Bump versions.

Fixed issues

MANIFEST.in

@@ -0,0 +1 @@
+include DESCRIPTION.rst

calibre-plugin/__init__.py

@@ -42,7 +42,7 @@ class FanFicFareBase(InterfaceActionBase):
     description         = _('UI plugin to download FanFiction stories from various sites.')
     supported_platforms = ['windows', 'osx', 'linux']
     author              = 'Jim Miller'
-    version             = (2, 2, 11)
+    version             = (2, 2, 14)
     minimum_calibre_version = (1, 48, 0)
 
     #: This field defines the GUI plugin class that contains all the code

calibre-plugin/config.py

@@ -243,6 +243,7 @@ class ConfigWidget(QWidget):
         prefs['fileform'] = unicode(self.basic_tab.fileform.currentText())
         prefs['collision'] = save_collisions[unicode(self.basic_tab.collision.currentText())]
         prefs['updatemeta'] = self.basic_tab.updatemeta.isChecked()
+        prefs['bgmeta'] = self.basic_tab.bgmeta.isChecked()
         prefs['updateepubcover'] = self.basic_tab.updateepubcover.isChecked()
         prefs['keeptags'] = self.basic_tab.keeptags.isChecked()
         prefs['suppressauthorsort'] = self.basic_tab.suppressauthorsort.isChecked()
@@ -430,6 +431,12 @@ class BasicTab(QWidget):
         self.updateepubcover.setToolTip(_("On each download, FanFicFare 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'])
         horz.addWidget(self.updateepubcover)
+        
+        self.bgmeta = QCheckBox(_('Default Background Metadata?'),self)
+        self.bgmeta.setToolTip(_("On each download, FanFicFare offers an option to Collect Metadata from sites in a Background process.<br />This returns control to you quicker while updating, but you won't be asked for username/passwords or if you are an adult--stories that need those will just fail.<br />Only available for Update/Overwrite of existing books in case URL given isn't canonical or matches to existing book by Title/Author."))
+        self.bgmeta.setChecked(prefs['bgmeta'])
+        horz.addWidget(self.bgmeta)
+
         self.l.addLayout(horz)
 
         cali_gb = groupbox = QGroupBox(_("Updating Calibre Options"))
@@ -457,7 +464,7 @@ class BasicTab(QWidget):
         self.l.addWidget(self.suppresstitlesort)
 
         self.checkforseriesurlid = QCheckBox(_("Check for existing Series Anthology books?"),self)
-        self.checkforseriesurlid.setToolTip(_("Check for existings Series Anthology books using each new story's series URL before downloading.\nOffer to skip downloading if a Series Anthology is found."))
+        self.checkforseriesurlid.setToolTip(_("Check for existings Series Anthology books using each new story's series URL before downloading.\nOffer to skip downloading if a Series Anthology is found.\nDoesn't work when Collect Metadata in Background is selected."))
         self.checkforseriesurlid.setChecked(prefs['checkforseriesurlid'])
         self.l.addWidget(self.checkforseriesurlid)
 

calibre-plugin/dialogs.py

@@ -117,7 +117,7 @@ save_collisions={
     SAVE_CALIBREONLY:CALIBREONLY,
     SAVE_CALIBREONLYSAVECOL:CALIBREONLYSAVECOL,
     }
-    
+
 anthology_collision_order=[UPDATE,
                            UPDATEALWAYS,
                            OVERWRITEALWAYS]
@@ -127,7 +127,7 @@ gpstyle='QGroupBox {border:0; padding-top:10px; padding-bottom:0px; margin-botto
 class RejectUrlEntry:
 
     matchpat=re.compile(r"^(?P<url>[^,]+?)(,(?P<fullnote>(((?P<title>.+?) by (?P<auth>.+?)( - (?P<note>.+))?)|.*)))?$")
-    
+
     def __init__(self,url_or_line,note=None,title=None,auth=None,
                  addreasontext=None,fromline=False,book_id=None):
 
@@ -151,7 +151,7 @@ class RejectUrlEntry:
                 self.note=note
                 self.title=title
                 self.auth=auth
-        
+
         if not self.note:
             if addreasontext:
                 self.note = addreasontext
@@ -160,14 +160,14 @@ class RejectUrlEntry:
         else:
             if addreasontext:
                 self.note = self.note + ' - ' + addreasontext
-                
+
         self.url = getNormalStoryURL(self.url)
         self.valid = self.url != None
-                
+
     def to_line(self):
         # always 'url,'
         return self.url+","+self.fullnote()
-        
+
     def fullnote(self):
         retval = ""
         if self.title and self.auth:
@@ -175,10 +175,10 @@ class RejectUrlEntry:
             retval = retval + "%s by %s"%(self.title,self.auth)
             if self.note:
                 retval = retval + " - "
-                
+
         if self.note:
             retval = retval + self.note
-            
+
         return retval
 
 class NotGoingToDownload(Exception):
@@ -222,7 +222,7 @@ class DroppableQTextEdit(QTextEdit):
             self.append("\n".join(urllist))
             return None
         return QTextEdit.dropEvent(self,event)
-        
+
     def canInsertFromMimeData(self, source):
         if source.hasUrls():
             return True
@@ -234,7 +234,7 @@ class DroppableQTextEdit(QTextEdit):
             self.append(source.text())
         else:
             return QTextEdit.insertFromMimeData(self, source)
-                            
+
 class AddNewDialog(SizePersistedDialog):
 
     go_signal = pyqtSignal(object, object, object, object)
@@ -242,7 +242,7 @@ class AddNewDialog(SizePersistedDialog):
     def __init__(self, gui, prefs, icon):
         SizePersistedDialog.__init__(self, gui, 'fff:add new dialog')
         self.prefs = prefs
-        
+
         self.setMinimumWidth(300)
         self.l = QVBoxLayout()
         self.setLayout(self.l)
@@ -259,7 +259,7 @@ class AddNewDialog(SizePersistedDialog):
 
         self.merge = self.newmerge = False
         self.extraoptions = {}
-        
+
         # elements to hide when doing merge.
         self.mergehide = []
         # elements to show again when doing *update* merge
@@ -282,11 +282,11 @@ class AddNewDialog(SizePersistedDialog):
 
         self.gbf.setVisible(False)
         self.groupbox.toggled.connect(self.gbf.setVisible)
-        
+
         horz = QHBoxLayout()
         label = QLabel(_('Output &Format:'))
         self.mergehide.append(label)
-        
+
         self.fileform = QComboBox(self)
         self.fileform.addItem('epub')
         self.fileform.addItem('mobi')
@@ -294,7 +294,7 @@ class AddNewDialog(SizePersistedDialog):
         self.fileform.addItem('txt')
         self.fileform.setToolTip(_('Choose output format to create.  May set default from plugin configuration.'))
         self.fileform.activated.connect(self.set_collisions)
-        
+
         horz.addWidget(label)
         label.setBuddy(self.fileform)
         horz.addWidget(self.fileform)
@@ -332,15 +332,27 @@ class AddNewDialog(SizePersistedDialog):
         self.updateepubcover.setChecked(self.prefs['updateepubcover'])
         horz.addWidget(self.updateepubcover)
         self.mergehide.append(self.updateepubcover)
-        
+
         self.gbl.addLayout(horz)
 
+        ## bgmeta not used with Add New because of stories that change
+        ## story URL and for title/author collision matching.
+        # horz = QHBoxLayout()
+        # self.bgmeta = QCheckBox(_('Background Metadata?'),self)
+        # self.bgmeta.setToolTip(_("Collect Metadata from sites in a Background process.<br />This returns control to you quicker while updating, but you won't be asked for username/passwords or if you are an adult--stories that need those will just fail."))
+        # self.bgmeta.setChecked(self.prefs['bgmeta'])
+        # horz.addWidget(self.bgmeta)
+        # self.mergehide.append(self.bgmeta)
+        # self.mergeupdateshow.append(self.bgmeta)
+
+        # self.gbl.addLayout(horz)
+
         self.button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
         self.button_box.accepted.connect(self.ok_clicked)
         self.button_box.rejected.connect(self.reject)
         self.l.addWidget(self.button_box)
 
-    # invoke the 
+    # invoke the
     def ok_clicked(self):
         self.dialog_closing(None) # save persistent size.
         self.hide()
@@ -376,7 +388,7 @@ class AddNewDialog(SizePersistedDialog):
         self.extrapayload = extrapayload
 
         self.groupbox.setVisible(not(self.merge and self.newmerge))
-        
+
         if self.merge:
             self.toplabel.setText(_('Story URLs for anthology, one per line:'))
             self.url.setToolTip(_('URLs for stories to include in the anthology, one per line.\nWill take URLs from clipboard, but only valid URLs.'))
@@ -398,7 +410,7 @@ class AddNewDialog(SizePersistedDialog):
         # Need to re-able after hiding/showing
         self.setAcceptDrops(True)
         self.url.setFocus()
-            
+
         if self.prefs['adddialogstaysontop']:
             QDialog.setWindowFlags ( self, Qt.Dialog | Qt.WindowStaysOnTopHint )
         else:
@@ -415,18 +427,19 @@ class AddNewDialog(SizePersistedDialog):
         i = self.collision.findText(save_collisions[self.prefs['collision']])
         if i > -1:
             self.collision.setCurrentIndex(i)
-            
+
         self.updatemeta.setChecked(self.prefs['updatemeta'])
-            
+        # self.bgmeta.setChecked(self.prefs['bgmeta'])
+
         if not self.merge:
             self.updateepubcover.setChecked(self.prefs['updateepubcover'])
-                
+
         self.url.setText(url_list_text)
         if url_list_text:
             self.button_box.button(QDialogButtonBox.Ok).setFocus()
         # restore saved size.
         self.resize_dialog()
-        
+
         if show: # so anthology update can be modal still.
             self.show()
         #self.resize(self.sizeHint())
@@ -447,27 +460,28 @@ class AddNewDialog(SizePersistedDialog):
 
         for o in order:
             self.collision.addItem(o)
-            
+
         i = self.collision.findText(prev)
         if i > -1:
             self.collision.setCurrentIndex(i)
-        
+
     def get_fff_options(self):
         retval =  {
             'fileform': unicode(self.fileform.currentText()),
             'collision': unicode(self.collision.currentText()),
             'updatemeta': self.updatemeta.isChecked(),
+            'bgmeta': False, # self.bgmeta.isChecked(),
             'updateepubcover': self.updateepubcover.isChecked(),
             'smarten_punctuation':self.prefs['smarten_punctuation']
                 }
-        
+
         if self.merge:
             retval['fileform']=='epub'
             retval['updateepubcover']=True
             if self.newmerge:
                 retval['updatemeta']=True
                 retval['collision']=ADDNEW
-            
+
         return dict(retval.items() + self.extraoptions.items() )
 
     def get_urlstext(self):
@@ -477,21 +491,21 @@ class AddNewDialog(SizePersistedDialog):
 class FakeLineEdit():
     def __init__(self):
         pass
-    
+
     def text(self):
         pass
-    
+
 class CollectURLDialog(SizePersistedDialog):
     '''
     Collect single url for get urls.
     '''
-    def __init__(self, gui, title, url_text, anthology=False, indiv=True): 
+    def __init__(self, gui, title, url_text, anthology=False, indiv=True):
         SizePersistedDialog.__init__(self, gui, 'fff:get story urls')
         self.status=False
         self.anthology=False
 
         self.setMinimumWidth(300)
-        
+
         self.l = QVBoxLayout()
         self.setLayout(self.l)
 
@@ -561,16 +575,16 @@ class UserPassDialog(QDialog):
         else:
             self.setWindowTitle(_('User/Password'))
             self.l.addWidget(QLabel(_("%s requires you to login to download this story.")%site),0,0,1,2)
-        
+
             self.l.addWidget(QLabel(_("User:")),1,0)
             self.user = QLineEdit(self)
             self.l.addWidget(self.user,1,1)
-   
+
         self.l.addWidget(QLabel(_("Password:")),2,0)
         self.passwd = QLineEdit(self)
         self.passwd.setEchoMode(QLineEdit.Password)
         self.l.addWidget(self.passwd,2,1)
-   
+
         self.ok_button = QPushButton(_('OK'), self)
         self.ok_button.clicked.connect(self.ok)
         self.l.addWidget(self.ok_button,3,0)
@@ -616,6 +630,9 @@ class LoopProgressDialog(QProgressDialog):
         from calibre_plugins.fanficfare_plugin.prefs import prefs
         self.show_est_time = prefs['show_est_time']
 
+        self.setLabelText('%s %d / %d' % (self.status_prefix, self.i, len(self.book_list)))
+        self.setValue(self.i)
+
         ## self.do_loop does QTimer.singleShot on self.do_loop also.
         ## A weird way to do a loop, but that was the example I had.
         QTimer.singleShot(0, self.do_loop)
@@ -642,7 +659,7 @@ class LoopProgressDialog(QProgressDialog):
             ## collision spec passed into getadapter by partial from fff_plugin
             ## no retval only if it exists, but collision is SKIP
             self.foreach_function(book)
-            
+
         except NotGoingToDownload as d:
             book['good']=False
             book['comment']=unicode(d)
@@ -653,10 +670,10 @@ class LoopProgressDialog(QProgressDialog):
             book['comment']=unicode(e)
             logger.error("Exception: %s:%s"%(book,unicode(e)))
             traceback.print_exc()
-            
+
         self.updateStatus()
         self.i += 1
-            
+
         if self.i >= len(self.book_list) or self.wasCanceled():
             return self.do_when_finished()
         else:
@@ -747,7 +764,7 @@ class UpdateExistingDialog(SizePersistedDialog):
         self.prefs = prefs
         self.setWindowTitle(header)
         self.setWindowIcon(icon)
-        
+
         layout = QVBoxLayout(self)
         self.setLayout(layout)
         title_layout = ImageTitleLayout(self, 'images/icon.png',
@@ -784,15 +801,18 @@ class UpdateExistingDialog(SizePersistedDialog):
         gbl = QVBoxLayout()
         gbl.addWidget(gbf)
         groupbox.setLayout(gbl)
-        gbl = QHBoxLayout()
+        gbl = QVBoxLayout()
         gbf.setLayout(gbl)
         options_layout.addWidget(groupbox)
 
         gbf.setVisible(False)
         groupbox.toggled.connect(gbf.setVisible)
+
+        horz = QHBoxLayout()
+        gbl.addLayout(horz)
         
         label = QLabel(_('Output &Format:'))
-        gbl.addWidget(label)
+        horz.addWidget(label)
         self.fileform = QComboBox(self)
         self.fileform.addItem('epub')
         self.fileform.addItem('mobi')
@@ -802,10 +822,10 @@ class UpdateExistingDialog(SizePersistedDialog):
         self.fileform.setToolTip(_('Choose output format to create.  May set default from plugin configuration.'))
         self.fileform.activated.connect(self.set_collisions)
         label.setBuddy(self.fileform)
-        gbl.addWidget(self.fileform)
-        
+        horz.addWidget(self.fileform)
+
         label = QLabel(_('Update Mode:'))
-        gbl.addWidget(label)
+        horz.addWidget(label)
         self.collision = QComboBox(self)
         self.collision.setToolTip(_("What sort of update to perform.  May set default from plugin configuration."))
         # add collision options
@@ -814,27 +834,33 @@ class UpdateExistingDialog(SizePersistedDialog):
         if i > -1:
             self.collision.setCurrentIndex(i)
         label.setBuddy(self.collision)
-        gbl.addWidget(self.collision)
+        horz.addWidget(self.collision)
 
+        horz = QHBoxLayout()
+        gbl.addLayout(horz)
+        
         self.updatemeta = QCheckBox(_('Update Calibre &Metadata?'),self)
         self.updatemeta.setToolTip(_("Update metadata for existing stories in Calibre from web site?\n(Columns set to 'New Only' in the column tabs will only be set for new books.)"))
         self.updatemeta.setChecked(self.prefs['updatemeta'])
-        gbl.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(self.prefs['updateepubcover'])
-        gbl.addWidget(self.updateepubcover)
+        horz.addWidget(self.updateepubcover)
 
+        self.bgmeta = QCheckBox(_('Background Metadata?'),self)
+        self.bgmeta.setToolTip(_("Collect Metadata from sites in a Background process.<br />This returns control to you quicker while updating, but you won't be asked for username/passwords or if you are an adult--stories that need those will just fail."))
+        self.bgmeta.setChecked(self.prefs['bgmeta'])
+        horz.addWidget(self.bgmeta)
 
-        
         button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
         button_box.accepted.connect(self.accept)
         button_box.rejected.connect(self.reject)
         options_layout.addWidget(button_box)
-        
+
         layout.addLayout(options_layout)
-        
+
         # Cause our dialog size to be restored from prefs or created on first usage
         self.resize_dialog()
         self.books_table.populate_table(books)
@@ -850,14 +876,14 @@ class UpdateExistingDialog(SizePersistedDialog):
             order.remove(UPDATEALWAYS)
         if self.prefs['savemetacol'] == '':
             order.remove(CALIBREONLYSAVECOL)
-            
+
         for o in order:
             self.collision.addItem(o)
-            
+
         i = self.collision.findText(prev)
         if i > -1:
             self.collision.setCurrentIndex(i)
-        
+
     def remove_from_list(self):
         self.books_table.remove_selected_rows()
 
@@ -869,6 +895,7 @@ class UpdateExistingDialog(SizePersistedDialog):
             'fileform': unicode(self.fileform.currentText()),
             'collision': unicode(self.collision.currentText()),
             'updatemeta': self.updatemeta.isChecked(),
+            'bgmeta': self.bgmeta.isChecked(),
             'updateepubcover': self.updateepubcover.isChecked(),
             'smarten_punctuation':self.prefs['smarten_punctuation']
             }
@@ -924,16 +951,16 @@ class StoryListTableWidget(QTableWidget):
         status_cell = IconWidgetItem(None,icon,val)
         status_cell.setData(Qt.UserRole, val)
         self.setItem(row, 0, status_cell)
-        
+
         title_cell = ReadOnlyTableWidgetItem(book['title'])
         title_cell.setData(Qt.UserRole, row)
         self.setItem(row, 1, title_cell)
-        
+
         self.setItem(row, 2, AuthorTableWidgetItem(", ".join(book['author']), ", ".join(book['author_sort'])))
-        
+
         url_cell = ReadOnlyTableWidgetItem(book['url'])
         self.setItem(row, 3, url_cell)
-        
+
         comment_cell = ReadOnlyTableWidgetItem(book['comment'])
         self.setItem(row, 4, comment_cell)
 
@@ -1011,9 +1038,9 @@ class RejectListTableWidget(QTableWidget):
         self.setItem(row, 0, url_cell)
         self.setItem(row, 1, ReadOnlyTableWidgetItem(rej.title))
         self.setItem(row, 2, ReadOnlyTableWidgetItem(rej.auth))
-        
+
         note_cell = EditWithComplete(self,sort_func=lambda x:1)
-        
+
         items = [rej.note]+self.rejectreasons
         note_cell.update_items_cache(items)
         note_cell.show_initial_value(rej.note)
@@ -1021,7 +1048,7 @@ class RejectListTableWidget(QTableWidget):
         note_cell.setToolTip(_('Select or Edit Reject Note.'))
         self.setCellWidget(row, 3, note_cell)
         note_cell.setCursorPosition(0)
-        
+
     def remove_selected_rows(self):
         self.setFocus()
         rows = self.selectionModel().selectedRows()
@@ -1053,10 +1080,10 @@ class RejectListDialog(SizePersistedDialog):
                  show_all_reasons=True,
                  save_size_name='fff:reject list dialog'):
         SizePersistedDialog.__init__(self, gui, save_size_name)
-      
+
         self.setWindowTitle(header)
         self.setWindowIcon(get_icon(icon))
-      
+
         layout = QVBoxLayout(self)
         self.setLayout(layout)
         title_layout = ImageTitleLayout(self, icon, header,
@@ -1072,7 +1099,7 @@ class RejectListDialog(SizePersistedDialog):
         rejects_layout.addLayout(button_layout)
         spacerItem = QtGui.QSpacerItem(20, 40, QtGui.QSizePolicy.Minimum, QtGui.QSizePolicy.Expanding)
         button_layout.addItem(spacerItem)
-        
+
         self.remove_button = QtGui.QToolButton(self)
         self.remove_button.setToolTip(_('Remove selected URLs from the list'))
         self.remove_button.setIcon(get_icon('list_remove.png'))
@@ -1084,13 +1111,13 @@ class RejectListDialog(SizePersistedDialog):
 
         if show_all_reasons:
             self.reason_edit = EditWithComplete(self,sort_func=lambda x:1)
-            
+
             items = ['']+rejectreasons
             self.reason_edit.update_items_cache(items)
             self.reason_edit.show_initial_value('')
             self.reason_edit.set_separator(None)
             self.reason_edit.setToolTip(_("This will be added to whatever note you've set for each URL above."))
-            
+
             horz = QHBoxLayout()
             label = QLabel(_("Add this reason to all URLs added:"))
             label.setToolTip(_("This will be added to whatever note you've set for each URL above."))
@@ -1099,7 +1126,7 @@ class RejectListDialog(SizePersistedDialog):
             self.reason_edit.setCursorPosition(0)
             horz.insertStretch(-1)
             layout.addLayout(horz)
-                    
+
         options_layout = QHBoxLayout()
 
         if show_delete:
@@ -1107,14 +1134,14 @@ class RejectListDialog(SizePersistedDialog):
             self.deletebooks.setToolTip(_("Delete the selected books after adding them to the Rejected URLs list."))
             self.deletebooks.setChecked(True)
             options_layout.addWidget(self.deletebooks)
-        
+
         button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
         button_box.accepted.connect(self.accept)
         button_box.rejected.connect(self.reject)
         options_layout.addWidget(button_box)
-      
+
         layout.addLayout(options_layout)
-      
+
         # Cause our dialog size to be restored from prefs or created on first usage
         self.resize_dialog()
         self.rejects_table.populate_table(reject_list)
@@ -1147,7 +1174,7 @@ class RejectListDialog(SizePersistedDialog):
         except:
             # doesn't have self.reason_edit when editing existing list.
             return None
-    
+
     def get_deletebooks(self):
         return self.deletebooks.isChecked()
 
@@ -1169,7 +1196,7 @@ class EditTextDialog(SizePersistedDialog):
         if icon:
             self.setWindowIcon(icon)
         self.l.addWidget(self.label)
-        
+
         self.textedit = QTextEdit(self)
         self.textedit.setLineWrapMode(QTextEdit.NoWrap)
         self.textedit.setReadOnly(read_only)
@@ -1182,13 +1209,13 @@ class EditTextDialog(SizePersistedDialog):
 
         if rejectreasons or reasonslabel:
             self.reason_edit = EditWithComplete(self,sort_func=lambda x:1)
-            
+
             items = ['']+rejectreasons
             self.reason_edit.update_items_cache(items)
             self.reason_edit.show_initial_value('')
             self.reason_edit.set_separator(None)
             self.reason_edit.setToolTip(reasonslabel)
-            
+
             if reasonslabel:
                 horz = QHBoxLayout()
                 label = QLabel(reasonslabel)
@@ -1199,12 +1226,12 @@ class EditTextDialog(SizePersistedDialog):
             else:
                 self.l.addWidget(self.reason_edit)
             self.reason_edit.setCursorPosition(0)
-            
+
         button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
         button_box.accepted.connect(self.accept)
         button_box.rejected.connect(self.reject)
         self.l.addWidget(button_box)
-        
+
         # Cause our dialog size to be restored from prefs or created on first usage
         self.resize_dialog()
 
@@ -1213,7 +1240,7 @@ class EditTextDialog(SizePersistedDialog):
 
     def get_reason_text(self):
         return unicode(self.reason_edit.currentText()).strip()
-    
+
 class IniTextDialog(SizePersistedDialog):
 
     def __init__(self, parent, text,
@@ -1223,9 +1250,9 @@ class IniTextDialog(SizePersistedDialog):
                  save_size_name='fff:ini text dialog',
                  ):
         SizePersistedDialog.__init__(self, parent, save_size_name)
-        
+
         self.keys=dict()
-        
+
         self.l = QVBoxLayout()
         self.setLayout(self.l)
         self.label = QLabel(label)
@@ -1234,7 +1261,7 @@ class IniTextDialog(SizePersistedDialog):
         if icon:
             self.setWindowIcon(icon)
         self.l.addWidget(self.label)
-        
+
         self.textedit = QTextEdit(self)
 
         highlighter = IniHighlighter(self.textedit,
@@ -1243,7 +1270,7 @@ class IniTextDialog(SizePersistedDialog):
                                      entries=get_valid_entries(),
                                      entry_keywords=get_valid_entry_keywords(),
                                      )
-        
+
         self.textedit.setLineWrapMode(QTextEdit.NoWrap)
         try:
             self.textedit.setFont(QFont("Courier",
@@ -1261,41 +1288,41 @@ class IniTextDialog(SizePersistedDialog):
         if use_find:
 
             findtooltip=_('Search for string in edit box.')
-            
+
             horz = QHBoxLayout()
             label = QLabel(_('Find:'))
 
             label.setToolTip(findtooltip)
-                
+
             # Button to search the document for something
             self.findButton = QtGui.QPushButton(_('Find'),self)
             self.findButton.clicked.connect(self.find)
             self.findButton.setToolTip(findtooltip)
-        
+
             # The field into which to type the query
             self.findField = QLineEdit(self)
             self.findField.setToolTip(findtooltip)
             self.findField.returnPressed.connect(self.findButton.setFocus)
-            
+
             # Case Sensitivity option
             self.caseSens = QtGui.QCheckBox(_('Case sensitive'),self)
             self.caseSens.setToolTip(_("Search for case sensitive string; don't treat Harry, HARRY and harry all the same."))
-            
+
             horz.addWidget(label)
             horz.addWidget(self.findField)
             horz.addWidget(self.findButton)
             horz.addWidget(self.caseSens)
-            
+
             self.l.addLayout(horz)
 
             self.addCtrlKeyPress(QtCore.Qt.Key_F,self.findFocus)
             self.addCtrlKeyPress(QtCore.Qt.Key_G,self.find)
-        
+
         button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
         button_box.accepted.connect(self.accept)
         button_box.rejected.connect(self.reject)
         self.l.addWidget(button_box)
-        
+
         # Cause our dialog size to be restored from prefs or created on first usage
         self.resize_dialog()
 
@@ -1311,9 +1338,9 @@ class IniTextDialog(SizePersistedDialog):
                         _('Go back to fix errors?'),
                         errors)
             retry = d.exec_() == d.Accepted
-            
+
             # print("retry:%s"%retry)
-        
+
         if retry:
             lineno=d.get_lineno()
             if lineno:
@@ -1335,19 +1362,19 @@ class IniTextDialog(SizePersistedDialog):
             return func()
         else:
             return SizePersistedDialog.keyPressEvent(self, event)
-    
+
     def get_plain_text(self):
         return unicode(self.textedit.toPlainText())
 
     def findFocus(self):
         # print("findFocus called")
         self.findField.setFocus()
-        self.findField.selectAll()        
-        
+        self.findField.selectAll()
+
     def find(self):
 
         #print("find self.lastStart:%s"%self.lastStart)
-        
+
         # Grab the parent's text
         text = self.textedit.toPlainText()
 
@@ -1362,7 +1389,7 @@ class IniTextDialog(SizePersistedDialog):
         # last starting position
         self.lastStart = text.find(query,self.lastStart + 1)
         # If the find() method didn't return -1 (not found)
-        
+
         if self.lastStart >= 0:
             end = self.lastStart + len(query)
             self.moveCursor(self.lastStart,end)
@@ -1370,7 +1397,7 @@ class IniTextDialog(SizePersistedDialog):
             # Make the next search start from the begining again
             self.lastStart = 0
             self.textedit.moveCursor(self.textedit.textCursor().Start)
-                    
+
     def moveCursor(self,start,end):
 
         # We retrieve the QTextCursor object from the parent's QTextEdit
@@ -1387,7 +1414,7 @@ class IniTextDialog(SizePersistedDialog):
         self.textedit.setTextCursor(cursor)
 
     def select_line(self,lineno):
-        
+
         # We retrieve the QTextCursor object from the parent's QTextEdit
         cursor = self.textedit.textCursor()
 
@@ -1413,8 +1440,8 @@ class ViewLog(SizePersistedDialog):
 
     def get_lineno(self):
         return self.lineno
-        
-    def __init__(self, parent, title, errors, 
+
+    def __init__(self, parent, title, errors,
                  save_size_name='fff:view log dialog',):
         SizePersistedDialog.__init__(self, parent,save_size_name)
         self.l = l = QVBoxLayout()
@@ -1435,9 +1462,9 @@ class ViewLog(SizePersistedDialog):
             label.setToolTip(_('Click to go to line %s')%lineno)
             label.mouseReleaseEvent = partial(self.label_clicked, lineno=lineno)
             self.l.addWidget(label)
-        
+
         # html='<p>'+'</p><p>'.join([ '(lineno: %s) %s'%e for e in errors ])+'</p>'
-        
+
         # self.tb = QTextBrowser(self)
         # self.tb.setFont(QFont("Courier",
         #                       parent.font().pointSize()+1))
@@ -1455,13 +1482,13 @@ class ViewLog(SizePersistedDialog):
         saveanyway = QPushButton(_('Save Anyway'), self)
         saveanyway.clicked.connect(self.reject)
         horz.addWidget(saveanyway)
-        
+
         l.addLayout(horz)
         self.setModal(False)
         self.setWindowTitle(title)
         self.setWindowIcon(QIcon(I('debug.png')))
         #self.show()
-        
+
         # Cause our dialog size to be restored from prefs or created on first usage
         self.resize_dialog()
 
@@ -1482,7 +1509,7 @@ class EmailPassDialog(QDialog):
 
         self.setWindowTitle(_('Password'))
         self.l.addWidget(QLabel(_("Enter Email Password for %s:")%user),0,0,1,2)
-   
+
         # self.l.addWidget(QLabel(_("Password:")),1,0)
         self.passwd = QLineEdit(self)
         self.passwd.setEchoMode(QLineEdit.Password)

calibre-plugin/fff_plugin.py

@@ -10,7 +10,7 @@ __docformat__ = 'restructuredtext en'
 import logging
 logger = logging.getLogger(__name__)
 
-import time, os, copy, threading, re, platform, sys
+import os, copy, threading, re, platform, sys
 from StringIO import StringIO
 from functools import partial
 from datetime import datetime, time, date
@@ -454,6 +454,10 @@ class FanFicFarePlugin(InterfaceAction):
                                       imap_pass,
                                       prefs['imapfolder'],
                                       prefs['imapmarkread'],)
+
+        ## reject will now be redundant with reject check inside
+        ## prep_downloads because of change-able story URLs.
+        ## Keeping here to because it's the far more common case.
         reject_list=set()
         if prefs['auto_reject_from_email']:
             # need to normalize for reject list.
@@ -466,8 +470,14 @@ class FanFicFarePlugin(InterfaceAction):
         if prefs['download_from_email_immediately']:
             ## do imap fetch w/o GUI elements
             if url_list:
-                self.prep_downloads(self.add_new_dialog.get_fff_options(),
-                                    "\n".join(url_list))
+                self.prep_downloads({
+                        'fileform': prefs['fileform'],
+                        'collision': prefs['collision'],
+                        'updatemeta': prefs['updatemeta'],
+                        'bgmeta': False,
+                        'updateepubcover': prefs['updateepubcover'],
+                        'smarten_punctuation':prefs['smarten_punctuation']
+                        },"\n".join(url_list))
             else:
                 self.gui.status_bar.show_message(_('Finished Fetching Story URLs from Email.'),3000)
                 
@@ -919,11 +929,25 @@ class FanFicFarePlugin(InterfaceAction):
             options['tdir']=tdir
 
         if 0 < len(filter(lambda x : x['good'], books)):
-            self.gui.status_bar.show_message(_('Started fetching metadata for %s stories.')%len(books), 3000)
+            if options['bgmeta']:
+                status_bar=_('Start queuing downloading for %s stories.')%len(books)
+                init_label=_("Queuing download for stories...")
+                win_title=_("Queuing download for stories")
+                status_prefix=_("Queued download for")
+            else:
+                status_bar=_('Started fetching metadata for %s stories.')%len(books)
+                init_label=_("Fetching metadata for stories...")
+                win_title=_("Downloading metadata for stories")
+                status_prefix=_("Fetched metadata for")
+                
+            self.gui.status_bar.show_message(status_bar, 3000)
             LoopProgressDialog(self.gui,
                                books,
                                partial(self.prep_download_loop, options = options, merge=merge),
-                               partial(self.start_download_job, options = options, merge=merge))
+                               partial(self.start_download_job, options = options, merge=merge),
+                               init_label=init_label,
+                               win_title=win_title,
+                               status_prefix=status_prefix)
         else:
             self.gui.status_bar.show_message(_('No valid story URLs entered.'), 3000)
         # LoopProgressDialog calls prep_download_loop for each 'good' story,
@@ -931,10 +955,48 @@ class FanFicFarePlugin(InterfaceAction):
         # LoopProgressDialog calls start_download_job at the end which goes
         # into the BG, or shows list if no 'good' books.
 
+    def reject_url(self,merge,book):
+        url = book['url']
+        if not merge and rejecturllist.check(url): # skip reject list when merging.
+            rejnote = rejecturllist.get_full_note(url)
+            if prefs['reject_always'] or question_dialog(self.gui, _('Reject URL?'),'''
+                      <h3>%s</h3>
+                      <p>%s</p>
+                      <p>"<b>%s</b>"</p>
+                      <p>%s</p>
+                      <p>%s</p>'''%(
+                    _('Reject URL?'),
+                    _('<b>%s</b> is on your Reject URL list:')%url,
+                    rejnote,
+                    _("Click '<b>Yes</b>' to Reject."),
+                    _("Click '<b>No</b>' to download anyway.")),
+                               show_copy_button=False):
+                book['comment'] = _("Story on Reject URLs list (%s).")%rejnote
+                book['good']=False
+                book['icon']='rotate-right.png'
+                book['status'] = _('Rejected')
+                return True
+            else:
+                if question_dialog(self.gui, _('Remove Reject URL?'),'''
+                          <h3>%s</h3>
+                          <p>%s</p>
+                          <p>"<b>%s</b>"</p>
+                          <p>%s</p>
+                          <p>%s</p>'''%(
+                        _("Remove URL from Reject List?"),
+                        _('<b>%s</b> is on your Reject URL list:')%url,
+                        rejnote,
+                        _("Click '<b>Yes</b>' to remove it from the list,"),
+                        _("Click '<b>No</b>' to leave it on the list.")),
+                                   show_copy_button=False):
+                    rejecturllist.remove(url)
+        return False
+            
     def prep_download_loop(self,book,
                            options={'fileform':'epub',
                                     'collision':ADDNEW,
                                     'updatemeta':True,
+                                    'bgmeta':False,
                                     'updateepubcover':True},
                            merge=False):
         '''
@@ -947,40 +1009,11 @@ class FanFicFarePlugin(InterfaceAction):
         logger.debug("url:%s"%url)
         mi = None
 
-        if not merge: # skip reject list when merging.
-            if rejecturllist.check(url):
-                rejnote = rejecturllist.get_full_note(url)
-                if prefs['reject_always'] or question_dialog(self.gui, _('Reject URL?'),'''
-                          <h3>%s</h3>
-                          <p>%s</p>
-                          <p>"<b>%s</b>"</p>
-                          <p>%s</p>
-                          <p>%s</p>'''%(
-                        _('Reject URL?'),
-                        _('<b>%s</b> is on your Reject URL list:')%url,
-                        rejnote,
-                        _("Click '<b>Yes</b>' to Reject."),
-                        _("Click '<b>No</b>' to download anyway.")),
-                                   show_copy_button=False):
-                    book['comment'] = _("Story on Reject URLs list (%s).")%rejnote
-                    book['good']=False
-                    book['icon']='rotate-right.png'
-                    book['status'] = _('Rejected')
-                    return
-                else:
-                    if question_dialog(self.gui, _('Remove Reject URL?'),'''
-                              <h3>%s</h3>
-                              <p>%s</p>
-                              <p>"<b>%s</b>"</p>
-                              <p>%s</p>
-                              <p>%s</p>'''%(
-                            _("Remove URL from Reject List?"),
-                            _('<b>%s</b> is on your Reject URL list:')%url,
-                            rejnote,
-                            _("Click '<b>Yes</b>' to remove it from the list,"),
-                            _("Click '<b>No</b>' to leave it on the list.")),
-                                       show_copy_button=False):
-                        rejecturllist.remove(url)
+        ## Check reject list.  Redundant with below for when story URL
+        ## changes, but also kept here to avoid network hit in most
+        ## common case where given url is story url.
+        if self.reject_url(merge,book):
+            return
 
         # The current database shown in the GUI
         # db is an instance of the class LibraryDatabase2 from database.py
@@ -991,6 +1024,7 @@ class FanFicFarePlugin(InterfaceAction):
         fileform  = options['fileform']
         collision = options['collision']
         updatemeta= options['updatemeta']
+        bgmeta= options['bgmeta']
         updateepubcover= options['updateepubcover']
 
         # Dialogs should prevent this case now.
@@ -1036,9 +1070,11 @@ class FanFicFarePlugin(InterfaceAction):
                 if savedmetadata:
                     # sets flag inside story so getStoryMetadataOnly won't hit server.
                     adapter.setStoryMetadata(savedmetadata)
-                
+
             # let other exceptions percolate up.
+            # bgmeta doesn't work with CALIBREONLY.
             story = adapter.getStoryMetadataOnly(get_cover=False)
+            bgmeta = False
         else:
             # reduce foreground sleep time for ffnet when few books.
             if 'ffnetcount' in options and \
@@ -1052,74 +1088,66 @@ class FanFicFarePlugin(InterfaceAction):
                 slp = min(maxslp,m*float(options['ffnetcount'])+b)
                 #print("m:%s b:%s = %s"%(m,b,slp))
                 adapter.set_sleep(slp)
-    
-            ## three tries, that's enough if both user/pass & is_adult needed,
-            ## or a couple tries of one or the other
-            for x in range(0,2):
-                try:
-                    adapter.getStoryMetadataOnly(get_cover=False)
-                except exceptions.FailedToLogin, f:
-                    logger.warn("Login Failed, Need Username/Password.")
-                    userpass = UserPassDialog(self.gui,url,f)
-                    userpass.exec_() # exec_ will make it act modal
-                    if userpass.status:
-                        adapter.username = userpass.user.text()
-                        adapter.password = userpass.passwd.text()
-    
-                except exceptions.AdultCheckRequired:
-                    if question_dialog(self.gui, _('Are You an Adult?'), '<p>'+
-                                       _("%s requires that you be an adult.  Please confirm you are an adult in your locale:")%url,
-                                       show_copy_button=False):
-                        adapter.is_adult=True
-    
-            # let other exceptions percolate up.
-            story = adapter.getStoryMetadataOnly(get_cover=False)
-    
-            series = story.getMetadata('series')
-            if not merge and series and prefs['checkforseriesurlid']:
-                # try to find *series anthology* by *seriesUrl* identifier url or uri first.
-                identicalbooks = self.do_id_search(story.getMetadata('seriesUrl'))
-                # print("identicalbooks:%s"%identicalbooks)
-                if len(identicalbooks) > 0 and question_dialog(self.gui, _('Skip Story?'),'''
-                                                                  <h3>%s</h3>
-                                                                  <p>%s</p>
-                                                                  <p>%s</p>
-                                                                  <p>%s</p>
-                                                               '''%(
-                                                               _('Skip Anthology Story?'),
-                                                               _('"<b>%s</b>" is in series "<b><a href="%s">%s</a></b>" that you have an anthology book for.')%(story.getMetadata('title'),story.getMetadata('seriesUrl'),series[:series.index(' [')]),
-                                                               _("Click '<b>Yes</b>' to Skip."),
-                                                               _("Click '<b>No</b>' to download anyway.")),
-                                                               show_copy_button=False):
-                    book['comment'] = _("Story in Series Anthology(%s).")%series
-                    book['title'] = story.getMetadata('title')
-                    book['author'] = [story.getMetadata('author')]
-                    book['good']=False
-                    book['icon']='rotate-right.png'
-                    book['status'] = _('Skipped')
-                    return
 
-        ################################################################################################################################################33
-
-        # set PI version instead of default.
-        if 'version' in options:
-            story.setMetadata('version',options['version'])
-
-        # all_metadata duplicates some data, but also includes extra_entries, etc.
-        book['all_metadata'] = story.getAllMetadata(removeallentities=True)
-        if prefs['savemetacol'] != '':
-            # get metadata to save in configured column.
-            book['savemetacol'] = story.dump_html_metadata()
+            if not bgmeta:
+                ## three tries, that's enough if both user/pass & is_adult needed,
+                ## or a couple tries of one or the other
+                for x in range(0,2):
+                    try:
+                        adapter.getStoryMetadataOnly(get_cover=False)
+                    except exceptions.FailedToLogin, f:
+                        logger.warn("Login Failed, Need Username/Password.")
+                        userpass = UserPassDialog(self.gui,url,f)
+                        userpass.exec_() # exec_ will make it act modal
+                        if userpass.status:
+                            adapter.username = userpass.user.text()
+                            adapter.password = userpass.passwd.text()
         
-        book['title'] = story.getMetadata("title", removeallentities=True)
-        book['author_sort'] = book['author'] = story.getList("author", removeallentities=True)
-        book['publisher'] = story.getMetadata("site")
-        book['tags'] = story.getSubjectTags(removeallentities=True)
-        if story.getMetadata("description"):
-            book['comments'] = sanitize_comments_html(story.getMetadata("description"))
-        else:
-            book['comments']=''
-        book['series'] = story.getMetadata("series", removeallentities=True)
+                    except exceptions.AdultCheckRequired:
+                        if question_dialog(self.gui, _('Are You an Adult?'), '<p>'+
+                                           _("%s requires that you be an adult.  Please confirm you are an adult in your locale:")%url,
+                                           show_copy_button=False):
+                            adapter.is_adult=True
+        
+                # let other exceptions percolate up.
+                story = adapter.getStoryMetadataOnly(get_cover=False)
+                book['title'] = story.getMetadata('title')
+                book['author'] = [story.getMetadata('author')]
+                book['url'] = story.getMetadata('storyUrl')
+        
+            ## Check reject list.  Redundant with below for when story
+            ## URL changes, but also kept here to avoid network hit in
+            ## most common case where given url is story url.
+            if self.reject_url(merge,book):
+                return
+
+            if not bgmeta:
+                series = story.getMetadata('series')
+                if not merge and series and prefs['checkforseriesurlid']:
+                    # try to find *series anthology* by *seriesUrl* identifier url or uri first.
+                    identicalbooks = self.do_id_search(story.getMetadata('seriesUrl'))
+                    # print("identicalbooks:%s"%identicalbooks)
+                    if len(identicalbooks) > 0 and question_dialog(self.gui, _('Skip Story?'),'''
+                                                                      <h3>%s</h3>
+                                                                      <p>%s</p>
+                                                                      <p>%s</p>
+                                                                      <p>%s</p>
+                                                                   '''%(
+                                                                   _('Skip Anthology Story?'),
+                                                                   _('"<b>%s</b>" is in series "<b><a href="%s">%s</a></b>" that you have an anthology book for.')%(story.getMetadata('title'),story.getMetadata('seriesUrl'),series[:series.index(' [')]),
+                                                                   _("Click '<b>Yes</b>' to Skip."),
+                                                                   _("Click '<b>No</b>' to download anyway.")),
+                                                                   show_copy_button=False):
+                        book['comment'] = _("Story in Series Anthology(%s).")%series
+                        book['title'] = story.getMetadata('title')
+                        book['author'] = [story.getMetadata('author')]
+                        book['url'] = story.getMetadata('storyUrl')
+                        book['good']=False
+                        book['icon']='rotate-right.png'
+                        book['status'] = _('Skipped')
+                        return
+    
+        ################################################################################################################################################33
 
         book['is_adult'] = adapter.is_adult
         book['username'] = adapter.username
@@ -1127,15 +1155,38 @@ class FanFicFarePlugin(InterfaceAction):
 
         book['icon'] = 'plus.png'
         book['status'] = _('Add')
-        if story.getMetadataRaw('datePublished'):
-            book['pubdate'] = story.getMetadataRaw('datePublished').replace(tzinfo=local_tz)
-        if story.getMetadataRaw('dateUpdated'):
-            book['updatedate'] = story.getMetadataRaw('dateUpdated').replace(tzinfo=local_tz)
-        if story.getMetadataRaw('dateCreated'):
-            book['timestamp'] = story.getMetadataRaw('dateCreated').replace(tzinfo=local_tz)
-        else:
-            book['timestamp'] = None # need *something* there for calibre.
+        
+        if not bgmeta:
+            # set PI version instead of default.
+            if 'version' in options:
+                story.setMetadata('version',options['version'])
 
+            # all_metadata duplicates some data, but also includes extra_entries, etc.
+            book['all_metadata'] = story.getAllMetadata(removeallentities=True)
+            if prefs['savemetacol'] != '':
+                # get metadata to save in configured column.
+                book['savemetacol'] = story.dump_html_metadata()
+            
+            book['title'] = story.getMetadata("title", removeallentities=True)
+            book['author_sort'] = book['author'] = story.getList("author", removeallentities=True)
+            book['publisher'] = story.getMetadata("site")
+            book['url'] = story.getMetadata("storyUrl")
+            book['tags'] = story.getSubjectTags(removeallentities=True)
+            if story.getMetadata("description"):
+                book['comments'] = sanitize_comments_html(story.getMetadata("description"))
+            else:
+                book['comments']=''
+            book['series'] = story.getMetadata("series", removeallentities=True)
+    
+            if story.getMetadataRaw('datePublished'):
+                book['pubdate'] = story.getMetadataRaw('datePublished').replace(tzinfo=local_tz)
+            if story.getMetadataRaw('dateUpdated'):
+                book['updatedate'] = story.getMetadataRaw('dateUpdated').replace(tzinfo=local_tz)
+            if story.getMetadataRaw('dateCreated'):
+                book['timestamp'] = story.getMetadataRaw('dateCreated').replace(tzinfo=local_tz)
+            else:
+                book['timestamp'] = None # need *something* there for calibre.
+    
         if not merge:# skip all the collision code when d/ling for merging.
             if collision in (CALIBREONLY, CALIBREONLYSAVECOL):
                 book['icon'] = 'metadata.png'
@@ -1159,9 +1210,7 @@ class FanFicFarePlugin(InterfaceAction):
                 # print("identicalbooks:%s"%identicalbooks)
                 if len(identicalbooks) < 1 and prefs['matchtitleauth']:
                     # find dups
-                    authlist = story.getList("author", removeallentities=True)
-                    mi = MetaInformation(story.getMetadata("title", removeallentities=True),
-                                         authlist)
+                    mi = MetaInformation(book['title'],book['author'])
                     identicalbooks = db.find_identical_books(mi)
                     if len(identicalbooks) > 0:
                         logger.debug("existing found by title/author(s)")
@@ -1238,7 +1287,7 @@ class FanFicFarePlugin(InterfaceAction):
 
                 ## newer/chaptercount checks are the same for both:
                 # Update epub, but only if more chapters.
-                if collision in (UPDATE,UPDATEALWAYS): # collision == UPDATE
+                if not bgmeta and collision in (UPDATE,UPDATEALWAYS): # collision == UPDATE
                     # 'book' can exist without epub.  If there's no existing epub,
                     # let it go and it will download it.
                     if db.has_format(book_id,fileform,index_is_id=True):
@@ -1256,17 +1305,17 @@ class FanFicFarePlugin(InterfaceAction):
 
                 if collision == OVERWRITE and \
                         db.has_format(book_id,formmapping[fileform],index_is_id=True):
-                    # check make sure incoming is newer.
-                    lastupdated=story.getMetadataRaw('dateUpdated')
                     fileupdated=datetime.fromtimestamp(os.stat(db.format_abspath(book_id, formmapping[fileform], index_is_id=True))[8])
-
-                    # updated doesn't have time (or is midnight), use dates only.
-                    # updated does have time, use full timestamps.
-                    if (lastupdated.time() == time.min and fileupdated.date() > lastupdated.date()) or \
-                            (lastupdated.time() != time.min and fileupdated > lastupdated):
-                        raise NotGoingToDownload(_("Not Overwriting, web site is not newer."),'edit-undo.png')
-
-
+                    book['fileupdated']=fileupdated
+                    if not bgmeta:
+                        # check make sure incoming is newer.
+                        lastupdated=story.getMetadataRaw('dateUpdated')
+    
+                        # updated doesn't have time (or is midnight), use dates only.
+                        # updated does have time, use full timestamps.
+                        if (lastupdated.time() == time.min and fileupdated.date() > lastupdated.date()) or \
+                                (lastupdated.time() != time.min and fileupdated > lastupdated):
+                            raise NotGoingToDownload(_("Not Overwriting, web site is not newer."),'edit-undo.png')
 
                 # For update, provide a tmp file copy of the existing epub so
                 # it can't change underneath us.  Now also overwrite for logpage preserve.
@@ -1337,7 +1386,11 @@ class FanFicFarePlugin(InterfaceAction):
             # For HTML format users, make the filename inside the zip something reasonable.
             # For crazy long titles/authors, limit it to 200chars.
             # For weird/OS-unsafe characters, use file safe only.
-            tmp = PersistentTemporaryFile(prefix=story.formatFileName("${title}-${author}-",allowunsafefilename=False)[:100],
+            try:
+                prefix = story.formatFileName("${title}-${author}-",allowunsafefilename=False)[:100]
+            except NameError:
+                prefix = "bgmeta-"
+            tmp = PersistentTemporaryFile(prefix=prefix,
                                           suffix='.'+options['fileform'],
                                           dir=options['tdir'])
             logger.debug("title:"+book['title'])
@@ -1350,6 +1403,7 @@ class FanFicFarePlugin(InterfaceAction):
                             options={'fileform':'epub',
                                      'collision':ADDNEW,
                                      'updatemeta':True,
+                                     'bgmeta':False,
                                      'updateepubcover':True},
                             merge=False):
         '''
@@ -1415,7 +1469,7 @@ class FanFicFarePlugin(InterfaceAction):
         func = 'arbitrary_n'
         cpus = self.gui.job_manager.server.pool_size
         args = ['calibre_plugins.fanficfare_plugin.jobs', 'do_download_worker',
-                (book_list, options, cpus)]
+                (book_list, options, cpus, merge)]
         desc = _('Download FanFiction Book')
         job = self.gui.job_manager.run_job(
                 self.Dispatcher(partial(self.download_list_completed,options=options,merge=merge)),
@@ -1429,6 +1483,7 @@ class FanFicFarePlugin(InterfaceAction):
                      options={'fileform':'epub',
                               'collision':ADDNEW,
                               'updatemeta':True,
+                              'bgmeta':False,
                               'updateepubcover':True}):
         custom_columns = self.gui.library_view.model().custom_columns
         if book['calibre_id'] and prefs['errorcol'] != '' and prefs['errorcol'] in custom_columns:
@@ -1936,7 +1991,8 @@ class FanFicFarePlugin(InterfaceAction):
 
             author_id_to_link_map = dict()
             for i, author in enumerate(authorlist):
-                author_id_to_link_map[authorids[author]] = authurls[i]
+                if len(authurls) > i:
+                    author_id_to_link_map[authorids[author]] = authurls[i]
 
             # print("author_id_to_link_map:%s\n\n"%author_id_to_link_map)
             db.new_api.set_link_for_authors(author_id_to_link_map)
@@ -2132,8 +2188,10 @@ class FanFicFarePlugin(InterfaceAction):
         book['comment'] = '' # note this is a comment on the d/l or update.
         book['url'] = ''
         book['site'] = ''
+        book['series'] = ''
         book['added'] = False
         book['pubdate'] = None
+        book['publisher'] = None
         return book
 
     def convert_urls_to_books(self, urls):

calibre-plugin/jobs.py

@@ -10,12 +10,15 @@ __docformat__ = 'restructuredtext en'
 import logging
 logger = logging.getLogger(__name__)
 
-import time, traceback
+import traceback
+from datetime import time
 from StringIO import StringIO
     
 from calibre.utils.ipc.server import Server
 from calibre.utils.ipc.job import ParallelJob
 from calibre.constants import numeric_version as calibre_version
+from calibre.utils.date import local_tz
+from calibre.library.comments import sanitize_comments_html
 
 # ------------------------------------------------------------------------------
 #
@@ -23,8 +26,11 @@ from calibre.constants import numeric_version as calibre_version
 #
 # ------------------------------------------------------------------------------
 
-def do_download_worker(book_list, options,
-                       cpus, notification=lambda x,y:x):
+def do_download_worker(book_list,
+                       options,
+                       cpus,
+                       merge=False,
+                       notification=lambda x,y:x):
     '''
     Master job, to launch child jobs to extract ISBN for a set of books
     This is run as a worker job in the background to keep the UI more
@@ -44,7 +50,7 @@ def do_download_worker(book_list, options,
             total += 1
             args = ['calibre_plugins.fanficfare_plugin.jobs',
                     'do_download_for_worker',
-                    (book,options)]
+                    (book,options,merge)]
             job = ParallelJob('arbitrary_n',
                               "url:(%s) id:(%s)"%(book['url'],book['calibre_id']),
                               done=None,
@@ -90,7 +96,7 @@ def do_download_worker(book_list, options,
     # return the book list as the job result
     return book_list
 
-def do_download_for_worker(book,options,notification=lambda x,y:x):
+def do_download_for_worker(book,options,merge,notification=lambda x,y:x):
     '''
     Child job, to download story when run as a worker job
     '''
@@ -147,6 +153,26 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
             if 'version' in options:
                 story.setMetadata('version',options['version'])
                 
+            book['title'] = story.getMetadata("title", removeallentities=True)
+            book['author_sort'] = book['author'] = story.getList("author", removeallentities=True)
+            book['publisher'] = story.getMetadata("site")
+            book['url'] = story.getMetadata("storyUrl")
+            book['tags'] = story.getSubjectTags(removeallentities=True)
+            if story.getMetadata("description"):
+                book['comments'] = sanitize_comments_html(story.getMetadata("description"))
+            else:
+                book['comments']=''
+            book['series'] = story.getMetadata("series", removeallentities=True)
+    
+            if story.getMetadataRaw('datePublished'):
+                book['pubdate'] = story.getMetadataRaw('datePublished').replace(tzinfo=local_tz)
+            if story.getMetadataRaw('dateUpdated'):
+                book['updatedate'] = story.getMetadataRaw('dateUpdated').replace(tzinfo=local_tz)
+            if story.getMetadataRaw('dateCreated'):
+                book['timestamp'] = story.getMetadataRaw('dateCreated').replace(tzinfo=local_tz)
+            else:
+                book['timestamp'] = None # need *something* there for calibre.
+                
             writer = writers.getWriter(options['fileform'],configuration,adapter)
     
             outfile = book['outfile']
@@ -165,12 +191,22 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
     
                 # preserve logfile even on overwrite.
                 if 'epub_for_update' in book:
-                    
                     adapter.logfile = get_update_data(book['epub_for_update'])[6]
                     # change the existing entries id to notid so
                     # write_epub writes a whole new set to indicate overwrite.
                     if adapter.logfile:
                         adapter.logfile = adapter.logfile.replace("span id","span notid")
+
+                if options['collision'] == OVERWRITE and 'fileupdated' in book:
+                    lastupdated=story.getMetadataRaw('dateUpdated')
+                    fileupdated=book['fileupdated']
+
+                    # updated doesn't have time (or is midnight), use dates only.
+                    # updated does have time, use full timestamps.
+                    if (lastupdated.time() == time.min and fileupdated.date() > lastupdated.date()) or \
+                            (lastupdated.time() != time.min and fileupdated > lastupdated):
+                        raise NotGoingToDownload(_("Not Overwriting, web site is not newer."),'edit-undo.png')
+
                 
                 logger.info("write to %s"%outfile)
                 inject_cal_cols(book,story,configuration)
@@ -199,17 +235,20 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
                 # dup handling from fff_plugin needed for anthology updates.
                 if options['collision'] == UPDATE:
                     if chaptercount == urlchaptercount:
-                        book['comment']=_("Already contains %d chapters.  Reuse as is.")%chaptercount
-                        book['all_metadata'] = story.getAllMetadata(removeallentities=True)
-                        if options['savemetacol'] != '':
-                            book['savemetacol'] = story.dump_html_metadata()
-                        book['outfile'] = book['epub_for_update'] # for anthology merge ops.
-                        return book
-    
-                # dup handling from fff_plugin needed for anthology updates.
-                if chaptercount > urlchaptercount:
-                    raise NotGoingToDownload(_("Existing epub contains %d chapters, web site only has %d. Use Overwrite to force update.") % (chaptercount,urlchaptercount),'dialog_error.png')
-    
+                        if merge:
+                            book['comment']=_("Already contains %d chapters.  Reuse as is.")%chaptercount
+                            book['all_metadata'] = story.getAllMetadata(removeallentities=True)
+                            if options['savemetacol'] != '':
+                                book['savemetacol'] = story.dump_html_metadata()
+                            book['outfile'] = book['epub_for_update'] # for anthology merge ops.
+                            return book
+                        else: # not merge,
+                            raise NotGoingToDownload(_("Already contains %d chapters.")%chaptercount,'edit-undo.png')
+                    elif chaptercount > urlchaptercount:
+                        raise NotGoingToDownload(_("Existing epub contains %d chapters, web site only has %d. Use Overwrite to force update.") % (chaptercount,urlchaptercount),'dialog_error.png')
+                    elif chaptercount == 0:
+                        raise NotGoingToDownload(_("FanFicFare doesn't recognize chapters in existing epub, epub is probably from a different source. Use Overwrite to force update."),'dialog_error.png')
+                    
                 if not (options['collision'] == UPDATEALWAYS and chaptercount == urlchaptercount) \
                         and adapter.getConfig("do_update_hook"):
                     chaptercount = adapter.hookForUpdates(chaptercount)

calibre-plugin/plugin-defaults.ini

@@ -163,20 +163,29 @@ connect_timeout:60.0
 ## For example, you could change Sci-Fi=>SF, remove *-Centered tags,
 ## etc.  See http://docs.python.org/library/re.html (look for re.sub)
 ## for regexp details.
+##
 ## Make sure to keep at least one space at the start of each line and
 ## to escape % to %%, if used.
+##
 ## Two, three or five part lines.  Two part effect everything.
 ## Three part effect only those key(s) lists.
 ## *Five* part lines.  Effect only when trailing conditional key=>regexp matches
 ## metakey[,metakey]=>pattern=>replacement[&&conditionalkey=>regexp]
+##
 ## Note that if metakey == conditionalkey the conditional is ignored.
 ## You can use \s in the replacement to add explicit spaces.  (The config parser
 ## tends to discard trailing spaces.)
+##
 ## replace_metadata <entry>_LIST options: FanFicFare replace_metadata lines
 ## operate on individual list items for list entries. But if you
 ## want to do a replacement on the joined string for the whole list,
 ## you can by using <entry>_LIST. Example, if you added
 ## calibre_author: calibre_author_LIST=>^(.{,100}).*$=>\1
+##
+## You can 'split' one list item into multiple list entries by using
+## \' in the replacement string.
+##
+## Examples:
 #replace_metadata:
 # genre,category=>Sci-Fi=>SF
 # Puella Magi Madoka Magica.* => Madoka
@@ -186,6 +195,8 @@ connect_timeout:60.0
 # .*-Centered=>
 # characters=>Sam W\.=>Sam Witwicky&&category=>Transformers
 # characters=>Sam W\.=>Sam Winchester&&category=>Supernatural
+# category=>Bitextual=>M/M\,F/M
+
 
 ## Include/Exclude metadata
 ##
@@ -210,7 +221,7 @@ connect_timeout:60.0
 ##
 ## This is fairly complicated, so it's documented on its own wiki
 ## page:
-## https://code.google.com/p/fanficdownloader/wiki/InExcludeMetadataFeature
+## https://github.com/JimmXinu/FanFicFare/wiki/InExcludeMetadataFeature
 
 ## Some readers don't show horizontal rule (<hr />) tags correctly.
 ## This replaces them all with a centered '* * *'.  (Note centering
@@ -368,21 +379,21 @@ user_agent:FFF/2.X
 bulk_load:true
 
 [base_xenforoforum]
-## Currently only forums.spacebattles.com and forums.sufficientvelocity.com
 
-cover_exclusion_regexp:/clear.png
+cover_exclusion_regexp:/styles/
 
 ## I saw lots of chapters name simply '1.1' etc during testing.
 strip_chapter_numbers:false
 
 ## Copy title to tagsfromtitle for parsing tags.
-add_to_extra_valid_entries:,tagsfromtitle
+add_to_extra_valid_entries:,tagsfromtitle,forumtags
 
 ## '.NOREPL' tells the system to *not* apply title's
 ## in/exclude/replace_metadata -- Only works on include_in_ lines.
 include_in_tagsfromtitle:title.NOREPL
 
 tagsfromtitle_label:Tags from Title
+forumtags_label:Tags from Forum
 
 ## might want to do this, maybe not.  Will often include category, but
 ## also often include non-category stuff.
@@ -391,26 +402,40 @@ tagsfromtitle_label:Tags from Title
 add_to_include_metadata_pre:
 # only keep tagsfromtitle with ( or [ in.
  tagsfromtitle=~[\[\(]
- 
+
+## disable chapter range in title because of tagsfromtitle processing.
+title_chapter_range_pattern:
+
 add_to_replace_metadata:
+# for QuestionableQuesting NSFW subforum.
+ tagsfromtitle=>^\[NSFW\].*?([\(\[]([^\]\)]+)[\)\]]).*?$=>NSFW,\2
 # remove anything outside () or []
- tagsfromtitle=>^.*?([\(\[]([^\]\)]+)[\)\]]).*?$=>\1
+ tagsfromtitle=>^.*?([\(\[]([^\]\)]+)[\)\]]).*?$=>\2
 # remove () []
- tagsfromtitle=>[\(\)\[\]]=>
+# tagsfromtitle=>[\(\)\[\]]=>
 # change (spaces)slash(or semicolon)(spaces) to comma
  tagsfromtitle=> *[/;] *=>,
- tagsfromtitle=> x =>,
- 
+ tagsfromtitle=> [xX] =>,
+
 # remove [] or () blocks and leading/trailing spaces/dashes/colons
  title=>[-: ]*[\(\[]([^\]\)]+)[\)\]][-: ]*=>
 # remove 'Thread' and the next word, usually "Thread 2", "Thread
-# four", "Thread iv", etc
- title=>[-: ]*[Tt]hread [^ ]+[-: ]*=>
+# four", "Thread iv", "Story Thread", etc
+ title,tagsfromtitle=>[-: ]*(Story *)?[Tt]hread [^ ]+[-: ]*=>
 
-add_to_extra_titlepage_entries:,tagsfromtitle
+# Normalize 'fanfiction/fanfic/fan-fiction' a little.
+ forumtags=>[Ff]an-?[Ff]ic(tion)?=>FanFiction
 
+add_to_extra_titlepage_entries:,tagsfromtitle,forumtags
+
+## XenForo tags are all lowercase everywhere that I've seen.  This
+## makes the first letter of each word uppercase.  Applied before
+## replace_metadata.
+capitalize_forumtags:true
+
+## Add both title tags and forumtags to standard (subject) tags.
 ## '.SPLIT' tells the system to split by ','
-add_to_include_subject_tags:,tagsfromtitle.SPLIT
+add_to_include_subject_tags:,tagsfromtitle.SPLIT,forumtags
 
 ## base_xenforoforum reads Published and Updated datetimes from
 ## Threadmarks if used, or from the posted & updated times of the
@@ -422,6 +447,13 @@ dateUpdated_format:%%Y-%%m-%%d %%H:%%M:%%S
 ## the description.
 description_limit:500
 
+## Because base_xenforoforum adapters can pull chapter URLs from human
+## posts, the odds of errors in the chapter URLs are vastly higher.
+## You can set continue_on_chapter_error:true to continue on after
+## failing to download a chapter and instead record an error message
+## in the ebook for that chapter.
+continue_on_chapter_error:false
+
 ## Each output format has a section that overrides [defaults]
 [html]
 
@@ -614,6 +646,7 @@ nook_img_fix:true
 ## URLs like: http://test1.com?sid=12345
 [test1.com]
 extratags: FanFiction,Testing
+
 # extracategories:Fafner
 # extragenres:Romance,Fluff
 # extracharacters:Reginald Smythe-Smythe,Mokona,Harry P.
@@ -854,12 +887,6 @@ extracategories:Buffy: The Vampire Slayer
 extracharacters:Buffy, Spike
 extraships:Spike/Buffy
 
-[devianthearts.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
-
 [dramione.org]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -1265,7 +1292,7 @@ extracategories:NCIS
 extracategories:Buffy: The Vampire Slayer
 extracharacters:Willow
 
-[ninelives.dark-solace.org]
+[ninelivesarchive.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:The Walking Dead
 extracharacters:Carol,Daryl
@@ -1344,6 +1371,16 @@ extracategories:My Little Pony: Friendship is Magic
 ## Site dedicated to these categories/characters/ships
 extracategories:The Pretender
 
+[forum.questionablequesting.com]
+## see [base_xenforoforum]
+
+## 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
+
 [samandjack.net]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -1513,22 +1550,6 @@ readings_label: Readings
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
-[thequidditchpitch.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
-
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-
 [tokra.fandomnet.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
@@ -1871,6 +1892,15 @@ rating_titles: R=RESTRICTED (16+), E=EXEMPT (18+), I=ART HOUSE, T=To every, A=IN
 adult_ratings: E,R
 
 [www.mediaminer.org]
+dateUpdated_format:%%Y-%%m-%%d %%H:%%M:%%S
+## Note that mediaminer doesn't give datePublished on the story's
+## index page--it's collected from the earliest uploaded chapter.  So
+## it's not available when only fetching metadata.
+datePublished_format:%%Y-%%m-%%d %%H:%%M:%%S
+
+## some sites include images that we don't ever want becoming the
+## cover image.  This lets you exclude them.
+cover_exclusion_regexp:/img/rss.png
 
 [www.midnightwhispers.ca]
 ## Some sites do not require a login, but do require the user to
@@ -1889,7 +1919,7 @@ cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
 ## Site dedicated to these categories/characters/ships
 extracategories:NCIS
 
-[www.nickandgreg.net]
+[www.nickngreg.nl]
 ## Site dedicated to these categories/characters/ships
 extracategories:CSI
 extraships:Nick Stokes/Greg Sanders
@@ -1938,6 +1968,13 @@ extracategories:Psych
 ## Site dedicated to these categories/characters/ships
 extracategories:Queer as Folk
 
+[quotev.com]
+extra_valid_entries:pages,readers,reads,favorites
+pages_label:Pages
+readers_label:Readers
+reads_label:Reads
+favorites_label:Favorites
+
 [www.restrictedsection.org]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In

calibre-plugin/prefs.py

@@ -59,6 +59,7 @@ Dup from another site'''
 default_prefs['reject_always'] = False
 
 default_prefs['updatemeta'] = True
+default_prefs['bgmeta'] = False
 default_prefs['updateepubcover'] = False
 default_prefs['keeptags'] = False
 default_prefs['suppressauthorsort'] = False

fanficfare/adapters/__init__.py

@@ -49,7 +49,6 @@ import adapter_ficbooknet
 import adapter_portkeyorg
 import adapter_mugglenetcom
 import adapter_hpfandomnet
-import adapter_thequidditchpitchorg
 import adapter_nfacommunitycom
 import adapter_midnightwhispersca
 import adapter_ksarchivecom
@@ -132,13 +131,14 @@ import adapter_csiforensicscom
 import adapter_lotrfanfictioncom
 import adapter_fhsarchivecom
 import adapter_fanfictionjunkiesde
-import adapter_devianthearts
 import adapter_tgstorytimecom
 import adapter_itcouldhappennet
 import adapter_forumsspacebattlescom
 import adapter_forumssufficientvelocitycom
-import adapter_ninelivesdarksolaceorg
+import adapter_forumquestionablequestingcom
+import adapter_ninelivesarchivecom
 import adapter_masseffect2in
+import adapter_quotevcom
 
 ## This bit of complexity allows adapters to be added by just adding
 ## importing.  It eliminates the long if/else clauses we used to need
@@ -238,8 +238,11 @@ def getClassFor(url):
         fixedurl = "http:%s"%url
     if not fixedurl.startswith("http"):
         fixedurl = "http://%s"%url
-    ## remove any trailing '#' locations.
-    fixedurl = re.sub(r"#.*$","",fixedurl)
+        
+    ## remove any trailing '#' locations, except for #post-12345 for
+    ## XenForo
+    if not "#post-" in fixedurl:
+        fixedurl = re.sub(r"#.*$","",fixedurl)
 
     parsedUrl = up.urlparse(fixedurl)
     domain = parsedUrl.netloc.lower()

fanficfare/adapters/adapter_bloodshedversecom.py

@@ -62,7 +62,7 @@ class BloodshedverseComAdapter(BaseSiteAdapter):
         return cls.READ_URL_TEMPLATE % 1234
 
     def getSiteURLPattern(self):
-        return re.escape(self.BASE_URL + 'stories.php?go=') + r'(read|chapters)\&no=\d+$'
+        return re.escape(self.BASE_URL + 'stories.php?go=') + r'(read|chapters)\&(amp;)?no=\d+$'
 
     # Override stripURLParameters so the "no" parameter won't get stripped
     @classmethod

fanficfare/adapters/adapter_darksolaceorg.py

@@ -16,321 +16,26 @@
 #
 
 # Software: eFiction
-import time
-import logging
-logger = logging.getLogger(__name__)
-import re
-import urllib2
+from base_efiction_adapter import BaseEfictionAdapter
 
-from .. import BeautifulSoup as bs
-from ..htmlcleanup import stripHTML
-from .. import exceptions as exceptions
+class DarkSolaceOrgAdapter(BaseEfictionAdapter):
 
-from base_adapter import BaseSiteAdapter,  makeDate
+    @staticmethod
+    def getSiteDomain():
+        return 'dark-solace.org'
 
+    @classmethod
+    def getPathToArchive(self):
+        return '/elysian'
+
+    @classmethod
+    def getSiteAbbrev(self):
+        return 'dksl'
+        
+    @classmethod
+    def getDateFormat(self):
+        return "%B %d, %Y"
+                           
 def getClass():
     return DarkSolaceOrgAdapter
-
-# Class name has to be unique.  Our convention is camel case the
-# sitename with Adapter at the end.  www is skipped.
-class DarkSolaceOrgAdapter(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])
-        
-        
-        # normalized story URL.
-        self._setURL('http://' + self.getSiteDomain() + '/elysian/viewstory.php?sid='+self.story.getMetadata('storyId'))
-        
-        # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','dksl')
-
-        # 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 'dark-solace.org'
-        
-    @classmethod
-    def getAcceptDomains(cls):
-        return ['www.dark-solace.org','dark-solace.org']
-
-    @classmethod
-    def getSiteExampleURLs(cls):
-        return "http://"+cls.getSiteDomain()+"/elysian/viewstory.php?sid=1234"
-
-    def getSiteURLPattern(self):
-        return re.escape("http://")+"(www\.)?"+re.escape(self.getSiteDomain()+"/elysian/viewstory.php?sid=")+r"\d+$"
-
-    ## Login seems to be reasonably standard across eFiction sites.
-    def needToLoginCheck(self, data):
-        if 'This story contains adult content not suitable for children' in data \
-                or "That password doesn't match the one in our database" in data \
-                or "Registered Users Only" 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['action'] = 'login'
-        params['submit'] = 'Submit'
     
-        loginUrl = 'http://www.' + self.getSiteDomain() + '/elysian/user.php'
-        logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
-                                                              params['penname']))
-    
-        d = self._postUrl(loginUrl, params)
-    
-        if "Member Account" not in d : #User Account Page
-            logger.info("Failed to login to URL %s as %s, or have no authorization to access the story" % (loginUrl, params['penname']))
-            raise exceptions.FailedToLogin(url,params['penname'])
-            return False
-        else:
-            return True
-
-    ## Getting the chapter list and the meta data, plus 'is adult' checking.
-    def extractChapterUrlsAndMetadata(self):
-        
-        if self.is_adult or self.getConfig("is_adult"):
-            # Weirdly, different sites use different warning numbers.
-            # If the title search below fails, there's a good chance
-            # you need a different number.  print data at that point
-            # and see what the 'click here to continue' url says.
-            addurl = "&ageconsent=ok&warning=5"
-        else:
-            addurl=""
-
-        # index=1 makes sure we see the story chapter index.  Some
-        # sites skip that for one-chapter stories.
-        url = self.url+'&index=1'+addurl
-        logger.debug("URL: "+url)
-
-        try:
-            data = self._fetchUrl(url)
-        except urllib2.HTTPError, e:
-            if e.code == 404:
-                raise exceptions.StoryDoesNotExist(self.url)
-            else:
-                raise e
-
-        if self.needToLoginCheck(data):
-            # need to log in for this one.
-            self.performLogin(url)
-            data = self._fetchUrl(url)
-            
-        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
-        if m != None:
-            if self.is_adult or self.getConfig("is_adult"):
-                # We tried the default and still got a warning, so
-                # let's pull the warning number from the 'continue'
-                # link and reload data.
-                addurl = m.group(1)
-                # correct stupid & error in url.
-                addurl = addurl.replace("&","&")
-                url = self.url+'&index=1'+addurl
-                logger.debug("URL 2nd try: "+url)
-
-                try:
-                    data = self._fetchUrl(url)
-                except urllib2.HTTPError, e:
-                    if e.code == 404:
-                        raise exceptions.StoryDoesNotExist(self.url)
-                    else:
-                        raise e    
-            else:
-                raise exceptions.AdultCheckRequired(self.url)
-            
-        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
-        # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
-        # print data
-
-        # Now go hunting for all the meta data and the chapter list.
-        
-        ## Title and author
-        div = soup.find('div', {'id' : 'pagetitle'})
-        
-        aut = div.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
-        self.story.setMetadata('authorId',aut['href'].split('=')[1])
-        self.story.setMetadata('authorUrl','http://'+self.host+'/elysian/'+aut['href'])
-        self.story.setMetadata('author',aut.string)
-        aut.extract()
-
-        # first a tag in pagetitle is title
-        self.story.setMetadata('title',stripHTML(div.find('a')))
-        div.find('a').extract()
-        # only thing left in div(pagetitle) now should be 'by' and rating.
-        rating = stripHTML(div)
-        if '[' in rating:
-            self.story.setMetadata('rating', rating[rating.index('[')+1:-1])
-
-        for chapa in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+
-                                                       self.story.getMetadata('storyId')+'&chapter=\d+')):
-            self.chapterUrls.append((stripHTML(chapa),'http://'+self.host+'/elysian/'+chapa['href']))
-        
-        self.story.setMetadata('numChapters',len(self.chapterUrls))
-
-        asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
-        storylink = asoup.find('a', href=re.compile(r'viewstory.php\?sid='+
-                                                    self.story.getMetadata('storyId')+'($|[^\d])'))
-        # author's story list is paginated if there's a pagelinks div.
-        # Only need to look in it if the story wasn't on the first page.
-        pagelinks = asoup.find('div',{'id':'pagelinks'})
-        if pagelinks and storylink==None:
-            authpageslist = pagelinks.findAll('a',href=re.compile(r'action=storiesby'))
-            for page in authpageslist[1:]: # skip first, already checked above.
-                asoup = bs.BeautifulSoup(self._fetchUrl('http://'+self.host+'/elysian/'+page['href']))
-                storylink = asoup.find('a', href=re.compile(r'viewstory.php\?sid='+
-                                                            self.story.getMetadata('storyId')+'($|[^\d])'))
-                if storylink:
-                    break
-
-        if not storylink:
-            raise exceptions.FailedToDownload("Unable to find story metadata on author's page(s)")
-        
-        metalist = storylink.parent.parent
-        # 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 = metalist.findAll('span', {'class' : 'label'})
-        for labelspan in labels:
-            label = labelspan.text
-            value = labelspan.nextSibling
-
-            if 'Summary' in label:
-                ## Everything until the next span class='label'
-                svalue = ""
-                while value and not (defaultGetattr(value,'class') == 'label' or "Chapters: " in stripHTML(value)):
-                    svalue += str(value)
-                    value = value.nextSibling
-                self.setDescription(url,svalue)
-                #self.story.setMetadata('description',stripHTML(svalue))
-
-            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))
-
-        try:
-            # Find Series name from series URL.
-            a = metalist.find('a', href=re.compile(r"series.php\?seriesid=\d+"))
-            series_name = a.string
-            series_url = 'http://'+self.host+'/elysian/'+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.
-            storylink = seriessoup.find('a', href=re.compile(r'viewstory.php\?sid='+
-                                                             self.story.getMetadata('storyId')+'($|[^\d])'))
-            if storylink and storylink.parent and storylink.parent['class'] != 'title': # in case of links inside story summaries.
-                storylink = None
-
-            offset = 0
-            # series story list is paginated if there's a pagelinks div.
-            # Only need to look in it if the story wasn't on the first page.
-            pagelinks = seriessoup.find('div',{'id':'pagelinks'})
-            if pagelinks and storylink==None:
-                authpageslist = pagelinks.findAll('a',href=re.compile(r'offset='))
-                for page in authpageslist[1:]: # skip first, already checked above.
-                    seriessoup = bs.BeautifulSoup(self._fetchUrl('http://'+self.host+'/elysian/'+page['href']))
-                    storylink = seriessoup.find('a', href=re.compile(r'viewstory.php\?sid='+
-                                                                     self.story.getMetadata('storyId')+'($|[^\d])'))
-                    if storylink and storylink.parent and storylink.parent['class'] != 'title': # in case of links inside story summaries.
-                        storylink = None
-                    if storylink:
-                        offset = int(page['href'].split('=')[-1]) # offset is last.
-                        break
-
-            # for reasons I don't understand, searching for story
-            # links by regex wasn't working reliably.  It was missing
-            # the javascript links sometimes.  This is cleaner anyway.
-            for i, div in enumerate(seriessoup.findAll('div', {'class':'title'})):
-                a = div.find('a') # first a is story link.
-                # skip 'report this' and 'TOC' links
-                if a == storylink:
-                    self.setSeries(series_name, 1+i+offset)
-                    self.story.setMetadata('seriesUrl',series_url)
-                    break
-            
-        except Exception, e:
-            logger.debug("Series parsing failed: %s"%e)
-            
-    # grab the text for an individual chapter.
-    def getChapterText(self, url):
-
-        logger.debug('Getting chapter text from: %s' % url)
-
-        soup = bs.BeautifulSoup(self._fetchUrl(url))
-        
-        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)

fanficfare/adapters/adapter_devianthearts.py

@@ -1,38 +0,0 @@
-# -*- coding: utf-8 -*-
-
-# Copyright 2015 Fanficdownloader team, 2015 FanFicFare 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.
-#
-
-# Software: eFiction
-import re
-from base_efiction_adapter import BaseEfictionAdapter
-
-class DeviantHeartsAdapter(BaseEfictionAdapter):
-
-    @staticmethod
-    def getSiteDomain():
-        return 'devianthearts.com'
-
-    @classmethod
-    def getSiteAbbrev(self):
-        return 'devhrt'
-        
-    @classmethod
-    def getDateFormat(self):
-        return "%m/%d/%y" 
-                           
-def getClass():
-    return DeviantHeartsAdapter
-    

fanficfare/adapters/adapter_dramioneorg.py

@@ -38,8 +38,9 @@ class DramioneOrgAdapter(BaseSiteAdapter):
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
 
-        self.decode = ["Windows-1252",
-                       "utf8"] # 1252 is a superset of iso-8859-1.
+        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.

fanficfare/adapters/adapter_fanfictionnet.py

@@ -104,7 +104,7 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
             data = self._fetchUrl(url)
             #logger.debug("\n===================\n%s\n===================\n"%data)
             soup = self.make_soup(data)
-        except urllib2.HTTPError, e:
+        except urllib2.HTTPError as e:
             if e.code == 404:
                 raise exceptions.StoryDoesNotExist(url)
             else:
@@ -135,11 +135,15 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
                                                 chapcount+1)
                 logger.debug('=Trying newer chapter: %s' % tryurl)
                 newdata = self._fetchUrl(tryurl)
-                if "not found. Please check to see you are not using an outdated url." \
-                        not in newdata:
+                if "not found. Please check to see you are not using an outdated url." not in newdata \
+                        and "This request takes too long to process, it is timed out by the server." not in newdata:
                     logger.debug('=======Found newer chapter: %s' % tryurl)
                     soup = self.make_soup(newdata)
-            except:
+            except urllib2.HTTPError as e:
+                if e.code == 503:
+                    raise e
+            except e:
+                logger.warn("Caught an exception reading URL: %s sleeptime(%s) Exception %s."%(unicode(url),sleeptime,unicode(e)))
                 pass
             
         # Find authorid and URL from... author url.

fanficfare/adapters/adapter_fimfictionnet.py

@@ -178,8 +178,11 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
             if get_cover:
                 # try setting from href, if fails, try using the img src
                 if self.setCoverImage(self.url,coverurl)[0] == "failedtoload":
-                    coverurl = storyImage.find('img')['src']
-                    self.setCoverImage(self.url,coverurl)
+                    img = storyImage.find('img')
+                    # try src, then data-src, then leave None.
+                    coverurl = img.get('src',img.get('data-src',None))
+                    if coverurl:
+                        self.setCoverImage(self.url,coverurl)
 
             coverSource = storyImage.find('a', {'class':'source'})
             if coverSource:

fanficfare/adapters/adapter_forumquestionablequestingcom.py

@@ -0,0 +1,36 @@
+#  -*- coding: utf-8 -*-
+
+# Copyright 2015 FanFicFare 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
+
+from base_xenforoforum_adapter import BaseXenForoForumAdapter
+
+def getClass():
+    return QuestionablequestingComAdapter
+
+class QuestionablequestingComAdapter(BaseXenForoForumAdapter):
+
+    def __init__(self, config, url):
+        BaseXenForoForumAdapter.__init__(self, config, url)
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','qq')
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'forum.questionablequesting.com'
+

fanficfare/adapters/adapter_forumsspacebattlescom.py

@@ -15,15 +15,6 @@
 # limitations under the License.
 #
 
-import time
-import logging
-logger = logging.getLogger(__name__)
-import re
-import urllib2
-
-from ..htmlcleanup import stripHTML
-from .. import exceptions as exceptions
-
 from base_xenforoforum_adapter import BaseXenForoForumAdapter
 
 def getClass():
@@ -42,7 +33,3 @@ class ForumsSpacebattlesComAdapter(BaseXenForoForumAdapter):
         # The site domain.  Does have www here, if it uses it.
         return 'forums.spacebattles.com'
 
-    @classmethod
-    def getURLPrefix(cls):
-        return 'https://' + cls.getSiteDomain() 
-

fanficfare/adapters/adapter_forumssufficientvelocitycom.py

@@ -32,7 +32,3 @@ class ForumsSufficientVelocityComAdapter(BaseXenForoForumAdapter):
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
         return 'forums.sufficientvelocity.com'
-
-    @classmethod
-    def getURLPrefix(cls):
-        return 'http://' + cls.getSiteDomain()

fanficfare/adapters/adapter_hpfandomnet.py

@@ -22,7 +22,6 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 
-from .. import BeautifulSoup as bs
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
@@ -93,11 +92,33 @@ class HPFandomNetAdapterAdapter(BaseSiteAdapter): # XXX
                 raise e
 
         # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
+        soup = self.make_soup(data)
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
         
+        # set first URL
+        a = soup.find('a', href=re.compile(r"viewstory.php\?sid=\d+"))
+        ## href = "javascript:if (confirm('Slash/het fiction which incorporates sexual situations to a somewhat graphic degree  as well as graphic violent situations.  ')) location = 'viewstory.php?sid=49111&i=1'"
+        m = re.match(r'.*?(viewstory.php\?sid=\d+)&i=\d+.*?',a['href'])
+        self._setURL('http://'+self.host+'/eff/'+m.group(1))
+        if self.parsedUrl.query.split('=',)[1] != self.story.getMetadata('storyId'):
+            self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+            url = self.url
+            logger.debug("reset 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 = self.make_soup(data)
+            
+#        self.story.setMetadata('storyId', re.compile(self.getSiteURLPattern()).match(a).group('storyId'))
+        
         # 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])
@@ -109,14 +130,13 @@ class HPFandomNetAdapterAdapter(BaseSiteAdapter): # XXX
         # fix a typo in the site HTML so I can find the Characters list.
         authdata = authdata.replace('<td width=10%">','<td width="10%">')
 
-        # hpfandom.net only seems to indicate adult-only by javascript on the story/chapter links.
-        if "javascript:if (confirm('Slash/het fiction which incorporates sexual situations to a somewhat graphic degree and some violence. ')) location = 'viewstory.php?sid=%s'"%self.story.getMetadata('storyId') in authdata \
+        if "javascript:if (confirm('Slash/het fiction which incorporates sexual situations to a somewhat graphic degree  as well as graphic violent situations.  ')) location = 'viewstory.php?sid=%s&i=1'"%self.story.getMetadata('storyId') in authdata \
                 and not (self.is_adult or self.getConfig("is_adult")):
             raise exceptions.AdultCheckRequired(self.url)
         
-        authsoup = bs.BeautifulSoup(authdata)
+        authsoup = self.make_soup(authdata)
 
-        reviewsa = authsoup.find('a', href="reviews.php?sid="+self.story.getMetadata('storyId')+"&a=")
+        reviewsa = authsoup.find('a', href=re.compile(r"reviews\.php\?sid="+self.story.getMetadata('storyId')+r".*"))
         # <table><tr><td><p><b><a ...>
         metablock = reviewsa.findParent("table")
         #print("metablock:%s"%metablock)
@@ -223,7 +243,7 @@ class HPFandomNetAdapterAdapter(BaseSiteAdapter): # XXX
         data = re.sub(r'<table width="100%">.*?</table>','</div>',
                       data,count=1,flags=re.DOTALL)
         
-        soup = bs.BeautifulStoneSoup(data,selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        soup = self.make_soup(data)
 
         div = soup.find("div",{'name':'storybody'})
         #print("\n\ndiv:%s\n\n"%div)

fanficfare/adapters/adapter_mediaminerorg.py

@@ -40,39 +40,53 @@ class MediaMinerOrgSiteAdapter(BaseSiteAdapter):
         
         # get storyId from url--url validation guarantees query correct
         m = re.match(self.getSiteURLPattern(),url)
+        urltitle='urltitle'
         if m:
-            if m.group('id'):
-                self.story.setMetadata('storyId',m.group('id'))
+            if m.group('id1'):
+                self.story.setMetadata('storyId',m.group('id1'))
+                urltitle=m.group('urltitle1')
             elif m.group('id2'):
                 self.story.setMetadata('storyId',m.group('id2'))
+                urltitle=m.group('urltitle2')
             elif m.group('id3'):
-                self.story.setMetadata('storyId',m.group('id2'))
+                self.story.setMetadata('storyId',m.group('id3'))
+            else:
+                raise InvalidStoryURL(url,
+                                      self.getSiteDomain(),
+                                      self.getSiteExampleURLs())
             
             # normalized story URL.
-            self._setURL('http://' + self.getSiteDomain() + '/fanfic/view_st.php/'+self.story.getMetadata('storyId'))
+            self._setURL('http://' + self.getSiteDomain() + '/fanfic/s/'+urltitle+'/'+self.story.getMetadata('storyId'))
         else:
             raise exceptions.InvalidStoryURL(url,
                                              self.getSiteDomain(),
                                              self.getSiteExampleURLs())
             
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%B %d, %Y %H:%M"
+            
     @staticmethod
     def getSiteDomain():
         return 'www.mediaminer.org'
 
     @classmethod
     def getSiteExampleURLs(cls):
-        return "http://"+cls.getSiteDomain()+"/fanfic/view_st.php/123456 http://"+cls.getSiteDomain()+"/fanfic/view_ch.php/1234123/123444#fic_c"
+        return "http://"+cls.getSiteDomain()+"/fanfic/s/story-title/123456 http://"+cls.getSiteDomain()+"/fanfic/c/story-title/chapter-title/123456/987612"
 
     def getSiteURLPattern(self):
-        ##  http://www.mediaminer.org/fanfic/view_st.php/76882
-        ##  http://www.mediaminer.org/fanfic/view_ch.php/167618/594087#fic_c
-        ##  http://www.mediaminer.org/fanfic/view_ch.php?submit=View+Chapter&id=105816&cid=357151
-        ##  http://www.mediaminer.org/fanfic/view_ch.php?cid=612153&submit=View+Chapter&id=171668
-        return re.escape("http://"+self.getSiteDomain())+\
-            r"/fanfic/view_(st|ch)\.php"+\
-            r"(/(?P<id>\d+)(/\d+(#fic_c)?)?/?|"+\
-            r"\?((submit=View(\+| )Chapter|id=(?P<id2>\d+)|cid=\d+)&?)+)"
-
+        ## old urls
+        ## http://www.mediaminer.org/fanfic/view_st.php/76882
+        ## new urls
+        ## http://www.mediaminer.org/fanfic/s/ghosts-from-the-past/72
+        ## http://www.mediaminer.org/fanfic/c/ghosts-from-the-past/chapter-2/72/174
+        ## http://www.mediaminer.org/fanfic/s/robtech-final-missions/61553
+        ## http://www.mediaminer.org/fanfic/c/robtech-final-missions/robotech-final-missions-oneshot/61553/189830
+        return re.escape("http://"+self.getSiteDomain())+r"/fanfic/"+\
+            r"((s/(?P<urltitle1>[^/]+)/(?P<id1>\d+))|"+\
+            r"((c/(?P<urltitle2>[^/]+)/[^/]+/(?P<id2>\d+))/\d+)|"+\
+            r"(view_st\.php/(?P<id3>\d+)))"
+            
     # Override stripURLParameters so the id parameter won't get stripped
     @classmethod
     def stripURLParameters(cls, url):
@@ -84,9 +98,10 @@ class MediaMinerOrgSiteAdapter(BaseSiteAdapter):
         logger.debug("URL: "+url)
 
         try:
-            data = self._fetchUrl(url+'/') # trailing / gets 'chapter list' page even for one-shots.
+            data = self._fetchUrl(url) # w/o trailing / gets 'chapter list' page even for one-shots.
         except urllib2.HTTPError, e:
             if e.code == 404:
+                logger.error("404 on %s"%url)
                 raise exceptions.StoryDoesNotExist(self.url)
             else:
                 raise e
@@ -96,11 +111,13 @@ class MediaMinerOrgSiteAdapter(BaseSiteAdapter):
 
         # [ A - All Readers ], strip '[' ']'
         ## Above title because we remove the smtxt font to get title.
-        smtxt = soup.find("font",{"class":"smtxt"})
+        smtxt = soup.find("h3",{"id":"post-rating"})
         if not smtxt:
+            logger.error("can't find rating")
             raise exceptions.StoryDoesNotExist(self.url)
-        rating = smtxt.string[1:-1]
-        self.story.setMetadata('rating',rating)
+        else:
+            rating = smtxt.string[1:-1]
+            self.story.setMetadata('rating',rating)
 
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"/fanfic/src.php/u/\d+"))
@@ -116,37 +133,24 @@ class MediaMinerOrgSiteAdapter(BaseSiteAdapter):
         ## <td class="ffh">The Kraut, The Bartender, and The Drunkard: Chapter 1</b> <font class="smtxt">[ P - Pre-Teen ]</font></td>
         ## <td class="ffh">Betrayal and Justice: A Cold Heart</b> <font size="-1">( Chapter 1 )</font> <font class="smtxt">[ A - All Readers ]</font></td>
         ## <td class="ffh">Question and Answer: Question and Answer</b> <font size="-1">( One-Shot )</font> <font class="smtxt">[ A - All Readers ]</font></td>
-        title = soup.find('td',{'class':'ffh'})
-        for font in title.findAll('font'):
-            font.extract() # removes 'font' tags from inside the td.        
-        if title.has_attr('colspan'):
-            titlet = stripHTML(title)
-        else:
-            ## No colspan, it's part chapter title--even if it's a one-shot.
-            titlet = ':'.join(stripHTML(title).split(':')[:-1]) # strip trailing 'Chapter X' or chapter title
-        self.story.setMetadata('title',titlet)
+        # title = soup.find('td',{'class':'ffh'})
+        # for font in title.findAll('font'):
+        #     font.extract() # removes 'font' tags from inside the td.        
+        # if title.has_attr('colspan'):
+        #     titlet = stripHTML(title)
+        # else:
+        #     ## No colspan, it's part chapter title--even if it's a one-shot.
+        #     titlet = ':'.join(stripHTML(title).split(':')[:-1]) # strip trailing 'Chapter X' or chapter title
+        self.story.setMetadata('title',stripHTML(soup.find('h1',{'id':'post-title'})))
 
         # save date from first for later.
         firstdate=None
         
-        # Find the chapters
-        select = soup.find('select',{'name':'cid'})
-        if not select:
-            self.chapterUrls.append(( self.story.getMetadata('title'),self.url))
-        else:
-            for option in select.findAll("option"):
-                chapter = stripHTML(option.string)
-                ## chapter can be: Chapter 7 [Jan 23, 2011]
-                ##             or: Vigilant Moonlight ( Chapter 1 ) [Jan 30, 2004]
-                ##        or even: Prologue ( Prologue ) [Jul 31, 2010]
-                m = re.match(r'^(.*?) (\( .*? \) )?\[(.*?)\]$',chapter)
-                chapter = m.group(1)
-                # save date from first for later.
-                if not firstdate:
-                    firstdate = m.group(3)
-                # http://www.mediaminer.org/fanfic/view_ch.php?cid=376587&submit=View+Chapter&id=105816
-                # self.chapterUrls.append((chapter,'http://'+self.host+'/fanfic/view_ch.php/'+self.story.getMetadata('storyId')+'/'+option['value']))
-                self.chapterUrls.append((chapter,'http://'+self.host+'/fanfic/view_ch.php?submit=View Chapter&id='+self.story.getMetadata('storyId')+'&cid='+option['value']))
+        # Find the chapters - one-shot now have chapter list, too.
+        chap_p = soup.find('p',{'style':'margin-left:10px;'})
+        for (atag,aurl,name) in [ (x,x['href'],stripHTML(x)) for x in chap_p.find_all('a') ]:
+            self.chapterUrls.append((name,'http://'+self.host+aurl))
+            
         self.story.setMetadata('numChapters',len(self.chapterUrls))
 
         # category
@@ -155,27 +159,20 @@ class MediaMinerOrgSiteAdapter(BaseSiteAdapter):
             self.story.addToList('category',a.string)
         
         # genre
-        # <a href="/fanfic/src.php/a/567">Ranma 1/2</a>
+        # <a href="/fanfic/src.php/g/567">Ranma 1/2</a>
         for a in soup.findAll('a',href=re.compile(r"^/fanfic/src.php/g/")):
             self.story.addToList('genre',a.string)
 
-        # if firstdate, then the block below will only have last updated.
-        if firstdate:
-            self.story.setMetadata('datePublished', makeDate(firstdate, "%b %d, %Y"))
-        # Everything else is in <tr bgcolor="#EEEED4">
-
-        metastr = stripHTML(soup.find("tr",{"bgcolor":"#EEEED4"})).replace('\n',' ').replace('\r',' ').replace('\t',' ')
-        # Latest Revision: August 03, 2010
-        m = re.match(r".*?(?:Latest Revision|Uploaded On): ([a-zA-Z]+ \d\d, \d\d\d\d)",metastr)
+        metastr = stripHTML(soup.find("div",{"class":"post-meta"}))
+        
+        # Latest Revision: February 07, 2015 15:21 PST
+        m = re.match(r".*?(?:Latest Revision|Uploaded On): ([a-zA-Z]+ \d\d, \d\d\d\d \d\d:\d\d)",metastr)
         if m:
-            self.story.setMetadata('dateUpdated', makeDate(m.group(1), "%B %d, %Y"))
-            if not firstdate:
-                self.story.setMetadata('datePublished',
-                                       self.story.getMetadataRaw('dateUpdated'))
-                
-        else:
-            self.story.setMetadata('dateUpdated',
-                                   self.story.getMetadataRaw('datePublished'))
+            self.story.setMetadata('dateUpdated', makeDate(m.group(1), self.dateformat))
+            # site doesn't give date published on index page.
+            # set to updated, change in chapters below.
+            # self.story.setMetadata('datePublished',
+            #                        self.story.getMetadataRaw('dateUpdated'))
 
         # Words: 123456
         m = re.match(r".*?\| Words: (\d+) \|",metastr)
@@ -201,43 +198,54 @@ class MediaMinerOrgSiteAdapter(BaseSiteAdapter):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        data=self._fetchUrl(url)
+        data = self._fetchUrl(url)
         soup = self.make_soup(data)
 
-        header = soup.find('div',{'class':'post-meta clearfix '})
+        headerstr = stripHTML(soup.find('div',{'class':'post-meta clearfix '}))
         # print("data:%s"%data)
+        #header.extract()
 
-        chapter=self.make_soup('<div class="story"></div>').find('div')
-
-        if None == header:
-            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-
-        ## find divs with align=left, those are paragraphs in newer stories.
-        divlist = header.findAllNext('div',{'align':'left'})
-        if divlist:
-            for div in divlist:
-                div.name='p' # convert to <p> mediaminer uses div with
-                             # a margin for paragraphs.
-                chapter.append(div)
-                del div['style']
-                del div['align']
-            return self.utf8FromSoup(url,chapter)
-        
-        else:
-            logger.debug('Using kludgey text find for older mediaminer story.')
-            ## Some older mediaminer stories are unparsable with BeautifulSoup.
-            ## Really nasty formatting.  Sooo... Cheat!  Parse it ourselves a bit first.
-            ## Story stuff falls between:
-            data = "<div id='HERE'>" + data[data.find('<div class="adWrap">'):data.find('<div class="addthis_sharing_toolbox">')] +"</div>"
-            soup = self.make_soup(data)
-            for tag in soup.findAll('td',{'class':'ffh'}) + \
-                    soup.findAll('div',{'class':'acl'}) + \
-                    soup.findAll('div',{'class':'adWrap'}) + \
-                    soup.findAll('div',{'class':'footer smtxt'}) + \
-                    soup.findAll('table',{'class':'tbbrdr'}):
-                tag.extract() # remove tag from soup.
+        m = re.match(r".*?Uploaded On: ([a-zA-Z]+ \d\d, \d\d\d\d \d\d:\d\d)",headerstr)
+        if m:
+            date = makeDate(m.group(1), self.dateformat)
+            if not self.story.getMetadataRaw('datePublished') or date < self.story.getMetadataRaw('datePublished'):
+                self.story.setMetadata('datePublished', date)
                 
-            return self.utf8FromSoup(url,soup)
+        chapter = soup.find('div',{'id':'fanfic-text'})
+        
+        return self.utf8FromSoup(url,chapter)
+    
+        # chapter=self.make_soup('<div class="story"></div>').find('div')
+
+        # if None == header:
+        #     raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+
+        # ## find divs with align=left, those are paragraphs in newer stories.
+        # divlist = header.findAllNext('div',{'align':'left'})
+        # if divlist:
+        #     for div in divlist:
+        #         div.name='p' # convert to <p> mediaminer uses div with
+        #                      # a margin for paragraphs.
+        #         chapter.append(div)
+        #         del div['style']
+        #         del div['align']
+        #     return self.utf8FromSoup(url,chapter)
+        
+        # else:
+        #     logger.debug('Using kludgey text find for older mediaminer story.')
+        #     ## Some older mediaminer stories are unparsable with BeautifulSoup.
+        #     ## Really nasty formatting.  Sooo... Cheat!  Parse it ourselves a bit first.
+        #     ## Story stuff falls between:
+        #     data = "<div id='HERE'>" + data[data.find('<div class="adWrap">'):data.find('<div class="addthis_sharing_toolbox">')] +"</div>"
+        #     soup = self.make_soup(data)
+        #     for tag in soup.findAll('td',{'class':'ffh'}) + \
+        #             soup.findAll('div',{'class':'acl'}) + \
+        #             soup.findAll('div',{'class':'adWrap'}) + \
+        #             soup.findAll('div',{'class':'footer smtxt'}) + \
+        #             soup.findAll('table',{'class':'tbbrdr'}):
+        #         tag.extract() # remove tag from soup.
+                
+        #     return self.utf8FromSoup(url,soup)
         
 
 def getClass():

fanficfare/adapters/adapter_nickandgregnet.py

@@ -65,14 +65,18 @@ class NickAndGregNetAdapter(BaseSiteAdapter):
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
-        return 'www.nickandgreg.net'
+        return 'www.nickngreg.nl'
 
+    @classmethod
+    def getAcceptDomains(cls):
+        return ['www.nickngreg.nl','www.nickandgreg.net']
+    
     @classmethod
     def getSiteExampleURLs(cls):
         return "http://"+cls.getSiteDomain()+"/desert_archive/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
-        return re.escape("http://"+self.getSiteDomain()+"/desert_archive/viewstory.php?sid=")+r"\d+$"
+        return "http://("+self.getSiteDomain()+"|www.nickandgreg.net)"+re.escape("/desert_archive/viewstory.php?sid=")+r"\d+$"
     
 
     ## Getting the chapter list and the meta data, plus 'is adult' checking.

fanficfare/adapters/adapter_ninelivesarchivecom.py

@@ -19,12 +19,29 @@
 import re
 from base_efiction_adapter import BaseEfictionAdapter
 
-class NineLivesDarkSolaceAdapter(BaseEfictionAdapter):
+class NineLivesAdapter(BaseEfictionAdapter):
 
     @staticmethod
     def getSiteDomain():
-        return 'ninelives.dark-solace.org'
+        return 'ninelivesarchive.com'
 
+    @classmethod
+    def getAcceptDomains(cls):
+        return ['ninelivesarchive.com','ninelives.dark-solace.org']
+
+    @classmethod
+    def getSiteExampleURLs(cls):
+        return "http://"+cls.getSiteDomain()+"/viewstory.php?sid=1234"
+ 
+    @classmethod
+    def getSiteURLPattern(self):
+        return "http://("+self.getSiteDomain()+"|ninelives.dark-solace.org)"+re.escape("/viewstory.php?sid=")+r"(?P<storyId>\d+)$"
+     
+    @classmethod
+    def getConfigSections(cls):
+        "Only needs to be overriden if has additional ini sections."
+        return ['base_efiction','ninelives.dark-solace.org',cls.getSiteDomain()]
+    
     @classmethod
     def getSiteAbbrev(self):
         return '9lvs'
@@ -32,7 +49,7 @@ class NineLivesDarkSolaceAdapter(BaseEfictionAdapter):
     @classmethod
     def getDateFormat(self):
         return "%B %d, %Y" 
-                           
+                            
 def getClass():
-    return NineLivesDarkSolaceAdapter
+    return NineLivesAdapter
     

fanficfare/adapters/adapter_portkeyorg.py

@@ -258,6 +258,7 @@ class PortkeyOrgAdapter(BaseSiteAdapter): # XXX
         data = self._fetchUrl(url)
 
         data = data.replace("HTML>","div>")
+        data = data.replace("html>","div>")
         
         soup = bs.BeautifulSoup(data)
 

fanficfare/adapters/adapter_potterficscom.py

@@ -155,7 +155,10 @@ class PotterFicsComAdapter(BaseSiteAdapter):
             else:
                 raise e
 
-        #print data
+        if "Esta historia no existe. Probablemente ha sido eliminada." in data:
+            raise exceptions.StoryDoesNotExist(self.url)
+        
+        ##print data
 
         #deal with adult content login
         if self.needToLoginCheck(data):

fanficfare/adapters/adapter_quotevcom.py

@@ -0,0 +1,129 @@
+import re
+import urlparse
+import urllib2
+import datetime
+
+from .. import exceptions
+from base_adapter import BaseSiteAdapter
+
+SITE_DOMAIN = 'quotev.com'
+STORY_URL_TEMPLATE = 'http://www.quotev.com/story/%s'
+
+
+def getClass():
+    return QuotevComAdapter
+
+
+def get_url_path_segments(url):
+    return tuple(filter(None, url.split('/')[3:]))
+
+
+class QuotevComAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        story_id = get_url_path_segments(url)[1]
+        self._setURL(STORY_URL_TEMPLATE % story_id)
+        self.story.setMetadata('storyId', story_id)
+        self.story.setMetadata('siteabbrev', SITE_DOMAIN)
+
+    @staticmethod
+    def getSiteDomain():
+        return SITE_DOMAIN
+
+    @classmethod
+    def getSiteExampleURLs(cls):
+        return STORY_URL_TEMPLATE % '1234'
+
+    def getSiteURLPattern(self):
+        pattern = re.escape(STORY_URL_TEMPLATE.rsplit('%', 1)[0]) + r'(.+?)($|&|/)'
+        pattern = pattern.replace(r'http\:', r'https?\:')
+        pattern = pattern.replace(r'https?\:\/\/www\.', r'https?\:\/\/(www\.)?')
+        return pattern
+
+    def use_pagecache(self):
+        return True
+
+    def extractChapterUrlsAndMetadata(self):
+        try:
+            data = self._fetchUrl(self.url)
+        except urllib2.HTTPError:
+            raise exceptions.FailedToDownload(self.url)
+
+        soup = self.make_soup(data)
+
+        element = soup.find('div', {'class': 'result_head'})
+        if not element:
+            raise exceptions.StoryDoesNotExist(self.url)
+
+        self.story.setMetadata('title', element.find('span', recursive=False).get_text())
+
+        element = soup.find('div', {'class': 'desc_creator'})
+        if element:
+            a = element('a')[1]
+            self.story.setMetadata('author', a.get_text())
+            self.story.setMetadata('authorId', get_url_path_segments(a['href'])[0])
+            self.story.setMetadata('authorUrl', urlparse.urljoin(self.url, a['href']))
+
+        # Multiple authors
+        else:
+            element = soup.find('div', id='qheadx')
+            for a in element('div', recursive=False)[1]('a'):
+                author = a.get_text()
+                if not a.get_text():
+                    continue
+
+                self.story.addToList('author', author)
+                self.story.addToList('authorId', get_url_path_segments(a['href'])[0])
+                self.story.addToList('authorUrl', urlparse.urljoin(self.url, a['href']))
+
+        self.setDescription(self.url, soup.find('div', id='qdesct'))
+        self.setCoverImage(self.url, urlparse.urljoin(self.url, soup.find('img', {'class': 'logo'})['src']))
+
+        for a in soup.find('div', {'class': 'tag'})('a'):
+            if a['href'] == '#':
+                continue
+
+            self.story.addToList('category', a.get_text())
+
+        elements = soup('span', {'class': 'q_time'})
+        self.story.setMetadata('datePublished', datetime.datetime.fromtimestamp(float(elements[0]['ts'])))
+        if len(elements) > 1:
+            self.story.setMetadata('dateUpdated', datetime.datetime.fromtimestamp(float(elements[1]['ts'])))
+
+        for a in soup.find('div', id='rselect')('a'):
+            self.chapterUrls.append((a.get_text(), urlparse.urljoin(self.url, a['href'])))
+
+        self.story.setMetadata('numChapters', len(self.chapterUrls))
+
+        element = soup.find('div', {'class': 't'})('div', recursive=False)[1].div
+        data = filter(None, (x.strip() for x in element.get_text().split(u'\xb7')))
+        if 'completed' in data:
+            self.story.setMetadata('status', 'Completed')
+            data.remove('completed')
+        else:
+            self.story.setMetadata('status', 'In-Progress')
+
+        for datum in data:
+            parts = datum.split()
+            # Not a valid metadatum
+            if not len(parts) == 2:
+                continue
+
+            key, value = parts
+            self.story.setMetadata(key, value.replace(',', '').replace('.', ''))
+
+        self.story.setMetadata('favorites', soup.find('div', id='favqn').get_text())
+        element = soup.find('a', id='comment_btn').span
+        self.story.setMetadata('comments', element.get_text() if element else 0)
+
+    def getChapterText(self, url):
+        data = self._fetchUrl(url)
+        soup = self.make_soup(data)
+
+        element = soup.find('div', id='restxt')
+        for a in element('a'):
+            a.unwrap()
+
+        return self.utf8FromSoup(url, element)

fanficfare/adapters/adapter_test1.py

@@ -72,8 +72,13 @@ class TestSiteAdapter(BaseSiteAdapter):
                     #print("set:%s->%s"%(key,self.story.getMetadata(key)))
 
             self.chapterUrls = []
-            for (j,chap) in enumerate(self.get_config_list(sections,'chaptertitles'),start=1):
-                self.chapterUrls.append( (chap,self.url+"&chapter=%d"%j) )
+            if self.has_config(sections,'chapter_urls'):
+                for l in self.get_config(sections,'chapter_urls').splitlines() :
+                    if l:
+                        self.chapterUrls.append( (l[1+l.index(','):],l[:l.index(',')]) )                    
+            else:
+                for (j,chap) in enumerate(self.get_config_list(sections,'chaptertitles'),start=1):
+                    self.chapterUrls.append( (chap,self.url+"&chapter=%d"%j) )
             # self.chapterUrls = [(u'Prologue '+self.crazystring,self.url+"&chapter=1"),
             #                 ('Chapter 1, Xenos on Cinnabar',self.url+"&chapter=2"),
             #                 ]
@@ -81,6 +86,12 @@ class TestSiteAdapter(BaseSiteAdapter):
             
             return
 
+        if idnum >= 700 and idnum <= 710:
+            self._setURL('http://test1.com?sid=%s'%(idnum+100))
+            self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+            idstr = self.story.getMetadata('storyId')
+            idnum = int(idstr)
+
         if idstr == '665' and not (self.is_adult or self.getConfig("is_adult")):
             logger.warn("self.is_adult:%s"%self.is_adult)
             raise exceptions.AdultCheckRequired(self.url)
@@ -207,7 +218,7 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
             self.story.addToList('category','SG-1')
             self.story.addToList('genre','Porn')
             self.story.addToList('genre','Drama')
-        else:
+        elif idnum < 1000:
             self.story.setMetadata('authorId','98765')
             self.story.setMetadata('authorUrl','http://author/url')
 
@@ -324,7 +335,8 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
 <p>http://test1.com?sid=671 - Succeeds, but sleeps 2sec metadata only</p>
 <p>http://test1.com?sid=672 - Succeeds, quick meta, sleeps 2sec chapters only</p>
 <p>http://test1.com?sid=673 - Succeeds, multiple authors, extra categories, genres</p>
-<p>http://test1.com?sid=673 - Succeeds, no numWords set</p>
+<p>http://test1.com?sid=674 - Succeeds, no numWords set</p>
+<p>http://test1.com?sid=700 - 710 - Succeeds, changes sid to 80X</p>
 <p>http://test1.com?sid=0 - Succeeds, generates some text specifically for testing hyphenation problems with Nook STR/STRwG</p>
 <p>Odd sid's will be In-Progress, evens complete.  sid&lt;10 will be assigned one of four languages and included in a series.</p>
 </div>
@@ -341,13 +353,55 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
 <br />
 </div>
 '''
+        elif self.story.getMetadata('storyId') == '667':
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!" % url)
+        elif 'test1.com' not in url:
+            ## for chapter_urls setting.
+            logger.debug('Getting chapter text from: %s' % url)
+    
+            try:
+                origurl = url
+                (data,opened) = self._fetchUrlOpened(url,extrasleep=2.0)
+                url = opened.geturl()
+                if '#' in origurl and '#' not in url:
+                    url = url + origurl[origurl.index('#'):]
+                logger.debug("chapter URL redirected to: %s"%url)
+                
+                soup = self.make_soup(data)
+        
+                if '#' in url:
+                    anchorid = url.split('#')[1]
+                    soup = soup.find('li',id=anchorid)
+        
+                bq = soup.find('blockquote')
+        
+                bq.name='div'
+        
+                for iframe in bq.find_all('iframe'):
+                    iframe.extract() # calibre book reader & editor don't like iframes to youtube.
+        
+                for qdiv in bq.find_all('div',{'class':'quoteExpand'}):
+                    qdiv.extract() # Remove <div class="quoteExpand">click to expand</div>
+        
+            except Exception as e:
+                if self.getConfig('continue_on_chapter_error'):
+                    bq = self.make_soup("""<div>
+<p><b>Error</b></p>
+<p>FanFicFare failed to download this chapter.  Because you have
+<b>continue_on_chapter_error</b> set to <b>true</b> in your personal.ini, the download continued.</p>
+<p>Chapter URL:<br>%s</p>
+<p>Error:<br><pre>%s</pre></p>
+</div>"""%(url,traceback.format_exc()))
+                else:
+                    raise
+                
+            return self.utf8FromSoup(url[:url.index('/',8)+1],bq)
+                
         else:
-            if self.story.getMetadata('storyId') == '667':
-                raise exceptions.FailedToDownload("Error downloading Chapter: %s!" % url)
-
             text=u'''
 <div>
 <h3 extra="value">Chapter title from site</h3>
+<p>chapter URL:'''+url+'''</p>
 <p>Timestamp:'''+datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")+'''</p>
 <p>Lorem '''+self.crazystring+u''' <i>italics</i>, <b>bold</b>, <u>underline</u> consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.</p>
 br breaks<br><br>

fanficfare/adapters/adapter_thequidditchpitchorg.py

@@ -1,292 +0,0 @@
-# -*- coding: utf-8 -*-
-
-# Copyright 2011 Fanficdownloader team, 2015 FanFicFare 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.
-#
-
-# Software: eFiction
-import time
-import logging
-logger = logging.getLogger(__name__)
-import re
-import urllib2
-
-from .. import BeautifulSoup as bs
-from ..htmlcleanup import stripHTML
-from .. import exceptions as exceptions
-
-from base_adapter import BaseSiteAdapter,  makeDate
-
-# This function is called by the downloader in all adapter_*.py files
-# in this dir to register the adapter class.  So it needs to be
-# updated to reflect the class below it.  That, plus getSiteDomain()
-# take care of 'Registering'.
-def getClass():
-    return TheQuidditchPitchOrgAdapter # XXX
-
-# Class name has to be unique.  Our convention is camel case the
-# sitename with Adapter at the end.  www is skipped.
-class TheQuidditchPitchOrgAdapter(BaseSiteAdapter): # XXX
-
-    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])
-        
-        
-        # normalized story URL.
-        # XXX Most sites don't have the  part.  Replace all to remove it usually.
-        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','tqdpch') # XXX
-
-        # The date format will vary from site to site.
-        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%m/%d/%Y" # XXX
-            
-    @staticmethod # must be @staticmethod, don't remove it.
-    def getSiteDomain():
-        # The site domain.  Does have www here, if it uses it.
-        return 'thequidditchpitch.org' # XXX
-
-    @classmethod
-    def getAcceptDomains(cls):
-        return ['www.thequidditchpitch.org','thequidditchpitch.org']
-
-    @classmethod
-    def getSiteExampleURLs(cls):
-        return "http://"+cls.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 - Not suitable for readers under the age of legal consent in their country.' in data \
-                or 'There is no such account on our website' in data \
-                or "That password doesn't match the one in our database" in data:
-            return True
-        else:
-            return False
-        
-    def performLogin(self, url):
-        params = {}
-
-        if self.password:
-            params['penname'] = self.username
-            params['password'] = self.password
-        else:
-            params['penname'] = self.getConfig("username")
-            params['password'] = self.getConfig("password")
-        params['cookiecheck'] = '1'
-        params['submit'] = 'Submit'
-    
-        loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login'
-        logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
-                                                              params['penname']))
-    
-        d = self._fetchUrl(loginUrl, params)
-    
-        if "Member Account" not in d : #Member Account
-            logger.info("Failed to login to URL %s as %s" % (loginUrl,
-                                                              params['penname']))
-            raise exceptions.FailedToLogin(url,params['penname'])
-            return False
-        else:
-            return True
-
-    ## Getting the chapter list and the meta data, plus 'is adult' checking.
-    def extractChapterUrlsAndMetadata(self):
-
-        if self.is_adult or self.getConfig("is_adult"):
-            # Weirdly, different sites use different warning numbers.
-            # If the title search below fails, there's a good chance
-            # you need a different number.  print data at that point
-            # and see what the 'click here to continue' url says.
-            addurl = "&ageconsent=ok&warning=4" # XXX
-        else:
-            addurl=""
-
-        # index=1 makes sure we see the story chapter index.  Some
-        # sites skip that for one-chapter stories.
-        url = self.url+'&index=1'+addurl
-        logger.debug("URL: "+url)
-
-        try:
-            data = self._fetchUrl(url)
-        except urllib2.HTTPError, e:
-            if e.code == 404:
-                raise exceptions.StoryDoesNotExist(self.url)
-            else:
-                raise e
-
-        if self.needToLoginCheck(data):
-            # need to log in for this one.
-            self.performLogin(url)
-            data = self._fetchUrl(url)
-
-        # 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 ("Not suitable for readers under the age of legal consent in their country." in data \
-                or "Not suitable for readers under 16 yrs. \r\nStories may contain violence, slight nudity, and/or sexual situations." in data ) \
-                and not (self.is_adult or self.getConfig("is_adult")): # XXX 
-            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',stripHTML(a))
-        
-        # 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'))
-                catstext = [cat.string for cat in cats]
-                for cat in catstext:
-                    self.story.addToList('category',cat.string)
-
-            if 'Characters' in label:
-                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
-                charstext = [char.string for char in chars]
-                for char in charstext:
-                    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
-                genrestext = [genre.string for genre in genres]
-                self.genre = ', '.join(genrestext)
-                for genre in genrestext:
-                    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
-                warningstext = [warning.string for warning in warnings]
-                self.warning = ', '.join(warningstext)
-                for warning in warningstext:
-                    self.story.addToList('warnings',warning.string)
-
-            if 'Completed' in label:
-                if 'Yes' in value:
-                    self.story.setMetadata('status', 'Completed')
-                else:
-                    self.story.setMetadata('status', 'In-Progress')
-
-            if 'Published' in label:
-                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
-            if 'Updated' in label:
-                # there's a stray [ at the end.
-                #value = value[0:-1]
-                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
-
-        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)
-                    self.story.setMetadata('seriesUrl',series_url)
-                    break
-                i+=1
-            
-        except:
-            # I find it hard to care if the series parsing fails
-            pass
-            
-    # grab the text for an individual chapter.
-    def getChapterText(self, url):
-
-        logger.debug('Getting chapter text from: %s' % url)
-
-        
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-
-        # span?  Really?  span?  Yeah... I don't think so.
-        div = soup.find('span', {'style' : 'font-size: 100%;'})
-        div.name='div'
-
-        if None == div:
-            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
-        return self.utf8FromSoup(url,div)

fanficfare/adapters/base_adapter.py

@@ -338,7 +338,7 @@ class BaseSiteAdapter(Configurable):
                 return (self._decode(data),opened)
             except u2.HTTPError, he:
                 excpt=he
-                if he.code == 404:
+                if he.code in (403,404):
                     logger.warn("Caught an exception reading URL: %s  Exception %s."%(unicode(url),unicode(he)))
                     break # break out on 404
             except Exception, e:
@@ -600,7 +600,8 @@ class BaseSiteAdapter(Configurable):
                     if t.name not in ('p') and t.string != None and len(t.string.strip()) == 0 :
                         t.extract()
         except AttributeError, ae:
-            logger.error("Error parsing HTML, probably poor input HTML. %s"%ae)
+            if "%s"%ae != "'NoneType' object has no attribute 'next_element'":
+                logger.error("Error parsing HTML, probably poor input HTML. %s"%ae)
         
         retval = unicode(soup)
 
@@ -623,7 +624,7 @@ class BaseSiteAdapter(Configurable):
         if self.getConfig('replace_hr'):
             # replacing a self-closing tag with a container tag in the
             # soup is more difficult than it first appears.  So cheat.
-            retval = retval.replace("<hr />","<div class='center'>* * *</div>")
+            retval = re.sub("<hr[^>]*>","<div class='center'>* * *</div>",retval)
 
         return retval
 

fanficfare/adapters/base_efiction_adapter.py

@@ -148,7 +148,7 @@ class BaseEfictionAdapter(BaseSiteAdapter):
         """
         Get the URL to a user page on this site.
         """
-        return "%s?sid=%s" % (self.getUrlForPhp(self.getViewUserPhpName()), userId)
+        return "%s?uid=%s" % (self.getUrlForPhp(self.getViewUserPhpName()), userId)
 
     @classmethod
     def getLoginUrl(self):

fanficfare/adapters/base_xenforoforum_adapter.py

@@ -17,6 +17,7 @@
 
 import time
 import logging
+import traceback
 logger = logging.getLogger(__name__)
 import re
 import urllib2
@@ -31,6 +32,7 @@ logger = logging.getLogger(__name__)
 class BaseXenForoForumAdapter(BaseSiteAdapter):
 
     def __init__(self, config, url):
+        #logger.info("init url: "+url)
         BaseSiteAdapter.__init__(self, config, url)
 
         self.decode = ["utf8",
@@ -38,47 +40,51 @@ class BaseXenForoForumAdapter(BaseSiteAdapter):
                                # Most sites that claim to be
                                # iso-8859-1 (and some that claim to be
                                # utf8) are really windows-1252.
-							   
-							   
+
+
         # get storyId from url--url validation guarantees query is only sid=1234
-        self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])        
-        
+        self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])
+
         # get storyId from url--url validation guarantees query correct
         m = re.match(self.getSiteURLPattern(),url)
         if m:
-            self.story.setMetadata('storyId',m.group('id'))
-
-            # normalized story URL.
-            self._setURL(self.getURLPrefix() + '/'+m.group('tp')+'/'+self.story.getMetadata('storyId')+'/')
+            #logger.debug("groupdict:%s"%m.groupdict())
+            if m.group('post'):
+                self.story.setMetadata('storyId',m.group('post'))
+                self._setURL(self.getURLPrefix() + '/posts/'+m.group('post')+'/')
+            else:
+                self.story.setMetadata('storyId',m.group('id'))
+                # normalized story URL.
+                self._setURL(self.getURLPrefix() + '/'+m.group('tp')+'/'+self.story.getMetadata('storyId')+'/')
         else:
             raise exceptions.InvalidStoryURL(url,
                                              self.getSiteDomain(),
                                              self.getSiteExampleURLs())
-        
+
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','fsb')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
         self.dateformat = "%b %d, %Y at %I:%M %p"
-            
+
     @classmethod
     def getConfigSections(cls):
         "Only needs to be overriden if has additional ini sections."
         return ['base_xenforoforum',cls.getConfigSection()]
-    
+
     @classmethod
     def getURLPrefix(cls):
         # The site domain.  Does have www here, if it uses it.
-        return 'https://' + cls.getSiteDomain() 
+        return 'https://' + cls.getSiteDomain()
 
     @classmethod
     def getSiteExampleURLs(cls):
-        return cls.getURLPrefix()+"/threads/some-story-name.123456/"
+        return cls.getURLPrefix()+"/threads/some-story-name.123456/ "+cls.getURLPrefix()+"/posts/123456/"
 
     def getSiteURLPattern(self):
-        return r"https?://"+re.escape(self.getSiteDomain())+r"/(?P<tp>threads|posts)/(.+\.)?(?P<id>\d+)/"
-        
+        return r"https?://"+re.escape(self.getSiteDomain())+r"/(?P<tp>threads|posts)/(.+\.)?(?P<id>\d+)/?[^#]*?(#post-(?P<post>\d+))?$"
+
     def use_pagecache(self):
         '''
         adapters that will work with the page cache need to implement
@@ -86,6 +92,42 @@ class BaseXenForoForumAdapter(BaseSiteAdapter):
         '''
         return True
 
+    def performLogin(self):
+        params = {}
+
+        if self.password:
+            params['login'] = self.username
+            params['password'] = self.password
+        else:
+            params['login'] = self.getConfig("username")
+            params['password'] = self.getConfig("password")
+        params['register'] = '0'
+        params['cookie_check'] = '1'
+        params['_xfToken'] = ''
+        params['redirect'] = 'https://' + self.getSiteDomain() + '/'
+
+        if not params['password']:
+            return
+
+        ## https://forum.questionablequesting.com/login/login
+        loginUrl = 'https://' + self.getSiteDomain() + '/login/login'
+        logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
+                                                              params['login']))
+
+        # soup = self.make_soup(self._fetchUrl(loginUrl))
+        # params['ctkn']=soup.find('input', {'name':'ctkn'})['value']
+        # params[soup.find('input', {'id':'password'})['name']] = params['password']
+
+        d = self._fetchUrl(loginUrl, params)
+    
+        if "Log Out" not in d :
+            logger.info("Failed to login to URL %s as %s" % (loginUrl,
+                                                             params['login']))
+            raise exceptions.FailedToLogin(self.url,params['login'])
+            return False
+        else:
+            return True
+
     ## Getting the chapter list and the meta data, plus 'is adult' checking.
     def extractChapterUrlsAndMetadata(self):
 
@@ -99,8 +141,13 @@ class BaseXenForoForumAdapter(BaseSiteAdapter):
         except urllib2.HTTPError, e:
             if e.code == 404:
                 raise exceptions.StoryDoesNotExist(self.url)
+            elif e.code == 403:
+                self.performLogin()
+                (data,opened) = self._fetchUrlOpened(useurl)
+                useurl = opened.geturl()
+                logger.info("use useurl: "+useurl)
             else:
-                raise e
+                raise
 
         # use BeautifulSoup HTML parser to make everything easier to find.
         soup = self.make_soup(data)
@@ -112,7 +159,7 @@ class BaseXenForoForumAdapter(BaseSiteAdapter):
 
         h1 = soup.find('div',{'class':'titleBar'}).h1
         self.story.setMetadata('title',stripHTML(h1))
-        
+
         if '#' in useurl:
             anchorid = useurl.split('#')[1]
             soup = soup.find('li',id=anchorid)
@@ -129,14 +176,22 @@ class BaseXenForoForumAdapter(BaseSiteAdapter):
                             self.story.setMetadata('datePublished', date)
                         if not self.story.getMetadataRaw('dateUpdated') or date > self.story.getMetadataRaw('dateUpdated'):
                             self.story.setMetadata('dateUpdated', date)
-                            
+
                         self.chapterUrls.append((name,self.getURLPrefix()+'/'+url))
-                        
+
+                    ## only use tags if threadmarks for chapters.
+                    ##  a bit arbitrary, but likely.
+                    for tag in soup.findAll('a',{'class':'tag'}):
+                        tstr = stripHTML(tag)
+                        if self.getConfig('capitalize_forumtags'):
+                            tstr = tstr.title()
+                        self.story.addToList('forumtags',tstr)
+
             soup = soup.find('li',{'class':'message'}) # limit first post for date stuff below. ('#' posts above)
-                
+
         # Now go hunting for the 'chapter list'.
         bq = soup.find('blockquote') # assume first posting contains TOC urls.
-        
+
         bq.name='div'
 
         for iframe in bq.find_all('iframe'):
@@ -144,7 +199,7 @@ class BaseXenForoForumAdapter(BaseSiteAdapter):
 
         for qdiv in bq.find_all('div',{'class':'quoteExpand'}):
             qdiv.extract() # Remove <div class="quoteExpand">click to expand</div>
-            
+
         self.setDescription(useurl,bq)
 
         # otherwise, use first post links--include first post since
@@ -152,33 +207,37 @@ class BaseXenForoForumAdapter(BaseSiteAdapter):
         if not self.chapterUrls:
             self.chapterUrls.append(("First Post",useurl))
             for (url,name) in [ (x['href'],stripHTML(x)) for x in bq.find_all('a') ]:
-                logger.debug("found chapurl:%s"%url)
+                #logger.debug("found chapurl:%s"%url)
                 if not url.startswith('http'):
                     url = self.getURLPrefix()+'/'+url
-    
+
                 if ( url.startswith(self.getURLPrefix()) or
                      url.startswith('http://'+self.getSiteDomain()) or
                      url.startswith('https://'+self.getSiteDomain()) ) and ('/posts/' in url or '/threads/' in url):
+
                     # brute force way to deal with SB's http->https change when hardcoded http urls.
                     url = url.replace('http://'+self.getSiteDomain(),self.getURLPrefix())
-                    logger.debug("used chapurl:%s"%(url))
+
+                    url = re.sub(r'(^[\'"]+|[\'"]+$)','',url) # strip leading or trailing '" from incorrect quoting.
+
+                    logger.debug("(ch:%s)used chapurl:%s"%(len(self.chapterUrls)+1,url))
                     self.chapterUrls.append((name,url))
                     if url == useurl and 'First Post' == self.chapterUrls[0][0]:
                         # remove "First Post" if included in list.
                         logger.debug("delete dup 'First Post' chapter: %s %s"%self.chapterUrls[0])
                         del self.chapterUrls[0]
-                        
+
             # Didn't use threadmarks, so take created/updated dates
             # from the 'first' posting created and updated.
             date = self.make_date(soup.find('a',{'class':'datePermalink'}))
             if date:
                 self.story.setMetadata('datePublished', date)
                 self.story.setMetadata('dateUpdated', date) # updated overwritten below if found.
-        
+
             date = self.make_date(soup.find('div',{'class':'editDate'}))
             if date:
-                self.story.setMetadata('dateUpdated', date) 
-            
+                self.story.setMetadata('dateUpdated', date)
+
         self.story.setMetadata('numChapters',len(self.chapterUrls))
 
     def make_date(self,parenttag): # forums use a BS thing where dates
@@ -199,31 +258,62 @@ class BaseXenForoForumAdapter(BaseSiteAdapter):
         except:
             logger.debug('No date found in %s'%parenttag)
             return None
-        
+
     # grab the text for an individual chapter.
     def getChapterText(self, url):
         logger.debug('Getting chapter text from: %s' % url)
 
-        origurl = url
-        (data,opened) = self._fetchUrlOpened(url)
-        url = opened.geturl()
-        if '#' in origurl and '#' not in url:
-            url = url + origurl[origurl.index('#'):]
-        logger.debug("chapter URL redirected to: %s"%url)
+        ## there's some history of stories with links to the wrong
+        ## page.  This changes page#post URLs to perma-link URLs.
+        ## Which will be redirected back to page#posts, but the
+        ## *correct* ones.
+        # http://forums.sufficientvelocity.com/threads/harry-potter-and-the-not-fatal-at-all-cultural-exchange-program.330/page-4#post-39915
+        # https://forums.sufficientvelocity.com/posts/39915/
+        if '#post-' in url:
+            url = self.getURLPrefix()+'/posts/'+url.split('#post-')[1]+'/'
 
-        soup = self.make_soup(data)
+        ## Same as above except for for case where author mistakenly
+        ## used the reply link instead of normal link to post.
+        # "http://forums.spacebattles.com/threads/manager-worm-story-thread-iv.301602/reply?quote=15962513"
+        # https://forums.spacebattles.com/posts/
+        if 'reply?quote=' in url:
+            url = self.getURLPrefix()+'/posts/'+url.split('reply?quote=')[1]+'/'
 
-        if '#' in url:
-            anchorid = url.split('#')[1]
-            soup = soup.find('li',id=anchorid)
-        bq = soup.find('blockquote')
+        try:
+            origurl = url
+            (data,opened) = self._fetchUrlOpened(url)
+            url = opened.geturl()
+            if '#' in origurl and '#' not in url:
+                url = url + origurl[origurl.index('#'):]
+            logger.debug("chapter URL redirected to: %s"%url)
+            
+            soup = self.make_soup(data)
+    
+            if '#' in url:
+                anchorid = url.split('#')[1]
+                soup = soup.find('li',id=anchorid)
+    
+            bq = soup.find('blockquote')
+    
+            bq.name='div'
+    
+            for iframe in bq.find_all('iframe'):
+                iframe.extract() # calibre book reader & editor don't like iframes to youtube.
+    
+            for qdiv in bq.find_all('div',{'class':'quoteExpand'}):
+                qdiv.extract() # Remove <div class="quoteExpand">click to expand</div>
+    
+        except Exception as e:
+            if self.getConfig('continue_on_chapter_error'):
+                bq = self.make_soup("""<div>
+<p><b>Error</b></p>
+<p>FanFicFare failed to download this chapter.  Because you have
+<b>continue_on_chapter_error</b> set to <b>true</b> in your personal.ini, the download continued.</p>
+<p>Chapter URL:<br>%s</p>
+<p>Error:<br><pre>%s</pre></p>
+</div>"""%(url,traceback.format_exc()))
+            else:
+                raise
 
-        bq.name='div'
-
-        for iframe in bq.find_all('iframe'):
-            iframe.extract() # calibre book reader & editor don't like iframes to youtube.
-
-        for qdiv in bq.find_all('div',{'class':'quoteExpand'}):
-            qdiv.extract() # Remove <div class="quoteExpand">click to expand</div>
-
-        return self.utf8FromSoup(url,bq)
+        # XenForo uses <base href="https://forums.spacebattles.com/" />
+        return self.utf8FromSoup(self.getURLPrefix()+'/',bq)

fanficfare/cli.py

@@ -159,6 +159,7 @@ def main(argv=None, parser=None, passed_defaultsini=None, passed_personalini=Non
                             options,
                             passed_defaultsini,
                             passed_personalini)
+                print("pagecache:%s"%options.pagecache.keys())
             except Exception, e:
                 print "URL(%s) Failed: Exception (%s). Run URL individually for more detail."%(url,e)
     else:
@@ -264,6 +265,14 @@ def do_download(arg,
 
     try:
         adapter = adapters.getAdapter(configuration, url)
+
+        if not hasattr(options,'pagecache'):
+            options.pagecache = adapter.get_empty_pagecache()
+            options.cookiejar = adapter.get_empty_cookiejar()
+        
+        adapter.set_pagecache(options.pagecache)
+        adapter.set_cookiejar(options.cookiejar)
+        
         adapter.setChaptersRange(options.begin, options.end)
 
         # check for updating from URL (vs from file)

fanficfare/configurable.py

@@ -82,7 +82,7 @@ def get_valid_sections():
     sitesections = list(othersections)
     for section in sites:
         sitesections.append(section)
-        # also allows [www.base_efiction] and [www.base_forum]. Not
+        # also allows [www.base_efiction] and [www.base_xenforoforum]. Not
         # likely to matter.
         if section.startswith('www.'):
             # add w/o www if has www
@@ -166,6 +166,12 @@ def get_valid_set_options():
                'include_images':(None,['epub','html'],boollist),
                'grayscale_images':(None,['epub','html'],boollist),
                'no_image_processing':(None,['epub','html'],boollist),
+
+               'continue_on_chapter_error':(['base_xenforoforum',
+                                             'forums.spacebattles.com',
+                                             'forums.sufficientvelocity.com',
+                                             'questionablequesting.com',
+                                             ],None,boollist),
                }
 
     return dict(valdict)
@@ -220,6 +226,7 @@ def get_valid_keywords():
                  'chapter_title_add_pattern',
                  'chapter_title_new_pattern',
                  'chapter_title_addnew_pattern',
+                 'title_chapter_range_pattern',
                  'mark_new_chapters',
                  'check_next_chapter',
                  'skip_author_cover',
@@ -319,6 +326,7 @@ def get_valid_keywords():
                  'wrap_width',
                  'zip_filename',
                  'zip_output',
+                 'continue_on_chapter_error',
                  ])
 
 # *known* entry keywords -- or rather regexps for them.

fanficfare/defaults.ini

@@ -148,8 +148,10 @@ zip_filename: ${title}-${siteabbrev}_${storyId}${formatext}.zip
 ## zip_filename.
 allow_unsafe_filename: false
 
-## The regex pattern of 'unsafe' filename chars for above.
-#output_filename_safepattern:[^a-zA-Z0-9_\. \[\]\(\)&'-]+
+## The regex pattern of 'unsafe' filename chars for above.  First
+## character . OR any one or more characters that are NOT a letter,
+## number, or one of _. []()&'-
+output_filename_safepattern:(^\.|/\.|[^a-zA-Z0-9_\. \[\]\(\)&'-]+)
 
 ## entries to make epub subjects and calibre tags
 ## lastupdate creates two tags: "Last Update Year/Month: %Y/%m" and "Last Update: %Y/%m/%d"
@@ -196,20 +198,29 @@ connect_timeout:60.0
 ## For example, you could change Sci-Fi=>SF, remove *-Centered tags,
 ## etc.  See http://docs.python.org/library/re.html (look for re.sub)
 ## for regexp details.
+##
 ## Make sure to keep at least one space at the start of each line and
 ## to escape % to %%, if used.
+##
 ## Two, three or five part lines.  Two part effect everything.
 ## Three part effect only those key(s) lists.
 ## *Five* part lines.  Effect only when trailing conditional key=>regexp matches
 ## metakey[,metakey]=>pattern=>replacement[&&conditionalkey=>regexp]
+##
 ## Note that if metakey == conditionalkey the conditional is ignored.
 ## You can use \s in the replacement to add explicit spaces.  (The config parser
 ## tends to discard trailing spaces.)
+##
 ## replace_metadata <entry>_LIST options: FanFicFare replace_metadata lines
 ## operate on individual list items for list entries. But if you
 ## want to do a replacement on the joined string for the whole list,
 ## you can by using <entry>_LIST. Example, if you added
 ## calibre_author: calibre_author_LIST=>^(.{,100}).*$=>\1
+##
+## You can 'split' one list item into multiple list entries by using
+## \' in the replacement string.
+##
+## Examples:
 #replace_metadata:
 # genre,category=>Sci-Fi=>SF
 # Puella Magi Madoka Magica.* => Madoka
@@ -219,6 +230,8 @@ connect_timeout:60.0
 # .*-Centered=>
 # characters=>Sam W\.=>Sam Witwicky&&category=>Transformers
 # characters=>Sam W\.=>Sam Winchester&&category=>Supernatural
+# category=>Bitextual=>M/M\,F/M
+
 
 ## Include/Exclude metadata
 ##
@@ -243,7 +256,7 @@ connect_timeout:60.0
 ##
 ## This is fairly complicated, so it's documented on its own wiki
 ## page:
-## https://code.google.com/p/fanficdownloader/wiki/InExcludeMetadataFeature
+## https://github.com/JimmXinu/FanFicFare/wiki/InExcludeMetadataFeature
 
 ## Some readers don't show horizontal rule (<hr />) tags correctly.
 ## This replaces them all with a centered '* * *'.  (Note centering
@@ -365,21 +378,21 @@ user_agent:FFF/2.X
 bulk_load:true
 
 [base_xenforoforum]
-## Currently only forums.spacebattles.com and forums.sufficientvelocity.com
 
-cover_exclusion_regexp:/clear.png
+cover_exclusion_regexp:/styles/
 
 ## I saw lots of chapters name simply '1.1' etc during testing.
 strip_chapter_numbers:false
 
 ## Copy title to tagsfromtitle for parsing tags.
-add_to_extra_valid_entries:,tagsfromtitle
+add_to_extra_valid_entries:,tagsfromtitle,forumtags
 
 ## '.NOREPL' tells the system to *not* apply title's
 ## in/exclude/replace_metadata -- Only works on include_in_ lines.
 include_in_tagsfromtitle:title.NOREPL
 
 tagsfromtitle_label:Tags from Title
+forumtags_label:Tags from Forum
 
 ## might want to do this, maybe not.  Will often include category, but
 ## also often include non-category stuff.
@@ -388,26 +401,40 @@ tagsfromtitle_label:Tags from Title
 add_to_include_metadata_pre:
 # only keep tagsfromtitle with ( or [ in.
  tagsfromtitle=~[\[\(]
- 
+
+## disable chapter range in title because of tagsfromtitle processing.
+title_chapter_range_pattern:
+
 add_to_replace_metadata:
+# for QuestionableQuesting NSFW subforum.
+ tagsfromtitle=>^\[NSFW\].*?([\(\[]([^\]\)]+)[\)\]]).*?$=>NSFW,\2
 # remove anything outside () or []
- tagsfromtitle=>^.*?([\(\[]([^\]\)]+)[\)\]]).*?$=>\1
+ tagsfromtitle=>^.*?([\(\[]([^\]\)]+)[\)\]]).*?$=>\2
 # remove () []
- tagsfromtitle=>[\(\)\[\]]=>
+# tagsfromtitle=>[\(\)\[\]]=>
 # change (spaces)slash(or semicolon)(spaces) to comma
  tagsfromtitle=> *[/;] *=>,
- tagsfromtitle=> x =>,
- 
+ tagsfromtitle=> [xX] =>,
+
 # remove [] or () blocks and leading/trailing spaces/dashes/colons
  title=>[-: ]*[\(\[]([^\]\)]+)[\)\]][-: ]*=>
 # remove 'Thread' and the next word, usually "Thread 2", "Thread
-# four", "Thread iv", etc
- title=>[-: ]*[Tt]hread [^ ]+[-: ]*=>
+# four", "Thread iv", "Story Thread", etc
+ title,tagsfromtitle=>[-: ]*(Story *)?[Tt]hread [^ ]+[-: ]*=>
 
-add_to_extra_titlepage_entries:,tagsfromtitle
+# Normalize 'fanfiction/fanfic/fan-fiction' a little.
+ forumtags=>[Ff]an-?[Ff]ic(tion)?=>FanFiction
 
+add_to_extra_titlepage_entries:,tagsfromtitle,forumtags
+
+## XenForo tags are all lowercase everywhere that I've seen.  This
+## makes the first letter of each word uppercase.  Applied before
+## replace_metadata.
+capitalize_forumtags:true
+
+## Add both title tags and forumtags to standard (subject) tags.
 ## '.SPLIT' tells the system to split by ','
-add_to_include_subject_tags:,tagsfromtitle.SPLIT
+add_to_include_subject_tags:,tagsfromtitle.SPLIT,forumtags
 
 ## base_xenforoforum reads Published and Updated datetimes from
 ## Threadmarks if used, or from the posted & updated times of the
@@ -419,6 +446,13 @@ dateUpdated_format:%%Y-%%m-%%d %%H:%%M:%%S
 ## the description.
 description_limit:500
 
+## Because base_xenforoforum adapters can pull chapter URLs from human
+## posts, the odds of errors in the chapter URLs are vastly higher.
+## You can set continue_on_chapter_error:true to continue on after
+## failing to download a chapter and instead record an error message
+## in the ebook for that chapter.
+continue_on_chapter_error:false
+
 ## Each output format has a section that overrides [defaults]
 [html]
 
@@ -618,6 +652,7 @@ nook_img_fix:true
 ## URLs like: http://test1.com?sid=12345
 [test1.com]
 extratags: FanFiction,Testing
+
 # extracategories:Fafner
 # extragenres:Romance,Fluff
 # extracharacters:Reginald Smythe-Smythe,Mokona,Harry P.
@@ -858,12 +893,6 @@ extracategories:Buffy: The Vampire Slayer
 extracharacters:Buffy, Spike
 extraships:Spike/Buffy
 
-[devianthearts.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
-
 [dramione.org]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -1251,7 +1280,7 @@ extracategories:NCIS
 extracategories:Buffy: The Vampire Slayer
 extracharacters:Willow
 
-[ninelives.dark-solace.org]
+[ninelivesarchive.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:The Walking Dead
 extracharacters:Carol,Daryl
@@ -1330,6 +1359,16 @@ extracategories:My Little Pony: Friendship is Magic
 ## Site dedicated to these categories/characters/ships
 extracategories:The Pretender
 
+[forum.questionablequesting.com]
+## see [base_xenforoforum]
+
+## 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
+
 [samandjack.net]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -1499,22 +1538,6 @@ readings_label: Readings
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
-[thequidditchpitch.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
-
-## Site dedicated to these categories/characters/ships
-extracategories:Harry Potter
-
 [tokra.fandomnet.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
@@ -1851,6 +1874,15 @@ rating_titles: R=RESTRICTED (16+), E=EXEMPT (18+), I=ART HOUSE, T=To every, A=IN
 adult_ratings: E,R
 
 [www.mediaminer.org]
+dateUpdated_format:%%Y-%%m-%%d %%H:%%M:%%S
+## Note that mediaminer doesn't give datePublished on the story's
+## index page--it's collected from the earliest uploaded chapter.  So
+## it's not available when only fetching metadata.
+datePublished_format:%%Y-%%m-%%d %%H:%%M:%%S
+
+## some sites include images that we don't ever want becoming the
+## cover image.  This lets you exclude them.
+cover_exclusion_regexp:/img/rss.png
 
 [www.midnightwhispers.ca]
 ## Some sites do not require a login, but do require the user to
@@ -1869,7 +1901,7 @@ cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
 ## Site dedicated to these categories/characters/ships
 extracategories:NCIS
 
-[www.nickandgreg.net]
+[www.nickngreg.nl]
 ## Site dedicated to these categories/characters/ships
 extracategories:CSI
 extraships:Nick Stokes/Greg Sanders
@@ -1918,6 +1950,13 @@ extracategories:Psych
 ## Site dedicated to these categories/characters/ships
 extracategories:Queer as Folk
 
+[quotev.com]
+extra_valid_entries:pages,readers,reads,favorites
+pages_label:Pages
+readers_label:Readers
+reads_label:Reads
+favorites_label:Favorites
+
 [www.restrictedsection.org]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In

fanficfare/epubutils.py

@@ -41,7 +41,7 @@ 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
     logfile = None
@@ -158,20 +158,20 @@ def get_update_data(inputio,
                         chapterorigtitle = soup.find('meta',{'name':'chapterorigtitle'})
                         if chapterorigtitle:
                             datamaps[currenturl]['chapterorigtitle'] = chapterorigtitle['content']
-                            
+
                         chaptertitle = soup.find('meta',{'name':'chaptertitle'})
                         if chaptertitle:
                             datamaps[currenturl]['chaptertitle'] = chaptertitle['content']
-                            
+
                         soups.append(bodysoup)
-                        
+
                     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])))
     # print("datamaps:%s"%datamaps)
@@ -199,7 +199,7 @@ def get_story_url_from_html(inputio,_is_good_url=None):
 
     ## Save the path to the .opf file--hrefs inside it are relative to it.
     relpath = get_path_part(rootfilename)
-            
+
     # spin through the manifest--only place there are item tags.
     for item in contentdom.getElementsByTagName("item"):
         # First, count the 'chapter' files.  FFF uses file0000.xhtml,
@@ -225,7 +225,7 @@ def reset_orig_chapters_epub(inputio,outfile):
 
     ## build zip in memory in case updating in place(CLI).
     zipio = StringIO()
-    
+
     ## Write mimetype file, must be first and uncompressed.
     ## Older versions of python(2.4/5) don't allow you to specify
     ## compression by individual file.
@@ -240,37 +240,47 @@ def reset_orig_chapters_epub(inputio,outfile):
     outputepub.debug = 3
 
     changed = False
-    
+
+    unmerge_tocncxdoms = {}
+    ## spin through file contents, saving any unmerge toc.ncx files.
+    for zf in inputepub.namelist():
+        ## logger.debug("zf:%s"%zf)
+        if zf.endswith('/toc.ncx'):
+            ## logger.debug("toc.ncx zf:%s"%zf)
+            unmerge_tocncxdoms[zf] = parseString(inputepub.read(zf))
+
     tocncxdom = parseString(inputepub.read('toc.ncx'))
     ## spin through file contents.
     for zf in inputepub.namelist():
-        if zf not in ['mimetype','toc.ncx'] :
+        if zf not in ['mimetype','toc.ncx'] and not zf.endswith('/toc.ncx'):
             entrychanged = False
             data = inputepub.read(zf)
             # if isinstance(data,unicode):
             #     logger.debug("\n\n\ndata is unicode\n\n\n")
             if re.match(r'.*/file\d+\.xhtml',zf):
+                #logger.debug("zf:%s"%zf)
                 data = data.decode('utf-8')
                 soup = bs.BeautifulSoup(data,"html5lib")
-                
+
                 chapterorigtitle = None
                 tag = soup.find('meta',{'name':'chapterorigtitle'})
                 if tag:
-                    chapterorigtitle = tag['content']
+                    chapterorigtitle = tag['content'].replace('&','&').replace('"','"')
 
                 # toctitle is separate for add_chapter_numbers:toconly users.
                 chaptertoctitle = None
                 tag = soup.find('meta',{'name':'chaptertoctitle'})
                 if tag:
-                    chaptertoctitle = tag['content']
+                    chaptertoctitle = tag['content'].replace('&','&').replace('"','"')
                 elif chapterorigtitle:
                     chaptertoctitle = chapterorigtitle
-                    
+
                 chaptertitle = None
                 tag = soup.find('meta',{'name':'chaptertitle'})
                 if tag:
-                    chaptertitle = tag['content']
+                    chaptertitle = tag['content'].replace('&','&').replace('"','"')
 
+                # logger.debug("chaptertitle:(%s) chapterorigtitle:(%s)"%(chaptertitle, chapterorigtitle))
                 if chaptertitle and chapterorigtitle and chapterorigtitle != chaptertitle:
                     origdata = data
                     # print("\n%s\n%s\n"%(chapterorigtitle,chaptertitle))
@@ -281,34 +291,33 @@ def reset_orig_chapters_epub(inputio,outfile):
 
                     entrychanged = ( origdata != data )
                     changed = changed or entrychanged
-                    
+
                     if entrychanged:
-                        ## go after the TOC entry, too.
-                        # <navPoint id="file0005" playOrder="6">
-                        #   <navLabel>
-                        #     <text>5. (new) Chapter 4</text>
-                        #   </navLabel>
-                        #   <content src="OEBPS/file0005.xhtml"/>
-                        # </navPoint>
-                        for contenttag in tocncxdom.getElementsByTagName("content"):
-                            if contenttag.getAttribute('src') == zf:
-                                texttag = contenttag.parentNode.getElementsByTagName('navLabel')[0].getElementsByTagName('text')[0]
-                                texttag.childNodes[0].replaceWholeText(chaptertoctitle)
-                                # logger.debug("text label:%s"%texttag.toxml())
-                                continue
-                    
+                        _replace_tocncx(tocncxdom,zf,chaptertoctitle)
+                        ## Also look for and update individual
+                        ## book toc.ncx files for anthology in case
+                        ## it's unmerged.
+                        zf_toc = zf[:zf.rfind('/OEBPS/')]+'/toc.ncx'
+                        mergedprefix_len = len(zf[:zf.rfind('/OEBPS/')])+1
+
+                        if zf_toc in unmerge_tocncxdoms:
+                            _replace_tocncx(unmerge_tocncxdoms[zf_toc],zf[mergedprefix_len:],chaptertoctitle)
+
                 outputepub.writestr(zf,data.encode('utf-8'))
             else:
                 # possibly binary data, thus no .encode().
                 outputepub.writestr(zf,data)
 
+    for tocnm, tocdom in unmerge_tocncxdoms.items():
+        outputepub.writestr(tocnm,tocdom.toxml(encoding='utf-8'))
+
     outputepub.writestr('toc.ncx',tocncxdom.toxml(encoding='utf-8'))
     outputepub.close()
     # 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:
         zf.create_system = 0
-        
+
     # only *actually* write if changed.
     if changed:
         if isinstance(outfile,basestring):
@@ -319,5 +328,21 @@ def reset_orig_chapters_epub(inputio,outfile):
 
     inputepub.close()
     zipio.close()
-            
+
     return changed
+
+
+def _replace_tocncx(tocncxdom,zf,chaptertoctitle):
+    ## go after the TOC entry, too.
+    # <navPoint id="file0005" playOrder="6">
+    #   <navLabel>
+    #     <text>5. (new) Chapter 4</text>
+    #   </navLabel>
+    #   <content src="OEBPS/file0005.xhtml"/>
+    # </navPoint>
+    for contenttag in tocncxdom.getElementsByTagName("content"):
+        if contenttag.getAttribute('src') == zf:
+            texttag = contenttag.parentNode.getElementsByTagName('navLabel')[0].getElementsByTagName('text')[0]
+            texttag.childNodes[0].replaceWholeText(chaptertoctitle)
+            #logger.debug("text label:%s"%texttag.toxml())
+            continue

fanficfare/story.py

@@ -682,7 +682,10 @@ class Story(Configurable):
         if self.isList('author'): # more than one author, assume multiple authorUrl too.
             htmllist=[]
             for i, v in enumerate(self.getList('author')):
-                aurl = self.getList('authorUrl')[i]
+                if len(self.getList('authorUrl')) <= i:
+                    aurl = None
+                else:
+                    aurl = self.getList('authorUrl')[i]
                 auth = v
                 # make sure doreplacements & removeallentities are honored.
                 if doreplacements:
@@ -927,9 +930,12 @@ class Story(Configurable):
 
         if not allowunsafefilename:
             values={}
-            pattern = re_compile(self.getConfig("output_filename_safepattern",r"[^a-zA-Z0-9_\. \[\]\(\)&'-]+"),"output_filename_safepattern")
+            pattern = re_compile(self.getConfig("output_filename_safepattern",r"(^\.|/\.|[^a-zA-Z0-9_\. \[\]\(\)&'-]+)"),"output_filename_safepattern")
             for k in origvalues.keys():
-                values[k]=re.sub(pattern,'_', removeAllEntities(self.getMetadata(k)))
+                if k == 'formatext': # don't do file extension--we set it anyway.
+                    values[k]=self.getMetadata(k)
+                else:
+                    values[k]=re.sub(pattern,'_', removeAllEntities(self.getMetadata(k)))
 
         return string.Template(template).substitute(values).encode('utf8')
 

fanficfare/writers/writer_epub.py

@@ -48,7 +48,6 @@ class EpubWriter(BaseStoryWriter):
         self.EPUB_CSS = string.Template('''${output_css}''')
         
         self.EPUB_TITLE_PAGE_START = string.Template('''<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
 <html xmlns="http://www.w3.org/1999/xhtml">
 <head>
 <title>${title} by ${author}</title>
@@ -75,7 +74,6 @@ ${value}<br />
 ''')
 
         self.EPUB_TABLE_TITLE_PAGE_START = string.Template('''<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
 <html xmlns="http://www.w3.org/1999/xhtml">
 <head>
 <title>${title} by ${author}</title>
@@ -106,7 +104,6 @@ ${value}<br />
 ''')
 
         self.EPUB_TOC_PAGE_START = string.Template('''<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
 <html xmlns="http://www.w3.org/1999/xhtml">
 <head>
 <title>${title} by ${author}</title>
@@ -128,7 +125,6 @@ ${value}<br />
 ''')
 
         self.EPUB_CHAPTER_START = string.Template('''<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
 <html xmlns="http://www.w3.org/1999/xhtml">
 <head>
 <title>${chapter}</title>
@@ -148,7 +144,6 @@ ${value}<br />
 ''')
 
         self.EPUB_LOG_PAGE_START = string.Template('''<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
 <html xmlns="http://www.w3.org/1999/xhtml">
 <head>
 <title>Update Log</title>
@@ -233,7 +228,7 @@ div { margin: 0pt; padding: 0pt; }
                 # <span id="dateUpdated">1975-04-15</span>
                 span = '<span id="%s">'%entry
                 idx = logfile.rindex(span)+len(span)
-                values[entry] = logfile[idx:logfile.index('</span>',idx)]
+                values[entry] = logfile[idx:logfile.index('</span>\n',idx)]
             except Exception, e:
                 #print("e:%s"%e)
                 pass
@@ -284,7 +279,9 @@ div { margin: 0pt; padding: 0pt; }
         retval = retval + END.substitute(self.story.getAllMetadata())
         
         if self.getConfig('replace_hr'):
-            retval = retval.replace("<hr />","<div class='center'>* * *</div>")
+            # replacing a self-closing tag with a container tag in the
+            # soup is more difficult than it first appears.  So cheat.
+            retval = re.sub("<hr[^>]*>","<div class='center'>* * *</div>",retval)
             
         return retval
                 
@@ -658,11 +655,14 @@ div { margin: 0pt; padding: 0pt; }
             if chap.html:
                 logger.debug('Writing chapter text for: %s' % chap.title)
                 vals={'url':removeEntities(chap.url),
-                      'chapter':chap.title,
-                      'origchapter':chap.origtitle,
-                      'tocchapter':chap.toctitle,
+                      'chapter':removeEntities(chap.title),
+                      'origchapter':removeEntities(chap.origtitle),
+                      'tocchapter':removeEntities(chap.toctitle),
                       'index':"%04d"%(index+1),
                       'number':index+1}
+                # escape double quotes in all vals.
+                for k,v in vals.items():
+                    if isinstance(v,basestring): vals[k]=v.replace('"','&quot;')
                 fullhtml = CHAPTER_START.substitute(vals) + \
                     chap.html + CHAPTER_END.substitute(vals)
                 # ffnet(& maybe others) gives the whole chapter text

fanficfare/writers/writer_html.py

@@ -33,9 +33,8 @@ class HTMLWriter(BaseStoryWriter):
     def __init__(self, config, story):
         BaseStoryWriter.__init__(self, config, story)
         
-        self.HTML_FILE_START = string.Template('''<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
-<html xmlns="http://www.w3.org/1999/xhtml">
+        self.HTML_FILE_START = string.Template('''<!DOCTYPE html>
+<html>
 <head>
 <title>${title} by ${author}</title>
 <style type="text/css">
@@ -87,7 +86,6 @@ ${output_css}
 
 
     def writeStoryImpl(self, out):
-
         if self.hasConfig("cover_content"):
             COVER = string.Template(self.getConfig("cover_content"))
         else:

setup.py

@@ -10,13 +10,11 @@ https://github.com/pypa/sampleproject
 # Always prefer setuptools over distutils
 from setuptools import setup, find_packages
 # To use a consistent encoding
-from codecs import open
+import codecs
 from os import path
 
-here = path.abspath(path.dirname(__file__))
-
 # Get the long description from the relevant file
-with open(path.join(here, 'DESCRIPTION.rst'), encoding='utf-8') as f:
+with codecs.open('DESCRIPTION.rst', encoding='utf-8') as f:
     long_description = f.read()
 
 setup(
@@ -25,7 +23,7 @@ setup(
     # Versions should comply with PEP440.  For a discussion on single-sourcing
     # the version across setup.py and the project code, see
     # https://packaging.python.org/en/latest/single_source_version.html
-    version="2.2.11",
+    version="2.2.14",
 
     description='A tool for downloading fanfiction to eBook formats',
     long_description=long_description,

webservice/app.yaml

@@ -1,6 +1,6 @@
 # ffd-retief-hrd fanficfare
 application: fanficfare
-version: 2-2-11
+version: 2-2-14
 runtime: python27
 api_version: 1
 threadsafe: true

webservice/index.html

@@ -27,43 +27,25 @@
 	      much easier. </p>
 	  </div>
 
-	  <h3>New Name and URL</h3>
-          <p>
-            This version changes the name of the project from
-            FanFictionDownLoader(FFDL) to FanFicFare.  Along with
-            the name change, there are changes to the internal
-            structuring of the project code, but not to the functionality.
-          </p>
-          <p>
-            If you had saved configuration (including your
-            username/password for fic sites) in FFDL, you will need to
-            copy it over to FanFicFare.  Visit
-            the <a href="http://fanfictiondownloader.appspot.com/editconfig">FFDL
-            User Config</a> page, copy your settings and then paste
-            them on
-            the <a href="http://fanficfare.appspot.com/editconfig">FanFicFare
-            User Config</a> page.
-          </p>
 	  <h3>Changes:</h3>
 	  <ul>
-            <li>Add chapter limits with URL by giving chapter range.<br>
-              Examples:<br>
-              <ul>
-              <li>https://www.fanfiction.net/s/2565609/1/[4] <i>Chapter 4 only</i></li>
-              <li>https://www.fanfiction.net/s/2565609/1/[6-10] <i>Chapters 6, 7, 8, 9 &amp; 10 only</i></li>
-              <li>https://www.fanfiction.net/s/2565609/1/[-10] <i>Chapters 1-10 only</i></li>
-              <li>https://www.fanfiction.net/s/2565609/1/[150-] <i>Chapters 150 and up only</i></li>
-              </ul>
-              The chapter range will be included in the ebook title.  Can be changed or disabled in config with title_chapter_range_pattern.
-            </li>
-            <li>New base_xenforoforum adapter type.  The details are complex enough that I've started a <a href="https://github.com/JimmXinu/FanFicFare/wiki/BaseXenForoForumAdapters">new wiki page</a> for future reference. Please refer to it for more details.</li>
-            <li>New [base_efiction] and [base_xenforoforum] sections for common settings for eFiction Base and XenForoForum Base adapters respectively.</li>
-            <li>New site: <a href="https://forums.spacebattles.com/forums/creative-writing.18/">forums.spacebattles.com</a> base_xenforoforum adapter</li>
-            <li>New site: <a href="https://forums.sufficientvelocity.com/forums/user-fiction.2/">forums.sufficientvelocity.com</a> base_xenforoforum adapter</li>
-            <li>New site: <a href="http://ninelives.dark-solace.org/">ninelives.dark-solace.org</a> base_efiction adapter</li>
-            <li>New description_limit feature to explicitly limit the allowable length of the description.</li>
-            <li>Fixes for http://spikeluver.com</li>
-            <li>New Russian language site: masseffect2.in -- Thanks to PlushBeaver for adding this.</li>
+            <li>Remove site thequidditchpitch.org, domain is parked.</li>
+            <li>Remove site devianthearts.com, server not found for a week.</li>
+            <li>Change site www.nickandgreg.net to www.nickngreg.nl while still accepting old URLs.</li>
+            <li>Change site ninelives.dark-solace.org to new domain ninelivesarchive.com.</li>
+            <li>Change site questionablequesting.com to forum.questionablequesting.com only.  Supporting both caused problems.</li>
+            <li>Fixes for hpfandom.net changes.</li>
+            <li>Fix for bloodshedverse.com.</li>
+            <li>Fixes for quotev.com (thanks, cryzed)</li>
+            <li>Fixes for base_xenforoforum adapters.</li>
+            <li>Add continue_on_chapter_error feature for base_xenforoforum adapters.</li>
+            <li>Add user/pass login for NSFW forums on forum.questionablequesting.com.</li>
+            <li>Add capitalize_forumtags feature to base_xenforoforum and include forumtags by default.</li>
+            <li>Account for base href in base_xenforoforum so emoticon images work.</li>
+            <li>Correct cover_exclusion_regexp for base_xenforoforum.</li>
+            <li>Change default HTML output to HTML5 header.</li>
+            <li>Update html tag header at beginning of each epub file.  Prompted by failure of old header on latest tolino ereader.</li>
+            <li>Fix replace_hr feature.</li>
 	  </ul>
 	  <p>
 	    Questions?  Check out our 
@@ -73,7 +55,7 @@
 	    If you have any problems with this application, please
 	    report them in
 	    the <a href="http://groups.google.com/group/fanfic-downloader">FanFicFare Google Group</a>.  The
-	    <a href="http://2-2-10.fanficfare.appspot.com">previous version
+	    <a href="http://2-2-13.fanficfare.appspot.com">previous version
 	    </a> is also available for you to use if necessary.
 	  </p>
 	  <div id='error'>