_plugin.config import (prefs)
+from calibre_plugins.fanfictiondownloader_plugin.config import (prefs, permitted_values)
 from calibre_plugins.fanfictiondownloader_plugin.dialogs import (
-    AddNewDialog, UpdateExistingDialog, DisplayStoryListDialog,
-    MetadataProgressDialog, UserPassDialog, AboutDialog,
+    AddNewDialog, UpdateExistingDialog, display_story_list, DisplayStoryListDialog,
+    LoopProgressDialog, UserPassDialog, AboutDialog,
     OVERWRITE, OVERWRITEALWAYS, UPDATE, UPDATEALWAYS, ADDNEW, SKIP, CALIBREONLY,
     NotGoingToDownload )
 
@@ -51,9 +52,6 @@ formmapping = {
 
 PLUGIN_ICONS = ['images/icon.png']
 
-sendlists = ["Send to Nook", "Send to Kindle", "Send to Droid", "Add to Nook", "Add to Kindle", "Add to Droid"]
-readlists = ["000"]
-
 class FanFictionDownLoaderPlugin(InterfaceAction):
 
     name = 'FanFictionDownLoader'
@@ -65,7 +63,8 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
     # (text, icon_path, tooltip, keyboard shortcut)
     # icon_path isn't in the zip--icon loaded below.
     action_spec = (name, None,
-                   'Download FanFiction stories from various web sites', None)
+                   'Download FanFiction stories from various web sites', ())
+    # None for keyboard shortcut doesn't allow shortcut.  () does, there just isn't one yet
 
     action_type = 'global'
     # make button menu drop down only
@@ -117,6 +116,10 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
     def about_to_show_menu(self):
         self.rebuild_menus()
 
+    def library_changed(self, db):
+        # We need to reset our menus after switching libraries
+        self.rebuild_menus()
+        
     def rebuild_menus(self):
         with self.menus_lock:
             # Show the config dialog
@@ -137,7 +140,6 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                                                           triggered=self.update_existing)
 
             if 'Reading List' in self.gui.iactions and (prefs['addtolists'] or prefs['addtoreadlists']) :
-                ## XXX mod and rebuild menu when lists selected/empty
                 self.menu.addSeparator()
                 addmenutxt, rmmenutxt = None, None
                 if prefs['addtolists'] and prefs['addtoreadlists'] :
@@ -164,14 +166,14 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                                                                       shortcut_name=rmmenutxt,
                                                                       triggered=partial(self.update_lists,add=False))
                 
-                try:
-                    self.add_send_action.setEnabled( len(self.gui.library_view.get_selected_ids()) > 0 )
-                except:
-                    pass
-                try:
-                    self.add_remove_action.setEnabled( len(self.gui.library_view.get_selected_ids()) > 0 )
-                except:
-                    pass
+                # try:
+                #     self.add_send_action.setEnabled( len(self.gui.library_view.get_selected_ids()) > 0 )
+                # except:
+                #     pass
+                # try:
+                #     self.add_remove_action.setEnabled( len(self.gui.library_view.get_selected_ids()) > 0 )
+                # except:
+                #     pass
 
             self.menu.addSeparator()
             self.get_list_action = self.create_menu_item_ex(self.menu, 'Get URLs from Selected Books', image='bookmarks.png',
@@ -192,8 +194,8 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                                                            shortcut_name='About FanFictionDownLoader',
                                                            triggered=self.about)
             
-            self.update_action.setEnabled( len(self.gui.library_view.get_selected_ids()) > 0 )
-            self.get_list_action.setEnabled( len(self.gui.library_view.get_selected_ids()) > 0 )
+            # self.update_action.setEnabled( len(self.gui.library_view.get_selected_ids()) > 0 )
+            # self.get_list_action.setEnabled( len(self.gui.library_view.get_selected_ids()) > 0 )
 
             # Before we finalize, make sure we delete any actions for menus that are no longer displayed
             for menu_id, unique_name in self.old_actions_unique_map.iteritems():
@@ -238,22 +240,35 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
 
     def get_list_urls(self):
         if len(self.gui.library_view.get_selected_ids()) > 0:
-            url_list = []
-            for book_id in self.gui.library_view.get_selected_ids():
-                url = self._get_story_url(self.gui.current_db, book_id)
-                if url != None:
-                    url_list.append(url)
+            book_list = map( partial(self._convert_id_to_book, good=False), self.gui.library_view.get_selected_ids() )
 
-            if url_list:
-                d = ViewLog(_("List of URLs"),"\n".join(url_list),parent=self.gui)
-                d.setWindowIcon(get_icon('bookmarks.png'))
-                d.exec_()
-            else:
-                info_dialog(self.gui, _('List of URLs'),
-                            _('No URLs found in selected books.'),
-                            show=True,
-                            show_copy_button=False)
+            LoopProgressDialog(self.gui,
+                               book_list,
+                               partial(self._get_story_url_for_list, db=self.gui.current_db),
+                               self._finish_get_list_urls,
+                               init_label="Collecting URLs for stories...",
+                               win_title="Get URLs for stories",
+                               status_prefix="URL retrieved")
             
+    def _get_story_url_for_list(self,book,db=None):
+        book['url'] = self._get_story_url(db,book['calibre_id'])
+        if book['url'] == None:
+            book['good']=False
+        else:
+            book['good']=True
+            
+    def _finish_get_list_urls(self, book_list):
+        url_list = [ x['url'] for x in book_list if x['good'] ]
+        if url_list:
+            d = ViewLog(_("List of URLs"),"\n".join(url_list),parent=self.gui)
+            d.setWindowIcon(get_icon('bookmarks.png'))
+            d.exec_()
+        else:
+            info_dialog(self.gui, _('List of URLs'),
+                        _('No URLs found in selected books.'),
+                        show=True,
+                        show_copy_button=False)
+                
     def add_dialog(self):
 
         #print("add_dialog()")
@@ -286,18 +301,32 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         self.start_downloads( options, add_books )
         
     def update_existing(self):
+        if len(self.gui.library_view.get_selected_ids()) == 0:
+            return
         #print("update_existing()")
-        previous = self.gui.library_view.currentIndex()
+        
         db = self.gui.current_db
-        book_ids = self.gui.library_view.get_selected_ids()
-        books = self._convert_calibre_ids_to_books(db, book_ids)
+        book_list = map( partial(self._convert_id_to_book, good=False), self.gui.library_view.get_selected_ids() )
+        #book_ids = self.gui.library_view.get_selected_ids()
+
+        LoopProgressDialog(self.gui,
+                           book_list,
+                           partial(self._populate_book_from_calibre_id, db=self.gui.current_db),
+                           self._update_existing_2,
+                           init_label="Collecting stories for update...",
+                           win_title="Get stories for updates",
+                           status_prefix="URL retrieved")            
+        
+        #books = self._convert_calibre_ids_to_books(db, book_ids)
         #print("update books:%s"%books)
 
+    def _update_existing_2(self,book_list):
+        
         d = UpdateExistingDialog(self.gui,
                                  'Update Existing List',
                                  prefs,
                                  self.qaction.icon(),
-                                 books,
+                                 book_list,
                                  )
         d.exec_()
         if d.result() != d.Accepted:
@@ -336,14 +365,14 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
 
         self.gui.status_bar.show_message(_('Started fetching metadata for %s stories.'%len(books)), 3000)
         
-        MetadataProgressDialog(self.gui,
+        if 0 < len(filter(lambda x : x['good'], books)):
+            LoopProgressDialog(self.gui,
                                books,
-                               options,
                                partial(self.get_metadata_for_book, options = options),
                                partial(self.start_download_list, options = options))
-        # MetadataProgressDialog calls get_metadata_for_book for each 'good' story,
+        # LoopProgressDialog calls get_metadata_for_book for each 'good' story,
         # get_metadata_for_book updates book for each,
-        # MetadataProgressDialog calls start_download_list at the end which goes
+        # LoopProgressDialog calls start_download_list at the end which goes
         # into the BG, or shows list if no 'good' books.
 
     def get_metadata_for_book(self,book,
@@ -352,7 +381,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                                        'updatemeta':True}):
         '''
         Update passed in book dict with metadata from website and
-        necessary data.  To be called from MetadataProgressDialog
+        necessary data.  To be called from LoopProgressDialog
         'loop'.  Also pops dialogs for is adult, user/pass.
         '''
         
@@ -406,11 +435,13 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         story = adapter.getStoryMetadataOnly()
         writer = writers.getWriter(options['fileform'],adapter.config,adapter)
 
+        book['all_metadata'] = story.getAllMetadata(removeallentities=True)
         book['title'] = story.getMetadata("title", removeallentities=True)
         book['author_sort'] = book['author'] = story.getMetadata("author", removeallentities=True)
         book['publisher'] = story.getMetadata("site")
         book['tags'] = writer.getTags()
         book['comments'] = story.getMetadata("description") #, removeallentities=True) comments handles entities better.
+        book['series'] = story.getMetadata("series")
         
         # adapter.opener is the element with a threadlock.  But del
         # adapter.opener doesn't work--subproc fails when it tries
@@ -422,7 +453,10 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         book['password'] = adapter.password
 
         book['icon'] = 'plus.png'
-        book['pubdate'] = story.getMetadataRaw('datePublished')
+        if story.getMetadataRaw('datePublished'):
+            # should only happen when an adapter is broken, but better to
+            # fail gracefully.
+            book['pubdate'] = story.getMetadataRaw('datePublished').replace(tzinfo=local_tz)
         book['timestamp'] = None # filled below if not skipped.
         
         if collision in (CALIBREONLY):
@@ -523,7 +557,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             # I'm half convinced this should be dateUpdated instead, but
             # this behavior matches how epubs come out when imported
             # dateCreated == packaged--epub/etc created.
-            book['timestamp'] = story.getMetadataRaw('dateCreated')
+            book['timestamp'] = story.getMetadataRaw('dateCreated').replace(tzinfo=local_tz)
         
         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.
@@ -541,7 +575,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                                      'collision':ADDNEW,
                                      'updatemeta':True}):
         '''
-        Called by MetadataProgressDialog to start story downloads BG processing.
+        Called by LoopProgressDialog to start story downloads BG processing.
         adapter_list is a list of tuples of (url,adapter)
         '''
         #print("start_download_list:book_list:%s"%book_list)
@@ -556,18 +590,6 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             self.download_list_completed(notjob,options=options)
             return
 
-        # ## XXX show list before starting download.
-        # d = DisplayStoryListDialog(self.gui,
-        #                            'Download List',
-        #                            prefs,
-        #                            self.qaction.icon(),
-        #                            book_list,
-        #                            label_text='Status of stories to be downloaded'
-        #                            )
-        # d.exec_()
-        # if d.result() != d.Accepted:
-        #     return
-            
         for book in book_list:
             if book['good']:
                 break
@@ -596,73 +618,82 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         
         self.gui.status_bar.show_message('Starting %d FanFictionDownLoads'%len(book_list),3000)
 
+    def _update_book(self,book,db=None,
+                     options={'fileform':'epub',
+                              'collision':ADDNEW,
+                              'updatemeta':True}):
+        print("add/update %s %s"%(book['title'],book['url']))
+        mi = self._make_mi_from_book(book)
+                
+        if options['collision'] != CALIBREONLY:
+            self._add_or_update_book(book,options,prefs,mi)
+
+        if options['collision'] == CALIBREONLY or \
+                (options['updatemeta'] and book['good']):
+            self._update_metadata(db, book['calibre_id'], book, mi)        
+
+    def _update_books_completed(self, book_list, options={}):
+        
+        add_list = filter(lambda x : x['good'] and x['added'], book_list)
+        update_list = filter(lambda x : x['good'] and not x['added'], book_list)
+        update_ids = [ x['calibre_id'] for x in update_list ]
+        
+        if len(add_list):
+            ## even shows up added to searchs.  Nice.
+            self.gui.library_view.model().books_added(len(add_list))
+
+        if update_ids:
+            self.gui.library_view.model().refresh_ids(update_ids)
+
+        current = self.gui.library_view.currentIndex()
+        self.gui.library_view.model().current_changed(current, self.previous)
+        self.gui.tags_view.recount()
+        
+        self.gui.status_bar.show_message(_('Finished Adding/Updating %d books.'%(len(update_list) + len(add_list))), 3000)
+            
+        if len(update_list) + len(add_list) != len(book_list):
+            d = DisplayStoryListDialog(self.gui,
+                                       'Updates completed, final status',
+                                       prefs,
+                                       self.qaction.icon(),
+                                       book_list,
+                                       label_text='Stories have be added or updated in Calibre, some had additional problems.'
+                                       )
+            d.exec_()
+    
+        print("all done, remove temp dir.")
+        remove_dir(options['tdir'])
+        
     def download_list_completed(self, job, options={}):
         if job.failed:
             self.gui.job_exception(job, dialog_title='Failed to Download Stories')
             return
 
-        previous = self.gui.library_view.currentIndex()
+        self.previous = self.gui.library_view.currentIndex()
         db = self.gui.current_db
 
-        d = DisplayStoryListDialog(self.gui,
-                                   'Downloads finished, confirm to update Calibre',
-                                   prefs,
-                                   self.qaction.icon(),
-                                   job.result,
-                                   label_text='Stories will not be added or updated in Calibre without confirmation.'
-                                   )
-        d.exec_()
-        if d.result() == d.Accepted:
+        if display_story_list(self.gui,
+                              'Downloads finished, confirm to update Calibre',
+                              prefs,
+                              self.qaction.icon(),
+                              job.result,
+                              label_text='Stories will not be added or updated in Calibre without confirmation.',
+                              offer_skip=True):
             
-            ## in case the user removed any from the list.
-            book_list = d.get_books()
-
+            book_list = job.result
             good_list = filter(lambda x : x['good'], book_list)
-
             total_good = len(good_list)
 
-            self.gui.status_bar.show_message(_('Adding/Updating %s books.'%total_good), 3000)
-            
-            for book in good_list:
-                print("add/update %s %s"%(book['title'],book['url']))
-                mi = self._make_mi_from_book(book)
-                
-                if options['collision'] != CALIBREONLY:
-                    self._add_or_update_book(book,options,prefs,mi)
+            self.gui.status_bar.show_message(_('Adding/Updating %s books.'%total_good))
 
-                if options['collision'] == CALIBREONLY or \
-                        (options['updatemeta'] and book['good']) :
-                    self._update_metadata(db, book['calibre_id'], book, mi)
-                    
-            add_list = filter(lambda x : x['good'] and x['added'], book_list)
-            update_list = filter(lambda x : x['good'] and not x['added'], book_list)
-            update_ids = [ x['calibre_id'] for x in update_list ]
-                    
-            if len(add_list):
-                ## even shows up added to searchs.  Nice.
-                self.gui.library_view.model().books_added(len(add_list))
-
-            if update_ids:
-                self.gui.library_view.model().refresh_ids(update_ids)
-
-            current = self.gui.library_view.currentIndex()
-            self.gui.library_view.model().current_changed(current, previous)
-            self.gui.tags_view.recount()
-            
-            self.gui.status_bar.show_message(_('Finished Adding/Updating %d books.'%(len(update_list) + len(add_list))), 3000)
-            
-            if len(update_list) + len(add_list) != total_good:
-                d = DisplayStoryListDialog(self.gui,
-                                           'Updates completed, final status',
-                                           prefs,
-                                           self.qaction.icon(),
-                                           book_list,
-                                           label_text='Stories have be added or updated in Calibre, some had additional problems.'
-                                           )
-                d.exec_()
-    
-        print("all done, remove temp dir.")
-        remove_dir(options['tdir'])
+            if total_good > 0:
+                LoopProgressDialog(self.gui,
+                                   good_list,
+                                   partial(self._update_book, options=options, db=self.gui.current_db),
+                                   partial(self._update_books_completed, options=options),
+                                   init_label="Updating calibre for stories...",
+                                   win_title="Update calibre for stories",
+                                   status_prefix="Updated")
 
     def _add_or_update_book(self,book,options,prefs,mi=None):
         db = self.gui.current_db
@@ -708,13 +739,50 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             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)) 
-        # Set language english, but only if not already set.
-        oldmi = db.get_metadata(book_id,index_is_id=True)
-        if not oldmi.languages:
-            mi.languages=['eng']
+            mi.tags = list(set(list(old_tags)+mi.tags))
+
+        if 'langcode' in book['all_metadata']:
+            mi.languages=[book['all_metadata']['langcode']]
+        else:
+            # Set language english, but only if not already set.
+            oldmi = db.get_metadata(book_id,index_is_id=True)
+            if not oldmi.languages:
+                mi.languages=['eng']
+                
         db.set_metadata(book_id,mi)
 
+        # do configured column updates here.
+        #print("all_metadata: %s"%book['all_metadata'])
+        custom_columns = self.gui.library_view.model().custom_columns
+
+        #print("prefs['custom_cols'] %s"%prefs['custom_cols'])
+        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)
+                continue
+            coldef = custom_columns[col]
+            if not meta.startswith('status-') and meta not in book['all_metadata']:
+                print("No value for %s, skipping."%meta)
+                continue
+            if meta not in permitted_values[coldef['datatype']]:
+                print("%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)
+            elif coldef['datatype'] in ('int','float'):
+                num = unicode(book['all_metadata'][meta]).replace(",","")
+                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'
+                if meta == 'status-I':
+                    val = book['all_metadata']['status'] == 'In-Progress'
+                db.set_custom(book_id, val, label=label, commit=False)
+                
+        db.commit()
+
     def _get_clean_reading_lists(self,lists):
         if lists == None or lists.strip() == "" :
             return []
@@ -788,6 +856,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         mi.pubdate = book['pubdate']
         mi.timestamp = book['timestamp']
         mi.comments = book['comments']
+        mi.series = book['series']
         return mi
 
 
@@ -818,35 +887,42 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         self._set_book_url_and_comment(book,url)
         return book
         
-    
-    def _convert_calibre_ids_to_books(self, db, ids):
-        books = []
-        for book_id in ids:
-            books.append(self._convert_calibre_id_to_book(db,book_id))
-        return books
-            
-    def _convert_calibre_id_to_book(self, db, book_id):
-        mi = db.get_metadata(book_id, index_is_id=True)
+    def _convert_id_to_book(self, idval, good=True):
         book = {}
+        book['good'] = good
+        book['calibre_id'] = idval
+        book['title'] = 'Unknown'
+        book['author'] = 'Unknown'
+        book['author_sort'] = 'Unknown'
+            
+        book['comment'] = ''
+        book['url'] = ''
+        book['added'] = False
+        
+        return book
+        
+    
+    # def _convert_calibre_ids_to_books(self, db, ids):
+    #     books = []
+    #     for book_id in ids:
+    #         books.append(self._convert_calibre_id_to_book(db,book_id))
+    #     return books
+            
+    def _populate_book_from_calibre_id(self, book, db=None):
+        mi = db.get_metadata(book['calibre_id'], index_is_id=True)
+        #book = {}
         book['good'] = True
         book['calibre_id'] = mi.id
         book['title'] = mi.title
         book['author'] = authors_to_string(mi.authors)
         book['author_sort'] = mi.author_sort
-        # book['series'] = mi.series
-        # if mi.series:
-        #     book['series_index'] = mi.series_index
-        # else:
-        #     book['series_index'] = 0
-            
         book['comment'] = ''
         book['url'] = ""
         book['added'] = False
         
-        url = self._get_story_url(db,book_id)
+        url = self._get_story_url(db,book['calibre_id'])
         self._set_book_url_and_comment(book,url)
-
-        return book
+        #return book
 
     def _set_book_url_and_comment(self,book,url):
         if not url:
@@ -897,40 +973,6 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         except:
             return None;
 
-
-
-def get_job_details(job):
-    '''
-    Convert the job result into a set of parameters including a detail message
-    summarising the success of the extraction operation.
-    This is used by both the threaded and worker approaches to extraction
-    '''
-    extracted_ids, same_isbn_ids, failed_ids, no_format_ids = job.result
-    if not hasattr(job, 'html_details'):
-        job.html_details = job.details
-    det_msg = []
-    for i, title in failed_ids:
-        if i in no_format_ids:
-            msg = title + ' (No formats)'
-        else:
-            msg = title + ' (ISBN not found)'
-        det_msg.append(msg)
-    if same_isbn_ids:
-        if det_msg:
-            det_msg.append('----------------------------------')
-        for i, title in same_isbn_ids:
-            msg = title + ' (Same ISBN)'
-            det_msg.append(msg)
-    if len(extracted_ids) > 0:
-        if det_msg:
-            det_msg.append('----------------------------------')
-        for i, title, last_modified, isbn in extracted_ids:
-            msg = '%s (Extracted %s)'%(title, isbn)
-            det_msg.append(msg)
-
-    det_msg = '\n'.join(det_msg)
-    return extracted_ids, same_isbn_ids, failed_ids, det_msg
-
 def get_url_list(urls):
     def f(x):
         if x.strip(): return True

defaults.ini

@@ -1,4 +1,4 @@
-# Copyright 2011 Fanficdownloader team
+# Copyright 2012 Fanficdownloader team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -36,7 +36,9 @@ formatext_label:File Extension
 ## Sometimes there are multiple categories and/or genres.
 category_label:Category
 genre_label:Genre
+language_label:Language
 characters_label:Characters
+series_label:Series
 ## Completed/In-Progress
 status_label:Status
 ## Dates story first published, last updated, and downloaded(last with time).
@@ -61,12 +63,19 @@ authorId_label:Author ID
 extratags_label:Extra Tags
 ## The version of fanficdownloader
 ##
-version_label:FFD Version
+version_label:FFDL Version
 
 ## items to include in the title page
 ## Empty entries will *not* appear, even if in the list.
 ## All current formats already include title and author.
-titlepage_entries: category,genre,characters,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,description
+titlepage_entries: series,category,genre,language,characters,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,description
+
+## Try to collect series name and number of this story in series.
+## Some sites (ab)use 'series' for reading lists and personal
+## collections.  This lets us turn it on and off by site without
+## keeping a lengthy titlepage_entries per site and prevents it
+## updating in the plugin.
+collect_series: true
 
 ## include title page as first page.
 include_titlepage: true
@@ -120,21 +129,55 @@ extratags: FanFiction
 ## Primarily for commandline.
 #slow_down_sleep_time:0.5
 
-## output background color--only used by html and epub (and ignored in
-## epub by many readers).  Must be hex code, # will be added.
-background_color: ffffff
-
 ## For use only with stand-alone CLI version--run a command on the
 ## generated file after it's produced.  All of the titlepage_entries
 ## values are available, plus output_filename.
 #post_process_cmd: addbook -f "${output_filename}" -t "${title}"
 
+## Use regular expressions to find and replace (or remove) metadata.
+## For example, you could change Sci-Fi=>SF, remove *-Centered tags,
+## etc.  See http://docs.python.org/library/re.html (look for re.sub)
+## for regexp details.
+## Make sure to keep at least one space at the start of each line and
+## to escape % to %%, if used.
+#replace_metadata:
+# Sci-Fi=>SF
+# Puella Magi Madoka Magica.* => Madoka
+# Comedy=>Humor
+# Crossover: (.*)=>\1
+# (.*)Great(.*)=>\1Moderate\2
+# .*-Centered=>
+
 ## Each output format has a section that overrides [defaults]
 [html]
 
+## output background color--only used by html and epub (and ignored in
+## epub by many readers).  Included below in output_css--will be
+## ignored if not in output_css.
+background_color: ffffff
+
+## Allow customization of CSS.  Make sure to keep at least one space
+## at the start of each line and to escape % to %%.  Also need
+## background_color to be in the same section, if included in CSS.
+output_css:
+ body { background-color: #%(background_color)s; }
+ .CI {
+     text-align:center;
+     margin-top:0px;
+     margin-bottom:0px;
+     padding:0px;
+     }
+ .center   {text-align: center;}
+ .cover    {text-align: center;}
+ .full     {width: 100%%; }
+ .quarter  {width: 25%%; }
+ .smcap    {font-variant: small-caps;}
+ .u        {text-decoration: underline;}
+ .bold     {font-weight: bold;}
+
 [txt]
 ## Add URLs since there aren't links.
-titlepage_entries: category,genre,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,storyUrl, authorUrl, description
+titlepage_entries: series,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,storyUrl, authorUrl, description
 
 ## use \r\n for line endings, the windows convention.  text output only.
 windows_eol: true
@@ -154,11 +197,44 @@ titlepage_use_table: false
 ## When using tables, make these span both columns.
 wide_titlepage_entries: description, storyUrl, author URL
 
+## output background color--only used by html and epub (and ignored in
+## epub by many readers).  Included below in output_css--will be
+## ignored if not in output_css.
+background_color: ffffff
+
+## Allow customization of CSS.  Make sure to keep at least one space
+## at the start of each line and to escape % to %%.  Also need
+## background_color to be in the same section, if included in CSS.
+output_css: 
+ body { background-color: #%(background_color)s;
+        text-align: justify;
+        margin: 2%%; }
+ pre { font-size: x-small; }
+ sml { font-size: small; }
+ h1 { text-align: center; }
+ h2 { text-align: center; }
+ h3 { text-align: center; }
+ h4 { text-align: center; }
+ h5 { text-align: center; }
+ h6 { text-align: center; }
+ .CI {
+     text-align:center;
+     margin-top:0px;
+     margin-bottom:0px;
+     padding:0px;
+     }
+ .center   {text-align: center;}
+ .cover    {text-align: center;}
+ .full     {width: 100%%; }
+ .quarter  {width: 25%%; }
+ .smcap    {font-variant: small-caps;}
+ .u        {text-decoration: underline;}
+ .bold     {font-weight: bold;}
+
 [mobi]
 ## 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,
 ## it is a fake site for testing configuration and output.  It uses
@@ -197,6 +273,9 @@ extratags:
 #username:YourName
 #password:yourpassword
 
+## twilighted.net (ab)uses series as personal reading lists.
+collect_series: false
+
 [www.twiwrite.net]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -205,6 +284,9 @@ extratags:
 #username:YourName
 #password:yourpassword
 
+## twiwrite.net (ab)uses series as personal reading lists.
+collect_series: false
+
 [www.whofic.com]
 
 [www.mediaminer.org]
@@ -222,6 +304,9 @@ extratags:
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+## thewriterscoffeeshop.com (ab)uses series as personal reading lists.
+collect_series: false
+
 [www.ficwad.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -262,6 +347,12 @@ output_filename: ${title}-${siteabbrev}_${authorId}_${storyId}${formatext}
 ## confirm they are adult for adult content.  In commandline version,
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
+## tth is a little unusual--it doesn't require user/pass, but the site
+## keeps track of which chapters you've read and won't send another
+## update until it thinks you're up to date.  This way, on download,
+## it thinks you're up to date.
+#username:YourName
+#password:yourpassword
 
 [overrides]
 ## It may sometimes be useful to override all of the specific format,

downloader.py

@@ -46,7 +46,6 @@ def writeStory(config,adapter,writeformat,metaonly=False,outstream=None):
     return output_filename
 
 def main():
-
    # read in args, anything starting with -- will be treated as --<varible>=<value>
    usage = "usage: %prog [options] storyurl"
    parser = OptionParser(usage)
@@ -215,4 +214,7 @@ def main():
        print us
    
 if __name__ == "__main__":
+    #import time
+    #start = time.time()
     main()
+    #print("Total time seconds:%f"%(time.time()-start))

editconfig.html

@@ -2,7 +2,7 @@
 <html>
   <head>
     <link href="/css/index.css" rel="stylesheet" type="text/css">
-    <title>Fanfiction Downloader - read fanfiction from twilighted.net, fanfiction.net, fictionpress.com, fictionalley.org, ficwad.com, potionsandsnitches.net, harrypotterfanfiction.com, mediaminer.org on Kindle, Nook, Sony Reader, iPad, iPhone, Android, Aldiko, Stanza</title>
+    <title>FanFictionDownLoader - read fanfiction from twilighted.net, fanfiction.net, fictionpress.com, fictionalley.org, ficwad.com, potionsandsnitches.net, harrypotterfanfiction.com, mediaminer.org on Kindle, Nook, Sony Reader, iPad, iPhone, Android, Aldiko, Stanza</title>
     <meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
     <meta name="google-site-verification" content="kCFc-G4bka_pJN6Rv8CapPBcwmq0hbAUZPkKWqRsAYU" />
     <script type="text/javascript">
@@ -22,7 +22,7 @@
   <body>
     <div id='main' style="width: 80%; margin-left: 10%;">
       <h1>
-	<a href="/" style="text-decoration: none; color: black;">FanFiction Downloader</a>
+	<a href="/" style="text-decoration: none; color: black;">FanFictionDownLoader</a>
       </h1>
 
       <div style="text-align: center">
@@ -67,7 +67,7 @@
 	<img src="http://code.google.com/appengine/images/appengine-silver-120x30.gif"
 	     alt="Powered by Google App Engine" />
 	<br/><br/>
-	FanfictionLoader is a web front-end to <A href="http://code.google.com/p/fanficdownloader/">fanficdownloader</a><br/>
+	This is a web front-end to <A href="http://code.google.com/p/fanficdownloader/">FanFictionDownLoader</a><br/>
 	Copyright &copy; Fanficdownloader team
       </div>
 

fanficdownloader/adapters/__init__.py

@@ -1,96 +1,98 @@
-# -*- coding: utf-8 -*-
-
-# Copyright 2011 Fanficdownloader team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-#
-
-import os, re, sys, glob, types
-from os.path import dirname, basename, normpath
-import logging
-import urlparse as up
-
-from .. import exceptions as exceptions
-
-## must import each adapter here.
-
-import adapter_test1
-import adapter_fanfictionnet
-import adapter_castlefansorg
-import adapter_fanfictionnet
-import adapter_fictionalleyorg
-import adapter_fictionpresscom
-import adapter_ficwadcom
-import adapter_fimfictionnet
-import adapter_harrypotterfanfictioncom
-import adapter_mediaminerorg
-import adapter_potionsandsnitchesnet
-import adapter_tenhawkpresentscom
-import adapter_adastrafanficcom
-import adapter_thewriterscoffeeshopcom
-import adapter_tthfanficorg
-import adapter_twilightednet
-import adapter_twiwritenet
-import adapter_whoficcom
-import adapter_siyecouk
-
-## This bit of complexity allows adapters to be added by just adding
-## importing.  It eliminates the long if/else clauses we used to need
-## to pick out the adapter.
-    
-## List of registered site adapters.
-__class_list = []
-
-def imports():
-    for name, val in globals().items():
-        if isinstance(val, types.ModuleType):
-            yield val.__name__
-
-for x in imports():
-    if "fanficdownloader.adapters.adapter_" in x:
-        #print x
-        __class_list.append(sys.modules[x].getClass())
-            
-def getAdapter(config,url):
-    ## fix up leading protocol.
-    fixedurl = re.sub(r"(?i)^[htp]+[:/]+","http://",url.strip())
-    if not fixedurl.startswith("http"):
-        fixedurl = "http://%s"%url
-    ## remove any trailing '#' locations.
-    fixedurl = re.sub(r"#.*$","",fixedurl)
-    
-    ## remove any trailing '&' parameters--?sid=999 will be left.
-    ## that's all that any of the current adapters need or want.
-    fixedurl = re.sub(r"&.*$","",fixedurl)
-    
-    parsedUrl = up.urlparse(fixedurl)
-    domain = parsedUrl.netloc.lower()
-    if( domain != parsedUrl.netloc ):
-        fixedurl = fixedurl.replace(parsedUrl.netloc,domain)
-
-    logging.debug("site:"+domain)
-    cls = getClassFor(domain)
-    if not cls:
-        logging.debug("trying site:www."+domain)
-        cls = getClassFor("www."+domain)
-        fixedurl = fixedurl.replace("http://","http://www.")
-    if cls:
-        adapter = cls(config,fixedurl) # raises InvalidStoryURL
-        return adapter
-    # No adapter found.
-    raise exceptions.UnknownSite( url, [cls.getSiteDomain() for cls in __class_list] )
-
-def getClassFor(domain):
-    for cls in __class_list:
-        if cls.matchesSite(domain):
-            return cls
+# -*- coding: utf-8 -*-
+
+# Copyright 2011 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import os, re, sys, glob, types
+from os.path import dirname, basename, normpath
+import logging
+import urlparse as up
+
+from .. import exceptions as exceptions
+
+## must import each adapter here.
+
+import adapter_test1
+import adapter_fanfictionnet
+import adapter_castlefansorg
+import adapter_fanfictionnet
+import adapter_fictionalleyorg
+import adapter_fictionpresscom
+import adapter_ficwadcom
+import adapter_fimfictionnet
+import adapter_harrypotterfanfictioncom
+import adapter_mediaminerorg
+import adapter_potionsandsnitchesnet
+import adapter_tenhawkpresentscom
+import adapter_adastrafanficcom
+import adapter_thewriterscoffeeshopcom
+import adapter_tthfanficorg
+import adapter_twilightednet
+import adapter_twiwritenet
+import adapter_whoficcom
+import adapter_siyecouk
+import adapter_archiveofourownorg
+import adapter_ficbooknet
+
+## This bit of complexity allows adapters to be added by just adding
+## importing.  It eliminates the long if/else clauses we used to need
+## to pick out the adapter.
+    
+## List of registered site adapters.
+__class_list = []
+
+def imports():
+    for name, val in globals().items():
+        if isinstance(val, types.ModuleType):
+            yield val.__name__
+
+for x in imports():
+    if "fanficdownloader.adapters.adapter_" in x:
+        #print x
+        __class_list.append(sys.modules[x].getClass())
+            
+def getAdapter(config,url):
+    ## fix up leading protocol.
+    fixedurl = re.sub(r"(?i)^[htp]+[:/]+","http://",url.strip())
+    if not fixedurl.startswith("http"):
+        fixedurl = "http://%s"%url
+    ## remove any trailing '#' locations.
+    fixedurl = re.sub(r"#.*$","",fixedurl)
+    
+    ## remove any trailing '&' parameters--?sid=999 will be left.
+    ## that's all that any of the current adapters need or want.
+    fixedurl = re.sub(r"&.*$","",fixedurl)
+    
+    parsedUrl = up.urlparse(fixedurl)
+    domain = parsedUrl.netloc.lower()
+    if( domain != parsedUrl.netloc ):
+        fixedurl = fixedurl.replace(parsedUrl.netloc,domain)
+
+    logging.debug("site:"+domain)
+    cls = getClassFor(domain)
+    if not cls:
+        logging.debug("trying site:www."+domain)
+        cls = getClassFor("www."+domain)
+        fixedurl = fixedurl.replace("http://","http://www.")
+    if cls:
+        adapter = cls(config,fixedurl) # raises InvalidStoryURL
+        return adapter
+    # No adapter found.
+    raise exceptions.UnknownSite( url, [cls.getSiteDomain() for cls in __class_list] )
+
+def getClassFor(domain):
+    for cls in __class_list:
+        if cls.matchesSite(domain):
+            return cls

fanficdownloader/adapters/adapter_adastrafanficcom.py

@@ -174,13 +174,33 @@ class AdAstraFanficComSiteAdapter(BaseSiteAdapter):
                     self.story.setMetadata('status', 'In-Progress')
 
             if 'Published' in label:
-                self.story.setMetadata('datePublished', makeDate(value.strip(), "%m/%d/%Y"))
+                self.story.setMetadata('datePublished', makeDate(value.strip(), "%d %b %Y"))
             
             if 'Updated' in label:
                 # there's a stray [ at the end.
                 #value = value[0:-1]
-                self.story.setMetadata('dateUpdated', makeDate(value.strip(), "%m/%d/%Y"))
+                self.story.setMetadata('dateUpdated', makeDate(value.strip(), "%d %b %Y"))
 
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    break
+                i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
 
     def getChapterText(self, url):
 

fanficdownloader/adapters/adapter_archiveofourownorg.py

@@ -0,0 +1,267 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2011 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter, utf8FromSoup, makeDate
+
+def getClass():
+    return ArchiveOfOurOwnOrgAdapter
+
+
+class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["utf8",
+                       "Windows-1252"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+							   
+							   
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])
+        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/works/'+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','ao3')
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%Y-%b-%d"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'www.archiveofourown.org'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/works/123456"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/works/")+r"\d+(/chapters/\d+)?/?$"
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        if self.is_adult or self.getConfig("is_adult"):
+            addurl = "?view_adult=true"
+        else:
+            addurl=""
+
+        meta = self.url+addurl
+        url = self.url+'/navigate'+addurl
+        logging.debug("URL: "+meta)
+
+        try:
+            data = self._fetchUrl(url)
+            meta = self._fetchUrl(meta)
+
+            if "This work could have adult content. If you proceed you have agreed that you are willing to see such content." in meta:
+                raise exceptions.AdultCheckRequired(self.url)
+            
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.meta)
+            else:
+                raise e
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        metasoup = bs.BeautifulSoup(meta)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        a = soup.find('a', href=re.compile(r"^/works/\w+"))
+        self.story.setMetadata('title',a.string)
+		
+        # Find authorid and URL from... author url.
+        a = soup.find('a', href=re.compile(r"^/users/\w+/pseuds/\w+"))
+        self.story.setMetadata('authorId',a['href'].split('/')[2])
+        self.story.setMetadata('authorUrl','http://'+self.host+a['href'])
+        self.story.setMetadata('author',a.text)
+
+        # Find the chapters:
+        chapters=soup.findAll('a', href=re.compile(r'/works/'+self.story.getMetadata('storyId')+"/chapters/\d+$"))
+        self.story.setMetadata('numChapters',len(chapters))
+        logging.debug("numChapters: (%s)"%self.story.getMetadata('numChapters'))
+        for x in range(0,len(chapters)):
+            # just in case there's tags, like <i> in chapter titles.
+            chapter=chapters[x]
+            if len(chapters)==1:
+                self.chapterUrls.append((self.story.getMetadata('title'),'http://'+self.host+chapter['href']+addurl))
+            else:
+                self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+chapter['href']+addurl))
+
+
+
+        a = metasoup.find('blockquote',{'class':'userstuff'})
+        if a != None:
+            self.story.setMetadata('description',a.text)
+		
+        a = metasoup.find('dd',{'class':"rating tags"})
+        if a != None:
+            self.story.setMetadata('rating',stripHTML(a.text))
+		
+        a = metasoup.find('dd',{'class':"fandom tags"})
+        fandoms = a.findAll('a',{'class':"tag"})
+        fandomstext = [fandom.string for fandom in fandoms]
+        for fandom in fandomstext:
+            self.story.addToList('category',fandom.string)
+		
+        a = metasoup.find('dd',{'class':"warning tags"})
+        if a != None:
+            warnings = a.findAll('a',{'class':"tag"})
+            warningstext = [warning.string for warning in warnings]
+            for warning in warningstext:
+                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)
+		
+        a = metasoup.find('dd',{'class':"freeform tags"})
+        if a != None:
+            genres = a.findAll('a',{'class':"tag"})
+            genrestext = [genre.string for genre in genres]
+            for genre in genrestext:
+                self.story.addToList('genre',genre.string)
+        a = metasoup.find('dd',{'class':"category tags"})
+        if a != None:
+            genres = a.findAll('a',{'class':"tag"})
+            genrestext = [genre.string for genre in genres]
+            for genre in genrestext:
+                if genre != "Gen":
+                    self.story.addToList('genre',genre.string)
+		
+        a = metasoup.find('dd',{'class':"character tags"})
+        if a != None:
+            chars = a.findAll('a',{'class':"tag"})
+            charstext = [char.string for char in chars]
+            for char in charstext:
+                self.story.addToList('characters',char.string)
+        a = metasoup.find('dd',{'class':"relationship tags"})
+        if a != None:
+            chars = a.findAll('a',{'class':"tag"})
+            charstext = [char.string for char in chars]
+            for char in charstext:
+                self.story.addToList('characters',char.string)
+		
+
+        stats = metasoup.find('dl',{'class':'stats'})
+        dt = stats.findAll('dt')
+        dd = stats.findAll('dd')
+        for x in range(0,len(dt)):
+            label = dt[x].text
+            value = dd[x].text
+
+            if 'Words:' in label:
+                self.story.setMetadata('numWords', value)
+				
+            if 'Chapters:' in label:
+                if value.split('/')[0] == value.split('/')[1]:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Updated' in label:
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+				
+            if 'Completed' in label:
+                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+'/fanfic/'+b['href']
+            series_index = int(a.text.split(' ')[1])
+            self.setSeries(series_name, series_index)
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+        logging.debug('Getting chapter text from: %s' % url)
+		
+        chapter=bs.BeautifulSoup('<div class="story"></div>')
+        soup = bs.BeautifulSoup(self._fetchUrl(url),selfClosingTags=('br','hr'))
+		
+        headnotes = soup.find('div', {'class' : "preface group"}).find('div', {'class' : "notes module"})
+        if headnotes != None:
+            headnotes = headnotes.find('blockquote', {'class' : "userstuff"})
+            if headnotes != None:
+                chapter.append(bs.BeautifulSoup("<b>Author's Note:</b>"))
+                chapter.append(headnotes)
+        
+        chapsumm = soup.find('div', {'id' : "summary"})
+        if chapsumm != None:
+            chapsumm = chapsumm.find('blockquote')
+            chapter.append(bs.BeautifulSoup("<b>Summary for the Chapter:</b>"))
+            chapter.append(chapsumm)
+        chapnotes = soup.find('div', {'id' : "notes"})
+        if chapnotes != None:
+            chapnotes = chapnotes.find('blockquote')
+            if chapnotes != None:
+                chapter.append(bs.BeautifulSoup("<b>Notes for the Chapter:</b>"))
+                chapter.append(chapnotes)
+		
+        text = soup.find('div', {'class' : "userstuff module"})
+        chtext = text.find('h3', {'class' : "landmark heading"})
+        if chtext:
+            chtext.extract()
+        chapter.append(text)
+		
+        chapfoot = soup.find('div', {'class' : "end notes module", 'role' : "complementary"})
+        if chapfoot != None:
+            chapfoot = chapfoot.find('blockquote')
+            chapter.append(bs.BeautifulSoup("<b>Notes for the Chapter:</b>"))
+            chapter.append(chapfoot)
+		
+        footnotes = soup.find('div', {'id' : "work_endnotes"})
+        if footnotes != None:
+            footnotes = footnotes.find('blockquote')
+            chapter.append(bs.BeautifulSoup("<b>Author's Note:</b>"))
+            chapter.append(footnotes)
+			
+        if None == soup:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return utf8FromSoup(chapter)

fanficdownloader/adapters/adapter_castlefansorg.py

@@ -272,6 +272,26 @@ class CastleFansOrgAdapter(BaseSiteAdapter): # XXX
                 #value = value[0:-1]
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
 
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/fanfic/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    break
+                i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 

fanficdownloader/adapters/adapter_fanfictionnet.py

@@ -91,17 +91,20 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
             # rather nasty way to check for a newer chapter.  ffnet has a
             # tendency to send out update notices in email before all
             # their servers are showing the update on the first chapter.
-            chapcount = len(soup.find('select', { 'name' : 'chapter' } ).findAll('option'))
+            try:
+                chapcount = len(soup.find('select', { 'name' : 'chapter' } ).findAll('option'))
             # get chapter part of url.
+            except:
+                chapcount = 1
             chapter = url.split('/',)[5]
             tryurl = "http://%s/s/%s/%d/"%(self.getSiteDomain(),
                                            self.story.getMetadata('storyId'),
                                            chapcount+1)
-            #print('=Trying newer chapter: %s' % tryurl)
+            print('=Trying newer chapter: %s' % tryurl)
             newdata = self._fetchUrl(tryurl)
             if "Chapter not found. Please check to see you are not using an outdated url." \
                     not in newdata:
-                #print('=======Found newer chapter: %s' % tryurl)
+                print('=======Found newer chapter: %s' % tryurl)
                 soup = bs.BeautifulSoup(newdata)
         except:
             pass
@@ -198,7 +201,6 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         metatext = a.findNext(text=re.compile(r' - Reviews:'))
         if metatext == None: # indicates there's no Reviews, look for id: instead.
             metatext = a.findNext(text=re.compile(r' - id:'))
-        #print("========= metatext:\n%s"%metatext)
 
         # after Rating, the same bit of text containing id:123456 contains
         # Complete--if completed.
@@ -212,7 +214,8 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         # <meta name="description" content="Chapter 1 of a Transformers/Beast Wars  - Adventure/Friendship fanfiction with characters Bumblebee. TFA: What would you do if you was being abused all you life? Follow NightRunner as she goes through her spark breaking adventure of getting away from her father..">
         # (fp)<meta name="description" content="Chapter 1 of a Sci-Fi  - Adventure/Humor fiction. Felix Max was just your regular hyperactive kid until he accidently caused his own fathers death. Now he has meta-humans trying to hunt him down with a corrupt goverment to back them up. Oh, and did I mention he has no Powers yet?.">
         # <meta name="description" content="Chapter 1 of a Bleach  - Adventure/Angst fanfiction with characters Ichigo K. & Neliel T. O./Nel. Time travel with a twist. Time can be a real bi***. Ichigo finds that fact out when he accidentally goes back in time. Is this his second chance or is fate just screwing with him. Not a crack fic.IchixNelXHime.">
-        m = re.match(r"^(?:Chapter \d+ of a|A) (?:.*?)  (?:- (?P<genres>.*?) )?(?:crossover )?(?:fan)?fiction(?:[ ]+with characters (?P<char1>.*?\.?)(?: & (?P<char2>.*?\.?))?\. )?",
+        # <meta name="description" content="Chapter 1 of a Harry Potter and Transformers  - Humor/Adventure crossover fanfiction  with characters: Harry P. & Ironhide. IT’s one thing to be tossed thru the Veil for something he didn’t do. It was quite another to wake in his animigus form in a world not his own. Harry just knew someone was laughing at him somewhere. Mech/Mech pairings inside..">
+        m = re.match(r"^(?:Chapter \d+ of a|A) (?:.*?)  (?:- (?P<genres>.*?) )?(?:crossover )?(?:fan)?fiction(?P<chars>[ ]+with characters)?",
                      soup.find('meta',{'name':'description'})['content'])
         if m != None:
             genres=m.group('genres')
@@ -222,7 +225,8 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
                 for g in genres.split('/'):
                     self.story.addToList('genre',g)
 
-            if m.group('char1') != None:
+            if m.group('chars') != None:
+
                 # At this point we've proven that there's character(s)
                 # We can't reliably parse characters out of meta name="description".
                 # There's no way to tell that "with characters Ichigo K. & Neliel T. O./Nel. " ends at "Nel.", not "T."
@@ -230,12 +234,16 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
                 # reviewstext can take form of:
                 # - English -  Shinji H. - Updated: 01-13-12 - Published: 12-20-11 - id:7654123
                 # - English - Adventure/Angst -  Ichigo K. & Neliel T. O./Nel - Reviews:
+                # - English - Humor/Adventure -  Harry P. & Ironhide - Reviews:
                 mc = re.match(r" - (?P<lang>[^ ]+ - )(?P<genres>[^ ]+ - )? (?P<chars>.+?) - (Reviews|Updated|Published)",
                               metatext)
                 chars = mc.group("chars")
                 for c in chars.split(' & '):
                     self.story.addToList('characters',c)
-        
+        m = re.match(r" - (?P<lang>[^ ]+)",metatext)
+        if m.group('lang') != None:
+            self.story.setMetadata('language',m.group('lang'))
+                    
         return
 
     def getChapterText(self, url):

fanficdownloader/adapters/adapter_ficbooknet.py

@@ -0,0 +1,221 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2011 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import datetime
+import logging
+import re
+import urllib2
+from .. import translit
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter, utf8FromSoup, makeDate
+
+
+def getClass():
+    return FicBookNetAdapter
+
+
+class FicBookNetAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["utf8",
+                       "Windows-1252"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])
+        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/readfic/'+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','fbn')
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%d %m %Y" 
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'www.ficbook.net'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/readfic/12345"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/readfic/")+r"\d+"
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+        url=self.url
+        logging.debug("URL: "+url)
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+				
+
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+
+        # Now go hunting for all the meta data and the chapter list.
+		
+        table = soup.find('td',{'width':'50%'})
+        
+        ## Title
+        a = soup.find('h1')
+        self.story.setMetadata('title',a.string)
+        logging.debug("Title: (%s)"%self.story.getMetadata('title'))
+        
+        # Find authorid and URL from... author url.
+        a = table.find('a')
+        self.story.setMetadata('authorId',a.text) # Author's name is unique
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.text)
+        logging.debug("Author: (%s)"%self.story.getMetadata('author'))
+
+        # Find the chapters:
+        chapters = soup.find('div', {'class' : 'part_list'})
+        if chapters != None:
+            chapters=chapters.findAll('a', href=re.compile(r'/readfic/'+self.story.getMetadata('storyId')+"/\d+#part_content$"))
+            self.story.setMetadata('numChapters',len(chapters))
+            for x in range(0,len(chapters)):
+                chapter=chapters[x]
+                churl='http://'+self.host+chapter['href']
+                self.chapterUrls.append((stripHTML(chapter),churl))
+                if x == 0:
+                    pubdate = translit.translit(stripHTML(bs.BeautifulSoup(self._fetchUrl(churl)).find('div', {'class' : 'part_added'}).find('span')))
+                if x == len(chapters)-1:
+                    update = translit.translit(stripHTML(bs.BeautifulSoup(self._fetchUrl(churl)).find('div', {'class' : 'part_added'}).find('span')))
+        else:
+            self.chapterUrls.append((self.story.getMetadata('title'),url))
+            self.story.setMetadata('numChapters',1)
+            pubdate=translit.translit(stripHTML(soup.find('div', {'class' : 'part_added'}).find('span')))
+            update=pubdate
+
+        logging.debug("numChapters: (%s)"%self.story.getMetadata('numChapters'))
+
+        if not ',' in pubdate:
+            pubdate=datetime.date.today().strftime(self.dateformat)
+        if not ',' in update:
+            update=datetime.date.today().strftime(self.dateformat)
+        pubdate=pubdate.split(',')[0]
+        update=update.split(',')[0]
+		
+        fullmon = {"yanvarya":"01", "января":"01",
+           "fievralya":"02", "февраля":"02",
+           "marta":"03", "марта":"03",
+           "aprielya":"04", "апреля":"04",
+           "maya":"05", "мая":"05",
+           "iyunya":"06", "июня":"06",
+           "iyulya":"07", "июля":"07",
+           "avghusta":"08", "августа":"08",
+           "sentyabrya":"09", "сентября":"09",
+           "oktyabrya":"10", "октября":"10",
+           "noyabrya":"11", "ноября":"11",
+           "diekabrya":"12", "декабря":"12" }
+        for (name,num) in fullmon.items():
+            if name in pubdate:
+                pubdate = pubdate.replace(name,num)
+            if name in update:
+                update = update.replace(name,num)
+
+        self.story.setMetadata('dateUpdated', makeDate(update, self.dateformat))
+        self.story.setMetadata('datePublished', makeDate(pubdate, self.dateformat))
+        self.story.setMetadata('language','Russian')
+		
+        pr=soup.find('a', href=re.compile(r'/printfic/\w+'))
+        pr='http://'+self.host+pr['href']
+        pr = bs.BeautifulSoup(self._fetchUrl(pr))
+        pr=pr.findAll('div', {'class' : 'part_text'})
+        i=0
+        for part in pr:
+            i=i+len(stripHTML(part).split(' '))
+        self.story.setMetadata('numWords', str(i))
+		
+        i=0
+        fandoms = table.findAll('a', href=re.compile(r'/fanfiction/\w+'))
+        for fandom in fandoms:
+            self.story.addToList('category',fandom.string)
+            i=i+1
+        if i > 1:
+            self.story.addToList('genre', 'Кроссовер')
+		
+        meta=table.findAll('a', href=re.compile(r'/ratings/'))
+        i=0
+        for m in meta:
+            if i == 0:
+                self.story.setMetadata('rating', m.find('b').text)
+                i=1
+            elif i == 1:
+                if not "," in m.nextSibling:
+                    i=2
+                self.story.addToList('genre', m.find('b').text)
+            elif i == 2:
+                self.story.addToList('warnings', m.find('b').text)
+		
+
+        if table.find('span', {'style' : 'color: green'}):
+            self.story.setMetadata('status', 'Completed')
+        else:
+            self.story.setMetadata('status', 'In Progress')
+		
+
+        tags = table.findAll('b')
+        for tag in tags:
+            label = translit.translit(tag.text)
+            if 'Piersonazhi:' in label or 'Персонажи:' in label:
+                chars=tag.nextSibling.string.split(', ')
+                for char in chars:
+                    self.story.addToList('characters',char)
+                break
+				
+        summary=soup.find('span', {'class' : 'urlize'})
+        self.story.setMetadata('description', summary.text)
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        chapter = soup.find('div', {'class' : 'public_beta'})
+        if chapter == None:
+            chapter = soup.find('div', {'class' : 'public_beta_disabled'})
+
+        if None == chapter:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return utf8FromSoup(chapter)

fanficdownloader/adapters/adapter_ficwadcom.py

@@ -201,9 +201,6 @@ class FicwadComSiteAdapter(BaseSiteAdapter):
 
     def getChapterText(self, url):
         logging.debug('Getting chapter text from: %s' % url)
-        time.sleep(0.5) ## ffnet tends to fail more if hit too fast.
-                        ## This is in additional to what ever the
-                        ## slow_down_sleep_time setting is.
         soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
                                      selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
 

fanficdownloader/adapters/adapter_fimfictionnet.py

@@ -20,6 +20,7 @@ import logging
 import re
 import urllib2
 import cookielib as cl
+import datetime
 
 from .. import BeautifulSoup as bs
 from ..htmlcleanup import stripHTML
@@ -107,7 +108,7 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
         for character in [character_icon['title'] for character_icon in soup.findAll("a", {"class":"character_icon"})]:
             self.story.addToList("characters", character)
         for category in [category.text for category in soup.find("div", {"class":"categories"}).findAll("a")]:
-            self.story.addToList("category", category)
+            self.story.addToList("genre", category)
         self.story.addToList("category", "My Little Pony")
         
         
@@ -142,18 +143,27 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
             pass
         self.story.setMetadata('description', description_soup.text)
         
-        # Unfortunately, nowhere on the page is the year mentioned. Because we would much rather update the story needlessly
-        # than miss an update, we hardcode the year of creation and update to be 2011.
+        # Unfortunately, nowhere on the page is the year mentioned.
+        # Best effort to deal with this:
+        # Use this year, if that's a date in the future, subtract one year.
+        # Their earliest story is Jun, so they'll probably change the date
+        # around then.
 
+        now = datetime.datetime.now()
+        
         # Get the date of creation from the first chapter
         datePublished_text = chapterDates[0]
         day, month = datePublished_text.split()
         day = re.sub(r"[^\d.]+", '', day)
-        datePublished = makeDate("2011"+month+day, "%Y%b%d")
+        datePublished = makeDate("%s%s%s"%(now.year,month,day), "%Y%b%d")
+        if datePublished > now :
+            datePublished = datePublished.replace(year=now.year-1)
         self.story.setMetadata("datePublished", datePublished)
         dateUpdated_soup = bs.BeautifulSoup(data).find("div", {"class":"calendar"})
         dateUpdated_soup.find('span').extract()
-        dateUpdated = makeDate("2011"+dateUpdated_soup.text, "%Y%b%d")
+        dateUpdated = makeDate("%s%s"%(now.year,dateUpdated_soup.text), "%Y%b%d")
+        if dateUpdated > now :
+            dateUpdated = datePublished.replace(year=now.year-1)
         self.story.setMetadata("dateUpdated", dateUpdated)
         
     def getChapterText(self, url):

fanficdownloader/adapters/adapter_potionsandsnitchesnet.py

@@ -176,7 +176,27 @@ class PotionsAndSnitchesNetSiteAdapter(BaseSiteAdapter):
                 #value = value[0:-1]
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), "%b %d %Y"))
 
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/fanfiction/'+a['href']
 
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    break
+                i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+        
     def getChapterText(self, url):
 
         logging.debug('Getting chapter text from: %s' % url)

fanficdownloader/adapters/adapter_siyecouk.py

@@ -81,7 +81,7 @@ class SiyeCoUkAdapter(BaseSiteAdapter): # XXX
         return "http://"+self.getSiteDomain()+"/siye/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
-        return re.escape("http://")+r"(www\.)?"+re.escape("siye.co.uk/siye/viewstory.php?sid=")+r"\d+$"
+        return re.escape("http://")+r"(www\.)?siye\.co\.uk/(siye/)?"+re.escape("viewstory.php?sid=")+r"\d+$"
 
     # ## Login seems to be reasonably standard across eFiction sites.
     # def needToLoginCheck(self, data):
@@ -228,15 +228,13 @@ class SiyeCoUkAdapter(BaseSiteAdapter): # XXX
             if part.startswith("Summary:"):
                 part = part[part.find(':')+1:]
                 self.story.setMetadata('description',part)
-
-        
-
+                
         # want to get the next tr of the table.
         #print("%s"%titlea.parent.parent.findNextSibling('tr'))
             
         # eFiction sites don't help us out a lot with their meta data
         # formating, so it's a little ugly.
-        moremeta = stripHTML(titlea.parent.parent.findNextSibling('tr'))
+        moremeta = stripHTML(titlea.parent.parent.parent.find('div',{'class':'desc'}))
         for part in moremeta.replace(' - ','\n').split('\n'):
             #print("part:%s"%part)
             try:
@@ -259,7 +257,25 @@ class SiyeCoUkAdapter(BaseSiteAdapter): # XXX
             if name == 'Words':
                 self.story.setMetadata('numWords', value)
 
-        
+        try:
+            # Find Series name from series URL.
+            a = titlea.findPrevious('a', href=re.compile(r"series.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    break
+                i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass        
 
     # grab the text for an individual chapter.
     def getChapterText(self, url):

fanficdownloader/adapters/adapter_tenhawkpresentscom.py

@@ -205,6 +205,26 @@ class TenhawkPresentsComSiteAdapter(BaseSiteAdapter):
                 #value = value[0:-1]
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
 
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    break
+                i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
 
     def getChapterText(self, url):
 

fanficdownloader/adapters/adapter_test1.py

@@ -84,7 +84,25 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
         else:
             self.story.setMetadata('dateUpdated',makeDate("1975-04-15","%Y-%m-%d"))
         self.story.setMetadata('numWords','123456')
-        self.story.setMetadata('status','In-Completed')
+
+        idnum = int(self.story.getMetadata('storyId'))
+        if idnum % 2 == 1:
+            self.story.setMetadata('status','In-Progress')
+        else:
+            self.story.setMetadata('status','Completed')
+
+        langs = {
+            0:"English",
+            1:"Russian",
+            2:"French",
+            3:"German",
+            }
+        if idnum < 10:
+            self.story.setMetadata('language',langs[idnum%len(langs)])
+        # greater than 10, no language.
+            
+        self.setSeries('The Great Test',idnum)
+        
         self.story.setMetadata('rating','Tweenie')
         
         self.story.setMetadata('authorId','98765')
@@ -96,7 +114,8 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
         self.story.addToList('category','Harry Potter')
         self.story.addToList('category','Furbie')
         self.story.addToList('category','Crossover')
-        
+        self.story.addToList('category',u'Puella Magi Madoka Magica/魔法少女まどか★マギカ')
+        self.story.addToList('category',u'Magical Girl Lyrical Nanoha')
         self.story.addToList('genre','Fantasy')
         self.story.addToList('genre','SF')
         self.story.addToList('genre','Noir')
@@ -108,7 +127,7 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
                             ('Chapter 4',self.url+"&chapter=5"),
                             ('Chapter 5',self.url+"&chapter=6"),
                             ('Chapter 6',self.url+"&chapter=6"),
-                            # ('Chapter 7',self.url+"&chapter=6"),
+                            ('Chapter 7',self.url+"&chapter=6"),
                             # ('Chapter 8',self.url+"&chapter=6"),
                             # ('Chapter 9',self.url+"&chapter=6"),
                             # ('Chapter 0',self.url+"&chapter=6"),

fanficdownloader/adapters/adapter_thewriterscoffeeshopcom.py

@@ -207,7 +207,26 @@ class TheWritersCoffeeShopComSiteAdapter(BaseSiteAdapter):
                 #value = value[0:-1]
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
 
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/library/'+a['href']
 
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    break
+                i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
     def getChapterText(self, url):
 
         logging.debug('Getting chapter text from: %s' % url)

fanficdownloader/adapters/adapter_tthfanficorg.py

@@ -214,6 +214,12 @@ class TwistingTheHellmouthSiteAdapter(BaseSiteAdapter):
                 self.chapterUrls.append((stripHTML(o),url))
 
         self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        pseries = soup.find('p', {'style':'margin-top:0px'})
+        m = re.match('This story is No\. (?P<num>\d+) in the series &quot;(?P<series>.+)&quot;\.',
+                     pseries.text)
+        if m:
+            self.setSeries(m.group('series'),m.group('num'))
         
         return
 

fanficdownloader/adapters/adapter_twilightednet.py

@@ -204,6 +204,25 @@ class TwilightedNetSiteAdapter(BaseSiteAdapter):
                 #value = value[0:-1]
                 self.story.setMetadata('dateUpdated', makeDate(value.strip(), "%B %d, %Y"))
 
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/'+a['href']
+            
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    break
+                i+=1
+        
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
 
     def getChapterText(self, url):
 

fanficdownloader/adapters/adapter_twiwritenet.py

@@ -217,6 +217,25 @@ class TwiwriteNetSiteAdapter(BaseSiteAdapter):
                 value = value[0:-1]
                 self.story.setMetadata('dateUpdated', makeDate(value.strip(), "%B %d, %Y"))
 
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    break
+                i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
 
     def getChapterText(self, url):
 

fanficdownloader/adapters/adapter_whoficcom.py

@@ -189,6 +189,26 @@ class WhoficComSiteAdapter(BaseSiteAdapter):
             if name == 'Word Count':
                 self.story.setMetadata('numWords', value)
 
+        try:
+            # Find Series name from series URL.
+            a = metadata.find('a', href=re.compile(r"series.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    break
+                i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
     def getChapterText(self, url):
 
         logging.debug('Getting chapter text from: %s' % url)

fanficdownloader/adapters/base_adapter.py

@@ -40,6 +40,7 @@ except:
     #logging.info("Hook to make default deadline 10.0 NOT installed--not using appengine")
 
 from ..story import Story
+from ..gziphttp import GZipProcessor
 from ..configurable import Configurable
 from ..htmlcleanup import removeEntities, removeAllEntities, stripHTML
 from ..exceptions import InvalidStoryURL
@@ -72,7 +73,7 @@ class BaseSiteAdapter(Configurable):
         self.password = ""
         self.is_adult=False
         
-        self.opener = u2.build_opener(u2.HTTPCookieProcessor())
+        self.opener = u2.build_opener(u2.HTTPCookieProcessor(),GZipProcessor())
         self.storyDone = False
         self.metadataDone = False
         self.story = Story()
@@ -229,6 +230,11 @@ class BaseSiteAdapter(Configurable):
         "Needs to be overriden in each adapter class."
         pass
 
+    # Just for series, in case we choose to change how it's stored or represented later.
+    def setSeries(self,name,num):
+        if self.getConfig('collect_series'):
+            self.story.setMetadata('series','%s [%s]'%(name, num))
+
 fullmon = {"January":"01", "February":"02", "March":"03", "April":"04", "May":"05",
            "June":"06","July":"07", "August":"08", "September":"09", "October":"10",
            "November":"11", "December":"12" }

fanficdownloader/gziphttp.py

@@ -0,0 +1,38 @@
+## Borrowed from http://techknack.net/python-urllib2-handlers/
+
+import urllib2
+from gzip import GzipFile
+from StringIO import StringIO
+
+class GZipProcessor(urllib2.BaseHandler):
+    """A handler to add gzip capabilities to urllib2 requests
+    """
+    def http_request(self, req):
+        req.add_header("Accept-Encoding", "gzip")
+        return req
+    https_request = http_request
+
+    def http_response(self, req, resp):
+        #print("Content-Encoding:%s"%resp.headers.get("Content-Encoding"))
+        if resp.headers.get("Content-Encoding") == "gzip":
+            gz = GzipFile(
+                        fileobj=StringIO(resp.read()),
+                        mode="r"
+                      )
+#            resp.read = gz.read
+#            resp.readlines = gz.readlines
+#            resp.readline = gz.readline
+#            resp.next = gz.next
+            old_resp = resp
+            resp = urllib2.addinfourl(gz, old_resp.headers, old_resp.url, old_resp.code)
+            resp.msg = old_resp.msg
+        return resp
+    https_response = http_response
+
+# brave new world - 1:30 w/o, 1:10 with?  40 chapters, so 20s from sleeps.
+# with gzip, no sleep: 47.469
+# w/o gzip, no sleep: 47.736
+
+# I Am What I Am 67 chapters
+# w/o gzip: 57.168
+# w/ gzip: 40.692

fanficdownloader/htmlcleanup.py

@@ -27,7 +27,7 @@ def _unirepl(match):
     return unichr(value)
 
 def _replaceNumberEntities(data):
-    p = re.compile(r'&#(x?)(\d+);')
+    p = re.compile(r'&#(x?)([0-9a-fA-F]+);')
     return p.sub(_unirepl, data)
 
 def _replaceNotEntities(data):

fanficdownloader/story.py

@@ -15,27 +15,83 @@
 # limitations under the License.
 #
 
-import os
+import os, re
 
 from htmlcleanup import conditionalRemoveEntities, removeAllEntities
 
+# The list comes from ffnet, the only multi-language site we support
+# at the time of writing.  Values are taken largely from pycountry,
+# but with some corrections and guesses.
+langs = {
+    "English":"en",
+    "Spanish":"es",
+    "French":"fr",
+    "German":"de",
+    "Chinese":"zh",
+    "Japanese":"ja",
+    "Dutch":"nl",
+    "Portuguese":"pt",
+    "Russian":"ru",
+    "Italian":"it",
+    "Bulgarian":"bg",
+    "Polish":"pl",
+    "Hungarian":"hu",
+    "Hebrew":"he",
+    "Arabic":"ar",
+    "Swedish":"sv",
+    "Norwegian":"no",
+    "Danish":"da",
+    "Finnish":"fi",
+    "Filipino":"fil",
+    "Esperanto":"eo",
+    "Hindi":"hi",
+    "Punjabi":"pa",
+    "Farsi":"fa",
+    "Greek":"el",
+    "Romanian":"ro",
+    "Albanian":"sq",
+    "Serbian":"sr",
+    "Turkish":"tr",
+    "Czech":"cs",
+    "Indonesian":"id",
+    "Croatian":"hr",
+    "Catalan":"ca",
+    "Latin":"la",
+    "Korean":"ko",
+    "Vietnamese":"vi",
+    "Thai":"th",
+    "Devanagari":"hi",
+    }
+
 class Story:
     
     def __init__(self):
         try:
             self.metadata = {'version':os.environ['CURRENT_VERSION_ID']}
         except:
-            self.metadata = {'version':'4.2'}
+            self.metadata = {'version':'4.3'}
+        self.replacements = []
         self.chapters = [] # chapters will be tuples of (title,html)
         self.listables = {} # some items (extratags, category, warnings & genres) are also kept as lists.
 
     def setMetadata(self, key, value):
         ## still keeps < < and &
         self.metadata[key]=conditionalRemoveEntities(value)
+        if key == "language":
+            try:
+                self.metadata['langcode'] = langs[self.metadata[key]]
+            except:
+                self.metadata['langcode'] = 'en'
 
     def getMetadataRaw(self,key):
         if self.metadata.has_key(key):
             return self.metadata[key]
+
+    def doReplacments(self,value):
+        for (p,v) in self.replacements:
+            if (isinstance(value,str) or isinstance(value,unicode)) and re.match(p,value):
+                value = re.sub(p,v,value)                
+        return value;
         
     def getMetadata(self, key, removeallentities=False):
         value = None
@@ -50,21 +106,22 @@ class Story:
                     value = value.strftime("%Y-%m-%d %H:%M:%S")
                 if key == "datePublished" or key == "dateUpdated":
                  value = value.strftime("%Y-%m-%d")
-                 
+
+        value=self.doReplacments(value)
         if removeallentities and value != None:
             return removeAllEntities(value)
         else:
             return value
 
-    def getAllMetadata(self):
+    def getAllMetadata(self, removeallentities=False):
         '''
         All single value *and* list value metadata as strings.
         '''
         allmetadata = {}
         for k in self.metadata.keys():
-            allmetadata[k] = self.getMetadata(k)
+            allmetadata[k] = self.getMetadata(k, removeallentities)
         for l in self.listables.keys():
-            allmetadata[l] = self.getMetadata(l)
+            allmetadata[l] = self.getMetadata(l, removeallentities)
 
         return allmetadata
         
@@ -81,10 +138,14 @@ class Story:
     def getList(self,listname):
         if not self.listables.has_key(listname):
             return []
-        return self.listables[listname]
+        return filter( lambda x : x!=None and x!='' ,
+                       map(self.doReplacments,self.listables[listname]) )
 
     def getLists(self):
-        return self.listables
+        lsts = {}
+        for ln in self.listables.keys():
+            lsts[ln] = self.getList(ln)
+        return lsts
     
     def addChapter(self, title, html):
         self.chapters.append( (title,html) )
@@ -96,6 +157,11 @@ class Story:
     def __str__(self):
         return "Metadata: " +str(self.metadata) + "\nListables: " +str(self.listables) #+ "\nChapters: "+str(self.chapters)
 
+    def setReplace(self,replace):
+        for line in replace.splitlines():
+            if "=>" in line:
+                self.replacements.append(map( lambda x: x.strip(), line.split("=>") ))
+    
 def commaGroups(s):
     groups = []
     while s and s[-1].isdigit():

fanficdownloader/translit.py

@@ -0,0 +1,57 @@
+#-*-coding:utf-8-*-
+# Code taken from http://python.su/forum/viewtopic.php?pid=66946
+import unicodedata
+def is_syllable(letter):
+    syllables = ("A", "E", "I", "O", "U", "a", "e", "i", "o", "u")
+    if letter in syllables:
+        return True
+    return False
+def is_consonant(letter):
+    return not is_syllable(letter)
+def romanize(letter):
+    try:
+        str(letter)
+    except UnicodeEncodeError:
+        pass
+    else:
+        return str(letter)
+    unid = unicodedata.name(letter)
+    exceptions = {"NUMERO SIGN": "No", "LEFT-POINTING DOUBLE ANGLE QUOTATION MARK": "\"", "RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK": "\"", "DASH": "-"}
+    for name_contains in exceptions:
+        if unid.find(name_contains)!=-1:
+            return exceptions[name_contains]
+    assert(unid.startswith("CYRILLIC"))# Not ready to romanize anything but cyrillics
+    transformation_pairs = {"CYRILLIC CAPITAL LETTER ": str.capitalize, "CYRILLIC SMALL LETTER ": str.lower}
+    func = str.lower
+    for name_contains in transformation_pairs:
+        if unid.find(name_contains)!=-1:
+            func = transformation_pairs[name_contains]
+            unid = unid.replace(name_contains, "")
+    cyrillic_exceptions = {"YERU": "y", "SHORT I": "y", "HARD SIGN": "\'", "SOFT SIGN": "\'", "BYELORUSSIAN-UKRAINIAN I": "i", "GHE WITH UPTURN": "g", "UKRAINIAN IE": "ie", "YU": "yu", "YA": "ya"}
+    for name_contains in cyrillic_exceptions:
+        if unid.find(name_contains)!=-1:
+            return cyrillic_exceptions[name_contains]
+    if all(map(is_syllable, unid)):
+        return func(unid)
+    else:
+        return func(filter(is_consonant, unid))
+def translit(text):
+    output = ""
+    for letter in text:
+        output += romanize(letter)
+    return output
+#def main():
+    #text = u"русск.: Любя, съешь щипцы, — вздохнёт мэр, — кайф жгуч."
+    #print translit(text)
+    #text = u"укр.: Гей, хлопці, не вспію - на ґанку ваша файна їжа знищується бурундучком."
+    #print translit(text)
+    #text = u"болг.: Ах, чудна българска земьо, полюшквай цъфтящи жита."
+    #print translit(text)
+    #text = u"серб.: Неуредне ноћне даме досађивале су Џеку К."
+    #print translit(text)
+    #russk.: Lyubya, s'iesh' shchiptsy, - vzdohniot mer, - kayf zhghuch.
+    #ukr.: Ghiey, hloptsi, nie vspiyu - na ganku vasha fayna yzha znishchuiet'sya burunduchkom.
+    #bolgh.: Ah, chudna b'lgharska ziem'o, polyushkvay ts'ftyashchi zhita.
+    #sierb.: Nieuriednie notshnie damie dosadjivalie su Dzhieku K.
+if __name__=="__main__":
+    main()

fanficdownloader/writers/base_writer.py

@@ -46,10 +46,15 @@ class BaseStoryWriter(Configurable):
         
         self.adapter = adapter
         self.story = adapter.getStoryMetadataOnly() # only cache the metadata initially.
+        
+        self.story.setReplace(self.getConfig('replace_metadata'))
+        
         self.validEntries = [
             'category',
             'genre',
+            'language',
             'characters',
+            'series',
             'status',
             'datePublished',
             'dateUpdated',
@@ -76,7 +81,9 @@ class BaseStoryWriter(Configurable):
         self.titleLabels = {
             'category':'Category',
             'genre':'Genre',
+            'language':'Language',
             'status':'Status',
+            'series':'Series',
             'characters':'Characters',
             'datePublished':'Published',
             'dateUpdated':'Updated',
@@ -97,7 +104,7 @@ class BaseStoryWriter(Configurable):
             'formatname':'File Format',
             'formatext':'File Extension',
             'siteabbrev':'Site Abbrev',
-            'version':'FFD Version'
+            'version':'FFDL Version'
             }
         self.story.setMetadata('formatname',self.getFormatName())
         self.story.setMetadata('formatext',self.getFormatExt())
@@ -192,6 +199,12 @@ class BaseStoryWriter(Configurable):
         if outfilename == None:
             outfilename=self.getOutputFileName()
 
+        # minor cheat, tucking css into metadata.
+        if self.getConfig("output_css"):
+            self.story.metadata["output_css"] = self.getConfig("output_css")
+        else:
+            self.story.metadata["output_css"] = ''
+            
         if not outstream:
             close=True
             logging.debug("Save directly to file: %s" % outfilename)

fanficdownloader/writers/writer_epub.py

@@ -41,32 +41,7 @@ class EpubWriter(BaseStoryWriter):
     def __init__(self, config, story):
         BaseStoryWriter.__init__(self, config, story)
 
-        self.EPUB_CSS = string.Template('''
-body { margin: 2%;
-       text-align: justify;
-       background-color: #${background_color}; }
-pre { font-size: x-small; }
-sml { font-size: small; }
-h1 { text-align: center; }
-h2 { text-align: center; }
-h3 { text-align: center; }
-h4 { text-align: center; }
-h5 { text-align: center; }
-h6 { text-align: center; }
-.CI {
-    text-align:center;
-    margin-top:0px;
-    margin-bottom:0px;
-    padding:0px;
-    }
-.center   {text-align: center;}
-.cover    {text-align: center;}
-.full     {width: 100%; }
-.quarter  {width: 25%; }
-.smcap    {font-variant: small-caps;}
-.u        {text-decoration: underline;}
-.bold     {font-weight: bold;}
-''')
+        self.EPUB_CSS = string.Template('''${output_css}''')
         
         self.EPUB_TITLE_PAGE_START = string.Template('''<?xml version="1.0" encoding="UTF-8"?>
 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
@@ -228,7 +203,10 @@ h6 { text-align: center; }
 
         metadata.appendChild(newTag(contentdom,"dc:contributor",text="fanficdownloader [http://fanficdownloader.googlecode.com]",attrs={"opf:role":"bkp"}))
         metadata.appendChild(newTag(contentdom,"dc:rights",text=""))
-        metadata.appendChild(newTag(contentdom,"dc:language",text="en"))
+        if self.story.getMetadata('langcode') != None:
+            metadata.appendChild(newTag(contentdom,"dc:language",text=self.story.getMetadata('langcode')))
+        else:
+            metadata.appendChild(newTag(contentdom,"dc:language",text='en'))
 
         #  published, created, updated, calibre
         #  Leave calling self.story.getMetadataRaw directly in case date format changes.
@@ -361,7 +339,7 @@ h6 { text-align: center; }
         del tocncxdom
 
         # write stylesheet.css file.
-        outputepub.writestr("OEBPS/stylesheet.css",self.EPUB_CSS.substitute({"background_color":self.getConfig("background_color")})) 
+        outputepub.writestr("OEBPS/stylesheet.css",self.EPUB_CSS.substitute(self.story.metadata)) 
 
         # write title page.
         if self.getConfig("titlepage_use_table"):
@@ -424,4 +402,4 @@ def newTag(dom,name,attrs=None,text=None):
     if( text is not None ):
         tag.appendChild(dom.createTextNode(text))
     return tag
-    
+

fanficdownloader/writers/writer_html.py

@@ -39,20 +39,7 @@ class HTMLWriter(BaseStoryWriter):
 <head>
 <title>${title} by ${author}</title>
 <style type="text/css">
-body { background-color: #${background_color}; }
-.CI {
-    text-align:center;
-    margin-top:0px;
-    margin-bottom:0px;
-    padding:0px;
-    }
-.center   {text-align: center;}
-.cover    {text-align: center;}
-.full     {width: 100%; }
-.quarter  {width: 25%; }
-.smcap    {font-variant: small-caps;}
-.u        {text-decoration: underline;}
-.bold     {font-weight: bold;}
+${output_css}
 </style>
 </head>
 <body>
@@ -95,9 +82,6 @@ body { background-color: #${background_color}; }
 
     def writeStoryImpl(self, out):
 
-        # minor cheat, tucking bg into metadata.
-        if self.getConfig("background_color"):
-            self.story.metadata["background_color"] = self.getConfig("background_color")
         self._write(out,self.HTML_FILE_START.substitute(self.story.metadata))
 
         self.writeTitlePage(out,

fanficdownloader/writers/writer_mobi.py

@@ -41,7 +41,6 @@ class MobiWriter(BaseStoryWriter):
 <html xmlns="http://www.w3.org/1999/xhtml">
 <head>
 <title>${title} by ${author}</title>
-<link href="stylesheet.css" type="text/css" charset="UTF-8" rel="stylesheet"/>
 </head>
 <body>
 <h3><a href="${storyUrl}">${title}</a> by <a href="${authorUrl}">${author}</a></h3>
@@ -64,7 +63,6 @@ class MobiWriter(BaseStoryWriter):
 <html xmlns="http://www.w3.org/1999/xhtml">
 <head>
 <title>${title} by ${author}</title>
-<link href="stylesheet.css" type="text/css" charset="UTF-8" rel="stylesheet"/>
 </head>
 <body>
 <h3><a href="${storyUrl}">${title}</a> by <a href="${authorUrl}">${author}</a></h3>
@@ -91,7 +89,6 @@ class MobiWriter(BaseStoryWriter):
 <html xmlns="http://www.w3.org/1999/xhtml">
 <head>
 <title>${title} by ${author}</title>
-<link href="stylesheet.css" type="text/css" charset="UTF-8" rel="stylesheet"/>
 </head>
 <body>
 <div>
@@ -113,7 +110,6 @@ class MobiWriter(BaseStoryWriter):
 <html xmlns="http://www.w3.org/1999/xhtml">
 <head>
 <title>${chapter}</title>
-<link href="stylesheet.css" type="text/css" charset="UTF-8" rel="stylesheet"/>
 </head>
 <body>
 <h3>${chapter}</h3>

index-ajax.html

@@ -4,7 +4,7 @@
 		<link href="css/index.css" rel="stylesheet" type="text/css">
 		<link type="text/css" href="http://jqueryui.com/latest/themes/base/ui.all.css" rel="stylesheet" />
 	 
-		<title>Fanfiction Downloader (fanfiction.net, fictionalley, ficwad to epub and HTML)</title>
+		<title>FanFictionDownLoader (fanfiction.net, fictionalley, ficwad to epub and HTML)</title>
 		<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
 		<script src="/js/jquery-1.3.2.js"></script>
 		<script src="/js/fdownloader.js"></script>
@@ -16,7 +16,7 @@
 	<body>
 		<div id='main'>
 			<h1>
-				<a href="/" style="text-decoration: none; color: black;">FanFiction Downloader</a>
+				<a href="/" style="text-decoration: none; color: black;">FanFictionDownLoader</a>
 			</h1>
 				
 <!--			<form action="/fdown" method="post"> -->
@@ -91,8 +91,8 @@
 					<img src="http://code.google.com/appengine/images/appengine-silver-120x30.gif"
 					alt="Powered by Google App Engine" />
 					<br/><br/>
-					FanfictionLoader is a web front-end to <A href="http://code.google.com/p/fanficdownloader/">fanficdownloader</a><br/>
-					Copyright &copy; <a href="http://twitter.com/sigizmund">Roman Kirillov</a>
+	This is a web front-end to <A href="http://code.google.com/p/fanficdownloader/">FanFictionDownLoader</a><br/>
+	Copyright &copy; Fanficdownloader team
 				</div>
 <!--			</form> -->
 		</div>

index.html

@@ -2,7 +2,7 @@
 <html>
   <head>
     <link href="/css/index.css" rel="stylesheet" type="text/css">
-    <title>Fanfiction Downloader - read fanfiction from twilighted.net, fanfiction.net, fictionpress.com, fictionalley.org, ficwad.com, potionsandsnitches.net, harrypotterfanfiction.com, mediaminer.org on Kindle, Nook, Sony Reader, iPad, iPhone, Android, Aldiko, Stanza</title>
+    <title>FanFictionDownLoader - read fanfiction from twilighted.net, fanfiction.net, fictionpress.com, fictionalley.org, ficwad.com, potionsandsnitches.net, harrypotterfanfiction.com, mediaminer.org on Kindle, Nook, Sony Reader, iPad, iPhone, Android, Aldiko, Stanza</title>
     <meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
     <meta name="google-site-verification" content="kCFc-G4bka_pJN6Rv8CapPBcwmq0hbAUZPkKWqRsAYU" />
     <script type="text/javascript">
@@ -26,7 +26,7 @@
   <body>
     <div id='main'>
       <h1>
-	<a href="/" style="text-decoration: none; color: black;">FanFiction Downloader</a> <g:plusone size="medium"></g:plusone>
+	<a href="/" style="text-decoration: none; color: black;">FanFictionDownLoader</a> <g:plusone size="medium"></g:plusone>
       </h1>
 
       <div style="text-align: center">
@@ -50,58 +50,34 @@
       <form action="/fdown" method="post">
 	<div id='urlbox'>
 	  <div id='greeting'>
-	    <p>Hi, {{ nickname }}! This is a fan fiction downloader, which makes reading stories from various websites
+	    <p>Hi, {{ nickname }}! This is FanFictionDownLoader, which makes reading stories from various websites
 	      much easier. </p>
 	  </div>
 	  <!-- put announcements here, h3 is a good title size. -->
-	  <h3>This is the Official Multithreading Version</h3>
+	  <h3>New Russian Language Site ficbook.net</h3>
 	  <p>
-	    This version of the application uses Python 2.7 and
-	    multithreading to try and reduce our usage.  Google
-	    considers Python 2.7 Experimental still, so there may be issues.
+	    Thanks to Ida Leter's hard work, we now support <a href="http://ficbook.net">ficbook.net</a>, a Russian language fanfiction site.
+	  </p>
+	  <h3>Support for Language, Custom CSS and Replacement of Metadata</h3>
+	  <p>
+	    There's now a 'Language' metadata field that can be filled, if the site supports different languages.  Currently, it's only used
+	    with fanfiction.net and ficbook.net.
 	  </p>
 	  <p>
-	    <b>FanFictionDownLoader calibre Plugin</b>
-	    <br /><br />
-	    
-	    There's now a version of this downloader that runs
-	    entirely inside the
-	    popular <a href="http://calibre-ebook.com/">calibre</a>
-	    ebook management package as a plugin.
-	    
-	    <br /><br />
-	    
-	    Once you have calibre installed and running, inside
-	    calibre, you can go to 'Get plugins to enhance calibre' or
-	    'Get new plugins' and
-	    install <a href="http://www.mobileread.com/forums/showthread.php?t=163261">FanFictionDownLoader</a>.
-	    
+	    The CSS included in the HTML and EPUB output formats is now a customizable parameter.
 	  </p>
 	  <p>
-	    <b>Wider support for 'Characters'</b>
-	    <br /><br />
-	    We now collect 'Character' lists for most of the supported sites.  
-	    <br /><br />
-	    There's huge variation in how different sites choose to define characters--well beyond our ability to standardize.
-	    <br /><br />
-	    So if you don't like and don't want to see characters in your title pages or tags, you can turn them off in your configuration with:
-	    <pre>
-[defaults]
-# note that characters is removed.  This removes it from your title page.
-titlepage_entries: category,genre,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,description
-
-# note that characters is removed.  This removes it from your tags.
-include_subject_tags: extratags, genre, category, status
-	    </pre>
-	    If you like them for some sites, but not others, just copy the titlepage_entries and include_subject_tags to sections for different sites and edit to taste.
+	    There's now a customizable parameter to include a list of regular expressions to replace metadata as you see fit.
+	  </p>
+	  <p>
+	    Examples of how to use both new features can be found in the
+	    <a href="http://www.mobileread.com/forums/showthread.php?p=1962034#post1962034">plugin forum</a>.
 	  </p>
 	  <p>
 	    If you have any problems with this application, please
 	    report them in
-	    the <a href="http://groups.google.com/group/fanfic-downloader">Fanfiction
-	      Downloader Google Group</a>.  The
-	    <a href="http://4-2-0.fanfictiondownloader.appspot.com">Previous
-	      Version</a> is also available for you to use if necessary.
+	    the <a href="http://groups.google.com/group/fanfic-downloader">FanFictionDownLoader Google Group</a>.  The
+	    <a href="http://4-3-1.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
 	  </p>
 	  <div id='error'>
 	    {{ error_message }}
@@ -137,14 +113,33 @@ include_subject_tags: extratags, genre, category, status
       <div id='urlbox'>
 	<div id='greeting'>
 	  <p>
-	    This is a fan fiction downloader, which makes reading stories from various websites much easier. Before you
-	    can start downloading fanfics, you need to login, so downloader can remember your fanfics and store them.
+	    This is a FanFictionDownLoader, which makes reading stories from various websites much easier. Before you
+	    can start downloading fanfics, you need to login, so FanFictionDownLoader can remember your fanfics and store them.
 	  </p>
 	  <p><a href="{{ login_url }}">Login using Google account</a></p>
 	</div>
       </div>
       {% endif %}
       
+      <div id='typebox'>
+	  <p>
+	    <b>FanFictionDownLoader calibre Plugin</b>
+	    <br /><br />
+	    
+	    There's now a version of this downloader that runs
+	    entirely inside the
+	    popular <a href="http://calibre-ebook.com/">calibre</a>
+	    ebook management package as a plugin.
+	    
+	    <br /><br />
+	    
+	    Once you have calibre installed and running, inside
+	    calibre, you can go to 'Get plugins to enhance calibre' or
+	    'Get new plugins' and
+	    install <a href="http://www.mobileread.com/forums/showthread.php?t=163261">FanFictionDownLoader</a>.
+	    
+	  </p>
+      </div>
       <div id='helpbox'>
 	<dl>
 	  <dt>fictionalley.org</dt>
@@ -245,10 +240,23 @@ include_subject_tags: extratags, genre, category, status
 	    Use the URL of the story's chapter list, such as
 	    <br /><a href="http://www.siye.co.uk/siye/viewstory.php?sid=123">http://www.siye.co.uk/siye/viewstory.php?sid=123</a>.
 	  </dd>
+	  <dt>archiveofourown.org</dt>
+	  <dd>
+	    Use the URL of the story, or one of it's chapters, such as
+	    <br /><a href="http://archiveofourown.org/works/76366">http://archiveofourown.org/works/76366</a>.
+	    <br /><a href="http://archiveofourown.org/works/76366/chapters/101584">http://archiveofourown.org/works/76366/chapters/101584</a>.
+	  </dd>
 	</dl>	
-
-	
-	A few additional things to know, which will make your life substantially easier:
+	  <dt>ficbook.net(Russian)</dt>
+	  <dd>
+	    Use the URL of the story, or one of it's chapters, such as
+	    <br /><a href="http://ficbook.net/readfic/93626">http://ficbook.net/readfic/93626</a>.
+	    <br /><a href="http://ficbook.net/readfic/93626/246417#part_content">http://ficbook.net/readfic/93626/246417#part_content</a>.
+	  </dd>
+	</dl>
+	<p>
+	  A few additional things to know, which will make your life substantially easier:
+	</p>
 	<ol>
 	  <li>
 	    First thing to know: I do not use your Google login and password. In fact, all I know about it is your ID &ndash; password
@@ -281,8 +289,8 @@ include_subject_tags: extratags, genre, category, status
 	<img src="http://code.google.com/appengine/images/appengine-silver-120x30.gif"
 	     alt="Powered by Google App Engine" />
 	<br/><br/>
-	FanfictionLoader is a web front-end to <A href="http://code.google.com/p/fanficdownloader/">fanficdownloader</a><br/>
-	Copyright &copy; Fanficdownloader team
+	This is a web front-end to <A href="http://code.google.com/p/fanficdownloader/">FanFictionDownLoader</a><br/>
+	Copyright &copy; FanFictionDownLoader team
       </div>
 
       <div style="margin-top: 1em; text-align: center'">

login.html

@@ -2,7 +2,7 @@
 <html>
   <head>
     <link href="/css/index.css" rel="stylesheet" type="text/css">
-    <title>Login Needed Fanfiction Downloader</title>
+    <title>Login Needed FanFictionDownLoader</title>
     <meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
     <meta name="google-site-verification" content="kCFc-G4bka_pJN6Rv8CapPBcwmq0hbAUZPkKWqRsAYU" />
     <script type="text/javascript">
@@ -22,7 +22,7 @@
   <body>
     <div id='main'>
       <h1>
-	<a href="/" style="text-decoration: none; color: black;">FanFiction Downloader</a>
+	<a href="/" style="text-decoration: none; color: black;">FanFictionDownLoader</a>
       </h1>
 
       <div style="text-align: center">
@@ -88,8 +88,8 @@
 	<img src="http://code.google.com/appengine/images/appengine-silver-120x30.gif"
 	     alt="Powered by Google App Engine" />
 	<br/><br/>
-	FanfictionLoader is a web front-end to <A href="http://code.google.com/p/fanficdownloader/">fanficdownloader</a><br/>
-	Copyright &copy; Fanficdownloader team
+	This is a web front-end to <A href="http://code.google.com/p/fanficdownloader/">FanFictionDownLoader</a><br/>
+	Copyright &copy; FanFictionDownLoader team
       </div>
 
       <div style="margin-top: 1em; text-align: center'">

plugin-defaults.ini

@@ -41,7 +41,9 @@ formatext_label:File Extension
 ## Sometimes there are multiple categories and/or genres.
 category_label:Category
 genre_label:Genre
+language_label:Language
 characters_label:Characters
+series_label:Series
 ## Completed/In-Progress
 status_label:Status
 ## Dates story first published, last updated, and downloaded(last with time).
@@ -71,7 +73,14 @@ version_label:FFDL Version
 ## items to include in the title page
 ## Empty entries will *not* appear, even if in the list.
 ## All current formats already include title and author.
-titlepage_entries: category,genre,characters,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,description
+titlepage_entries: series,category,genre,language,characters,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,description
+
+## Try to collect series name and number of this story in series.
+## Some sites (ab)use 'series' for reading lists and personal
+## collections.  This lets us turn it on and off by site without
+## keeping a lengthy titlepage_entries per site and prevents it
+## updating in the plugin.
+collect_series: true
 
 ## include title page as first page.
 include_titlepage: true
@@ -103,12 +112,57 @@ extratags: FanFiction
 ## epub by many readers).  Must be hex code, # will be added.
 background_color: ffffff
 
+## Use regular expressions to find and replace (or remove) metadata.
+## For example, you could change Sci-Fi=>SF, remove *-Centered tags,
+## etc.  See http://docs.python.org/library/re.html (look for re.sub)
+## for regexp details.
+## Make sure to keep at least one space at the start of each line and
+## to escape % to %%, if used.
+#replace_metadata:
+# Sci-Fi=>SF
+# Puella Magi Madoka Magica.* => Madoka
+# Comedy=>Humor
+# Crossover: (.*)=>\1
+# (.*)Great(.*)=>\1Moderate\2
+# .*-Centered=>
+
 ## Each output format has a section that overrides [defaults]
 [html]
 
+## output background color--only used by html and epub (and ignored in
+## epub by many readers).  Included below in output_css--will be
+## ignored if not in output_css.
+background_color: ffffff
+
+## Allow customization of CSS.  Make sure to keep at least one space
+## at the start of each line and to escape % to %%.  Also need
+## background_color to be in the same section, if included in CSS.
+output_css:
+ body { background-color: #%(background_color)s; }
+ .CI {
+     text-align:center;
+     margin-top:0px;
+     margin-bottom:0px;
+     padding:0px;
+     }
+ .center   {text-align: center;}
+ .cover    {text-align: center;}
+ .full     {width: 100%%; }
+ .quarter  {width: 25%%; }
+ .smcap    {font-variant: small-caps;}
+ .u        {text-decoration: underline;}
+ .bold     {font-weight: bold;}
+
 [txt]
 ## Add URLs since there aren't links.
-titlepage_entries: category,genre,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,storyUrl, authorUrl, description
+titlepage_entries: series,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,storyUrl, authorUrl, description
+
+## use \r\n for line endings, the windows convention.  text output only.
+windows_eol: true
+
+[txt]
+## Add URLs since there aren't links.
+titlepage_entries: series,category,genre,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,storyUrl, authorUrl, description
 
 ## use \r\n for line endings, the windows convention.  text output only.
 windows_eol: true
@@ -125,6 +179,40 @@ titlepage_use_table: false
 ## When using tables, make these span both columns.
 wide_titlepage_entries: description, storyUrl, author URL
 
+## output background color--only used by html and epub (and ignored in
+## epub by many readers).  Included below in output_css--will be
+## ignored if not in output_css.
+background_color: ffffff
+
+## Allow customization of CSS.  Make sure to keep at least one space
+## at the start of each line and to escape % to %%.  Also need
+## background_color to be in the same section, if included in CSS.
+output_css: 
+ body { background-color: #%(background_color)s;
+        text-align: justify;
+        margin: 2%%; }
+ pre { font-size: x-small; }
+ sml { font-size: small; }
+ h1 { text-align: center; }
+ h2 { text-align: center; }
+ h3 { text-align: center; }
+ h4 { text-align: center; }
+ h5 { text-align: center; }
+ h6 { text-align: center; }
+ .CI {
+     text-align:center;
+     margin-top:0px;
+     margin-bottom:0px;
+     padding:0px;
+     }
+ .center   {text-align: center;}
+ .cover    {text-align: center;}
+ .full     {width: 100%%; }
+ .quarter  {width: 25%%; }
+ .smcap    {font-variant: small-caps;}
+ .u        {text-decoration: underline;}
+ .bold     {font-weight: bold;}
+
 [mobi]
 ## mobi TOC cannot be turned off right now.
 #include_tocpage: true
@@ -168,6 +256,9 @@ extratags:
 #username:YourName
 #password:yourpassword
 
+## twilighted.net (ab)uses series as personal reading lists.
+collect_series: false
+
 [www.twiwrite.net]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -176,6 +267,9 @@ extratags:
 #username:YourName
 #password:yourpassword
 
+## twiwrite.net (ab)uses series as personal reading lists.
+collect_series: false
+
 [www.whofic.com]
 
 [www.mediaminer.org]
@@ -193,6 +287,9 @@ extratags:
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+## thewriterscoffeeshop.com (ab)uses series as personal reading lists.
+collect_series: false
+
 [www.ficwad.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In

plugin-example.ini

@@ -7,11 +7,23 @@
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+## Try to collect series name and number of this story in series.
+## Some sites (ab)use 'series' for reading lists and personal
+## collections.  This lets us turn it on and off by site without
+## keeping a lengthy titlepage_entries per site and prevents it
+## updating in the plugin.
+## Turn off in [defaults] or [overrides] to prevent all sites from
+## updating series column.
+## default is true
+#collect_series: false
+
 ## Most common, I expect will be using this to save username/passwords
 ## for different sites.
 [www.twilighted.net]
 #username:YourPenname
 #password:YourPassword
+## default is false
+#collect_series: true
 
 [www.ficwad.com]
 #username:YourUsername
@@ -20,6 +32,8 @@
 [www.twiwrite.net]
 #username:YourName
 #password:yourpassword
+## default is false
+#collect_series: true
 
 [www.adastrafanfic.com]
 ## Some sites do not require a login, but do require the user to
@@ -30,6 +44,8 @@
 #username:YourName
 #password:yourpassword
 #is_adult:true
+## default is false
+#collect_series: true
 
 [www.fictionalley.org]
 #is_adult:true
@@ -53,3 +69,6 @@
 ## This section will override anything in the system defaults or other
 ## sections here.
 [overrides]
+## default varies by site.  Set true here to force all sites to
+## collect series.
+#collect_series: true

recent.html

@@ -2,7 +2,7 @@
 <html>
   <head>
     <link href="/css/index.css" rel="stylesheet" type="text/css">
-    <title>Fanfiction Downloader (fanfiction.net, fanficauthors, fictionalley, ficwad to epub and HTML)</title>
+    <title>FanFictionDownLoader (fanfiction.net, fanficauthors, fictionalley, ficwad to epub and HTML)</title>
     <meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
     <script type="text/javascript">
 
@@ -21,7 +21,7 @@
   <body>
     <div id='main'>
       <h1>
-	<a href="/" style="text-decoration: none; color: black;">FanFiction Downloader</a>
+	<a href="/" style="text-decoration: none; color: black;">FanFictionDownLoader</a>
       </h1>
       
       <script type="text/javascript"><!--
@@ -46,26 +46,6 @@
 	</div>
       </div>
 
-      <div id='typebox'>
-	  <p>
-	    <b>FanFictionDownLoader calibre Plugin</b>
-	    <br /><br />
-	    
-	    There's now a version of this downloader that runs
-	    entirely inside the
-	    popular <a href="http://calibre-ebook.com/">calibre</a>
-	    ebook management package as a plugin.
-	    
-	    <br /><br />
-	    
-	    Once you have calibre installed and running, inside
-	    calibre, you can go to 'Get plugins to enhance calibre' or
-	    'Get new plugins' and
-	    install <a href="http://www.mobileread.com/forums/showthread.php?t=163261">FanFictionDownLoader</a>.
-	    
-	  </p>
-      </div>
-      
       <div id='helpbox'>
 	{% for fic in fics %}
 	<p>

status.html

@@ -2,7 +2,7 @@
 <html>
   <head>
     <link href="/css/index.css" rel="stylesheet" type="text/css">
-    <title>{% if fic.completed %} Finished {% else %} {% if fic.failure %} Failed {% else %} Working... {% endif %} {% endif %} - Fanfiction Downloader</title>
+    <title>{% if fic.completed %} Finished {% else %} {% if fic.failure %} Failed {% else %} Working... {% endif %} {% endif %} - FanFictionDownLoader</title>
     <meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
     <meta name="google-site-verification" content="kCFc-G4bka_pJN6Rv8CapPBcwmq0hbAUZPkKWqRsAYU" />
     {% if not fic.completed and not fic.failure %}
@@ -25,7 +25,7 @@
   <body>
     <div id='main'>
       <h1>
-	<a href="/" style="text-decoration: none; color: black;">FanFiction Downloader</a>
+	<a href="/" style="text-decoration: none; color: black;">FanFictionDownLoader</a>
       </h1>
       <div style="text-align: center">
         <script type="text/javascript"><!--
@@ -68,30 +68,11 @@
 	  <p>See your personal list of <a href="/recent">previously downloaded fanfics</a>.</p>
       </div>
 
-      <div id='typebox'>
-	  <p>
-	    <b>FanFictionDownLoader calibre Plugin</b>
-	    <br /><br />
-	    
-	    There's now a version of this downloader that runs
-	    entirely inside the
-	    popular <a href="http://calibre-ebook.com/">calibre</a>
-	    ebook management package as a plugin.
-	    
-	    <br /><br />
-	    
-	    Once you have calibre installed and running, inside
-	    calibre, you can go to 'Get plugins to enhance calibre' or
-	    'Get new plugins' and
-	    install <a href="http://www.mobileread.com/forums/showthread.php?t=163261">FanFictionDownLoader</a>.
-	    
-	  </p>
-      </div>
       <div style='text-align: center'>
 	<img src="http://code.google.com/appengine/images/appengine-silver-120x30.gif"
 	     alt="Powered by Google App Engine" />
 	<br/><br/>
-	FanfictionLoader is a web front-end to <A href="http://code.google.com/p/fanficdownloader/">fanficdownloader</a><br/>
+	This is a web front-end to <A href="http://code.google.com/p/fanficdownloader/">FanFictionDownLoader</a><br/>
 	Copyright &copy; Fanficdownloader team
       </div>