Fix author URLs for multiple author stories, bump versions again.

efiction.esteliel.de, and pommedesang.com

app.yaml

@@ -1,6 +1,6 @@
 # ffd-retief-hrd fanfictiondownloader
 application: fanfictiondownloader
-version: 4-4-29
+version: 4-4-42
 runtime: python27
 api_version: 1
 threadsafe: true

calibre-plugin/__init__.py

@@ -27,7 +27,7 @@ class FanFictionDownLoaderBase(InterfaceActionBase):
     description         = 'UI plugin to download FanFiction stories from various sites.'
     supported_platforms = ['windows', 'osx', 'linux']
     author              = 'Jim Miller'
-    version             = (1, 6, 14)
+    version             = (1, 7, 8)
     minimum_calibre_version = (0, 8, 57)
 
     #: This field defines the GUI plugin class that contains all the code

calibre-plugin/common_utils.py

@@ -196,7 +196,7 @@ class ImageTitleLayout(QHBoxLayout):
     '''
     A reusable layout widget displaying an image followed by a title
     '''
-    def __init__(self, parent, icon_name, title):
+    def __init__(self, parent, icon_name, title, tooltip=None):
         QHBoxLayout.__init__(self)
         title_image_label = QLabel(parent)
         pixmap = get_pixmap(icon_name)
@@ -217,6 +217,9 @@ class ImageTitleLayout(QHBoxLayout):
         self.addWidget(shelf_label)
         self.insertStretch(-1)
 
+        if tooltip:
+            title_image_label.setToolTip(tooltip)
+            shelf_label.setToolTip(tooltip)
 
 class SizePersistedDialog(QDialog):
     '''

calibre-plugin/config.py

@@ -7,20 +7,24 @@ __license__   = 'GPL v3'
 __copyright__ = '2012, Jim Miller'
 __docformat__ = 'restructuredtext en'
 
-import traceback, copy
+import traceback, copy, threading
 from collections import OrderedDict
 
-from PyQt4.Qt import (QDialog, QWidget, QVBoxLayout, QHBoxLayout, QLabel, QLineEdit, QFont, QWidget,
-                      QTextEdit, QComboBox, QCheckBox, QPushButton, QTabWidget, QVariant, QScrollArea)
+from PyQt4.Qt import (QDialog, QWidget, QVBoxLayout, QHBoxLayout, QLabel,
+                      QLineEdit, QFont, QWidget, QTextEdit, QComboBox,
+                      QCheckBox, QPushButton, QTabWidget, QVariant, QScrollArea,
+                      QDialogButtonBox )
 
 from calibre.gui2 import dynamic, info_dialog
 from calibre.utils.config import JSONConfig
 from calibre.gui2.ui import get_gui
 
 from calibre_plugins.fanfictiondownloader_plugin.dialogs \
-    import (UPDATE, UPDATEALWAYS, OVERWRITE, collision_order)
-
-from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.adapters import getConfigSections
+    import (UPDATE, UPDATEALWAYS, OVERWRITE, collision_order, RejectListDialog,
+            EditTextDialog)
+    
+from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.adapters \
+    import (getConfigSections, getNormalStoryURL)
 
 from calibre_plugins.fanfictiondownloader_plugin.common_utils \
     import ( get_library_uuid, KeyboardConfigDialog, PrefsViewerDialog )
@@ -34,6 +38,10 @@ PREFS_KEY_SETTINGS = 'settings'
 # take from here.
 default_prefs = {}
 default_prefs['personal.ini'] = get_resources('plugin-example.ini')
+default_prefs['rejecturls'] = ''
+default_prefs['rejectreasons'] = '''Sucked
+Boring
+Dup from another site'''
 
 default_prefs['updatemeta'] = True
 default_prefs['updatecover'] = False
@@ -137,8 +145,86 @@ class PrefsFacade():
     def save_to_db(self):
         set_library_config(self._get_prefs())
         
-
 prefs = PrefsFacade(default_prefs)
+
+class RejectURLList:
+    def __init__(self,prefs):
+        self.prefs = prefs
+        self.sync_lock = threading.RLock()
+        self.listcache = None
+
+    def _read_list_from_text(self,text,addreasontext=None):
+        cache = {}
+        for line in text.splitlines():
+            if ',' in line:
+                (rejurl,note) = line.split(',',1)
+            else:
+                (rejurl,note) = (line,'')
+            rejurl = getNormalStoryURL(rejurl)
+            if rejurl:
+                if addreasontext and note:
+                    note = note +" - "+addreasontext
+                elif addreasontext:
+                    note = addreasontext
+                cache[rejurl] = note
+        return cache
+        
+
+    def _get_listcache(self):
+        if self.listcache == None:
+            self.listcache = self._read_list_from_text(prefs['rejecturls'])
+        return self.listcache
+
+    def _save_list(self,listcache):
+        rejectlist = []
+        for url in listcache:
+            rejectlist.append("%s,%s"%(url,listcache[url]))
+            
+        self.prefs['rejecturls'] = '\n'.join(rejectlist)
+        self.prefs.save_to_db()
+        self.listcache = None
+        
+    def clear_cache(self):
+        self.listcache = None
+
+    def check(self,url):
+        with self.sync_lock:
+            listcache = self._get_listcache()
+            if url in listcache:
+                note = listcache[url]
+                return note
+            
+            # not found
+            return None
+
+    def remove(self,url):
+        with self.sync_lock:
+            listcache = self._get_listcache()
+            if url in listcache:
+                del listcache[url]
+                self._save_list(listcache)
+
+    def add_text(self,rejecttext,addreasontext):
+        self.add(self._read_list_from_text(rejecttext,addreasontext).items())
+            
+    def add(self,rejectlist,clear=False):
+        # rejectlist=list of (url,note) tuples.
+        with self.sync_lock:
+            if clear:
+                listcache={}
+            else:
+                listcache = self._get_listcache()
+            for (url,note) in rejectlist:
+                listcache[url]=note
+            self._save_list(listcache)
+
+    def get_list(self):
+        return copy.deepcopy(self._get_listcache())
+            
+    def get_reject_reasons(self):
+        return self.prefs['rejectreasons'].splitlines()
+
+rejecturllist = RejectURLList(prefs)
     
 class ConfigWidget(QWidget):
 
@@ -396,6 +482,27 @@ class BasicTab(QWidget):
         self.injectseries.setChecked(prefs['injectseries'])
         self.l.addWidget(self.injectseries)
 
+        self.l.addSpacing(10)        
+
+        horz = QHBoxLayout()
+        
+        self.rejectlist = QPushButton('Edit Reject URL List', self)
+        self.rejectlist.setToolTip("Edit list of URLs FFDL will automatically Reject.")
+        self.rejectlist.clicked.connect(self.show_rejectlist)
+        horz.addWidget(self.rejectlist)
+        
+        self.reject_urls = QPushButton('Add Reject URLs', self)
+        self.reject_urls.setToolTip("Add additional URLs to Reject as text.")
+        self.reject_urls.clicked.connect(self.add_reject_urls)
+        horz.addWidget(self.reject_urls)
+        
+        self.reject_reasons = QPushButton('Edit Reject Reasons List', self)
+        self.reject_reasons.setToolTip("Customize the Reasons presented when Rejecting URLs")
+        self.reject_reasons.clicked.connect(self.show_reject_reasons)
+        horz.addWidget(self.reject_reasons)
+        
+        self.l.addLayout(horz)
+        
         self.l.insertStretch(-1)
         
     def set_collisions(self):
@@ -411,7 +518,53 @@ class BasicTab(QWidget):
     def show_defaults(self):
         text = get_resources('plugin-defaults.ini')
         ShowDefaultsIniDialog(self.windowIcon(),text,self).exec_()
+
+    def show_rejectlist(self):
+        rejectlist = []
+        for (url,note) in rejecturllist.get_list().items():
+            rejectlist.append((None,url,note,note))
+            
+        d = RejectListDialog(self,
+                             rejectlist,
+                             rejectreasons=rejecturllist.get_reject_reasons(),
+                             header="Edit Reject URLs List",
+                             show_delete=False,
+                             show_all_reasons=False)
+        d.exec_()
         
+        if d.result() != d.Accepted:
+            return
+        
+        rejectlist=[]
+        for (bookid,url,note) in d.get_reject_list():
+            rejectlist.append((url,note))
+
+        rejecturllist.add(rejectlist,clear=True)
+        
+    def show_reject_reasons(self):
+        d = EditTextDialog(self,
+                           prefs['rejectreasons'],
+                           icon=self.windowIcon(),
+                           title="Reject Reasons",
+                           label="Customize Reject List Reasons",
+                           tooltip="Customize the Reasons presented when Rejecting URLs")
+        d.exec_()
+        if d.result() == d.Accepted:
+            prefs['rejectreasons'] = d.get_plain_text()
+                
+    def add_reject_urls(self):
+        d = EditTextDialog(self,
+                           "http://example.com?story.php?sid=5,Reason why I rejected it",
+                           icon=self.windowIcon(),
+                           title="Add Reject URLs",
+                           label="Add Reject URLs. Use: <b>http://...,note</b><br>Invalid story URLs will be ignored.",
+                           tooltip="One URL per line, everything after <b>,</b> will be put in the note.",
+                           rejectreasons=rejecturllist.get_reject_reasons(),
+                           reasonslabel='Add this reason to all URLs added:')
+        d.exec_()
+        if d.result() == d.Accepted:
+            rejecturllist.add_text(d.get_plain_text(),d.get_reason_text())
+                
 class PersonalIniTab(QWidget):
 
     def __init__(self, parent_dialog, plugin_action):
@@ -451,7 +604,7 @@ class PersonalIniTab(QWidget):
     def show_defaults(self):
         text = get_resources('plugin-defaults.ini')
         ShowDefaultsIniDialog(self.windowIcon(),text,self).exec_()
-
+        
 class ShowDefaultsIniDialog(QDialog):
 
     def __init__(self, icon, text, parent=None):
@@ -916,3 +1069,4 @@ class StandardColumnsTab(QWidget):
             self.l.addLayout(horz)
         
         self.l.insertStretch(-1)
+

calibre-plugin/dialogs.py

@@ -8,15 +8,19 @@ __copyright__ = '2011, Jim Miller'
 __docformat__ = 'restructuredtext en'
 
 import traceback
+from functools import partial
 
 from PyQt4 import QtGui
-from PyQt4.Qt import (QDialog, QTableWidget, QMessageBox, QVBoxLayout, QHBoxLayout, QGridLayout,
-                      QPushButton, QProgressDialog, QString, QLabel, QCheckBox, QIcon, QTextCursor,
-                      QTextEdit, QLineEdit, QInputDialog, QComboBox, QClipboard, QVariant,
-                      QProgressDialog, QTimer, QDialogButtonBox, QPixmap, Qt, QAbstractItemView )
+from PyQt4.Qt import (QDialog, QTableWidget, QMessageBox, QVBoxLayout, QHBoxLayout,
+                      QGridLayout, QPushButton, QProgressDialog, QString, QLabel,
+                      QCheckBox, QIcon, QTextCursor, QTextEdit, QLineEdit, QInputDialog,
+                      QComboBox, QClipboard, QVariant, QProgressDialog, QTimer,
+                      QDialogButtonBox, QPixmap, Qt, QAbstractItemView, SIGNAL,
+                      QTableWidgetItem )
 
 from calibre.gui2 import error_dialog, warning_dialog, question_dialog, info_dialog
 from calibre.gui2.dialogs.confirm_delete import confirm
+from calibre.gui2.complete2 import EditWithComplete
 
 from calibre import confirm_config_name
 from calibre.gui2 import dynamic
@@ -41,6 +45,19 @@ collision_order=[SKIP,
                  OVERWRITEALWAYS,
                  CALIBREONLY,]
         
+# This is a more than slightly kludgey way to get
+# EditWithComplete to *not* alpha-order the reasons, but leave
+# them in the order entered.  If
+# calibre.gui2.complete2.CompleteModel.set_items ever changes,
+# this function will need to also.
+def complete_model_set_items_kludge(self, items):
+    items = [unicode(x.strip()) for x in items]
+    items = [x for x in items if x]
+    items = tuple(items)
+    self.all_items = self.current_items = items
+    self.current_prefix = ''
+    self.reset()
+    
 class NotGoingToDownload(Exception):
     def __init__(self,error,icon='dialog_error.png'):
         self.error=error
@@ -712,3 +729,321 @@ class StoryListTableWidget(QTableWidget):
             self.setItem(dest_row, col, self.takeItem(src_row, col))
         self.removeRow(src_row)
         self.blockSignals(False)
+
+class RejectListTableWidget(QTableWidget):
+
+    def __init__(self, parent,rejectreasons=[]):
+        QTableWidget.__init__(self, parent)
+        self.setSelectionBehavior(QAbstractItemView.SelectRows)
+        self.rejectreasons = rejectreasons
+
+    def on_headersection_clicked(self):
+        self.setSortingEnabled(True)
+        
+    def populate_table(self, reject_list):
+        self.clear()
+        self.setAlternatingRowColors(True)
+        self.setRowCount(len(reject_list))
+        header_labels = ['URL', 'Note']
+        self.setColumnCount(len(header_labels))
+        self.setHorizontalHeaderLabels(header_labels)
+        self.horizontalHeader().setStretchLastSection(True)
+        #self.verticalHeader().setDefaultSectionSize(24)
+        self.verticalHeader().hide()
+
+        # need sortingEnbled to sort, but off to up & down.
+        self.connect(self.horizontalHeader(),
+                     SIGNAL('sectionClicked(int)'),
+                     self.on_headersection_clicked)
+
+        # row is just row number.
+        for row, rejectrow in enumerate(reject_list):
+            self.populate_table_row(row,rejectrow)
+
+        self.resizeColumnsToContents()
+        self.setMinimumColumnWidth(1, 100)
+        self.setMinimumColumnWidth(2, 100)
+        self.setMinimumSize(300, 0)
+
+    def setMinimumColumnWidth(self, col, minimum):
+        if self.columnWidth(col) < minimum:
+            self.setColumnWidth(col, minimum)
+
+    def populate_table_row(self, row, rejectrow):
+
+        (bookid,url,titleauth,oldrejnote) = rejectrow
+        if oldrejnote:
+            noteprefix = note = oldrejnote
+            # incase the existing note ends with one of the known reasons.
+            for reason in self.rejectreasons:
+                if noteprefix.endswith(' - '+reason):
+                    noteprefix = noteprefix[:-len(' - '+reason)]
+                    break
+        else:
+            noteprefix = note = titleauth
+            
+        if len(noteprefix) > 0:
+            noteprefix = noteprefix+' - '
+            
+        url_cell = ReadOnlyTableWidgetItem(url)
+        url_cell.setData(Qt.UserRole, QVariant(bookid))
+        url_cell.setToolTip('URL to add to the Reject List.')
+        self.setItem(row, 0, url_cell)
+
+        note_cell = EditWithComplete(self)
+
+        note_cell.lineEdit().mcompleter.model().set_items = \
+            partial(complete_model_set_items_kludge,
+                    note_cell.lineEdit().mcompleter.model())
+        
+        items = [note]+[ noteprefix+x for x in self.rejectreasons ]
+        note_cell.update_items_cache(items)
+        note_cell.show_initial_value(note)
+        note_cell.set_separator(None)
+        note_cell.setToolTip('Select or Edit Reject Note.')
+        self.setCellWidget(row, 1, note_cell)
+        
+        # note_cell = QTableWidgetItem(note)
+        # note_cell.setToolTip('Double-click to edit note.')
+        # self.setItem(row, 1, note_cell)
+      
+    def get_reject_list(self):
+        rejectrows = []
+        for row in range(self.rowCount()):
+            bookid = self.item(row, 0).data(Qt.UserRole).toPyObject()
+            url = unicode(self.item(row, 0).text())
+            note = unicode(self.cellWidget(row, 1).currentText()).strip()
+            rejectrows.append((bookid,url,note))
+        return rejectrows
+
+    def remove_selected_rows(self):
+        self.setFocus()
+        rows = self.selectionModel().selectedRows()
+        if len(rows) == 0:
+            return
+        message = '<p>Are you sure you want to remove this URL from the list?'
+        if len(rows) > 1:
+            message = '<p>Are you sure you want to remove the %d selected URLs from the list?'%len(rows)
+        if not confirm(message,'ffdl_rejectlist_delete_item_again', self):
+            return
+        first_sel_row = self.currentRow()
+        for selrow in reversed(rows):
+            self.removeRow(selrow.row())
+        if first_sel_row < self.rowCount():
+            self.select_and_scroll_to_row(first_sel_row)
+        elif self.rowCount() > 0:
+            self.select_and_scroll_to_row(first_sel_row - 1)
+
+    def select_and_scroll_to_row(self, row):
+        self.selectRow(row)
+        self.scrollToItem(self.currentItem())
+
+    def move_rows_up(self):
+        self.setFocus()
+        rows = self.selectionModel().selectedRows()
+        if len(rows) == 0:
+            return
+        first_sel_row = rows[0].row()
+        if first_sel_row <= 0:
+            return
+        # Workaround for strange selection bug in Qt which "alters" the selection
+        # in certain circumstances which meant move down only worked properly "once"
+        selrows = []
+        for row in rows:
+            selrows.append(row.row())
+        selrows.sort()
+        for selrow in selrows:
+            self.swap_row_widgets(selrow - 1, selrow + 1)
+        scroll_to_row = first_sel_row - 1
+        if scroll_to_row > 0:
+            scroll_to_row = scroll_to_row - 1
+        self.scrollToItem(self.item(scroll_to_row, 0))
+
+    def move_rows_down(self):
+        self.setFocus()
+        rows = self.selectionModel().selectedRows()
+        if len(rows) == 0:
+            return
+        last_sel_row = rows[-1].row()
+        if last_sel_row == self.rowCount() - 1:
+            return
+        # Workaround for strange selection bug in Qt which "alters" the selection
+        # in certain circumstances which meant move down only worked properly "once"
+        selrows = []
+        for row in rows:
+            selrows.append(row.row())
+        selrows.sort()
+        for selrow in reversed(selrows):
+            self.swap_row_widgets(selrow + 2, selrow)
+        scroll_to_row = last_sel_row + 1
+        if scroll_to_row < self.rowCount() - 1:
+            scroll_to_row = scroll_to_row + 1
+        self.scrollToItem(self.item(scroll_to_row, 0))
+
+    def swap_row_widgets(self, src_row, dest_row):
+        self.blockSignals(True)
+        self.setSortingEnabled(False)
+        self.insertRow(dest_row)
+        for col in range(0, self.columnCount()):
+            self.setItem(dest_row, col, self.takeItem(src_row, col))
+        self.removeRow(src_row)
+        self.blockSignals(False)
+
+class RejectListDialog(SizePersistedDialog):
+    def __init__(self, gui, reject_list,
+                 rejectreasons=[],
+                 header="List of Books to Reject",
+                 icon='rotate-right.png',
+                 show_delete=True,
+                 show_all_reasons=True,
+                 save_size_name='ffdl:reject list dialog'):
+        SizePersistedDialog.__init__(self, gui, save_size_name)
+        self.gui = gui
+      
+        self.setWindowTitle(header)
+        self.setWindowIcon(get_icon(icon))
+      
+        layout = QVBoxLayout(self)
+        self.setLayout(layout)
+        title_layout = ImageTitleLayout(self, icon, header,
+                                        '<i></i>FFDL will remember these URLs and display the note and offer to reject them if you try to download them again later.')
+        layout.addLayout(title_layout)
+        rejects_layout = QHBoxLayout()
+        layout.addLayout(rejects_layout)
+
+        self.rejects_table = RejectListTableWidget(self,rejectreasons=rejectreasons)
+        rejects_layout.addWidget(self.rejects_table)
+
+        button_layout = QVBoxLayout()
+        rejects_layout.addLayout(button_layout)
+        spacerItem = QtGui.QSpacerItem(20, 40, QtGui.QSizePolicy.Minimum, QtGui.QSizePolicy.Expanding)
+        button_layout.addItem(spacerItem)
+        # self.move_up_button = QtGui.QToolButton(self)
+        # self.move_up_button.setToolTip('Move selected books up the list')
+        # self.move_up_button.setIcon(QIcon(I('arrow-up.png')))
+        # self.move_up_button.clicked.connect(self.books_table.move_rows_up)
+        # button_layout.addWidget(self.move_up_button)
+        self.remove_button = QtGui.QToolButton(self)
+        self.remove_button.setToolTip('Remove selected URL(s) from the list')
+        self.remove_button.setIcon(get_icon('list_remove.png'))
+        self.remove_button.clicked.connect(self.remove_from_list)
+        button_layout.addWidget(self.remove_button)
+        # self.move_down_button = QtGui.QToolButton(self)
+        # self.move_down_button.setToolTip('Move selected books down the list')
+        # self.move_down_button.setIcon(QIcon(I('arrow-down.png')))
+        # self.move_down_button.clicked.connect(self.books_table.move_rows_down)
+        # button_layout.addWidget(self.move_down_button)
+        spacerItem1 = QtGui.QSpacerItem(20, 40, QtGui.QSizePolicy.Minimum, QtGui.QSizePolicy.Expanding)
+        button_layout.addItem(spacerItem1)
+
+        if show_all_reasons:
+            self.reason_edit = EditWithComplete(self)
+            self.reason_edit.lineEdit().mcompleter.model().set_items = \
+                partial(complete_model_set_items_kludge,
+                        self.reason_edit.lineEdit().mcompleter.model())
+            
+            items = ['']+rejectreasons
+            self.reason_edit.update_items_cache(items)
+            self.reason_edit.show_initial_value('')
+            self.reason_edit.set_separator(None)
+            self.reason_edit.setToolTip("This will be added to whatever note you've set for each URL above.")
+            
+            horz = QHBoxLayout()
+            label = QLabel("Add this reason to all URLs added:")
+            label.setToolTip("This will be added to whatever note you've set for each URL above.")
+            horz.addWidget(label)
+            horz.addWidget(self.reason_edit)
+            horz.insertStretch(-1)
+            layout.addLayout(horz)
+                    
+        options_layout = QHBoxLayout()
+
+        if show_delete:
+            self.deletebooks = QCheckBox('Delete Books (including books without FanFiction URLs)?',self)
+            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)
+
+    def remove_from_list(self):
+        self.rejects_table.remove_selected_rows()
+
+    def get_reject_list(self):
+        return self.rejects_table.get_reject_list()
+
+    def get_reason_text(self):
+        return unicode(self.reason_edit.currentText()).strip()
+    
+    def get_deletebooks(self):
+        return self.deletebooks.isChecked()
+
+class EditTextDialog(QDialog):
+
+    def __init__(self, parent, text,
+                 icon=None, title=None, label=None, tooltip=None,
+                 rejectreasons=[],reasonslabel=None
+                 ):
+        QDialog.__init__(self, parent)
+        self.resize(600, 500)
+        self.l = QVBoxLayout()
+        self.setLayout(self.l)
+        self.label = QLabel(label)
+        if title:
+            self.setWindowTitle(title)
+        if icon:
+            self.setWindowIcon(icon)
+        self.l.addWidget(self.label)
+        
+        self.textedit = QTextEdit(self)
+        self.textedit.setLineWrapMode(QTextEdit.NoWrap)
+        self.textedit.setText(text)
+        self.l.addWidget(self.textedit)
+
+        if tooltip:
+            self.label.setToolTip(tooltip)
+            self.textedit.setToolTip(tooltip)
+
+        if rejectreasons or reasonslabel:
+            self.reason_edit = EditWithComplete(self)
+
+            self.reason_edit.lineEdit().mcompleter.model().set_items = \
+                partial(complete_model_set_items_kludge,
+                        self.reason_edit.lineEdit().mcompleter.model())
+            
+            items = ['']+rejectreasons
+            self.reason_edit.update_items_cache(items)
+            self.reason_edit.show_initial_value('')
+            self.reason_edit.set_separator(None)
+            self.reason_edit.setToolTip(reasonslabel)
+            
+            if reasonslabel:
+                horz = QHBoxLayout()
+                label = QLabel(reasonslabel)
+                label.setToolTip(reasonslabel)
+                horz.addWidget(label)
+                horz.addWidget(self.reason_edit)
+                self.l.addLayout(horz)
+            else:
+                self.l.addWidget(self.reason_edit)
+            
+        button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
+        button_box.accepted.connect(self.accept)
+        button_box.rejected.connect(self.reject)
+        self.l.addWidget(button_box)
+
+    def get_plain_text(self):
+        return unicode(self.textedit.toPlainText())
+
+    def get_reason_text(self):
+        return unicode(self.reason_edit.currentText()).strip()
+    

calibre-plugin/ffdl_plugin.py

@@ -41,10 +41,10 @@ from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.configurable i
 from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.epubutils import get_dcsource, get_dcsource_chaptercount, get_story_url_from_html
 from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.geturls import get_urls_from_page
 
-from calibre_plugins.fanfictiondownloader_plugin.config import (prefs, permitted_values)
+from calibre_plugins.fanfictiondownloader_plugin.config import (prefs, permitted_values, rejecturllist)
 from calibre_plugins.fanfictiondownloader_plugin.dialogs import (
     AddNewDialog, UpdateExistingDialog, display_story_list, DisplayStoryListDialog,
-    LoopProgressDialog, UserPassDialog, AboutDialog, CollectURLDialog, 
+    LoopProgressDialog, UserPassDialog, AboutDialog, CollectURLDialog, RejectListDialog,
     OVERWRITE, OVERWRITEALWAYS, UPDATE, UPDATEALWAYS, ADDNEW, SKIP, CALIBREONLY,
     NotGoingToDownload )
 
@@ -145,6 +145,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
     def library_changed(self, db):
         # We need to reset our menus after switching libraries
         self.rebuild_menus()
+        rejecturllist.clear_cache()
         
     def rebuild_menus(self):
         with self.menus_lock:
@@ -190,6 +191,9 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             self.get_list_url_action = self.create_menu_item_ex(self.menu, 'Get Story URLs from Web Page', image='view.png',
                                                                 triggered=self.get_urls_from_page)
 
+            self.reject_list_action = self.create_menu_item_ex(self.menu, 'Reject Selected Books', image='rotate-right.png',
+                                                               triggered=self.reject_list_urls)
+
             # print("platform.system():%s"%platform.system())
             # print("platform.mac_ver()[0]:%s"%platform.mac_ver()[0])
             if not self.check_macmenuhack(): # not platform.mac_ver()[0]: # Some macs crash on these menu items for unknown reasons.
@@ -211,7 +215,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                 if menu_id not in self.actions_unique_map:
                     self.gui.keyboard.unregister_shortcut(unique_name)
             self.old_actions_unique_map = self.actions_unique_map
-            self.gui.keyboard.finalize()            
+            self.gui.keyboard.finalize()
 
     def about(self):
         # Get the about text from a file inside the plugin zip file
@@ -238,15 +242,28 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         #print("create_menu_item_ex after %s"%menu_text)
         return ac
 
+    def is_library_view(self):
+        # 0 = library, 1 = main, 2 = card_a, 3 = card_b
+        return self.gui.stack.currentIndex() == 0
+    
     def plugin_button(self):
-        if len(self.gui.library_view.get_selected_ids()) > 0 and prefs['updatedefault']:
+        if self.is_library_view() and \
+                len(self.gui.library_view.get_selected_ids()) > 0 and \
+                prefs['updatedefault']:
             self.update_existing()
         else:
             self.add_dialog()
 
     def update_lists(self,add=True):
-        if len(self.gui.library_view.get_selected_ids()) > 0 and \
-                (prefs['addtolists'] or prefs['addtoreadlists']) :
+        if prefs['addtolists'] or prefs['addtoreadlists']:
+            if not self.is_library_view():
+                self.gui.status_bar.show_message(_('Cannot Update Reading Lists from Device View'), 3000)
+                return
+        
+            if len(self.gui.library_view.get_selected_ids()) == 0:
+                self.gui.status_bar.show_message(_('No Selected Books to Update Reading Lists'), 3000)
+                return
+
             self._update_reading_lists(self.gui.library_view.get_selected_ids(),add)
 
     def get_urls_from_page(self):
@@ -273,30 +290,44 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         url_list = get_urls_from_page(url,configuration)
 
         if url_list:
-            d = ViewLog(_("List of URLs"),"\n".join(url_list),parent=self.gui)
-            d.setWindowIcon(get_icon('bookmarks.png'))
-            d.exec_()
+            self.add_dialog("\n".join(url_list))
         else:
-            info_dialog(self.gui, _('List of URLs'),
-                        _('No Valid URLs found on given page.'),
+            info_dialog(self.gui, _('List of Story URLs'),
+                        _('No Valid Story URLs found on given page.'),
                         show=True,
                         show_copy_button=False)
         
             
     def get_list_urls(self):
-        if len(self.gui.library_view.get_selected_ids()) > 0:
-            book_list = map( partial(self._convert_id_to_book, good=False), self.gui.library_view.get_selected_ids() )
+        if self.gui.current_view().selectionModel().selectedRows() == 0 :
+            self.gui.status_bar.show_message(_('No Selected Books to Get URLs From'),
+                                             3000)
+            return
+            
+        if self.is_library_view():
+            book_list = map( partial(self._convert_id_to_book, good=False),
+                             self.gui.library_view.get_selected_ids() )
 
-            LoopProgressDialog(self.gui,
-                               book_list,
-                               partial(self._get_story_url_for_list, db=self.gui.current_db),
-                               self._finish_get_list_urls,
-                               init_label="Collecting URLs for stories...",
-                               win_title="Get URLs for stories",
-                               status_prefix="URL retrieved")
+        else: # device view, get from epubs on device.
+            view = self.gui.current_view()
+            rows = view.selectionModel().selectedRows()
+            # paths = view.model().paths(rows)
+            book_list = map( partial(self._convert_row_to_book, good=False), rows )
+            
+        LoopProgressDialog(self.gui,
+                           book_list,
+                           partial(self._get_story_url_for_list, db=self.gui.current_db),
+                           self._finish_get_list_urls,
+                           init_label="Collecting URLs for stories...",
+                           win_title="Get URLs for stories",
+                           status_prefix="URL retrieved")
             
     def _get_story_url_for_list(self,book,db=None):
-        book['url'] = self._get_story_url(db,book['calibre_id'])
+        if book['calibre_id']:
+            book['url'] = self._get_story_url(db,book_id=book['calibre_id'])
+        elif book['path']:
+            book['url'] = self._get_story_url(db,path=book['path'])
+            
         if book['url'] == None:
             book['good']=False
         else:
@@ -305,21 +336,99 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
     def _finish_get_list_urls(self, book_list):
         url_list = [ x['url'] for x in book_list if x['good'] ]
         if url_list:
-            d = ViewLog(_("List of URLs"),"\n".join(url_list),parent=self.gui)
+            d = ViewLog(_("List of Story URLs"),"\n".join(url_list),parent=self.gui)
             d.setWindowIcon(get_icon('bookmarks.png'))
             d.exec_()
         else:
             info_dialog(self.gui, _('List of URLs'),
-                        _('No URLs found in selected books.'),
+                        _('No Story URLs found in selected books.'),
                         show=True,
                         show_copy_button=False)
                 
-    def add_dialog(self):
+    def reject_list_urls(self):
+        if self.is_library_view():
+            book_list = map( partial(self._convert_id_to_book, good=False),
+                             self.gui.library_view.get_selected_ids() )
+
+        else: # device view, get from epubs on device.
+            view = self.gui.current_view()
+            rows = view.selectionModel().selectedRows()
+            #paths = view.model().paths(rows)
+            book_list = map( partial(self._convert_row_to_book, good=False), rows )
+            
+        if len(book_list) == 0 :
+            self.gui.status_bar.show_message(_('No Selected Books have URLs to Reject'), 3000)
+            return
+            
+        LoopProgressDialog(self.gui,
+                           book_list,
+                           partial(self._reject_story_url_for_list, db=self.gui.current_db),
+                           self._finish_reject_list_urls,
+                           init_label="Collecting URLs for Reject List...",
+                           win_title="Get URLs for Reject List",
+                           status_prefix="URL retrieved")
+            
+    def _reject_story_url_for_list(self,book,db=None): 
+        if book['calibre_id']:
+            # want title/author, too, for rejects.
+            self._populate_book_from_calibre_id(book,db)
+            book['url'] = self._get_story_url(db,book_id=book['calibre_id'])
+        elif book['path']:
+            book['url'] = self._get_story_url(db,path=book['path'])
+                
+        if book['url'] == None:
+            book['good']=False
+        else:
+            book['good']=True
+            # get existing note, if there is one.
+            book['oldrejnote']=rejecturllist.check(book['url'])
+            
+    def _finish_reject_list_urls(self, book_list):
+
+        # construct reject list of tuples:
+        # (calibre_id, url, "title, authors", old reject note).
+        reject_list = [ ( x['calibre_id'],x['url'],
+                          "%s by %s"%(x['title'],
+                                      ', '.join(x['author'])),
+                          x['oldrejnote'])
+                        for x in book_list if x['good'] ]
+        if reject_list:
+            d = RejectListDialog(self.gui,reject_list,
+                                 rejectreasons=rejecturllist.get_reject_reasons())
+            d.exec_()
+            
+            if d.result() != d.Accepted:
+                return
+
+            bookids=[]
+            rejectlist=[]
+            addreasontext=d.get_reason_text()
+            for (bookid,url,note) in d.get_reject_list():
+                bookids.append(bookid)
+                if addreasontext and note:
+                    note = note +" - "+addreasontext
+                elif addreasontext:
+                    note = addreasontext
+                rejectlist.append((url,note))
+                print("Adding (%s) to Reject List: %s"%(url,note))
+                
+            rejecturllist.add(rejectlist)
+
+            if d.get_deletebooks():
+                self.gui.iactions['Remove Books'].delete_books()
+            
+        else:
+            message="<p>Rejecting FFDL URLs: None of the books selected have FanFiction URLs.</p><p>Proceed to Remove?</p>"
+            if confirm(message,'fanfictiondownloader_reject_non_fanfiction', self.gui):
+                self.gui.iactions['Remove Books'].delete_books()
+                
+    def add_dialog(self,url_list_text=None):
 
         #print("add_dialog()")
 
-        url_list = self.get_urls_clip()
-        url_list_text = "\n".join(url_list)
+        if not url_list_text:
+            url_list = self.get_urls_clip()
+            url_list_text = "\n".join(url_list)
         
         # self.gui is the main calibre GUI. It acts as the gateway to access
         # all the elements of the calibre user interface, it should also be the
@@ -346,7 +455,12 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         self.start_downloads( options, add_books )
         
     def update_existing(self):
+        if not self.is_library_view():
+            self.gui.status_bar.show_message(_('Cannot Update Books from Device View'), 3000)
+            return
+        
         if len(self.gui.library_view.get_selected_ids()) == 0:
+            self.gui.status_bar.show_message(_('No Selected Books to Update'), 3000)
             return
         #print("update_existing()")
         
@@ -431,6 +545,29 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         necessary data.  To be called from LoopProgressDialog
         'loop'.  Also pops dialogs for is adult, user/pass.
         '''
+
+        url = book['url']
+        print("url:%s"%url)
+
+        rejnote = rejecturllist.check(url)
+        if rejnote:
+            if question_dialog(self.gui, 'Reject URL?',
+                               '<p>Reject URL?</p>'+
+                               '<p>%s is on the Reject URL list:<br />"%s"</p>'%(url,rejnote)+
+                               "<p>Click 'No' to download anyway.</p>",
+                               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?',
+                                   "<p>Remove URL from Reject List?</p>"+
+                                   '<p>%s is on the Reject URL list:<br />"%s"</p>'%(url,rejnote)+
+                                   "<p>Click 'Yes' to remove it from the list and download,<br /> 'No' to download, but leave it on the Reject list.</p>",
+                                   show_copy_button=False):
+                    rejecturllist.remove(url)
         
         # The current database shown in the GUI
         # db is an instance of the class LibraryDatabase2 from database.py
@@ -447,8 +584,6 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             # book has already been flagged bad for whatever reason.
             return
         
-        url = book['url']
-        print("url:%s"%url)
         skip_date_update = False
         
         options['personal.ini'] = prefs['personal.ini']
@@ -502,11 +637,6 @@ make_firstimage_cover:true
             book['comments']=''
         book['series'] = story.getMetadata("series", removeallentities=True)
         
-        # adapter.opener is the element with a threadlock.  But del
-        # adapter.opener doesn't work--subproc fails when it tries
-        # to pull in the adapter object that hasn't been imported yet.
-        # book['adapter'] = adapter
-        
         book['is_adult'] = adapter.is_adult
         book['username'] = adapter.username
         book['password'] = adapter.password
@@ -540,8 +670,8 @@ make_firstimage_cover:true
             # 'new' book from URL.  collision handling applies.
             print("from URL(%s)"%url)
 
-            # try to find by identifier url first.
-            searchstr = 'identifiers:"=url:=%s"'%url.replace(":","|")
+            # try to find by identifier url or uri first.
+            searchstr = 'identifiers:"~ur(i|l):=%s"'%url.replace(":","|")
             identicalbooks = db.search_getting_ids(searchstr, None)
             if len(identicalbooks) < 1:
                 # find dups
@@ -744,9 +874,14 @@ make_firstimage_cover:true
         add_ids = [ x['calibre_id'] for x in add_list ]
         update_list = filter(lambda x : x['good'] and not x['added'], book_list)
         update_ids = [ x['calibre_id'] for x in update_list ]
+        all_ids = add_ids
+        all_ids.extend(update_ids)
+
+        if options['collision'] != CALIBREONLY and \
+                (prefs['addtolists'] or prefs['addtoreadlists']):
+            self._update_reading_lists(all_ids,add=True)
         
         if len(add_list):
-            ## even shows up added to searchs.  Nice.
             self.gui.library_view.model().books_added(len(add_list))
             self.gui.library_view.model().refresh_ids(add_ids)
 
@@ -775,8 +910,6 @@ make_firstimage_cover:true
         print("all done, remove temp dir.")
         remove_dir(options['tdir'])
 
-        all_ids = add_ids
-        all_ids.extend(update_ids)
         if 'Count Pages' in self.gui.iactions and len(prefs['countpagesstats']) and len(all_ids):
             cp_plugin = self.gui.iactions['Count Pages']
             cp_plugin.count_statistics(all_ids,prefs['countpagesstats'])
@@ -791,7 +924,8 @@ make_firstimage_cover:true
 
         book_list = job.result
         good_list = filter(lambda x : x['good'], book_list)
-        bad_list = filter(lambda x : x['calibre_id'] and not x['good'], book_list)
+        bad_list = filter(lambda x : not x['good'], book_list)
+        print("book_list:%s"%book_list)
         payload = (good_list, bad_list, options)
         
         msg = '''
@@ -806,14 +940,14 @@ make_firstimage_cover:true
                 status = book['status']
             else:
                 status = 'Good'
-            htmllog = htmllog + '<tr><td>' + '</td><td>'.join([status,book['title'],", ".join(book['author']),book['comment'],book['url']]) + '</td></tr>'
+            htmllog = htmllog + '<tr><td>' + '</td><td>'.join([escapehtml(status),escapehtml(book['title']),escapehtml(", ".join(book['author'])),escapehtml(book['comment']),book['url']]) + '</td></tr>'
         
         for book in bad_list:
             if 'status' in book:
                 status = book['status']
             else:
                 status = 'Bad'
-            htmllog = htmllog + '<tr><td>' + '</td><td>'.join([status,book['title'],", ".join(book['author']),book['comment'],book['url']]) + '</td></tr>'
+            htmllog = htmllog + '<tr><td>' + '</td><td>'.join([escapehtml(status),escapehtml(book['title']),escapehtml(", ".join(book['author'])),escapehtml(book['comment']),book['url']]) + '</td></tr>'
         
         htmllog = htmllog + '</table></body></html>'
         
@@ -822,7 +956,6 @@ make_firstimage_cover:true
                 'FFDL log', 'FFDL download complete', msg,
                 show_copy_button=False)
         
-        
     def _do_download_list_update(self, payload):
         
         (good_list,bad_list,options) = payload
@@ -886,8 +1019,9 @@ make_firstimage_cover:true
                     print("remove f:"+fmt)
                     db.remove_format(book['calibre_id'], fmt, index_is_id=True)#, notify=False
 
-        if prefs['addtolists'] or prefs['addtoreadlists']:
-            self._update_reading_lists([book_id],add=True)
+        # moved up so whole lists are done at once for efficiency.
+        # if prefs['addtolists'] or prefs['addtoreadlists']:
+        #     self._update_reading_lists([book_id],add=True)
                 
         return book_id
 
@@ -904,13 +1038,13 @@ make_firstimage_cover:true
             # mi.tags needs to be list, but set kills dups.
             mi.tags = list(set(list(old_tags)+mi.tags))
 
-        if 'langcode' in book['all_metadata']:
+        if book['all_metadata']['langcode']:
             mi.languages=[book['all_metadata']['langcode']]
         else:
             # Set language english, but only if not already set.
             if not oldmi.languages:
-                mi.languages=['eng']
-
+                mi.languages=['en']
+                
         if options['fileform'] == 'epub' and prefs['updatecover']:
             existingepub = db.format(book_id,'EPUB',index_is_id=True, as_file=True)
             epubmi = get_metadata(existingepub,'EPUB')
@@ -921,6 +1055,7 @@ make_firstimage_cover:true
         if 'authorUrl' in book['all_metadata']:
             authurls = book['all_metadata']['authorUrl'].split(", ")
             for i, auth in enumerate(book['author']):
+                #print("===Update author url for %s to %s"%(auth,authurls[i]))
                 autid=db.get_author_id(auth)
                 db.set_link_field_for_author(autid, unicode(authurls[i]),
                                              commit=False, notify=False)
@@ -1118,12 +1253,6 @@ make_firstimage_cover:true
                 message="<p>You configured FanFictionDownLoader to automatically update \"Send to Device\" Reading Lists, but you don't have any lists set?</p>"
                 confirm(message,'fanfictiondownloader_no_send_lists', self.gui)
 
-            # Quick demo of how an 'allow send' list might work.
-            # Issues: allow list per send list?  Naming convention?  "send(allow)"
-            # allow_list = rl_plugin.get_book_list("Allow Send to Device")
-            # # intersection of book_ids & allow_list
-            # add_book_ids = list(set(book_ids) & set(allow_list))
-
             for l in lists:
                 if l in rl_plugin.get_list_names():
                     #print("good send l:(%s)"%l)
@@ -1136,17 +1265,6 @@ make_firstimage_cover:true
                         message="<p>You configured FanFictionDownLoader to automatically update Reading List '%s', but you don't have a list of that name?</p>"%l
                         confirm(message,'fanfictiondownloader_no_reading_list_%s'%l, self.gui)
 
-    # def _find_existing_book_id(self,db,book,matchurl=True):
-    #     mi = MetaInformation(book["title"],book["author"]) # author is a list.
-    #     identicalbooks = db.find_identical_books(mi)
-    #     if matchurl: # only *really* identical if URL matches, too.
-    #         for ib in identicalbooks:
-    #             if self._get_story_url(db,ib) == book['url']:
-    #                 return ib
-    #     if identicalbooks:
-    #         return identicalbooks.pop()
-    #     return None
-    
     def _make_mi_from_book(self,book):
         mi = MetaInformation(book['title'],book['author']) # author is a list.
         mi.set_identifiers({'url':book['url']})
@@ -1208,7 +1326,25 @@ make_firstimage_cover:true
         book['comment'] = ''
         book['url'] = ''
         book['added'] = False
-        
+
+        return book
+            
+    def _convert_row_to_book(self, row, good=True):
+        book = {}
+        mi = self.gui.current_view().model().get_book_display_info(row.row())
+        book['title'] = mi.title
+        book['author'] = mi.authors
+        book['path'] = mi.path
+        book['author_sort'] = mi.author_sort
+        book['good'] = good
+        book['calibre_id'] = None
+        book['begin'] = None
+        book['end'] = None
+            
+        book['comment'] = ''
+        book['url'] = ''
+        book['added'] = False
+
         return book
             
     def _populate_book_from_calibre_id(self, book, db=None):
@@ -1243,44 +1379,46 @@ make_firstimage_cover:true
                 book['icon']='dialog_error.png'
                 book['status'] = 'Bad URL'
     
-    def _get_story_url(self, db, book_id):
-        identifiers = db.get_identifiers(book_id,index_is_id=True)
+    def _get_story_url(self, db, book_id=None, path=None):
+        if book_id == None:
+            identifiers={}
+        else:
+            identifiers = db.get_identifiers(book_id,index_is_id=True)
         if 'url' in identifiers:
             # identifiers have :->| in url.
-            #print("url from book:"+identifiers['url'].replace('|',':'))
+            # print("url from ident url:%s"%identifiers['url'].replace('|',':'))
             return identifiers['url'].replace('|',':')
+        elif 'uri' in identifiers:
+            # identifiers have :->| in uri.
+            # print("uri from ident uri:%s"%identifiers['uri'].replace('|',':'))
+            return identifiers['uri'].replace('|',':')
         else:
-            ## only epub has URL in it--at least where I can easily find it.
-            if db.has_format(book_id,'EPUB',index_is_id=True):
+            existingepub = None
+            if path == None and db.has_format(book_id,'EPUB',index_is_id=True):
                 existingepub = db.format(book_id,'EPUB',index_is_id=True, as_file=True)
                 mi = get_metadata(existingepub,'EPUB')
                 identifiers = mi.get_identifiers()
                 if 'url' in identifiers:
-                    #print("url from epub:"+identifiers['url'].replace('|',':'))
+                    # print("url from get_metadata:%s"%identifiers['url'].replace('|',':'))
                     return identifiers['url'].replace('|',':')
-                # look for dc:source first, then scan HTML if 
+            elif path.lower().endswith('.epub'):
+                existingepub = path
+                
+            ## only epub has URL in it--at least where I can easily find it.
+            if existingepub:                
+                # look for dc:source first, then scan HTML if lookforurlinhtml
                 link = get_dcsource(existingepub)
                 if link:
+                    # print("url from get_dcsource:%s"%link)
                     return link
                 elif prefs['lookforurlinhtml']:
-                    return get_story_url_from_html(existingepub,self._is_good_downloader_url)
+                    link = get_story_url_from_html(existingepub,self._is_good_downloader_url)
+                    # print("url from get_story_url_from_html:%s"%link)
+                    return link
         return None
 
     def _is_good_downloader_url(self,url):
-        # this is the accepted way to 'check for existance of a class variable'?  really?
-        try:
-            self.dummyconfig
-        except AttributeError:
-            self.dummyconfig = Configuration("test1.com","EPUB")
-        # pulling up an adapter is pretty low over-head.  If
-        # it fails, it's a bad url.
-        try:
-            adapter = adapters.getAdapter(self.dummyconfig,url)
-            url = adapter.url
-            del adapter
-            return url
-        except:
-            return None;
+        return adapters.getNormalStoryURL(url)
 
 def get_url_list(urls):
     def f(x):
@@ -1289,3 +1427,6 @@ def get_url_list(urls):
     # set removes dups.
     return set(filter(f,urls.strip().splitlines()))
 
+def escapehtml(txt):
+    return txt.replace("&","&amp;").replace(">","&gt;").replace("<","&lt;")
+        

calibre-plugin/jobs.py

@@ -39,11 +39,12 @@ def do_download_worker(book_list, options,
 
     print(options['version'])
     total = 0
+    alreadybad = []
     # Queue all the jobs
     print("Adding jobs for URLs:")
     for book in book_list:
+        print("%s"%book['url'])
         if book['good']:
-            print("%s"%book['url'])
             total += 1
             args = ['calibre_plugins.fanfictiondownloader_plugin.jobs',
                     'do_download_for_worker',
@@ -58,6 +59,9 @@ def do_download_worker(book_list, options,
             # job._modified_date = modified_date
             # job._existing_isbn = existing_isbn
             server.add_job(job)
+        else:
+            # was already bad before the subprocess ever started.
+            alreadybad.append(book)
     
     # This server is an arbitrary_n job, so there is a notifier available.
     # Set the % complete to a small number to avoid the 'unavailable' indicator
@@ -90,11 +94,11 @@ def do_download_worker(book_list, options,
             print("Successfully downloaded:")
             for book in book_list:
                 if book['good']:
-                    print(book['title'])
+                    print("%s %s"%(book['title'],book['url']))
             print("\nUnsuccessful:")
             for book in book_list:
                 if not book['good']:
-                    print(book['title'])
+                    print("%s %s"%(book['title'],book['url']))
             break
 
     server.close()
@@ -126,6 +130,7 @@ def do_download_for_worker(book,options):
         adapter.is_adult = book['is_adult'] 
         adapter.username = book['username'] 
         adapter.password = book['password']
+        adapter.setChaptersRange(book['begin'],book['end'])
         
         story = adapter.getStoryMetadataOnly()
         if 'calibre_series' in book:
@@ -148,8 +153,6 @@ def do_download_for_worker(book,options):
         elif options['collision'] in (ADDNEW, SKIP, OVERWRITE, OVERWRITEALWAYS) or \
                 ('epub_for_update' not in book and options['collision'] in (UPDATE, UPDATEALWAYS)):
 
-            adapter.setChaptersRange(book['begin'],book['end'])
-            
             print("write to %s"%outfile)
             writer.writeStory(outfilename=outfile, forceOverwrite=True)
             book['comment'] = 'Download %s completed, %s chapters.'%(options['fileform'],story.getMetadata("numChapters"))

downloader.py

@@ -158,6 +158,8 @@ def main():
 
        adapter = adapters.getAdapter(configuration,url)
 
+       adapter.setChaptersRange(options.begin,options.end)
+           
        ## Check for include_images and absence of PIL, give warning.
        if adapter.getConfig('include_images'):
            try:
@@ -221,8 +223,6 @@ def main():
            if options.metaonly:
                print adapter.getStoryMetadataOnly()
            
-           adapter.setChaptersRange(options.begin,options.end)
-           
            output_filename=writeStory(configuration,adapter,options.format,options.metaonly)
        
        if not options.metaonly and adapter.getConfig("post_process_cmd"):

fanficdownloader/adapters/__init__.py

@@ -1,179 +1,203 @@
-# -*- coding: utf-8 -*-
-
-# Copyright 2011 Fanficdownloader team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-#
-
-import os, re, sys, glob, types
-from os.path import dirname, basename, normpath
-import logging
-import urlparse as up
-
-logger = logging.getLogger(__name__)
-
-from .. import exceptions as exceptions
-
-## must import each adapter here.
-
-import adapter_test1
-import adapter_fanfictionnet
-import adapter_castlefansorg
-import adapter_fictionalleyorg
-import adapter_fictionpresscom
-import adapter_ficwadcom
-import adapter_fimfictionnet
-import adapter_harrypotterfanfictioncom
-import adapter_mediaminerorg
-import adapter_potionsandsnitchesnet
-import adapter_tenhawkpresentscom
-import adapter_adastrafanficcom
-import adapter_thewriterscoffeeshopcom
-import adapter_tthfanficorg
-import adapter_twilightednet
-import adapter_twiwritenet
-import adapter_whoficcom
-import adapter_siyecouk
-import adapter_archiveofourownorg
-import adapter_ficbooknet
-import adapter_portkeyorg
-import adapter_mugglenetcom
-import adapter_hpfandomnet
-import adapter_thequidditchpitchorg
-import adapter_nfacommunitycom
-import adapter_midnightwhispersca
-import adapter_ksarchivecom
-import adapter_archiveskyehawkecom
-import adapter_squidgeorgpeja
-import adapter_libraryofmoriacom
-import adapter_wraithbaitcom
-import adapter_checkmatedcom
-import adapter_chaossycophanthexcom
-import adapter_dramioneorg
-import adapter_erosnsapphosycophanthexcom
-import adapter_lumossycophanthexcom
-import adapter_occlumencysycophanthexcom
-import adapter_phoenixsongnet
-import adapter_walkingtheplankorg
-import adapter_ashwindersycophanthexcom
-import adapter_thehexfilesnet
-import adapter_dokugacom
-import adapter_iketernalnet
-import adapter_onedirectionfanfictioncom
-import adapter_prisonbreakficnet
-import adapter_storiesofardacom
-import adapter_yourfanfictioncom
-import adapter_samdeanarchivenu
-import adapter_destinysgatewaycom
-import adapter_ncisfictioncom
-import adapter_stargateatlantisorg
-import adapter_thealphagatecom
-import adapter_fanfiktionde
-import adapter_ponyfictionarchivenet
-import adapter_sg1heliopoliscom
-import adapter_ncisficcom
-import adapter_nationallibrarynet
-import adapter_themasquenet
-import adapter_pretendercentrecom
-import adapter_darksolaceorg
-import adapter_finestoriescom
-import adapter_hpfanficarchivecom
-import adapter_svufictioncom
-import adapter_twilightarchivescom
-import adapter_wizardtalesnet
-import adapter_nhamagicalworldsus
-import adapter_hlfictionnet
-import adapter_grangerenchantedcom
-import adapter_dracoandginnycom
-import adapter_scarvesandcoffeenet
-import adapter_thepetulantpoetesscom
-import adapter_wolverineandroguecom
-import adapter_sinfuldesireorg
-import adapter_merlinficdtwinscouk
-import adapter_thehookupzonenet
-import adapter_bloodtiesfancom
-import adapter_qafficcom
-
-## This bit of complexity allows adapters to be added by just adding
-## importing.  It eliminates the long if/else clauses we used to need
-## to pick out the adapter.
-    
-## List of registered site adapters.
-__class_list = []
-
-def imports():
-    for name, val in globals().items():
-        if isinstance(val, types.ModuleType):
-            yield val.__name__
-
-for x in imports():
-    if "fanficdownloader.adapters.adapter_" in x:
-        #print x
-        __class_list.append(sys.modules[x].getClass())
-
-def getAdapter(config,url):
-
-    logger.debug("trying url:"+url)
-    (cls,fixedurl) = getClassFor(url)
-    logger.debug("fixedurl:"+fixedurl)
-    if cls:
-        adapter = cls(config,fixedurl) # raises InvalidStoryURL
-        return adapter
-    # No adapter found.
-    raise exceptions.UnknownSite( url, [cls.getSiteDomain() for cls in __class_list] )
-
-def getConfigSections():
-    return [cls.getConfigSection() for cls in __class_list]
-
-def getConfigSectionFor(url):
-    (cls,fixedurl) = getClassFor(url)
-    if cls:
-        return cls.getConfigSection()
-    
-    # No adapter found.
-    raise exceptions.UnknownSite( url, [cls.getSiteDomain() for cls in __class_list] )
-
-def getClassFor(url):
-    ## fix up leading protocol.
-    fixedurl = re.sub(r"(?i)^[htps]+[:/]+","http://",url.strip())
-    if not fixedurl.startswith("http"):
-        fixedurl = "http://%s"%url
-    ## remove any trailing '#' locations.
-    fixedurl = re.sub(r"#.*$","",fixedurl)
-    
-    ## remove any trailing '&' parameters--?sid=999 will be left.
-    ## that's all that any of the current adapters need or want.
-    fixedurl = re.sub(r"&.*$","",fixedurl)
-    
-    parsedUrl = up.urlparse(fixedurl)
-    domain = parsedUrl.netloc.lower()
-    if( domain != parsedUrl.netloc ):
-        fixedurl = fixedurl.replace(parsedUrl.netloc,domain)
-
-    cls = getClassFromList(domain)
-    if not cls and domain.startswith("www."):
-        domain = domain.replace("www.","")
-        logger.debug("trying site:without www: "+domain)
-        cls = getClassFromList(domain)
-        fixedurl = fixedurl.replace("http://www.","http://")
-    if not cls:
-        logger.debug("trying site:www."+domain)
-        cls = getClassFromList("www."+domain)
-        fixedurl = fixedurl.replace("http://","http://www.")
-        
-    return (cls,fixedurl)
-    
-def getClassFromList(domain):
-    for cls in __class_list:
-        if cls.matchesSite(domain):
-            return cls
+# -*- coding: utf-8 -*-
+
+# Copyright 2011 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import os, re, sys, glob, types
+from os.path import dirname, basename, normpath
+import logging
+import urlparse as up
+
+logger = logging.getLogger(__name__)
+
+from .. import exceptions as exceptions
+from ..configurable import Configuration
+
+## must import each adapter here.
+
+import adapter_test1
+import adapter_fanfictionnet
+import adapter_castlefansorg
+import adapter_fictionalleyorg
+import adapter_fictionpresscom
+import adapter_ficwadcom
+import adapter_fimfictionnet
+import adapter_harrypotterfanfictioncom
+import adapter_mediaminerorg
+import adapter_potionsandsnitchesnet
+import adapter_tenhawkpresentscom
+import adapter_adastrafanficcom
+import adapter_thewriterscoffeeshopcom
+import adapter_tthfanficorg
+import adapter_twilightednet
+import adapter_twiwritenet
+import adapter_whoficcom
+import adapter_siyecouk
+import adapter_archiveofourownorg
+import adapter_ficbooknet
+import adapter_portkeyorg
+import adapter_mugglenetcom
+import adapter_hpfandomnet
+import adapter_thequidditchpitchorg
+import adapter_nfacommunitycom
+import adapter_midnightwhispersca
+import adapter_ksarchivecom
+import adapter_archiveskyehawkecom
+import adapter_squidgeorgpeja
+import adapter_libraryofmoriacom
+import adapter_wraithbaitcom
+import adapter_checkmatedcom
+import adapter_chaossycophanthexcom
+import adapter_dramioneorg
+import adapter_erosnsapphosycophanthexcom
+import adapter_lumossycophanthexcom
+import adapter_occlumencysycophanthexcom
+import adapter_phoenixsongnet
+import adapter_walkingtheplankorg
+import adapter_ashwindersycophanthexcom
+import adapter_thehexfilesnet
+import adapter_dokugacom
+import adapter_iketernalnet
+import adapter_onedirectionfanfictioncom
+import adapter_prisonbreakficnet
+import adapter_storiesofardacom
+import adapter_samdeanarchivenu
+import adapter_destinysgatewaycom
+import adapter_ncisfictionnet
+import adapter_stargateatlantisorg
+import adapter_thealphagatecom
+import adapter_fanfiktionde
+import adapter_ponyfictionarchivenet
+import adapter_sg1heliopoliscom
+import adapter_ncisficcom
+import adapter_nationallibrarynet
+import adapter_themasquenet
+import adapter_pretendercentrecom
+import adapter_darksolaceorg
+import adapter_finestoriescom
+import adapter_hpfanficarchivecom
+import adapter_svufictioncom
+import adapter_twilightarchivescom
+import adapter_wizardtalesnet
+import adapter_nhamagicalworldsus
+import adapter_hlfictionnet
+import adapter_grangerenchantedcom
+import adapter_dracoandginnycom
+import adapter_scarvesandcoffeenet
+import adapter_thepetulantpoetesscom
+import adapter_wolverineandroguecom
+import adapter_sinfuldesireorg
+import adapter_merlinficdtwinscouk
+import adapter_thehookupzonenet
+import adapter_bloodtiesfancom
+import adapter_indeathnet
+import adapter_jlaunlimitedcom
+import adapter_qafficcom
+import adapter_efpfanficnet
+import adapter_potterficscom
+import adapter_efictionestelielde
+import adapter_dotmoonnet
+import adapter_pommedesangcom
+import adapter_restrictedsectionorg
+import adapter_imagineeficcom
+import adapter_buffynfaithnet
+
+## This bit of complexity allows adapters to be added by just adding
+## importing.  It eliminates the long if/else clauses we used to need
+## to pick out the adapter.
+    
+## List of registered site adapters.
+__class_list = []
+
+def imports():
+    for name, val in globals().items():
+        if isinstance(val, types.ModuleType):
+            yield val.__name__
+
+for x in imports():
+    if "fanficdownloader.adapters.adapter_" in x:
+        #print x
+        __class_list.append(sys.modules[x].getClass())
+
+def getNormalStoryURL(url):
+    if not getNormalStoryURL.__dummyconfig:
+        getNormalStoryURL.__dummyconfig = Configuration("test1.com","EPUB")
+    # pulling up an adapter is pretty low over-head.  If
+    # it fails, it's a bad url.
+    try:
+        adapter = getAdapter(getNormalStoryURL.__dummyconfig,url)
+        url = adapter.url
+        del adapter
+        return url
+    except:
+        return None;
+
+# kludgey function static/singleton
+getNormalStoryURL.__dummyconfig = None
+
+def getAdapter(config,url):
+
+    logger.debug("trying url:"+url)
+    (cls,fixedurl) = getClassFor(url)
+    logger.debug("fixedurl:"+fixedurl)
+    if cls:
+        adapter = cls(config,fixedurl) # raises InvalidStoryURL
+        return adapter
+    # No adapter found.
+    raise exceptions.UnknownSite( url, [cls.getSiteDomain() for cls in __class_list] )
+
+def getConfigSections():
+    return [cls.getConfigSection() for cls in __class_list]
+
+def getConfigSectionFor(url):
+    (cls,fixedurl) = getClassFor(url)
+    if cls:
+        return cls.getConfigSection()
+    
+    # No adapter found.
+    raise exceptions.UnknownSite( url, [cls.getSiteDomain() for cls in __class_list] )
+
+def getClassFor(url):
+    ## fix up leading protocol.
+    fixedurl = re.sub(r"(?i)^[htps]+[:/]+","http://",url.strip())
+    if not fixedurl.startswith("http"):
+        fixedurl = "http://%s"%url
+    ## remove any trailing '#' locations.
+    fixedurl = re.sub(r"#.*$","",fixedurl)
+    
+    parsedUrl = up.urlparse(fixedurl)
+    domain = parsedUrl.netloc.lower()
+    if( domain != parsedUrl.netloc ):
+        fixedurl = fixedurl.replace(parsedUrl.netloc,domain)
+
+    cls = getClassFromList(domain)
+    if not cls and domain.startswith("www."):
+        domain = domain.replace("www.","")
+        logger.debug("trying site:without www: "+domain)
+        cls = getClassFromList(domain)
+        fixedurl = fixedurl.replace("http://www.","http://")
+    if not cls:
+        logger.debug("trying site:www."+domain)
+        cls = getClassFromList("www."+domain)
+        fixedurl = fixedurl.replace("http://","http://www.")
+        
+    fixedurl = cls.stripURLParameters(fixedurl)
+    
+    return (cls,fixedurl)
+    
+def getClassFromList(domain):
+    for cls in __class_list:
+        if cls.matchesSite(domain):
+            return cls

fanficdownloader/adapters/adapter_archiveofourownorg.py

@@ -82,7 +82,8 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
 
     def getSiteURLPattern(self):
         # http://archiveofourown.org/collections/Smallville_Slash_Archive/works/159770
-        return re.escape("http://")+re.escape(self.getSiteDomain())+r"(/collections/[^/]+)?/works/(?P<id>\d+)"
+        # Discard leading zeros from story ID numbers--AO3 doesn't use them in it's own chapter URLs.
+        return re.escape("http://")+re.escape(self.getSiteDomain())+r"(/collections/[^/]+)?/works/0*(?P<id>\d+)"
         
     ## Login
     def needToLoginCheck(self, data):
@@ -217,7 +218,7 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
         if a != None:
             genres = a.findAll('a',{'class':"tag"})
             for genre in genres:
-                self.story.addToList('freefromtags',genre.string)
+                self.story.addToList('freeformtags',genre.string)
                 self.story.addToList('genre',genre.string)
                 
         a = metasoup.find('dd',{'class':"category tags"})
@@ -233,13 +234,19 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
             chars = a.findAll('a',{'class':"tag"})
             for char in chars:
                 self.story.addToList('characters',char.string)
+                
         a = metasoup.find('dd',{'class':"relationship tags"})
         if a != None:
             ships = a.findAll('a',{'class':"tag"})
             for ship in ships:
                 self.story.addToList('ships',ship.string)
 		
-
+        a = metasoup.find('dd',{'class':"collections"})
+        if a != None:
+            collections = a.findAll('a')
+            for collection in collections:
+                self.story.addToList('collections',collection.string)
+		
         stats = metasoup.find('dl',{'class':'stats'})
         dt = stats.findAll('dt')
         dd = stats.findAll('dd')

fanficdownloader/adapters/adapter_buffynfaithnet.py

@@ -0,0 +1,290 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2013 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+logger = logging.getLogger(__name__)
+import re
+import urllib2
+import cookielib as cl
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+
+# This function is called by the downloader in all adapter_*.py files
+# in this dir to register the adapter class.  So it needs to be
+# updated to reflect the class below it.  That, plus getSiteDomain()
+# take care of 'Registering'.
+def getClass():
+    return BuffyNFaithNetAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class BuffyNFaithNetAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+        
+        self.setHeader()
+        
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query correct
+        m = re.match(self.getSiteURLPattern(),url)
+        if m:
+            self.story.setMetadata('storyId',m.group('id'))
+            logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+            # normalized story URL. gets rid of chapter if there, left with ch 1 URL on this site
+            nurl = "http://"+self.getSiteDomain()+"/fanfictions/index.php?act=vie&id="+self.story.getMetadata('storyId')
+            self._setURL(nurl)
+            #argh, this mangles the ampersands I need on metadata['storyUrl']
+            #will set it this way
+            self.story.setMetadata('storyUrl',nurl,condremoveentities=False)
+        else:
+            raise exceptions.InvalidStoryURL(url,
+                                             self.getSiteDomain(),
+                                             self.getSiteExampleURLs())
+        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','bnfnet')
+
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'buffynfaith.net'
+
+    @classmethod
+    def stripURLParameters(cls,url):
+        "Only needs to be overriden if URL contains more than one parameter"
+        ## This adapter needs at least two parameters left on the URL, act and id
+        return re.sub(r"(\?act=(vie|ovr)&id=\d+)&.*$",r"\1",url)
+    
+    def setHeader(self):
+        "buffynfaith.net wants a Referer for images.  Used both above and below(after cookieproc added)"
+        self.opener.addheaders = [('Referer', 'http://'+self.getSiteDomain()+'/')]
+        
+    def getSiteExampleURLs(self):
+        return "http://buffynfaith.net/fanfictions/index.php?act=vie&id=963 http://buffynfaith.net/fanfictions/index.php?act=vie&id=949 http://buffynfaith.net/fanfictions/index.php?act=vie&id=949&ch=2"
+
+    def getSiteURLPattern(self):
+        #http://buffynfaith.net/fanfictions/index.php?act=vie&id=963
+        #http://buffynfaith.net/fanfictions/index.php?act=vie&id=949
+        #http://buffynfaith.net/fanfictions/index.php?act=vie&id=949&ch=2
+        p = re.escape("http://"+self.getSiteDomain()+"/fanfictions/index.php?act=")+\
+            r"(vie|ovr)&id=(?P<id>\d+)(&ch=(?P<ch>\d+))?$"
+        return p
+
+    def extractChapterUrlsAndMetadata(self):
+
+        dateformat = "%d %B %Y"
+        url = self.url
+        logger.debug("URL: "+url)
+        
+        #set a cookie to get past adult check
+        if self.is_adult or self.getConfig("is_adult"):
+            cookieproc = urllib2.HTTPCookieProcessor()
+            cookie = cl.Cookie(version=0, name='my_age', value='yes',
+                               port=None, port_specified=False,
+                               domain=self.getSiteDomain(), domain_specified=False, domain_initial_dot=False,
+                               path='/', path_specified=True,
+                               secure=False,
+                               expires=time.time()+10000,
+                               discard=False,
+                               comment=None,
+                               comment_url=None,
+                               rest={'HttpOnly': None},
+                               rfc2109=False)
+            cookieproc.cookiejar.set_cookie(cookie)
+            self.opener = urllib2.build_opener(cookieproc)        
+            self.setHeader()
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        #print data
+
+        if "ADULT CONTENT WARNING" in data: 
+            raise exceptions.AdultCheckRequired(self.url)
+
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        #stuff in <head>: description
+        svalue = soup.head.find('meta',attrs={'name':'description'})['content']
+        #self.story.setMetadata('description',svalue)
+        self.setDescription(url,svalue)
+        
+        #useful stuff in rest of doc, all contained in this:
+        doc = soup.body.find('div', id='my_wrapper')
+        
+        #first the site category (more of a genre to me, meh) and title, in this element:
+        mt = doc.find('div',attrs={'class':'maintitle'})
+        self.story.addToList('genre',mt.findAll('a')[1].string)
+        self.story.setMetadata('title',mt.findAll('a')[1].nextSibling[len('&nbsp;&raquo;&nbsp;'):])
+        del mt
+
+        #the actual category, for me, is 'Buffy: The Vampire Slayer'
+        #self.story.addToList('category','Buffy: The Vampire Slayer')
+        #No need to do it here, it is better to set it in in plugin-defaults.ini and defaults.ini
+        
+        #then a block that sits in a table cell like so:
+        #(contains a lot of metadata)
+        mblock = doc.find('td', align='left', width = '70%').contents
+        while len(mblock) > 0:
+            i = mblock.pop(0)
+            if 'Author:' in i.string:
+                #drop empty space
+                mblock.pop(0)
+                #get author link
+                a = mblock.pop(0)
+                authre = re.escape('./index.php?act=bio&id=')+'(?P<authid>\d+)'
+                m = re.match(authre,a['href'])
+                self.story.setMetadata('author',a.string)
+                self.story.setMetadata('authorId',m.group('authid'))
+                authurl = u'http://%s/fanfictions/index.php?act=bio&id=%s' % ( self.getSiteDomain(),
+                                            self.story.getMetadata('authorId'))
+                self.story.setMetadata('authorUrl',authurl,condremoveentities=False)
+                #drop empty space
+                mblock.pop(0)
+            if 'Rating:' in i.string:
+                self.story.setMetadata('rating',mblock.pop(0).strip())
+            if 'Published:' in i.string:
+                date = mblock.pop(0).strip()
+                #get rid of 'st', 'nd', 'rd', 'th' after day number
+                date = date[0:2]+date[4:]
+                self.story.setMetadata('datePublished',makeDate(date, dateformat))
+            if 'Last Updated:' in i.string:
+                date = mblock.pop(0).strip()
+                #get rid of 'st', 'nd', 'rd', 'th' after day number
+                date = date[0:2]+date[4:]
+                self.story.setMetadata('dateUpdated',makeDate(date, dateformat))
+            if 'Genre:' in i.string:
+                genres = mblock.pop(0).strip()
+                genres = genres.split('/')
+                for genre in genres: self.story.addToList('genre',genre)
+            #end ifs
+        #end while
+
+        # Find the chapter selector 
+        select = soup.find('select', { 'name' : 'ch' } )
+         
+        if select is None:
+           # no selector found, so it's a one-chapter story.
+           #self.chapterUrls.append((self.story.getMetadata('title'),url))
+           self.chapterUrls.append((self.story.getMetadata('title'),url))
+        else:
+            allOptions = select.findAll('option')
+            for o in allOptions:
+                url = u'http://%s/fanfictions/index.php?act=vie&id=%s&ch=%s' % ( self.getSiteDomain(),
+                                            self.story.getMetadata('storyId'),
+                                            o['value'])
+                title = u"%s" % o
+                title = stripHTML(title)
+                ts = title.split(' ',1)
+                title = ts[0]+'. '+ts[1]
+                self.chapterUrls.append((title,url))
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+        
+        ## Go scrape the rest of the metadata from the author's page.
+        data = self._fetchUrl(self.story.getMetadata('authorUrl'))
+        soup = bs.BeautifulSoup(data)
+        #find the story link and its parent div
+        storya = soup.find('a',{'href':self.story.getMetadata('storyUrl')})
+        storydiv = storya.parent
+        #warnings come under a <spawn> tag. Never seen that before...
+        #appears to just be a line of freeform text, not necessarily a list
+        #optional
+        spawn = storydiv.find('spawn',{'id':'warnings'})
+        if spawn is not None:
+            warns = spawn.nextSibling.strip()
+            self.story.addToList('warnings',warns)
+        #some meta in spans - this should get all, even the ones jammed in a table
+        spans = storydiv.findAll('span')
+        for s in spans:
+            if s.string == 'Ship:':
+                list = s.nextSibling.strip().split()
+                self.story.extendList('ships',list)
+            if s.string == 'Characters:':
+                list = s.nextSibling.strip().split(',')
+                self.story.extendList('characters',list)
+            if s.string == 'Status:':
+                st = s.nextSibling.strip()
+                self.story.setMetadata('status',st)
+            if s.string == 'Words:':
+                st = s.nextSibling.strip()
+                self.story.setMetadata('numWords',st)
+
+        #reviews - is this worth having?
+        #ffnet adapter gathers it, don't know if anything else does
+        #or if it's ever going to be used!
+        a = storydiv.find('a',{'id':'bold-blue'})
+        if a:
+            revs = a.nextSibling.strip()[1:-1]
+            self.story.setMetadata('reviews',st)
+        else:
+            revs = '0'
+            self.story.setMetadata('reviews',st)
+
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logger.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div', {'id' : 'fanfiction'})
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+        
+        #remove all the unnecessary bookmark tags
+        [s.extract() for s in div('div',{'class':"tiny_box2"})]
+        
+        #is there a review link?
+        r = div.find('a',href=re.compile(re.escape("./index.php?act=irv")+".*$"))
+        if r is not None:
+        #remove the review link and its parent div
+            r.parent.extract()
+        
+        #There might also be a link to the sequel on the last chapter
+        #I'm inclined to keep it in, but the URL needs to be changed from relative to absolute
+        #Shame there isn't proper series metadata available
+        #(I couldn't find it anyway)
+        s = div.find('a',href=re.compile(re.escape("./index.php?act=ovr")+".*$"))
+        if s is not None:
+            s['href'] = 'http://'+self.getSiteDomain()+'/fanfictions'+s['href'][1:]
+
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_dotmoonnet.py

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

fanficdownloader/adapters/adapter_efictionestelielde.py

@@ -0,0 +1,221 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2013 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+logger = logging.getLogger(__name__)
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return EfictionEstelielDeAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class EfictionEstelielDeAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','eesd')
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%B %d, %Y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'efiction.esteliel.de'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+       
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title and author
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+
+        pagetitle = soup.find('div',{'id':'pagetitle'})
+        ## Title
+        a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',a.string)
+        
+        # Find authorid and URL from... author url.
+        a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # Find the chapters:
+        for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
+            # just in case there's tags, like <i> in chapter titles.
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        # utility method
+        def defaultGetattr(d,k):
+            try:
+                return d[k]
+            except:
+                return ""
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        list = soup.find('div', {'class':'listbox'})
+        labelspan=list.find('span',{'class':'label'})
+        value = labelspan.nextSibling
+        label = labelspan.string
+        genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
+        for genre in genres:
+            self.story.addToList('genre',genre.string)
+        
+        labels = list.findAll('b')
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+
+            if 'Summary' in label:
+                ## Everything until the next span class='label'
+                svalue = ""
+                while 'Rating' not in str(value):
+                    svalue += str(value)
+                    value = value.nextSibling
+                self.setDescription(url,svalue)
+                #self.story.setMetadata('description',stripHTML(svalue))
+
+            if 'Rating' in label:
+                self.story.setMetadata('rating', value)
+
+            if 'Words' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Category' in label:
+                cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+                for cat in cats:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+                for char in chars:
+                    self.story.addToList('characters',char.string)
+
+            if 'Completed' in label:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Updated' in label:
+                # there's a stray [ at the end.
+                #value = value[0:-1]
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+
+        try:
+            if list.find('a', href=re.compile(r"series.php")) != None:
+                for series in asoup.findAll('a', href=re.compile(r"series.php\?seriesid=\d+")):
+                    # Find Series name from series URL.
+                    series_url = 'http://'+self.host+'/'+series['href']
+                    # use BeautifulSoup HTML parser to make everything easier to find.
+                    seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+                    storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+                    i=1
+                    for a in storyas:
+                        if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                            name=seriessoup.find('div', {'id' : 'pagetitle'})
+                            name.find('a').extract()
+                            self.setSeries(name.text.split(' by[')[0], i)
+                            i=0
+                            break
+                        i+=1
+                    if i == 0:
+                        break
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logger.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+                                     
+        div = soup.find('div', {'id' : 'story'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_efpfanficnet.py

@@ -0,0 +1,312 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2012 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+logger = logging.getLogger(__name__)
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return EFPFanFicNet
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class EFPFanFicNet(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','efp')
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%d/%m/%y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'www.efpfanfic.net'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+
+    ## Login seems to be reasonably standard across eFiction sites.
+    def needToLoginCheck(self, data):
+        if 'Fai il login e leggi la storia!' 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'] = 'Invia'
+
+        loginUrl = 'http://' + self.getSiteDomain() + '/user.php?sid='+self.story.getMetadata('storyId')
+        logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
+                                                              params['penname']))
+    
+        d = self._fetchUrl(loginUrl, params)
+    
+        if '<a class="menu" href="newaccount.php">' in d : # register for new account link
+            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):
+
+        url = self.url
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        if self.needToLoginCheck(data):
+            # need to log in for this one.
+            self.performLogin(url)
+            data = self._fetchUrl(url)
+
+        # if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+        #     raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+
+        ## Title
+        a = soup.find('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 chapter selector 
+        select = soup.find('select', { 'name' : 'sid' } )
+    	 
+        if select is None:
+    	   # no selector found, so it's a one-chapter story.
+    	   self.chapterUrls.append((self.story.getMetadata('title'),url))
+        else:
+            allOptions = select.findAll('option', {'value' : re.compile(r'viewstory')})
+            for o in allOptions:
+                url = u'http://%s/%s' % ( self.getSiteDomain(),
+                                          o['value'])
+                # just in case there's tags, like <i> in chapter titles.
+                title = stripHTML(o)
+                self.chapterUrls.append((title,url))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+        self.story.setMetadata('language','Italian')
+        
+        # normalize story URL to first chapter if later chapter URL was given:
+        url = self.chapterUrls[0][1].replace('&i=1','')
+        logger.debug("Normalizing to URL: "+url)
+        self._setURL(url)
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        storya = None
+        authsoup = None
+        storyblock = None
+        authurl = self.story.getMetadata('authorUrl')
+        
+        ## author can have more than one page of stories.
+        while storyblock == None:
+
+            # no storya, but do have authsoup--we're looping on author pages.
+            if authsoup != None:
+                # last author link with offset should be the 'next' link.
+                authurl = u'http://%s/%s' % ( self.getSiteDomain(),
+                                              authsoup.findAll('a',href=re.compile(r'viewuser\.php\?uid=\d+&catid=&offset='))[-1]['href'] )
+            
+            # Need author page for most of the metadata.
+            logger.debug("fetching author page: (%s)"%authurl)
+            authsoup = bs.BeautifulSoup(self._fetchUrl(authurl))
+            #print("authsoup:%s"%authsoup)
+
+            storyas = authsoup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+r'&i=1$'))
+            for storya in storyas:
+                #print("======storya:%s"%storya)
+                storyblock = storya.findParent('div',{'class':'storybloc'})
+                #print("======storyblock:%s"%storyblock)
+                if storyblock != None:
+                    continue
+
+        self.setDescription(url,storyblock.find('div', {'class':'introbloc'}))
+
+        noteblock = storyblock.find('div', {'class':'notebloc'})
+        #print("%s"%noteblock)
+        notetext = ("%s" % noteblock).replace("<br />"," |")
+        # <div class="notebloc">Autore: <a href="viewuser.php?uid=243036">Cendrillon89</a> | Pubblicata: 23/10/12 | Aggiornata: 30/10/12 | Rating: Arancione | Genere: Drammatico, Sentimentale | Capitoli: 10 | Completa<br />␍
+        # Tipo di coppia: Het |  Personaggi: Akasuna no Sasori , Akatsuki, Nuovo Personaggio |   Note: OOC | Avvertimenti: Tematiche delicate<br />␍
+        # Categoria: <a href="categories.php?catid=1&amp;parentcatid=1">Anime & Manga</a> > <a href="categories.php?catid=108&amp;parentcatid=108">Naruto</a> | Contesto: Naruto Shippuuden | Leggi le <a href="reviews.php?sid=1331275&amp;a=">3</a> recensioni</div>
+
+        cats = noteblock.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+        for cat in cats:
+            self.story.addToList('category',cat.string)
+            
+        for item in notetext.split("|"):
+            if ":" in item:
+                (label,value) = item.split(":")
+                label=label.strip()
+                value=value.strip()
+            else:
+                label=value=item.strip()
+
+            if 'Pubblicata' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Aggiornata' in label:
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+
+            if label == "Completa":
+                self.story.setMetadata('status', 'Completed')
+            
+            if label == "In corso":
+                self.story.setMetadata('status', 'In-Progress')
+
+            if 'Rating' in label:
+                self.story.setMetadata('rating', value)
+
+            if 'Personaggi' in label:
+                for val in value.split(","):
+                    self.story.addToList('characters',val)
+                    
+            if 'Genere' in label:
+                for val in value.split(","):
+                    self.story.addToList('genre',val)
+                    
+            if 'Coppie' in label:
+                for val in value.split(","):
+                    self.story.addToList('ships',val)
+
+            if 'Avvertimenti' in label:
+                for val in value.split(","):
+                    if val != "None":
+                        self.story.addToList('warnings',val)
+
+            # 'extra' metadata for this adapter:
+                    
+            if 'Tipo di coppia' in label:
+                for val in value.split(","):
+                    self.story.addToList('type',val)
+                    
+            if 'Note' in label:
+                for val in value.split(","):
+                    if val != "None":
+                        self.story.addToList('notes',val)
+                    
+            if 'Contesto' in label:
+                self.story.setMetadata('context', value)
+
+            ## Note--efp doesn't provide word count.
+                
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?ssid=\d+&i=1"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            # can't use ^viewstory...$ in case of higher rated stories with javascript href.
+            storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+&i=1'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId'))+'&i=1':
+                    self.setSeries(series_name, i)
+                    break
+                i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logger.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulSoup(self._fetchUrl(url))
+        
+        div = soup.find('div', {'class' : 'storia'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        # remove any header and 'o:p' tags.
+        for tag in div.findAll("head") + div.findAll("o:p"):
+            tag.extract()
+
+        # change any html and body tags to div.
+        for tag in div.findAll("html") + div.findAll("body"):
+            tag.name='div'
+
+        # remove extra bogus doctype.
+        #<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
+        return re.sub(r"<!DOCTYPE[^>]+>","",self.utf8FromSoup(url,div))

fanficdownloader/adapters/adapter_fanfictionnet.py

@@ -68,7 +68,7 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         return "http://www.fanfiction.net/s/1234/1/ http://www.fanfiction.net/s/1234/12/ http://www.fanfiction.net/s/1234/1/Story_Title"
 
     def getSiteURLPattern(self):
-        return r"http://(www|m)?\.fanfiction\.net/s/\d+(/\d+)?(/|/[a-zA-Z0-9_-]+)?/?$"
+        return r"http://(www|m)?\.fanfiction\.net/s/\d+(/\d+)?(/|/[^/]+)?/?$"
 
     def extractChapterUrlsAndMetadata(self):
 
@@ -215,9 +215,14 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         else:
             self.story.setMetadata('status', 'In-Progress')
 
-        img = soup.find('img',{'class':'cimage'})
-        if img:
-            self.setCoverImage(url,img['src'])
+        # Try the larger image first.
+        try:
+            img = soup.find('img',{'class':'lazy cimage'})
+            self.setCoverImage(url,img['data-original'])
+        except:
+            img = soup.find('img',{'class':'cimage'})
+            if img:
+                self.setCoverImage(url,img['src'])
             
         # Find the chapter selector 
         select = soup.find('select', { 'name' : 'chapter' } )

fanficdownloader/adapters/adapter_fanfiktionde.py

@@ -26,6 +26,7 @@ from .. import BeautifulSoup as bs
 from ..htmlcleanup import stripHTML
 from .. import exceptions as exceptions
 
+
 from base_adapter import BaseSiteAdapter,  makeDate
 
 def getClass():
@@ -140,7 +141,7 @@ class FanFiktionDeAdapter(BaseSiteAdapter):
         self.story.setMetadata('title',a.string)
         
         # Find authorid and URL from... author url.
-        head = soup.find('div', {'style' : 'width:85%;float:left;'})
+        head = soup.find('div', {'class' : 'story-metadata-left-top'})
         a = head.find('a')
         self.story.setMetadata('authorId',a['href'].split('/')[2])
         self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
@@ -176,7 +177,7 @@ class FanFiktionDeAdapter(BaseSiteAdapter):
         self.setDescription(url,a['onmouseover'].split("', '")[1])
         
         td = tr[i].findAll('td')
-        self.story.addToList('category',td[1].string)
+        self.story.addToList('category',stripHTML(td[1]))
         self.story.setMetadata('rating', td[4].string)
         self.story.setMetadata('numWords', td[5].string)
  

fanficdownloader/adapters/adapter_fictionalleyorg.py

@@ -223,7 +223,16 @@ class FictionAlleyOrgSiteAdapter(BaseSiteAdapter):
             
         if not data or not text:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
+
+        # not sure how, but we can get html, etc tags still in some
+        # stories.  That breaks later updates because it confuses
+        # epubutils.py
+        for tag in text.findAll('head'):
+            tag.extract()
+        
+        for tag in text.findAll('body') + text.findAll('html'):
+            tag.name = 'div'
+            
         return self.utf8FromSoup(url,text)
 
 def getClass():

fanficdownloader/adapters/adapter_fimfictionnet.py

@@ -81,8 +81,10 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
             apiResponse = urllib2.urlopen("http://www.fimfiction.net/api/story.php?story=%s" % (self.story.getMetadata("storyId"))).read()
             apiData = json.loads(apiResponse)
             
-            # Unfortunately, we still need to load the story index page to parse the characters
+            # Unfortunately, we still need to load the story index
+            # page to parse the characters.  And chapters, now, too.
             data = self._fetchUrl(self.url)
+            soup = bs.BeautifulSoup(data)
         except urllib2.HTTPError, e:
             if e.code == 404:
                 raise exceptions.StoryDoesNotExist(self.url)
@@ -95,9 +97,6 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
         if "/images/missing_story.png" in data:
             raise exceptions.StoryDoesNotExist(self.url)
         
-        if "Invalid story id" in apiData.values():
-            raise exceptions.StoryDoesNotExist(self.url)
-        
         if "This story has been marked as having adult content." in data:
             raise exceptions.AdultCheckRequired(self.url)
         
@@ -112,26 +111,59 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
             else:
                 raise exceptions.FailedToLogin(self.url,"Story requires individual password",passwdonly=True)
          
+        if "Invalid story id" in apiData.values():
+            raise exceptions.StoryDoesNotExist(self.url)
+        
         storyMetadata = apiData["story"]    
             
-        self.story.setMetadata("title", storyMetadata["title"])
+        ## Title
+        a = soup.find('a', href=re.compile(r'^/story/'+self.story.getMetadata('storyId')))
+        self.story.setMetadata('title',a.string)
+        
+        # self.story.setMetadata("title", storyMetadata["title"])
+        # if not storyMetadata["title"]:
+        #     raise exceptions.FailedToDownload("%s doesn't have a title in the API.  This is a known fimfiction.net bug with titles containing ."%self.url)
+        
         self.story.setMetadata("author", storyMetadata["author"]["name"])
         self.story.setMetadata("authorId", storyMetadata["author"]["id"])
         self.story.setMetadata("authorUrl", "http://%s/user/%s" % (self.getSiteDomain(), storyMetadata["author"]["name"]))
+
+        # chapters = [{"chapterTitle": chapter["title"], "chapterURL": chapter["link"]} for chapter in storyMetadata["chapters"]]
         
-        chapters = [{"chapterTitle": chapter["title"], "chapterURL": chapter["link"]} for chapter in storyMetadata["chapters"]]
-        for chapter in chapters:
-            self.chapterUrls.append((chapter["chapterTitle"], chapter["chapterURL"]))
-        self.story.setMetadata("numChapters", len(self.chapterUrls))
+        # ## this is bit of a kludge based on the assumption all the
+        # ## 'bad' chapters will be at the end.
+        # ## limit down to the number of chapters reported by chapter_count.
+        # chapters = chapters[:storyMetadata["chapter_count"]] 
         
+        # for chapter in chapters:
+        #     self.chapterUrls.append((chapter["chapterTitle"], chapter["chapterURL"]))
+        # self.story.setMetadata("numChapters", len(self.chapterUrls))
+
+        for chapter in soup.findAll('a',{'class':'chapter_link'}):
+            self.chapterUrls.append((stripHTML(chapter), 'http://'+self.host+chapter['href']))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+            
         # In the case of fimfiction.net, possible statuses are 'Completed', 'Incomplete', 'On Hiatus' and 'Cancelled'
-        # For the sake of bringing it in line with the other adapters, 'Incomplete' and 'On Hiatus' become 'In-Progress'
+        # For the sake of bringing it in line with the other adapters, 'Incomplete' becomes 'In-Progress'
         # and 'Complete' beomes 'Completed'. 'Cancelled' seems an important enough (not to mention more strictly true) 
         # status to leave unchanged.
-        status = storyMetadata["status"].replace("Incomplete", "In-Progress").replace("On Hiatus", "In-Progress").replace("Complete", "Completed")
+        # Nov2012 - 'On Hiatus' is now passed, too.  It's easy now for users to change/remove if they want
+        # with replace_metadata
+        status = storyMetadata["status"].replace("Incomplete", "In-Progress").replace("Complete", "Completed")
         self.story.setMetadata("status", status)
         self.story.setMetadata("rating", storyMetadata["content_rating_text"])
-            
+
+        ## Warnings aren't included in the API.
+        bottomli = soup.find('li',{'class':'bottom'})
+        if bottomli:
+            bottomspans = bottomli.findAll('span')
+            # the first span in bottom is the rating, obtained above.
+            if bottomspans and len(bottomspans) > 1:
+                for warning in bottomspans[1:]:
+                    self.story.addToList('warnings',warning.string)
+                
+        
         for category in storyMetadata["categories"]:
             if storyMetadata["categories"][category]:
                 self.story.addToList("genre", category) 
@@ -144,8 +176,9 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
                 coverurl = storyMetadata["full_image"]
             else:
                 coverurl = storyMetadata["image"]
-            if coverurl.startswith('//static.fimfiction.net'): # fix for img urls missing 'http:'
+            if coverurl.startswith('//'): # fix for img urls missing 'http:'
                 coverurl = "http:"+coverurl
+
             self.setCoverImage(self.url,coverurl)
 
         # the fimfic API gives bbcode for desc, not html.
@@ -159,12 +192,12 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
         self.story.setMetadata("datePublished", datetime.fromtimestamp(rawDatePublished))
         rawDateUpdated = storyMetadata["date_modified"]
         self.story.setMetadata("dateUpdated", datetime.fromtimestamp(rawDateUpdated))
-        
-        soup = bs.BeautifulSoup(data).find("div", {"class":"story"})
+
+        chars = soup.find("div", {"class":"story"})
         # fimfic stopped putting the char name on or around the char
         # icon now for some reason.  Pull it from the image name with
         # some heuristics.
-        for character in [character_icon["src"] for character_icon in soup.findAll("img", {"class":"character_icon"})]:
+        for character in [character_icon["src"] for character_icon in chars.findAll("img", {"class":"character_icon"})]:
             # //static.fimfiction.net/images/characters/twilight_sparkle.png
             # 5th split /, remove last four, replace _, capitolize every word(title())
             char = character.split('/')[5][:-4].replace('_',' ').title()
@@ -174,6 +207,15 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
                 char = "Cutie Mark Crusaders"
             self.story.addToList("characters", char)
             
+        # extra site specific metadata
+        extralist = ["likes","dislikes","views","total_views","short_description"]
+        for metakey in extralist:
+            if metakey in storyMetadata:
+                value = storyMetadata[metakey]
+                if not isinstance(value,basestring):
+                    value = unicode(value)
+                self.story.setMetadata(metakey, value)
+        
             
     def getChapterText(self, url):
         logger.debug('Getting chapter text from: %s' % url)

fanficdownloader/adapters/adapter_imagineeficcom.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2012 Fanficdownloader team
+# Copyright 2013 Fanficdownloader team
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -28,22 +28,15 @@ from .. import exceptions as exceptions
 from base_adapter import BaseSiteAdapter,  makeDate
 
 def getClass():
-    return YourFanfictionComAdapter
+    return ImagineEFicComAdapter
 
 # Class name has to be unique.  Our convention is camel case the
 # sitename with Adapter at the end.  www is skipped.
-class YourFanfictionComAdapter(BaseSiteAdapter):
+class ImagineEFicComAdapter(BaseSiteAdapter):
 
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
 
-        # yourfanfiction.com blocks the default user-agent.  However,
-        # when asked, they said it was just general anti-spam, not
-        # targeted as us and offered to 'whitelist our IP'.  Clearly,
-        # that wouldn't work, but it does let me do this in good
-        # conscience:
-        self.opener.addheaders = [('User-agent', 'FFDL/1.6')]
-
         self.decode = ["Windows-1252",
                        "utf8"] # 1252 is a superset of iso-8859-1.
                                # Most sites that claim to be
@@ -61,16 +54,16 @@ class YourFanfictionComAdapter(BaseSiteAdapter):
         self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
         
         # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','yff')
+        self.story.setMetadata('siteabbrev','ime')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%d %b %Y"
+        self.dateformat = "%Y.%m.%d"
             
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
-        return 'www.yourfanfiction.com'
+        return 'imagine.e-fic.com'
 
     def getSiteExampleURLs(self):
         return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
@@ -78,6 +71,41 @@ class YourFanfictionComAdapter(BaseSiteAdapter):
     def getSiteURLPattern(self):
         return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
 
+    ## Login seems to be reasonably standard across eFiction sites.
+    def needToLoginCheck(self, data):
+        if 'Registered Users Only' in data \
+                or 'There is no such account on our website' in data \
+                or "That password doesn't match the one in our database" in data:
+            return True
+        else:
+            return False
+        
+    def performLogin(self, url):
+        params = {}
+
+        if self.password:
+            params['penname'] = self.username
+            params['password'] = self.password
+        else:
+            params['penname'] = self.getConfig("username")
+            params['password'] = self.getConfig("password")
+        params['cookiecheck'] = '1'
+        params['submit'] = 'Submit'
+    
+        loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login'
+        logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
+                                                              params['penname']))
+    
+        d = self._fetchUrl(loginUrl, params)
+    
+        if "Member Account" not in d : #Member Account
+            logger.info("Failed to login to URL %s as %s" % (loginUrl,
+                                                              params['penname']))
+            raise exceptions.FailedToLogin(url,params['penname'])
+            return False
+        else:
+            return True
+
     ## Getting the chapter list and the meta data, plus 'is adult' checking.
     def extractChapterUrlsAndMetadata(self):
 
@@ -103,20 +131,12 @@ class YourFanfictionComAdapter(BaseSiteAdapter):
             else:
                 raise e
 
-        # The actual text that is used to announce you need to be an
-        # adult varies from site to site.  Again, print data before
-        # the title search to troubleshoot.
-            
-        # Since the warning text can change by warning level, let's
-        # look for the warning pass url.  ksarchive uses
-        # &warning= -- actually, so do other sites.  Must be an
-        # eFiction book.
-            
-        # viewstory.php?sid=1882&warning=4
-        # viewstory.php?sid=1654&ageconsent=ok&warning=5
-        #print data
-        #m = re.search(r"'viewstory.php\?sid=1882(&warning=4)'",data)
-        m = re.search(r"'viewstory.php\?sid=\d+((&ageconsent=ok)?&warning=\d+)'",data)
+        if self.needToLoginCheck(data):
+            # need to log in for this one.
+            self.performLogin(url)
+            data = self._fetchUrl(url)
+
+        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
         if m != None:
             if self.is_adult or self.getConfig("is_adult"):
                 # We tried the default and still got a warning, so
@@ -124,8 +144,7 @@ class YourFanfictionComAdapter(BaseSiteAdapter):
                 # link and reload data.
                 addurl = m.group(1)
                 # correct stupid & error in url.
-                # explicitly put ageconsent because google appengine regexp doesn't include it for some reason.
-                addurl = addurl.replace("&","&")+'&ageconsent=ok'
+                addurl = addurl.replace("&","&")
                 url = self.url+'&index=1'+addurl
                 logger.debug("URL 2nd try: "+url)
 
@@ -142,17 +161,9 @@ class YourFanfictionComAdapter(BaseSiteAdapter):
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
             raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
             
-        # because for some reason, this works while simple 'print data' errors on ascii conversion.
-        # loopdata = data
-        # chklen=5000
-        # while len(loopdata) > 0:
-        #     if len(loopdata) < 5000:
-        #         chklen = len(loopdata)
-        #     logger.info("loopdata: %s" % loopdata[:chklen])
-        #     loopdata = loopdata[chklen:]
-            
         # use BeautifulSoup HTML parser to make everything easier to find.
         soup = bs.BeautifulSoup(data)
+        # print data
 
         # Now go hunting for all the meta data and the chapter list.
         
@@ -182,6 +193,7 @@ class YourFanfictionComAdapter(BaseSiteAdapter):
                 return d[k]
             except:
                 return ""
+                
 
         # <span class="label">Rated:</span> NC-17<br /> etc
         labels = soup.findAll('span',{'class':'label'})
@@ -192,11 +204,9 @@ class YourFanfictionComAdapter(BaseSiteAdapter):
             if 'Summary' in label:
                 ## Everything until the next span class='label'
                 svalue = ""
-                while value and not defaultGetattr(value,'class') == 'label':
+                while not defaultGetattr(value,'class') == 'label':
                     svalue += str(value)
                     value = value.nextSibling
-                # sometimes poorly formated desc (<p> w/o </p>) leads
-                # to all labels being included.
                 self.setDescription(url,svalue)
                 #self.story.setMetadata('description',stripHTML(svalue))
 
@@ -217,17 +227,12 @@ class YourFanfictionComAdapter(BaseSiteAdapter):
                     self.story.addToList('characters',char.string)
 
             if 'Genre' in label:
-                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=5'))
-                for genre in genres:
-                    self.story.addToList('genre',genre.string)
-                    
-            if 'Tags' in label:
-                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=7'))
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
                 for genre in genres:
                     self.story.addToList('genre',genre.string)
 
             if 'Warnings' in label:
-                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=6'))
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
                 for warning in warnings:
                     self.story.addToList('warnings',warning.string)
 
@@ -241,8 +246,6 @@ class YourFanfictionComAdapter(BaseSiteAdapter):
                 self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
             
             if 'Updated' in label:
-                # there's a stray [ at the end.
-                #value = value[0:-1]
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
 
         try:

fanficdownloader/adapters/adapter_indeathnet.py

@@ -0,0 +1,179 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2012 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+logger = logging.getLogger(__name__)
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return InDeathNetAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class InDeathNetAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+		
+		  # get storyId from url--url validation guarantees query correct
+        m = re.match(self.getSiteURLPattern(),url)
+        if m:
+            self.story.setMetadata('storyId',m.group('id'))
+            logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+            # normalized story URL.
+            self._setURL('http://www.' + self.getSiteDomain() + '/blog/archive/'+self.story.getMetadata('storyId')+'-'+m.group('name')+'/')
+        else:
+            raise exceptions.InvalidStoryURL(url,
+                                             self.getSiteDomain(),
+                                             self.getSiteExampleURLs())
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','idn')
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%d %B %Y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'indeath.net'
+
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/blog/archive/123-story-in-death/"
+
+    def getSiteURLPattern(self):
+        # http://www.indeath.net/blog/archive/169-ransom-in-death/
+        return re.escape("http://")+re.escape(self.getSiteDomain())+r"/blog/(archive/)?(?P<id>\d+)\-(?P<name>[a-z0-9\-]*)/?$"     
+        
+            
+    def getDateFromComponents(self, postmonth, postday):
+        ym = re.search("Entries\ in\ (?P<mon>January|February|March|April|May|June|July|August|September|October|November|December)\ (?P<year>\d{4})",postmonth)
+        d = re.search("(?P<day>\d{2})\ (Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)",postday)
+        postdate = makeDate(d.group('day')+' '+ym.group('mon')+' '+ym.group('year'),self.dateformat)
+        return postdate
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        url = self.url
+        try:
+            data = self._fetchUrl(url)
+            
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.meta)
+            else:
+                raise e
+                
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        h = soup.find('a', id="blog_title")
+        t = h.find('span')
+        self.story.setMetadata('title',t.contents[0].string.strip())
+		
+        s = t.find('div')        
+        if s != None:
+            self.setDescription(url,s)
+		
+        # Find authorid and URL from first link in Recent Entries (don't yet reference 'recent entries' - let's see if that is required)
+        a = soup.find('a', href=re.compile(r"http://www.indeath.net/user/\d+\-[a-z0-9]+/$"))		#http://www.indeath.net/user/9083-cyrex/
+        m = re.search('http://www.indeath.net/user/(?P<id>\d+)\-(?P<name>[a-z0-9]*)/$',a['href'])
+        self.story.setMetadata('authorId',m.group('id'))
+        self.story.setMetadata('authorUrl',a['href'])
+        self.story.setMetadata('author',m.group('name'))
+
+
+
+
+        # Find the chapters:
+        chapters=soup.findAll('a', title="View entry", href=re.compile(r'http://www.indeath.net/blog/'+self.story.getMetadata('storyId')+"/entry\-(\d+)\-([^/]*)/$"))
+
+        #reverse the list since newest at the top
+        chapters.reverse()
+        
+        # Get date published & updated from first & last entries
+        posttable=soup.find('div', id="main_column")
+        
+        postmonths=posttable.findAll('th', text=re.compile(r'Entries\ in\ '))
+        postmonths.reverse()
+        
+        postdates=posttable.findAll('span', _class="desc", text=re.compile('\d{2}\ (Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)'))
+        postdates.reverse()
+        
+        self.story.setMetadata('datePublished',self.getDateFromComponents(postmonths[0],postdates[0]))
+        self.story.setMetadata('dateUpdated',self.getDateFromComponents(postmonths[len(postmonths)-1],postdates[len(postdates)-1]))
+        
+        # Process List of Chapters              
+        self.story.setMetadata('numChapters',len(chapters))
+        logger.debug("numChapters: (%s)"%self.story.getMetadata('numChapters'))
+        for x in range(0,len(chapters)):
+            # just in case there's tags, like <i> in chapter titles.
+            chapter=chapters[x]
+            if len(chapters)==1:
+                self.chapterUrls.append((self.story.getMetadata('title'),chapter['href']))
+            else:
+            	ct = stripHTML(chapter)
+            	tnew = re.match("(?i)"+self.story.getMetadata('title')+r" - (?P<newtitle>.*)$",ct)
+            	if tnew:
+            		chaptertitle = tnew.group('newtitle')
+            	else:
+            		chaptertitle = ct
+                self.chapterUrls.append((chaptertitle,chapter['href']))
+	
+		
+        
+        
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+        logger.debug('Getting chapter text from: %s' % url)
+		
+        #chapter=bs.BeautifulSoup('<div class="story"></div>')
+        data = self._fetchUrl(url)
+        soup = bs.BeautifulSoup(data,selfClosingTags=('br','hr','span','center'))
+
+        chapter = soup.find("div", "entry_content")
+        
+        if None == chapter:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+
+        return self.utf8FromSoup(url,chapter)
+

fanficdownloader/adapters/adapter_jlaunlimitedcom.py

@@ -0,0 +1,259 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2011 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+logger = logging.getLogger(__name__)
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+
+def getClass():
+    return JLAUnlimitedComAdapter
+
+
+class JLAUnlimitedComAdapter(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 = "" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+
+        self._setURL('http://' + self.getSiteDomain() + '/eFiction1.1/viewstory.php?sid='+self.story.getMetadata('storyId'))
+
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','jla')
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%m/%d/%y"
+
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'www.jlaunlimited.com'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/eFiction1.1/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/eFiction1.1/viewstory.php?sid=")+r"\d+$"
+
+
+
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        if self.is_adult or self.getConfig("is_adult"):
+            # Weirdly, different sites use different warning numbers.
+            # If the title search below fails, there's a good chance
+            # you need a different number.  print data at that point
+            # and see what the 'click here to continue' url says.
+            addurl = "&ageconsent=ok&warning=4" # 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
+
+        # Assume that if there is a url with 'warning=#' in the page then it is a 'check' page
+        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)
+                
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+
+        ## Title
+        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')))
+        self.story.setMetadata('title',a.string)
+        
+        # Find authorid and URL from... author url.
+        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # Find the chapters:
+        for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+")):
+            # just in case there's tags, like <i> in chapter titles.
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/eFiction1.1/'+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)
+
+            ## Not all sites use Genre, but there's no harm to
+            ## leaving it in.  Check to make sure the type_id number
+            ## is correct, though--it's site specific.
+            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)
+
+            ## Not all sites use Warnings, but there's no harm to
+            ## leaving it in.  Check to make sure the type_id number
+            ## is correct, though--it's site specific.
+            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+'/fanfic/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    break
+                i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+
+
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logger.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+
+        div = soup.find('div', {'id' : 'story'})
+        
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+
+        return self.utf8FromSoup(url,div)
+

fanficdownloader/adapters/adapter_ncisfictionnet.py

@@ -28,15 +28,20 @@ from .. import exceptions as exceptions
 from base_adapter import BaseSiteAdapter,  makeDate
 
 def getClass():
-    return NCISFictionComAdapter
+    return NCISFictionNetAdapter
 
 # Class name has to be unique.  Our convention is camel case the
 # sitename with Adapter at the end.  www is skipped.
-class NCISFictionComAdapter(BaseSiteAdapter):
+class NCISFictionNetAdapter(BaseSiteAdapter):
 
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
 
+        # ncisfiction.net blocks IPs the default user-agent.  However,
+        # when asked, they said it was just general anti-spam, not
+        # targeted at us.  That lets me do this in good conscience:
+        self.opener.addheaders = [('User-agent', 'FFDL/1.6')]
+        
         self.decode = ["iso-8859-1",
                        "Windows-1252"] # 1252 is a superset of iso-8859-1.
                                # Most sites that claim to be
@@ -64,13 +69,21 @@ class NCISFictionComAdapter(BaseSiteAdapter):
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
-        return 'www.ncisfiction.com'
+        return 'www.ncisfiction.net'
+
+    ## Changed from www.ncisfiction.com to www.ncisfiction.net Oct
+    ## 2012 due to the ncisfiction.com domain expiring.  Still accept
+    ## .com domains for existing updates, etc.
+    
+    @classmethod
+    def getAcceptDomains(cls):
+        return ['www.ncisfiction.net','www.ncisfiction.com']
 
     def getSiteExampleURLs(self):
         return "http://"+self.getSiteDomain()+"/story.php?stid=01234 http://"+self.getSiteDomain()+"/chapters.php?stid=1234"
 
     def getSiteURLPattern(self):
-        return "http://"+self.getSiteDomain()+r'/(chapters|story)?.php\?stid=\d+'
+        return r'http://www\.ncisfiction\.(net|com)/(chapters|story)?.php\?stid=\d+'
        
 
     ## Getting the chapter list and the meta data, plus 'is adult' checking.

fanficdownloader/adapters/adapter_pommedesangcom.py

@@ -0,0 +1,298 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2013 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+logger = logging.getLogger(__name__)
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return PommeDeSangComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class PommeDeSangComAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # pommedesang.com has two 'sections', shown in URL as
+        # 'efiction' and 'sds' that change how things should be
+        # handled.
+        # http://pommedesang.com/efiction/viewstory.php?sid=1234
+        # http://pommedesang.com/sds/viewstory.php?sid=1234
+        self.section=self.parsedUrl.path.split('/',)[1]
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/'+self.section+'/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','pmds')
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        if 'efiction' in self.section:
+            self.dateformat = "%b %d, %Y"
+        else:
+            self.dateformat = "%m/%d/%y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'pommedesang.com'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/efiction/viewstory.php?sid=1234 http://"+self.getSiteDomain()+"/sds/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return r"http://"+self.getSiteDomain()+"/(efiction|sds)?/viewstory.php\?sid=\d+$"
+
+    ## Login seems to be reasonably standard across eFiction sites.
+    def needToLoginCheck(self, data):
+        if 'Registered Users Only' in data \
+                or 'There is no such account on our website' in data \
+                or "That password doesn't match the one in our database" in data:
+            return True
+        else:
+            return False
+        
+    def performLogin(self, url):
+        params = {}
+
+        if self.password:
+            params['penname'] = self.username
+            params['password'] = self.password
+        else:
+            params['penname'] = self.getConfig("username")
+            params['password'] = self.getConfig("password")
+        params['cookiecheck'] = '1'
+        params['submit'] = 'Submit'
+    
+        loginUrl = 'http://' + self.getSiteDomain() + '/'+self.section+'/user.php?action=login'
+        logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
+                                                              params['penname']))
+    
+        d = self._fetchUrl(loginUrl, params)
+    
+        if "Member Account" not in d : #Member Account
+            logger.info("Failed to login to URL %s as %s" % (loginUrl,
+                                                              params['penname']))
+            raise exceptions.FailedToLogin(url,params['penname'])
+            return False
+        else:
+            return True
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        if self.is_adult or self.getConfig("is_adult"):
+            # Weirdly, different sites use different warning numbers.
+            # If the title search below fails, there's a good chance
+            # you need a different number.  print data at that point
+            # and see what the 'click here to continue' url says.
+            addurl = "&ageconsent=ok&warning=5"
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'+addurl
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        if self.needToLoginCheck(data):
+            # need to log in for this one.
+            self.performLogin(url)
+            data = self._fetchUrl(url)
+
+        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
+        if m != None:
+            if self.is_adult or self.getConfig("is_adult"):
+                # We tried the default and still got a warning, so
+                # let's pull the warning number from the 'continue'
+                # link and reload data.
+                addurl = m.group(1)
+                # correct stupid & error in url.
+                addurl = addurl.replace("&","&")
+                url = self.url+'&index=1'+addurl
+                logger.debug("URL 2nd try: "+url)
+
+                try:
+                    data = self._fetchUrl(url)
+                except urllib2.HTTPError, e:
+                    if e.code == 404:
+                        raise exceptions.StoryDoesNotExist(self.url)
+                    else:
+                        raise e    
+            else:
+                raise exceptions.AdultCheckRequired(self.url)
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        a = soup.find('a', href=re.compile('viewstory.php\?sid=\d+'))
+        self.story.setMetadata('title',a.string)
+        
+        # Find authorid and URL from... author url.
+        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # Find the chapters:
+        for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
+            # just in case there's tags, like <i> in chapter titles.
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+self.section+'/'+chapter['href']+addurl))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        # utility method
+        def defaultGetattr(d,k):
+            try:
+                return d[k]
+            except:
+                return ""
+                
+# summary, rated, word count, categories, characters, genre, warnings, completed, published, updated, seires
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        labels = soup.findAll('span',{'class':'label'})
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+
+            if 'Summary' in label:
+                ## Everything until the next span class='label'
+                svalue = ""
+                while not defaultGetattr(value,'class') == 'label':
+                    svalue += str(value)
+                    value = value.nextSibling
+                self.setDescription(url,svalue)
+                #self.story.setMetadata('description',stripHTML(svalue))
+
+            if 'Rated' in label:
+                self.story.setMetadata('rating', value)
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Categories' in label:
+                cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+                for cat in cats:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+                for char in chars:
+                    self.story.addToList('characters',char.string)
+
+            if 'Genre' in label:
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1')) # XXX
+                for genre in genres:
+                    self.story.addToList('genre',genre.string)
+
+            if 'Warnings' in label:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
+                for warning in warnings:
+                    self.story.addToList('warnings',warning.string)
+
+            if 'Completed' in label:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Updated' in label:
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/'+self.section+'/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            # can't use ^viewstory...$ in case of higher rated stories with javascript href.
+            storyas = seriessoup.findAll('a', href=re.compile('viewstory.php\?sid=\d+'))
+            i=1
+            for a in storyas:
+                # skip 'report this' and 'TOC' links
+                if 'contact.php' not in a['href'] and 'index' not in a['href']:
+                    if ('viewstory.php?sid='+self.story.getMetadata('storyId')) in a['href']:
+                        self.setSeries(series_name, i)
+                        break
+                    i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logger.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div', {'id' : 'story'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_ponyfictionarchivenet.py

@@ -237,8 +237,7 @@ class PonyFictionArchiveNetAdapter(BaseSiteAdapter):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        soup = bs.BeautifulSoup(self._fetchUrl(url)) # otherwise soup eats the br/hr tags.
         
         div = soup.find('div', {'id' : 'story'})
 

fanficdownloader/adapters/adapter_potionsandsnitchesnet.py

@@ -162,12 +162,12 @@ class PotionsAndSnitchesNetSiteAdapter(BaseSiteAdapter):
                     self.story.setMetadata('status', 'In-Progress')
 
             if 'Published' in label:
-                self.story.setMetadata('datePublished', makeDate(stripHTML(value), "%b %d %Y"))
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), "%d %b %Y"))
             
             if 'Updated' in label:
                 # there's a stray [ at the end.
                 #value = value[0:-1]
-                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), "%b %d %Y"))
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), "%d %b %Y"))
 
         try:
             # Find Series name from series URL.

fanficdownloader/adapters/adapter_potterficscom.py

@@ -0,0 +1,247 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2013 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import datetime
+import logging
+logger = logging.getLogger(__name__)
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter
+
+# This function is called by the downloader in all adapter_*.py files
+# in this dir to register the adapter class.  So it needs to be
+# updated to reflect the class below it.  That, plus getSiteDomain()
+# take care of 'Registering'.
+def getClass():
+    return PotterFicsComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class PotterFicsComAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+        
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query correct
+        m = re.match(self.getSiteURLPattern(),url)
+        if m:
+            self.story.setMetadata('storyId',m.group('id'))
+            logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+            # normalized story URL. gets rid of chapter if there, left with chapter index URL
+            nurl = "http://"+self.getSiteDomain()+"/historias/"+self.story.getMetadata('storyId')
+            self._setURL(nurl)
+        else:
+            raise exceptions.InvalidStoryURL(url,
+                                             self.getSiteDomain(),
+                                             self.getSiteExampleURLs())
+        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','potficscom')
+
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'www.potterfics.com'
+
+    def getSiteExampleURLs(self):
+        return \
+                "http://www.potterfics.com/historias/127583 "\
+                "http://www.potterfics.com/historias/127583/capitulo-1 "\
+                "http://www.potterfics.com/historias/127583/capitulo-4 "\
+                "http://www.potterfics.com/historias/92810 "\
+                "http://www.potterfics.com/historias/111194"
+
+    def getSiteURLPattern(self):
+        #http://www.potterfics.com/historias/127583
+        #http://www.potterfics.com/historias/127583/capitulo-1
+        #http://www.potterfics.com/historias/127583/capitulo-4
+        #http://www.potterfics.com/historias/92810              -> Complete story
+        #http://www.potterfics.com/historias/111194             -> Complete, single chap
+        p = re.escape("http://"+self.getSiteDomain()+"/historias/")+\
+            r"(?P<id>\d+)(/capitulo-(?P<ch>\d+))?/?$"
+        return p
+
+    def extractChapterUrlsAndMetadata(self):
+
+        #this converts '/historias/12345' to 'http://www.potterfics.com/historias/12345'
+        def makeAbsoluteURL(url):
+            if url[0] == '/':
+                url = 'http://'+self.getSiteDomain()+url
+            return url
+
+        #use this to get month numbers from Spanish months
+        SpanishMonths = {
+            'enero'      : '01',
+            'febrero'    : '02',
+            'marzo'      : '03',
+            'abril'      : '04',
+            'mayo'       : '05',
+            'junio'      : '06',
+            'julio'      : '07',
+            'agosto'     : '08',
+            'septiembre' : '09',
+            'octubre'    : '10',
+            'noviembre'  : '11',
+            'diciembre'  : '12'
+            }
+
+        url = self.url
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        #print data
+
+        #deal with adult content warnings - doesn't seem to apply to this site
+
+        #set constant meta for this site:
+        #Set Language = Spanish
+        self.story.setMetadata('language', 'Spanish')
+        #Set Category = Harry Potter
+        #  This is better done in plugin-defaults.ini and defaults.ini
+        #  by adding a section for this site with the line:
+        #  extracategories:Harry Potter
+        #self.story.addToList('category','Harry Potter')
+        
+        #get the rest of the meta
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        #self closing br and img present!
+        soup = bs.BeautifulSoup(data,selfClosingTags=('br','img'))
+    
+        #we want the second table directly under the body, contains all the metadata
+        table = soup.html.body.findAll('table', recursive=False)[1]
+        #within that, we want the second row, first cell
+        cell = table.tr.findNextSibling('tr').td
+
+        #find first metadata block
+        mb = cell.div.findNextSibling('div')
+        #Get meta...
+        self.story.setMetadata('title', mb.b.string)
+        #strip out brackets on rating
+        self.story.setMetadata('rating', mb.span.string[1:-1])
+        #Completion status is denoted by the presence of this image:
+        if mb.find('img',title="Historia terminada"):
+            self.story.setMetadata('status', 'Completed')
+        else:
+            self.story.setMetadata('status', 'In-Progress')
+
+        #find next metadata block
+        #author details
+        mb = mb.findNextSibling('div')
+        self.story.setMetadata('author', mb.b.a.string.strip())
+        self.story.setMetadata('authorUrl', makeAbsoluteURL(mb.b.a['href']))
+        self.story.setMetadata('authorId', self.story.getMetadata('authorUrl').split('/')[4])
+        #dates and times
+        mb = mb.find('span')
+        #posted/published = Escrita
+        date = mb.find(text=re.compile('Escrita el ')).strip().split()
+        year = int(date[7][:-1]) # need to remove the last char from year, it is a comma
+        month = int(SpanishMonths[date[5].lower()])
+        day = int(date[3])
+        time = date[8].split(':')
+        hour = int(time[0])
+        minute = int(time[1])
+        self.story.setMetadata('datePublished', datetime.datetime(year, month, day, hour, minute))
+        #updated = Actualizada
+        date = mb.find(text=re.compile('Actualizada el ')).strip().split()
+        year = int(date[7][:-1]) # need to remove the last char from year, it is a comma
+        month = int(SpanishMonths[date[5].lower()])
+        day = int(date[3])
+        time = date[8].split(':')
+        hour = int(time[0])
+        minute = int(time[1])
+        self.story.setMetadata('dateUpdated', datetime.datetime(year, month, day, hour, minute))
+        
+        mb = mb.span.findNextSibling('span').findNextSibling('span')
+        wc = mb.find(text=re.compile(' palabras en total')).strip()
+        self.story.setMetadata('numWords', wc.split()[0])
+        
+        #then we come to categories and genres. Oh dear. On this site, categories hold everything from genre, to ships, to crossovers.
+        #To make things worse, there is also another genre field, which often holds similar/duplicate info. Links to genre pages do not work
+        #though, so perhaps those will be phased out?
+        #for now, put them all into the genre list
+        links = mb.findAll('a',href=re.compile('/(categorias|generos)/\d+'))
+        genlist = [i.string.strip() for i in links]
+        self.story.extendList('genre',genlist)
+        
+        #get the chapter urls
+        #we can go back to the table cell we found before
+        #get its last element and work backwards to find the last ordered list on the page
+        list = cell.contents[len(cell)-1].findPrevious('ol')
+        chapters = []
+        revs = 0
+        chnum = 0
+        for li in list:
+            chnum += 1
+            chTitle = str(chnum) + '. ' + li.a.b.string.strip()
+            chURL = makeAbsoluteURL(li.a['href'])
+            chapters.append((chTitle,chURL))
+            #Get reviews, add to total
+            revs += int(li.div.a.string.split()[0])
+        
+        self.chapterUrls.extend(chapters)
+        self.story.setMetadata('numChapters', len(chapters))
+        self.story.setMetadata('reviews', revs)
+        
+        #Now for the description... this may be tricky...
+        #if it is there (doesn't have to be), it will be before the chapter list,
+        #separated by a horizontal rule, and after the google ad bar
+        
+        #get list's parent div
+        mb = list.parent
+        #get the div before that, will either be the description, or the google ad bar
+        mb = mb.findPreviousSibling('div')
+        if 'google_ad_client' in str(mb):
+            #couldn't find description, leaving it blank
+            pass
+        else:
+            self.setDescription(url,mb)
+        
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logger.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr','img'))
+        
+        div = soup.find('div', {'id' : 'cuerpoHistoria'})
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+        
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_restrictedsectionorg.py

@@ -0,0 +1,264 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2013 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+logger = logging.getLogger(__name__)
+import re
+import urllib2
+import cookielib as cl
+from datetime import datetime
+import json
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return RestrictedSectionOrgSiteAdapter
+
+class RestrictedSectionOrgSiteAdapter(BaseSiteAdapter):
+    
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+            
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        
+        # normalized story URL.
+        # get story/file and storyId from url--url validation guarantees query correct
+        m = re.match(self.getSiteURLPattern(),url)
+        if m:
+            self.story.setMetadata('storyId',m.group('id'))
+            logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+            # normalized story URL.
+            self._setURL('http://' + self.getSiteDomain() + '/' + m.group('filestory') + '.php?' + m.group('filestory') + '=' + self.story.getMetadata('storyId'))
+            logger.debug("storyUrl: (%s)"%self.story.getMetadata('storyUrl'))
+        else:
+            raise exceptions.InvalidStoryURL(url,
+                                             self.getSiteDomain(),
+                                             self.getSiteExampleURLs())
+        
+        self.story.setMetadata('siteabbrev','ressec')
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%d %b %Y" # 20 Nov 2005
+        
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        return 'www.restrictedsection.org'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/story.php?story=1234 http://"+self.getSiteDomain()+"/file.php?file=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain())+r"/(?P<filestory>file|story).php\?(file|story)=(?P<id>\d+)$"
+        
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        url = self.url
+        logger.debug("URL: "+url)
+
+        # one-shot stories use file url instead of story.  'Luckily',
+        # we don't have to worry about one-shots becoming
+        # multi-chapter because ressec is frozen.  Still need 'story'
+        # url for metadata, however.
+        try:
+            if 'file' in url:
+                data = self._postUrlUP(url)
+                soup = bs.BeautifulSoup(data)
+                storya = soup.find('a',href=re.compile(r"^story.php\?story=\d+"))
+                url = 'http://'+self.host+'/'+storya['href'].split('&')[0]  # strip rs_session
+
+                fileas = soup.find('a',href=re.compile(r"^file.php\?file=\d+"))
+                if fileas:
+                    for filea in fileas:
+                        if 'Previous Chapter' in filea.string or 'Next Chapter' in filea.string:
+                            raise exceptions.FailedToDownload(self.getSiteDomain() +" Cannot use chapter url with multi-chapter stories on this site.")
+                    
+            logger.debug("metadata URL: "+url)
+            data = self._fetchUrl(url)
+            # print data
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+        if "Story not found" in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Story not found.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+
+        # check user/pass on a chapter for multi-chapter
+        if 'file' not in self.url:
+            self._postUrlUP('http://'+self.host+'/'+soup.find('a', href=re.compile(r"^file.php\?file=\d+"))['href'])
+
+        ## Title
+        h2 = soup.find('h2')
+
+        # Find authorid and URL from... author url.
+        a = h2.find('a')
+        ahref = a['href'].split('&')[0]  # strip rs_session
+        
+        self.story.setMetadata('authorId',ahref.split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+ahref)
+        self.story.setMetadata('author',a.string)
+
+        # title, remove byauthorname.
+        self.story.setMetadata('title',h2.text[:h2.text.index("by"+a.string)])
+
+        dates = soup.findAll('span', {'class':'date'})
+        if dates: # only for multi-chapter
+            self.story.setMetadata('datePublished', makeDate(stripHTML(dates[0]), self.dateformat))
+            self.story.setMetadata('dateUpdated', makeDate(stripHTML(dates[-1]), self.dateformat))
+
+        words = soup.findAll('span', {'class':'size'})
+        wordcount=0
+        for w in words:
+            wordcount = wordcount + int(w.string[:-6].replace(',',''))
+
+        self.story.setMetadata('numWords',"%s"%wordcount)
+
+        self.story.setMetadata('rating', soup.find('a',href=re.compile(r"^rating.php\?rating=\d+")).string)
+        
+        # other tags
+
+        labels = soup.find('table', {'class':'info'}).findAll('th')
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+            
+            if label != None:
+                
+                if 'Categories' in label:
+                    for g in stripHTML(value).split('\n'):
+                        self.story.addToList('genre',g)
+                
+                if 'Pairings' in label:
+                    for g in stripHTML(value).split('\n'):
+                        self.story.addToList('ships',g)
+                
+                if 'Summary' in label:
+                    self.setDescription(url,stripHTML(value).replace("\n"," ").replace("\r",""))
+                    value.extract() # remove summary incase it contains file URLs.
+
+                if 'Updated' in label: # one-shots only.
+                    print "value:%s"%value
+                    value.find('sup').extract() # remove 'st', 'nd', 'th' ordinals
+                    print "value:%s"%value
+                    date = makeDate(stripHTML(value), '%d %B %Y') # full month name
+                    self.story.setMetadata('datePublished', date)
+
+                if 'Length' in label: # one-shots only.
+                    self.story.setMetadata('numWords',value.string[:-6])
+                    
+        # one-shot.
+        if 'file' in self.url:
+            self.chapterUrls.append((self.story.getMetadata('title'),self.url))
+        else: # multi-chapter
+            # Find the chapters: 'library_storyview.php?chapterid=3
+            chapters=soup.findAll('a', href=re.compile(r"^file.php\?file=\d+"))
+            if len(chapters)==0:
+                raise exceptions.FailedToDownload(self.getSiteDomain() +" says: No chapters found.")
+            else:
+                for chapter in chapters:
+                    chhref = chapter['href'].split('&')[0] # strip rs_session
+                    # just in case there's tags, like <i> in chapter titles.
+                    self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chhref))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+
+
+    def _postUrlUP(self, url):
+        params = {}
+        if self.password:
+            params['username'] = self.username
+            params['password'] = self.password
+        else:
+            params['username'] = self.getConfig("username")
+            params['password'] = self.getConfig("password")
+        params['accept.x'] = 1
+        params['accept.y'] = 1
+
+        excpt=None
+        for sleeptime in [0.5, 1.5, 4, 9]:
+            time.sleep(sleeptime)	
+            try:
+                data = self._postUrl(url, params)
+                if data == "Unable to connect to the database":
+                    raise exceptions.FailedToDownload("Site reported 'Unable to connect to the database'")
+                if "I certify that I am over the age of 18 and that accessing the following story will not violate the laws of my country or local ordinances." in data:
+                    raise exceptions.FailedToLogin(url,params['username'])
+                return data
+            except exceptions.FailedToLogin, ftl:
+                # no need to retry these.
+                raise(ftl)
+            except Exception, e:
+                excpt=e
+                logger.warn("Caught an exception reading URL: %s  Exception %s."%(unicode(url),unicode(e)))
+
+        logger.error("Giving up on %s" %url)
+        logger.exception(excpt)
+        raise(excpt)
+        
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logger.debug('Getting chapter text from: %s' % url)
+
+        data = self._postUrlUP(url)
+        #print("data:%s"%data)
+        
+        # some stories have html that confuses the parser.  For story
+        # text we don't care about anything before '<table id="page"'
+        # and seems to clear the issue.
+        data = data[data.index('<table id="page"'):]
+        
+        soup = bs.BeautifulSoup(data)
+        
+        div = soup.find('td',{'id':'page_content'})
+        div.name='div'
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+
+        ## Remove stuff from page_content
+
+        # Remove all tags before the first <hr> after class=info table (including hr)
+        hr = div.find('table',{'class':'info'}).findNext('hr')
+        for tag in hr.findAllPrevious():
+            tag.extract()
+        hr.extract()
+        
+        # Remove all tags after the last <hr> (including hr)
+        hr = div.findAll('hr')[-1]
+        for tag in hr.findAllNext():
+            tag.extract()
+        hr.extract()
+        
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_squidgeorgpeja.py

@@ -76,7 +76,7 @@ class SquidgeOrgPejaAdapter(BaseSiteAdapter):
         # The site domain.  Does have www here, if it uses it.
         return 'www.squidge.org'
     
-    @classmethod # must be @staticmethod, don't remove it.
+    @classmethod # must be @classmethod, don't remove it.
     def getConfigSection(cls):
         # The config section name.  Only override if != site domain.
         return cls.getSiteDomain()+'/peja'

fanficdownloader/adapters/adapter_test1.py

@@ -101,9 +101,10 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
                 }
             self.story.setMetadata('language',langs[idnum%len(langs)])
             self.setSeries('The Great Test',idnum)
-        
+        if idnum == 0:
+            self.setSeries("A Nook Hyphen Test "+self.story.getMetadata('dateCreated'),idnum)
+            
         self.story.setMetadata('rating','Tweenie')
-        
 
         if self.story.getMetadata('storyId') == '673':
             self.story.addToList('author','Author From List')
@@ -129,7 +130,7 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
 
         self.story.addToList('genre','Fantasy')
         self.story.addToList('genre','Comedy')
-        self.story.addToList('genre','SF')
+        self.story.addToList('genre','Sci-Fi')
         self.story.addToList('genre','Noir')
         
         self.story.addToList('characters','Bob Smith')
@@ -205,11 +206,24 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
 <p>http://test1.com?sid=668 - raises FailedToLogin unless username='Me'</p>
 <p>http://test1.com?sid=669 - Succeeds with Updated Date=now</p>
 <p>http://test1.com?sid=670 - Succeeds, but sleeps 2sec on each chapter</p>
+
+
+
+
 <p>http://test1.com?sid=671 - Succeeds, but sleeps 2sec metadata only</p>
-<p>http://test1.com?sid=672 - Succeeds, quick meta, sleeps 2sec chapters only</p>
-<p>http://test1.com?sid=673 - Succeeds, multiple authors</p>
-<p>Odd sid's will be In-Progress, evens complete.  sid&lt;10 will be assigned one of four languages and included in a series.</p>
+<p>http://test1.com?sid=672 - Succeeds, quick meta, sleeps 2sec chapters only</p><p>http://test1.com?sid=0 - Succeeds, generates some text specifically for testing hyphenation problems with Nook STR/STRwG</p><p>Odd sid's will be In-Progress, evens complete.  sid&lt;10 will be assigned one of four languages and included in a series.</p>
 </div>
+'''
+        elif self.story.getMetadata('storyId') == '0':
+            text=u'''
+<h3>45. Pronglet Returns to Hogwarts: Chapter 7</h3>
+<br />
+    eyes… but I’m not convinced we should automatically<br />
+<br /><br />
+<b>Thanks to the latest to recommend me: Alastor</b><br />
+<br /><br />
+    “Sure, invite her along. Does she have children?”<br />
+<br />
 '''
         else:
             text=u'''

fanficdownloader/adapters/adapter_thehexfilesnet.py

@@ -147,6 +147,7 @@ class TheHexFilesNetAdapter(BaseSiteAdapter):
             self.story.setMetadata('status', 'In-Progress')
 						
         summary = info.find('td', {'class' : 'summary'})
+        summary.name='div' # change td to div so it doesn't mess up the display when using table titlepage.
         self.setDescription(url,summary)
 		
         rating=stripHTML(info.find('td', {'align' : 'left'})).split('(')[1].split(')')[0]

fanficdownloader/adapters/adapter_thewriterscoffeeshopcom.py

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

fanficdownloader/adapters/adapter_twiwritenet.py

@@ -139,12 +139,14 @@ class TwiwriteNetSiteAdapter(BaseSiteAdapter):
         # use BeautifulSoup HTML parser to make everything easier to find.
         soup = bs.BeautifulSoup(data)
 
+        pagetitlediv = soup.find('div',id='pagetitle')
+        
         ## Title
-        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        a = pagetitlediv.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',a.string)
         
         # Find authorid and URL from... author url.
-        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        a = pagetitlediv.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)

fanficdownloader/adapters/base_adapter.py

@@ -255,6 +255,13 @@ class BaseSiteAdapter(Configurable):
         "Only needs to be overriden if != site domain."
         return cls.getSiteDomain()
     
+    @classmethod
+    def stripURLParameters(cls,url):
+        "Only needs to be overriden if URL contains more than one parameter"
+        ## remove any trailing '&' parameters--?sid=999 will be left.
+        ## that's all that any of the current adapters need or want.
+        return re.sub(r"&.*$","",url)
+    
     ## URL pattern validation is done *after* picking an adaptor based
     ## on domain instead of *as* the adaptor selector so we can offer
     ## the user example(s) for that particular site.

fanficdownloader/bbcodeutils/bbcodeparser.py

@@ -201,8 +201,11 @@ class bbcodeparser:
     #re_tagArgs = re.compile (r'\s*([^=]*)=(("([^"]+)")|([^\s]+))',  re.DOTALL | re.UNICODE)
     re_tagArgs = re.compile (r'\s*([\w]*)=(("([^"]+)")|([^\s]+))',  re.DOTALL | re.UNICODE)
 
-    # get a unique name and replace escaped braces 
-    unique = hashlib.md5(code).hexdigest()
+    # get a unique name and replace escaped braces encode utf8 to
+    # prevent CLI/Web from barfing on unicode chars.  Not sure why
+    # this even needs to be 'unique' like this, but that's the way
+    # they wrote it.
+    unique = hashlib.md5(code.encode('utf8')).hexdigest()
     code   = code.replace ('\[', unique+'_OPEN_BRACE')
     code   = code.replace ('\]', unique+'_CLOSE_BRACE')
 

fanficdownloader/configurable.py

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

fanficdownloader/epubutils.py

@@ -22,7 +22,7 @@ def get_dcsource_chaptercount(inputio):
 def get_update_data(inputio,
                     getfilecount=True,
                     getsoups=True):
-    epub = ZipFile(inputio, 'r')
+    epub = ZipFile(inputio, 'r') # works equally well with inputio as a path or a blob
 
     ## Find the .opf file.
     container = epub.read("META-INF/container.xml")
@@ -153,7 +153,7 @@ def get_path_part(n):
 def get_story_url_from_html(inputio,_is_good_url=None):
 
     #print("get_story_url_from_html called")
-    epub = ZipFile(inputio, 'r')
+    epub = ZipFile(inputio, 'r') # works equally well with inputio as a path or a blob
 
     ## Find the .opf file.
     container = epub.read("META-INF/container.xml")

fanficdownloader/story.py

@@ -21,6 +21,7 @@ import string
 from math import floor
 from functools import partial
 import logging
+logger = logging.getLogger(__name__)
 import urlparse as up
 
 import exceptions
@@ -29,10 +30,21 @@ from configurable import Configurable
 
 # Create convert_image method depending on which graphics lib we can
 # load.  Preferred: calibre, PIL, none
+        
+imagetypes = {
+    'jpg':'image/jpeg',
+    'jpeg':'image/jpeg',
+    'png':'image/png',
+    'gif':'image/gif',
+    'svg':'image/svg+xml',
+    }
+
 try:
     from calibre.utils.magick import Image
+    convtype = {'jpg':'JPG', 'png':'PNG'}
 
-    def convert_image(url,data,sizes,grayscale):
+    def convert_image(url,data,sizes,grayscale,
+                      removetrans,imgtype="jpg",background='#ffffff'):
         export = False
         img = Image()
         img.load(data)
@@ -44,18 +56,25 @@ try:
             img.size = (nwidth, nheight)
             export = True
             
+        if normalize_format_name(img.format) != imgtype:
+            export = True
+
+        if removetrans and img.has_transparent_pixels():
+            canvas = Image()
+            canvas.create_canvas(int(img.size[0]), int(img.size[1]), str(background))
+            canvas.compose(img)
+            img = canvas
+            export = True
+            
         if grayscale and img.type != "GrayscaleType":
             img.type = "GrayscaleType"
             export = True
 
-        if normalize_format_name(img.format) != "jpg":
-            export = True
-
         if export:
-            return (img.export('JPG'),'jpg','image/jpeg')
+            return (img.export(convtype[imgtype]),imgtype,imagetypes[imgtype])
         else:
-            logging.debug("image used unchanged")
-            return (data,'jpg','image/jpeg')
+            logger.debug("image used unchanged")
+            return (data,imgtype,imagetypes[imgtype])
         
 except:
 
@@ -63,8 +82,9 @@ except:
     try:
         import Image
         from StringIO import StringIO
-        def convert_image(url,data,sizes,grayscale):
-            
+        convtype = {'jpg':'JPEG', 'png':'PNG'}
+        def convert_image(url,data,sizes,grayscale,
+                          removetrans,imgtype="jpg",background='#ffffff'):
             export = False
             img = Image.open(StringIO(data))
             
@@ -75,36 +95,36 @@ except:
                 img = img.resize((nwidth, nheight),Image.ANTIALIAS)
                 export = True
                 
-            if grayscale and img.mode != "L":
-                img = img.convert("L")
-                export = True
-
-            if normalize_format_name(img.format) != "jpg":
+            if normalize_format_name(img.format) != imgtype:
                 if img.mode == "P":
                     # convert pallete gifs to RGB so jpg save doesn't fail.
                     img = img.convert("RGB")
                 export = True
 
+            if removetrans and img.mode == "RGBA":
+                background = Image.new('RGBA', img.size, background)
+                # Paste the image on top of the background
+                background.paste(img, img)
+                img = background.convert('RGB')
+                export = True
+
+            if grayscale and img.mode != "L":
+                img = img.convert("L")
+                export = True
+
             if export:
                 outsio = StringIO()
-                img.save(outsio,'JPEG')
-                return (outsio.getvalue(),'jpg','image/jpeg')
+                img.save(outsio,convtype[imgtype])
+                return (outsio.getvalue(),imgtype,imagetypes[imgtype])
             else:
-                logging.debug("image used unchanged")
-                return (data,'jpg','image/jpeg')
+                logger.debug("image used unchanged")
+                return (data,imgtype,imagetypes[imgtype])
         
     except:
         # No calibre or PIL, simple pass through with mimetype.
-        def convert_image(url,data,sizes,grayscale):
+        def convert_image(url,data,sizes,grayscale,
+                          removetrans,imgtype="jpg",background='#ffffff'):
             return no_convert_image(url,data)
-        
-imagetypes = {
-    'jpg':'image/jpeg',
-    'jpeg':'image/jpeg',
-    'png':'image/png',
-    'gif':'image/gif',
-    'svg':'image/svg+xml',
-    }
 
 ## also used for explicit no image processing.
 def no_convert_image(url,data):
@@ -113,7 +133,7 @@ def no_convert_image(url,data):
     ext=parsedUrl.path[parsedUrl.path.rfind('.')+1:].lower()
     
     if ext not in imagetypes:
-        logging.debug("no_convert_image url:%s - no known extension"%url)
+        logger.debug("no_convert_image url:%s - no known extension"%url)
         # doesn't have extension? use jpg.
         ext='jpg'
         
@@ -240,7 +260,8 @@ class Story(Configurable):
             self.metadata[key]=value
         if key == "language":
             try:
-                self.metadata['langcode'] = langs[self.metadata[key]]
+                # getMetadata not just self.metadata[] to do replace_metadata.
+                self.metadata['langcode'] = langs[self.getMetadata(key)]
             except:
                 self.metadata['langcode'] = 'en'
         if key == 'dateUpdated':
@@ -253,24 +274,40 @@ class Story(Configurable):
     ## Three part effect only those key(s) lists.
     ## pattern=>replacement
     ## metakey,metakey=>pattern=>replacement
+    ## *Five* part lines.  Effect only when trailing conditional key=>regexp matches
+    ## metakey[,metakey]=>pattern=>replacement[&&metakey=>regexp]
     def setReplace(self,replace):
         for line in replace.splitlines():
+            (metakeys,regexp,replacement,condkey,condregexp)=(None,None,None,None,None)
+            if "&&" in line:
+                (line,conditional) = map( lambda x: x.strip(), line.split("&&") )
+                (condkey,condregexp) = map( lambda x: x.strip(), conditional.split("=>") )
             if "=>" in line:
                 parts = map( lambda x: x.strip(), line.split("=>") )
                 if len(parts) > 2:
-                    parts[0] = map( lambda x: x.strip(), parts[0].split(",") )
-                    self.replacements.append(parts)
+                    metakeys = map( lambda x: x.strip(), parts[0].split(",") )
+                    (regexp,replacement)=parts[1:]
                 else:
-                    self.replacements.append([None]+parts)
+                    (regexp,replacement)=parts
+
+            if regexp:
+                regexp = re.compile(regexp)
+                if condregexp:
+                    condregexp = re.compile(condregexp)
+                self.replacements.append([metakeys,regexp,replacement,condkey,condregexp])
     
     def doReplacments(self,value,key):
-        for (keys,p,v) in self.replacements:
-            if (keys == None or key in keys) \
+        for (metakeys,regexp,replacement,condkey,condregexp) in self.replacements:
+            if (metakeys == None or key in metakeys) \
                     and isinstance(value,basestring) \
-                    and re.search(p,value):
-                #pv=value
-                value = re.sub(p,v,value)
-                #print("change:%s => %s === %s => %s "%(p,v,pv,value))
+                    and regexp.search(value):
+                doreplace=True
+                if condkey and condkey != key: # prevent infinite recursion.
+                    condval = self.getMetadata(condkey)
+                    doreplace = condval != None and condregexp.search(condval)
+                    
+                if doreplace:
+                    value = regexp.sub(replacement,value)
         return value
         
     def getMetadataRaw(self,key):
@@ -395,8 +432,13 @@ class Story(Configurable):
                                   map(removeAllEntities,retlist) )
 
         if retlist:
-            # remove dups and sort.
-            return sorted(list(set(retlist)))
+            if listname in ('author','authorUrl'):
+                # need to retain order for author & authorUrl so the
+                # two match up.
+                return retlist
+            else:
+                # remove dups and sort.
+                return sorted(list(set(retlist)))
         else:
             return []
 
@@ -452,7 +494,7 @@ class Story(Configurable):
             pattern = re.compile(r"[^a-zA-Z0-9_\. \[\]\(\)&'-]+")
             for k in origvalues.keys():
                 values[k]=re.sub(pattern,'_', removeAllEntities(self.getMetadata(k)))
-
+    
         return string.Template(template).substitute(values).encode('utf8')
 
     # pass fetch in from adapter in case we need the cookies collected
@@ -502,18 +544,27 @@ class Story(Configurable):
             try:
                 if self.getConfig('no_image_processing'):
                     (data,ext,mime) = no_convert_image(imgurl,
-                                                   fetch(imgurl))
+                                                       fetch(imgurl))
                 else:
                     try:
                         sizes = [ int(x) for x in self.getConfigList('image_max_size') ]
                     except Exception, e:
                         raise exceptions.FailedToDownload("Failed to parse image_max_size from personal.ini:%s\nException: %s"%(self.getConfigList('image_max_size'),e))
+                    grayscale = self.getConfig('grayscale_images')
+                    imgtype = self.getConfig('convert_images_to')
+                    if not imgtype:
+                        imgtype = "jpg"
+                    removetrans = self.getConfig('remove_transparency')
+                    removetrans = removetrans or grayscale or imgtype=="jpg"
                     (data,ext,mime) = convert_image(imgurl,
                                                     fetch(imgurl),
                                                     sizes,
-                                                    self.getConfig('grayscale_images'))
+                                                    grayscale,
+                                                    removetrans,
+                                                    imgtype,
+                                                    background="#"+self.getConfig('background_color'))
             except Exception, e:
-                logging.info("Failed to load or convert image, skipping:\n%s\nException: %s"%(imgurl,e))
+                logger.info("Failed to load or convert image, skipping:\n%s\nException: %s"%(imgurl,e))
                 return "failedtoload"
             
             # explicit cover, make the first image.
@@ -548,7 +599,7 @@ class Story(Configurable):
                     ext)
                 self.imgtuples.append({'newsrc':newsrc,'mime':mime,'data':data})
                 
-            logging.debug("\nimgurl:%s\nnewsrc:%s\nimage size:%d\n"%(imgurl,newsrc,len(data)))
+            logger.debug("\nimgurl:%s\nnewsrc:%s\nimage size:%d\n"%(imgurl,newsrc,len(data)))
         else:
             newsrc = self.imgtuples[self.imgurls.index(imgurl)]['newsrc']
             

fanficdownloader/writers/writer_epub.py

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

index.html

@@ -54,6 +54,17 @@
 	      much easier. </p>
 	  </div>
 	  <!-- put announcements here, h3 is a good title size. -->
+	  <h3>Changes:</h3>
+	  <p>
+	    All minor changes this time.
+	    <ul>
+	      <li>Improve error handling, add retry for restrictedsection.org.</li>
+	      <li>Strip leading 0s from story ids for canonical ids in AO3.</li>
+	      <li>Better fix for Nook hyphenation issue--Nook now honors adobe-hyphenate: none.</li>
+	      <li>Fix broken lastupdate tags feature.  Defaulted off for PI.</li>
+	      <li>Fix author URLs for multiple author stories.</li>
+	    </ul>
+	  </p>
 	  <p>
 	    Questions?  Check out our 
 	    <a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderFAQs">FAQs</a>.
@@ -62,7 +73,7 @@
 	    If you have any problems with this application, please
 	    report them in
 	    the <a href="http://groups.google.com/group/fanfic-downloader">FanFictionDownLoader Google Group</a>.  The
-	    <a href="http://4-4-28.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
+	    <a href="http://4-4-41.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
 	  </p>
 	  <div id='error'>
 	    {{ error_message }}
@@ -385,11 +396,6 @@
 	    Use the URL of the story's first chapter, such as
 	    <br /><a href="http://samdean.archive.nu/viewstory.php?sid=1234">http://samdean.archive.nu/viewstory.php?sid=1234</a>
 	  </dd>
-	  <dt>www.yourfanfiction.com</dt>
-	  <dd>
-	    Use the URL of the story's first chapter, such as
-	    <br /><a href="http://www.yourfanfiction.com/viewstory.php?sid=1234">http://www.yourfanfiction.com/viewstory.php?sid=1234</a>
-	  </dd>
 	  <dt>www.destinysgateway.com</dt>
 	  <dd>
 	    Use the URL of the story's first chapter, such as
@@ -544,8 +550,62 @@
 	    Use the URL of the story's chapter list, such as
 	    <br /><a href="http://www.qaf-fic.com/atp/viewstory.php?sid=1234">http://www.qaf-fic.com/atp/viewstory.php?sid=1234</a>
 	  </dd>
+	  <dt>indeath.net</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://www.indeath.net/blog/25-nightmare-in-death/">http://www.indeath.net/blog/25-nightmare-in-death/</a>
+	  </dd>
+	  <dt>www.jlaunlimited.com</dt>
+	  <dd>
+	    Use the URL of the story's first chapter, such as
+	    <br /><a href="http://www.jlaunlimited.com/eFiction1.1/viewstory.php?sid=1234">http://www.jlaunlimited.com/eFiction1.1/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>www.efpfanfic.net</dt>
+	  <dd>
+	    Use the URL of any story chapter, such as
+	    <br /><a href="http://www.efpfanfic.net/viewstory.php?sid=12345">http://www.efpfanfic.net/viewstory.php?sid=12345</a>
+	  </dd>
+	  <dt>www.potterfics.com</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://www.potterfics.com/historias/127583">http://www.potterfics.com/historias/127583</a>
+	  </dd>
+	  <dt>www.dotmoon.net</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://www.dotmoon.net/library_view.php?storyid=1234">http://www.dotmoon.net/library_view.php?storyid=1234</a>
+	  </dd>
+	  <dt>efiction.esteliel.de</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://efiction.esteliel.de/viewstory.php?sid=1234">http://efiction.esteliel.de/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>pommedesang.com</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://pommedesang.com/efiction/viewstory.php?sid=1234">http://pommedesang.com/efiction/viewstory.php?sid=1234</a>
+	    <br /><a href="http://pommedesang.com/sds/viewstory.php?sid=1234">http://pommedesang.com/sds/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>www.restrictedsection.org</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://www.restrictedsection.org/story.php?story=1234">http://www.restrictedsection.org/story.php?story=1234</a>
+	    <br />Or the story URL for one-shots, such as
+	    <br /><a href="http://www.restrictedsection.org/file.php?file=1234">http://www.restrictedsection.org/file.php?file=1234</a>
+	  </dd>
+	  <dt>imagine.e-fic.com</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://imagine.e-fic.com/viewstory.php?sid=1234">http://imagine.e-fic.com/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>buffynfaith.net</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://buffynfaith.net/fanfictions/index.php?act=vie&id=1234">http://buffynfaith.net/fanfictions/index.php?act=vie&amp;id=1234</a>
+	    <br />Or, use the URL of any story chapter, such as
+	    <br /><a href="http://buffynfaith.net/fanfictions/index.php?act=vie&id=1234&ch=2">http://buffynfaith.net/fanfictions/index.php?act=vie&amp;id=1234&amp;ch=2</a>
+	  </dd>
 	</dl>
-		    
 
 	<p>
 	  A few additional things to know, which will make your life substantially easier:

plugin-defaults.ini

@@ -131,8 +131,11 @@ extratags: FanFiction
 ## for regexp details.
 ## Make sure to keep at least one space at the start of each line and
 ## to escape % to %%, if used.
-## Two or three part lines.  Two part effect everything.
+## 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.
 #replace_metadata:
 # genre,category=>Sci-Fi=>SF
 # Puella Magi Madoka Magica.* => Madoka
@@ -140,7 +143,9 @@ extratags: FanFiction
 # Crossover: (.*)=>\1
 # title=>(.*)Great(.*)=>\1Moderate\2
 # .*-Centered=>
-
+# characters=>Sam W\.=>Sam Witwicky&&category=>Transformers
+# characters=>Sam W\.=>Sam Winchester&&category=>Supernatural
+ 
 ## Some readers don't show horizontal rule (<hr />) tags correctly.
 ## This replaces them all with a centered '* * *'.  (Note centering
 ## doesn't work on some devices either.)
@@ -291,12 +296,13 @@ background_color: ffffff
 ## Allow customization of CSS.  Make sure to keep at least one space
 ## at the start of each line and to escape % to %%.  Also need
 ## background_color to be in the same section, if included in CSS.
-## 'adobe-text-layout: optimizeSpeed;' prevents hyphenation on newer Nooks
+## 'adobe-hyphenate: none;' prevents hyphenation on newer Nooks
+## STR(wG) (1.2.1+ for sure)
 output_css: 
  body { background-color: #%(background_color)s;
         text-align: justify;
         margin: 2%%;
-	adobe-text-layout: optimizeSpeed; }
+	adobe-hyphenate: none; }
  pre { font-size: x-small; }
  sml { font-size: small; }
  h1 { text-align: center; }
@@ -428,20 +434,26 @@ extratags: FanFiction,Testing,HTML
 #is_adult:true
 
 ## AO3 adapter defines a few extra metadata entries.
-extra_valid_entries:fandoms,freefromtags,ao3categories,comments,kudos,hits,bookmarks
+extra_valid_entries:fandoms,freeformtags,freefromtags,ao3categories,comments,kudos,hits,bookmarks,collections
 fandoms_label:Fandoms
+freeformtags_label:Freeform Tags
 freefromtags_label:Freeform Tags
 ao3categories_label:AO3 Categories
 comments_label:Comments
 kudos_label:Kudos
 hits_label:Hits
-bookmarks:Bookmarks
+collections_label:Collections
+bookmarks_label:Bookmarks
+
+## freeformtags was previously typo'ed as freefromtags.  This way,
+## freefromtags will still work for people who've used it.
+include_in_freefromtags:freeformtags
 
 ## adds to titlepage_entries instead of replacing it.
-#extra_titlepage_entries: fandoms,freefromtags,ao3categories,comments,kudos,hits,bookmarks
+#extra_titlepage_entries: fandoms,freeformtags,ao3categories,comments,kudos,hits,bookmarks
 
 ## adds to include_subject_tags instead of replacing it.
-#extra_subject_tags:fandoms,freefromtags,ao3categories
+#extra_subject_tags:fandoms,freeformtags,ao3categories
 
 [ashwinder.sycophanthex.com]
 ## Site dedicated to these categories/characters/ships
@@ -472,6 +484,15 @@ extracategories:Blood Ties
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+[buffynfaith.net]
+## Site dedicated to these categories/characters/ships
+extracategories:Buffy: The Vampire Slayer
+
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
+#is_adult:true
+
 [castlefans.org]
 ## Site dedicated to these categories/characters/ships
 extracategories:Castle
@@ -529,6 +550,10 @@ extraships:Draco Malfoy/Hermione Granger
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+## some sites include images that we don't ever want becoming the
+## cover image.  This lets you exclude them.
+cover_exclusion_regexp:/images/.*?ribbon.gif
+
 ## Some adapters collect additional meta information beyond the
 ## standard ones.  They need to be defined in extra_valid_entries to
 ## tell the rest of the FFDL system about them.  They can be used in
@@ -569,15 +594,19 @@ cliches_label:Character Cliches
 ## then the label of the calibre custom column, then (optionally) a
 ## 'mode'.  'r' to Replace any existing values, 'a' to Add to existing
 ## value (use with tag-like columns), and 'n' for setting on New books
-## only.
-## Make sure to keep at least one space at the start of each
-## line.
+## only.  (Default is 'r'.)
+## Each metadata=>column mapping must be on a separate line and each
+## needs to have one space at the start of each line.
 
 #custom_columns_settings:
 # cliches=>#acolumn,r
 # themes=>#bcolumn,a
 # timeline=>#ccolumn,n
 
+[efiction.esteliel.de]
+## Site dedicated to these categories/characters/ships
+extracategories:Lord of the Rings
+
 [erosnsappho.sycophanthex.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
@@ -654,6 +683,23 @@ extracharacters:Hermione Granger
 ## Site dedicated to these categories/characters/ships
 extracategories:Highlander
 
+[imagine.e-fic.com]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
+#is_adult:true
+
+[indeath.net]
+## Site dedicated to these categories/characters/ships
+extracategories:In Death
+
 [ksarchive.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Star Trek
@@ -735,6 +781,22 @@ extracategories:One Direction
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+[pommedesang.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Anita Blake Vampire Hunter 
+
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
+#is_adult:true
+
 [ponyfictionarchive.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:My Little Pony: Friendship is Magic
@@ -887,6 +949,29 @@ extracategories:InuYasha
 extracharacters:Sesshoumaru,Kagome
 extraships:Sesshoumaru/Kagome
 
+[www.dotmoon.net]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+[www.efpfanfic.net]
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Extra metadata that this adapter knows about.  See [dramione.org]
+## for examples of how to use them.
+extra_valid_entries:notes,context,type
+notes_label:Notes
+context_label:Context
+type_label:Type of Couple
+
 [www.fanfiction.net]
 ## fanfiction.net's 'cover' images are really just tiny thumbnails.
 ## Change this to false to use them anyway.
@@ -935,6 +1020,15 @@ extra_valid_entries:reviews,favs,follows
 ## Site dedicated to these categories/characters/ships
 extracategories:My Little Pony: Friendship is Magic
 
+## Extra metadata that this adapter knows about.  See [dramione.org]
+## for examples of how to use them.
+extra_valid_entries:likes,dislikes,views,total_views,short_description
+likes_label:Likes
+dislikes_label:Dislikes
+views_label:Highest Single Chapter Views
+total_views_label:Total Views
+short_description_label:Short Summary
+
 ## 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.
@@ -985,6 +1079,10 @@ extraships:InuYasha/Kagome
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+[www.jlaunlimited.com]
+## Site dedicated to these categories/characters/ships
+extracategories:JLA
+
 [www.libraryofmoria.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Lord of the Rings
@@ -1009,7 +1107,7 @@ extracategories:Queer as Folk
 ## cover image.  This lets you exclude them.
 cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
 
-[www.ncisfiction.com]
+[www.ncisfiction.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:NCIS
 
@@ -1029,6 +1127,10 @@ extraships:Harry Potter/Ginny Weasley
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
 
+[www.potterfics.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
 [www.prisonbreakfic.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:Prison Break
@@ -1042,6 +1144,16 @@ extracategories:Queer as Folk
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[www.restrictedsection.org]
+extracategories:Harry Potter
+extragenres:Erotica
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
 [www.scarvesandcoffee.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:Glee
@@ -1191,12 +1303,6 @@ extracategories:Stargate: Atlantis
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
-[www.yourfanfiction.com]
-## Some sites do not require a login, but do require the user to
-## confirm they are adult for adult content.  In commandline version,
-## this should go in your personal.ini, not defaults.ini.
-#is_adult:true
-
 [overrides]
 ## It may sometimes be useful to override all of the specific format,
 ## site and site:format sections in your private configuration.  For