Bump calibre version.

Bump web service number.

app.yaml

@@ -1,6 +1,6 @@
 # ffd-retief-hrd fanfictiondownloader
 application: fanfictiondownloader
-version: 4-4-12
+version: 4-4-18
 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, 5, 24)
+    version             = (1, 5, 40)
     minimum_calibre_version = (0, 8, 30)
 
     #: This field defines the GUI plugin class that contains all the code

calibre-plugin/config.py

@@ -39,6 +39,7 @@ all_prefs.defaults['personal.ini'] = get_resources('plugin-example.ini')
 
 all_prefs.defaults['updatemeta'] = True
 all_prefs.defaults['updatecover'] = False
+all_prefs.defaults['updateepubcover'] = False
 all_prefs.defaults['keeptags'] = False
 all_prefs.defaults['urlsfromclip'] = True
 all_prefs.defaults['updatedefault'] = True
@@ -60,6 +61,7 @@ all_prefs.defaults['gcnewonly'] = False
 all_prefs.defaults['gc_site_settings'] = {}
 all_prefs.defaults['allow_gc_from_ini'] = True
 
+all_prefs.defaults['errorcol'] = ''
 all_prefs.defaults['custom_cols'] = {}
 
 # The list of settings to copy from all_prefs or the previous library
@@ -67,6 +69,7 @@ all_prefs.defaults['custom_cols'] = {}
 copylist = ['personal.ini',
             'updatemeta',
             'updatecover',
+            'updateepubcover',
             'keeptags',
             'urlsfromclip',
             'updatedefault',
@@ -162,7 +165,7 @@ class ConfigWidget(QWidget):
         if 'Generate Cover' not in plugin_action.gui.iactions:
             self.generatecover_tab.setEnabled(False)
 
-        self.columns_tab = ColumnsTab(self, plugin_action)
+        self.columns_tab = CustomColumnsTab(self, plugin_action)
         tab_widget.addTab(self.columns_tab, 'Custom Columns')
 
         self.other_tab = OtherTab(self, plugin_action)
@@ -176,6 +179,7 @@ class ConfigWidget(QWidget):
         prefs['collision'] = unicode(self.basic_tab.collision.currentText())
         prefs['updatemeta'] = self.basic_tab.updatemeta.isChecked()
         prefs['updatecover'] = self.basic_tab.updatecover.isChecked()
+        prefs['updateepubcover'] = self.basic_tab.updateepubcover.isChecked()
         prefs['keeptags'] = self.basic_tab.keeptags.isChecked()
         prefs['urlsfromclip'] = self.basic_tab.urlsfromclip.isChecked()
         prefs['updatedefault'] = self.basic_tab.updatedefault.isChecked()
@@ -215,6 +219,11 @@ class ConfigWidget(QWidget):
         prefs['allow_gc_from_ini'] = self.generatecover_tab.allow_gc_from_ini.isChecked()
 
         # Custom Columns tab
+
+        # error column
+        prefs['errorcol'] = unicode(self.columns_tab.errorcol.itemData(self.columns_tab.errorcol.currentIndex()).toString())
+
+        # cust cols
         colsmap = {}
         for (col,combo) in self.columns_tab.custcol_dropdowns.iteritems():
             val = unicode(combo.itemData(combo.currentIndex()).toString())
@@ -245,9 +254,11 @@ class BasicTab(QWidget):
         label.setWordWrap(True)
         self.l.addWidget(label)
         self.l.addSpacing(5)
-        
+
+        tooltip = "On each download, FFDL offers an option to select the output format. <br />This sets what that option will default to."
         horz = QHBoxLayout()
         label = QLabel('Default Output &Format:')
+        label.setToolTip(tooltip)
         horz.addWidget(label)
         self.fileform = QComboBox(self)
         self.fileform.addItem('epub')
@@ -255,15 +266,16 @@ class BasicTab(QWidget):
         self.fileform.addItem('html')
         self.fileform.addItem('txt')
         self.fileform.setCurrentIndex(self.fileform.findText(prefs['fileform']))
-        self.fileform.setToolTip('Choose output format to create.  May set default from plugin configuration.')
+        self.fileform.setToolTip(tooltip)
         self.fileform.activated.connect(self.set_collisions)
         label.setBuddy(self.fileform)
         horz.addWidget(self.fileform)
         self.l.addLayout(horz)
 
+        tooltip = "On each download, FFDL offers an option of what happens if that story already exists. <br />This sets what that option will default to."
         horz = QHBoxLayout()
         label = QLabel('Default If Story Already Exists?')
-        label.setToolTip("What to do if there's already an existing story with the same title and author.")
+        label.setToolTip(tooltip)
         horz.addWidget(label)
         self.collision = QComboBox(self)
         # add collision options
@@ -271,18 +283,23 @@ class BasicTab(QWidget):
         i = self.collision.findText(prefs['collision'])
         if i > -1:
             self.collision.setCurrentIndex(i)
-        # self.collision.setToolTip('Overwrite will replace the existing story.  Add New will create a new story with the same title and author.')
+        self.collision.setToolTip(tooltip)
         label.setBuddy(self.collision)
         horz.addWidget(self.collision)
         self.l.addLayout(horz)
 
         self.updatemeta = QCheckBox('Default Update Calibre &Metadata?',self)
-        self.updatemeta.setToolTip('Update title, author, URL, tags, custom columns, etc for story in Calibre from web site.')
+        self.updatemeta.setToolTip("On each download, FFDL offers an option to update Calibre's metadata (title, author, URL, tags, custom columns, etc) from the web site. <br />This sets whether that will default to on or off.")
         self.updatemeta.setChecked(prefs['updatemeta'])
         self.l.addWidget(self.updatemeta)
 
-        self.updatecover = QCheckBox('Update Cover when Updating Metadata?',self)
-        self.updatecover.setToolTip("Update cover image from EPUB when metadata is updated.  (EPUB only.)\nDoesn't go looking for new images on 'Update Calibre Metadata Only'.")
+        self.updateepubcover = QCheckBox('Default Update EPUB Cover when Updating EPUB?',self)
+        self.updateepubcover.setToolTip("On each download, FFDL offers an option to update the book cover image <i>inside</i> the EPUB from the web site when the EPUB is updated.<br />This sets whether that will default to on or off.")
+        self.updateepubcover.setChecked(prefs['updateepubcover'])
+        self.l.addWidget(self.updateepubcover)
+
+        self.updatecover = QCheckBox('Update Calibre Cover when Updating Metadata?',self)
+        self.updatecover.setToolTip("Update calibre book cover image from EPUB when metadata is updated.  (EPUB only.)\nDoesn't go looking for new images on 'Update Calibre Metadata Only'.")
         self.updatecover.setChecked(prefs['updatecover'])
         self.l.addWidget(self.updatecover)
 
@@ -514,7 +531,7 @@ class GenerateCoverTab(QWidget):
             if site == u"Default":
                 s = "On Metadata update, run Generate Cover with this setting, if not selected for specific site."
             else:
-                s = "On Metadata update, run Generate Cover with this setting for site (%s)."%site
+                s = "On Metadata update, run Generate Cover with this setting for %s stories."%site
 
             label.setToolTip(s)
             horz.addWidget(label)
@@ -536,7 +553,7 @@ class GenerateCoverTab(QWidget):
         self.l.addWidget(self.gcnewonly)
 
         self.allow_gc_from_ini = QCheckBox('Allow generate_cover_settings from personal.ini to override.',self)
-        self.allow_gc_from_ini.setToolTip("The INI parameter generate_cover_settings allows you to choose a GC setting based on metadata rather than site,\nbut it's much more complex.  generate_cover_settings is ignored when this is off.")
+        self.allow_gc_from_ini.setToolTip("The personal.ini parameter generate_cover_settings allows you to choose a GC setting based on metadata rather than site, but it's much more complex.<br \>generate_cover_settings is ignored when this is off.")
         self.allow_gc_from_ini.setChecked(prefs['allow_gc_from_ini'])
         self.l.addWidget(self.allow_gc_from_ini)
             
@@ -650,13 +667,15 @@ titleLabels = {
     'version':'FFDL Version'
     }
 
-class ColumnsTab(QWidget):
+class CustomColumnsTab(QWidget):
 
     def __init__(self, parent_dialog, plugin_action):
         self.parent_dialog = parent_dialog
         self.plugin_action = plugin_action
         QWidget.__init__(self)
         
+        custom_columns = self.plugin_action.gui.library_view.model().custom_columns
+
         self.l = QVBoxLayout()
         self.setLayout(self.l)
 
@@ -667,8 +686,6 @@ class ColumnsTab(QWidget):
         
         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:
@@ -696,4 +713,26 @@ class ColumnsTab(QWidget):
         
         self.l.insertStretch(-1)
 
+        self.l.addSpacing(5)
+        label = QLabel("Special column:")
+        label.setWordWrap(True)
+        self.l.addWidget(label)
+        self.l.addSpacing(5)
+        
+        horz = QHBoxLayout()
+        label = QLabel("Update/Overwrite Error Column:")
+        tooltip="When an update or overwrite of an existing story fails, record the reason in this column.\n(Text and Long Text columns only.)"
+        label.setToolTip(tooltip)
+        horz.addWidget(label)
+        self.errorcol = QComboBox(self)
+        self.errorcol.setToolTip(tooltip)
+        self.errorcol.addItem('',QVariant('none'))
+        for key, column in custom_columns.iteritems():
+            if column['datatype'] in ('text','comments'):
+                self.errorcol.addItem(column['name'],QVariant(key))
+        self.errorcol.setCurrentIndex(self.errorcol.findData(QVariant(prefs['errorcol'])))
+        horz.addWidget(self.errorcol)
+        self.l.addLayout(horz)
+        
+        
         #print("prefs['custom_cols'] %s"%prefs['custom_cols'])

calibre-plugin/dialogs.py

@@ -83,7 +83,7 @@ class AddNewDialog(SizePersistedDialog):
 
         self.l.addWidget(QLabel('Story URL(s), one per line:'))
         self.url = DroppableQTextEdit(self)
-        self.url.setToolTip('URLs for stories, one per line.\nWill take URLs from clipboard, but only valid URLs.')
+        self.url.setToolTip('URLs for stories, one per line.\nWill take URLs from clipboard, but only valid URLs.\nAdd [1,5] after the URL to limit the download to chapters 1-5.')
         self.url.setLineWrapMode(QTextEdit.NoWrap)
         self.url.setText(url_list_text)
         self.l.addWidget(self.url)
@@ -123,10 +123,18 @@ class AddNewDialog(SizePersistedDialog):
         horz.addWidget(self.collision)
         self.l.addLayout(horz)
 
+        horz = QHBoxLayout()
         self.updatemeta = QCheckBox('Update Calibre &Metadata?',self)
         self.updatemeta.setToolTip('Update metadata for story in Calibre from web site?')
         self.updatemeta.setChecked(prefs['updatemeta'])
-        self.l.addWidget(self.updatemeta)
+        horz.addWidget(self.updatemeta)
+
+        self.updateepubcover = QCheckBox('Update EPUB Cover?',self)
+        self.updateepubcover.setToolTip('Update book cover image from site or defaults (if found) <i>inside</i> the EPUB when EPUB is updated.')
+        self.updateepubcover.setChecked(prefs['updateepubcover'])
+        horz.addWidget(self.updateepubcover)
+        
+        self.l.addLayout(horz)
 
         button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
         button_box.accepted.connect(self.accept)
@@ -155,6 +163,7 @@ class AddNewDialog(SizePersistedDialog):
             'fileform': unicode(self.fileform.currentText()),
             'collision': unicode(self.collision.currentText()),
             'updatemeta': self.updatemeta.isChecked(),
+            'updateepubcover': self.updateepubcover.isChecked(),
             }
 
     def get_urlstext(self):
@@ -168,6 +177,43 @@ class FakeLineEdit():
     def text(self):
         pass
     
+class CollectURLDialog(QDialog):
+    '''
+    Collect single url for get urls.
+    '''
+    def __init__(self, gui, title):
+        QDialog.__init__(self, gui)
+        self.gui = gui
+        self.status=False
+
+        self.l = QGridLayout()
+        self.setLayout(self.l)
+
+        self.setWindowTitle(title)
+        self.l.addWidget(QLabel(title),0,0,1,2)
+        
+        self.l.addWidget(QLabel("URL:"),1,0)
+        self.url = QLineEdit(self)
+        self.l.addWidget(self.url,1,1)
+   
+        self.ok_button = QPushButton('OK', self)
+        self.ok_button.clicked.connect(self.ok)
+        self.l.addWidget(self.ok_button,2,0)
+
+        self.cancel_button = QPushButton('Cancel', self)
+        self.cancel_button.clicked.connect(self.cancel)
+        self.l.addWidget(self.cancel_button,2,1)
+
+        self.resize(self.sizeHint())
+
+    def ok(self):
+        self.status=True
+        self.hide()
+
+    def cancel(self):
+        self.status=False
+        self.hide()
+
 class UserPassDialog(QDialog):
     '''
     Need to collect User/Pass for some sites.
@@ -402,6 +448,11 @@ class UpdateExistingDialog(SizePersistedDialog):
         self.updatemeta.setChecked(prefs['updatemeta'])
         options_layout.addWidget(self.updatemeta)
                 
+        self.updateepubcover = QCheckBox('Update EPUB Cover?',self)
+        self.updateepubcover.setToolTip('Update book cover image from site or defaults (if found) <i>inside</i> the EPUB when EPUB is updated.')
+        self.updateepubcover.setChecked(prefs['updateepubcover'])
+        options_layout.addWidget(self.updateepubcover)
+        
         button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
         button_box.accepted.connect(self.accept)
         button_box.rejected.connect(self.reject)
@@ -435,6 +486,7 @@ class UpdateExistingDialog(SizePersistedDialog):
             'fileform': unicode(self.fileform.currentText()),
             'collision': unicode(self.collision.currentText()),
             'updatemeta': self.updatemeta.isChecked(),
+            'updateepubcover': self.updateepubcover.isChecked(),
             }
 
 def display_story_list(gui, header, prefs, icon, books,

calibre-plugin/ffdl_plugin.py

@@ -37,11 +37,12 @@ from calibre_plugins.fanfictiondownloader_plugin.common_utils import (set_plugin
 from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader import adapters, writers, exceptions
 from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.htmlcleanup import stripHTML
 from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.epubutils import get_dcsource, get_dcsource_chaptercount, get_story_url_from_html
+from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.geturls import get_urls_from_page
 
 from calibre_plugins.fanfictiondownloader_plugin.config import (prefs, permitted_values)
 from calibre_plugins.fanfictiondownloader_plugin.dialogs import (
     AddNewDialog, UpdateExistingDialog, display_story_list, DisplayStoryListDialog,
-    LoopProgressDialog, UserPassDialog, AboutDialog,
+    LoopProgressDialog, UserPassDialog, AboutDialog, CollectURLDialog, 
     OVERWRITE, OVERWRITEALWAYS, UPDATE, UPDATEALWAYS, ADDNEW, SKIP, CALIBREONLY,
     NotGoingToDownload )
 
@@ -192,6 +193,11 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                                                             shortcut_name='Get URLs from Selected Books',
                                                             triggered=self.get_list_urls)
 
+            self.get_list_action = self.create_menu_item_ex(self.menu, 'Get Story URLs from Web Page', image='view.png',
+                                                            unique_name='Get Story URLs from Web Page',
+                                                            shortcut_name='Get Story URLs from Web Page',
+                                                            triggered=self.get_urls_from_page)
+
             self.menu.addSeparator()
             self.config_action = create_menu_action_unique(self, self.menu, '&Configure Plugin', shortcut=False,
                                                            image= 'config.png',
@@ -246,6 +252,26 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                 (prefs['addtolists'] or prefs['addtoreadlists']) :
             self._update_reading_lists(self.gui.library_view.get_selected_ids(),add)
 
+    def get_urls_from_page(self):
+        d = CollectURLDialog(self.gui,"Get Story URLs from Web Page")
+        d.exec_()
+        if not d.status:
+            return
+        print("URL:%s"%d.url.text())
+
+        url_list = get_urls_from_page("%s"%d.url.text())
+
+        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 Valid URLs found on given page.'),
+                        show=True,
+                        show_copy_button=False)
+        
+            
     def get_list_urls(self):
         if len(self.gui.library_view.get_selected_ids()) > 0:
             book_list = map( partial(self._convert_id_to_book, good=False), self.gui.library_view.get_selected_ids() )
@@ -386,7 +412,8 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
     def get_metadata_for_book(self,book,
                               options={'fileform':'epub',
                                        'collision':ADDNEW,
-                                       'updatemeta':True}):
+                                       'updatemeta':True,
+                                       'updateepubcover':True}):
         '''
         Update passed in book dict with metadata from website and
         necessary data.  To be called from LoopProgressDialog
@@ -402,6 +429,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         fileform  = options['fileform']
         collision = options['collision']
         updatemeta= options['updatemeta']
+        updateepubcover= options['updateepubcover']
 
         if not book['good']:
             # book has already been flagged bad for whatever reason.
@@ -496,7 +524,7 @@ make_firstimage_cover:true
 
             # find dups
             mi = MetaInformation(story.getMetadata("title", removeallentities=True),
-                                 (story.getMetadata("author", removeallentities=True),)) # author is a list.
+                                 [story.getMetadata("author", removeallentities=True)]) # author is a list.
             identicalbooks = db.find_identical_books(mi)
             ## removed for being overkill.
             # for ib in identicalbooks:
@@ -593,7 +621,8 @@ make_firstimage_cover:true
     def start_download_list(self,book_list,
                             options={'fileform':'epub',
                                      'collision':ADDNEW,
-                                     'updatemeta':True}):
+                                     'updatemeta':True,
+                                     'updateepubcover':True}):
         '''
         Called by LoopProgressDialog to start story downloads BG processing.
         adapter_list is a list of tuples of (url,adapter)
@@ -624,6 +653,23 @@ make_firstimage_cover:true
                                        label_text='None of the URLs/stories given can be/need to be downloaded.'
                                        )
             d.exec_()
+
+            
+            custom_columns = self.gui.library_view.model().custom_columns
+            if prefs['errorcol'] != '' and prefs['errorcol'] in custom_columns:
+                label = custom_columns[prefs['errorcol']]['label']
+                print("errorcol label:%s"%label)
+                ## if error column and all bad.
+                self.previous = self.gui.library_view.currentIndex()
+                LoopProgressDialog(self.gui,
+                                   book_list,
+                                   partial(self._update_bad_book, label=label, options=options, db=self.gui.current_db),
+                                   partial(self._update_books_completed, options=options, showlist=False),
+                                   init_label="Updating calibre for BAD FanFiction stories...",
+                                   win_title="Update calibre for BAD FanFiction stories",
+                                   status_prefix="Updated")
+            
+            
             return
             
         func = 'arbitrary_n'
@@ -641,7 +687,8 @@ make_firstimage_cover:true
     def _update_book(self,book,db=None,
                      options={'fileform':'epub',
                               'collision':ADDNEW,
-                              'updatemeta':True}):
+                              'updatemeta':True,
+                              'updateepubcover':True}):
         print("add/update %s %s"%(book['title'],book['url']))
         mi = self._make_mi_from_book(book)
                 
@@ -652,7 +699,16 @@ make_firstimage_cover:true
                 (options['updatemeta'] and book['good']):
             self._update_metadata(db, book['calibre_id'], book, mi, options)
 
-    def _update_books_completed(self, book_list, options={}):
+    def _update_bad_book(self,book,db=None,label='errorcol',
+                         options={'fileform':'epub',
+                                  'collision':ADDNEW,
+                                  'updatemeta':True,
+                                  'updateepubcover':True},):
+        
+        print("add/update bad %s %s %s"%(book['title'],book['url'],book['comment']))
+        db.set_custom(book['calibre_id'], book['comment'], label=label, commit=True)
+
+    def _update_books_completed(self, book_list, options={}, showlist=True):
         
         add_list = filter(lambda x : x['good'] and x['added'], book_list)
         add_ids = [ x['calibre_id'] for x in add_list ]
@@ -676,7 +732,7 @@ make_firstimage_cover:true
         
         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):
+        if showlist and (len(update_list) + len(add_list) != len(book_list)):
             d = DisplayStoryListDialog(self.gui,
                                        'Updates completed, final status',
                                        prefs,
@@ -716,10 +772,30 @@ make_firstimage_cover:true
                                    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",
+                                   init_label="Updating calibre for FanFiction stories...",
+                                   win_title="Update calibre for FanFiction stories",
                                    status_prefix="Updated")
 
+            bad_list = filter(lambda x : x['calibre_id'] and not x['good'], book_list)
+            total_bad = len(bad_list)
+
+            self.gui.status_bar.show_message(_('Adding/Updating %s BAD books.'%total_bad))
+
+            if total_bad > 0:
+                custom_columns = self.gui.library_view.model().custom_columns
+                if prefs['errorcol'] != '' and prefs['errorcol'] in custom_columns:
+                    label = custom_columns[prefs['errorcol']]['label']
+                    print("errorcol label:%s"%label)
+                    ## if error column and all bad.
+                    LoopProgressDialog(self.gui,
+                                       bad_list,
+                                       partial(self._update_bad_book, label=label, options=options, db=self.gui.current_db),
+                                       partial(self._update_books_completed, options=options, showlist=False),
+                                       init_label="Updating calibre for BAD FanFiction stories...",
+                                       win_title="Update calibre for BAD FanFiction stories",
+                                       status_prefix="Updated")
+
+                
     def _add_or_update_book(self,book,options,prefs,mi=None):
         db = self.gui.current_db
         
@@ -780,7 +856,7 @@ make_firstimage_cover:true
             if epubmi.cover_data[1] is not None:
                 db.set_cover(book_id, epubmi.cover_data[1])
 
-        # set author link if found.  All current adapters have authorUrl.
+        # set author link if found.  All current adapters have authorUrl, except anonymous on AO3.
         if 'authorUrl' in book['all_metadata']:
             autid=db.get_author_id(book['author'])
             db.set_link_field_for_author(autid, unicode(book['all_metadata']['authorUrl']),
@@ -858,7 +934,12 @@ make_firstimage_cover:true
                 print("Running Generate Cover with settings %s."%setting_name)
                 realmi = db.get_metadata(book_id, index_is_id=True)
                 gc_plugin.generate_cover_for_book(realmi,saved_setting_name=setting_name)
-        
+
+        ## if error column set.
+        if prefs['errorcol'] != '' and prefs['errorcol'] in custom_columns:
+            label = custom_columns[prefs['errorcol']]['label']
+            print("_update_book label:%s"%label)
+            db.set_custom(book['calibre_id'], '', label=label, commit=True) # book['comment']
 
     def _get_clean_reading_lists(self,lists):
         if lists == None or lists.strip() == "" :
@@ -902,10 +983,18 @@ make_firstimage_cover:true
             if len(lists) < 1 :
                 message="<p>You configured FanFictionDownLoader to automatically update \"Send to Device\" Reading Lists, but you don't have any lists set?</p>"
                 confirm(message,'fanfictiondownloader_no_send_lists', self.gui)
+
+            # Quick demo of how an 'allow send' list might work.
+            # Issues: allow list per send list?  Naming convention?  "send(allow)"
+            # allow_list = rl_plugin.get_book_list("Allow Send to Device")
+            # # intersection of book_ids & allow_list
+            # add_book_ids = list(set(book_ids) & set(allow_list))
+
             for l in lists:
                 if l in rl_plugin.get_list_names():
                     #print("good send l:(%s)"%l)
                     rl_plugin.add_books_to_list(l,
+                                                #add_book_ids,
                                                 book_ids,
                                                 display_warnings=False)
                 else:
@@ -914,7 +1003,7 @@ make_firstimage_cover:true
                         confirm(message,'fanfictiondownloader_no_reading_list_%s'%l, self.gui)
 
     def _find_existing_book_id(self,db,book,matchurl=True):
-        mi = MetaInformation(book["title"],(book["author"],)) # author is a list.
+        mi = MetaInformation(book["title"],[book["author"]]) # author is a list.
         identicalbooks = db.find_identical_books(mi)
         if matchurl: # only *really* identical if URL matches, too.
             for ib in identicalbooks:
@@ -925,7 +1014,7 @@ make_firstimage_cover:true
         return None
     
     def _make_mi_from_book(self,book):
-        mi = MetaInformation(book['title'],(book['author'],)) # author is a list.
+        mi = MetaInformation(book['title'],[book['author']]) # author is a list.
         mi.set_identifiers({'url':book['url']})
         mi.publisher = book['publisher']
         mi.tags = book['tags']
@@ -941,7 +1030,15 @@ make_firstimage_cover:true
         books = []
         uniqueurls = set()
         for url in urls:
+            # look here for [\d,\d] at end of url, and remove?
+            mc = re.match(r"^(?P<url>.*?)(?:\[(?P<begin>\d+)?(?P<comma>,)?(?P<end>\d+)?\])?$",url)
+            print("url:(%s) begin:(%s) end:(%s)"%(mc.group('url'),mc.group('begin'),mc.group('end')))
+            url = mc.group('url')
             book = self._convert_url_to_book(url)
+            book['begin'] = mc.group('begin')
+            book['end'] = mc.group('end')
+            if book['begin'] and not mc.group('comma'):
+                book['end'] = book['begin']
             if book['url'] in uniqueurls:
                 book['good'] = False
                 book['comment'] = "Same story already included."
@@ -956,6 +1053,8 @@ make_firstimage_cover:true
         book['title'] = 'Unknown'
         book['author'] = 'Unknown'
         book['author_sort'] = 'Unknown'
+        book['begin'] = None
+        book['end'] = None
             
         book['comment'] = ''
         book['url'] = ''
@@ -971,6 +1070,8 @@ make_firstimage_cover:true
         book['title'] = 'Unknown'
         book['author'] = 'Unknown'
         book['author_sort'] = 'Unknown'
+        book['begin'] = None
+        book['end'] = None
             
         book['comment'] = ''
         book['url'] = ''

calibre-plugin/jobs.py

@@ -87,7 +87,15 @@ def do_download_worker(book_list, options,
         print(job.details)
 
         if count >= total:
-            # All done!
+            # All done!  Output some lists for convenience of some users.
+            print("Successfully downloaded:")
+            for book in book_list:
+                if book['good']:
+                    print(book['title'])
+            print("\nUnsuccessful:")
+            for book in book_list:
+                if not book['good']:
+                    print(book['title'])
             break
 
     server.close()
@@ -107,6 +115,9 @@ def do_download_for_worker(book,options):
         ffdlconfig.readfp(StringIO(get_resources("plugin-defaults.ini")))
         ffdlconfig.readfp(StringIO(options['personal.ini']))
         
+        if not options['updateepubcover'] and 'epub_for_update' in book and options['collision'] in (UPDATE, UPDATEALWAYS):
+            ffdlconfig.set("overrides","never_make_cover","true")
+        
         adapter = adapters.getAdapter(ffdlconfig,book['url'],options['fileform'])
         adapter.is_adult = book['is_adult'] 
         adapter.username = book['username'] 
@@ -114,10 +125,10 @@ def do_download_for_worker(book,options):
         
         story = adapter.getStoryMetadataOnly()
         if 'calibre_series' in book:
-            print("calibre_series:%s [%d]"%book['calibre_series'])
+            # print("calibre_series:%s [%d]"%book['calibre_series'])
             adapter.setSeries(book['calibre_series'][0],book['calibre_series'][1])
-        else:
-            print("no calibre_series")
+        # else:
+        #     print("no calibre_series")
         writer = writers.getWriter(options['fileform'],adapter.config,adapter)
 
         outfile = book['outfile']
@@ -130,19 +141,24 @@ def do_download_for_worker(book,options):
         ## checks were done earlier, it's new or not dup or newer--just write it.
         elif options['collision'] in (ADDNEW, SKIP, OVERWRITE, OVERWRITEALWAYS) or \
                 ('epub_for_update' not in book and options['collision'] in (UPDATE, UPDATEALWAYS)):
+
+            adapter.setChaptersRange(book['begin'],book['end'])
+            
             print("write to %s"%outfile)
             writer.writeStory(outfilename=outfile, forceOverwrite=True)
             book['comment'] = 'Download %s completed, %s chapters.'%(options['fileform'],story.getMetadata("numChapters"))
             
         ## checks were done earlier, just update it.
         elif 'epub_for_update' in book and options['collision'] in (UPDATE, UPDATEALWAYS):
-            
+
             # update now handled by pre-populating the old images and
             # chapters in the adapter rather than merging epubs.
             urlchaptercount = int(story.getMetadata('numChapters'))
             (url,chaptercount,
              adapter.oldchapters,
-             adapter.oldimgs) = get_update_data(book['epub_for_update'])
+             adapter.oldimgs,
+             adapter.oldcover,
+             adapter.calibrebookmark) = get_update_data(book['epub_for_update'])
 
             print("Do update - epub(%d) vs url(%d)" % (chaptercount, urlchaptercount))
             print("write to %s"%outfile)

defaults.ini

@@ -66,7 +66,9 @@ extratags_label:Extra Tags
 version_label:FFDL Version
 
 ## items to include in the title page
-## Empty entries will *not* appear, even if in the list.
+## Empty metadata entries will *not* appear, even if in the list.
+## You can include extra text or HTML that will be included as-is in
+## the title page. Eg: titlepage_entries: ...,<br />,summary,<br />,...
 ## All current formats already include title and author.
 titlepage_entries: series,category,genre,language,characters,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,description
 
@@ -183,6 +185,9 @@ output_css:
 ## Add URLs since there aren't links.
 titlepage_entries: series,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,storyUrl, authorUrl, description
 
+## Width to word wrap text output.  0 indicates no wrapping.
+wrap_width: 78
+
 ## use \r\n for line endings, the windows convention.  text output only.
 windows_eol: true
 
@@ -308,6 +313,19 @@ extratags: FanFiction,Testing,HTML
 
 [archive.skyehawke.com]
 
+[archiveofourown.org]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
+#is_adult:true
+
 [ashwinder.sycophanthex.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -395,6 +413,10 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[national-library.net]
+
+[ncisfic.com]
+
 [nfacommunity.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
@@ -409,6 +431,35 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #username:YourName
 #password:yourpassword
 
+[onedirectionfanfiction.com]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
+#is_adult:true
+
+[ponyfictionarchive.net]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+[samdean.archive.nu]
+
+[sg1-heliopolis.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+[stargate-atlantis.org]
+
 [thehexfiles.net]
 
 [thequidditchpitch.org]
@@ -430,11 +481,7 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
-[www.archiveofourown.org]
-## Some sites do not require a login, but do require the user to
-## confirm they are adult for adult content.  In commandline version,
-## this should go in your personal.ini, not defaults.ini.
-#is_adult:true
+[www.thealphagate.com]
 
 [www.checkmated.com]
 ## Some sites require login (or login for some rated stories) The
@@ -444,7 +491,26 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #username:YourName
 #password:yourpassword
 
+[www.destinysgateway.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+[www.dokuga.com]
+
 [www.fanfiction.net]
+## fanfiction.net's 'cover' images are really just tiny thumbnails.
+## Comment this out or change it to false to use them anyway.
+never_make_cover: true
+
+[www.fanfiktion.de]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
 
 [www.ficbook.net]
 
@@ -492,6 +558,19 @@ extratags:
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[www.ik-eternal.net]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
+#is_adult:true
+
 [www.libraryofmoria.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
@@ -510,6 +589,8 @@ extratags:
 ## cover image.  This lets you exclude them.
 cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
 
+[www.ncisfiction.com]
+
 [www.phoenixsong.net]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -520,6 +601,8 @@ cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
 
 [www.potionsandsnitches.net]
 
+[www.prisonbreakfic.net]
+
 [www.siye.co.uk]
 
 [www.squidge.org/peja]
@@ -533,6 +616,8 @@ titlepage_entries: series,category,genre,language,characters,status,datePublishe
 # Remove numWords -- www.squidge.org/peja word counts are inaccurate
 titlepage_entries: series,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,storyUrl, authorUrl, description
 
+[www.storiesofarda.com]
+
 [www.thewriterscoffeeshop.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -598,6 +683,12 @@ collect_series: false
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[www.yourfanfiction.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
 [overrides]
 ## It may sometimes be useful to override all of the specific format,
 ## site and site:format sections in your private configuration.  For

downloader.py

@@ -17,7 +17,7 @@
 
 import logging
 ## XXX cli option for logging level.
-logging.basicConfig(level=logging.DEBUG,format="%(levelname)s:%(filename)s(%(lineno)d):%(message)s")
+logging.basicConfig(level=logging.INFO,format="%(levelname)s:%(filename)s(%(lineno)d):%(message)s")
 
 import sys, os
 from os.path import normpath, expanduser, isfile, join
@@ -30,6 +30,7 @@ from subprocess import call
 
 from fanficdownloader import adapters,writers,exceptions
 from fanficdownloader.epubutils import get_dcsource_chaptercount, get_update_data
+from fanficdownloader.geturls import get_urls_from_page
 
 if sys.version_info < (2, 5):
     print "This program requires Python 2.5 or newer."
@@ -64,9 +65,15 @@ def main():
    parser.add_option("-u", "--update-epub",
                      action="store_true", dest="update",
                      help="Update an existing epub with new chapter, give epub filename instead of storyurl.",)
+   parser.add_option("--update-cover",
+                     action="store_true", dest="updatecover",
+                     help="Update cover in an existing epub, otherwise existing cover (if any) is used on update.  Only valid with --update-epub.",)
    parser.add_option("--force",
                      action="store_true", dest="force",
                      help="Force overwrite or update of an existing epub, download and overwrite all chapters.",)
+   parser.add_option("-l", "--list",
+                     action="store_true", dest="list",
+                     help="Get list of valid story URLs from page given.",)
    
    (options, args) = parser.parse_args()
 
@@ -104,12 +111,21 @@ def main():
 
    if options.force:
        config.set("overrides","always_overwrite","true")
+
+   if options.update and not options.updatecover:
+       config.set("overrides","never_make_cover","true")
        
    if options.options:
        for opt in options.options:
            (var,val) = opt.split('=')
            config.set("overrides",var,val)
 
+   if options.list:
+       retlist = get_urls_from_page(args[0])
+       print "\n".join(retlist)
+               
+       return
+
    try:
        ## Attempt to update an existing epub.
        if options.update:
@@ -167,7 +183,9 @@ def main():
                    # merging epubs.
                    (url,chaptercount,
                     adapter.oldchapters,
-                    adapter.oldimgs) = get_update_data(args[0])
+                    adapter.oldimgs,
+                    adapter.oldcover,
+                    adapter.calibrebookmark) = get_update_data(args[0])
 
                    writeStory(config,adapter,"epub")
                    
@@ -194,7 +212,7 @@ def main():
        print dne
    except exceptions.UnknownSite, us:
        print us
-   
+
 if __name__ == "__main__":
     #import time
     #start = time.time()

fanficdownloader/adapters/__init__.py

@@ -65,6 +65,22 @@ import adapter_phoenixsongnet
 import adapter_walkingtheplankorg
 import adapter_ashwindersycophanthexcom
 import adapter_thehexfilesnet
+import adapter_dokugacom
+import adapter_iketernalnet
+import adapter_onedirectionfanfictioncom
+import adapter_prisonbreakficnet
+import adapter_storiesofardacom
+import adapter_yourfanfictioncom
+import adapter_samdeanarchivenu
+import adapter_destinysgatewaycom
+import adapter_ncisfictioncom
+import adapter_stargateatlantisorg
+import adapter_thealphagatecom
+import adapter_fanfiktionde
+import adapter_ponyfictionarchivenet
+import adapter_sg1heliopoliscom
+import adapter_ncisficcom
+import adapter_nationallibrarynet
 
 ## This bit of complexity allows adapters to be added by just adding
 ## importing.  It eliminates the long if/else clauses we used to need

fanficdownloader/adapters/adapter_archiveofourownorg.py

@@ -42,6 +42,9 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
                                # 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])
@@ -60,13 +63,54 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
     @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'
+        return 'archiveofourown.org'
+
+    @classmethod
+    def getAcceptDomains(cls):
+        return ['www.archiveofourown.org','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+)?/?$"
+        return re.escape("http://")+"(www\.)?"+re.escape(self.getSiteDomain()+"/works/")+r"\d+(/chapters/\d+)?/?$"
+        
+    ## Login
+    def needToLoginCheck(self, data):
+        if 'This work is only available to registered users of the Archive.' in data \
+                or "The password or user name you entered doesn't match our records" in data:
+            return True
+        else:
+            return False
+        
+    def performLogin(self, url, data):
+
+        params = {}
+        if self.password:
+            params['user_session[login]'] = self.username
+            params['user_session[password]'] = self.password
+        else:
+            params['user_session[login]'] = self.getConfig("username")
+            params['user_session[password]'] = self.getConfig("password")
+        params['user_session[remember_me]'] = '1'
+        params['commit'] = 'Log in'
+        #params['utf8'] = u'✓'#u'\x2713' # gets along with out it, and it confuses the encoder.
+        params['authenticity_token'] = data.split('input name="authenticity_token" type="hidden" value="')[1].split('" /></div>')[0]
+
+        loginUrl = 'http://' + self.getSiteDomain() + '/user_sessions'
+        logging.info("Will now login to URL (%s) as (%s)" % (loginUrl,
+                                                              params['user_session[login]']))
+    
+        d = self._postUrl(loginUrl, params)
+        #logging.info(d)
+    
+        if "Successfully logged in" not in d : #Member Account
+            logging.info("Failed to login to URL %s as %s" % (loginUrl,
+                                                              params['user_session[login]']))
+            raise exceptions.FailedToLogin(url,params['user_session[login]'])
+            return False
+        else:
+            return True
 
     ## Getting the chapter list and the meta data, plus 'is adult' checking.
     def extractChapterUrlsAndMetadata(self):
@@ -76,13 +120,14 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
         else:
             addurl=""
 
-        meta = self.url+addurl
+        metaurl = self.url+addurl
         url = self.url+'/navigate'+addurl
-        logging.debug("URL: "+meta)
+        logging.info("url: "+url)
+        logging.info("metaurl: "+metaurl)
 
         try:
             data = self._fetchUrl(url)
-            meta = self._fetchUrl(meta)
+            meta = self._fetchUrl(metaurl)
 
             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)
@@ -92,11 +137,16 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
                 raise exceptions.StoryDoesNotExist(self.meta)
             else:
                 raise e
+                
+        if self.needToLoginCheck(data):
+            # need to log in for this one.
+            self.performLogin(url,data)
+            data = self._fetchUrl(url)
+            meta = self._fetchUrl(metaurl)
             
         # 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.
         
@@ -106,9 +156,13 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
 		
         # 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)
+        if a == None: # ao3 allows for author 'Anonymous' with no author link.
+            self.story.setMetadata('author','Anonymous')
+            self.story.setMetadata('authorUrl',self.url)
+        else:
+            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+$"))

fanficdownloader/adapters/adapter_ashwindersycophanthexcom.py

@@ -104,7 +104,7 @@ class AshwinderSycophantHexComAdapter(BaseSiteAdapter):
     
         d = self._fetchUrl(loginUrl, params)
     
-        if "User Account Page" not in d : #Member Account
+        if "Logout" not in d : #Member Account
             logging.info("Failed to login to URL %s as %s" % (loginUrl,
                                                               params['penname']))
             raise exceptions.FailedToLogin(url,params['penname'])
@@ -157,10 +157,10 @@ class AshwinderSycophantHexComAdapter(BaseSiteAdapter):
         except:
             pass
 		
-        for info in asoup.findAll('table', {'bordercolor' : '#1A1919'}):
+        for info in asoup.findAll('table', {'width' : '100%', 'bordercolor' : re.compile(r'#')}):
             a = info.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
             if a != None:
-                self.story.setMetadata('title',a.text)
+                self.story.setMetadata('title',a.string)
                 break
 		
 
@@ -189,7 +189,6 @@ class AshwinderSycophantHexComAdapter(BaseSiteAdapter):
         for cat in cats:
             self.story.addToList('category',cat.string)
 					
-			
         a = info.find('a', href=re.compile(r'reviews.php\?sid='+self.story.getMetadata('storyId')))
         val = a.nextSibling
         svalue = ""

fanficdownloader/adapters/adapter_destinysgatewaycom.py

@@ -0,0 +1,240 @@
+# -*- coding: utf-8 -*-
+
+# 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.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return DestinysGatewayComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class DestinysGatewayComAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','dgrfa')
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%b %d %Y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'www.destinysgateway.com'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        if self.is_adult or self.getConfig("is_adult"):
+            # Weirdly, different sites use different warning numbers.
+            # If the title search below fails, there's a good chance
+            # you need a different number.  print data at that point
+            # and see what the 'click here to continue' url says.
+            addurl = "&warning=4"
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'+addurl
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
+        if m != None:
+            if self.is_adult or self.getConfig("is_adult"):
+                # We tried the default and still got a warning, so
+                # let's pull the warning number from the 'continue'
+                # link and reload data.
+                addurl = m.group(1)
+                # correct stupid & error in url.
+                addurl = addurl.replace("&","&")
+                url = self.url+'&index=1'+addurl
+                logging.debug("URL 2nd try: "+url)
+
+                try:
+                    data = self._fetchUrl(url)
+                except urllib2.HTTPError, e:
+                    if e.code == 404:
+                        raise exceptions.StoryDoesNotExist(self.url)
+                    else:
+                        raise e    
+            else:
+                raise exceptions.AdultCheckRequired(self.url)
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',a.string)
+        
+        # Find authorid and URL from... author url.
+        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # Find the chapters:
+        for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
+            # just in case there's tags, like <i> in chapter titles.
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        # utility method
+        def defaultGetattr(d,k):
+            try:
+                return d[k]
+            except:
+                return ""
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        labels = soup.findAll('span',{'class':'label'})
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+
+            if 'Summary' in label:
+                ## Everything until the next span class='label'
+                svalue = ""
+                while not defaultGetattr(value,'class') == 'label':
+                    svalue += str(value)
+                    value = value.nextSibling
+                self.setDescription(url,svalue)
+                #self.story.setMetadata('description',stripHTML(svalue))
+
+            if 'Rated' in label:
+                self.story.setMetadata('rating', value)
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Categories' in label:
+                cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+                for cat in cats:
+                    self.story.addToList('category',cat.string)
+
+            if 'Genre' in label:
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
+                for genre in genres:
+                    self.story.addToList('genre',genre.string)
+
+            if 'Warnings' in label:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
+                for warning in warnings:
+                    self.story.addToList('warnings',warning.string)
+
+            if 'Completed' in label:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Updated' in label:
+                # there's a stray [ at the end.
+                #value = value[0:-1]
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    break
+                i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div', {'id' : 'story'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_dokugacom.py

@@ -0,0 +1,236 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2011 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return DokugaComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class DokugaComAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[3])
+        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        self.story.setMetadata('section',self.parsedUrl.path.split('/',)[1])
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/'+self.parsedUrl.path.split('/',)[1]+'/story/'+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','dkg')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        self.story.addToList("category","InuYasha")
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        if 'fanfiction' in self.story.getMetadata('section'):
+            self.dateformat = "%d %b %Y"
+        else:
+            self.dateformat = "%m-%d-%y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'www.dokuga.com'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/fanfiction/story/1234/1 http://"+self.getSiteDomain()+"/spark/story/1234/1"
+
+    def getSiteURLPattern(self):
+        return r"http://"+self.getSiteDomain()+"/(fanfiction|spark)?/story/\d+/?\d+?$"
+
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title and author
+        a = soup.find('div', {'align' : 'center'}).find('h3')
+        
+        # Find authorid and URL from... author url.
+        aut = a.find('a')
+        self.story.setMetadata('authorId',aut['href'].split('=')[1])
+        alink='http://'+self.host+aut['href']
+        self.story.setMetadata('authorUrl','http://'+self.host+aut['href'])
+        self.story.setMetadata('author',aut.string)
+        aut.extract()
+        
+        a = a.string[:(len(a.string)-4)]
+        self.story.setMetadata('title',a)
+
+        # Find the chapters:
+        chapters = soup.find('select').findAll('option')
+        if len(chapters)==1:
+            self.chapterUrls.append((self.story.getMetadata('title'),'http://'+self.host+'/'+self.story.getMetadata('section')+'/story/'+self.story.getMetadata('storyId')+'/1'))
+        else:
+            for chapter in chapters:
+                # just in case there's tags, like <i> in chapter titles. /fanfiction/story/7406/1
+                self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+self.story.getMetadata('section')+'/story/'+self.story.getMetadata('storyId')+'/'+chapter['value']))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+        
+        asoup = bs.BeautifulSoup(self._fetchUrl(alink))
+        
+        if 'fanfiction' in self.story.getMetadata('section'):
+            asoup=asoup.find('div', {'id' : 'cb_tabid_52'}).find('div')
+        
+            #grab the rest of the metadata from the author's page
+            for div in asoup.findAll('div'):
+                nav=div.find('a', href=re.compile(r'/fanfiction/story/'+self.story.getMetadata('storyId')+"/1$"))
+                if nav != None:
+                    break
+            div=div.nextSibling
+            self.setDescription(url,div)
+        
+            div=div.nextSibling
+            
+            a=div.text.split('Rating: ')
+            if len(a) == 2: self.story.setMetadata('rating', a[1].split('&')[0])
+        
+            a=div.text.split('Status: ')
+            if len(a)==2:
+                iscomp=a[1].split('&')[0]
+                if 'Complete' in iscomp:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+            
+            a=div.text.split('Category: ')
+            if len(a) == 2: self.story.addToList('category', a[1].split('&')[0])
+            self.story.addToList('category', 'Fanfiction')
+        
+            a=div.text.split('Created: ')
+            if len(a) == 2: self.story.setMetadata('datePublished', makeDate(stripHTML(a[1].split('&')[0]), self.dateformat))
+        
+            a=div.text.split('Updated: ')
+            if len(a) == 2: self.story.setMetadata('dateUpdated', makeDate(stripHTML(a[1]), self.dateformat))
+            
+            div=div.nextSibling.nextSibling
+            a=div.text.split('Words: ')
+            if len(a) == 2: self.story.setMetadata('numWords', a[1].split('&')[0])
+        
+            a=div.text.split('Genre: ')
+            if len(a) == 2:
+                for genre in a[1].split('&')[0].split(', '):
+                    self.story.addToList('genre',genre)
+        
+        else:
+            asoup=asoup.find('div', {'id' : 'maincol'}).find('div', {'class' : 'padding'})
+            for div in asoup.findAll('div'):
+                nav=div.find('a', href=re.compile(r'/spark/story/'+self.story.getMetadata('storyId')+"/1$"))
+                if nav != None:
+                    break
+                    
+            div=div.nextSibling.nextSibling
+            self.setDescription(url,div)
+            self.story.addToList('category', 'Spark')
+            
+            div=div.nextSibling.nextSibling
+            a=div.text.split('Rating: ')
+            if len(a) == 2: self.story.setMetadata('rating', a[1].split(' - ')[0])
+            
+            a=div.text.split('Status: ')
+            if len(a)==2:
+                iscomp=a[1].split(' - ')[0]
+                if 'Complete' in iscomp:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+            
+            a=div.text.split('Genre: ')
+            if len(a)==2:
+                for genre in a[1].split(' - ')[0].split('/'):
+                    self.story.addToList('genre',genre)
+                
+            div=div.nextSibling.nextSibling
+            
+            a=div.text.split('Updated: ')
+            if len(a)==2:
+                date=a[1].split('      -')[0]
+                self.story.setMetadata('dateUpdated', makeDate(date, self.dateformat))
+        
+                # does not have published date anywhere
+                self.story.setMetadata('datePublished', makeDate(date, self.dateformat))
+            
+            a=div.text.split('Words ')
+            if len(a)==2: self.story.setMetadata('numWords', a[1])
+            
+        
+
+
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div', {'id' : 'chtext'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_erosnsapphosycophanthexcom.py

@@ -227,13 +227,15 @@ class ErosnSapphoSycophantHexComAdapter(BaseSiteAdapter):
 
             # 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+$'))
+            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
+                # skip 'report this' and 'TOC' links
+                if 'contact.php' not in a['href'] and 'index' not in a['href']:
+                    if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                        self.setSeries(series_name, i)
+                        break
+                    i+=1
             
         except:
             # I find it hard to care if the series parsing fails

fanficdownloader/adapters/adapter_fanfictionnet.py

@@ -19,13 +19,19 @@ import time
 import logging
 import re
 import urllib2
+from urllib import unquote_plus
 import time
 
 from .. import BeautifulSoup as bs
 from .. import exceptions as exceptions
+from ..htmlcleanup import stripHTML
 
 from base_adapter import BaseSiteAdapter,  makeDate
 
+ffnetgenres=["Adventure", "Angst", "Crime", "Drama", "Family", "Fantasy", "Friendship", "General",
+             "Horror", "Humor", "Hurt-Comfort", "Mystery", "Parody", "Poetry", "Romance", "Sci-Fi",
+             "Spiritual", "Supernatural", "Suspense", "Tragedy", "Western"]
+
 class FanFictionNetSiteAdapter(BaseSiteAdapter):
 
     def __init__(self, config, url):
@@ -117,64 +123,92 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         self.story.setMetadata('authorUrl','http://'+self.host+a['href'])
         self.story.setMetadata('author',a.string)
 
-            
-        # start by finding a script towards the bottom that has a
-        # bunch of useful stuff in it.
-            
-        # var storyid = 6577076;
-        # var chapter = 1;
-        # var chapters = 17;
-        # var words = 42787;
-        # var userid = 2645830;
-        # var title = 'The+Invitation';
-        # var title_t = 'The Invitation';
-        # var summary = 'Dudley Dursley would be the first to say he lived a very normal life. But what happens when he gets invited to his cousin Harry Potter\'s wedding? Will Dudley get the courage to apologize for the torture he caused all those years ago? Harry/Ginny story.';
-        # var categoryid = 224;
-        # var cat_title = 'Harry Potter';
-        # var datep = '12-21-10';
-        # var dateu = '04-06-11';
-        # var author = 'U n F a b u l o u s M e';
+        ## Pull some additional data from html.
 
-        for script in soup.findAll('script', src=None):
-            if not script:
-                continue
-            if not script.string:
-                continue
-            if 'var storyid' in script.string:
-                for line in script.string.split('\n'):
-                    m = re.match(r"^ +var ([^ ]+) = '?(.*?)'?;\r?$",line)
-                    if m == None : continue
-                    var,value = m.groups()
-                    # remove javascript escaping from values.
-                    value = re.sub(r'\\(.)',r'\1',value)
-                    #print var,value
-                    if 'words' in var:
-                        self.story.setMetadata('numWords', value)
-                    if 'title_t' in var:
-                        self.story.setMetadata('title', value)
-                    if 'summary' in var:
-                        self.setDescription(url,value)
-                        #self.story.setMetadata('description', value)
-                    if 'datep' in var:
-                        self.story.setMetadata('datePublished',makeDate(value, '%m-%d-%y'))
-                    if 'dateu' in var:
-                        self.story.setMetadata('dateUpdated',makeDate(value, '%m-%d-%y'))
-                    if 'cat_title' in var:
-                        if "Crossover" in value:
-                            value = re.sub(r' Crossover$','',value)
-                            for c in value.split(' and '):
-                                self.story.addToList('category',c)
-                                # Screws up when the category itself
-                                # contains ' and '.  But that's rare
-                                # and the only alternative is to find
-                                # the 'Crossover' category URL and
-                                # parse that page to search for <a>
-                                # with href /crossovers/(name)/(num)/
-				# <a href="/crossovers/Harry_Potter/224/">Harry Potter</a>
-				# <a href="/crossovers/Naruto/1402/">Naruto</a>
-                        else:
-                            self.story.addToList('category',value)
-                break # for script in soup.findAll('script', src=None):
+        ## ffnet shows category two ways
+        ## 1) class(Book, TV, Game,etc) >> category(Harry Potter, Sailor Moon, etc)
+        ## 2) cat1_cat2_Crossover
+        ## For 1, use the second link.
+        ## For 2, fetch the crossover page and pull the two categories from there.
+
+        categories = soup.findAll('a',{'class':'xcontrast_txt'})
+        if len(categories) > 1:
+            self.story.addToList('category',stripHTML(categories[-1]))
+        elif 'Crossover' in categories[0]['href']:
+            caturl = "http://%s%s"%(self.getSiteDomain(),categories[0]['href'])
+            catsoup = bs.BeautifulSoup(self._fetchUrl(caturl))
+            for a in catsoup.findAll('a',href=re.compile(r"^/crossovers/")):
+                self.story.addToList('category',stripHTML(a))
+            
+        a = soup.find('a', href='http://www.fictionratings.com/')
+        rating = a.string
+        if 'Fiction' in rating: # if rating has 'Fiction ', strip that out for consistency with past.
+            rating = rating[8:]
+            
+        self.story.setMetadata('rating',rating)
+
+        # after Rating, the same bit of text containing id:123456 contains
+        # Complete--if completed.
+        gui_table1i = soup.find(id="gui_table1i")
+
+        self.story.setMetadata('title', stripHTML(gui_table1i.find('b'))) # title appears to be only(or at least first) bold tag in gui_table1i
+
+        summarydiv = gui_table1i.find('div',{'style':'margin-top:2px'})
+        if summarydiv:
+            self.setDescription(url,stripHTML(summarydiv))
+            
+        
+        metatext = stripHTML(gui_table1i.find('div', {'style':'color:gray;'})).replace('Hurt/Comfort','Hurt-Comfort')
+        metalist = metatext.split(" - ")
+        #print("metatext:(%s)"%metalist)
+
+        # Rated: Fiction K - English - Words: 158,078 - Published: 02-04-11
+
+        # rating is obtained above more robustly.
+        if metalist[0].startswith('Rated:'):
+            metalist=metalist[1:]
+
+        # next is assumed to be language.
+        self.story.setMetadata('language',metalist[0])
+        metalist=metalist[1:]
+
+        # next might be genre.
+        genrelist = metalist[0].split('/') # Hurt/Comfort already changed above.
+        goodgenres=True
+        for g in genrelist:
+            if g not in ffnetgenres:
+                goodgenres=False
+        if goodgenres:
+            self.story.extendList('genre',genrelist)
+            metalist=metalist[1:]
+
+        while len(metalist) > 0:
+            if  metalist[0].startswith('Reviews') or metalist[0].startswith('Chapters') or metalist[0].startswith('Status'):
+                pass
+            elif  metalist[0].startswith('Updated'):
+                self.story.setMetadata('dateUpdated',makeDate(metalist[0].split(':')[1].strip(), '%m-%d-%y'))
+            elif  metalist[0].startswith('Published'):
+                self.story.setMetadata('datePublished',makeDate(metalist[0].split(':')[1].strip(), '%m-%d-%y'))
+            elif  metalist[0].startswith('Words'):
+                self.story.setMetadata('numWords',metalist[0].split(':')[1].strip())
+                pass
+            else:
+                self.story.extendList('characters',metalist[0].split('&'))
+            metalist=metalist[1:]
+
+        # next might be characters, otherwise Reviews, Updated, Published, Words
+        # if not ( metalist[0].startswith('Reviews') or metalist[0].startswith('Updated') or metalist[0].startswith('Published') or metalist[0].startswith('Words') or metalist[0].startswith('Chapters') ):
+        #     self.story.extendList('characters',metalist[0].split('&'))
+        
+        if 'Status: Complete' in metatext:
+            self.story.setMetadata('status', 'Completed')
+        else:
+            self.story.setMetadata('status', 'In-Progress')
+
+        if self.getConfig('include_images'):
+            img = soup.find('img',{'class':'cimage'})
+            if img:
+                self.story.addImgUrl(self,url,img['src'],self._fetchUrlRaw,cover=True)
             
         # Find the chapter selector 
         select = soup.find('select', { 'name' : 'chapter' } )
@@ -195,58 +229,6 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
 
         self.story.setMetadata('numChapters',len(self.chapterUrls))
 
-        ## Pull some additional data from html.  Find Rating and look around it.
-
-        a = soup.find('a', href='http://www.fictionratings.com/')
-        self.story.setMetadata('rating',a.string)
-
-        # used below to get correct characters.
-        metatext = a.findNext(text=re.compile(r' - Reviews:'))
-        if metatext == None: # indicates there's no Reviews, look for id: instead.
-            metatext = a.findNext(text=re.compile(r' - id:'))
-
-        # after Rating, the same bit of text containing id:123456 contains
-        # Complete--if completed.
-        if 'Complete' in a.findNext(text=re.compile(r'id:'+self.story.getMetadata('storyId'))):
-            self.story.setMetadata('status', 'Completed')
-        else:
-            self.story.setMetadata('status', 'In-Progress')
-
-        # Parse genre(s) from <meta name="description" content="..."
-        # <meta name="description" content="A Transformers/Beast Wars  - Humor fanfiction with characters Prowl & Sideswipe. Story summary: Sideswipe is bored. Prowl appears to be so, too  or at least, Sideswipe thinks he looks bored . So Sideswipe entertains them. After all, what's more fun than a race? Song-fic.">
-        # <meta name="description" content="Chapter 1 of a Transformers/Beast Wars  - Adventure/Friendship fanfiction with characters Bumblebee. TFA: What would you do if you was being abused all you life? Follow NightRunner as she goes through her spark breaking adventure of getting away from her father..">
-        # (fp)<meta name="description" content="Chapter 1 of a Sci-Fi  - Adventure/Humor fiction. Felix Max was just your regular hyperactive kid until he accidently caused his own fathers death. Now he has meta-humans trying to hunt him down with a corrupt goverment to back them up. Oh, and did I mention he has no Powers yet?.">
-        # <meta name="description" content="Chapter 1 of a Bleach  - Adventure/Angst fanfiction with characters Ichigo K. & Neliel T. O./Nel. Time travel with a twist. Time can be a real bi***. Ichigo finds that fact out when he accidentally goes back in time. Is this his second chance or is fate just screwing with him. Not a crack fic.IchixNelXHime.">
-        # <meta name="description" content="Chapter 1 of a Harry Potter and Transformers  - Humor/Adventure crossover fanfiction  with characters: Harry P. & Ironhide. 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')
-            if genres != None:
-                # Hurt/Comfort is one genre.
-                genres=re.sub('Hurt/Comfort','Hurt-Comfort',genres)
-                for g in genres.split('/'):
-                    self.story.addToList('genre',g)
-
-            if m.group('chars') != None:
-
-                # At this point we've proven that there's character(s)
-                # We can't reliably parse characters out of meta name="description".
-                # There's no way to tell that "with characters Ichigo K. & Neliel T. O./Nel. " ends at "Nel.", not "T."
-                # But we can pull them from the reviewstext line, now that we know about existance of chars.
-                # reviewstext can take form of:
-                # - English -  Shinji H. - Updated: 01-13-12 - Published: 12-20-11 - id:7654123
-                # - English - Adventure/Angst -  Ichigo K. & Neliel T. O./Nel - Reviews:
-                # - English - Humor/Adventure -  Harry P. & Ironhide - Reviews:
-                mc = re.match(r" - (?P<lang>[^ ]+ - )(?P<genres>[^ ]+ - )? (?P<chars>.+?) - (Reviews|Updated|Published)",
-                              metatext)
-                chars = mc.group("chars")
-                for c in chars.split(' & '):
-                    self.story.addToList('characters',c)
-        m = re.match(r" - (?P<lang>[^ ]+)",metatext)
-        if m.group('lang') != None:
-            self.story.setMetadata('language',m.group('lang'))
-                    
         return
 
     def getChapterText(self, url):
@@ -262,13 +244,11 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         sharediv = soup.find('div', {'class' : 'a2a_kit a2a_default_style'})
         if sharediv:
             sharediv.extract()
-        else:
-            logging.debug('share button div not found')
         
-        div = soup.find('div', {'id' : 'storytext'})
+        div = soup.find('div', {'id' : 'storytextp'})
         
         if None == div:
-            logging.debug('div id=storytext not found.  data:%s'%data)
+            logging.debug('div id=storytextp not found.  data:%s'%data)
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
 
         return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_fanfiktionde.py

@@ -0,0 +1,199 @@
+# -*- coding: utf-8 -*-
+
+# 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.
+# 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 urllib
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return FanFiktionDeAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class FanFiktionDeAdapter(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() + '/s/'+self.story.getMetadata('storyId') + '/1')
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','ffde')
+
+        # 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.fanfiktion.de'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/s/46ccbef30000616306614050"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/s/")+r"\w+(/\d+)?$"
+        
+        ## Login seems to be reasonably standard across eFiction sites.
+    def needToLoginCheck(self, data):
+        if 'Diese Geschichte wurde als entwicklungsbeeintr' in data \
+                or 'There is no such account on our website' in data \
+                or "Noch kein registrierter Benutzer?" in data:
+            return True
+        else:
+            return False
+        
+    def performLogin(self,url):
+        params = {}
+
+        if self.password:
+            params['nickname'] = self.username
+            params['passwd'] = self.password
+        else:
+            params['nickname'] = self.getConfig("username")
+            params['passwd'] = self.getConfig("password")
+        params['savelogindata'] = '1'
+        params['a'] = 'l'
+        params['submit'] = 'Login...'
+
+        loginUrl = 'https://ssl.fanfiktion.de/'
+        logging.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
+                                                              params['nickname']))
+        d = self._postUrl(loginUrl,params)
+    
+        if "Login erfolgreich" not in d : #Member Account
+            logging.info("Failed to login to URL %s as %s" % (loginUrl,
+                                                              params['nickname']))
+            raise exceptions.FailedToLogin(url,params['nickname'])
+            return False
+        else:
+            return True
+
+    ## 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
+                
+        if self.needToLoginCheck(data):
+            # need to log in for this one.
+            self.performLogin(url)
+            data = self._fetchUrl(url)
+            
+        if "Uhr ist diese Geschichte nur nach einer" in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Auserhalb der Zeit von 23:00 Uhr bis 04:00 Uhr ist diese Geschichte nur nach einer erfolgreichen Altersverifikation zuganglich.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        a = soup.find('a', href=re.compile(r'/s/'+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',a.string)
+        
+        # Find authorid and URL from... author url.
+        head = soup.find('div', {'style' : 'width:85%;float:left;'})
+        a = head.find('a')
+        self.story.setMetadata('authorId',a['href'].split('/')[2])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # Find the chapters:
+        for chapter in soup.find('select').findAll('option'):
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/s/'+self.story.getMetadata('storyId')+'/'+chapter['value']))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+        self.story.setMetadata('language','German')
+
+        #find metadata on the story page
+        self.story.setMetadata('datePublished', makeDate(head.text.split('erstellt: ')[1].split('\n')[0], self.dateformat))
+        
+        self.story.setMetadata('dateUpdated', makeDate(head.text.split('letztes Update: ')[1].split('\n')[0], self.dateformat))
+        
+        for genre in head.text.split('   ')[3].split('/')[0].split(', '):
+            self.story.addToList('genre',genre)
+            
+        if 'fertiggestellt' in head.text:
+            self.story.setMetadata('status', 'Fertiggestellt')
+        else:
+            self.story.setMetadata('status', 'In Arbeit')
+
+        #find metadata on the author's page
+        asoup = bs.BeautifulSoup(self._fetchUrl("http://"+self.getSiteDomain()+"?a=q&a1=v&t=nickdetailsstories&lbi=stories&ar=0&nick="+self.story.getMetadata('authorId')))
+        tr=asoup.findAll('tr')
+        for i in range(1,len(tr)):
+            a = tr[i].find('a')
+            if a['href'] == '/s/'+self.story.getMetadata('storyId'):
+                break
+        self.setDescription(url,a['onmouseover'].split("', '")[1])
+        
+        td = tr[i].findAll('td')
+        self.story.addToList('category',td[1].string)
+        self.story.setMetadata('rating', td[4].string)
+        self.story.setMetadata('numWords', td[5].string)
+ 
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+        time.sleep(0.5) ## ffde has "floodlock" protection
+
+        soup = bs.BeautifulSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div', {'id' : 'storytext'})
+        for a in div.findAll('script'):
+            a.extract()
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_ficbooknet.py

@@ -94,7 +94,7 @@ class FicBookNetAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('h1')
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         logging.debug("Title: (%s)"%self.story.getMetadata('title'))
         
         # Find authorid and URL from... author url.

fanficdownloader/adapters/adapter_iketernalnet.py

@@ -0,0 +1,285 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2011 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return IkEternalNetAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class IkEternalNetAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','ike')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        self.story.addToList("category","InuYasha")
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%B %d, %Y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'www.ik-eternal.net'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+
+    ## Login seems to be reasonably standard across eFiction sites.
+    def needToLoginCheck(self, data):
+        if 'Registered Users Only' in data \
+                or 'There is no such account on our website' in data \
+                or "That password doesn't match the one in our database" in data:
+            return True
+        else:
+            return False
+        
+    def performLogin(self, url):
+        params = {}
+
+        if self.password:
+            params['penname'] = self.username
+            params['password'] = self.password
+        else:
+            params['penname'] = self.getConfig("username")
+            params['password'] = self.getConfig("password")
+        params['cookiecheck'] = '1'
+        params['submit'] = 'Submit'
+    
+        loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login'
+        logging.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
+                                                              params['penname']))
+    
+        d = self._fetchUrl(loginUrl, params)
+    
+        if "Member Account" not in d : #Member Account
+            logging.info("Failed to login to URL %s as %s" % (loginUrl,
+                                                              params['penname']))
+            raise exceptions.FailedToLogin(url,params['penname'])
+            return False
+        else:
+            return True
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        if self.is_adult or self.getConfig("is_adult"):
+            # Weirdly, different sites use different warning numbers.
+            # If the title search below fails, there's a good chance
+            # you need a different number.  print data at that point
+            # and see what the 'click here to continue' url says.
+            addurl = "&warning=1"
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'+addurl
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        if self.needToLoginCheck(data):
+            # need to log in for this one.
+            self.performLogin(url)
+            data = self._fetchUrl(url)
+
+        # The actual text that is used to announce you need to be an
+        # adult varies from site to site.  Again, print data before
+        # the title search to troubleshoot.
+            
+        # Since the warning text can change by warning level, let's
+        # look for the warning pass url.  ksarchive uses
+        # &warning= -- actually, so do other sites.  Must be an
+        # eFiction book.
+            
+        # viewstory.php?sid=1882&warning=4
+        # viewstory.php?sid=1654&ageconsent=ok&warning=5
+        #print data
+        #m = re.search(r"'viewstory.php\?sid=1882(&warning=4)'",data)
+        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
+        if m != None:
+            if self.is_adult or self.getConfig("is_adult"):
+                # We tried the default and still got a warning, so
+                # let's pull the warning number from the 'continue'
+                # link and reload data.
+                addurl = m.group(1)
+                # correct stupid & error in url.
+                addurl = addurl.replace("&","&")
+                url = self.url+'&index=1'+addurl
+                logging.debug("URL 2nd try: "+url)
+
+                try:
+                    data = self._fetchUrl(url)
+                except urllib2.HTTPError, e:
+                    if e.code == 404:
+                        raise exceptions.StoryDoesNotExist(self.url)
+                    else:
+                        raise e    
+            else:
+                raise exceptions.AdultCheckRequired(self.url)
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data,selfClosingTags=('p')) #poor formatting of the paragraphs in the title page
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',a.string)
+        
+        # Find authorid and URL from... author url.
+        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # Find the chapters:
+        for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
+            # just in case there's tags, like <i> in chapter titles.
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        # utility method
+        def defaultGetattr(d,k):
+            try:
+                return d[k]
+            except:
+                return ""
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        asoup = soup.find('div', {'class': 'listbox'})
+        for a in asoup.findAll('p'):
+            a.name='br'
+        labels = asoup.findAll('span',{'class':'label'})
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+
+            if 'Summary' in label:
+                ## Everything until the next span class='label'
+                svalue = ""
+                while not defaultGetattr(value,'class') == 'label':
+                    svalue += str(value)
+                    value = value.nextSibling
+                self.setDescription(url,svalue)
+                #self.story.setMetadata('description',stripHTML(svalue))
+
+            if 'Rated' in label:
+                self.story.setMetadata('rating', value)
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Categories' in label:
+                cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+                for cat in cats:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+                for char in chars:
+                    self.story.addToList('characters',char.string)
+
+            if 'Genre' in label:
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
+                for genre in genres:
+                    self.story.addToList('genre',genre.string)
+
+            if 'Warnings' in label:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
+                for warning in warnings:
+                    self.story.addToList('warnings',warning.string)
+
+            if 'Completed' in label:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Updated' in label:
+                # there's a stray [ at the end.
+                #value = value[0:-1]
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div', {'id' : 'story'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_ksarchivecom.py

@@ -274,13 +274,15 @@ class KSArchiveComAdapter(BaseSiteAdapter): # XXX
 
             # 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+$'))
+            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
+                # skip 'report this' and 'TOC' links
+                if 'contact.php' not in a['href'] and 'index' not in a['href']:
+                    if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                        self.setSeries(series_name, i)
+                        break
+                    i+=1
             
         except:
             # I find it hard to care if the series parsing fails

fanficdownloader/adapters/adapter_libraryofmoriacom.py

@@ -222,13 +222,15 @@ class LibraryOfMoriaComAdapter(BaseSiteAdapter):
 
             # 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+$'))
+            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
+                # skip 'report this' and 'TOC' links
+                if 'contact.php' not in a['href'] and 'index' not in a['href']:
+                    if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                        self.setSeries(series_name, i)
+                        break
+                    i+=1
             
         except:
             # I find it hard to care if the series parsing fails

fanficdownloader/adapters/adapter_midnightwhispersca.py

@@ -260,10 +260,12 @@ class MidnightwhispersCaAdapter(BaseSiteAdapter): # XXX
             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
+                # skip 'report this' and 'TOC' links
+                if 'contact.php' not in a['href'] and 'index' not in a['href']:
+                    if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                        self.setSeries(series_name, i)
+                        break
+                    i+=1
             
         except:
             # I find it hard to care if the series parsing fails

fanficdownloader/adapters/adapter_mugglenetcom.py

@@ -303,13 +303,15 @@ class MuggleNetComAdapter(BaseSiteAdapter): # XXX
 
             # 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+$'))
+            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
+                # skip 'report this' and 'TOC' links
+                if 'contact.php' not in a['href'] and 'index' not in a['href']:
+                    if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                        self.setSeries(series_name, i)
+                        break
+                    i+=1
             
         except:
             # I find it hard to care if the series parsing fails

fanficdownloader/adapters/adapter_nationallibrarynet.py

@@ -0,0 +1,209 @@
+# -*- coding: utf-8 -*-
+
+# 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.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return NationalLibraryNetAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class NationalLibraryNetAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only storyid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?storyid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','ntlb')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        self.story.addToList("category","West Wing")
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%m-%d-%y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        return 'national-library.net'
+        
+    @classmethod
+    def getAcceptDomains(cls):
+        return ['www.national-library.net','national-library.net']
+
+    def getSiteExampleURLs(self):
+        return "ONLY the stories archived on or after June 17, 2006 and that are hosted on the website: http://"+self.getSiteDomain()+"/viewstory.php?storyid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://")+"(www\.)?"+re.escape(self.getSiteDomain()+"/viewstory.php?storyid=")+r"\d+$"
+
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        a = soup.find('h1')
+        self.story.setMetadata('title',a.string)
+        
+        # Find authorid and URL from... author url.
+        a = soup.find('a', href=re.compile(r"authorresults.php\?author=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # Find the chapters:
+        for p in soup.findAll('p'):
+            chapters = p.findAll('a', href=re.compile(r'viewstory.php\?storyid='+self.story.getMetadata('storyId')+"&chapnum=\d+$"))
+            if len(chapters) > 0:
+                for chapter in chapters:
+                    # just in case there's tags, like <i> in chapter titles.
+                    self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']))
+                break
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+        self.story.setMetadata('status', 'Completed')
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        labels = soup.findAll('b')
+        for x in range(2,len(labels)):
+            value = labels[x].nextSibling
+            label = labels[x].string
+            
+            if 'Summary' in label:
+                self.setDescription(url,value)
+                #self.story.setMetadata('description',stripHTML(svalue))
+
+            if 'Rating' in label:
+                self.story.setMetadata('rating', stripHTML(value.nextSibling))
+
+            if 'Word Count' in label:
+                self.story.setMetadata('numWords', value.string)
+
+            if 'Category' in label:
+                for cat in value.string.split(', '):
+                    self.story.addToList('category',cat)
+            if 'Crossover Shows' in label:
+                for cat in value.string.split(', '):
+                    if "No Show" not in cat:
+                        self.story.addToList('category',cat)
+
+            if 'Character' in label:
+                for char in value.string.split(', '):
+                    self.story.addToList('characters',char)
+                    
+            if 'Warnings' in label:
+                for warning in value.string.split(', '):
+                    self.story.addToList('warnings',warning)
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Series' in label:
+                self.setSeries(stripHTML(value.nextSibling), value.nextSibling.nextSibling.string[2:])
+                
+        asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
+        story=asoup.find('a', href=re.compile(r'viewstory.php\?storyid='+self.story.getMetadata('storyId')))
+            
+        a=story.findNext(text=re.compile('Genre')).parent.nextSibling.string.split(', ')
+        for genre in a:
+            self.story.setMetadata('genre', genre)
+        
+        a=story.findNext(text=re.compile('Archived'))
+        self.story.setMetadata('datePublished', makeDate(stripHTML(a.parent.nextSibling), self.dateformat))
+        self.story.setMetadata('dateUpdated', makeDate(stripHTML(a.parent.nextSibling), self.dateformat))
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div')
+        
+        # bit messy since higly inconsistent
+        for p in soup.findAll('p', {'align' : 'center'}):
+            p.extract()
+        p = soup.findAll('p')
+        for x in range(0,3):
+            p[x].extract()
+        if "Chapters: " in stripHTML(p[3]):
+            p[3].extract()
+        for x in range(len(p)-2,len(p)-1):
+            p[x].extract()
+
+        for p in soup.findAll('h1'):
+            p.extract()
+        for p in soup.findAll('h3'):
+            p.extract()
+        for p in soup.findAll('a'):
+            p.extract()
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_ncisficcom.py

@@ -0,0 +1,216 @@
+# -*- coding: utf-8 -*-
+
+# 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.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return NCISFicComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class NCISFicComAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only storyid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?storyid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','ncisf')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        self.story.addToList("category","NCIS")
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%m-%d-%y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        return 'ncisfic.com'
+        
+    @classmethod
+    def getAcceptDomains(cls):
+        return ['www.ncisfic.com','ncisfic.com']
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/viewstory.php?storyid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://")+"(www\.)?"+re.escape(self.getSiteDomain()+"/viewstory.php?storyid=")+r"\d+$"
+
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        a = soup.find('h1')
+        self.story.setMetadata('title',a.string)
+        
+        # Find authorid and URL from... author url.
+        a = soup.find('a', href=re.compile(r"authorresults.php\?author=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # Find the chapters:
+        for p in soup.findAll('p'):
+            chapters = p.findAll('a', href=re.compile(r'viewstory.php\?storyid='+self.story.getMetadata('storyId')+"&chapnum=\d+$"))
+            if len(chapters) > 0:
+                for chapter in chapters:
+                    # just in case there's tags, like <i> in chapter titles.
+                    self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']))
+                break
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+        self.story.setMetadata('status', 'Completed')
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        labels = soup.findAll('b')
+        for x in range(2,len(labels)):
+            value = labels[x].nextSibling
+            label = labels[x].string
+            
+            if 'Summary' in label:
+                self.setDescription(url,value)
+                #self.story.setMetadata('description',stripHTML(svalue))
+
+            if 'Rating' in label:
+                self.story.setMetadata('rating', stripHTML(value.nextSibling))
+
+            if 'Word Count' in label:
+                self.story.setMetadata('numWords', value.string)
+
+            if 'Category' in label:
+                for cat in value.string.split(', '):
+                    self.story.addToList('category',cat)
+            if 'Crossover Shows' in label:
+                for cat in value.string.split(', '):
+                    if "No Show" not in cat:
+                        self.story.addToList('category',cat)
+
+            if 'Character' in label:
+                for char in value.string.split(', '):
+                    self.story.addToList('characters',char)
+                    
+            if 'Warnings' in label:
+                for warning in value.string.split(', '):
+                    self.story.addToList('warnings',warning)
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Series' in label:
+                if "No Series" not in value.nextSibling.string:
+                    self.setSeries(stripHTML(value.nextSibling), value.nextSibling.nextSibling.string[2:])
+                
+        asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
+        story=asoup.find('a', href=re.compile(r'viewstory.php\?storyid='+self.story.getMetadata('storyId')))
+        
+        a=story.findNext('font')
+        if 'Complete' in a.string:
+            self.story.setMetadata('status', 'Completed')
+        else:
+            self.story.setMetadata('status', 'In-Progress')
+            
+        a=story.findNext(text=re.compile('Genre')).parent.nextSibling.string.split(', ')
+        for genre in a:
+            self.story.setMetadata('genre', genre)
+        
+        a=story.findNext(text=re.compile('Archived'))
+        self.story.setMetadata('datePublished', makeDate(stripHTML(a.parent.nextSibling), self.dateformat))
+        self.story.setMetadata('dateUpdated', makeDate(stripHTML(a.parent.nextSibling), self.dateformat))
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div')
+        
+        # bit messy since higly inconsistent
+        for p in soup.findAll('p', {'align' : 'center'}):
+            p.extract()
+        p = soup.findAll('p')
+        for x in range(0,3):
+            p[x].extract()
+        if "Chapters: " in stripHTML(p[3]):
+            p[3].extract()
+        for x in range(len(p)-2,len(p)-1):
+            p[x].extract()
+
+        for p in soup.findAll('h1'):
+            p.extract()
+        for p in soup.findAll('h3'):
+            p.extract()
+        for p in soup.findAll('a'):
+            p.extract()
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_ncisfictioncom.py

@@ -0,0 +1,200 @@
+# -*- coding: utf-8 -*-
+
+# 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.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return NCISFictionComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class NCISFictionComAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["iso-8859-1",
+                       "Windows-1252"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL("http://"+self.getSiteDomain()\
+                         +"/chapters.php?stid="+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','ncisfn')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        self.story.addToList("category","NCIS")
+
+        # 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.ncisfiction.com'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/story.php?stid=01234 http://"+self.getSiteDomain()+"/chapters.php?stid=1234"
+
+    def getSiteURLPattern(self):
+        return "http://"+self.getSiteDomain()+r'/(chapters|story)?.php\?stid=\d+'
+       
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulStoneSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title and author
+        a = soup.find('div', {'class' : 'main_title'})
+        
+        aut = a.find('a')
+        self.story.setMetadata('authorId',aut['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+aut['href'])
+        self.story.setMetadata('author',aut.string)
+        
+        aut.extract()
+        self.story.setMetadata('title',stripHTML(a)[:len(stripHTML(a))-2])
+
+        # Find the chapters:
+        i=0
+        chapters=soup.findAll('table', {'class' : 'story_table'})
+        for chapter in chapters:
+            ch=chapter.find('a')
+            # just in case there's tags, like <i> in chapter titles.
+            self.chapterUrls.append((stripHTML(ch),'http://'+self.host+'/'+ch['href']))
+            if i == 0:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(chapter.find('td')).split('Added: ')[1], self.dateformat))
+            if i == len(chapters)-1:
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(chapter.find('td')).split('Added: ')[1], self.dateformat))
+            i=i+1
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        info = soup.find('table', {'class' : 'story_info'})
+        
+        # no convenient way to calculate word count as it is logged differently for stories with and without series
+        
+        labels = info.findAll('tr')
+        for tr in labels:
+            value = tr.find('td')
+            label = tr.find('th').string
+
+            if 'Summary' in label:
+                self.setDescription(url,value)
+
+            if 'Rating' in label:
+                self.story.setMetadata('rating', value.string)
+
+            if 'Category' in label:
+                cats = value.findAll('a')
+                for cat in cats:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                chars = value.findAll('a')
+                for char in chars:
+                    self.story.addToList('characters',char.string)
+
+            if 'Genre' in label:
+                genres = value.findAll('a')
+                for genre in genres:
+                    self.story.addToList('genre',genre.string)
+
+            if 'Warnings' in label:
+                warnings = value.findAll('a')
+                for warning in warnings:
+                    self.story.addToList('warnings',warning.string)
+
+            if 'Status' in label:
+                if 'not completed' in value.text:
+                    self.story.setMetadata('status', 'In-Progress')
+                else:
+                    self.story.setMetadata('status', 'Completed')
+                    
+        try:
+            # Find Series name from series URL.
+            a = soup.find('div',{'class' : 'sub_header'})
+            series_name = a.find('a').string
+            i = a.text.split('#')[1]
+            self.setSeries(series_name, i)
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div', {'class' : 'story_text'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_nfacommunitycom.py

@@ -261,13 +261,15 @@ class NfaCommunityComAdapter(BaseSiteAdapter): # XXX
 
             # 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+$'))
+            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
+                # skip 'report this' and 'TOC' links
+                if 'contact.php' not in a['href'] and 'index' not in a['href']:
+                    if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                        self.setSeries(series_name, i)
+                        break
+                    i+=1
             
         except:
             # I find it hard to care if the series parsing fails

fanficdownloader/adapters/adapter_onedirectionfanfictioncom.py

@@ -0,0 +1,271 @@
+# -*- coding: utf-8 -*-
+
+# 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.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return OneDirectionFanfictionComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class OneDirectionFanfictionComAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','odf')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        self.story.addToList("category","One Direction")
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%m/%d/%y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'onedirectionfanfiction.com'
+        
+    @classmethod
+    def getAcceptDomains(cls):
+        return ['www.onedirectionfanfiction.com','onedirectionfanfiction.com']
+
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://")+"(www\.)?"+re.escape(self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+        
+        ## Login seems to be reasonably standard across eFiction sites.
+    def needToLoginCheck(self, data):
+        if 'Registered Users Only' in data \
+                or 'There is no such account on our website' in data \
+                or "That password doesn't match the one in our database" in data:
+            return True
+        else:
+            return False
+        
+    def performLogin(self, url):
+        params = {}
+
+        if self.password:
+            params['penname'] = self.username
+            params['password'] = self.password
+        else:
+            params['penname'] = self.getConfig("username")
+            params['password'] = self.getConfig("password")
+        params['cookiecheck'] = '1'
+        params['submit'] = 'Submit'
+    
+        loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login'
+        logging.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
+                                                              params['penname']))
+    
+        d = self._fetchUrl(loginUrl, params)
+    
+        if "Member Account" not in d : #Member Account
+            logging.info("Failed to login to URL %s as %s" % (loginUrl,
+                                                              params['penname']))
+            raise exceptions.FailedToLogin(url,params['penname'])
+            return False
+        else:
+            return True
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+    
+        if self.is_adult or self.getConfig("is_adult"):
+            # Weirdly, different sites use different warning numbers.
+            # If the title search below fails, there's a good chance
+            # you need a different number.  print data at that point
+            # and see what the 'click here to continue' url says.
+            addurl = "&ageconsent=ok&warning=4"
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'+addurl
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+            
+        if self.needToLoginCheck(data):
+            # need to log in for this one.
+            self.performLogin(url)
+            data = self._fetchUrl(url)
+        
+        # The actual text that is used to announce you need to be an
+        # adult varies from site to site.  Again, print data before
+        # the title search to troubleshoot.
+        if "Age Consent Required" in data:
+            raise exceptions.AdultCheckRequired(self.url)
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',a.string)
+        
+        # Find authorid and URL from... author url.
+        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # Find the chapters:
+        for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
+            # just in case there's tags, like <i> in chapter titles.
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        # utility method
+        def defaultGetattr(d,k):
+            try:
+                return d[k]
+            except:
+                return ""
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        labels = soup.findAll('span',{'class':'label'})
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+
+            if 'Summary' in label:
+                ## Everything until the next span class='label'
+                svalue = ""
+                while not defaultGetattr(value,'class') == 'label':
+                    svalue += str(value)
+                    value = value.nextSibling
+                self.setDescription(url,svalue)
+
+            if 'Rated' in label:
+                self.story.setMetadata('rating', value)
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Categories' in label:
+                cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+                for cat in cats:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+                for char in chars:
+                    self.story.addToList('characters',char.string)
+
+            if 'Warnings' in label:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=6'))
+                for warning in warnings:
+                    self.story.addToList('warnings',warning.string)
+
+            if 'Completed' in label:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Updated' in label:
+                # there's a stray [ at the end.
+                #value = value[0:-1]
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    break
+                i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div', {'id' : 'story'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_ponyfictionarchivenet.py

@@ -0,0 +1,252 @@
+# -*- coding: utf-8 -*-
+
+# 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.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return PonyFictionArchiveNetAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class PonyFictionArchiveNetAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        logging.info(self.parsedUrl.netloc)
+        # normalized story URL.
+        if "explicit" in self.parsedUrl.netloc:
+            self._setURL('http://explicit.' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
+            self.dateformat = "%d/%b/%y"
+        else:
+            self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
+            self.dateformat = "%d %b %Y"
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','pffa')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        self.story.addToList("category","My Little Pony")
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'ponyfictionarchive.net'
+        
+    @classmethod
+    def getAcceptDomains(cls):
+        return ['www.ponyfictionarchive.net','ponyfictionarchive.net','explicit.ponyfictionarchive.net']
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://")+"(www\.|explicit\.)?"+re.escape(self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        if self.is_adult or self.getConfig("is_adult"):
+            # Weirdly, different sites use different warning numbers.
+            # If the title search below fails, there's a good chance
+            # you need a different number.  print data at that point
+            # and see what the 'click here to continue' url says.
+            addurl = "&warning=9"
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'+addurl
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+
+        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
+        if m != None:
+            if self.is_adult or self.getConfig("is_adult"):
+                # We tried the default and still got a warning, so
+                # let's pull the warning number from the 'continue'
+                # link and reload data.
+                addurl = m.group(1)
+                # correct stupid & error in url.
+                addurl = addurl.replace("&","&")
+                url = self.url+'&index=1'+addurl
+                logging.debug("URL 2nd try: "+url)
+
+                try:
+                    data = self._fetchUrl(url)
+                except urllib2.HTTPError, e:
+                    if e.code == 404:
+                        raise exceptions.StoryDoesNotExist(self.url)
+                    else:
+                        raise e    
+            else:
+                raise exceptions.AdultCheckRequired(self.url)
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',a.string)
+        
+        # Find authorid and URL from... author url.
+        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # Find the chapters:
+        for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
+            # just in case there's tags, like <i> in chapter titles.
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        # utility method
+        def defaultGetattr(d,k):
+            try:
+                return d[k]
+            except:
+                return ""
+
+        genres = soup.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
+        for genre in genres:
+            self.story.addToList('genre',genre.string)
+           
+        warnings = soup.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=3'))
+        for warning in warnings:
+            self.story.addToList('warnings',warning.string)
+        
+        status = soup.find('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
+        self.story.setMetadata('status',status.string)
+        
+        section = soup.findAll('span', {'class' : 'General'})[1]            
+        
+        self.story.setMetadata('rating', section.previousSibling.previousSibling.string)
+
+        value = section.nextSibling
+        svalue = ""
+        while not defaultGetattr(value,'class') == 'label':
+            svalue += str(value)
+            value = value.nextSibling
+        self.setDescription(url,svalue)
+        
+        # <span class="label">Rated:</span> NC-17<br /> etc           
+        labels = soup.findAll('span',{'class':'label'})
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Characters' in label:
+                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+                for char in chars:
+                    self.story.addToList('characters',char.string)
+
+            if 'Completed' in label:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Updated' in label:
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            # can't use ^viewstory...$ in case of higher rated stories with javascript href.
+            storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
+            i=1
+            for a in storyas:
+                # skip 'report this' and 'TOC' links
+                if 'contact.php' not in a['href'] and 'index' not in a['href']:
+                    if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                        self.setSeries(series_name, i)
+                        break
+                    i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div', {'id' : 'story'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_prisonbreakficnet.py

@@ -0,0 +1,215 @@
+# -*- coding: utf-8 -*-
+
+# 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.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return PrisonBreakFicNetAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class PrisonBreakFicNetAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','pbf')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        self.story.addToList("category","Prison Break")
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%B %d, %Y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'www.prisonbreakfic.net'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',a.string)
+        
+        # Find authorid and URL from... author url.
+        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # Find the chapters:
+        for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
+            # just in case there's tags, like <i> in chapter titles.
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        # utility method
+        def defaultGetattr(d,k):
+            try:
+                return d[k]
+            except:
+                return ""
+                
+# summary, rated, word count, categories, characters, genre, warnings, completed, published, updated, seires
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        labels = soup.findAll('span',{'class':'label'})
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+
+            if 'Summary' in label:
+                ## Everything until the next span class='label'
+                svalue = ""
+                while not defaultGetattr(value,'class') == 'label':
+                    svalue += str(value)
+                    value = value.nextSibling
+                self.setDescription(url,svalue)
+                #self.story.setMetadata('description',stripHTML(svalue))
+
+            if 'Rated' in label:
+                self.story.setMetadata('rating', value)
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Categories' in label:
+                cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+                for cat in cats:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+                for char in chars:
+                    self.story.addToList('characters',char.string)
+
+            if 'Genre' in label:
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1')) # XXX
+                for genre in genres:
+                    self.story.addToList('genre',genre.string)
+
+            if 'Warnings' in label:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
+                for warning in warnings:
+                    self.story.addToList('warnings',warning.string)
+
+            if 'Completed' in label:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Updated' in label:
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    break
+                i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div', {'id' : 'story'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_samdeanarchivenu.py

@@ -0,0 +1,234 @@
+# -*- coding: utf-8 -*-
+
+# 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.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return SamDeanArchiveNuAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class SamDeanArchiveNuAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','sda')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        self.story.addToList("category","Supernatural")
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%m/%d/%y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'samdean.archive.nu'
+
+    @classmethod
+    def getAcceptDomains(cls):
+        return ['www.samdean.archive.nu','samdean.archive.nu']
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://")+r"(www\.)?"+re.escape(self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title and author
+        a = soup.find('div', {'id' : 'pagetitle'})
+        
+        aut = a.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        self.story.setMetadata('authorId',aut['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+aut['href'])
+        self.story.setMetadata('author',aut.string)
+        aut.extract()
+        
+        self.story.setMetadata('title',a.string[:(len(a.string)-3)])
+
+        # Find the chapters:
+        chapters=soup.find('select')
+        if chapters != None:
+            for chapter in chapters.findAll('option'):
+                # just in case there's tags, like <i> in chapter titles. http://samdean.archive.nu/viewstory.php?sid=4317&chapter=2
+                self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/viewstory.php?sid='+self.story.getMetadata('storyId')+'&chapter='+chapter['value']))
+        else:
+            self.chapterUrls.append((self.story.getMetadata('title'),url))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+        
+        asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
+        
+        for list in asoup.findAll('div', {'class' : re.compile('listbox\s+')}):
+            a = list.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+            if a != None:
+                break
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        # utility method
+        def defaultGetattr(d,k):
+            try:
+                return d[k]
+            except:
+                return ""
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        labels = list.findAll('span', {'class' : 'classification'})
+        for labelspan in labels:
+            label = labelspan.string
+            value = labelspan.nextSibling
+
+            if 'Summary' in label:
+                ## Everything until the next span class='label'
+                svalue = ""
+                while not defaultGetattr(value,'class') == 'classification':
+                    svalue += str(value)
+                    value = value.nextSibling
+                self.setDescription(url,svalue)
+                #self.story.setMetadata('description',stripHTML(svalue))
+
+            if 'Rated' in label:
+                self.story.setMetadata('rating', value[:len(value)-2])
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Categories' in label:
+                cats = labelspan.parent.findAll('a',href=re.compile(r'categories.php\?catid=\d+'))
+                for cat in cats:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                for char in value.string.split(', '):
+                    if not 'None' in char:
+                        self.story.addToList('characters',char)
+
+            if 'Genre' in label:
+                for genre in value.string.split(', '):
+                    if not 'None' in genre:
+                        self.story.addToList('genre',genre)
+
+            if 'Warnings' in label:
+                for warning in value.string.split(', '):
+                    if not 'None' in warning:
+                        self.story.addToList('warnings',warning)
+
+            if 'Completed' in label:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Updated' in label:
+                # there's a stray [ at the end.
+                #value = value[0:-1]
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+
+        try:
+            # Find Series name from series URL.
+            a = list.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
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div', {'id' : 'story'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_sg1heliopoliscom.py

@@ -0,0 +1,255 @@
+# -*- coding: utf-8 -*-
+
+# 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.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return SG1HeliopolisComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class SG1HeliopolisComAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        self.story.setMetadata('section',self.parsedUrl.path.split('/',)[1])
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/'+self.story.getMetadata('section')+'/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','sghp')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        if 'atlantis' in self.story.getMetadata('section'):
+            self.story.addToList("category","Stargate: Atlantis")
+        else:
+            self.story.addToList("category","Stargate: SG-1")
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%Y.%m.%d"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'sg1-heliopolis.com'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/archive/viewstory.php?sid=1234 http://"+self.getSiteDomain()+"/adult/viewstory.php?sid=1234 http://"+self.getSiteDomain()+"/atlantis/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return r"http://sg1-heliopolis.com/(archive|adult|atlantis)?/viewstory.php\?sid=\d+$"
+
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        if self.is_adult or self.getConfig("is_adult"):
+            # Weirdly, different sites use different warning numbers.
+            # If the title search below fails, there's a good chance
+            # you need a different number.  print data at that point
+            # and see what the 'click here to continue' url says.
+            addurl = "&warning=4"
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'+addurl
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
+        if m != None:
+            if self.is_adult or self.getConfig("is_adult"):
+                # We tried the default and still got a warning, so
+                # let's pull the warning number from the 'continue'
+                # link and reload data.
+                addurl = m.group(1)
+                # correct stupid & error in url.
+                addurl = addurl.replace("&","&")
+                url = self.url+'&index=1'+addurl
+                logging.debug("URL 2nd try: "+url)
+
+                try:
+                    data = self._fetchUrl(url)
+                except urllib2.HTTPError, e:
+                    if e.code == 404:
+                        raise exceptions.StoryDoesNotExist(self.url)
+                    else:
+                        raise e    
+            else:
+                raise exceptions.AdultCheckRequired(self.url)
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',a.string)
+        
+        # Find authorid and URL from... author url.
+        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # Find the chapters:
+        for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
+            # just in case there's tags, like <i> in chapter titles.
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+self.story.getMetadata('section')+'/'+chapter['href']+addurl))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        # utility method
+        def defaultGetattr(d,k):
+            try:
+                return d[k]
+            except:
+                return ""
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        labels = soup.findAll('span',{'class':'label'})
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+
+            if 'Summary' in label:
+                ## Everything until the next span class='label'
+                svalue = ""
+                while not defaultGetattr(value,'class') == 'label':
+                    svalue += str(value)
+                    value = value.nextSibling
+                self.setDescription(url,svalue)
+                #self.story.setMetadata('description',stripHTML(svalue))
+
+            if 'Rated' in label:
+                self.story.setMetadata('rating', value)
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Categories' in label:
+                cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+                for cat in cats:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+                for char in chars:
+                    self.story.addToList('characters',char.string)
+
+            if 'Genre' in label:
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
+                for genre in genres:
+                    self.story.addToList('genre',genre.string)
+
+            if 'Warnings' in label:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
+                for warning in warnings:
+                    self.story.addToList('warnings',warning.string)
+
+            if 'Completed' in label:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Updated' in label:
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/'+self.story.getMetadata('section')+'/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            # can't use ^viewstory...$ in case of higher rated stories with javascript href.
+            storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
+            i=1
+            for a in storyas:
+                # skip 'report this' and 'TOC' links
+                if 'contact.php' not in a['href'] and 'index' not in a['href']:
+                    if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                        self.setSeries(series_name, i)
+                        break
+                    i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div', {'id' : 'story'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_siyecouk.py

@@ -174,7 +174,16 @@ class SiyeCoUkAdapter(BaseSiteAdapter): # XXX
             
         # 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.parent.find('div',{'class':'desc'}))
+                
+        # SIYE formats stories in the author list differently when their part of a series.
+        # Look for non-series...
+        divdesc = titlea.parent.parent.find('div',{'class':'desc'})
+        if not divdesc:
+            # ... now look for series.
+            divdesc = titlea.parent.parent.findNextSibling('tr').find('div',{'class':'desc'})
+
+        moremeta = stripHTML(divdesc)
+        #print("moremeta:%s"%moremeta)
         for part in moremeta.replace(' - ','\n').split('\n'):
             #print("part:%s"%part)
             try:

fanficdownloader/adapters/adapter_squidgeorgpeja.py

@@ -84,7 +84,7 @@ class SquidgeOrgPejaAdapter(BaseSiteAdapter):
         return "http://"+self.getSiteDomain()+"/peja/cgi-bin/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
-        return re.escape("http://"+self.getSiteDomain()+"/peja/cgi-bin/viewstory.php?sid=")+r"\d+$"        
+        return re.escape("http://"+self.getSiteDomain()+"/")+"~?"+re.escape("peja/cgi-bin/viewstory.php?sid=")+r"\d+$"        
 
     ## Getting the chapter list and the meta data, plus 'is adult' checking.
     def extractChapterUrlsAndMetadata(self):

fanficdownloader/adapters/adapter_stargateatlantisorg.py

@@ -0,0 +1,231 @@
+# -*- coding: utf-8 -*-
+
+# 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.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return StargateAtlantisOrgAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class StargateAtlantisOrgAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/fanfics/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','stat')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        self.story.addToList("category","Stargate: Atlantis")
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%B %d %Y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'stargate-atlantis.org'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/fanfics/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/fanfics/viewstory.php?sid=")+r"\d+$"
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title and author
+        a = soup.find('div', {'id' : 'pagetitle'})
+        
+        aut = a.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        self.story.setMetadata('authorId',aut['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/fanfics/'+aut['href'])
+        self.story.setMetadata('author',aut.string)
+        aut.extract()
+        
+        self.story.setMetadata('title',a.string[:(len(a.string)-3)])
+
+        # Find the chapters:
+        chapters=soup.findAll('div', {'class' : 'content'})
+        if len(chapters) > 1:
+            for chapter in chapters:
+                # just in case there's tags, like <i> in chapter titles. 
+                link = chapter.find('a')
+                self.chapterUrls.append((stripHTML(link),'http://'+self.host+'/fanfics/'+link['href']))
+        else:
+            self.chapterUrls.append((self.story.getMetadata('title'),url))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+        
+        asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
+        
+        for list in asoup.findAll('div', {'class' : re.compile('listbox\s+')}):
+            a = list.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+            if a != None:
+                break
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        # utility method
+        def defaultGetattr(d,k):
+            try:
+                return d[k]
+            except:
+                return ""
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        labels = list.findAll('span', {'class' : 'classification'})
+        for labelspan in labels:
+            label = labelspan.string
+            value = labelspan.nextSibling
+
+            if 'Summary' in label:
+                ## Everything until the next span class='label'
+                svalue = ""
+                while not defaultGetattr(value,'class') == 'tail' and value != None:
+                    svalue += str(value)
+                    value = value.nextSibling
+                self.setDescription(url,svalue)
+                #self.story.setMetadata('description',stripHTML(svalue))
+
+            if 'Rated' in label:
+                self.story.setMetadata('rating', value[:len(value)-2])
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Categories' in label:
+                cats = labelspan.parent.findAll('a',href=re.compile(r'categories.php\?catid=\d+'))
+                for cat in cats:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                for char in value.string.split(', '):
+                    if not 'None' in char:
+                        self.story.addToList('characters',char)
+
+            if 'Genre' in label:
+                for genre in value.string.split(', '):
+                    if not 'None' in genre:
+                        self.story.addToList('genre',genre)
+
+            if 'Warnings' in label:
+                for warning in value.string.split(', '):
+                    if not 'None' in warning:
+                        self.story.addToList('warnings',warning)
+
+            if 'Completed' in label:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value.split(' ::')[0]), self.dateformat))
+            
+            if 'Updated' in label:
+                # there's a stray [ at the end.
+                #value = value[0:-1]
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+
+        try:
+            # Find Series name from series URL.
+            a = list.find('a', href=re.compile(r"series.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/fanfics/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    break
+                i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+                                     
+        div = soup.find('div', {'id' : 'story'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_storiesofardacom.py

@@ -0,0 +1,152 @@
+# -*- coding: utf-8 -*-
+
+# 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.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return StoriesOfArdaComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class StoriesOfArdaComAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/chapterlistview.asp?SID='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','soa')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        self.story.addToList("category","Lord of the Rings")
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%m/%d/%Y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'www.storiesofarda.com'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/chapterlistview.asp?SID=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/chapterlistview.asp?SID=")+r"\d+$"
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title and author
+        a = soup.find('th', {'colspan' : '3'})
+        
+        aut = a.find('a')
+        self.story.setMetadata('authorId',aut['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+aut['href'])
+        self.story.setMetadata('author',aut.string)
+        asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
+        
+        a.find('em').extract()
+        self.story.setMetadata('title',a.text)
+
+        # Find the chapters: chapterview.asp?sid=7000&cid=30919
+        chapters=soup.findAll('a', href=re.compile(r'chapterview.asp\?sid='+self.story.getMetadata('storyId')+"&cid=\d+$"))
+        if len(chapters)==1:
+            self.chapterUrls.append((self.story.getMetadata('title'),'http://'+self.host+'/'+chapters[0]['href']))
+        else:
+            for chapter in chapters:
+                self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+        
+        summary = soup.find('td', {'colspan' : '3'})
+        self.setDescription(url,summary)
+        
+        # no convenient way to get word count
+
+        for td in asoup.findAll('td', {'colspan' : '3'}):
+            if td.find('a', href=re.compile('chapterlistview.asp\?SID='+self.story.getMetadata('storyId'))) != None:
+                break     
+        td=td.nextSibling.nextSibling
+        self.story.setMetadata('dateUpdated', makeDate(stripHTML(td).split(': ')[1], self.dateformat))
+        tr=td.parent.nextSibling.nextSibling.nextSibling.nextSibling
+        td=tr.findAll('td')
+        self.story.setMetadata('rating', td[0].string.split(': ')[1])
+        self.story.setMetadata('status', td[2].string.split(': ')[1])
+        self.story.setMetadata('datePublished', makeDate(stripHTML(td[4]).split(': ')[1], self.dateformat))
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('table', {'width' : '90%'}).find('td')
+        div.name='div'
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_thealphagatecom.py

@@ -0,0 +1,216 @@
+# -*- coding: utf-8 -*-
+
+# 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.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return TheAlphaGateComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class TheAlphaGateComAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','tag')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        self.story.addToList("category","Stargate: SG-1")
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%d %b %Y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'www.thealphagate.com'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',a.string)
+        
+        # Find authorid and URL from... author url.
+        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # Find the chapters:
+        for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
+            # just in case there's tags, like <i> in chapter titles.
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        # utility method
+        def defaultGetattr(d,k):
+            try:
+                return d[k]
+            except:
+                return ""
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        labels = soup.findAll('span',{'class':'label'})
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+
+            if 'Summary' in label:
+                ## Everything until the next span class='label'
+                svalue = ""
+                while not defaultGetattr(value,'class') == 'label':
+                    svalue += str(value)
+                    value = value.nextSibling
+                self.setDescription(url,svalue)
+                #self.story.setMetadata('description',stripHTML(svalue))
+
+            if 'Rated' in label:
+                self.story.setMetadata('rating', value)
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Categories' in label:
+                cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+                for cat in cats:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+                for char in chars:
+                    self.story.addToList('characters',char.string)
+
+            if 'Genre' in label:
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
+                for genre in genres:
+                    self.story.addToList('genre',genre.string)
+
+            if 'Warnings' in label:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
+                for warning in warnings:
+                    self.story.addToList('warnings',warning.string)
+
+            if 'Completed' in label:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Updated' in label:
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    break
+                i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div', {'id' : 'story'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_thehexfilesnet.py

@@ -69,13 +69,15 @@ class TheHexFilesNetAdapter(BaseSiteAdapter):
         # The site domain.  Does have www here, if it uses it.
         return 'thehexfiles.net'
 
+    @classmethod
+    def getAcceptDomains(cls):
+        return ['www.thehexfiles.net','thehexfiles.net']
+
     def getSiteExampleURLs(self):
         return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
-        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
-
-
+        return re.escape("http://")+"(www\.)?"+re.escape(self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
 
     ## Getting the chapter list and the meta data, plus 'is adult' checking.
     def extractChapterUrlsAndMetadata(self):
@@ -196,4 +198,4 @@ class TheHexFilesNetAdapter(BaseSiteAdapter):
         if None == soup:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
     
-        return self.utf8FromSoup(url,soup)
+        return self.utf8FromSoup(url,soup)

fanficdownloader/adapters/adapter_thewriterscoffeeshopcom.py

@@ -165,7 +165,13 @@ class TheWritersCoffeeShopComSiteAdapter(BaseSiteAdapter):
                 svalue = ""
                 while not defaultGetattr(value,'class') == 'label':
                     svalue += str(value)
-                    value = value.nextSibling
+                    # poor HTML(unclosed <p> for one) can cause run on
+                    # over the next label.
+                    if '<span class="label">' in svalue:
+                        svalue = svalue[0:svalue.find('<span class="label">')]
+                        break
+                    else:
+                        value = value.nextSibling
                 self.setDescription(url,svalue)
 
             if 'Rated' in label:

fanficdownloader/adapters/adapter_yourfanfictioncom.py

@@ -0,0 +1,266 @@
+# -*- coding: utf-8 -*-
+
+# 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.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return YourFanfictionComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class YourFanfictionComAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','yff')
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%d %b %Y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'www.yourfanfiction.com'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        if self.is_adult or self.getConfig("is_adult"):
+            # Weirdly, different sites use different warning numbers.
+            # If the title search below fails, there's a good chance
+            # you need a different number.  print data at that point
+            # and see what the 'click here to continue' url says.
+            addurl = "&ageconsent=ok&warning=4"
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'+addurl
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        # The actual text that is used to announce you need to be an
+        # adult varies from site to site.  Again, print data before
+        # the title search to troubleshoot.
+            
+        # Since the warning text can change by warning level, let's
+        # look for the warning pass url.  ksarchive uses
+        # &warning= -- actually, so do other sites.  Must be an
+        # eFiction book.
+            
+        # viewstory.php?sid=1882&warning=4
+        # viewstory.php?sid=1654&ageconsent=ok&warning=5
+        #print data
+        #m = re.search(r"'viewstory.php\?sid=1882(&warning=4)'",data)
+        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
+        if m != None:
+            if self.is_adult or self.getConfig("is_adult"):
+                # We tried the default and still got a warning, so
+                # let's pull the warning number from the 'continue'
+                # link and reload data.
+                addurl = m.group(1)
+                # correct stupid & error in url.
+                addurl = addurl.replace("&","&")
+                url = self.url+'&index=1'+addurl
+                logging.debug("URL 2nd try: "+url)
+
+                try:
+                    data = self._fetchUrl(url)
+                except urllib2.HTTPError, e:
+                    if e.code == 404:
+                        raise exceptions.StoryDoesNotExist(self.url)
+                    else:
+                        raise e    
+            else:
+                raise exceptions.AdultCheckRequired(self.url)
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',a.string)
+        
+        # Find authorid and URL from... author url.
+        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # Find the chapters:
+        for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
+            # just in case there's tags, like <i> in chapter titles.
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        # utility method
+        def defaultGetattr(d,k):
+            try:
+                return d[k]
+            except:
+                return ""
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        labels = soup.findAll('span',{'class':'label'})
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+
+            if 'Summary' in label:
+                ## Everything until the next span class='label'
+                svalue = ""
+                while not defaultGetattr(value,'class') == 'label':
+                    svalue += str(value)
+                    value = value.nextSibling
+                self.setDescription(url,svalue)
+                #self.story.setMetadata('description',stripHTML(svalue))
+
+            if 'Rated' in label:
+                self.story.setMetadata('rating', value)
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Categories' in label:
+                cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+                for cat in cats:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+                for char in chars:
+                    self.story.addToList('characters',char.string)
+
+            if 'Genre' in label:
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=5'))
+                for genre in genres:
+                    self.story.addToList('genre',genre.string)
+                    
+            if 'Tags' in label:
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=7'))
+                for genre in genres:
+                    self.story.addToList('genre',genre.string)
+
+            if 'Warnings' in label:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=6'))
+                for warning in warnings:
+                    self.story.addToList('warnings',warning.string)
+
+            if 'Completed' in label:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Updated' in label:
+                # there's a stray [ at the end.
+                #value = value[0:-1]
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            # can't use ^viewstory...$ in case of higher rated stories with javascript href.
+            storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
+            i=1
+            for a in storyas:
+                print("series a['href']:%s"%a['href'])
+                # skip 'report this' and 'TOC' links
+                if 'contact.php' not in a['href'] and 'index' not in a['href']:
+                    if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                        self.setSeries(series_name, i)
+                        break
+                    i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div', {'id' : 'story'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/base_adapter.py

@@ -87,6 +87,8 @@ class BaseSiteAdapter(Configurable):
         self.chapterLast = None
         self.oldchapters = None
         self.oldimgs = None
+        self.oldcover = None # (data of existing cover html, data of existing cover image)
+        self.calibrebookmark = None
         ## order of preference for decoding.
         self.decode = ["utf8",
                        "Windows-1252"] # 1252 is a superset of
@@ -132,9 +134,10 @@ class BaseSiteAdapter(Configurable):
                         code=detected['encoding']
                     else:
                         continue
+                logging.debug("try code:"+code)
                 return data.decode(code)
             except:
-                logging.debug("code failed:"+code)
+                logging.info("code failed:"+code)
                 pass
         logging.info("Could not decode story, tried:%s Stripping non-ASCII."%decode)
         return "".join([x for x in data if ord(x) < 128])
@@ -218,11 +221,24 @@ class BaseSiteAdapter(Configurable):
                                                                self.getConfig('allow_unsafe_filename')),
                                      self._fetchUrlRaw,
                                      cover=True)
+
+            # no new cover, set old cover, if there is one.
+            if not self.story.cover and self.oldcover:
+                self.story.oldcover = self.oldcover
+                
+            # cheesy way to carry calibre bookmark file forward across update.
+            if self.calibrebookmark:
+                self.story.calibrebookmark = self.calibrebookmark
+                
         return self.story
 
     def getStoryMetadataOnly(self):
         if not self.metadataDone:
             self.extractChapterUrlsAndMetadata()
+            
+            if not self.story.getMetadataRaw('dateUpdated'):
+                self.story.setMetadata('dateUpdated',self.story.getMetadataRaw('datePublished'))
+
             self.metadataDone = True
         return self.story
 

fanficdownloader/configurable.py

@@ -54,6 +54,17 @@ class Configurable(object):
     def addConfigSection(self,section):
         self.sectionslist.insert(0,section)
 
+    def hasConfig(self, key):
+        for section in self.sectionslist:
+            try:
+                self.config.get(section,key)
+                #print("found %s in section [%s]"%(key,section))
+                return True
+            except:
+                pass
+
+        return False
+        
     def getConfig(self, key):
         val = ""
         for section in self.sectionslist:

fanficdownloader/epubutils.py

@@ -40,6 +40,50 @@ def get_update_data(inputio,
     ## Save the path to the .opf file--hrefs inside it are relative to it.
     relpath = get_path_part(rootfilename)
             
+    oldcover = None
+    calibrebookmark = None
+    # Looking for pre-existing cover.
+    for item in contentdom.getElementsByTagName("reference"):
+        if item.getAttribute("type") == "cover":
+            # there is a cover (x)html file, save the soup for it.
+            href=relpath+item.getAttribute("href")
+            oldcoverhtmlhref = href
+            oldcoverhtmldata = epub.read(href)
+            oldcoverhtmltype = "application/xhtml+xml"
+            for item in contentdom.getElementsByTagName("item"):
+                if( relpath+item.getAttribute("href") == oldcoverhtmlhref ):
+                    oldcoverhtmltype = item.getAttribute("media-type")
+                    break
+            soup = bs.BeautifulSoup(oldcoverhtmldata.decode("utf-8"))
+            src = None
+            # first img or image tag.
+            imgs = soup.findAll('img')
+            if imgs:
+                src = get_path_part(href)+imgs[0]['src']
+            else:
+                imgs = soup.findAll('image')
+                if imgs:
+                    src=get_path_part(href)+imgs[0]['xlink:href']
+
+            if not src:
+                continue
+            try:
+                # remove all .. and the path part above it, if present.
+                # Mostly for epubs edited by Sigil.
+                src = re.sub(r"([^/]+/\.\./)","",src)
+                print("epubutils: found pre-existing cover image:%s"%src)
+                oldcoverimghref = src
+                oldcoverimgdata = epub.read(src)
+                for item in contentdom.getElementsByTagName("item"):
+                    if( relpath+item.getAttribute("href") == oldcoverimghref ):
+                        oldcoverimgtype = item.getAttribute("media-type")
+                        break
+                oldcover = (oldcoverhtmlhref,oldcoverhtmltype,oldcoverhtmldata,oldcoverimghref,oldcoverimgtype,oldcoverimgdata)
+            except Exception as e:
+                print("Cover Image %s not found"%src)
+                print("Exception: %s"%(unicode(e)))
+                traceback.print_exc()
+
     filecount = 0
     soups = [] # list of xhmtl blocks
     images = {} # dict() longdesc->data
@@ -61,7 +105,7 @@ def get_update_data(inputio,
                             try:
                                 newsrc=get_path_part(href)+img['src']
                                 # remove all .. and the path part above it, if present.
-                                # Most for epubs edited by Sigil.
+                                # Mostly for epubs edited by Sigil.
                                 newsrc = re.sub(r"([^/]+/\.\./)","",newsrc)
                                 longdesc=img['longdesc']
                                 data = epub.read(newsrc)
@@ -85,9 +129,14 @@ def get_update_data(inputio,
                         
                     filecount+=1
 
+    try:
+        calibrebookmark = epub.read("META-INF/calibre_bookmarks.txt")
+    except:
+        pass
+                    
     for k in images.keys():
         print("\tlongdesc:%s\n\tData len:%s\n"%(k,len(images[k])))
-    return (source,filecount,soups,images)
+    return (source,filecount,soups,images,oldcover,calibrebookmark)
 
 def get_path_part(n):
     relpath = os.path.dirname(n)

fanficdownloader/geturls.py

@@ -0,0 +1,82 @@
+# -*- coding: utf-8 -*-
+
+# 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.
+# 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 re
+import urlparse
+import urllib2 as u2
+import ConfigParser
+
+from BeautifulSoup import BeautifulSoup 
+from gziphttp import GZipProcessor
+
+import adapters
+
+def get_urls_from_page(url):
+    
+    opener = u2.build_opener(u2.HTTPCookieProcessor(),GZipProcessor())
+    soup = BeautifulSoup(opener.open(url).read())
+    
+    normalized = set() # normalized url
+    retlist = [] # orig urls.
+    config = ConfigParser.SafeConfigParser()
+    
+    for a in soup.findAll('a'):
+        if a.has_key('href'):
+            href = form_url(url,a['href'])
+            # lots of eFiction sites use similar 'are you old enough' javascript links.
+            if 'javascript' in a['href'] and 'viewstory.php' in a['href']:
+                m = re.search(r"'(?P<sid>(view)?story\.php\?(sid|psid|no|story|stid)=\d+)",a['href'])
+                if m != None:
+                    href = form_url(url,m.group('sid'))
+            try:
+                href = href.replace('&index=1','')
+                adapter = adapters.getAdapter(config,href,"EPUB")
+                if adapter.story.getMetadata('storyUrl') not in normalized:
+                    normalized.add(adapter.story.getMetadata('storyUrl'))
+                    retlist.append(href)
+            except:
+                pass
+
+    return retlist
+
+def form_url(parenturl,url):
+     url = url.strip() # ran across an image with a space in the
+                       # src. Browser handled it, so we'd better, too.
+ 
+     if "//" in url or parenturl == None:
+         returl = url
+     else:
+         parsedUrl = urlparse.urlparse(parenturl)
+         if url.startswith("/") :
+             returl = urlparse.urlunparse(
+                 (parsedUrl.scheme,
+                  parsedUrl.netloc,
+                  url,
+                  '','',''))
+         else:
+             toppath=""
+             if parsedUrl.path.endswith("/"):
+                 toppath = parsedUrl.path
+             else:
+                 toppath = parsedUrl.path[:parsedUrl.path.rindex('/')]
+             returl = urlparse.urlunparse(
+                 (parsedUrl.scheme,
+                  parsedUrl.netloc,
+                  toppath + '/' + url,
+                  '','',''))
+     return returl
+       

fanficdownloader/html2text.py

@@ -103,9 +103,10 @@ def onlywhite(line):
             return c is ' '
     return line
 
-def optwrap(text):
+def optwrap(text,wrap_width=BODY_WIDTH):
     """Wrap all paragraphs in the provided text."""
-    if not BODY_WIDTH:
+    
+    if not wrap_width:
         return text
     
     assert wrap, "Requires Python 2.3."
@@ -114,7 +115,7 @@ def optwrap(text):
     for para in text.split("\n"):
         if len(para) > 0:
             if para[0] is not ' ' and para[0] is not '-' and para[0] is not '*':
-                for line in wrap(para, BODY_WIDTH):
+                for line in wrap(para, wrap_width):
                     result += line + "\n"
                 result += "\n"
                 newlines = 2
@@ -423,8 +424,8 @@ def html2text_file(html, out=wrapwrite, baseurl=''):
     h.feed("")
     return h.close()
 
-def html2text(html, baseurl=''):
-    return optwrap(html2text_file(html, None, baseurl))
+def html2text(html, baseurl='', wrap_width=BODY_WIDTH):
+    return optwrap(html2text_file(html, None, baseurl),wrap_width)
 
 if __name__ == "__main__":
     baseurl = ''

fanficdownloader/story.py

@@ -20,6 +20,7 @@ import urlparse
 import string
 from math import floor
 
+import exceptions
 from htmlcleanup import conditionalRemoveEntities, removeAllEntities
 
 # Create convert_image method depending on which graphics lib we can
@@ -197,7 +198,9 @@ class Story:
         self.imgurls = []
         self.imgtuples = []
         self.listables = {} # some items (extratags, category, warnings & genres) are also kept as lists.
-        self.cover=None
+        self.cover=None # *href* of new cover image--need to create html.
+        self.oldcover=None # (oldcoverhtmlhref,oldcoverhtmltype,oldcoverhtmldata,oldcoverimghref,oldcoverimgtype,oldcoverimgdata)
+        self.calibrebookmark=None # cheesy way to carry calibre bookmark file forward across update.
 
     def setMetadata(self, key, value):
         ## still keeps < < and &
@@ -250,7 +253,12 @@ class Story:
             allmetadata[l] = self.getMetadata(l, removeallentities, doreplacements)
 
         return allmetadata
-        
+
+    # just for less clutter in adapters.
+    def extendList(self,listname,l):
+        for v in l:
+            self.addToList(listname,v)
+    
     def addToList(self,listname,value):
         if value==None:
             return
@@ -297,6 +305,11 @@ class Story:
     # pass fetch in from adapter in case we need the cookies collected
     # as well as it's a base_story class method.
     def addImgUrl(self,configurable,parenturl,url,fetch,cover=False,coverexclusion=None):
+
+        # otherwise it saves the image in the epub even though it
+        # isn't used anywhere.
+        if cover and configurable.getConfig('never_make_cover'):
+            return
         
         url = url.strip() # ran across an image with a space in the
                           # src. Browser handled it, so we'd better, too.
@@ -332,7 +345,10 @@ class Story:
         prefix='ffdl'
         if imgurl not in self.imgurls:
             parsedUrl = urlparse.urlparse(imgurl)
-            sizes = [ int(x) for x in configurable.getConfigList('image_max_size') ]
+            try:
+                sizes = [ int(x) for x in configurable.getConfigList('image_max_size') ]
+            except Exception, e:
+                raise exceptions.FailedToDownload("Failed to parse image_max_size from personal.ini:%s\nException: %s"%(configurable.getConfigList('image_max_size'),e))
             try:
                 (data,ext,mime) = convert_image(imgurl,
                                                 fetch(imgurl),

fanficdownloader/writers/base_writer.py

@@ -149,18 +149,22 @@ class BaseStoryWriter(Configurable):
                             TEMPLATE=WIDE_ENTRY
                         else:
                             TEMPLATE=ENTRY
-                        if self.getConfigList(entry):
+                            
+                        if self.hasConfig(entry+"_label"):
                             label=self.getConfig(entry+"_label")
                         else:
+                            print("Using fallback label for %s_label"%entry)
                             label=self.titleLabels[entry]
 
                         # If the label for the title entry is empty, use the
-                        # 'no title' option if there is one.  
+                        # 'no title' option if there is one.
                         if label == "" and NO_TITLE_ENTRY:
                            TEMPLATE= NO_TITLE_ENTRY
                            
                         self._write(out,TEMPLATE.substitute({'label':label,
                                                              'value':self.story.getMetadata(entry)}))
+                else:
+                    self._write(out, entry)
 
             self._write(out,END.substitute(self.story.metadata))
 
@@ -195,7 +199,7 @@ class BaseStoryWriter(Configurable):
             
         if not outstream:
             close=True
-            logging.debug("Save directly to file: %s" % outfilename)
+            logging.info("Save directly to file: %s" % outfilename)
             if self.getConfig('make_directories'):
                 path=""
                 dirs = os.path.dirname(outfilename).split('/')

fanficdownloader/writers/writer_epub.py

@@ -262,6 +262,37 @@ ${value}<br />
         items.append(("ncx","toc.ncx","application/x-dtbncx+xml",None)) ## we'll generate the toc.ncx file,
                                                                    ## but it needs to be in the items manifest.
 
+        guide = None
+        coverIO = None
+                
+        imgid = "image0000"
+        if not self.story.cover and self.story.oldcover:
+            print("writer_epub: no new cover, has old cover, write image.")
+            (oldcoverhtmlhref,
+             oldcoverhtmltype,
+             oldcoverhtmldata,
+             oldcoverimghref,
+             oldcoverimgtype,
+             oldcoverimgdata) = self.story.oldcover
+            outputepub.writestr(oldcoverhtmlhref,oldcoverhtmldata)
+            outputepub.writestr(oldcoverimghref,oldcoverimgdata)
+            
+            imgid = "image0"
+            items.append((imgid,
+                          oldcoverimghref,
+                          oldcoverimgtype,
+                          None))
+            items.append(("cover",oldcoverhtmlhref,oldcoverhtmltype,None))
+            itemrefs.append("cover")
+            metadata.appendChild(newTag(contentdom,"meta",{"content":"image0",
+                                                           "name":"cover"}))
+            guide = newTag(contentdom,"guide")
+            guide.appendChild(newTag(contentdom,"reference",attrs={"type":"cover",
+                                                                   "title":"Cover",
+                                                                   "href":oldcoverhtmlhref}))
+            
+            
+
         if self.getConfig('include_images'):
             imgcount=0
             for imgmap in self.story.getImgUrls():
@@ -276,9 +307,6 @@ ${value}<br />
         
         items.append(("style","OEBPS/stylesheet.css","text/css",None))
 
-        guide = None
-        coverIO = None
-
         if self.story.cover:
             # Note that the id of the cover xhmtl *must* be 'cover'
             # for it to work on Nook.
@@ -347,8 +375,8 @@ div { margin: 0pt; padding: 0pt; }
         contentxml = contentdom.toxml(encoding='utf-8')
         
         # tweak for brain damaged Nook STR.  Nook insists on name before content.
-        contentxml = contentxml.replace('<meta content="image0000" name="cover"/>',
-                                        '<meta name="cover" content="image0000"/>')
+        contentxml = contentxml.replace('<meta content="%s" name="cover"/>'%imgid,
+                                        '<meta name="cover" content="%s"/>'%imgid)
         outputepub.writestr("content.opf",contentxml)
 
         contentdom.unlink()
@@ -458,6 +486,9 @@ div { margin: 0pt; padding: 0pt; }
                 outputepub.writestr("OEBPS/file%04d.xhtml"%(index+1),fullhtml.encode('utf-8'))
                 del fullhtml
 
+        if self.story.calibrebookmark:
+            outputepub.writestr("META-INF/calibre_bookmarks.txt",self.story.calibrebookmark)
+
 	# declares all the files created by Windows.  otherwise, when
         # it runs in appengine, windows unzips the files as 000 perms.
         for zf in outputepub.filelist:

fanficdownloader/writers/writer_txt.py

@@ -21,7 +21,7 @@ from textwrap import wrap
 
 from base_writer import *
 
-from ..html2text import html2text, BODY_WIDTH
+from ..html2text import html2text
 
 ## In BaseStoryWriter, we define _write to encode <unicode> objects
 ## back into <string> for true output.  But txt needs to write the
@@ -106,6 +106,12 @@ End file.
 
     def writeStoryImpl(self, out):
 
+        self.wrap_width = self.getConfig('wrap_width')
+        if self.wrap_width == '' or self.wrap_width == '0':
+            self.wrap_width = None
+        else:
+            self.wrap_width = int(self.wrap_width)
+        
         wrapout = KludgeStringIO()
         
         wrapout.write(self.TEXT_FILE_START.substitute(self.story.metadata))
@@ -131,15 +137,19 @@ End file.
             if html:
                 logging.debug('Writing chapter text for: %s' % title)
                 self._write(out,self.lineends(self.wraplines(removeAllEntities(self.TEXT_CHAPTER_START.substitute({'chapter':title, 'index':index+1})))))
-                self._write(out,self.lineends(html2text(html)))
+                self._write(out,self.lineends(html2text(html,wrap_width=self.wrap_width)))
 
         self._write(out,self.lineends(self.wraplines(self.TEXT_FILE_END.substitute(self.story.metadata))))
 
     def wraplines(self, text):
+        
+        if not self.wrap_width:
+            return text
+        
         result=''
         for para in text.split("\n"):
             first=True
-            for line in wrap(para, BODY_WIDTH):
+            for line in wrap(para, self.wrap_width):
                 if first:
                     first=False
                 else:

index.html

@@ -54,9 +54,27 @@
 	      much easier. </p>
 	  </div>
 	  <!-- put announcements here, h3 is a good title size. -->
-	  <h3>New Site</h3>
+	  <h3>New Sites</h3>
 	  <p>
-	    Now supporting thehexfiles.net, that brings us up to an even 40 supported sites.  Thanks again, Ida.
+	    
+	    New sites ncisfic.com and national-library.net added.
+	    <br />Thanks, Ida!
+	    
+	  </p>
+	  <h3>New Fixes</h3>
+	  <p>
+
+	    Fixes to support www.fanfiktion.de and archiveofourown.org username and password.
+	    
+	  </p>
+	  <p>
+
+	    <b>Note:</b> As part of the archiveofourown.org fix, the
+	    configuration section for AO3 is now
+	    [archiveofourown.org], not [www.archiveofourown.org].
+	    Please change your personal configuration accordingly, if
+	    you have customized your settings for archiveofourown.org.
+	    
 	  </p>
 	  <p>
 	    Questions?  Check out our 
@@ -66,7 +84,7 @@
 	    If you have any problems with this application, please
 	    report them in
 	    the <a href="http://groups.google.com/group/fanfic-downloader">FanFictionDownLoader Google Group</a>.  The
-	    <a href="http://4-4-11.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
+	    <a href="http://4-4-17.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
 	  </p>
 	  <div id='error'>
 	    {{ error_message }}
@@ -358,6 +376,95 @@
 	    Use the URL of the story's chapter list, such as
 	    <br /><a href="http://thehexfiles.net/viewstory.php?sid=1234">http://thehexfiles.net/viewstory.php?sid=1234</a>
 	  </dd>
+	  <dt>www.dokuga.com</dt>
+	  <dd>
+	    Use the URL of any story chapter, such as
+	    <br /><a href="http://www.dokuga.com/fanfiction/story/1234/1">http://www.dokuga.com/fanfiction/story/1234/1</a> or
+	    <br /><a href="http://www.dokuga.com/spark/story/1234/1">http://www.dokuga.com/spark/story/1234/1</a>
+	  </dd>
+	  <dt>www.ik-eternal.net</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://www.ik-eternal.net/viewstory.php?sid=1234">http://www.ik-eternal.net/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>onedirectionfanfiction.com</dt>
+	  <dd>
+	    Use the URL of the story's first chapter, such as
+	    <br /><a href="http://onedirectionfanfiction.com/viewstory.php?sid=1234">http://onedirectionfanfiction.com/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>www.prisonbreakfic.net</dt>
+	  <dd>
+	    Use the URL of the story's first chapter, such as
+	    <br /><a href="http://www.prisonbreakfic.net/viewstory.php?sid=1234">http://www.prisonbreakfic.net/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>www.storiesofarda.com</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://www.storiesofarda.com/chapterlistview.asp?SID=7000">http://www.storiesofarda.com/chapterlistview.asp?SID=7000</a>
+	  </dd>
+	  <dt>samdean.archive.nu</dt>
+	  <dd>
+	    Use the URL of the story's first chapter, such as
+	    <br /><a href="http://samdean.archive.nu/viewstory.php?sid=1234">http://samdean.archive.nu/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>www.yourfanfiction.com</dt>
+	  <dd>
+	    Use the URL of the story's first chapter, such as
+	    <br /><a href="http://www.yourfanfiction.com/viewstory.php?sid=1234">http://www.yourfanfiction.com/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>www.destinysgateway.com</dt>
+	  <dd>
+	    Use the URL of the story's first chapter, such as
+	    <br /><a href="http://www.destinysgateway.com/viewstory.php?sid=1234">http://www.destinysgateway.com/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>www.thealphagate.com</dt>
+	  <dd>
+	    Use the URL of the story's first chapter, such as
+	    <br /><a href="http://www.thealphagate.com/viewstory.php?sid=1234">http://www.thealphagate.com/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>stargate-atlantis.org</dt>
+	  <dd>
+	    Use the URL of the story's first chapter, such as
+	    <br /><a href="http://stargate-atlantis.org/fanfics/viewstory.php?sid=1234">http://stargate-atlantis.org/fanfics/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>www.ncisfiction.com</dt>
+	  <dd>
+	    Use the URL of the story's first chapter, such as
+	    <br /><a href="http://www.ncisfiction.com/story.php?stid=1234">http://www.ncisfiction.com/story.php?stid=1234</a>
+	    Or use the URL of the story's chapter list, such as
+	    <br /><a href="http://www.ncisfiction.com/chapters.php?stid=1234">http://www.ncisfiction.com/chapters.php?stid=1234</a>
+	  </dd>
+	  <dt>www.fanfiktion.de</dt>
+	  <dd>
+	    Use the URL of the story's first chapter, such as
+	    <br /><a href="http://www.fanfiktion.de/s/46ccbef30000616306614050">http://www.fanfiktion.de/s/46ccbef30000616306614050</a>
+	  </dd>
+	  <dt>ponyfictionarchive.net</dt>
+	  <dd>
+	    Use the URL of the story's first chapter, such as
+	    <br /><a href="http://ponyfictionarchive.net/viewstory.php?sid=1234">http://ponyfictionarchive.net/viewstory.php?sid=1234</a>
+	    <br />Or:
+	    <br /><a href="http://explicit.ponyfictionarchive.net/viewstory.php?sid=1234">http://explicit.ponyfictionarchive.net/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>sg1-heliopolis.com</dt>
+	  <dd>
+	    Use the URL of the story's first chapter, such as
+	    <br /><a href="http://sg1-heliopolis.com/archive/viewstory.php?sid=1234">http://sg1-heliopolis.com/archive/viewstory.php?sid=1234</a>
+	    <br />Or:
+	    <br /><a href="http://sg1-heliopolis.com/adult/viewstory.php?sid=1234">http://sg1-heliopolis.com/adult/viewstory.php?sid=1234</a>
+	    <br />Or:
+	    <br /><a href="http://sg1-heliopolis.com/atlantis/viewstory.php?sid=1234">http://sg1-heliopolis.com/atlantis/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>ncisfic.com</dt>
+	  <dd>
+	    Use the URL of the story's first chapter, such as
+	    <br /><a href="http://ncisfic.com/viewstory.php?storyid=1234">http://ncisfic.com/viewstory.php?storyid=1234</a>
+	  </dd>
+	  <dt>national-library.net</dt>
+	  <dd>
+	    Use the URL of the story's first chapter, such as
+	    <br /><a href="http://national-library.net/viewstory.php?storyid=1234">http://national-library.net/viewstory.php?storyid=1234</a>
+	  </dd>
 	</dl>
 	<p>
 	  A few additional things to know, which will make your life substantially easier:

makeplugin.py

@@ -24,7 +24,7 @@ from makezip import createZipFile
 
 if __name__=="__main__":
     filename="FanFictionDownLoader.zip"
-    exclude=['*.pyc','*~','*.xcf']
+    exclude=['*.pyc','*~','*.xcf','*[0-9].png']
     # from top dir. 'w' for overwrite
     createZipFile(filename,"w",
                   ['plugin-defaults.ini','plugin-example.ini','epubmerge.py','fanficdownloader'],

plugin-defaults.ini

@@ -71,7 +71,9 @@ extratags_label:Extra Tags
 version_label:FFDL Version
 
 ## items to include in the title page
-## Empty entries will *not* appear, even if in the list.
+## Empty metadata entries will *not* appear, even if in the list.
+## You can include extra text or HTML that will be included as-is in
+## the title page. Eg: titlepage_entries: ...,<br />,summary,<br />,...
 ## All current formats already include title and author.
 titlepage_entries: series,category,genre,language,characters,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,description
 
@@ -172,6 +174,9 @@ output_css:
 ## Add URLs since there aren't links.
 titlepage_entries: series,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,storyUrl, authorUrl, description
 
+## Width to word wrap text output.  0 indicates no wrapping.
+wrap_width: 78
+
 ## use \r\n for line endings, the windows convention.  text output only.
 windows_eol: true
 
@@ -294,6 +299,19 @@ extratags: FanFiction,Testing,HTML
 
 [archive.skyehawke.com]
 
+[archiveofourown.org]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
+#is_adult:true
+
 [ashwinder.sycophanthex.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -381,6 +399,10 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[national-library.net]
+
+[ncisfic.com]
+
 [nfacommunity.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
@@ -395,6 +417,35 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #username:YourName
 #password:yourpassword
 
+[onedirectionfanfiction.com]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
+#is_adult:true
+
+[ponyfictionarchive.net]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+[samdean.archive.nu]
+
+[sg1-heliopolis.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+[stargate-atlantis.org]
+
 [thehexfiles.net]
 
 [thequidditchpitch.org]
@@ -416,11 +467,7 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
-[www.archiveofourown.org]
-## Some sites do not require a login, but do require the user to
-## confirm they are adult for adult content.  In commandline version,
-## this should go in your personal.ini, not defaults.ini.
-#is_adult:true
+[www.thealphagate.com]
 
 [www.checkmated.com]
 ## Some sites require login (or login for some rated stories) The
@@ -430,7 +477,26 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 #username:YourName
 #password:yourpassword
 
+[www.destinysgateway.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
+[www.dokuga.com]
+
 [www.fanfiction.net]
+## fanfiction.net's 'cover' images are really just tiny thumbnails.
+## Comment this out or change it to false to use them anyway.
+never_make_cover: true
+
+[www.fanfiktion.de]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
 
 [www.ficbook.net]
 
@@ -475,6 +541,19 @@ extratags:
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[www.ik-eternal.net]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
+#is_adult:true
+
 [www.libraryofmoria.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
@@ -493,6 +572,8 @@ extratags:
 ## cover image.  This lets you exclude them.
 cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
 
+[www.ncisfiction.com]
+
 [www.phoenixsong.net]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -503,6 +584,8 @@ cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
 
 [www.potionsandsnitches.net]
 
+[www.prisonbreakfic.net]
+
 [www.siye.co.uk]
 
 [www.squidge.org/peja]
@@ -516,6 +599,8 @@ titlepage_entries: series,category,genre,language,characters,status,datePublishe
 # Remove numWords -- www.squidge.org/peja word counts are inaccurate
 titlepage_entries: series,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,storyUrl, authorUrl, description
 
+[www.storiesofarda.com]
+
 [www.thewriterscoffeeshop.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -581,6 +666,12 @@ collect_series: false
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[www.yourfanfiction.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
 [overrides]
 ## It may sometimes be useful to override all of the specific format,
 ## site and site:format sections in your private configuration.  For