Bump versions.

meta section, fix highbyte chars in description.

app.yaml

@@ -1,6 +1,6 @@
 # ffd-retief-hrd fanfictiondownloader
 application: fanfictiondownloader
-version: 4-4-50
+version: 4-4-63
 runtime: python27
 api_version: 1
 threadsafe: true

calibre-plugin/__init__.py

@@ -1,11 +1,10 @@
 #!/usr/bin/env python
-# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
 # -*- coding: utf-8 -*-
 from __future__ import (unicode_literals, division, absolute_import,
                         print_function)
 
 __license__   = 'GPL v3'
-__copyright__ = '2011, Jim Miller'
+__copyright__ = '2013, Jim Miller'
 __docformat__ = 'restructuredtext en'
 
 # The class that all Interface Action plugin wrappers must inherit from
@@ -27,7 +26,7 @@ class FanFictionDownLoaderBase(InterfaceActionBase):
     description         = 'UI plugin to download FanFiction stories from various sites.'
     supported_platforms = ['windows', 'osx', 'linux']
     author              = 'Jim Miller'
-    version             = (1, 7, 17)
+    version             = (1, 7, 30)
     minimum_calibre_version = (0, 8, 57)
 
     #: This field defines the GUI plugin class that contains all the code

calibre-plugin/common_utils.py

@@ -239,8 +239,8 @@ class SizePersistedDialog(QDialog):
             self.restoreGeometry(self.geom)
 
     def dialog_closing(self, result):
-        geom = bytearray(self.saveGeometry())
-        gprefs[self.unique_pref_name] = geom
+        self.geom = bytearray(self.saveGeometry())
+        gprefs[self.unique_pref_name] = self.geom
 
 
 class ReadOnlyTableWidgetItem(QTableWidgetItem):

calibre-plugin/config.py

@@ -13,10 +13,10 @@ from collections import OrderedDict
 from PyQt4.Qt import (QDialog, QWidget, QVBoxLayout, QHBoxLayout, QLabel,
                       QLineEdit, QFont, QWidget, QTextEdit, QComboBox,
                       QCheckBox, QPushButton, QTabWidget, QVariant, QScrollArea,
-                      QDialogButtonBox )
+                      QDialogButtonBox, QGroupBox )
 
-from calibre.utils.config import JSONConfig
 from calibre.gui2.ui import get_gui
+from calibre.gui2 import dynamic, info_dialog
 
 from calibre_plugins.fanfictiondownloader_plugin.prefs import prefs, PREFS_NAMESPACE
 from calibre_plugins.fanfictiondownloader_plugin.dialogs \
@@ -266,13 +266,16 @@ class BasicTab(QWidget):
         self.plugin_action = plugin_action
         QWidget.__init__(self)
         
-        self.l = QVBoxLayout()
-        self.setLayout(self.l)
+        topl = QVBoxLayout()
+        self.setLayout(topl)
 
         label = QLabel('These settings control the basic features of the plugin--downloading FanFiction.')
         label.setWordWrap(True)
-        self.l.addWidget(label)
-        self.l.addSpacing(5)
+        topl.addWidget(label)
+
+        defs_gb = groupbox = QGroupBox("Defaults Options on Download")
+        self.l = QVBoxLayout()
+        groupbox.setLayout(self.l)
 
         tooltip = "On each download, FFDL offers an option to select the output format. <br />This sets what that option will default to."
         horz = QHBoxLayout()
@@ -317,7 +320,9 @@ class BasicTab(QWidget):
         self.updateepubcover.setChecked(prefs['updateepubcover'])
         self.l.addWidget(self.updateepubcover)
 
-        self.l.addSpacing(10)        
+        cali_gb = groupbox = QGroupBox("Updating Calibre Options")
+        self.l = QVBoxLayout()
+        groupbox.setLayout(self.l)
 
         self.deleteotherforms = QCheckBox('Delete other existing formats?',self)
         self.deleteotherforms.setToolTip('Check this to automatically delete all other ebook formats when updating an existing book.\nHandy if you have both a Nook(epub) and Kindle(mobi), for example.')
@@ -334,14 +339,24 @@ class BasicTab(QWidget):
         self.keeptags.setChecked(prefs['keeptags'])
         self.l.addWidget(self.keeptags)
 
-        self.l.addSpacing(10)        
+        self.checkforseriesurlid = QCheckBox("Check for existing Series Anthology books?",self)
+        self.checkforseriesurlid.setToolTip("Check for existings Series Anthology books using each new story's series URL before downloading.\nOffer to skip downloading if a Series Anthology is found.")
+        self.checkforseriesurlid.setChecked(prefs['checkforseriesurlid'])
+        self.l.addWidget(self.checkforseriesurlid)
+
+        self.lookforurlinhtml = QCheckBox("Search EPUB text for Story URL?",self)
+        self.lookforurlinhtml.setToolTip("Look for first valid story URL inside EPUB text if not found in metadata.\nSomewhat risky, could find wrong URL depending on EPUB content.\nAlso finds and corrects bad ffnet URLs from ficsaver.com files.")
+        self.lookforurlinhtml.setChecked(prefs['lookforurlinhtml'])
+        self.l.addWidget(self.lookforurlinhtml)
 
         self.showmarked = QCheckBox("Show added/updated books when finished?",self)
         self.showmarked.setToolTip("Show added/updated books only when finished.\nYou can also manually search for 'marked:ffdl_success'.\n'marked:ffdl_failed' is also available, or search 'marked:ffdl' for both.")
         self.showmarked.setChecked(prefs['showmarked'])
         self.l.addWidget(self.showmarked)
 
-        self.l.addSpacing(10)        
+        gui_gb = groupbox = QGroupBox("GUI Options")
+        self.l = QVBoxLayout()
+        groupbox.setLayout(self.l)
 
         self.urlsfromclip = QCheckBox('Take URLs from Clipboard?',self)
         self.urlsfromclip.setToolTip('Prefill URLs from valid URLs in Clipboard when Adding New.')
@@ -359,7 +374,9 @@ class BasicTab(QWidget):
         self.adddialogstaysontop.setChecked(prefs['adddialogstaysontop'])
         self.l.addWidget(self.adddialogstaysontop)
 
-        self.l.addSpacing(10)        
+        misc_gb = groupbox = QGroupBox("Misc Options")
+        self.l = QVBoxLayout()
+        groupbox.setLayout(self.l)
 
         # this is a cheat to make it easier for users to realize there's a new include_images features.
         self.includeimages = QCheckBox("Include images in EPUBs?",self)
@@ -367,43 +384,43 @@ class BasicTab(QWidget):
         self.includeimages.setChecked(prefs['includeimages'])
         self.l.addWidget(self.includeimages)
 
-        self.lookforurlinhtml = QCheckBox("Search EPUB text for Story URL?",self)
-        self.lookforurlinhtml.setToolTip("Look for first valid story URL inside EPUB text if not found in metadata.\nSomewhat risky, could find wrong URL depending on EPUB content.\nAlso finds and corrects bad ffnet URLs from ficsaver.com files.")
-        self.lookforurlinhtml.setChecked(prefs['lookforurlinhtml'])
-        self.l.addWidget(self.lookforurlinhtml)
-
-        self.checkforseriesurlid = QCheckBox("Check for existing Series Anthology books?",self)
-        self.checkforseriesurlid.setToolTip("Check for existings Series Anthology books using each new story's series URL before downloading.\nOffer to skip downloading if a Series Anthology is found.")
-        self.checkforseriesurlid.setChecked(prefs['checkforseriesurlid'])
-        self.l.addWidget(self.checkforseriesurlid)
-
         self.injectseries = QCheckBox("Inject calibre Series when none found?",self)
         self.injectseries.setToolTip("If no series is found, inject the calibre series (if there is one) so it appears on the FFDL title page(not cover).")
         self.injectseries.setChecked(prefs['injectseries'])
         self.l.addWidget(self.injectseries)
 
-        self.l.addSpacing(10)        
+        rej_gb = groupbox = QGroupBox("Reject List")
+        self.l = QVBoxLayout()
+        groupbox.setLayout(self.l)
 
-        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.l.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.l.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.addWidget(self.reject_reasons)
+
+        topl.addWidget(defs_gb)
+
+        horz = QHBoxLayout()
+        topl.addLayout(horz)
+        horz.addWidget(cali_gb)
+        horz.addWidget(rej_gb)
         
-        self.l.addLayout(horz)
-        
-        self.l.insertStretch(-1)
+        horz = QHBoxLayout()
+        topl.addLayout(horz)
+        horz.addWidget(gui_gb)
+        horz.addWidget(misc_gb)
+
+        topl.insertStretch(-1)
         
     def set_collisions(self):
         prev=self.collision.currentText()

calibre-plugin/dialogs.py

@@ -17,7 +17,8 @@ from PyQt4 import QtGui
 from PyQt4.Qt import (QDialog, QTableWidget, QVBoxLayout, QHBoxLayout, QGridLayout,
                       QPushButton, QString, QLabel, QCheckBox, QIcon, QLineEdit,
                       QComboBox, QVariant, QProgressDialog, QTimer, QDialogButtonBox,
-                      QPixmap, Qt, QAbstractItemView, SIGNAL, QTextEdit, pyqtSignal)
+                      QPixmap, Qt, QAbstractItemView, SIGNAL, QTextEdit, pyqtSignal,
+                      QGroupBox, QFrame)
 
 from calibre.gui2.dialogs.confirm_delete import confirm
 from calibre.gui2.complete2 import EditWithComplete
@@ -48,18 +49,21 @@ anthology_collision_order=[UPDATE,
                            UPDATEALWAYS,
                            OVERWRITEALWAYS]
 
+gpstyle='QGroupBox {border:0; padding-top:10px; padding-bottom:0px; margin-bottom:0px;}' #  background-color:red;
+
 class RejectUrlEntry:
 
     matchpat=re.compile(r"^(?P<url>[^,]+)(,(?P<fullnote>(((?P<title>.+) by (?P<auth>.+?)( - (?P<note>.+))?)|.*)))?$")
     
     def __init__(self,url_or_line,note=None,title=None,auth=None,
-                 addreasontext=None,fromline=False):
-        
+                 addreasontext=None,fromline=False,book_id=None):
+
         self.url=url_or_line
         self.note=note
         self.title=title
         self.auth=auth
         self.valid=False
+        self.book_id=book_id
 
         if fromline:
             mc = re.match(self.matchpat,url_or_line)
@@ -199,6 +203,24 @@ class AddNewDialog(SizePersistedDialog):
         # elements to show again when doing *update* merge
         self.mergeupdateshow = []
 
+        self.groupbox = QGroupBox("Show Download Options")
+        self.groupbox.setCheckable(True)
+        self.groupbox.setChecked(False)
+        self.groupbox.setFlat(True)
+        print("style:%s"%self.groupbox.styleSheet())
+        self.groupbox.setStyleSheet(gpstyle);
+
+        self.gbf = QFrame()
+        self.gbl = QVBoxLayout()
+        self.gbl.addWidget(self.gbf)
+        self.groupbox.setLayout(self.gbl)
+        self.gbl = QVBoxLayout()
+        self.gbf.setLayout(self.gbl)
+        self.l.addWidget(self.groupbox)
+
+        self.gbf.setVisible(False)
+        self.groupbox.toggled.connect(self.gbf.setVisible)
+        
         horz = QHBoxLayout()
         label = QLabel('Output &Format:')
         self.mergehide.append(label)
@@ -214,7 +236,7 @@ class AddNewDialog(SizePersistedDialog):
         horz.addWidget(label)
         label.setBuddy(self.fileform)
         horz.addWidget(self.fileform)
-        self.l.addLayout(horz)
+        self.gbl.addLayout(horz)
         self.mergehide.append(self.fileform)
 
         horz = QHBoxLayout()
@@ -229,7 +251,7 @@ class AddNewDialog(SizePersistedDialog):
             self.collision.setCurrentIndex(i)
         self.collisionlabel.setBuddy(self.collision)
         horz.addWidget(self.collision)
-        self.l.addLayout(horz)
+        self.gbl.addLayout(horz)
         self.mergehide.append(self.collisionlabel)
         self.mergehide.append(self.collision)
         self.mergeupdateshow.append(self.collisionlabel)
@@ -249,7 +271,7 @@ class AddNewDialog(SizePersistedDialog):
         horz.addWidget(self.updateepubcover)
         self.mergehide.append(self.updateepubcover)
         
-        self.l.addLayout(horz)
+        self.gbl.addLayout(horz)
 
         self.button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
         self.button_box.accepted.connect(self.ok_clicked)
@@ -258,8 +280,8 @@ class AddNewDialog(SizePersistedDialog):
 
     # invoke the 
     def ok_clicked(self):
+        self.dialog_closing(None) # save persistent size.
         self.hide()
-        print("ok_clicked called")
         self.go_signal.emit( self.get_ffdl_options(),
                              self.get_urlstext(),
                              self.merge,
@@ -287,6 +309,8 @@ class AddNewDialog(SizePersistedDialog):
         self.newmerge = newmerge
         self.extraoptions = extraoptions
         self.extrapayload = extrapayload
+
+        self.groupbox.setVisible(not(self.merge and self.newmerge))
         
         if self.merge:
             self.toplabel.setText('Story URL(s) for anthology, one per line:')
@@ -624,8 +648,25 @@ class UpdateExistingDialog(SizePersistedDialog):
 
         options_layout = QHBoxLayout()
 
+        groupbox = QGroupBox("Show Download Options")
+        groupbox.setCheckable(True)
+        groupbox.setChecked(False)
+        groupbox.setFlat(True)
+        groupbox.setStyleSheet(gpstyle)
+
+        gbf = QFrame()
+        gbl = QVBoxLayout()
+        gbl.addWidget(gbf)
+        groupbox.setLayout(gbl)
+        gbl = QHBoxLayout()
+        gbf.setLayout(gbl)
+        options_layout.addWidget(groupbox)
+
+        gbf.setVisible(False)
+        groupbox.toggled.connect(gbf.setVisible)
+        
         label = QLabel('Output &Format:')
-        options_layout.addWidget(label)
+        gbl.addWidget(label)
         self.fileform = QComboBox(self)
         self.fileform.addItem('epub')
         self.fileform.addItem('mobi')
@@ -635,10 +676,10 @@ class UpdateExistingDialog(SizePersistedDialog):
         self.fileform.setToolTip('Choose output format to create.  May set default from plugin configuration.')
         self.fileform.activated.connect(self.set_collisions)
         label.setBuddy(self.fileform)
-        options_layout.addWidget(self.fileform)
+        gbl.addWidget(self.fileform)
         
         label = QLabel('Update Mode:')
-        options_layout.addWidget(label)
+        gbl.addWidget(label)
         self.collision = QComboBox(self)
         self.collision.setToolTip("What sort of update to perform.  May set default from plugin configuration.")
         # add collision options
@@ -647,17 +688,19 @@ class UpdateExistingDialog(SizePersistedDialog):
         if i > -1:
             self.collision.setCurrentIndex(i)
         label.setBuddy(self.collision)
-        options_layout.addWidget(self.collision)
+        gbl.addWidget(self.collision)
 
         self.updatemeta = QCheckBox('Update Calibre &Metadata?',self)
         self.updatemeta.setToolTip("Update metadata for existing stories in Calibre from web site?\n(Columns set to 'New Only' in the column tabs will only be set for new books.)")
         self.updatemeta.setChecked(prefs['updatemeta'])
-        options_layout.addWidget(self.updatemeta)
+        gbl.addWidget(self.updatemeta)
                 
         self.updateepubcover = QCheckBox('Update EPUB Cover?',self)
         self.updateepubcover.setToolTip('Update book cover image from site or defaults (if found) <i>inside</i> the EPUB when EPUB is updated.')
         self.updateepubcover.setChecked(prefs['updateepubcover'])
-        options_layout.addWidget(self.updateepubcover)
+        gbl.addWidget(self.updateepubcover)
+
+
         
         button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
         button_box.accepted.connect(self.accept)
@@ -828,7 +871,9 @@ class RejectListTableWidget(QTableWidget):
 
     def populate_table_row(self, row, rej):
 
-        self.setItem(row, 0, ReadOnlyTableWidgetItem(rej.url))
+        url_cell = ReadOnlyTableWidgetItem(rej.url)
+        url_cell.setData(Qt.UserRole, QVariant(rej.book_id))
+        self.setItem(row, 0, url_cell)
         self.setItem(row, 1, ReadOnlyTableWidgetItem(rej.title))
         self.setItem(row, 2, ReadOnlyTableWidgetItem(rej.auth))
         
@@ -950,10 +995,19 @@ class RejectListDialog(SizePersistedDialog):
         rejectrows = []
         for row in range(self.rejects_table.rowCount()):
             url = unicode(self.rejects_table.item(row, 0).text()).strip()
+            book_id = self.rejects_table.item(row, 0).data(Qt.UserRole).toPyObject()
             title = unicode(self.rejects_table.item(row, 1).text()).strip()
             auth = unicode(self.rejects_table.item(row, 2).text()).strip()
             note = unicode(self.rejects_table.cellWidget(row, 3).currentText()).strip()
-            rejectrows.append(RejectUrlEntry(url,note,title,auth,self.get_reason_text()))
+            rejectrows.append(RejectUrlEntry(url,note,title,auth,self.get_reason_text(),book_id=book_id))
+        return rejectrows
+
+    def get_reject_list_ids(self):
+        rejectrows = []
+        for row in range(self.rejects_table.rowCount()):
+            book_id = self.rejects_table.item(row, 0).data(Qt.UserRole).toPyObject()
+            if book_id:
+                rejectrows.append(book_id)
         return rejectrows
 
     def get_reason_text(self):

calibre-plugin/ffdl_plugin.py

@@ -140,7 +140,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             file_path = os.path.join(calibre_config_dir,
                                      *("plugins/fanfictiondownloader_macmenuhack.txt".split('/')))
             file_path = os.path.abspath(file_path)
-            print("macmenuhack file_path:%s"%file_path)
+            print("Plugin %s macmenuhack file_path:%s"%(self.name,file_path))
             self.macmenuhack = os.access(file_path, os.F_OK)
             return self.macmenuhack
 
@@ -408,12 +408,12 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             
     def reject_list_urls_finish(self, book_list):
 
-        # construct reject list of tuples:
-        # (calibre_id, url, "title, authors", old reject note).
+        # construct reject list of objects
         reject_list = [ RejectUrlEntry(x['url'],
                                        x['oldrejnote'],
                                        x['title'],
-                                       ', '.join(x['author']))
+                                       ', '.join(x['author']),
+                                       book_id=x['calibre_id'])
                         for x in book_list if x['good'] ]
         if reject_list:
             d = RejectListDialog(self.gui,reject_list,
@@ -426,7 +426,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             rejecturllist.add(d.get_reject_list())
 
             if d.get_deletebooks():
-                self.gui.iactions['Remove Books'].delete_books()
+                self.gui.iactions['Remove Books'].do_library_delete(d.get_reject_list_ids())
             
         else:
             message="<p>Rejecting FFDL URLs: None of the books selected have FanFiction URLs.</p><p>Proceed to Remove?</p>"
@@ -661,6 +661,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
 
         url = book['url']
         print("url:%s"%url)
+        mi = None
 
         if not merge: # skip reject list when merging.
             if rejecturllist.check(url):
@@ -845,6 +846,42 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                     book['icon'] = 'edit-redo.png'
                     book['status'] = 'Update'
     
+                if book_id and mi: # book_id and mi only set if matched by title/author.
+                    liburl = self.get_story_url(db,book_id)
+                    if book['url'] != liburl:
+                        if collision in (OVERWRITE,OVERWRITEALWAYS):
+                            updat="overwrit"
+                        else:
+                            updat="updat"
+                        if not question_dialog(self.gui, 'Change Story URL?',
+                                               '<h3>Change Story URL?</h3>'+
+                                               '<p><b>%s</b> by <b>%s</b> is already in your library with a different source URL:</p>'%
+                                                   (mi.title,', '.join(mi.author))+
+                                               '<p>In library: <a href="%(liburl)s">%(liburl)s</a></p><p>New URL: <a href="%(newurl)s">%(newurl)s</a></p>'%
+                                                   {'liburl':liburl,'newurl':book['url']}+
+                                               "<p>Click '<b>Yes</b>' to %se book with new URL.</p>"%updat+
+                                               "<p>Click '<b>No</b>' to skip %sing this book.</p>"%updat,
+                                               show_copy_button=False):
+                            if question_dialog(self.gui, 'Download as New Book?',
+                                               '<h3>Download as New Book?</h3>'+
+                                               '<p><b>%s</b> by <b>%s</b> is already in your library with a different source URL.</p>'%
+                                               (mi.title,', '.join(mi.author))+
+                                               '<p>You chose not to update the existing book.  Do you want to add a new book for this URL?</p>'+
+                                               '<p>New URL: <a href="%(newurl)s">%(newurl)s</a></p>'%
+                                               {'newurl':book['url']}+
+                                               "<p>Click '<b>Yes</b>' to a new book with new URL.</p>"+
+                                               "<p>Click '<b>No</b>' to skip URL.</p>",
+                                               show_copy_button=False):
+                                book_id = None
+                                mi = None
+                                book['calibre_id'] = None
+                            else:
+                                book['comment'] = "Update declined by user due to differing story URL(%s)"%liburl
+                                book['good']=False
+                                book['icon']='rotate-right.png'
+                                book['status'] = 'Different URL'
+                                return
+        
             if book_id != None and collision != ADDNEW:
                 if collision in (CALIBREONLY):
                     book['comment'] = 'Metadata collected.'
@@ -889,7 +926,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                     db.copy_format_to(book_id,fileform,tmp,index_is_id=True)
                     print("existing epub tmp:"+tmp.name)
                     book['epub_for_update'] = tmp.name
-    
+
             if book_id != None and prefs['injectseries']:
                 mi = db.get_metadata(book_id,index_is_id=True)
                 if not book['series'] and mi.series != None:
@@ -1159,7 +1196,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         if 'mergebook' in options:
             existingbook = options['mergebook']
         #print("existingbook:\n%s"%existingbook)
-        mergebook = self.merge_meta_books(existingbook,good_list)
+        mergebook = self.merge_meta_books(existingbook,good_list,options['fileform'])
 
         if 'mergebook' in options:
             mergebook['calibre_id'] = options['mergebook']['calibre_id']
@@ -1281,16 +1318,10 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             existingepub = db.format(book_id,'EPUB',index_is_id=True, as_file=True)
             epubmi = get_metadata(existingepub,'EPUB')
             if epubmi.cover_data[1] is not None:
-                db.set_cover(book_id, epubmi.cover_data[1])
-
-        # set author link if found.  All current adapters have authorUrl, except anonymous on AO3.
-        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)
+                try:
+                    db.set_cover(book_id, epubmi.cover_data[1])
+                except:
+                    print("Failed to set_cover, skipping")
 
         # implement 'newonly' flags here by setting to the current
         # value again.
@@ -1369,7 +1400,11 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
 
                     if flag == 'r' or book['added']: # flag 'n' isn't actually needed--*always* set if configured and new book.
                         if coldef['datatype'] in ('int','float'): # for favs, etc--site specific metadata.
-                            val = unicode(book['all_metadata'][meta]).replace(",","")
+                            if 'anthology_meta_list' in book and meta in book['anthology_meta_list']:
+                                # re-split list, strip commas, convert to floats, sum up.
+                                val = sum([ float(x.replace(",","")) for x in book['all_metadata'][meta].split(", ") ])
+                            else:
+                                val = unicode(book['all_metadata'][meta]).replace(",","")
                         else:
                             val = book['all_metadata'][meta]
                         db.set_custom(book_id, val, label=label, commit=False)
@@ -1390,6 +1425,16 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                             
                         db.set_custom(book_id, ", ".join(vallist), label=label, commit=False)
 
+        # set author link if found.  All current adapters have authorUrl, except anonymous on AO3.
+        # Moved down so author's already in the DB.
+        if 'authorUrl' in book['all_metadata']:
+            authurls = book['all_metadata']['authorUrl'].split(", ")
+            for i, auth in enumerate(book['author']):
+                #print("===Update author url for %s to %s"%(auth,authurls[i]))
+                autid=db.get_author_id(auth)
+                db.set_link_field_for_author(autid, unicode(authurls[i]),
+                                             commit=False, notify=False)
+
         db.commit()
 
         if 'Generate Cover' in self.gui.iactions and (book['added'] or not prefs['gcnewonly']):
@@ -1533,7 +1578,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
     def convert_url_to_book(self, url):
         book = self.make_book()
         # look here for [\d,\d] at end of url, and remove?
-        mc = re.match(r"^(?P<url>.*?)(?:\[(?P<begin>\d+)?(?P<comma>,)?(?P<end>\d+)?\])?$",url)
+        mc = re.match(r"^(?P<url>.*?)(?:\[(?P<begin>\d+)?(?P<comma>[,-])?(?P<end>\d+)?\])?$",url)
         #print("url:(%s) begin:(%s) end:(%s)"%(mc.group('url'),mc.group('begin'),mc.group('end')))
         url = mc.group('url')
         book['begin'] = mc.group('begin')
@@ -1623,7 +1668,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                     # identifiers have :->| in uri.
                     # print("uri from ident uri:%s"%identifiers['uri'].replace('|',':'))
                     return identifiers['uri'].replace('|',':')
-            elif path.lower().endswith('.epub'):
+            elif path and path.lower().endswith('.epub'):
                 existingepub = path
                 
             ## only epub has URL in it--at least where I can easily find it.
@@ -1642,12 +1687,13 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
     def is_good_downloader_url(self,url):
         return adapters.getNormalStoryURL(url)
 
-    def merge_meta_books(self,existingbook,book_list):
+    def merge_meta_books(self,existingbook,book_list,fileform):
         book = self.make_book()
         book['author'] = []
         book['tags'] = []
         book['url'] = ''
         book['all_metadata'] = {}
+        book['anthology_meta_list'] = {}
         book['comment'] = ''
         book['added'] = True
         book['good'] = True
@@ -1714,12 +1760,16 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                         book['all_metadata'][k]=book['all_metadata'][k]+"\n\n"+v
                     else:
                         book['all_metadata'][k]=book['all_metadata'][k]+", "+v
+                        # flag psuedo list element.  Used so numeric
+                        # cust cols can convert back to numbers and
+                        # add.
+                        book['anthology_meta_list'][k]=True
     
         if existingbook:
             book['title'] = deftitle = existingbook['title']
             book['comments'] = existingbook['comments']
         else:
-            book['title'] = deftitle = book_list[0]['title']+" Anthology"
+            book['title'] = deftitle = book_list[0]['title']
             book['comments'] = "Anthology containing:\n" + \
                 "\n".join([ "%s by %s"%(b['title'],', '.join(b['author'])) for b in book_list ])
             # book['all_metadata']['description']
@@ -1727,12 +1777,22 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
             # if all same series, use series for name.  But only if all and not previous named
             if len(serieslist) == len(book_list):
                 series = serieslist[0]
-                book['title'] = series+" Anthology"
+                book['title'] = series
                 for sr in serieslist:
                     if series != sr:
                         book['title'] = deftitle;
                         break
             
+            configuration = get_ffdl_config(book['url'],fileform)
+            print("anthology_title_pattern:%s"%configuration.getConfig('anthology_title_pattern'))
+            if configuration.getConfig('anthology_title_pattern'):
+                tmplt = Template(configuration.getConfig('anthology_title_pattern'))
+                book['title'] = tmplt.safe_substitute({'title':book['title']}).encode('utf8')
+            else:
+                # No setting, do fall back default.  Shouldn't happen,
+                # should always have a version in defaults.
+                book['title'] = book['title']+" Anthology"
+        
         book['all_metadata']['title'] = book['title'] # because custom columns are set from all_metadata
         book['all_metadata']['author'] = ", ".join(book['author'])
         book['author_sort']=book['author']
@@ -1741,6 +1801,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                 book['tags'].remove(v)
         book['tags'].append('Anthology')
         book['all_metadata']['anthology'] = "true"
+        
         return book
 
 def split_text_to_urls(urls):

calibre-plugin/prefs.py

@@ -61,6 +61,13 @@ default_prefs['allow_custcol_from_ini'] = True
 
 default_prefs['std_cols_newonly'] = {}
 
+# This is where all preferences for this plugin *were* stored
+# Remember that this name (i.e. plugins/fanfictiondownloader_plugin) is also
+# in a global namespace, so make it as unique as possible.
+# You should always prefix your config file name with plugins/,
+# so as to ensure you dont accidentally clobber a calibre config file
+old_prefs = JSONConfig('plugins/fanfictiondownloader_plugin')
+
 def set_library_config(library_config,db):
     db.prefs.set_namespaced(PREFS_NAMESPACE,
                             PREFS_KEY_SETTINGS,
@@ -74,7 +81,7 @@ def get_library_config(db):
     if library_id in old_prefs:
         #print("get prefs from old_prefs")
         library_config = old_prefs[library_id]
-        set_library_config(library_config)
+        set_library_config(library_config,db)
         old_prefs["migrated to library db %s"%library_id] = old_prefs[library_id]
         del old_prefs[library_id]
 
@@ -84,13 +91,6 @@ def get_library_config(db):
                                                  copy.deepcopy(default_prefs))
     return library_config
 
-# This is where all preferences for this plugin *were* stored
-# Remember that this name (i.e. plugins/fanfictiondownloader_plugin) is also
-# in a global namespace, so make it as unique as possible.
-# You should always prefix your config file name with plugins/,
-# so as to ensure you dont accidentally clobber a calibre config file
-old_prefs = JSONConfig('plugins/fanfictiondownloader_plugin')
-
 # fake out so I don't have to change the prefs calls anywhere.  The
 # Java programmer in me is offended by op-overloading, but it's very
 # tidy.

defaults.ini

@@ -1,4 +1,4 @@
-# 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.
@@ -169,6 +169,8 @@ extratags: FanFiction
 ## *Five* part lines.  Effect only when trailing conditional key=>regexp matches
 ## metakey[,metakey]=>pattern=>replacement[&&conditionalkey=>regexp]
 ## Note that if metakey == conditionalkey the conditional is ignored.
+## You can use \s in the replacement to add explicit spaces.  (The config parser
+## tends to discard trailing spaces.)
 #replace_metadata:
 # genre,category=>Sci-Fi=>SF
 # Puella Magi Madoka Magica.* => Madoka
@@ -189,6 +191,10 @@ extratags: FanFiction
 ## summary.
 keep_summary_html:true
 
+## If set true, any style attributes on tags in the story HTML will be
+## kept.  Useful for keeping extra colors & formatting from original.
+#keep_style_attr: false
+
 ## Don't like the numbers at the start of chapter titles on some
 ## sites?  You can use strip_chapter_numbers to strip them off.  Just
 ## want to make them all look the same?  Strip them off, then add them
@@ -273,7 +279,7 @@ output_css:
 
 [txt]
 ## Add URLs since there aren't links.
-titlepage_entries: series,seriesUrl,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,storyUrl, authorUrl, description
+titlepage_entries: series,seriesUrl,category,genre,language,characters,ships,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,numWords,site,storyUrl, authorUrl, description
 
 ## Width to word wrap text output.  0 indicates no wrapping.
 wrap_width: 78
@@ -507,6 +513,15 @@ extraships:Severus Snape/Hermione Granger
 #username:YourName
 #password:yourpassword
 
+[asr3.slashzone.org]
+## Site dedicated to these categories/characters/ships
+extracategories:The Sentinel
+
+## 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
+
 [bloodties-fans.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Blood Ties
@@ -571,6 +586,11 @@ extraships:Spike/Buffy
 #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
+
 [dramione.org]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
@@ -602,7 +622,7 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 ## composite metadata entries.  dramione.org, for example, adds
 ## 'cliches' and then defines as the composite of hermiones,dracos in
 ## include_in_cliches.
-extra_valid_entries:themes,hermiones,dracos,timeline,cliches
+extra_valid_entries:themes,hermiones,dracos,timeline,cliches,read,reviews
 include_in_cliches:hermiones,dracos
 
 ## For another example, you could, by uncommenting this line, include
@@ -647,6 +667,11 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
 
+## 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
+
 ## 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
@@ -654,11 +679,22 @@ extracategories:Harry Potter
 #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.
+[fanfic.potterheadsanonymous.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
+## 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
 
+## 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
+
 [fanfiction.portkey.org]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
@@ -702,6 +738,10 @@ extracharacters:Hermione Granger
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+## Extra metadata that this adapter knows about.  See [dramione.org]
+## for examples of how to use them.
+extra_valid_entries:read,reviews
+
 [hlfiction.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:Highlander
@@ -762,6 +802,8 @@ extracategories:West Wing
 ## Site dedicated to these categories/characters/ships
 extracategories:NCIS
 
+[netraptor.org]
+
 [nfacommunity.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:NCIS
@@ -844,6 +886,22 @@ extracategories:Supernatural
 extracharacters:Sam,Dean
 extraships:Sam/Dean
 
+[scarhead.net]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
+## 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
+
 [sg1-heliopolis.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
@@ -918,6 +976,15 @@ extracategories:Harry Potter
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+[tokra.fandomnet.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Stargate: SG-1
+
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
 [www.adastrafanfic.com]
 ## Site dedicated to these categories/characters/ships
 extracategories:Star Trek
@@ -1148,6 +1215,11 @@ cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
 ## Site dedicated to these categories/characters/ships
 extracategories:NCIS
 
+[www.nickandgreg.net]
+## Site dedicated to these categories/characters/ships
+extracategories:CSI
+extraships:Nick Stokes/Greg Sanders
+
 [www.phoenixsong.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
@@ -1160,6 +1232,12 @@ extraships:Harry Potter/Ginny Weasley
 #username:YourName
 #password:yourpassword
 
+## phoenixsong.net, oddly, can have high rated chapters (login
+## required) in the middle of a lower rated story.  Use this to force
+## FFDL to always login to phoenixsong.net so those stories download
+## correctly.
+#force_login:true
+
 [www.potionsandsnitches.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
@@ -1210,6 +1288,17 @@ extracharacters:Kurt Hummel,Blaine Anderson
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[www.simplyundeniable.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
+## 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.sinful-desire.org]
 ## Site dedicated to these categories/characters/ships
 extracategories:Supernatural
@@ -1356,3 +1445,47 @@ extracategories:Stargate: Atlantis
 ## extratags params in all other sections.  Only commandline options
 ## beat overrides.
 #extratags:fanficdownloader
+
+
+[teststory:defaults]
+valid_entries:title,author_list,authorId_list,authorUrl_list,storyUrl,
+ datePublished,dateUpdated,numWords,status,language,series,seriesUrl,
+ rating,category_list,genre_list,warnings_list,characters_list
+
+# {{storyId}} is a special case--it's the only one that works.
+title:Test Story Title {{storyId}}
+author_list:Test Author aa
+authorId_list:1
+authorUrl_list:http://test1.com?authid=1
+storyUrl:http://test1.com?sid={{storyId}}
+datePublished:1975-03-15
+dateUpdated:1975-04-15
+numWords:123,456
+status:In-Progress
+language:English
+
+chaptertitles:Prologue
+
+## Add additional sections with different numbers to get different
+## parameters for different story urls.
+## test1.com?sid=1000
+[teststory:1000]
+# note the leading commas when doing add_to_ with valid_entries and *_list
+add_to_valid_entries:,favs
+title:Testing New Feature {{storyId}}
+author_list:Bob Smith
+authorId_list:45
+authorUrl_list:http://test1.com?authid=45
+datePublished:2013-03-15
+dateUpdated:2013-04-15
+numWords:1456
+favs:56
+series:The Great Test [4]
+seriesUrl:http://test1.com?seriesid=1
+rating:Tweenie
+category_list:Harry Potter,Furbie,Crossover,Puella Magi Madoka Magica/魔法少女まどか★マギカ,Magical Girl Lyrical Nanoha
+genre_list:Fantasy,Comedy,Sci-Fi,Noir
+warnings_list:Swearing,Violence
+characters_list:Bob Smith,George Johnson,Fred Smythe
+
+chaptertitles:Prologue,Chapter 1\, Xenos on Cinnabar,Chapter 2\, Sinmay on Kintikin,3. Chapter 3

downloader.py

@@ -33,16 +33,24 @@ if sys.version_info >= (2, 7):
     rootlogger.addHandler(loghandler)
 
 try:
-    from fanficdownloader import adapters,writers,exceptions
-    from fanficdownloader.configurable import Configuration
-    from fanficdownloader.epubutils import get_dcsource_chaptercount, get_update_data
-    from fanficdownloader.geturls import get_urls_from_page
+    from calibre.constants import numeric_version as calibre_version
+    is_calibre = True
 except:
+    is_calibre = False
+
+# using try/except directly was masking errors during development.
+if is_calibre:
     # running under calibre
     from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader import adapters,writers,exceptions
     from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.configurable import Configuration
     from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.epubutils import get_dcsource_chaptercount, get_update_data
     from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.geturls import get_urls_from_page
+else:
+    from fanficdownloader import adapters,writers,exceptions
+    from fanficdownloader.configurable import Configuration
+    from fanficdownloader.epubutils import get_dcsource_chaptercount, get_update_data
+    from fanficdownloader.geturls import get_urls_from_page
+    
 
 if sys.version_info < (2, 5):
     print "This program requires Python 2.5 or newer."
@@ -94,6 +102,9 @@ def main(argv,
    parser.add_option("-l", "--list",
                      action="store_true", dest="list",
                      help="Get list of valid story URLs from page given.",)
+   parser.add_option("-n", "--normalize-list",
+                     action="store_true", dest="normalize",default=False,
+                     help="Get list of valid story URLs from page given, but normalized to standard forms.",)
    parser.add_option("-d", "--debug",
                      action="store_true", dest="debug",
                      help="Show debug output while downloading.",)
@@ -169,8 +180,8 @@ def main(argv,
            (var,val) = opt.split('=')
            configuration.set("overrides",var,val)
 
-   if options.list:
-       retlist = get_urls_from_page(args[0], configuration)
+   if options.list or options.normalize:
+       retlist = get_urls_from_page(args[0], configuration, normalize=options.normalize)
        print "\n".join(retlist)
                
        return

fanficdownloader/adapters/__init__.py

@@ -71,7 +71,6 @@ import adapter_thehexfilesnet
 import adapter_dokugacom
 import adapter_iketernalnet
 import adapter_onedirectionfanfictioncom
-import adapter_prisonbreakficnet
 import adapter_storiesofardacom
 import adapter_samdeanarchivenu
 import adapter_destinysgatewaycom
@@ -88,7 +87,6 @@ import adapter_pretendercentrecom
 import adapter_darksolaceorg
 import adapter_finestoriescom
 import adapter_hpfanficarchivecom
-import adapter_svufictioncom
 import adapter_twilightarchivescom
 import adapter_wizardtalesnet
 import adapter_nhamagicalworldsus
@@ -103,7 +101,6 @@ import adapter_merlinficdtwinscouk
 import adapter_thehookupzonenet
 import adapter_bloodtiesfancom
 import adapter_indeathnet
-import adapter_jlaunlimitedcom
 import adapter_qafficcom
 import adapter_efpfanficnet
 import adapter_potterficscom
@@ -115,6 +112,13 @@ import adapter_imagineeficcom
 import adapter_buffynfaithnet
 import adapter_psychficcom
 import adapter_hennethannunnet
+import adapter_tokrafandomnetcom
+import adapter_netraptororg
+import adapter_asr3slashzoneorg
+import adapter_nickandgregnet
+import adapter_potterheadsanonymouscom
+import adapter_simplyundeniablecom
+import adapter_scarheadnet
 
 ## This bit of complexity allows adapters to be added by just adding
 ## importing.  It eliminates the long if/else clauses we used to need

fanficdownloader/adapters/adapter_archiveofourownorg.py

@@ -1,4 +1,4 @@
-# -*- coding: utf-8 -*-
+#  -*- coding: utf-8 -*-
 
 # Copyright 2011 Fanficdownloader team
 #
@@ -292,7 +292,7 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
             a = metasoup.find('dd',{'class':"series"})
             b = a.find('a', href=re.compile(r"/series/\d+"))
             series_name = b.string
-            series_url = 'http://'+self.host+'/fanfic/'+b['href']
+            series_url = 'http://'+self.host+b['href']
             series_index = int(a.text.split(' ')[1])
             self.setSeries(series_name, series_index)
             self.story.setMetadata('seriesUrl',series_url)

fanficdownloader/adapters/adapter_asr3slashzoneorg.py

@@ -0,0 +1,225 @@
+# -*- 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 Asr3SlashzoneOrgAdapter
+
+class Asr3SlashzoneOrgAdapter(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() + '/archive/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','asr3')
+
+        # 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 'asr3.slashzone.org'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/archive/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/archive/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=3"
+        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
+
+        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(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+'/archive/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # Rating
+        rate = stripHTML(soup.find('div',{'id':'pagetitle'}))
+        rate = rate[rate.rindex('[')+1:rate.rindex(']')]
+        self.story.setMetadata('rating', rate)
+
+        # 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+'/archive/'+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.
+
+        metadiv = soup.find('div',{'class':'content'})
+        smalldiv = metadiv.find('div',{'class':'small'})
+
+        categorys = smalldiv.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+        for category in categorys:
+            self.story.addToList('category',category.string)
+        
+        chars = smalldiv.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+        for char in chars:
+            self.story.addToList('characters',char.string)
+
+        ships = smalldiv.parent.findAll('a',href=re.compile(r'browse\.php\?type=class&type_id=2&classid=1'))
+        for ship in ships:
+            self.story.addToList('ships',ship.string)
+
+        metatext = stripHTML(smalldiv)
+
+        if 'Completed: Yes' in metatext:
+            self.story.setMetadata('status', 'Completed')
+        else:
+            self.story.setMetadata('status', 'In-Progress')
+
+        wordstart=metatext.rindex('Word count:')+12
+        words = metatext[wordstart:metatext.index(' ',wordstart)]
+        self.story.setMetadata('numWords', words)
+
+        datesdiv = soup.find('div',{'class':'bottom'})
+        dates = stripHTML(datesdiv).split()
+        # Published: 04/26/2011 Updated: 03/06/2013
+        self.story.setMetadata('datePublished', makeDate(dates[1], self.dateformat))
+        self.story.setMetadata('dateUpdated', makeDate(dates[3], 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+'/archive/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            # can't use ^viewstory...$ in case of higher rated stories with javascript href.
+            storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
+            i=1
+            for a in storyas:
+                # skip 'report this' and 'TOC' links
+                if 'contact.php' not in a['href'] and 'index' not in a['href']:
+                    if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                        self.setSeries(series_name, i)
+                        self.story.setMetadata('seriesUrl',series_url)
+                        break
+                    i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+        # remove 'small' leaving only summary.
+        smalldiv.extract()
+        self.setDescription(url,metadiv)
+        
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logger.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulSoup(self._fetchUrl(url))
+        
+        div = soup.find('div', {'id' : 'story'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_bloodtiesfancom.py

@@ -211,7 +211,7 @@ class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX
         # 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('authorUrl','http://'+self.host+'/fiction/'+a['href'])
         self.story.setMetadata('author',a.string)
 
         # Find the chapters:

fanficdownloader/adapters/adapter_castlefansorg.py

@@ -184,7 +184,7 @@ class CastleFansOrgAdapter(BaseSiteAdapter): # XXX
         # 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('authorUrl','http://'+self.host+'/fanfic/'+a['href'])
         self.story.setMetadata('author',a.string)
 
         # Find the chapters:

fanficdownloader/adapters/adapter_darksolaceorg.py

@@ -49,7 +49,6 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
         # 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() + '/elysian/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -59,7 +58,7 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
 
         # 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 = "%B %d, %Y"
             
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
@@ -79,7 +78,8 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
     ## Login seems to be reasonably standard across eFiction sites.
     def needToLoginCheck(self, data):
         if 'This story contains adult content not suitable for children' in data \
-                or "That password doesn't match the one in our database" in data:
+                or "That password doesn't match the one in our database" in data \
+                or "Registered Users Only" in data:
             return True
         else:
             return False
@@ -94,17 +94,16 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
             params['penname'] = self.getConfig("username")
             params['password'] = self.getConfig("password")
         params['rememberme'] = '1'
-        params['sid'] = ''
-        params['intent'] = ''
+        params['action'] = 'login'
         params['submit'] = 'Submit'
     
         loginUrl = 'http://' + self.getSiteDomain() + '/elysian/user.php'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['penname']))
     
-        d = self._fetchUrl(loginUrl, params)
+        d = self._postUrl(loginUrl, params)
     
-        if "User Account Page" not in d : #Member Account
+        if "Member Account" not in d : #User Account Page
             logger.info("Failed to login to URL %s as %s, or have no authorization to access the story" % (loginUrl, params['penname']))
             raise exceptions.FailedToLogin(url,params['penname'])
             return False
@@ -113,9 +112,19 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
 
     ## 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
+        url = self.url+'&index=1'+addurl
         logger.debug("URL: "+url)
 
         try:
@@ -128,9 +137,30 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
 
         if self.needToLoginCheck(data):
             # need to log in for this one.
-            addurl="&ageconsent=ok"
             self.performLogin(url)
-            data = self._fetchUrl(url+addurl)
+            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.")
@@ -142,33 +172,41 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
         # Now go hunting for all the meta data and the chapter list.
         
         ## Title and author
-        a = soup.find('div', {'id' : 'pagetitle'})
+        div = soup.find('div', {'id' : 'pagetitle'})
         
-        aut = a.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        aut = div.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',aut['href'].split('=')[1])
         self.story.setMetadata('authorUrl','http://'+self.host+'/elysian/'+aut['href'])
         self.story.setMetadata('author',aut.string)
         aut.extract()
-        
-        self.story.setMetadata('title',a.string[:(len(a.string)-3)])
+
+        # first a tag in pagetitle is title
+        self.story.setMetadata('title',stripHTML(div.find('a')))
 
         # Find the chapters:
-        chapters=soup.find('select', {'name' : 'chapter'})
-        if chapters != None:
-            for chapter in chapters.findAll('option'):
-                self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/elysian/viewstory.php?sid='+self.story.getMetadata('storyId')+'&chapter='+chapter['value']))
-        else:
-            self.chapterUrls.append((self.story.getMetadata('title'),url))
+        # chapters=soup.find('select', {'name' : 'chapter'})
+        # if chapters != None:
+        #     for chapter in chapters.findAll('option'):
+        #         self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/elysian/viewstory.php?sid='+self.story.getMetadata('storyId')+'&chapter='+chapter['value']))
+        # else:
+        #     self.chapterUrls.append((self.story.getMetadata('title'),url+"&chapter=1"))
 
+        for chapa in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+
+                                                       self.story.getMetadata('storyId')+'&chapter=\d+')):
+            self.chapterUrls.append((stripHTML(chapa),'http://'+self.host+'/elysian/'+chapa['href']))
+        
         self.story.setMetadata('numChapters',len(self.chapterUrls))
         
         asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
         
-        for list in asoup.findAll('div', {'class' : re.compile('listbox\s+')}):
-            a = list.find('a', href=re.compile(r'viewstory.php\?sid='))
-            if a != None:
-                if 'viewstory.php?sid='+self.story.getMetadata('storyId') in a['href']:
-                    break
+        # for metalist in asoup.findAll('div', {'class' : re.compile('listbox\s+')}):
+        #     a = metalist.find('a', href=re.compile(r'viewstory.php\?sid='))
+        #     if a != None:
+        #         if 'viewstory.php?sid='+self.story.getMetadata('storyId') in a['href']:
+        #             break
+
+        metalist = asoup.find('a', href=re.compile(r'viewstory.php\?sid='+
+                                                   self.story.getMetadata('storyId')+'($|[^\d])')).parent.parent
 
         # eFiction sites don't help us out a lot with their meta data
         # formating, so it's a little ugly.
@@ -182,7 +220,7 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
                 
 
         # <span class="label">Rated:</span> NC-17<br /> etc
-        labels = list.findAll('span', {'class' : 'classification'})
+        labels = metalist.findAll('span', {'class' : 'label'})
         for labelspan in labels:
             label = labelspan.text
             value = labelspan.nextSibling
@@ -190,7 +228,7 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
             if 'Summary' in label:
                 ## Everything until the next span class='label'
                 svalue = ""
-                while not (defaultGetattr(value,'class') == 'classification' or "Chapters: " in stripHTML(value)):
+                while not (defaultGetattr(value,'class') == 'label' or "Chapters: " in stripHTML(value)):
                     svalue += str(value)
                     value = value.nextSibling
                 self.setDescription(url,svalue)
@@ -238,7 +276,7 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
 
         try:
             # Find Series name from series URL.
-            a = list.find('a', href=re.compile(r"series.php\?seriesid=\d+"))
+            a = metalist.find('a', href=re.compile(r"series.php\?seriesid=\d+"))
             series_name = a.string
             series_url = 'http://'+self.host+'/elysian/'+a['href']
 
@@ -265,8 +303,7 @@ class DarkSolaceOrgAdapter(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))
         
         div = soup.find('div', {'id' : 'story'})
 

fanficdownloader/adapters/adapter_dramioneorg.py

@@ -237,6 +237,9 @@ class DramioneOrgAdapter(BaseSiteAdapter):
             if 'Word count' in label:
                 self.story.setMetadata('numWords', value)
 
+            if 'Read' in label:
+                self.story.setMetadata('read', value)
+
             if 'Categories' in label:
                 cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
                 for cat in cats:
@@ -282,6 +285,14 @@ class DramioneOrgAdapter(BaseSiteAdapter):
             # I find it hard to care if the series parsing fails
             pass
             
+        try:
+            self.story.setMetadata('reviews',
+                                   stripHTML(soup.find('h2',{'id':'pagetitle'}).
+                                             findAll('a', href=re.compile(r'^reviews.php'))[1]))
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
     # grab the text for an individual chapter.
     def getChapterText(self, url):
 

fanficdownloader/adapters/adapter_fanfictionnet.py

@@ -132,14 +132,28 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         ## For 1, use the second link.
         ## For 2, fetch the crossover page and pull the two categories from there.
 
-        categories = soup.findAll('a',{'class':'xcontrast_txt'})
+        categories = soup.find('div',{'id':'pre_story_links'}).findAll('a',{'class':'xcontrast_txt'})
+        #print("xcontrast_txt a:%s"%categories)
         if len(categories) > 1:
-            self.story.addToList('category',stripHTML(categories[-1]))
+            # Strangely, the ones with *two* links are the
+            # non-crossover categories.  Each is in a category itself
+            # of Book, Movie, etc.
+            self.story.addToList('category',stripHTML(categories[1]))
         elif 'Crossover' in categories[0]['href']:
             caturl = "http://%s%s"%(self.getSiteDomain(),categories[0]['href'])
             catsoup = bs.BeautifulSoup(self._fetchUrl(caturl))
             for a in catsoup.findAll('a',href=re.compile(r"^/crossovers/")):
                 self.story.addToList('category',stripHTML(a))
+            else:
+                # Fall back.  I ran across a story with a Crossver
+                # category link to a broken page once.
+                # http://www.fanfiction.net/s/2622060/1/
+                # Naruto + Harry Potter Crossover
+                logger.info("Fall back category collection")
+                for c in stripHTML(categories[0]).replace(" Crossover","").split(' + '):
+                    self.story.addToList('category',c)
+                
+                
             
         a = soup.find('a', href='http://www.fictionratings.com/')
         rating = a.string
@@ -150,7 +164,7 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
 
         # after Rating, the same bit of text containing id:123456 contains
         # Complete--if completed.
-        gui_table1i = soup.find(id="gui_table1i")
+        gui_table1i = soup.find('table',{'cellpadding':'5'})
 
         self.story.setMetadata('title', stripHTML(gui_table1i.find('b'))) # title appears to be only(or at least first) bold tag in gui_table1i
 
@@ -159,15 +173,16 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
             self.setDescription(url,stripHTML(summarydiv))
             
 
-        graydiv = gui_table1i.find('div', {'class':'xgray'})
-        for b in graydiv.findAll('button'):
-            b.extract()
-        metatext = stripHTML(graydiv).replace('Hurt/Comfort','Hurt-Comfort')
+        grayspan = gui_table1i.find('span', {'class':'xgray xcontrast_txt'})
+        # for b in grayspan.findAll('button'):
+        #     b.extract()
+        metatext = stripHTML(grayspan).replace('Hurt/Comfort','Hurt-Comfort')
         #logger.debug("metatext:(%s)"%metatext)
         metalist = metatext.split(" - ")
         #logger.debug("metalist:(%s)"%metalist)
 
         # Rated: Fiction K - English - Words: 158,078 - Published: 02-04-11
+        # Rated: Fiction T - English - Adventure/Sci-Fi - Naruto U. - Chapters: 22 - Words: 114,414 - Reviews: 395 - Favs: 779 - Follows: 835 - Updated: 03-21-13 - Published: 04-28-12 - id: 8067258 
 
         # rating is obtained above more robustly.
         if metalist[0].startswith('Rated:'):
@@ -257,12 +272,18 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
                         ## slow_down_sleep_time setting is.
         data = self._fetchUrl(url)
 
+        if "Please email this error message in full to <a href='mailto:support@fanfiction.com'>support@fanfiction.com</a>" in data:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  FanFiction.net Site Error!" % url)
+        
         # some ancient stories have body tags inside them that cause
         # soup parsing to discard the content.  For story text we
         # don't care about anything before "<div class='storytextp"
         # (there's a space after storytextp, so no close quote(')) and
         # this kills any body tags.
-        data = data[data.index("<div class='storytextp"):]
+        if "<div class='storytextp" not in data:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+        else:
+            data = data[data.index("<div class='storytextp"):]
         data.replace("<body","<notbody").replace("<BODY","<NOTBODY")
         
         soup = bs.BeautifulSoup(data)

fanficdownloader/adapters/adapter_grangerenchantedcom.py

@@ -227,6 +227,9 @@ class GrangerEnchantedCom(BaseSiteAdapter):
             if 'Word count' in label:
                 self.story.setMetadata('numWords', value)
 
+            if 'Read' in label:
+                self.story.setMetadata('read', value)
+
             if 'Categories' in label:
                 cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
                 for cat in cats:
@@ -278,7 +281,14 @@ class GrangerEnchantedCom(BaseSiteAdapter):
                         self.story.setMetadata('seriesUrl',series_url)
                         break
                     i+=1
-            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+
+        try:
+            self.story.setMetadata('reviews',
+                                   stripHTML(soup.find('div',{'id':'sort'}).
+                                             findAll('a', href=re.compile(r'^reviews.php'))[1]))
         except:
             # I find it hard to care if the series parsing fails
             pass

fanficdownloader/adapters/adapter_libraryofmoriacom.py

@@ -133,7 +133,7 @@ class LibraryOfMoriaComAdapter(BaseSiteAdapter):
         # 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('authorUrl','http://'+self.host+'/a/'+a['href'])
         self.story.setMetadata('author',a.string)
 
         # Find the chapters:

fanficdownloader/adapters/adapter_mugglenetcom.py

@@ -66,14 +66,18 @@ class MuggleNetComAdapter(BaseSiteAdapter): # XXX
             
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
-        # The site domain.  Does have www here, if it uses it.
-        return 'fanfiction.mugglenet.com' # XXX
+        # The site domain.
+        return 'fanfiction.mugglenet.com'
+
+    @classmethod
+    def getAcceptDomains(cls):
+        return ['fanfiction.mugglenet.com','fanfic.mugglenet.com']
 
     def getSiteExampleURLs(self):
         return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
-        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+        return re.escape("http://")+r"fanfic(tion)?\.mugglenet\.com"+re.escape("/viewstory.php?sid=")+r"\d+$"
 
     ## Login seems to be reasonably standard across eFiction sites.
     def needToLoginCheck(self, data):

fanficdownloader/adapters/adapter_netraptororg.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.
@@ -28,11 +28,9 @@ from .. import exceptions as exceptions
 from base_adapter import BaseSiteAdapter,  makeDate
 
 def getClass():
-    return PrisonBreakFicNetAdapter
+    return NetRaptorOrgAdapter
 
-# Class name has to be unique.  Our convention is camel case the
-# sitename with Adapter at the end.  www is skipped.
-class PrisonBreakFicNetAdapter(BaseSiteAdapter):
+class NetRaptorOrgAdapter(BaseSiteAdapter):
 
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
@@ -51,31 +49,29 @@ class PrisonBreakFicNetAdapter(BaseSiteAdapter):
         logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
         
         # normalized story URL.
-        self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        self._setURL('http://' + self.getSiteDomain() + '/fanfiction/viewstory.php?sid='+self.story.getMetadata('storyId'))
         
         # Each adapter needs to have a unique site abbreviation.
-        self.story.setMetadata('siteabbrev','pbf')
+        self.story.setMetadata('siteabbrev','netrap')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%B %d, %Y"
+        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.prisonbreakfic.net'
+        return 'netraptor.org'
 
     def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+        return "http://"+self.getSiteDomain()+"/fanfiction/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
-        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+        return re.escape("http://"+self.getSiteDomain()+"/fanfiction/viewstory.php?sid=")+r"\d+$"
 
     ## 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)
 
@@ -86,6 +82,10 @@ class PrisonBreakFicNetAdapter(BaseSiteAdapter):
                 raise exceptions.StoryDoesNotExist(self.url)
             else:
                 raise e
+
+
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
             
         # use BeautifulSoup HTML parser to make everything easier to find.
         soup = bs.BeautifulSoup(data)
@@ -94,19 +94,20 @@ class PrisonBreakFicNetAdapter(BaseSiteAdapter):
         # 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')+"$"))
+        pagetitle = soup.find('div',{'id':'pagetitle'})
+        a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
         self.story.setMetadata('title',a.string)
         
         # Find authorid and URL from... author url.
-        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        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('authorUrl','http://'+self.host+'/fanfiction/'+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.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/fanfiction/'+chapter['href']))
 
         self.story.setMetadata('numChapters',len(self.chapterUrls))
 
@@ -119,10 +120,7 @@ class PrisonBreakFicNetAdapter(BaseSiteAdapter):
                 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
@@ -145,21 +143,18 @@ class PrisonBreakFicNetAdapter(BaseSiteAdapter):
 
             if 'Categories' in label:
                 cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
-                for cat in cats:
+                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'))
-                for char in chars:
+                charstext = [char.string for char in chars]
+                for char in charstext:
                     self.story.addToList('characters',char.string)
 
-            if 'Pairing' in label:
-                ships = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=3')) # XXX
-                for ship in ships:
-                    self.story.addToList('ships',ship.string.replace(" and ","/"))
-
             if 'Genre' in label:
-                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1')) # XXX
+                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)
 
@@ -184,7 +179,7 @@ class PrisonBreakFicNetAdapter(BaseSiteAdapter):
             # Find Series name from series URL.
             a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
             series_name = a.string
-            series_url = 'http://'+self.host+'/'+a['href']
+            series_url = 'http://'+self.host+'/fanfiction/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
             seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
@@ -206,8 +201,7 @@ class PrisonBreakFicNetAdapter(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))
         
         div = soup.find('div', {'id' : 'story'})
 

fanficdownloader/adapters/adapter_nhamagicalworldsus.py

@@ -112,7 +112,8 @@ class NHAMagicalWorldsUsAdapter(BaseSiteAdapter):
 		
         for info in asoup.findAll('table', {'width' : '100%', 'bordercolor' : re.compile(r'#')}):
             a = info.find('a')
-            if ('viewstory.php?sid='+self.story.getMetadata('storyId')) in a['href']:
+            if 'viewstory.php?sid='+self.story.getMetadata('storyId') == a['href'] or \
+                    ('viewstory.php?sid='+self.story.getMetadata('storyId')+'&') in a['href']:
                 self.story.setMetadata('title',a.string)
                 break
 		
@@ -142,14 +143,14 @@ class NHAMagicalWorldsUsAdapter(BaseSiteAdapter):
         for cat in cats:
             self.story.addToList('category',cat.string)
 					
-        a = info.find('a', href=re.compile(r'reviews.php\?sid='+self.story.getMetadata('storyId')))
+        a = info.find('a', href=re.compile(r'viewuser.php'))
         val = a.nextSibling
         svalue = ""
         while not defaultGetattr(val) == 'br':
             val = val.nextSibling
         val = val.nextSibling
         while not defaultGetattr(val) == 'br':
-            svalue += str(val)
+            svalue += unicode(val)
             val = val.nextSibling
         self.setDescription(url,svalue)
         

fanficdownloader/adapters/adapter_nickandgregnet.py

@@ -0,0 +1,174 @@
+# -*- 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 NickAndGregNetAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class NickAndGregNetAdapter(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.
+        # XXX Most sites don't have the /fanfic part.  Replace all to remove it usually.
+        self._setURL('http://' + self.getSiteDomain() + '/desert_archive/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','nag')
+
+        # 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.nickandgreg.net'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/desert_archive/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/desert_archive/viewstory.php?sid=")+r"\d+$"
+    
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&i=1'
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+
+        ## Title
+        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        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+'/desert_archive/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # Find the chapters:
+        chapters = soup.find('select')
+        for chapter in chapters.findAll('option'):
+            if chapter.text != 'Story Index' and chapter.text != 'Chapters':
+                self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/desert_archive/'+chapter['value']))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+        
+        asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
+        
+        for div in asoup.findAll('td', {'class' : 'tblborder6'}):
+            a = div.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+            if a != None:
+                break
+        
+        self.setDescription(url,div.find('br').nextSibling)
+        
+        a=div.text.split('Rating:')
+        if len(a) == 2: self.story.setMetadata('rating', a[1].split(' -')[0])
+        
+        a=div.text.split('Characters:')
+        if len(a) == 2: 
+        	for char in a[1].split(' -')[0].split(', '):
+        	    self.story.addToList('characters',char)
+        	    
+        a=div.text.split('Genres:')
+        if len(a) == 2: 
+        	for genre in a[1].split(' -')[0].split(', '):
+        	    self.story.addToList('genre',genre)
+        	    
+        a=div.text.split('Warnings:')
+        if len(a) == 2: 
+        	for warn in a[1].split(' -')[0].split(', '):
+        	    if 'none' not in warn:
+        	        self.story.addToList('warnings',warn)
+        	    
+        a=div.text.split('Completed:')
+        if len(a) ==2:
+            if 'Yes' in a[1]:
+                self.story.setMetadata('status', 'Completed')
+            else:
+                self.story.setMetadata('status', 'In-Progress')
+                
+        a=div.text.split('Published:')
+        if len(a) == 2: self.story.setMetadata('datePublished', makeDate(stripHTML(a[1].split(' -')[0]), self.dateformat))
+        
+        a=div.text.split('Updated:')
+        if len(a) == 2: self.story.setMetadata('dateUpdated', makeDate(stripHTML(a[1].split(' -')[0]), self.dateformat))
+
+            
+    # 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('table', {'class' : 'tblborder6'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_phoenixsongnet.py

@@ -112,6 +112,8 @@ class PhoenixSongNetAdapter(BaseSiteAdapter):
         logger.debug("URL: "+url)
 
         try:
+            if self.getConfig('force_login'):
+                self.performLogin(url)
             data = self._fetchUrl(url)
         except urllib2.HTTPError, e:
             if e.code == 404:
@@ -123,7 +125,6 @@ class PhoenixSongNetAdapter(BaseSiteAdapter):
             # need to log in for this one.
             self.performLogin(url)
             data = self._fetchUrl(url)
-			
             
         # use BeautifulSoup HTML parser to make everything easier to find.
         soup = bs.BeautifulSoup(data)

fanficdownloader/adapters/adapter_potterheadsanonymouscom.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2011 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.
@@ -27,12 +27,12 @@ from .. import exceptions as exceptions
 
 from base_adapter import BaseSiteAdapter,  makeDate
 
-
 def getClass():
-    return JLAUnlimitedComAdapter
+    return PotterHeadsAnonymousComAdapter
 
-
-class JLAUnlimitedComAdapter(BaseSiteAdapter):
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class PotterHeadsAnonymousComAdapter(BaseSiteAdapter):
 
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
@@ -42,36 +42,69 @@ class JLAUnlimitedComAdapter(BaseSiteAdapter):
                                # 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.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'))
-
-        self._setURL('http://' + self.getSiteDomain() + '/eFiction1.1/viewstory.php?sid='+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','jla')
+        self.story.setMetadata('siteabbrev','pha')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%m/%d/%y"
-
+        self.dateformat = "%d %b %Y"
+            
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
         # The site domain.  Does have www here, if it uses it.
-        return 'www.jlaunlimited.com'
+        return 'fanfic.potterheadsanonymous.com'
 
     def getSiteExampleURLs(self):
-        return "http://"+self.getSiteDomain()+"/eFiction1.1/viewstory.php?sid=1234"
+        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
 
     def getSiteURLPattern(self):
-        return re.escape("http://"+self.getSiteDomain()+"/eFiction1.1/viewstory.php?sid=")+r"\d+$"
-
+        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
 
+    ## 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):
@@ -81,7 +114,7 @@ class JLAUnlimitedComAdapter(BaseSiteAdapter):
             # 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
+            addurl = "&ageconsent=ok&warning=4"
         else:
             addurl=""
 
@@ -98,8 +131,21 @@ class JLAUnlimitedComAdapter(BaseSiteAdapter):
             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 self.needToLoginCheck(data):
+            # need to log in for this one.
+            self.performLogin(url)
+            data = self._fetchUrl(url)
+            
+        # Since the warning text can change by warning level, let's
+        # look for the warning pass url.  ksarchive uses
+        # &warning= -- actually, so do other sites.  Must be an
+        # eFiction book.
+            
+        # viewstory.php?sid=1882&warning=4
+        # viewstory.php?sid=1654&ageconsent=ok&warning=5
+        #print data
+        #m = re.search(r"'viewstory.php\?sid=1882(&warning=4)'",data)
+        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
         if m != None:
             if self.is_adult or self.getConfig("is_adult"):
                 # We tried the default and still got a warning, so
@@ -120,27 +166,32 @@ class JLAUnlimitedComAdapter(BaseSiteAdapter):
                         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.
 
+        pagetitle = soup.find('div',{'id':'pagetitle'})
+        
         ## Title
-        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')))
+        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 = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        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+")):
+        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.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))
 
         self.story.setMetadata('numChapters',len(self.chapterUrls))
 
@@ -177,34 +228,22 @@ class JLAUnlimitedComAdapter(BaseSiteAdapter):
 
             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:
+                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'))
-                charstext = [char.string for char in chars]
-                for char in charstext:
+                for char in chars:
                     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:
+                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)
 
-            ## 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:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=3'))
+                for warning in warnings:
                     self.story.addToList('warnings',warning.string)
 
             if 'Completed' in label:
@@ -225,7 +264,7 @@ class JLAUnlimitedComAdapter(BaseSiteAdapter):
             # 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']
+            series_url = 'http://'+self.host+'/'+a['href']
 
             # use BeautifulSoup HTML parser to make everything easier to find.
             seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
@@ -241,20 +280,18 @@ class JLAUnlimitedComAdapter(BaseSiteAdapter):
         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),
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
                                      selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-
-        div = soup.find('div', {'id' : 'story'})
         
+        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_scarheadnet.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.
@@ -28,11 +28,11 @@ from .. import exceptions as exceptions
 from base_adapter import BaseSiteAdapter,  makeDate
 
 def getClass():
-    return SVUFictionComAdapter
+    return ScarHeadNetAdapter
 
 # Class name has to be unique.  Our convention is camel case the
 # sitename with Adapter at the end.  www is skipped.
-class SVUFictionComAdapter(BaseSiteAdapter):
+class ScarHeadNetAdapter(BaseSiteAdapter):
 
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
@@ -54,16 +54,16 @@ class SVUFictionComAdapter(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','svuf')
+        self.story.setMetadata('siteabbrev','shn')
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%b %d, %Y"
+        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 'svufiction.com'
+        return 'scarhead.net'
 
     def getSiteExampleURLs(self):
         return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
@@ -108,13 +108,13 @@ class SVUFictionComAdapter(BaseSiteAdapter):
 
     ## 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=6"
+            addurl = "&ageconsent=ok&warning=5"
         else:
             addurl=""
 
@@ -130,12 +130,21 @@ class SVUFictionComAdapter(BaseSiteAdapter):
                 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)
-                
+            
+        # Since the warning text can change by warning level, let's
+        # look for the warning pass url.  ksarchive uses
+        # &warning= -- actually, so do other sites.  Must be an
+        # eFiction book.
+            
+        # viewstory.php?sid=1882&warning=4
+        # viewstory.php?sid=1654&ageconsent=ok&warning=5
+        #print data
+        #m = re.search(r"'viewstory.php\?sid=1882(&warning=4)'",data)
         m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
         if m != None:
             if self.is_adult or self.getConfig("is_adult"):
@@ -166,24 +175,19 @@ class SVUFictionComAdapter(BaseSiteAdapter):
         # print data
 
         # Now go hunting for all the meta data and the chapter list.
+
+        pagetitle = soup.find('tr',{'valign':'top'})
         
         ## Title
-        pt = soup.find('div', {'class' : 'title'})
-        a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        if a.text != "":
-            self.story.setMetadata('title',a.text)
-        else:
-            self.story.setMetadata('title','Banner')
+        a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',a.string)
         
         # Find authorid and URL from... author url.
-        a = pt.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        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)
 
-        rating=pt.text.split('[')[1].split(']')[0]
-        self.story.setMetadata('rating', rating)
-
         # 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.
@@ -193,46 +197,70 @@ class SVUFictionComAdapter(BaseSiteAdapter):
 
         # 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 ""
-
-        bottom=soup.find('div', {'class' : 'bottom'}).text
-        self.story.setMetadata('numWords', bottom.split('Word count: ')[1].split(' Read:')[0])
-        self.story.setMetadata('datePublished', makeDate(bottom.split('Published: ')[1].split(' Updated:')[0], self.dateformat))
-        self.story.setMetadata('dateUpdated', makeDate(bottom.split('Updated: ')[1], self.dateformat))
-
         
-        content=soup.find('div', {'class' : 'content'})
-        value=content.find('h1').nextSibling
-        svalue = ""
-        while not defaultGetattr(value,'class') == 'smaller':
-            svalue += str(value)
-            value = value.nextSibling
-        self.setDescription(url,svalue)
-        
-        status = content.text.split('Completed: ')[1]
-        if 'Yes' in status:
+        cats = soup.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+        for cat in cats:
+            if '/' == cat.string[0]:
+                self.story.addToList('ships','Harry Potter'+cat.string.split('(')[0])
+            elif 'Harry' in cat.string:
+                self.story.addToList('ships',cat.string.split('(')[0])
+            else:
+                self.story.addToList('category',cat.string)
+            if '(' in cat.string:
+                self.story.addToList('category',cat.string.split('(')[1].split(')')[0])
+            
+                
+            
+
+        chars = soup.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+        for char in chars:
+            self.story.addToList('characters',char.string)
+
+        genres = soup.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
+        for genre in genres:
+            self.story.addToList('genre',genre.string)
+
+        warnings = soup.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
+        for warning in warnings:
+            self.story.addToList('warnings',warning.string)
+            
+        textsoup = stripHTML(soup)
+
+        a = textsoup.split('Published: ')[1].split(' ')[0]
+        self.story.setMetadata('datePublished', makeDate(stripHTML(a), self.dateformat))
+        a = textsoup.split('Updated: ')[1].split(' ')[0]
+        self.story.setMetadata('dateUpdated', makeDate(stripHTML(a), self.dateformat))
+        a = textsoup.split('Rating: ')[1].split(' ')[0]
+        self.story.setMetadata('rating', a)
+        a = textsoup.split('Length: ')[1].split('(')[1].split(' ')[0]
+        self.story.setMetadata('numWords', a)
+        a = textsoup.split('Completed: ')[1].split(' ')[0]
+        if 'Yes' in a:
             self.story.setMetadata('status', 'Completed')
         else:
             self.story.setMetadata('status', 'In-Progress')
+        #a = textsoup.split('Summary: ')[1].split('Add Story to Favorites')[0]
+        #self.setDescription(url,a)
         
-        cats = content.findAll('a',href=re.compile(r'browse.php\?type=categories'))
-        for cat in cats:
-            self.story.addToList('category',cat.string)
-            
-        chars = content.findAll('a',href=re.compile(r'browse.php\?type=characters'))
-        for char in chars:
-            self.story.addToList('characters',char.string)
-            
-        genres = content.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
-        for genre in genres:
-            self.story.addToList('genre',genre.string)
-            
+
+        
+        a=soup.find(text=re.compile("Summary: "))
+        i=0
+        svalue = ""
+        while i == 0:
+            try:
+                b = str(a)
+                svalue += b.split('Summary: ')[1]
+            except:
+                svalue += str(a)
+            if a.nextSibling != None:
+                a = a.nextSibling
+            else:
+                a = a.parent.nextSibling
+            if 'Disclaimer: ' in stripHTML(a):
+                i=1
+        self.setDescription(url,svalue)
+
         try:
             # Find Series name from series URL.
             a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
@@ -241,17 +269,14 @@ class SVUFictionComAdapter(BaseSiteAdapter):
 
             # 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+'))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
             i=1
             for a in storyas:
-                # skip 'report this' and 'TOC' links
-                if 'contact.php' not in a['href'] and 'index' not in a['href']:
-                    if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
-                        self.setSeries(series_name, i)
-                        self.story.setMetadata('seriesUrl',series_url)
-                        break
-                    i+=1
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    self.story.setMetadata('seriesUrl',series_url)
+                    break
+                i+=1
             
         except:
             # I find it hard to care if the series parsing fails
@@ -262,7 +287,7 @@ class SVUFictionComAdapter(BaseSiteAdapter):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+        soup = bs.BeautifulSoup(self._fetchUrl(url),
                                      selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
         
         div = soup.find('div', {'id' : 'story'})

fanficdownloader/adapters/adapter_scarvesandcoffeenet.py

@@ -141,7 +141,7 @@ class ScarvesAndCoffeeNetAdapter(BaseSiteAdapter):
         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 = soup.find('div',{"id":"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)

fanficdownloader/adapters/adapter_simplyundeniablecom.py

@@ -0,0 +1,217 @@
+# -*- 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 SimplyUndeniableComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class SimplyUndeniableComAdapter(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','sud')
+
+        # 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.simplyundeniable.com'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+
+    ## Login seems to be reasonably standard across eFiction sites.
+    def needToLoginCheck(self, data):
+        if 'Please log in now' 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 "My 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):
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        if self.needToLoginCheck(data):
+            # need to log in for this one.
+            self.performLogin(url)
+            data = self._fetchUrl(url)
+
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        if "Please log in now" in data:
+                raise exceptions.FailedToDownload(self.getSiteDomain() +" says: You need to have access to the restricted section.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        a = soup.find('h1')
+        self.story.setMetadata('title',a.text)
+        
+        # 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)
+        asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
+        
+        for info in asoup.findAll('table', {'cellpadding' : '5'}):
+            a = info.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+            if a != None:
+                self.story.setMetadata('title',a.string)
+                break
+                
+        # Find the chapters:
+        if "Disclaimer" in data:
+            self.chapterUrls.append((self.story.getMetadata('title'),url))
+        else:
+            for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+&i=1$')):
+            # 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.
+        
+        a = info.find('td', {'valign' : 'top'}).find('p')
+        self.setDescription(url,a)
+        
+        a = info.find('td', {'class' : 'greysm'}).findAll('b')
+        self.story.setMetadata('datePublished', makeDate(stripHTML(a[0].nextSibling), self.dateformat))
+        self.story.setMetadata('dateUpdated', makeDate(stripHTML(a[1].nextSibling), self.dateformat))
+        if 'Yes' in a[2].nextSibling:
+            self.story.setMetadata('status', 'Completed')
+        else:
+            self.story.setMetadata('status', 'In-Progress')
+        self.story.setMetadata('rating', a[3].nextSibling)
+        self.story.setMetadata('numWords', a[4].nextSibling)
+        
+        
+        warnings = info.find('td', {'width' : '45'}).nextSibling.nextSibling.text.split(', ')
+        for warning in warnings:
+            if 'none' not in warning:
+                self.story.addToList('warnings',warning)
+        chars = info.find('td', {'width' : '51'}).nextSibling.nextSibling.text.split(', ')
+        for char in chars:
+            if '&' in char:
+                self.story.addToList('ships',char)
+            else:
+                self.story.addToList('characters',char)
+        genres = info.find('td', {'width' : '36'}).nextSibling.nextSibling.text.split(', ')
+        for genre in genres:
+            self.story.addToList('genre',genre)
+            
+        cat = info.find('a', href=re.compile(r'categories.php'))
+        self.story.addToList('category',cat.string)
+            
+    # 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('span', {'class' : 'style'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_siyecouk.py

@@ -110,7 +110,7 @@ class SiyeCoUkAdapter(BaseSiteAdapter): # XXX
 
         ## Title
         titlea = authsoup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',titlea.string)
+        self.story.setMetadata('title',stripHTML(titlea))
         
         # Find the chapters (from soup, not authsoup):
         for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):

fanficdownloader/adapters/adapter_test1.py

@@ -47,31 +47,63 @@ class TestSiteAdapter(BaseSiteAdapter):
         return BaseSiteAdapter.getSiteURLPattern(self)+r'/?\?sid=\d+$'
 
     def extractChapterUrlsAndMetadata(self):
+        idstr = self.story.getMetadata('storyId')
+        idnum = int(idstr)
 
-        if self.story.getMetadata('storyId') == '665' and not (self.is_adult or self.getConfig("is_adult")):
+        if idnum >= 1000:
+            logger.warn("storyId:%s - Custom INI data will be used."%idstr)
+
+            sections = ['teststory:%s'%idstr,'teststory:defaults']
+            #print("self.get_config_list(sections,'valid_entries'):%s"%self.get_config_list(sections,'valid_entries'))
+            for key in self.get_config_list(sections,'valid_entries'):
+                if key.endswith("_list"):
+                    nkey = key[:-len("_list")]
+                    #print("addList:%s"%(nkey))
+                    for val in self.get_config_list(sections,key):
+                        #print("addList:%s->%s"%(nkey,val))
+                        self.story.addToList(nkey,val.decode('utf-8').replace('{{storyId}}',idstr))
+                else:
+                    # Special cases:
+                    if key in ['datePublished','dateUpdated']:
+                        self.story.setMetadata(key,makeDate(self.get_config(sections,key),"%Y-%m-%d"))
+                    else:
+                        self.story.setMetadata(key,self.get_config(sections,key).decode('utf-8').replace('{{storyId}}',idstr))
+                    #print("set:%s->%s"%(key,self.story.getMetadata(key)))
+
+            self.chapterUrls = []
+            for (j,chap) in enumerate(self.get_config_list(sections,'chaptertitles'),start=1):
+                self.chapterUrls.append( (chap,self.url+"&chapter=%d"%j) )
+            # self.chapterUrls = [(u'Prologue '+self.crazystring,self.url+"&chapter=1"),
+            #                 ('Chapter 1, Xenos on Cinnabar',self.url+"&chapter=2"),
+            #                 ]
+            self.story.setMetadata('numChapters',len(self.chapterUrls))
+            
+            return
+
+        if idstr == '665' and not (self.is_adult or self.getConfig("is_adult")):
             logger.warn("self.is_adult:%s"%self.is_adult)
             raise exceptions.AdultCheckRequired(self.url)
 
-        if self.story.getMetadata('storyId') == '666':
+        if idstr == '666':
             raise exceptions.StoryDoesNotExist(self.url)
 
-        if self.story.getMetadata('storyId').startswith('670'):
+        if idstr.startswith('670'):
             time.sleep(1.0)
             
-        if self.story.getMetadata('storyId').startswith('671'):
+        if idstr.startswith('671'):
             time.sleep(1.0)
             
         if self.getConfig("username"):
             self.username = self.getConfig("username")
         
-        if self.story.getMetadata('storyId') == '668' and self.username != "Me" :
+        if idstr == '668' and self.username != "Me" :
             raise exceptions.FailedToLogin(self.url,self.username)
 
-        if self.story.getMetadata('storyId') == '664':
-            self.story.setMetadata(u'title',"Test Story Title "+self.story.getMetadata('storyId')+self.crazystring)
+        if idstr == '664':
+            self.story.setMetadata(u'title',"Test Story Title "+idstr+self.crazystring)
             self.story.setMetadata('author','Test Author aa bare amp(&) quote(') amp(&)')
         else:
-            self.story.setMetadata(u'title',"Test Story Title "+self.story.getMetadata('storyId'))
+            self.story.setMetadata(u'title',"Test Story Title "+idstr)
             self.story.setMetadata('author','Test Author aa')
         self.story.setMetadata('storyUrl',self.url)
         self.setDescription(self.url,u'Description '+self.crazystring+u''' Done
@@ -79,13 +111,12 @@ class TestSiteAdapter(BaseSiteAdapter):
 Some more longer description.  "I suck at summaries!"  "Better than it sounds!"  "My first fic"
 ''')
         self.story.setMetadata('datePublished',makeDate("1975-03-15","%Y-%m-%d"))
-        if self.story.getMetadata('storyId') == '669':
+        if idstr == '669':
             self.story.setMetadata('dateUpdated',datetime.datetime.now())
         else:
             self.story.setMetadata('dateUpdated',makeDate("1975-04-15","%Y-%m-%d"))
         self.story.setMetadata('numWords','123456')
 
-        idnum = int(self.story.getMetadata('storyId'))
         if idnum % 2 == 1:
             self.story.setMetadata('status','In-Progress')
         else:
@@ -108,7 +139,7 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
             
         self.story.setMetadata('rating','Tweenie')
 
-        if self.story.getMetadata('storyId') == '673':
+        if idstr == '673':
             self.story.addToList('author','Author From List')
             self.story.addToList('author','Author From List 2')
         
@@ -128,18 +159,19 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
         self.story.addToList('warnings','Swearing')
         self.story.addToList('warnings','Violence')
 
-        if self.story.getMetadata('storyId') == '80':
+        if idstr == '80':
             self.story.addToList('category',u'Rizzoli & Isles')
             self.story.addToList('characters','J. Rizzoli')
-        elif self.story.getMetadata('storyId') == '81':
+        elif idstr == '81':
             self.story.addToList('category',u'Pitch Perfect')
             self.story.addToList('characters','Chloe B.')
-        elif self.story.getMetadata('storyId') == '83':
+        elif idstr == '83':
             self.story.addToList('category',u'Rizzoli & Isles')
             self.story.addToList('characters','J. Rizzoli')
             self.story.addToList('category',u'Pitch Perfect')
             self.story.addToList('characters','Chloe B.')
-        elif self.story.getMetadata('storyId') == '82':
+            self.story.addToList('ships','Chloe B. & J. Rizzoli')
+        elif idstr == '82':
             self.story.addToList('characters','Henry (Once Upon a Time)')        
             self.story.addToList('category',u'Once Upon a Time (TV)')
         else:
@@ -217,6 +249,9 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
 <div>
 <h3>Prologue</h3>
 <p>This is a fake adapter for testing purposes.  Different sid's will give different errors:</p>
+<h4>Config(personal.ini)</h4>
+<p>sid&gt;=1000 will use custom test story data from your configuration(personal.ini)</p>
+<p>Hard coded ids:</p>
 <p>http://test1.com?sid=664 - Crazy string title</p>
 <p>http://test1.com?sid=665 - raises AdultCheckRequired</p>
 <p>http://test1.com?sid=666 - raises StoryDoesNotExist</p>
@@ -224,10 +259,6 @@ 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, extra categories, genres</p>

fanficdownloader/adapters/adapter_thehookupzonenet.py

@@ -183,7 +183,7 @@ class TheHookupZoneNetAdapter(BaseSiteAdapter): # XXX
         # 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('authorUrl','http://'+self.host+'/CriminalMinds/'+a['href'])
         self.story.setMetadata('author',a.string)
 
         # Find the chapters:

fanficdownloader/adapters/adapter_thewriterscoffeeshopcom.py

@@ -244,16 +244,23 @@ class TheWritersCoffeeShopComSiteAdapter(BaseSiteAdapter):
         # issues with different SGML parsers in python.  This is a
         # nasty hack, but it works.
         data = data[data.index("<body"):]
-        
-        soup = bs.BeautifulStoneSoup(data,
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
-        
-        span = soup.find('div', {'id' : 'story'})
 
-        if None == span:
+        chapter=bs.BeautifulSoup('<div class="story"></div>')
+        
+        soup = bs.BeautifulSoup(data)
+
+        found=False
+        for div in soup.findAll('div'):
+            if div.has_key('class') and div['class'] == 'notes':
+                chapter.append(div)
+            if div.has_key('id') and div['id'] == 'story':
+                chapter.append(div)
+                found=True
+
+        if not found:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
-    
-        return self.utf8FromSoup(url,span)
+
+        return self.utf8FromSoup(url,chapter)
 
 def getClass():
     return TheWritersCoffeeShopComSiteAdapter

fanficdownloader/adapters/adapter_tokrafandomnetcom.py

@@ -0,0 +1,236 @@
+# -*- 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 TokraFandomnetComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class TokraFandomnetComAdapter(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','tokra')
+
+        # 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.  But it
+        # doesn't matter too much anymore.
+        return 'tokra.fandomnet.com'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        if self.is_adult or self.getConfig("is_adult"):
+            # Weirdly, different sites use different warning numbers.
+            # If the title search below fails, there's a good chance
+            # you need a different number.  print data at that point
+            # and see what the 'click here to continue' url says.
+            addurl = "&ageconsent=ok&warning=3"
+        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
+
+        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(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)
+
+        # Rating
+        rate = stripHTML(soup.find('div',{'id':'pagetitle'}))
+        rate = rate[rate.rindex('[')+1:rate.rindex(']')]
+        self.story.setMetadata('rating', rate)
+
+        # Find the chapters:
+        for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
+            # just in case there's tags, like <i> in chapter titles.
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        metadiv = soup.find('div',{'class':'content'})
+        smalldiv = metadiv.find('div',{'class':'small'})
+
+        # tokra categories -> genre
+        # categories will be filled from ini.
+        genres = smalldiv.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+        for genre in genres:
+            self.story.addToList('genre',genre.string)
+        
+        chars = smalldiv.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+        for char in chars:
+            self.story.addToList('characters',char.string)
+
+        metatext = stripHTML(smalldiv)
+
+        if 'Completed: Yes' in metatext:
+            self.story.setMetadata('status', 'Completed')
+        else:
+            self.story.setMetadata('status', 'In-Progress')
+
+        wordstart=metatext.rindex('Word count:')+12
+        words = metatext[wordstart:metatext.index(' ',wordstart)]
+        self.story.setMetadata('numWords', words)
+
+        datesdiv = soup.find('div',{'class':'bottom'})
+        dates = stripHTML(datesdiv).split()
+        # Published: 04/26/2011 Updated: 03/06/2013
+        self.story.setMetadata('datePublished', makeDate(dates[1], self.dateformat))
+        self.story.setMetadata('dateUpdated', makeDate(dates[3], self.dateformat))
+
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            # can't use ^viewstory...$ in case of higher rated stories with javascript href.
+            storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
+            i=1
+            for a in storyas:
+                # skip 'report this' and 'TOC' links
+                if 'contact.php' not in a['href'] and 'index' not in a['href']:
+                    if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                        self.setSeries(series_name, i)
+                        self.story.setMetadata('seriesUrl',series_url)
+                        break
+                    i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+        # remove 'small' leaving only summary.
+        smalldiv.extract()
+        self.setDescription(url,metadiv)
+        
+    # 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' : 'content'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+
+        # remove some decorations while keeping notes.
+        remove = div.find('div', {'id' : 'pagetitle'})
+        remove.extract()
+    
+        for remove in div.findAll('div', {'class' : 'right'}):
+            remove.extract()
+    
+        for remove in div.findAll('div', {'class' : 'left'}):
+            remove.extract()
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_tthfanficorg.py

@@ -154,26 +154,6 @@ class TwistingTheHellmouthSiteAdapter(BaseSiteAdapter):
         self.story.setMetadata('author',stripHTML(a))
         authorurl = 'http://'+self.host+a['href']
 
-        ainfo = soup.find('a', href='/StoryInfo-%s-1'%self.story.getMetadata('storyId'))
-        if ainfo != None: # indicates multiple authors/contributors.
-            try:
-                # going to pull part of the meta data from author list page.
-                infourl = 'http://'+self.host+ainfo['href']
-                logger.debug("**StoryInfo** URL: "+infourl)
-                infodata = self._fetchUrl(infourl)
-                infosoup = bs.BeautifulSoup(infodata)
-
-                for a in infosoup.findAll('a',href=re.compile(r"^/Author-\d+")):
-                    self.story.addToList('authorId',a['href'].split('/')[1].split('-')[1])
-                    self.story.addToList('authorUrl','http://'+self.host+a['href'].replace("/Author-","/AuthorStories-"))
-                    self.story.addToList('author',stripHTML(a))                
-                                            
-            except urllib2.HTTPError, e:
-                if e.code == 404:
-                    raise exceptions.StoryDoesNotExist(url)
-                else:
-                    raise e
-    
         try:
             # going to pull part of the meta data from *primary* author list page.
             logger.debug("**AUTHOR** URL: "+authorurl)
@@ -198,6 +178,53 @@ class TwistingTheHellmouthSiteAdapter(BaseSiteAdapter):
         #self.story.setMetadata('description',stripHTML(storydiv.find('div',{'class':'storydesc'})))
         self.story.setMetadata('title',stripHTML(storydiv.find('a',{'class':'storylink'})))
 
+        ainfo = soup.find('a', href='/StoryInfo-%s-1'%self.story.getMetadata('storyId'))
+        if ainfo != None: # indicates multiple authors/contributors.
+            try:
+                # going to pull part of the meta data from author list page.
+                infourl = 'http://'+self.host+ainfo['href']
+                logger.debug("**StoryInfo** URL: "+infourl)
+                infodata = self._fetchUrl(infourl)
+                infosoup = bs.BeautifulSoup(infodata)
+
+                # for a in infosoup.findAll('a',href=re.compile(r"^/Author-\d+")):
+                #     self.story.addToList('authorId',a['href'].split('/')[1].split('-')[1])
+                #     self.story.addToList('authorUrl','http://'+self.host+a['href'].replace("/Author-","/AuthorStories-"))
+                #     self.story.addToList('author',stripHTML(a))
+
+                # second verticaltable is the chapter list.
+                table = infosoup.findAll('table',{'class':'verticaltable'})[1]
+                for a in table.findAll('a',href=re.compile(r"^/Story-"+self.story.getMetadata('storyId'))):
+                    autha = a.findNext('a',href=re.compile(r"^/Author-\d+"))
+                    self.story.addToList('authorId',autha['href'].split('/')[1].split('-')[1])
+                    self.story.addToList('authorUrl','http://'+self.host+autha['href'].replace("/Author-","/AuthorStories-"))
+                    self.story.addToList('author',stripHTML(autha))
+                    # include leading number to match 1. ... 2. ...
+                    self.chapterUrls.append(("%d. %s by %s"%(len(self.chapterUrls)+1,
+                                                             stripHTML(a),
+                                                             stripHTML(autha)),'http://'+self.host+a['href']))
+                                            
+            except urllib2.HTTPError, e:
+                if e.code == 404:
+                    raise exceptions.StoryDoesNotExist(url)
+                else:
+                    raise e
+        else: # single author:
+            # Find the chapter selector 
+            select = soup.find('select', { 'name' : 'chapnav' } )
+        	 
+            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')
+                for o in allOptions:
+                    url = "http://"+self.host+o['value']
+                    # just in case there's tags, like <i> in chapter titles.
+                    self.chapterUrls.append((stripHTML(o),url))
+    
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
         verticaltable = soup.find('table', {'class':'verticaltable'})
 
         BtVS = True
@@ -235,21 +262,6 @@ class TwistingTheHellmouthSiteAdapter(BaseSiteAdapter):
         if BtVS:
             self.story.addToList('category','Buffy: The Vampire Slayer')
             
-        # Find the chapter selector 
-        select = soup.find('select', { 'name' : 'chapnav' } )
-    	 
-        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')
-            for o in allOptions:
-                url = "http://"+self.host+o['value']
-                # just in case there's tags, like <i> in chapter titles.
-                self.chapterUrls.append((stripHTML(o),url))
-
-        self.story.setMetadata('numChapters',len(self.chapterUrls))
-
         pseries = soup.find('p', {'style':'margin-top:0px'})
         m = re.match('This story is No\. (?P<num>\d+) in the series &quot;(?P<series>.+)&quot;\.',
                      pseries.text)

fanficdownloader/adapters/adapter_walkingtheplankorg.py

@@ -119,7 +119,7 @@ class WalkingThePlankOrgAdapter(BaseSiteAdapter):
         # 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('authorUrl','http://'+self.host+'/archive/'+a['href'])
         self.story.setMetadata('author',a.string)
 
         # Find the chapters:

fanficdownloader/adapters/adapter_wraithbaitcom.py

@@ -126,8 +126,13 @@ class WraithBaitComAdapter(BaseSiteAdapter):
 
         # Find the chapters:
         for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
+            # include author on chapters if multiple authors.
+            if len(alist) > 1:
+                add = " by %s"%stripHTML(chapter.findNext('a', href=re.compile(r"viewuser.php\?uid=\d+")))
+            else:
+                add = ""
             # just in case there's tags, like <i> in chapter titles.
-            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))
+            self.chapterUrls.append((stripHTML(chapter)+add,'http://'+self.host+'/'+chapter['href']+addurl))
 
         self.story.setMetadata('numChapters',len(self.chapterUrls))
 

fanficdownloader/adapters/base_adapter.py

@@ -197,7 +197,8 @@ class BaseSiteAdapter(Configurable):
             for index, (title,url) in enumerate(self.chapterUrls):
                 if (self.chapterFirst!=None and index < self.chapterFirst) or \
                         (self.chapterLast!=None and index > self.chapterLast):
-                    self.story.addChapter(removeEntities(title),
+                    self.story.addChapter(url,
+                                          removeEntities(title),
                                           None)
                 else:
                     if self.oldchapters and index < len(self.oldchapters):
@@ -206,7 +207,8 @@ class BaseSiteAdapter(Configurable):
                                                  partial(cachedfetch,self._fetchUrlRaw,self.oldimgs))
                     else:
                         data = self.getChapterText(url)
-                    self.story.addChapter(removeEntities(title),
+                    self.story.addChapter(url,
+                                          removeEntities(title),
                                           removeEntities(data))
             self.storyDone = True
             
@@ -313,6 +315,8 @@ class BaseSiteAdapter(Configurable):
             fetch=self._fetchUrlRaw
 
         acceptable_attributes = ['href','name','class','id']
+        if self.getConfig("keep_style_attr"):
+            acceptable_attributes.append('style')
         #print("include_images:"+self.getConfig('include_images'))
         if self.getConfig('include_images'):
             acceptable_attributes.extend(('src','alt','longdesc'))

fanficdownloader/configurable.py

@@ -15,7 +15,7 @@
 # limitations under the License.
 #
 
-import ConfigParser
+import ConfigParser, re
 
 # All of the writers(epub,html,txt) and adapters(ffnet,twlt,etc)
 # inherit from Configurable.  The config file(s) uses ini format:
@@ -37,10 +37,20 @@ class Configuration(ConfigParser.SafeConfigParser):
     def __init__(self, site, fileform):
         ConfigParser.SafeConfigParser.__init__(self)
         self.sectionslist = ['defaults']
-        self.addConfigSection(site)
+
+        if site.startswith("www."):
+            sitewith = site
+            sitewithout = site.replace("www.","")
+        else:
+            sitewith = "www."+site
+            sitewithout = site
+        
+        self.addConfigSection(sitewith)
+        self.addConfigSection(sitewithout)
         if fileform:
             self.addConfigSection(fileform)
-            self.addConfigSection(site+":"+fileform)
+            self.addConfigSection(sitewith+":"+fileform)
+            self.addConfigSection(sitewithout+":"+fileform)
         self.addConfigSection("overrides")
         
         self.validEntries = [
@@ -89,8 +99,12 @@ class Configuration(ConfigParser.SafeConfigParser):
     def getValidMetaList(self):
         return self.validEntries + self.getConfigList("extra_valid_entries")
 
+    # used by adapters & writers, non-convention naming style
     def hasConfig(self, key):
-        for section in self.sectionslist:
+        return self.has_config(self.sectionslist, key)
+
+    def has_config(self, sections, key):
+        for section in sections:
             try:
                 self.get(section,key)
                 #print("found %s in section [%s]"%(key,section))
@@ -104,10 +118,14 @@ class Configuration(ConfigParser.SafeConfigParser):
                     pass
 
         return False
-        
+
+    # used by adapters & writers, non-convention naming style
     def getConfig(self, key, default=""):
+        return self.get_config(self.sectionslist,key,default)
+    
+    def get_config(self, sections, key, default=""):        
         val = default
-        for section in self.sectionslist:
+        for section in sections:
             try:
                 val = self.get(section,key)
                 if val and val.lower() == "false":
@@ -117,7 +135,7 @@ class Configuration(ConfigParser.SafeConfigParser):
             except (ConfigParser.NoOptionError, ConfigParser.NoSectionError), e:
                 pass
 
-        for section in self.sectionslist[::-1]:
+        for section in sections[::-1]:
             # 'martian smiley' [::-1] reverses list by slicing whole list with -1 step.
             try:
                 val = val + self.get(section,"add_to_"+key)
@@ -128,11 +146,15 @@ class Configuration(ConfigParser.SafeConfigParser):
         return val
 
     # split and strip each.
-    def getConfigList(self, key):
-        vlist = self.getConfig(key).split(',')
-        vlist = filter( lambda x : x !='', [ v.strip() for v in vlist ])
+    def get_config_list(self, sections, key):
+        vlist = re.split(r'(?<!\\),',self.get_config(sections,key)) # don't split on \,
+        vlist = filter( lambda x : x !='', [ v.strip().replace('\,',',') for v in vlist ])
         #print "vlist("+key+"):"+str(vlist)
         return vlist        
+    
+    # used by adapters & writers, non-convention naming style
+    def getConfigList(self, key):
+        return self.get_config_list(self.sectionslist, key)
 
 # extended by adapter, writer and story for ease of calling configuration.
 class Configurable(object):
@@ -147,11 +169,19 @@ class Configurable(object):
         return self.configuration.getValidMetaList()
     
     def hasConfig(self, key):
-        return self.configuration.hasConfig(key)
+        return self.configuration.hasConfig(key)        
         
+    def has_config(self, sections, key):
+        return self.configuration.has_config(sections, key)
+
     def getConfig(self, key, default=""):
         return self.configuration.getConfig(key,default)
 
+    def get_config(self, sections, key, default=""):
+        return self.configuration.get_config(sections,key,default)
+
     def getConfigList(self, key):
         return self.configuration.getConfigList(key)
-        
+
+    def get_config_list(self, sections, key):
+        return self.configuration.get_config_list(sections,key)

fanficdownloader/epubutils.py

@@ -130,6 +130,9 @@ def get_update_data(inputio,
                         h2 = soup.find('h2')
                         if h2:
                             h2.extract()
+
+                        for skip in soup.findAll(attrs={'class':'skip_on_ffdl_update'}):
+                            skip.extract()
                             
                         soups.append(soup)
                         

fanficdownloader/exceptions.py

@@ -68,3 +68,10 @@ class UnknownSite(Exception):
     def __str__(self):
         return "Unknown Site(%s).  Supported sites: (%s)" % (self.url, ", ".join(self.supported_sites_list))
 
+class FailedToWriteOutput(Exception):
+    def __init__(self,error):
+        self.error=error
+
+    def __str__(self):
+        return self.error
+

fanficdownloader/geturls.py

@@ -25,7 +25,7 @@ from gziphttp import GZipProcessor
 import adapters
 from configurable import Configuration
 
-def get_urls_from_page(url,configuration=None):
+def get_urls_from_page(url,configuration=None,normalize=False):
 
     if not configuration:
         configuration = Configuration("test1.com","EPUB")
@@ -54,17 +54,25 @@ def get_urls_from_page(url,configuration=None):
         opener = u2.build_opener(u2.HTTPCookieProcessor(),GZipProcessor())
         data = opener.open(url).read()
 
-    return get_urls_from_html(data,url)
+    # kludge because I don't see it on enough sites to be worth generalizing yet.
+    restrictsearch=None
+    if 'scarvesandcoffee.net' in url:
+        restrictsearch=('div',{'id':'mainpage'})
 
-def get_urls_from_html(data,url=None,configuration=None):
+    return get_urls_from_html(data,url,configuration,normalize,restrictsearch)
 
-    normalized = set() # normalized url
+def get_urls_from_html(data,url=None,configuration=None,normalize=False,restrictsearch=None):
+
+    normalized = [] # normalized url
     retlist = [] # orig urls.
     
     if not configuration:
         configuration = Configuration("test1.com","EPUB")
 
     soup = BeautifulSoup(data)
+    if restrictsearch:
+        soup = soup.find(*restrictsearch)
+        print("restrict search:%s"%soup)
     
     for a in soup.findAll('a'):
         if a.has_key('href'):
@@ -82,16 +90,19 @@ def get_urls_from_html(data,url=None,configuration=None):
                 href = href.replace('&index=1','')
                 adapter = adapters.getAdapter(configuration,href)
                 if adapter.story.getMetadata('storyUrl') not in normalized:
-                    normalized.add(adapter.story.getMetadata('storyUrl'))
+                    normalized.append(adapter.story.getMetadata('storyUrl'))
                     retlist.append(href)
             except:
                 pass
 
-    return retlist
+    if normalize:
+        return normalized
+    else:
+        return retlist
 
-def get_urls_from_text(data,configuration=None):
+def get_urls_from_text(data,configuration=None,normalize=False):
 
-    normalized = set() # normalized url
+    normalized = [] # normalized url
     retlist = [] # orig urls.
     
     if not configuration:
@@ -102,19 +113,22 @@ def get_urls_from_text(data,configuration=None):
         # 'are you old enough' links, and 'Report This' links.
         # The 'normalized' set prevents duplicates.
         if 'story.php' in href:
-            m = re.search(r"(?P<sid>(view)?story\.php\?(sid|psid|no|story|stid)=\d+)",a['href'])
+            m = re.search(r"(?P<sid>(view)?story\.php\?(sid|psid|no|story|stid)=\d+)",href)
             if m != None:
-                href = form_url(None,m.group('sid'))
+                href = form_url(href,m.group('sid'))
         try:
             href = href.replace('&index=1','')
             adapter = adapters.getAdapter(configuration,href)
             if adapter.story.getMetadata('storyUrl') not in normalized:
-                normalized.add(adapter.story.getMetadata('storyUrl'))
+                normalized.append(adapter.story.getMetadata('storyUrl'))
                 retlist.append(href)
         except:
             pass
 
-    return retlist
+    if normalize:
+        return normalized
+    else:
+        return retlist
 
 def form_url(parenturl,url):
      url = url.strip() # ran across an image with a space in the

fanficdownloader/html.py

@@ -17,7 +17,7 @@ class HtmlProcessor:
     self.unfill = unfill
     html = self._ProcessRawHtml(html)
     self._soup = BeautifulSoup(html)
-    if self._soup.title:
+    if self._soup.title.contents:
       self.title = self._soup.title.contents[0]
     else:
       self.title = None

fanficdownloader/mobi.py

@@ -8,6 +8,8 @@ import time
 import random
 import logging
 
+logger = logging.getLogger(__name__)
+
 from html import HtmlProcessor
 
 # http://wiki.mobileread.com/wiki/MOBI
@@ -124,8 +126,8 @@ class Converter:
       tmp = self.MakeOneHTML(html_strs)
       self._ConvertStringToFile(tmp, out_file)
     except Exception, e:
-      logging.error('Error %s', e)
-      logging.debug('Details: %s' % html_strs)
+      logger.error('Error %s', e)
+      #logger.debug('Details: %s' % html_strs)
 
   def _ConvertStringToFile(self, html_data, out):
     html = HtmlProcessor(html_data)

fanficdownloader/story.py

@@ -280,10 +280,10 @@ class Story(Configurable):
         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("=>") )
+                (line,conditional) = line.split("&&")
+                (condkey,condregexp) = conditional.split("=>")
             if "=>" in line:
-                parts = map( lambda x: x.strip(), line.split("=>") )
+                parts = line.split("=>")
                 if len(parts) > 2:
                     metakeys = map( lambda x: x.strip(), parts[0].split(",") )
                     (regexp,replacement)=parts[1:]
@@ -294,9 +294,13 @@ class Story(Configurable):
                 regexp = re.compile(regexp)
                 if condregexp:
                     condregexp = re.compile(condregexp)
+                # A way to explicitly include spaces in the
+                # replacement string.  The .ini parser eats any
+                # trailing spaces.
+                replacement=replacement.replace('\s',' ') 
                 self.replacements.append([metakeys,regexp,replacement,condkey,condregexp])
     
-    def doReplacments(self,value,key):
+    def doReplacements(self,value,key):
         for (metakeys,regexp,replacement,condkey,condregexp) in self.replacements:
             if (metakeys == None or key in metakeys) \
                     and isinstance(value,basestring) \
@@ -336,7 +340,7 @@ class Story(Configurable):
                     value = value.strftime(self.getConfig(key+"_format","%Y-%m-%d"))
 
             if doreplacements:
-                value=self.doReplacments(value,key)
+                value=self.doReplacements(value,key)
             if removeallentities and value != None:
                 return removeAllEntities(value)
             else:
@@ -360,8 +364,8 @@ class Story(Configurable):
                 auth = v
                 # make sure doreplacements & removeallentities are honored.
                 if doreplacements:
-                    aurl=self.doReplacments(aurl,'authorUrl')
-                    auth=self.doReplacments(auth,'author')
+                    aurl=self.doReplacements(aurl,'authorUrl')
+                    auth=self.doReplacements(auth,'author')
                 if removeallentities:
                     aurl=removeAllEntities(aurl)
                     auth=removeAllEntities(auth)
@@ -434,7 +438,7 @@ class Story(Configurable):
         if retlist:
             if doreplacements:
                 retlist = filter( lambda x : x!=None and x!='' ,
-                                  map(partial(self.doReplacments,key=listname),retlist) )
+                                  map(partial(self.doReplacements,key=listname),retlist) )
             if removeallentities:
                 retlist = filter( lambda x : x!=None and x!='' ,
                                   map(removeAllEntities,retlist) )
@@ -470,11 +474,11 @@ class Story(Configurable):
 
         return list(subjectset | set(self.getConfigList("extratags")))
             
-    def addChapter(self, title, html):
+    def addChapter(self, url, title, html):
         if self.getConfig('strip_chapter_numbers') and \
                 self.getConfig('chapter_title_strip_pattern'):
             title = re.sub(self.getConfig('chapter_title_strip_pattern'),"",title)
-        self.chapters.append( (title,html) )
+        self.chapters.append( (url,title,html) )
 
     def getChapters(self,fortoc=False):
         "Chapters will be tuples of (title,html)"
@@ -484,8 +488,10 @@ class Story(Configurable):
                 (self.getConfig('add_chapter_numbers') == "true" \
                      or (self.getConfig('add_chapter_numbers') == "toconly" and fortoc)) \
                      and self.getConfig('chapter_title_add_pattern'):
-            for index, (title,html) in enumerate(self.chapters):
-                retval.append( (string.Template(self.getConfig('chapter_title_add_pattern')).substitute({'index':index+1,'title':title}),html) ) 
+            for index, (url,title,html) in enumerate(self.chapters):
+                retval.append( (url,
+                                string.Template(self.getConfig('chapter_title_add_pattern')).substitute({'index':index+1,'title':title}),
+                                html) )
         else:
             retval = self.chapters
             

fanficdownloader/writers/base_writer.py

@@ -177,11 +177,12 @@ class BaseStoryWriter(Configurable):
             
             self._write(out,START.substitute(self.story.getAllMetadata()))
 
-            for index, (title,html) in enumerate(self.story.getChapters(fortoc=True)):
+            for index, (url,title,html) in enumerate(self.story.getChapters(fortoc=True)):
                 if html:
                     self._write(out,ENTRY.substitute({'chapter':title,
                                                       'number':index+1,
-                                                      'index':"%04d"%(index+1)}))
+                                                      'index':"%04d"%(index+1),
+                                                      'url':url}))
 
             self._write(out,END.substitute(self.story.getAllMetadata()))
 

fanficdownloader/writers/writer_epub.py

@@ -501,7 +501,7 @@ div { margin: 0pt; padding: 0pt; }
             items.append(("log_page","OEBPS/log_page.xhtml","application/xhtml+xml","Update Log"))
             itemrefs.append("log_page")
             
-        for index, (title,html) in enumerate(self.story.getChapters(fortoc=True)):
+        for index, (url,title,html) in enumerate(self.story.getChapters(fortoc=True)):
             if html:
                 i=index+1
                 items.append(("file%04d"%i,
@@ -649,10 +649,10 @@ div { margin: 0pt; padding: 0pt; }
         else:
             CHAPTER_END = self.EPUB_CHAPTER_END
         
-        for index, (title,html) in enumerate(self.story.getChapters()):
+        for index, (url,title,html) in enumerate(self.story.getChapters()):
             if html:
                 logger.debug('Writing chapter text for: %s' % title)
-                vals={'chapter':title, 'index':"%04d"%(index+1), 'number':index+1}
+                vals={'url':url, 'chapter':title, 'index':"%04d"%(index+1), 'number':index+1}
                 fullhtml = CHAPTER_START.substitute(vals) + html + CHAPTER_END.substitute(vals)
                 # ffnet(& maybe others) gives the whole chapter text
                 # as one line.  This causes problems for nook(at

fanficdownloader/writers/writer_html.py

@@ -128,10 +128,10 @@ ${output_css}
         else:
             CHAPTER_END = self.HTML_CHAPTER_END
         
-        for index, (title,html) in enumerate(self.story.getChapters()):
+        for index, (url,title,html) in enumerate(self.story.getChapters()):
             if html:
                 logging.debug('Writing chapter text for: %s' % title)
-                vals={'chapter':title, 'index':"%04d"%(index+1), 'number':index+1}
+                vals={'url':url, 'chapter':title, 'index':"%04d"%(index+1), 'number':index+1}
                 self._write(out,CHAPTER_START.substitute(vals))
                 self._write(out,html)
                 self._write(out,CHAPTER_END.substitute(vals))

fanficdownloader/writers/writer_mobi.py

@@ -22,6 +22,9 @@ import StringIO
 from base_writer import *
 from ..htmlcleanup import stripHTML
 from ..mobi import Converter
+from ..exceptions import FailedToWriteOutput
+
+logger = logging.getLogger(__name__)
 
 class MobiWriter(BaseStoryWriter):
 
@@ -158,10 +161,10 @@ ${value}<br />
         else:
             CHAPTER_END = self.MOBI_CHAPTER_END
         
-        for index, (title,html) in enumerate(self.story.getChapters()):
+        for index, (url,title,html) in enumerate(self.story.getChapters()):
             if html:
-                logging.debug('Writing chapter text for: %s' % title)
-                vals={'chapter':title, 'index':"%04d"%(index+1), 'number':index+1}
+                logger.debug('Writing chapter text for: %s' % title)
+                vals={'url':url, 'chapter':title, 'index':"%04d"%(index+1), 'number':index+1}
                 fullhtml = CHAPTER_START.substitute(vals) + html + CHAPTER_END.substitute(vals)
                 # ffnet(& maybe others) gives the whole chapter text
                 # as one line.  This causes problems for nook(at
@@ -175,6 +178,8 @@ ${value}<br />
                       author=self.getMetadata('author'),
                       publisher=self.getMetadata('site'))
         mobidata = c.ConvertStrings(files)
+        if len(mobidata) < 1:
+            raise FailedToWriteOutput("Zero length mobi output")
         out.write(mobidata)
         
         del files

fanficdownloader/writers/writer_txt.py

@@ -154,10 +154,10 @@ End file.
         else:
             CHAPTER_END = self.TEXT_CHAPTER_END
         
-        for index, (title,html) in enumerate(self.story.getChapters()):
+        for index, (url, title,html) in enumerate(self.story.getChapters()):
             if html:
                 logging.debug('Writing chapter text for: %s' % title)
-                vals={'chapter':title, 'index':"%04d"%(index+1), 'number':index+1}
+                vals={'url':url, 'chapter':title, 'index':"%04d"%(index+1), 'number':index+1}
                 self._write(out,self.lineends(self.wraplines(removeAllEntities(CHAPTER_START.substitute(vals)))))
                 self._write(out,self.lineends(html2text(html,wrap_width=self.wrap_width)))
                 self._write(out,self.lineends(self.wraplines(removeAllEntities(CHAPTER_END.substitute(vals)))))

index.html

@@ -57,11 +57,12 @@
 	  <h3>Changes:</h3>
 	  <p>
 	    <ul>
-	      <li>Fix for changes to fanfiction.net.</li>
-	      <li>Add seriesUrl (and generated seriesHTML) as valid metadata entries. The default series on title_page is now a link.</li>
-	      <li>Add user/pass for dokuga.com.</li>
+              <li>New Site: scarhead.net -- Thanks, Ida!</li>
+	      <li>Improved error reporting of fanfiction.net site errors</li>
+	      <li>New force_login parameter for phoenixsong.net site.</li>
 	    </ul>
 	  </p>
+	  
 	  <p>
 	    Questions?  Check out our 
 	    <a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderFAQs">FAQs</a>.
@@ -70,7 +71,7 @@
 	    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://4-4-47.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
+	    <a href="http://4-4-59.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
 	  </p>
 	  <div id='error'>
 	    {{ error_message }}
@@ -380,11 +381,6 @@
 	    Use the URL of the story's first chapter, such as
 	    <br /><a href="http://onedirectionfanfiction.com/viewstory.php?sid=1234">http://onedirectionfanfiction.com/viewstory.php?sid=1234</a>
 	  </dd>
-	  <dt>www.prisonbreakfic.net</dt>
-	  <dd>
-	    Use the URL of the story's first chapter, such as
-	    <br /><a href="http://www.prisonbreakfic.net/viewstory.php?sid=1234">http://www.prisonbreakfic.net/viewstory.php?sid=1234</a>
-	  </dd>
 	  <dt>www.storiesofarda.com</dt>
 	  <dd>
 	    Use the URL of the story's chapter list, such as
@@ -473,11 +469,6 @@
 	    Use the URL of the story's first chapter, such as
 	    <br /><a href="http://www.hpfanficarchive.com/stories/viewstory.php?sid=1234">http://www.hpfanficarchive.com/stories/viewstory.php?sid=1234</a>
 	  </dd>
-	  <dt>svufiction.com</dt>
-	  <dd>
-	    Use the URL of the story's first chapter, such as
-	    <br /><a href="http://svufiction.com/viewstory.php?sid=1234">http://svufiction.com/viewstory.php?sid=1234</a>
-	  </dd>
 	  <dt>www.twilightarchives.com</dt>
 	  <dd>
 	    Use the URL of the story's first chapter, such as
@@ -554,11 +545,6 @@
 	    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
@@ -609,11 +595,46 @@
 	    Use the URL of the story's chapter list, such as
 	    <br /><a href="http://www.henneth-annun.net/stories/chapter.cfm?stid=1234">http://www.henneth-annun.net/stories/chapter.cfm?stid=1234</a>
 	  </dd>
-	  <dt>http://www.psychfic.com</dt>
+	  <dt>www.psychfic.com</dt>
 	  <dd>
 	    Use the URL of the story's chapter list, such as
 	    <br /><a href="http://www.psychfic.com/viewstory.php?sid=1234">http://www.psychfic.com/viewstory.php?sid=1234</a>
 	  </dd>
+	  <dt>tokra.fandomnet.com</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://tokra.fandomnet.com/viewstory.php?sid=1234">http://tokra.fandomnet.com/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>asr3.slashzone.org</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://asr3.slashzone.org/archive/viewstory.php?sid=1234">http://asr3.slashzone.org/archive/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>netraptor.org</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://netraptor.org/archive/viewstory.php?sid=1234">http://netraptor.org/archive/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>nickandgreg.net</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://www.nickandgreg.net/desert_archive/viewstory.php?sid=1234">http://www.nickandgreg.net/desert_archive/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>fanfic.potterheadsanonymous.com</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://fanfic.potterheadsanonymous.com/viewstory.php?sid=1234">http://fanfic.potterheadsanonymous.com/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>www.simplyundeniable.com</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://www.simplyundeniable.com/viewstory.php?sid=1234">http://www.simplyundeniable.com/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>scarhead.net</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://scarhead.net/viewstory.php?sid=1234">http://scarhead.net/viewstory.php?sid=1234</a>
+	  </dd>
 	</dl>
 
 	<p>