Update CLI download zip.

Also don't retry 404 errors and bump versions.

app.yaml

@@ -1,6 +1,6 @@
 # ffd-retief-hrd fanfictiondownloader
 application: fanfictiondownloader
-version: 4-4-66
+version: 4-4-97
 runtime: python27
 api_version: 1
 threadsafe: true

calibre-plugin/__init__.py

@@ -7,6 +7,22 @@ __license__   = 'GPL v3'
 __copyright__ = '2013, Jim Miller'
 __docformat__ = 'restructuredtext en'
 
+import sys
+if sys.version_info >= (2, 7):
+    import logging
+    logger = logging.getLogger(__name__)
+    loghandler=logging.StreamHandler()
+    loghandler.setFormatter(logging.Formatter("FFDL:%(levelname)s:%(filename)s(%(lineno)d):%(message)s"))
+    logger.addHandler(loghandler)
+    loghandler.setLevel(logging.DEBUG)
+    logger.setLevel(logging.DEBUG)
+
+# pulls in translation files for _() strings
+try:
+    load_translations()
+except NameError:
+    pass # load_translations() added in calibre 1.9
+
 # The class that all Interface Action plugin wrappers must inherit from
 from calibre.customize import InterfaceActionBase
 
@@ -23,11 +39,11 @@ class FanFictionDownLoaderBase(InterfaceActionBase):
     calibre utilities to run without needing to load the GUI libraries.
     '''
     name                = 'FanFictionDownLoader'
-    description         = 'UI plugin to download FanFiction stories from various sites.'
+    description         = _('UI plugin to download FanFiction stories from various sites.')
     supported_platforms = ['windows', 'osx', 'linux']
     author              = 'Jim Miller'
-    version             = (1, 7, 32)
-    minimum_calibre_version = (0, 8, 57)
+    version             = (1, 8, 16)
+    minimum_calibre_version = (1, 13, 0)
 
     #: This field defines the GUI plugin class that contains all the code
     #: that actually does something. Its format is module_path:class_name

calibre-plugin/config.py

@@ -7,6 +7,9 @@ __license__   = 'GPL v3'
 __copyright__ = '2012, Jim Miller'
 __docformat__ = 'restructuredtext en'
 
+import logging
+logger = logging.getLogger(__name__)
+
 import traceback, copy, threading
 from collections import OrderedDict
 
@@ -19,13 +22,40 @@ from calibre.gui2.ui import get_gui
 from calibre.gui2 import dynamic, info_dialog
 from calibre.constants import numeric_version as calibre_version
 
+# pulls in translation files for _() strings
+try:
+    load_translations()
+except NameError:
+    pass # load_translations() added in calibre 1.9
+
+# There are a number of things used several times that shouldn't be
+# translated.  This is just a way to make that easier by keeping them
+# out of the _() strings.
+# I'm tempted to override _() to include them...
+no_trans = { 'pini':'personal.ini',
+             'imgset':'\n\n[epub]\ninclude_images:true\nkeep_summary_html:true\nmake_firstimage_cover:true\n\n',
+             'gcset':'generate_cover_settings',
+             'ccset':'custom_columns_settings',
+             'gc':'Generate Cover',
+             'rl':'Reading List',
+             'cp':'Count Pages',
+             'cmplt':'Completed',
+             'inprog':'In-Progress',
+             'lul':'Last Updated',
+             'lus':'lastupdate',
+             'is':'include_subject',
+             'isa':'is_adult',
+             'u':'username',
+             'p':'password',
+             }
+
 from calibre_plugins.fanfictiondownloader_plugin.prefs import prefs, PREFS_NAMESPACE
 from calibre_plugins.fanfictiondownloader_plugin.dialogs \
-    import (UPDATE, UPDATEALWAYS, OVERWRITE, collision_order, RejectListDialog,
+    import (UPDATE, UPDATEALWAYS, collision_order, save_collisions, RejectListDialog,
             EditTextDialog, RejectUrlEntry)
     
 from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.adapters \
-    import (getConfigSections, getNormalStoryURL)
+    import getConfigSections
 
 from calibre_plugins.fanfictiondownloader_plugin.common_utils \
     import ( KeyboardConfigDialog, PrefsViewerDialog )
@@ -122,15 +152,21 @@ class ConfigWidget(QWidget):
         self.l = QVBoxLayout()
         self.setLayout(self.l)
 
-        label = QLabel('<a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderSupportedsites">List of Supported Sites</a> -- <a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderFAQs">FAQs</a>')
+        label = QLabel('<a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderSupportedsites">'+_('List of Supported Sites')+'</a> -- <a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderFAQs">'+_('FAQs')+'</a>')
         label.setOpenExternalLinks(True)
         self.l.addWidget(label)
 
-        tab_widget = QTabWidget(self)
-        self.l.addWidget(tab_widget)
 
+        self.scroll_area = QScrollArea(self)
+        self.scroll_area.setFrameShape(QScrollArea.NoFrame)
+        self.scroll_area.setWidgetResizable(True)
+        self.l.addWidget(self.scroll_area)
+
+        tab_widget = QTabWidget(self)
+        self.scroll_area.setWidget(tab_widget)
+        
         self.basic_tab = BasicTab(self, plugin_action)
-        tab_widget.addTab(self.basic_tab, 'Basic')
+        tab_widget.addTab(self.basic_tab, _('Basic'))
 
         self.personalini_tab = PersonalIniTab(self, plugin_action)
         tab_widget.addTab(self.personalini_tab, 'personal.ini')
@@ -151,25 +187,29 @@ class ConfigWidget(QWidget):
             self.countpages_tab.setEnabled(False)
 
         self.std_columns_tab = StandardColumnsTab(self, plugin_action)
-        tab_widget.addTab(self.std_columns_tab, 'Standard Columns')
+        tab_widget.addTab(self.std_columns_tab, _('Standard Columns'))
 
         self.cust_columns_tab = CustomColumnsTab(self, plugin_action)
-        tab_widget.addTab(self.cust_columns_tab, 'Custom Columns')
+        tab_widget.addTab(self.cust_columns_tab, _('Custom Columns'))
 
         self.other_tab = OtherTab(self, plugin_action)
-        tab_widget.addTab(self.other_tab, 'Other')
+        tab_widget.addTab(self.other_tab, _('Other'))
 
 
     def save_settings(self):
 
         # basic
         prefs['fileform'] = unicode(self.basic_tab.fileform.currentText())
-        prefs['collision'] = unicode(self.basic_tab.collision.currentText())
+        prefs['collision'] = save_collisions[unicode(self.basic_tab.collision.currentText())]
         prefs['updatemeta'] = self.basic_tab.updatemeta.isChecked()
         prefs['updatecover'] = self.basic_tab.updatecover.isChecked()
         prefs['updateepubcover'] = self.basic_tab.updateepubcover.isChecked()
         prefs['keeptags'] = self.basic_tab.keeptags.isChecked()
+        prefs['suppressauthorsort'] = self.basic_tab.suppressauthorsort.isChecked()
+        prefs['suppresstitlesort'] = self.basic_tab.suppresstitlesort.isChecked()
+        prefs['mark'] = self.basic_tab.mark.isChecked()
         prefs['showmarked'] = self.basic_tab.showmarked.isChecked()
+        prefs['autoconvert'] = self.basic_tab.autoconvert.isChecked()
         prefs['urlsfromclip'] = self.basic_tab.urlsfromclip.isChecked()
         prefs['updatedefault'] = self.basic_tab.updatedefault.isChecked()
         prefs['deleteotherforms'] = self.basic_tab.deleteotherforms.isChecked()
@@ -177,6 +217,7 @@ class ConfigWidget(QWidget):
         prefs['includeimages'] = self.basic_tab.includeimages.isChecked()
         prefs['lookforurlinhtml'] = self.basic_tab.lookforurlinhtml.isChecked()
         prefs['checkforseriesurlid'] = self.basic_tab.checkforseriesurlid.isChecked()
+        prefs['checkforurlchange'] = self.basic_tab.checkforurlchange.isChecked()
         prefs['injectseries'] = self.basic_tab.injectseries.isChecked()
         prefs['smarten_punctuation'] = self.basic_tab.smarten_punctuation.isChecked()
 
@@ -208,6 +249,7 @@ class ConfigWidget(QWidget):
                 #print("gc_site_settings[%s]:%s"%(site,gc_site_settings[site]))
         prefs['gc_site_settings'] = gc_site_settings
         prefs['allow_gc_from_ini'] = self.generatecover_tab.allow_gc_from_ini.isChecked()
+        prefs['gc_polish_cover'] = self.generatecover_tab.gc_polish_cover.isChecked()
 
         # Count Pages tab
         countpagesstats = []
@@ -271,17 +313,17 @@ class BasicTab(QWidget):
         topl = QVBoxLayout()
         self.setLayout(topl)
 
-        label = QLabel('These settings control the basic features of the plugin--downloading FanFiction.')
+        label = QLabel(_('These settings control the basic features of the plugin--downloading FanFiction.'))
         label.setWordWrap(True)
         topl.addWidget(label)
 
-        defs_gb = groupbox = QGroupBox("Defaults Options on Download")
+        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."
+        tooltip = _("On each download, FFDL offers an option to select the output format. <br />This sets what that option will default to.")
         horz = QHBoxLayout()
-        label = QLabel('Default Output &Format:')
+        label = QLabel(_('Default Output &Format:'))
         label.setToolTip(tooltip)
         horz.addWidget(label)
         self.fileform = QComboBox(self)
@@ -296,15 +338,15 @@ class BasicTab(QWidget):
         horz.addWidget(self.fileform)
         self.l.addLayout(horz)
 
-        tooltip = "On each download, FFDL offers an option of what happens if that story already exists. <br />This sets what that option will default to."
+        tooltip = _("On each download, FFDL offers an option of what happens if that story already exists. <br />This sets what that option will default to.")
         horz = QHBoxLayout()
-        label = QLabel('Default If Story Already Exists?')
+        label = QLabel(_('Default If Story Already Exists?'))
         label.setToolTip(tooltip)
         horz.addWidget(label)
         self.collision = QComboBox(self)
         # add collision options
         self.set_collisions()
-        i = self.collision.findText(prefs['collision'])
+        i = self.collision.findText(save_collisions[prefs['collision']])
         if i > -1:
             self.collision.setCurrentIndex(i)
         self.collision.setToolTip(tooltip)
@@ -312,122 +354,148 @@ class BasicTab(QWidget):
         horz.addWidget(self.collision)
         self.l.addLayout(horz)
 
-        self.updatemeta = QCheckBox('Default Update Calibre &Metadata?',self)
-        self.updatemeta.setToolTip("On each download, FFDL offers an option to update Calibre's metadata (title, author, URL, tags, custom columns, etc) from the web site. <br />This sets whether that will default to on or off. <br />Columns set to 'New Only' in the column tabs will only be set for new books.")
+        self.updatemeta = QCheckBox(_('Default Update Calibre &Metadata?'),self)
+        self.updatemeta.setToolTip(_("On each download, FFDL offers an option to update Calibre's metadata (title, author, URL, tags, custom columns, etc) from the web site. <br />This sets whether that will default to on or off. <br />Columns set to 'New Only' in the column tabs will only be set for new books."))
         self.updatemeta.setChecked(prefs['updatemeta'])
         self.l.addWidget(self.updatemeta)
 
-        self.updateepubcover = QCheckBox('Default Update EPUB Cover when Updating EPUB?',self)
-        self.updateepubcover.setToolTip("On each download, FFDL offers an option to update the book cover image <i>inside</i> the EPUB from the web site when the EPUB is updated.<br />This sets whether that will default to on or off.")
+        self.updateepubcover = QCheckBox(_('Default Update EPUB Cover when Updating EPUB?'),self)
+        self.updateepubcover.setToolTip(_("On each download, FFDL offers an option to update the book cover image <i>inside</i> the EPUB from the web site when the EPUB is updated.<br />This sets whether that will default to on or off."))
         self.updateepubcover.setChecked(prefs['updateepubcover'])
         self.l.addWidget(self.updateepubcover)
 
+        self.smarten_punctuation = QCheckBox(_('Smarten Punctuation (EPUB only)'),self)
+        self.smarten_punctuation.setToolTip(_("Run Smarten Punctuation from Calibre's Polish Book feature on each EPUB download and update."))
+        self.smarten_punctuation.setChecked(prefs['smarten_punctuation'])
         if calibre_version >= (0, 9, 39):
-            self.smarten_punctuation = QCheckBox('Smarten Punctuation (EPUB only)',self)
-            self.smarten_punctuation.setToolTip("Run Smarten Punctuation from Calibre's Polish Book feature on each EPUB download and update.")
-            self.smarten_punctuation.setChecked(prefs['smarten_punctuation'])
             self.l.addWidget(self.smarten_punctuation)
 
-        cali_gb = groupbox = QGroupBox("Updating Calibre Options")
+        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.')
+        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.'))
         self.deleteotherforms.setChecked(prefs['deleteotherforms'])
         self.l.addWidget(self.deleteotherforms)
         
-        self.updatecover = QCheckBox('Update Calibre Cover when Updating Metadata?',self)
-        self.updatecover.setToolTip("Update calibre book cover image from EPUB when metadata is updated.  (EPUB only.)\nDoesn't go looking for new images on 'Update Calibre Metadata Only'.")
+        self.updatecover = QCheckBox(_('Update Calibre Cover when Updating Metadata?'),self)
+        self.updatecover.setToolTip(_("Update calibre book cover image from EPUB when metadata is updated.  (EPUB only.)\nDoesn't go looking for new images on 'Update Calibre Metadata Only'."))
         self.updatecover.setChecked(prefs['updatecover'])
         self.l.addWidget(self.updatecover)
 
-        self.keeptags = QCheckBox('Keep Existing Tags when Updating Metadata?',self)
-        self.keeptags.setToolTip("Existing tags will be kept and any new tags added.\nCompleted and In-Progress tags will be still be updated, if known.\nLast Updated tags will be updated if lastupdate in include_subject_tags.\n(If Tags is set to 'New Only' in the Standard Columns tab, this has no effect.)")
+        self.keeptags = QCheckBox(_('Keep Existing Tags when Updating Metadata?'),self)
+        self.keeptags.setToolTip(_("Existing tags will be kept and any new tags added.\n%(cmplt)s and %(inprog)s tags will be still be updated, if known.\n%(lul)s tags will be updated if %(lus)s in %(is)s.\n(If Tags is set to 'New Only' in the Standard Columns tab, this has no effect.)")%no_trans)
         self.keeptags.setChecked(prefs['keeptags'])
         self.l.addWidget(self.keeptags)
 
-        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.suppressauthorsort = QCheckBox(_('Force Author into Author Sort?'),self)
+        self.suppressauthorsort.setToolTip(_("If checked, the author(s) as given will be used for the Author Sort, too.\nIf not checked, calibre will apply it's built in algorithm which makes 'Bob Smith' sort as 'Smith, Bob', etc."))
+        self.suppressauthorsort.setChecked(prefs['suppressauthorsort'])
+        self.l.addWidget(self.suppressauthorsort)
+
+        self.suppresstitlesort = QCheckBox(_('Force Title into Title Sort?'),self)
+        self.suppresstitlesort.setToolTip(_("If checked, the title as given will be used for the Title Sort, too.\nIf not checked, calibre will apply it's built in algorithm which makes 'The Title' sort as 'Title, The', etc."))
+        self.suppresstitlesort.setChecked(prefs['suppresstitlesort'])
+        self.l.addWidget(self.suppresstitlesort)
+
+        self.checkforseriesurlid = QCheckBox(_("Check for existing Series Anthology books?"),self)
+        self.checkforseriesurlid.setToolTip(_("Check for existings Series Anthology books using each new story's series URL before downloading.\nOffer to skip downloading if a Series Anthology is found."))
         self.checkforseriesurlid.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.checkforurlchange = QCheckBox(_("Check for changed Story URL?"),self)
+        self.checkforurlchange.setToolTip(_("Warn you if an update will change the URL of an existing book.\nfanfiction.net URLs will change from http to https silently."))
+        self.checkforurlchange.setChecked(prefs['checkforurlchange'])
+        self.l.addWidget(self.checkforurlchange)
+
+        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.mark = QCheckBox(_("Mark added/updated books when finished?"),self)
+        self.mark.setToolTip(_("Mark added/updated books when finished.  Use with option below.\nYou can also manually search for 'marked:ffdl_success'.\n'marked:ffdl_failed' is also available, or search 'marked:ffdl' for both."))
+        self.mark.setChecked(prefs['mark'])
+        self.l.addWidget(self.mark)
+
+        self.showmarked = QCheckBox(_("Show Marked books when finished?"),self)
+        self.showmarked.setToolTip(_("Show Marked 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)
 
-        gui_gb = groupbox = QGroupBox("GUI Options")
+        self.autoconvert = QCheckBox(_("Automatically Convert new/update books?"),self)
+        self.autoconvert.setToolTip(_("Automatically call calibre's Convert for new/update books.\nConverts to the current output format as chosen in calibre's\nPreferences->Behavior settings."))
+        self.autoconvert.setChecked(prefs['autoconvert'])
+        self.l.addWidget(self.autoconvert)
+
+        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.')
+        self.urlsfromclip = QCheckBox(_('Take URLs from Clipboard?'),self)
+        self.urlsfromclip.setToolTip(_('Prefill URLs from valid URLs in Clipboard when Adding New.'))
         self.urlsfromclip.setChecked(prefs['urlsfromclip'])
         self.l.addWidget(self.urlsfromclip)
 
-        self.updatedefault = QCheckBox('Default to Update when books selected?',self)
-        self.updatedefault.setToolTip('The top FanFictionDownLoader plugin button will start Update if\n'+
-                                      'books are selected.  If unchecked, it will always bring up \'Add New\'.')
+        self.updatedefault = QCheckBox(_('Default to Update when books selected?'),self)
+        self.updatedefault.setToolTip(_('The top FanFictionDownLoader plugin button will start Update if\nbooks are selected.  If unchecked, it will always bring up \'Add New\'.'))
         self.updatedefault.setChecked(prefs['updatedefault'])
         self.l.addWidget(self.updatedefault)
 
-        self.adddialogstaysontop = QCheckBox("Keep 'Add New from URL(s)' dialog on top?",self)
-        self.adddialogstaysontop.setToolTip("Instructs the OS and Window Manager to keep the 'Add New from URL(s)'\ndialog on top of all other windows.  Useful for dragging URLs onto it.")
+        self.adddialogstaysontop = QCheckBox(_("Keep 'Add New from URL(s)' dialog on top?"),self)
+        self.adddialogstaysontop.setToolTip(_("Instructs the OS and Window Manager to keep the 'Add New from URL(s)'\ndialog on top of all other windows.  Useful for dragging URLs onto it."))
         self.adddialogstaysontop.setChecked(prefs['adddialogstaysontop'])
         self.l.addWidget(self.adddialogstaysontop)
 
-        misc_gb = groupbox = QGroupBox("Misc Options")
+        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)
-        self.includeimages.setToolTip("Download and include images in EPUB stories.  This is equivalent to adding:\n\n[epub]\ninclude_images:true\nkeep_summary_html:true\nmake_firstimage_cover:true\n\n ...to the top of personal.ini.  Your settings in personal.ini will override this.")
+        self.includeimages = QCheckBox(_("Include images in EPUBs?"),self)
+        self.includeimages.setToolTip(_("Download and include images in EPUB stories.  This is equivalent to adding:%(imgset)s ...to the top of %(pini)s.  Your settings in %(pini)s will override this.")%no_trans)
         self.includeimages.setChecked(prefs['includeimages'])
         self.l.addWidget(self.includeimages)
 
-        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 = 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)
 
-        rej_gb = groupbox = QGroupBox("Reject List")
+        rej_gb = groupbox = QGroupBox(_("Reject List"))
         self.l = QVBoxLayout()
         groupbox.setLayout(self.l)
 
-        self.rejectlist = QPushButton('Edit Reject URL List', self)
-        self.rejectlist.setToolTip("Edit list of URLs FFDL will automatically Reject.")
+        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)
         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 = 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)
         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 = 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)
         self.l.addWidget(self.reject_reasons)
 
         topl.addWidget(defs_gb)
 
         horz = QHBoxLayout()
-        topl.addLayout(horz)
-        horz.addWidget(cali_gb)
-        horz.addWidget(rej_gb)
-        
-        horz = QHBoxLayout()
-        topl.addLayout(horz)
-        horz.addWidget(gui_gb)
-        horz.addWidget(misc_gb)
 
+        horz.addWidget(cali_gb)
+
+        vert = QVBoxLayout()
+        vert.addWidget(gui_gb)
+        vert.addWidget(misc_gb)
+        vert.addWidget(rej_gb)
+        
+        horz.addLayout(vert)
+        
+        topl.addLayout(horz)
         topl.insertStretch(-1)
         
     def set_collisions(self):
@@ -448,7 +516,7 @@ class BasicTab(QWidget):
         d = RejectListDialog(self,
                              rejecturllist.get_list(),
                              rejectreasons=rejecturllist.get_reject_reasons(),
-                             header="Edit Reject URLs List",
+                             header=_("Edit Reject URLs List"),
                              show_delete=False,
                              show_all_reasons=False)
         d.exec_()
@@ -462,22 +530,22 @@ class BasicTab(QWidget):
         d = EditTextDialog(self,
                            prefs['rejectreasons'],
                            icon=self.windowIcon(),
-                           title="Reject Reasons",
-                           label="Customize Reject List Reasons",
-                           tooltip="Customize the Reasons presented when Rejecting URLs")
+                           title=_("Reject Reasons"),
+                           label=_("Customize Reject List Reasons"),
+                           tooltip=_("Customize the Reasons presented when Rejecting URLs"))
         d.exec_()
         if d.result() == d.Accepted:
             prefs['rejectreasons'] = d.get_plain_text()
                 
     def add_reject_urls(self):
         d = EditTextDialog(self,
-                           "http://example.com/story.php?sid=5,Reason why I rejected it\nhttp://example.com/story.php?sid=6,Title by Author - Reason why I rejected it",
+                           "http://example.com/story.php?sid=5,"+_("Reason why I rejected it")+"\nhttp://example.com/story.php?sid=6,"+_("Title by Author")+" - "+_("Reason why I rejected it"),
                            icon=self.windowIcon(),
-                           title="Add Reject URLs",
-                           label="Add Reject URLs. Use: <b>http://...,note</b> or <b>http://...,title by author - note</b><br>Invalid story URLs will be ignored.",
-                           tooltip="One URL per line:\n<b>http://...,note</b>\n<b>http://...,title by author - note</b>",
+                           title=_("Add Reject URLs"),
+                           label=_("Add Reject URLs. Use: <b>http://...,note</b> or <b>http://...,title by author - note</b><br>Invalid story URLs will be ignored."),
+                           tooltip=_("One URL per line:\n<b>http://...,note</b>\n<b>http://...,title by author - note</b>"),
                            rejectreasons=rejecturllist.get_reject_reasons(),
-                           reasonslabel='Add this reason to all URLs added:')
+                           reasonslabel=_('Add this reason to all URLs added:'))
         d.exec_()
         if d.result() == d.Accepted:
             rejecturllist.add_text(d.get_plain_text(),d.get_reason_text())
@@ -492,7 +560,7 @@ class PersonalIniTab(QWidget):
         self.l = QVBoxLayout()
         self.setLayout(self.l)
 
-        label = QLabel('These settings provide more detailed control over what metadata will be displayed inside the ebook as well as let you set is_adult and user/password for different sites.')
+        label = QLabel(_('These settings provide more detailed control over what metadata will be displayed inside the ebook as well as let you set %(isa)s and %(u)s/%(p)s for different sites.')%no_trans)
         label.setWordWrap(True)
         self.l.addWidget(label)
         self.l.addSpacing(5)
@@ -503,15 +571,15 @@ class PersonalIniTab(QWidget):
         self.ini = QTextEdit(self)
         try:
             self.ini.setFont(QFont("Courier",
-                                   self.plugin_action.gui.font().pointSize()+1));
+                                   self.plugin_action.gui.font().pointSize()+1))
         except Exception as e:
-            print("Couldn't get font: %s"%e)
+            logger.error("Couldn't get font: %s"%e)
         self.ini.setLineWrapMode(QTextEdit.NoWrap)
         self.ini.setText(prefs['personal.ini'])
         self.l.addWidget(self.ini)
 
-        self.defaults = QPushButton('View Defaults (plugin-defaults.ini)', self)
-        self.defaults.setToolTip("View all of the plugin's configurable settings\nand their default settings.")
+        self.defaults = QPushButton(_('View Defaults')+' (plugin-defaults.ini)', self)
+        self.defaults.setToolTip(_("View all of the plugin's configurable settings\nand their default settings."))
         self.defaults.clicked.connect(self.show_defaults)
         self.l.addWidget(self.defaults)
         
@@ -529,25 +597,25 @@ class ShowDefaultsIniDialog(QDialog):
         self.resize(600, 500)
         self.l = QVBoxLayout()
         self.setLayout(self.l)
-        self.label = QLabel("Plugin Defaults (plugin-defaults.ini) (Read-Only)")
-        self.label.setToolTip("These are all of the plugin's configurable options\nand their default settings.")
+        self.label = QLabel(_("Plugin Defaults (%s) (Read-Only)")%'plugin-defaults.ini')
+        self.label.setToolTip(_("These are all of the plugin's configurable options\nand their default settings."))
         self.setWindowTitle(_('Plugin Defaults'))
         self.setWindowIcon(icon)
         self.l.addWidget(self.label)
         
         self.ini = QTextEdit(self)
-        self.ini.setToolTip("These are all of the plugin's configurable options\nand their default settings.")
+        self.ini.setToolTip(_("These are all of the plugin's configurable options\nand their default settings."))
         try:
             self.ini.setFont(QFont("Courier",
-                                   get_gui().font().pointSize()+1));
+                                   get_gui().font().pointSize()+1))
         except Exception as e:
-            print("Couldn't get font: %s"%e)
+            logger.error("Couldn't get font: %s"%e)
         self.ini.setLineWrapMode(QTextEdit.NoWrap)
         self.ini.setText(text)
         self.ini.setReadOnly(True)
         self.l.addWidget(self.ini)
         
-        self.ok_button = QPushButton('OK', self)
+        self.ok_button = QPushButton(_('OK'), self)
         self.ok_button.clicked.connect(self.hide)
         self.l.addWidget(self.ok_button)
         
@@ -567,45 +635,45 @@ class ReadingListTab(QWidget):
         except KeyError:
             reading_lists= []
             
-        label = QLabel('These settings provide integration with the Reading List Plugin.  Reading List can automatically send to devices and change custom columns.  You have to create and configure the lists in Reading List to be useful.')
+        label = QLabel(_('These settings provide integration with the %(rl)s Plugin.  %(rl)s can automatically send to devices and change custom columns.  You have to create and configure the lists in %(rl)s to be useful.')%no_trans)
         label.setWordWrap(True)
         self.l.addWidget(label)
         self.l.addSpacing(5)
         
-        self.addtolists = QCheckBox('Add new/updated stories to "Send to Device" Reading List(s).',self)
-        self.addtolists.setToolTip('Automatically add new/updated stories to these lists in the Reading List plugin.')
+        self.addtolists = QCheckBox(_('Add new/updated stories to "Send to Device" Reading List(s).'),self)
+        self.addtolists.setToolTip(_('Automatically add new/updated stories to these lists in the %(rl)s plugin.')%no_trans)
         self.addtolists.setChecked(prefs['addtolists'])
         self.l.addWidget(self.addtolists)
             
         horz = QHBoxLayout()
-        label = QLabel('"Send to Device" Reading Lists')
-        label.setToolTip("When enabled, new/updated stories will be automatically added to these lists.")
+        label = QLabel(_('"Send to Device" Reading Lists'))
+        label.setToolTip(_("When enabled, new/updated stories will be automatically added to these lists."))
         horz.addWidget(label)        
         self.send_lists_box = MultiCompleteLineEdit(self)
-        self.send_lists_box.setToolTip("When enabled, new/updated stories will be automatically added to these lists.")
+        self.send_lists_box.setToolTip(_("When enabled, new/updated stories will be automatically added to these lists."))
         self.send_lists_box.update_items_cache(reading_lists)
         self.send_lists_box.setText(prefs['send_lists'])
         horz.addWidget(self.send_lists_box)
         self.l.addLayout(horz)
         
-        self.addtoreadlists = QCheckBox('Add new/updated stories to "To Read" Reading List(s).',self)
-        self.addtoreadlists.setToolTip('Automatically add new/updated stories to these lists in the Reading List plugin.\nAlso offers menu option to remove stories from the "To Read" lists.')
+        self.addtoreadlists = QCheckBox(_('Add new/updated stories to "To Read" Reading List(s).'),self)
+        self.addtoreadlists.setToolTip(_('Automatically add new/updated stories to these lists in the %(rl)s plugin.\nAlso offers menu option to remove stories from the "To Read" lists.')%no_trans)
         self.addtoreadlists.setChecked(prefs['addtoreadlists'])
         self.l.addWidget(self.addtoreadlists)
             
         horz = QHBoxLayout()
-        label = QLabel('"To Read" Reading Lists')
-        label.setToolTip("When enabled, new/updated stories will be automatically added to these lists.")
+        label = QLabel(_('"To Read" Reading Lists'))
+        label.setToolTip(_("When enabled, new/updated stories will be automatically added to these lists."))
         horz.addWidget(label)        
         self.read_lists_box = MultiCompleteLineEdit(self)
-        self.read_lists_box.setToolTip("When enabled, new/updated stories will be automatically added to these lists.")
+        self.read_lists_box.setToolTip(_("When enabled, new/updated stories will be automatically added to these lists."))
         self.read_lists_box.update_items_cache(reading_lists)
         self.read_lists_box.setText(prefs['read_lists'])
         horz.addWidget(self.read_lists_box)
         self.l.addLayout(horz)
         
-        self.addtolistsonread = QCheckBox('Add stories back to "Send to Device" Reading List(s) when marked "Read".',self)
-        self.addtolistsonread.setToolTip('Menu option to remove from "To Read" lists will also add stories back to "Send to Device" Reading List(s)')
+        self.addtolistsonread = QCheckBox(_('Add stories back to "Send to Device" Reading List(s) when marked "Read".'),self)
+        self.addtolistsonread.setToolTip(_('Menu option to remove from "To Read" lists will also add stories back to "Send to Device" Reading List(s)'))
         self.addtolistsonread.setChecked(prefs['addtolistsonread'])
         self.l.addWidget(self.addtolistsonread)
             
@@ -627,7 +695,7 @@ class GenerateCoverTab(QWidget):
         except KeyError:
             gc_settings= []
             
-        label = QLabel('The Generate Cover plugin can create cover images for books using various metadata and configurations.  If you have GC installed, FFDL can run GC on new downloads and metadata updates.  Pick a GC setting by site or Default.')
+        label = QLabel(_('The %(gc)s plugin can create cover images for books using various metadata and configurations.  If you have GC installed, FFDL can run GC on new downloads and metadata updates.  Pick a GC setting by site or Default.')%no_trans)
         label.setWordWrap(True)
         self.l.addWidget(label)
         self.l.addSpacing(5)
@@ -645,14 +713,15 @@ class GenerateCoverTab(QWidget):
 
         sitelist = getConfigSections()
         sitelist.sort()
-        sitelist.insert(0,u"Default")
+        sitelist.insert(0,_("Default"))
         for site in sitelist:
             horz = QHBoxLayout()
             label = QLabel(site)
-            if site == u"Default":
-                s = "On Metadata update, run Generate Cover with this setting, if not selected for specific site."
+            if site == _("Default"):
+                s = _("On Metadata update, run %(gc)s with this setting, if not selected for specific site.")%no_trans
             else:
-                s = "On Metadata update, run Generate Cover with this setting for %s stories."%site
+                no_trans['site']=site # not ideal, but, meh.
+                s = _("On Metadata update, run %(gc)s with this setting for %(site)s stories.")%no_trans
 
             label.setToolTip(s)
             horz.addWidget(label)
@@ -661,7 +730,12 @@ class GenerateCoverTab(QWidget):
             dropdown.addItem('',QVariant('none'))
             for setting in gc_settings:
                 dropdown.addItem(setting,QVariant(setting))
-            self.gc_dropdowns[site] = dropdown
+            if site == _("Default"):
+                self.gc_dropdowns["Default"] = dropdown
+                if 'Default' in prefs['gc_site_settings']:
+                    dropdown.setCurrentIndex(dropdown.findData(QVariant(prefs['gc_site_settings']['Default'])))
+            else:
+                self.gc_dropdowns[site] = dropdown
             if site in prefs['gc_site_settings']:
                 dropdown.setCurrentIndex(dropdown.findData(QVariant(prefs['gc_site_settings'][site])))
 
@@ -670,16 +744,21 @@ class GenerateCoverTab(QWidget):
         
         self.sl.insertStretch(-1)
         
-        self.gcnewonly = QCheckBox("Run Generate Cover Only on New Books",self)
-        self.gcnewonly.setToolTip("Default is to run GC any time the calibre metadata is updated.")
+        self.gcnewonly = QCheckBox(_("Run %(gc)s Only on New Books")%no_trans,self)
+        self.gcnewonly.setToolTip(_("Default is to run GC any time the calibre metadata is updated."))
         self.gcnewonly.setChecked(prefs['gcnewonly'])
         self.l.addWidget(self.gcnewonly)
 
-        self.allow_gc_from_ini = QCheckBox('Allow generate_cover_settings from personal.ini to override',self)
-        self.allow_gc_from_ini.setToolTip("The personal.ini parameter generate_cover_settings allows you to choose a GC setting based on metadata rather than site, but it's much more complex.<br \>generate_cover_settings is ignored when this is off.")
+        self.allow_gc_from_ini = QCheckBox(_('Allow %(gcset)s from %(pini)s to override')%no_trans,self)
+        self.allow_gc_from_ini.setToolTip(_("The %(pini)s parameter %(gcset)s allows you to choose a GC setting based on metadata rather than site, but it's much more complex.<br \>%(gcset)s is ignored when this is off.")%no_trans)
         self.allow_gc_from_ini.setChecked(prefs['allow_gc_from_ini'])
         self.l.addWidget(self.allow_gc_from_ini)
             
+        self.gc_polish_cover = QCheckBox(_("Use calibre's Polish feature to inject/update the cover"),self)
+        self.gc_polish_cover.setToolTip(_("Calibre's Polish feature will be used to inject or update the generated cover into the ebook, EPUB only."))
+        self.gc_polish_cover.setChecked(prefs['gc_polish_cover'])
+        self.l.addWidget(self.gc_polish_cover)
+            
 class CountPagesTab(QWidget):
 
     def __init__(self, parent_dialog, plugin_action):
@@ -690,39 +769,41 @@ class CountPagesTab(QWidget):
         self.l = QVBoxLayout()
         self.setLayout(self.l)
 
-        label = QLabel('These settings provide integration with the Count Pages Plugin.  Count Pages can automatically update custom columns with page, word and reading level statistics.  You have to create and configure the columns in Count Pages first.')
+        label = QLabel(_('These settings provide integration with the %(cp)s Plugin.  %(cp)s can automatically update custom columns with page, word and reading level statistics.  You have to create and configure the columns in %(cp)s first.')%no_trans)
         label.setWordWrap(True)
         self.l.addWidget(label)
         self.l.addSpacing(5)
 
-        label = QLabel('If any of the settings below are checked, when stories are added or updated, the Count Pages Plugin will be called to update the checked statistics.')
+        label = QLabel(_('If any of the settings below are checked, when stories are added or updated, the %(cp)s Plugin will be called to update the checked statistics.')%no_trans)
         label.setWordWrap(True)
         self.l.addWidget(label)
         self.l.addSpacing(5)
-        
+
+        # the same for all settings.  Mostly.
+        tooltip = _('Which column and algorithm to use are configured in %(cp)s.')%no_trans
         # 'PageCount', 'WordCount', 'FleschReading', 'FleschGrade', 'GunningFog'
         self.pagecount = QCheckBox('Page Count',self)
-        self.pagecount.setToolTip('Which column and algorithm to use are configured in Count Pages.')
+        self.pagecount.setToolTip(tooltip)
         self.pagecount.setChecked('PageCount' in prefs['countpagesstats'])
         self.l.addWidget(self.pagecount)
             
         self.wordcount = QCheckBox('Word Count',self)
-        self.wordcount.setToolTip('Which column and algorithm to use are configured in Count Words.\nWill overwrite word count from FFDL metadata if set to update the same custom column.')
+        self.wordcount.setToolTip(tooltip+"\n"+_('Will overwrite word count from FFDL metadata if set to update the same custom column.'))
         self.wordcount.setChecked('WordCount' in prefs['countpagesstats'])
         self.l.addWidget(self.wordcount)
 
         self.fleschreading = QCheckBox('Flesch Reading Ease',self)
-        self.fleschreading.setToolTip('Which column and algorithm to use are configured in Count Pages.')
+        self.fleschreading.setToolTip(tooltip)
         self.fleschreading.setChecked('FleschReading' in prefs['countpagesstats'])
         self.l.addWidget(self.fleschreading)
         
         self.fleschgrade = QCheckBox('Flesch-Kincaid Grade Level',self)
-        self.fleschgrade.setToolTip('Which column and algorithm to use are configured in Count Pages.')
+        self.fleschgrade.setToolTip(tooltip)
         self.fleschgrade.setChecked('FleschGrade' in prefs['countpagesstats'])
         self.l.addWidget(self.fleschgrade)
         
         self.gunningfog = QCheckBox('Gunning Fog Index',self)
-        self.gunningfog.setToolTip('Which column and algorithm to use are configured in Count Pages.')
+        self.gunningfog.setToolTip(tooltip)
         self.gunningfog.setChecked('GunningFog' in prefs['countpagesstats'])
         self.l.addWidget(self.gunningfog)
         
@@ -738,26 +819,23 @@ class OtherTab(QWidget):
         self.l = QVBoxLayout()
         self.setLayout(self.l)
 
-        label = QLabel("These controls aren't plugin settings as such, but convenience buttons for setting Keyboard shortcuts and getting all the FanFictionDownLoader confirmation dialogs back again.")
+        label = QLabel(_("These controls aren't plugin settings as such, but convenience buttons for setting Keyboard shortcuts and getting all the FanFictionDownLoader confirmation dialogs back again."))
         label.setWordWrap(True)
         self.l.addWidget(label)
         self.l.addSpacing(5)
         
-        keyboard_shortcuts_button = QPushButton('Keyboard shortcuts...', self)
-        keyboard_shortcuts_button.setToolTip(_(
-                    'Edit the keyboard shortcuts associated with this plugin'))
+        keyboard_shortcuts_button = QPushButton(_('Keyboard shortcuts...'), self)
+        keyboard_shortcuts_button.setToolTip(_('Edit the keyboard shortcuts associated with this plugin'))
         keyboard_shortcuts_button.clicked.connect(parent_dialog.edit_shortcuts)
         self.l.addWidget(keyboard_shortcuts_button)
 
         reset_confirmation_button = QPushButton(_('Reset disabled &confirmation dialogs'), self)
-        reset_confirmation_button.setToolTip(_(
-                    'Reset all show me again dialogs for the FanFictionDownLoader plugin'))
+        reset_confirmation_button.setToolTip(_('Reset all show me again dialogs for the FanFictionDownLoader plugin'))
         reset_confirmation_button.clicked.connect(self.reset_dialogs)
         self.l.addWidget(reset_confirmation_button)
         
-        view_prefs_button = QPushButton('&View library preferences...', self)
-        view_prefs_button.setToolTip(_(
-                    'View data stored in the library database for this plugin'))
+        view_prefs_button = QPushButton(_('&View library preferences...'), self)
+        view_prefs_button.setToolTip(_('View data stored in the library database for this plugin'))
         view_prefs_button.clicked.connect(self.view_prefs)
         self.l.addWidget(view_prefs_button)
         
@@ -817,35 +895,35 @@ permitted_values['text'] = permitted_values['enumeration']
 permitted_values['comments'] = permitted_values['enumeration']
 
 titleLabels = {
-    'category':'Category',
-    'genre':'Genre',
-    'language':'Language',
-    'status':'Status',
-    'status-C':'Status:Completed',
-    'status-I':'Status:In-Progress',
-    'series':'Series',
-    'characters':'Characters',
-    'ships':'Relationships',
-    'datePublished':'Published',
-    'dateUpdated':'Updated',
-    'dateCreated':'Created',
-    'rating':'Rating',
-    'warnings':'Warnings',
-    'numChapters':'Chapters',
-    'numWords':'Words',
-    'site':'Site',
-    'storyId':'Story ID',
-    'authorId':'Author ID',
-    'extratags':'Extra Tags',
-    'title':'Title',
-    'storyUrl':'Story URL',
-    'description':'Description',
-    'author':'Author',
-    'authorUrl':'Author URL',
-    'formatname':'File Format',
-    'formatext':'File Extension',
-    'siteabbrev':'Site Abbrev',
-    'version':'FFDL Version'
+    'category':_('Category'),
+    'genre':_('Genre'),
+    'language':_('Language'),
+    'status':_('Status'),
+    'status-C':_('Status:%(cmplt)s')%no_trans,
+    'status-I':_('Status:%(inprog)s')%no_trans,
+    'series':_('Series'),
+    'characters':_('Characters'),
+    'ships':_('Relationships'),
+    'datePublished':_('Published'),
+    'dateUpdated':_('Updated'),
+    'dateCreated':_('Created'),
+    'rating':_('Rating'),
+    'warnings':_('Warnings'),
+    'numChapters':_('Chapters'),
+    'numWords':_('Words'),
+    'site':_('Site'),
+    'storyId':_('Story ID'),
+    'authorId':_('Author ID'),
+    'extratags':_('Extra Tags'),
+    'title':_('Title'),
+    'storyUrl':_('Story URL'),
+    'description':_('Description'),
+    'author':_('Author'),
+    'authorUrl':_('Author URL'),
+    'formatname':_('File Format'),
+    'formatext':_('File Extension'),
+    'siteabbrev':_('Site Abbrev'),
+    'version':_('FFDL Version')
     }
 
 class CustomColumnsTab(QWidget):
@@ -860,7 +938,7 @@ class CustomColumnsTab(QWidget):
         self.l = QVBoxLayout()
         self.setLayout(self.l)
 
-        label = QLabel("If you have custom columns defined, they will be listed below.  Choose a metadata value type to fill your columns automatically.")
+        label = QLabel(_("If you have custom columns defined, they will be listed below.  Choose a metadata value type to fill your columns automatically."))
         label.setWordWrap(True)
         self.l.addWidget(label)
         self.l.addSpacing(5)
@@ -885,7 +963,7 @@ class CustomColumnsTab(QWidget):
                 #     print("column['%s'] => %s"%(k,v))
                 horz = QHBoxLayout()
                 label = QLabel(column['name'])
-                label.setToolTip("Update this %s column(%s) with..."%(key,column['datatype']))
+                label.setToolTip(_("Update this %s column(%s) with...")%(key,column['datatype']))
                 horz.addWidget(label)
                 dropdown = QComboBox(self)
                 dropdown.addItem('',QVariant('none'))
@@ -895,13 +973,13 @@ class CustomColumnsTab(QWidget):
                 if key in prefs['custom_cols']:
                     dropdown.setCurrentIndex(dropdown.findData(QVariant(prefs['custom_cols'][key])))
                 if column['datatype'] == 'enumeration':
-                    dropdown.setToolTip("Metadata values valid for this type of column.\nValues that aren't valid for this enumeration column will be ignored.")
+                    dropdown.setToolTip(_("Metadata values valid for this type of column.")+"\n"+_("Values that aren't valid for this enumeration column will be ignored."))
                 else:
-                    dropdown.setToolTip("Metadata values valid for this type of column.")
+                    dropdown.setToolTip(_("Metadata values valid for this type of column."))
                 horz.addWidget(dropdown)
 
-                newonlycheck = QCheckBox("New Only",self)
-                newonlycheck.setToolTip("Write to %s(%s) only for new\nbooks, not updates to existing books."%(column['name'],key))
+                newonlycheck = QCheckBox(_("New Only"),self)
+                newonlycheck.setToolTip(_("Write to %s(%s) only for new\nbooks, not updates to existing books.")%(column['name'],key))
                 self.custcol_newonlycheck[key] = newonlycheck
                 if key in prefs['custom_cols_newonly']:
                     newonlycheck.setChecked(prefs['custom_cols_newonly'][key])
@@ -912,19 +990,19 @@ class CustomColumnsTab(QWidget):
         self.sl.insertStretch(-1)
 
         self.l.addSpacing(5)
-        self.allow_custcol_from_ini = QCheckBox('Allow custom_columns_settings from personal.ini to override',self)
-        self.allow_custcol_from_ini.setToolTip("The personal.ini parameter custom_columns_settings allows you to set custom columns to site specific values that aren't common to all sites.<br \>custom_columns_settings is ignored when this is off.")
+        self.allow_custcol_from_ini = QCheckBox(_('Allow %(ccset)s from %(pini)s to override')%no_trans,self)
+        self.allow_custcol_from_ini.setToolTip(_("The %(pini)s parameter %(ccset)s allows you to set custom columns to site specific values that aren't common to all sites.<br />%(ccset)s is ignored when this is off.")%no_trans)
         self.allow_custcol_from_ini.setChecked(prefs['allow_custcol_from_ini'])
         self.l.addWidget(self.allow_custcol_from_ini)
         
         self.l.addSpacing(5)
-        label = QLabel("Special column:")
+        label = QLabel(_("Special column:"))
         label.setWordWrap(True)
         self.l.addWidget(label)
         
         horz = QHBoxLayout()
-        label = QLabel("Update/Overwrite Error Column:")
-        tooltip="When an update or overwrite of an existing story fails, record the reason in this column.\n(Text and Long Text columns only.)"
+        label = QLabel(_("Update/Overwrite Error Column:"))
+        tooltip=_("When an update or overwrite of an existing story fails, record the reason in this column.\n(Text and Long Text columns only.)")
         label.setToolTip(tooltip)
         horz.addWidget(label)
         self.errorcol = QComboBox(self)
@@ -949,21 +1027,21 @@ class StandardColumnsTab(QWidget):
 
         columns=OrderedDict()
         
-        columns["title"]="Title"
-        columns["authors"]="Author(s)"
-        columns["publisher"]="Publisher"
-        columns["tags"]="Tags"
-        columns["languages"]="Languages"
-        columns["pubdate"]="Published Date"
-        columns["timestamp"]="Date"
-        columns["comments"]="Comments"
-        columns["series"]="Series"
-        columns["identifiers"]="Ids(url id only)"
+        columns["title"]=_("Title")
+        columns["authors"]=_("Author(s)")
+        columns["publisher"]=_("Publisher")
+        columns["tags"]=_("Tags")
+        columns["languages"]=_("Languages")
+        columns["pubdate"]=_("Published Date")
+        columns["timestamp"]=_("Date")
+        columns["comments"]=_("Comments")
+        columns["series"]=_("Series")
+        columns["identifiers"]=_("Ids(url id only)")
 
         self.l = QVBoxLayout()
         self.setLayout(self.l)
 
-        label = QLabel("The standard calibre metadata columns are listed below.  You may choose whether FFDL will fill each column automatically on updates or only for new books.")
+        label = QLabel(_("The standard calibre metadata columns are listed below.  You may choose whether FFDL will fill each column automatically on updates or only for new books."))
         label.setWordWrap(True)
         self.l.addWidget(label)
         self.l.addSpacing(5)
@@ -976,8 +1054,8 @@ class StandardColumnsTab(QWidget):
             #label.setToolTip("Update this %s column(%s) with..."%(key,column['datatype']))
             horz.addWidget(label)
 
-            newonlycheck = QCheckBox("New Only",self)
-            newonlycheck.setToolTip("Write to %s only for new\nbooks, not updates to existing books."%column)
+            newonlycheck = QCheckBox(_("New Only"),self)
+            newonlycheck.setToolTip(_("Write to %s only for new\nbooks, not updates to existing books.")%column)
             self.stdcol_newonlycheck[key] = newonlycheck
             if key in prefs['std_cols_newonly']:
                 newonlycheck.setChecked(prefs['std_cols_newonly'][key])

calibre-plugin/dialogs.py

@@ -7,9 +7,15 @@ __license__   = 'GPL v3'
 __copyright__ = '2011, Jim Miller'
 __docformat__ = 'restructuredtext en'
 
+import logging
+logger = logging.getLogger(__name__)
+
 import traceback, re
 from functools import partial
 
+import logging
+logger = logging.getLogger(__name__)
+
 import urllib
 import email
 
@@ -23,6 +29,12 @@ from PyQt4.Qt import (QDialog, QTableWidget, QVBoxLayout, QHBoxLayout, QGridLayo
 from calibre.gui2.dialogs.confirm_delete import confirm
 from calibre.gui2.complete2 import EditWithComplete
 
+# pulls in translation files for _() strings
+try:
+    load_translations()
+except NameError:
+    pass # load_translations() added in calibre 1.9
+
 from calibre_plugins.fanfictiondownloader_plugin.common_utils \
     import (ReadOnlyTableWidgetItem, ReadOnlyTextIconWidgetItem, SizePersistedDialog,
             ImageTitleLayout, get_icon)
@@ -30,13 +42,13 @@ from calibre_plugins.fanfictiondownloader_plugin.common_utils \
 from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.geturls import get_urls_from_html, get_urls_from_text
 from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.adapters import getNormalStoryURL
 
-SKIP=u'Skip'
-ADDNEW=u'Add New Book'
-UPDATE=u'Update EPUB if New Chapters'
-UPDATEALWAYS=u'Update EPUB Always'
-OVERWRITE=u'Overwrite if Newer'
-OVERWRITEALWAYS=u'Overwrite Always'
-CALIBREONLY=u'Update Calibre Metadata Only'
+SKIP=_('Skip')
+ADDNEW=_('Add New Book')
+UPDATE=_('Update EPUB if New Chapters')
+UPDATEALWAYS=_('Update EPUB Always')
+OVERWRITE=_('Overwrite if Newer')
+OVERWRITEALWAYS=_('Overwrite Always')
+CALIBREONLY=_('Update Calibre Metadata Only')
 collision_order=[SKIP,
                  ADDNEW,
                  UPDATE,
@@ -45,6 +57,32 @@ collision_order=[SKIP,
                  OVERWRITEALWAYS,
                  CALIBREONLY,]
 
+# best idea I've had for how to deal with config/pref saving the
+# collision name in english.
+SAVE_SKIP='Skip'
+SAVE_ADDNEW='Add New Book'
+SAVE_UPDATE='Update EPUB if New Chapters'
+SAVE_UPDATEALWAYS='Update EPUB Always'
+SAVE_OVERWRITE='Overwrite if Newer'
+SAVE_OVERWRITEALWAYS='Overwrite Always'
+SAVE_CALIBREONLY='Update Calibre Metadata Only'
+save_collisions={
+    SKIP:SAVE_SKIP,
+    ADDNEW:SAVE_ADDNEW,
+    UPDATE:SAVE_UPDATE,
+    UPDATEALWAYS:SAVE_UPDATEALWAYS,
+    OVERWRITE:SAVE_OVERWRITE,
+    OVERWRITEALWAYS:SAVE_OVERWRITEALWAYS,
+    CALIBREONLY:SAVE_CALIBREONLY,
+    SAVE_SKIP:SKIP,
+    SAVE_ADDNEW:ADDNEW,
+    SAVE_UPDATE:UPDATE,
+    SAVE_UPDATEALWAYS:UPDATEALWAYS,
+    SAVE_OVERWRITE:OVERWRITE,
+    SAVE_OVERWRITEALWAYS:OVERWRITEALWAYS,
+    SAVE_CALIBREONLY:CALIBREONLY,
+    }
+    
 anthology_collision_order=[UPDATE,
                            UPDATEALWAYS,
                            OVERWRITEALWAYS]
@@ -98,6 +136,7 @@ class RejectUrlEntry:
     def fullnote(self):
         retval = ""
         if self.title and self.auth:
+            # don't translate--ends up being saved and confuses regex above.
             retval = retval + "%s by %s"%(self.title,self.auth)
             if self.note:
                 retval = retval + " - "
@@ -164,7 +203,7 @@ class DroppableQTextEdit(QTextEdit):
         
     def canInsertFromMimeData(self, source):
         if source.hasUrls():
-            return True;
+            return True
         else:
             return QTextEdit.canInsertFromMimeData(self,source)
 
@@ -186,7 +225,7 @@ class AddNewDialog(SizePersistedDialog):
         self.l = QVBoxLayout()
         self.setLayout(self.l)
 
-        self.setWindowTitle('FanFictionDownLoader')
+        self.setWindowTitle(_('FanFictionDownLoader'))
         self.setWindowIcon(icon)
 
         self.toplabel=QLabel("Toplabel")
@@ -203,12 +242,12 @@ class AddNewDialog(SizePersistedDialog):
         # elements to show again when doing *update* merge
         self.mergeupdateshow = []
 
-        self.groupbox = QGroupBox("Show Download Options")
+        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);
+        #print("style:%s"%self.groupbox.styleSheet())
+        self.groupbox.setStyleSheet(gpstyle)
 
         self.gbf = QFrame()
         self.gbl = QVBoxLayout()
@@ -222,7 +261,7 @@ class AddNewDialog(SizePersistedDialog):
         self.groupbox.toggled.connect(self.gbf.setVisible)
         
         horz = QHBoxLayout()
-        label = QLabel('Output &Format:')
+        label = QLabel(_('Output &Format:'))
         self.mergehide.append(label)
         
         self.fileform = QComboBox(self)
@@ -230,7 +269,7 @@ class AddNewDialog(SizePersistedDialog):
         self.fileform.addItem('mobi')
         self.fileform.addItem('html')
         self.fileform.addItem('txt')
-        self.fileform.setToolTip('Choose output format to create.  May set default from plugin configuration.')
+        self.fileform.setToolTip(_('Choose output format to create.  May set default from plugin configuration.'))
         self.fileform.activated.connect(self.set_collisions)
         
         horz.addWidget(label)
@@ -246,7 +285,7 @@ class AddNewDialog(SizePersistedDialog):
         self.collision.setToolTip("CollisionToolTip")
         # add collision options
         self.set_collisions()
-        i = self.collision.findText(prefs['collision'])
+        i = self.collision.findText(save_collisions[prefs['collision']])
         if i > -1:
             self.collision.setCurrentIndex(i)
         self.collisionlabel.setBuddy(self.collision)
@@ -258,15 +297,15 @@ class AddNewDialog(SizePersistedDialog):
         self.mergeupdateshow.append(self.collision)
 
         horz = QHBoxLayout()
-        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 = 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'])
         horz.addWidget(self.updatemeta)
         self.mergehide.append(self.updatemeta)
         self.mergeupdateshow.append(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 = QCheckBox(_('Update EPUB Cover?'),self)
+        self.updateepubcover.setToolTip(_('Update book cover image from site or defaults (if found) <i>inside</i> the EPUB when EPUB is updated.'))
         self.updateepubcover.setChecked(prefs['updateepubcover'])
         horz.addWidget(self.updateepubcover)
         self.mergehide.append(self.updateepubcover)
@@ -313,10 +352,10 @@ class AddNewDialog(SizePersistedDialog):
         self.groupbox.setVisible(not(self.merge and self.newmerge))
         
         if self.merge:
-            self.toplabel.setText('Story URL(s) for anthology, one per line:')
-            self.url.setToolTip('URLs for stories to include in the anthology, one per line.\nWill take URLs from clipboard, but only valid URLs.')
-            self.collisionlabel.setText('If Story Already Exists in Anthology?')
-            self.collision.setToolTip("What to do if there's already an existing story with the same URL in the anthology.")
+            self.toplabel.setText(_('Story URL(s) for anthology, one per line:'))
+            self.url.setToolTip(_('URLs for stories to include in the anthology, one per line.\nWill take URLs from clipboard, but only valid URLs.'))
+            self.collisionlabel.setText(_('If Story Already Exists in Anthology?'))
+            self.collision.setToolTip(_("What to do if there's already an existing story with the same URL in the anthology."))
             for widget in self.mergehide:
                 widget.setVisible(False)
             if not self.newmerge:
@@ -325,10 +364,10 @@ class AddNewDialog(SizePersistedDialog):
         else:
             for widget in self.mergehide:
                 widget.setVisible(True)
-            self.toplabel.setText('Story URL(s), one per line:')
-            self.url.setToolTip('URLs for stories, one per line.\nWill take URLs from clipboard, but only valid URLs.\nAdd [1,5] after the URL to limit the download to chapters 1-5.')
-            self.collisionlabel.setText('If Story Already Exists?')
-            self.collision.setToolTip("What to do if there's already an existing story with the same URL or title and author.")
+            self.toplabel.setText(_('Story URL(s), one per line:'))
+            self.url.setToolTip(_('URLs for stories, one per line.\nWill take URLs from clipboard, but only valid URLs.\nAdd [1,5] after the URL to limit the download to chapters 1-5.'))
+            self.collisionlabel.setText(_('If Story Already Exists?'))
+            self.collision.setToolTip(_("What to do if there's already an existing story with the same URL or title and author."))
 
         # Need to re-able after hiding/showing
         self.setAcceptDrops(True)
@@ -344,10 +383,10 @@ class AddNewDialog(SizePersistedDialog):
 
         # add collision options
         self.set_collisions()
-        
-        i = self.collision.findText(self.prefs['collision'])
+        i = self.collision.findText(save_collisions[self.prefs['collision']])
         if i > -1:
             self.collision.setCurrentIndex(i)
+            
         self.updatemeta.setChecked(self.prefs['updatemeta'])
             
         if not self.merge:
@@ -428,18 +467,18 @@ class CollectURLDialog(SizePersistedDialog):
         self.url.setText(url_text)
         self.l.addWidget(self.url,1,1,1,2)
    
-        self.indiv_button = QPushButton('For Individual Books', self)
-        self.indiv_button.setToolTip('Get URLs and go to dialog for individual story downloads.')
+        self.indiv_button = QPushButton(_('For Individual Books'), self)
+        self.indiv_button.setToolTip(_('Get URLs and go to dialog for individual story downloads.'))
         self.indiv_button.clicked.connect(self.indiv)
         self.l.addWidget(self.indiv_button,2,0)
 
-        self.merge_button = QPushButton('For Anthology Epub', self)
-        self.merge_button.setToolTip('Get URLs and go to dialog for Anthology download.\nRequires EpubMerge 1.3.1+ plugin.')
+        self.merge_button = QPushButton(_('For Anthology Epub'), self)
+        self.merge_button.setToolTip(_('Get URLs and go to dialog for Anthology download.\nRequires %s plugin.')%'EpubMerge 1.3.1+')
         self.merge_button.clicked.connect(self.merge)
         self.l.addWidget(self.merge_button,2,1)
         self.merge_button.setEnabled(epubmerge_plugin!=None)
 
-        self.cancel_button = QPushButton('Cancel', self)
+        self.cancel_button = QPushButton(_('Cancel'), self)
         self.cancel_button.clicked.connect(self.cancel)
         self.l.addWidget(self.cancel_button,2,2)
 
@@ -471,29 +510,29 @@ class UserPassDialog(QDialog):
         self.setLayout(self.l)
 
         if exception.passwdonly:
-            self.setWindowTitle('Password')
-            self.l.addWidget(QLabel("Author requires a password for this story(%s)."%exception.url),0,0,1,2)
+            self.setWindowTitle(_('Password'))
+            self.l.addWidget(QLabel(_("Author requires a password for this story(%s).")%exception.url),0,0,1,2)
             # user isn't used, but it's easier to still have it for
             # post processing.
             self.user = FakeLineEdit()
         else:
-            self.setWindowTitle('User/Password')
-            self.l.addWidget(QLabel("%s requires you to login to download this story."%site),0,0,1,2)
+            self.setWindowTitle(_('User/Password'))
+            self.l.addWidget(QLabel(_("%s requires you to login to download this story.")%site),0,0,1,2)
         
-            self.l.addWidget(QLabel("User:"),1,0)
+            self.l.addWidget(QLabel(_("User:")),1,0)
             self.user = QLineEdit(self)
             self.l.addWidget(self.user,1,1)
    
-        self.l.addWidget(QLabel("Password:"),2,0)
+        self.l.addWidget(QLabel(_("Password:")),2,0)
         self.passwd = QLineEdit(self)
         self.passwd.setEchoMode(QLineEdit.Password)
         self.l.addWidget(self.passwd,2,1)
    
-        self.ok_button = QPushButton('OK', self)
+        self.ok_button = QPushButton(_('OK'), self)
         self.ok_button.clicked.connect(self.ok)
         self.l.addWidget(self.ok_button,3,0)
 
-        self.cancel_button = QPushButton('Cancel', self)
+        self.cancel_button = QPushButton(_('Cancel'), self)
         self.cancel_button.clicked.connect(self.cancel)
         self.l.addWidget(self.cancel_button,3,1)
 
@@ -515,9 +554,9 @@ class LoopProgressDialog(QProgressDialog):
                  book_list,
                  foreach_function,
                  finish_function,
-                 init_label="Fetching metadata for stories...",
-                 win_title="Downloading metadata for stories",
-                 status_prefix="Fetched metadata for"):
+                 init_label=_("Fetching metadata for stories..."),
+                 win_title=_("Downloading metadata for stories"),
+                 status_prefix=_("Fetched metadata for")):
         QProgressDialog.__init__(self,
                                  init_label,
                                  QString(), 0, len(book_list), gui)
@@ -535,9 +574,9 @@ class LoopProgressDialog(QProgressDialog):
         self.exec_()
 
     def updateStatus(self):
-        self.setLabelText("%s %d of %d"%(self.status_prefix,self.i+1,len(self.book_list)))
+        self.setLabelText("%s %d / %d"%(self.status_prefix,self.i+1,len(self.book_list)))
         self.setValue(self.i+1)
-        print(self.labelText())
+        #print(self.labelText())
 
     def do_loop(self):
 
@@ -558,7 +597,7 @@ class LoopProgressDialog(QProgressDialog):
         except Exception as e:
             book['good']=False
             book['comment']=unicode(e)
-            print("Exception: %s:%s"%(book,unicode(e)))
+            logger.error("Exception: %s:%s"%(book,unicode(e)))
             traceback.print_exc()
             
         self.updateStatus()
@@ -641,7 +680,7 @@ class UpdateExistingDialog(SizePersistedDialog):
         spacerItem = QtGui.QSpacerItem(20, 40, QtGui.QSizePolicy.Minimum, QtGui.QSizePolicy.Expanding)
         button_layout.addItem(spacerItem)
         self.remove_button = QtGui.QToolButton(self)
-        self.remove_button.setToolTip('Remove selected books from the list')
+        self.remove_button.setToolTip(_('Remove selected books from the list'))
         self.remove_button.setIcon(get_icon('list_remove.png'))
         self.remove_button.clicked.connect(self.remove_from_list)
         button_layout.addWidget(self.remove_button)
@@ -650,7 +689,7 @@ class UpdateExistingDialog(SizePersistedDialog):
 
         options_layout = QHBoxLayout()
 
-        groupbox = QGroupBox("Show Download Options")
+        groupbox = QGroupBox(_("Show Download Options"))
         groupbox.setCheckable(True)
         groupbox.setChecked(False)
         groupbox.setFlat(True)
@@ -667,7 +706,7 @@ class UpdateExistingDialog(SizePersistedDialog):
         gbf.setVisible(False)
         groupbox.toggled.connect(gbf.setVisible)
         
-        label = QLabel('Output &Format:')
+        label = QLabel(_('Output &Format:'))
         gbl.addWidget(label)
         self.fileform = QComboBox(self)
         self.fileform.addItem('epub')
@@ -675,30 +714,30 @@ class UpdateExistingDialog(SizePersistedDialog):
         self.fileform.addItem('html')
         self.fileform.addItem('txt')
         self.fileform.setCurrentIndex(self.fileform.findText(prefs['fileform']))
-        self.fileform.setToolTip('Choose output format to create.  May set default from plugin configuration.')
+        self.fileform.setToolTip(_('Choose output format to create.  May set default from plugin configuration.'))
         self.fileform.activated.connect(self.set_collisions)
         label.setBuddy(self.fileform)
         gbl.addWidget(self.fileform)
         
-        label = QLabel('Update Mode:')
+        label = QLabel(_('Update Mode:'))
         gbl.addWidget(label)
         self.collision = QComboBox(self)
-        self.collision.setToolTip("What sort of update to perform.  May set default from plugin configuration.")
+        self.collision.setToolTip(_("What sort of update to perform.  May set default from plugin configuration."))
         # add collision options
         self.set_collisions()
-        i = self.collision.findText(prefs['collision'])
+        i = self.collision.findText(save_collisions[prefs['collision']])
         if i > -1:
             self.collision.setCurrentIndex(i)
         label.setBuddy(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 = 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'])
         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 = 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'])
         gbl.addWidget(self.updateepubcover)
 
@@ -751,7 +790,7 @@ class StoryListTableWidget(QTableWidget):
         self.clear()
         self.setAlternatingRowColors(True)
         self.setRowCount(len(books))
-        header_labels = ['','Title', 'Author', 'URL', 'Comment']
+        header_labels = ['',_('Title'), _('Author'), 'URL', _('Comment')]
         self.setColumnCount(len(header_labels))
         self.setHorizontalHeaderLabels(header_labels)
         self.horizontalHeader().setStretchLastSection(True)
@@ -819,9 +858,9 @@ class StoryListTableWidget(QTableWidget):
         rows = self.selectionModel().selectedRows()
         if len(rows) == 0:
             return
-        message = '<p>Are you sure you want to remove this book from the list?'
+        message = '<p>'+_('Are you sure you want to remove this book from the list?')
         if len(rows) > 1:
-            message = '<p>Are you sure you want to remove the selected %d books from the list?'%len(rows)
+            message = '<p>'+_('Are you sure you want to remove the selected %d books from the list?')%len(rows)
         if not confirm(message,'fanfictiondownloader_delete_item', self):
             return
         first_sel_row = self.currentRow()
@@ -847,7 +886,7 @@ class RejectListTableWidget(QTableWidget):
         self.clear()
         self.setAlternatingRowColors(True)
         self.setRowCount(len(reject_list))
-        header_labels = ['URL', 'Title', 'Author', 'Note']
+        header_labels = ['URL', _('Title'), _('Author'), _('Note')]
         self.setColumnCount(len(header_labels))
         self.setHorizontalHeaderLabels(header_labels)
         self.horizontalHeader().setStretchLastSection(True)
@@ -889,7 +928,7 @@ class RejectListTableWidget(QTableWidget):
         note_cell.update_items_cache(items)
         note_cell.show_initial_value(rej.note)
         note_cell.set_separator(None)
-        note_cell.setToolTip('Select or Edit Reject Note.')
+        note_cell.setToolTip(_('Select or Edit Reject Note.'))
         self.setCellWidget(row, 3, note_cell)
         
     def remove_selected_rows(self):
@@ -897,9 +936,9 @@ class RejectListTableWidget(QTableWidget):
         rows = self.selectionModel().selectedRows()
         if len(rows) == 0:
             return
-        message = '<p>Are you sure you want to remove this URL from the list?'
+        message = '<p>'+_('Are you sure you want to remove this URL from the list?')
         if len(rows) > 1:
-            message = '<p>Are you sure you want to remove the %d selected URLs from the list?'%len(rows)
+            message = '<p>'+_('Are you sure you want to remove the %d selected URLs from the list?')%len(rows)
         if not confirm(message,'ffdl_rejectlist_delete_item_again', self):
             return
         first_sel_row = self.currentRow()
@@ -917,7 +956,7 @@ class RejectListTableWidget(QTableWidget):
 class RejectListDialog(SizePersistedDialog):
     def __init__(self, gui, reject_list,
                  rejectreasons=[],
-                 header="List of Books to Reject",
+                 header=_("List of Books to Reject"),
                  icon='rotate-right.png',
                  show_delete=True,
                  show_all_reasons=True,
@@ -930,7 +969,7 @@ class RejectListDialog(SizePersistedDialog):
         layout = QVBoxLayout(self)
         self.setLayout(layout)
         title_layout = ImageTitleLayout(self, icon, header,
-                                        '<i></i>FFDL will remember these URLs and display the note and offer to reject them if you try to download them again later.')
+                                        '<i></i>'+_('FFDL will remember these URLs and display the note and offer to reject them if you try to download them again later.'))
         layout.addLayout(title_layout)
         rejects_layout = QHBoxLayout()
         layout.addLayout(rejects_layout)
@@ -944,7 +983,7 @@ class RejectListDialog(SizePersistedDialog):
         button_layout.addItem(spacerItem)
         
         self.remove_button = QtGui.QToolButton(self)
-        self.remove_button.setToolTip('Remove selected URL(s) from the list')
+        self.remove_button.setToolTip(_('Remove selected URL(s) from the list'))
         self.remove_button.setIcon(get_icon('list_remove.png'))
         self.remove_button.clicked.connect(self.remove_from_list)
         button_layout.addWidget(self.remove_button)
@@ -962,11 +1001,11 @@ class RejectListDialog(SizePersistedDialog):
             self.reason_edit.update_items_cache(items)
             self.reason_edit.show_initial_value('')
             self.reason_edit.set_separator(None)
-            self.reason_edit.setToolTip("This will be added to whatever note you've set for each URL above.")
+            self.reason_edit.setToolTip(_("This will be added to whatever note you've set for each URL above."))
             
             horz = QHBoxLayout()
-            label = QLabel("Add this reason to all URLs added:")
-            label.setToolTip("This will be added to whatever note you've set for each URL above.")
+            label = QLabel(_("Add this reason to all URLs added:"))
+            label.setToolTip(_("This will be added to whatever note you've set for each URL above."))
             horz.addWidget(label)
             horz.addWidget(self.reason_edit)
             horz.insertStretch(-1)
@@ -975,8 +1014,8 @@ class RejectListDialog(SizePersistedDialog):
         options_layout = QHBoxLayout()
 
         if show_delete:
-            self.deletebooks = QCheckBox('Delete Books (including books without FanFiction URLs)?',self)
-            self.deletebooks.setToolTip("Delete the selected books after adding them to the Rejected URLs list.")
+            self.deletebooks = QCheckBox(_('Delete Books (including books without FanFiction URLs)?'),self)
+            self.deletebooks.setToolTip(_("Delete the selected books after adding them to the Rejected URLs list."))
             self.deletebooks.setChecked(True)
             options_layout.addWidget(self.deletebooks)
         

calibre-plugin/jobs.py

@@ -8,6 +8,9 @@ __copyright__ = '2012, Jim Miller'
 __copyright__ = '2011, Grant Drake <grant.drake@gmail.com>'
 __docformat__ = 'restructuredtext en'
 
+import logging
+logger = logging.getLogger(__name__)
+
 import time, os, traceback
 
 from StringIO import StringIO
@@ -38,13 +41,13 @@ def do_download_worker(book_list, options,
     '''
     server = Server(pool_size=cpus)
 
-    print(options['version'])
+    logger.info(options['version'])
     total = 0
     alreadybad = []
     # Queue all the jobs
-    print("Adding jobs for URLs:")
+    logger.info("Adding jobs for URLs:")
     for book in book_list:
-        print("%s"%book['url'])
+        logger.info("%s"%book['url'])
         if book['good']:
             total += 1
             args = ['calibre_plugins.fanfictiondownloader_plugin.jobs',
@@ -87,19 +90,16 @@ def do_download_worker(book_list, options,
         count = count + 1
         notification(float(count)/total, '%d of %d stories finished downloading'%(count,total))
         # Add this job's output to the current log
-        print('Logfile for book ID %s (%s)'%(book_id, job._book['title']))
-        print(job.details)
+        logger.info('Logfile for book ID %s (%s)'%(book_id, job._book['title']))
+        logger.info(job.details)
+
+
 
         if count >= total:
-            # All done!  Output some lists for convenience of some users.
-            print("Successfully downloaded:")
-            for book in book_list:
-                if book['good']:
-                    print("%s %s"%(book['title'],book['url']))
-            print("\nUnsuccessful:")
-            for book in book_list:
-                if not book['good']:
-                    print("%s %s"%(book['title'],book['url']))
+            logger.info("\nSuccessful:\n%s\n"%("\n".join([book['url'] for book in 
+                                                      filter(lambda x: x['good'], book_list) ] ) ) )
+            logger.info("\nUnsuccessful:\n%s\n"%("\n".join([book['url'] for book in 
+                                                        filter(lambda x: not x['good'], book_list) ] ) ) )
             break
 
     server.close()
@@ -147,7 +147,7 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
 
         ## No need to download at all.  Shouldn't ever get down here.
         if options['collision'] in (CALIBREONLY):
-            print("Skipping CALIBREONLY 'update' down inside worker--this shouldn't be happening...")
+            logger.info("Skipping CALIBREONLY 'update' down inside worker--this shouldn't be happening...")
             book['comment'] = 'Metadata collected.'
             
         ## checks were done earlier, it's new or not dup or newer--just write it.
@@ -170,7 +170,7 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
                 if adapter.logfile:
                     adapter.logfile = adapter.logfile.replace("span id","span notid")
             
-            print("write to %s"%outfile)
+            logger.info("write to %s"%outfile)
             writer.writeStory(outfilename=outfile, forceOverwrite=True)
             book['comment'] = 'Download %s completed, %s chapters.'%(options['fileform'],story.getMetadata("numChapters"))
             
@@ -179,7 +179,7 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
 
             # update now handled by pre-populating the old images and
             # chapters in the adapter rather than merging epubs.
-            urlchaptercount = int(story.getMetadata('numChapters'))
+            urlchaptercount = int(story.getMetadata('numChapters').replace(',',''))
             (url,
              chaptercount,
              adapter.oldchapters,
@@ -198,9 +198,13 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
             # dup handling from ffdl_plugin needed for anthology updates.
             if chaptercount > urlchaptercount:
                 raise NotGoingToDownload("Existing epub contains %d chapters, web site only has %d. Use Overwrite to force update." % (chaptercount,urlchaptercount),'dialog_error.png')
-                            
-            print("Do update - epub(%d) vs url(%d)" % (chaptercount, urlchaptercount))
-            print("write to %s"%outfile)
+
+            if not (options['collision'] == UPDATEALWAYS and chaptercount == urlchaptercount) \
+                    and adapter.getConfig("do_update_hook"):
+                chaptercount = adapter.hookForUpdates(chaptercount)
+
+            logger.info("Do update - epub(%d) vs url(%d)" % (chaptercount, urlchaptercount))
+            logger.info("write to %s"%outfile)
 
             writer.writeStory(outfilename=outfile, forceOverwrite=True)
             
@@ -222,7 +226,7 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
             
             log = Log(level=Log.DEBUG)
             # report = []
-            polish({outfile:outfile}, opts, log, print) # report.append
+            polish({outfile:outfile}, opts, log, logger.info) # report.append
         
     except NotGoingToDownload as d:
         book['good']=False
@@ -234,7 +238,7 @@ def do_download_for_worker(book,options,notification=lambda x,y:x):
         book['comment']=unicode(e)
         book['icon']='dialog_error.png'
         book['status'] = 'Error'
-        print("Exception: %s:%s"%(book,unicode(e)))
+        logger.info("Exception: %s:%s"%(book,unicode(e)))
         traceback.print_exc()
         
     #time.sleep(10)

calibre-plugin/prefs.py

@@ -30,7 +30,11 @@ default_prefs['updatemeta'] = True
 default_prefs['updatecover'] = False
 default_prefs['updateepubcover'] = False
 default_prefs['keeptags'] = False
+default_prefs['suppressauthorsort'] = False
+default_prefs['suppresstitlesort'] = False
+default_prefs['mark'] = False
 default_prefs['showmarked'] = False
+default_prefs['autoconvert'] = False
 default_prefs['urlsfromclip'] = True
 default_prefs['updatedefault'] = True
 default_prefs['fileform'] = 'epub'
@@ -40,6 +44,7 @@ default_prefs['adddialogstaysontop'] = False
 default_prefs['includeimages'] = False
 default_prefs['lookforurlinhtml'] = False
 default_prefs['checkforseriesurlid'] = True
+default_prefs['checkforurlchange'] = True
 default_prefs['injectseries'] = False
 default_prefs['smarten_punctuation'] = False
 
@@ -52,6 +57,7 @@ default_prefs['addtolistsonread'] = False
 default_prefs['gcnewonly'] = False
 default_prefs['gc_site_settings'] = {}
 default_prefs['allow_gc_from_ini'] = True
+default_prefs['gc_polish_cover'] = False
 
 default_prefs['countpagesstats'] = []
 

downloader.py

@@ -137,6 +137,9 @@ def main(argv,
    if options.update:
        try:
            (url,chaptercount) = get_dcsource_chaptercount(args[0])
+           if not url:
+               print "No story URL found in epub to update."
+               return
            print "Updating %s, URL: %s" % (args[0],url)
            output_filename = args[0]
        except:
@@ -145,8 +148,15 @@ def main(argv,
            url = args[0]
    else:
        url = args[0]
-           
-   configuration = Configuration(adapters.getConfigSectionFor(url),options.format)
+
+   try:
+       configuration = Configuration(adapters.getConfigSectionFor(url),options.format)
+   except exceptions.UnknownSite, e:
+       if options.list or options.normalize:
+           # list for page doesn't have to be a supported site.
+           configuration = Configuration("test1.com",options.format)
+       else:
+           raise e
 
    conflist = []
    homepath = join(expanduser("~"),".fanficdownloader")
@@ -199,8 +209,7 @@ def main(argv,
 
    if options.list or options.normalize:
        retlist = get_urls_from_page(args[0], configuration, normalize=options.normalize)
-       print "\n".join(retlist)
-               
+       print "\n".join(retlist)               
        return
 
    try:
@@ -258,22 +267,27 @@ def main(argv,
                print "%s already contains %d chapters." % (output_filename,chaptercount)
            elif chaptercount > urlchaptercount:
                print "%s contains %d chapters, more than source: %d." % (output_filename,chaptercount,urlchaptercount)
+           elif chaptercount == 0:
+               print "%s doesn't contain any recognizable chapters, probably from a different source.  Not updating." % (output_filename)
            else:
+               # update now handled by pre-populating the old
+               # images and chapters in the adapter rather than
+               # merging epubs.
+               (url,
+                chaptercount,
+                adapter.oldchapters,
+                adapter.oldimgs,
+                adapter.oldcover,
+                adapter.calibrebookmark,
+                adapter.logfile) = get_update_data(output_filename)
+
                print "Do update - epub(%d) vs url(%d)" % (chaptercount, urlchaptercount)
-               if not options.metaonly:
 
-                   # update now handled by pre-populating the old
-                   # images and chapters in the adapter rather than
-                   # merging epubs.
-                   (url,
-                    chaptercount,
-                    adapter.oldchapters,
-                    adapter.oldimgs,
-                    adapter.oldcover,
-                    adapter.calibrebookmark,
-                    adapter.logfile) = get_update_data(output_filename)
+               if not (options.update and chaptercount == urlchaptercount) \
+                       and adapter.getConfig("do_update_hook"):
+                   chaptercount = adapter.hookForUpdates(chaptercount)
 
-                   writeStory(configuration,adapter,"epub")
+               writeStory(configuration,adapter,"epub")
                    
        else:
            # regular download

fanficdownloader/HtmlTagStack.py

@@ -0,0 +1,57 @@
+# coding: utf-8
+
+import re
+import codecs
+
+stack = []
+
+def get_end_tag(tag):
+    if len(tag) > 0 and tag.find(u'<') > -1 and tag.rfind(u'>') > -1:
+        return re.sub(r'.*<([^\ >]+).*', r'</\1>', tag)
+    return u''
+
+def get_tag_name(tag):
+    if len(tag) > 0 and tag.find(u'<') > -1 and tag.rfind(u'>') > -1:
+        return re.sub(r'</*([^\ >]+).*', r'\1', tag)
+    return u''
+
+def push(tag):
+    if len(tag) > 0 and tag.find(u'<') > -1 and tag.rfind(u'>') > -1:
+        stack.append(tag)
+
+def pop():
+    if len(stack) > 0:
+        return stack.pop()
+    return u''
+
+def pop_end_tag():
+    return unicode(get_end_tag(pop()))
+
+def spool_end():
+    html = u''
+    for tag in reversed(stack):
+        html += get_end_tag(tag)
+    return html
+
+def spool_start():
+    html = u''
+    for item in stack:
+        html += item
+    return html
+
+def has_elements():
+    return len(stack) > 0
+
+def get_last():
+    # t = pop()
+    # push(t)
+    # return t
+    if len(stack) > 0:
+        return stack[len(stack)-1]
+    return u''
+
+def flush():
+    del stack[:]
+
+def get_stack():
+    return stack

fanficdownloader/__init__.py

@@ -4,13 +4,16 @@ try:
     # just a way to switch between web service and CLI/PI
     import google.appengine.api 
 except:
-    import sys
-    if sys.version_info >= (2, 7):
-        import logging
-        logger = logging.getLogger(__name__)
-        loghandler=logging.StreamHandler()
-        loghandler.setFormatter(logging.Formatter("FFDL:%(levelname)s:%(filename)s(%(lineno)d):%(message)s"))
-        logger.addHandler(loghandler)
-        loghandler.setLevel(logging.DEBUG)
-        logger.setLevel(logging.DEBUG)
+    try: # just a way to switch between CLI and PI
+        import calibre.constants
+    except:
+        import sys
+        if sys.version_info >= (2, 7):
+            import logging
+            logger = logging.getLogger(__name__)
+            loghandler=logging.StreamHandler()
+            loghandler.setFormatter(logging.Formatter("FFDL:%(levelname)s:%(filename)s(%(lineno)d):%(message)s"))
+            logger.addHandler(loghandler)
+            loghandler.setLevel(logging.DEBUG)
+            logger.setLevel(logging.DEBUG)
 

fanficdownloader/adapters/__init__.py

@@ -119,6 +119,10 @@ import adapter_nickandgregnet
 import adapter_potterheadsanonymouscom
 import adapter_simplyundeniablecom
 import adapter_scarheadnet
+import adapter_fictionpadcom
+import adapter_storiesonlinenet
+import adapter_trekiverseorg
+import adapter_literotica
 
 ## This bit of complexity allows adapters to be added by just adding
 ## importing.  It eliminates the long if/else clauses we used to need
@@ -126,6 +130,7 @@ import adapter_scarheadnet
     
 ## List of registered site adapters.
 __class_list = []
+__domain_map = {}
 
 def imports():
     for name, val in globals().items():
@@ -135,9 +140,19 @@ def imports():
 for x in imports():
     if "fanficdownloader.adapters.adapter_" in x:
         #print x
-        __class_list.append(sys.modules[x].getClass())
+        cls = sys.modules[x].getClass()
+        __class_list.append(cls)
+        for site in cls.getAcceptDomains():
+            __domain_map[site]=cls
 
 def getNormalStoryURL(url):
+    r = getNormalStoryURLSite(url)
+    if r:
+        return r[0]
+    else:
+        return None
+
+def getNormalStoryURLSite(url):
     if not getNormalStoryURL.__dummyconfig:
         getNormalStoryURL.__dummyconfig = Configuration("test1.com","EPUB")
     # pulling up an adapter is pretty low over-head.  If
@@ -145,20 +160,23 @@ def getNormalStoryURL(url):
     try:
         adapter = getAdapter(getNormalStoryURL.__dummyconfig,url)
         url = adapter.url
+        site = adapter.getSiteDomain()
         del adapter
-        return url
+        return (url,site)
     except:
-        return None;
+        return None
 
 # kludgey function static/singleton
 getNormalStoryURL.__dummyconfig = None
 
-def getAdapter(config,url):
+def getAdapter(config,url,anyurl=False):
 
     #logger.debug("trying url:"+url)
     (cls,fixedurl) = getClassFor(url)
     #logger.debug("fixedurl:"+fixedurl)
     if cls:
+        if anyurl:
+            fixedurl = cls.getSiteExampleURLs().split()[0]
         adapter = cls(config,fixedurl) # raises InvalidStoryURL
         return adapter
     # No adapter found.
@@ -183,7 +201,7 @@ def getConfigSectionFor(url):
 
 def getClassFor(url):
     ## fix up leading protocol.
-    fixedurl = re.sub(r"(?i)^[htps]+[:/]+","http://",url.strip())
+    fixedurl = re.sub(r"(?i)^[htp]+(s?)[:/]+",r"http\1://",url.strip())
     if not fixedurl.startswith("http"):
         fixedurl = "http://%s"%url
     ## remove any trailing '#' locations.
@@ -204,12 +222,14 @@ def getClassFor(url):
         #logger.debug("trying site:www."+domain)
         cls = getClassFromList("www."+domain)
         fixedurl = fixedurl.replace("http://","http://www.")
-        
-    fixedurl = cls.stripURLParameters(fixedurl)
+
+    if cls:
+        fixedurl = cls.stripURLParameters(fixedurl)
     
     return (cls,fixedurl)
     
 def getClassFromList(domain):
-    for cls in __class_list:
-        if cls.matchesSite(domain):
-            return cls
+    try:
+        return __domain_map[domain]
+    except KeyError:
+        pass # return none.

fanficdownloader/adapters/adapter_adastrafanficcom.py

@@ -42,7 +42,7 @@ class AdAstraFanficComSiteAdapter(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() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -90,7 +90,7 @@ class AdAstraFanficComSiteAdapter(BaseSiteAdapter):
 
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php"))

fanficdownloader/adapters/adapter_archiveofourownorg.py

@@ -51,13 +51,13 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
         
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])
-        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
         
         # get storyId from url--url validation guarantees query correct
         m = re.match(self.getSiteURLPattern(),url)
         if m:
             self.story.setMetadata('storyId',m.group('id'))
-            logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+            
             # normalized story URL.
             self._setURL('http://' + self.getSiteDomain() + '/works/'+self.story.getMetadata('storyId'))
         else:
@@ -77,14 +77,14 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
         # The site domain.  Does have www here, if it uses it.
         return 'archiveofourown.org'
 
-    @classmethod
+    @classmethod
     def getSiteExampleURLs(self):
         return "http://"+self.getSiteDomain()+"/works/123456 http://"+self.getSiteDomain()+"/collections/Some_Archive/works/123456 http://"+self.getSiteDomain()+"/works/123456/chapters/78901"
 
     def getSiteURLPattern(self):
         # http://archiveofourown.org/collections/Smallville_Slash_Archive/works/159770
         # Discard leading zeros from story ID numbers--AO3 doesn't use them in it's own chapter URLs.
-        return re.escape("http://")+re.escape(self.getSiteDomain())+r"(/collections/[^/]+)?/works/0*(?P<id>\d+)"
+        return r"https?://"+re.escape(self.getSiteDomain())+r"(/collections/[^/]+)?/works/0*(?P<id>\d+)"
         
     ## Login
     def needToLoginCheck(self, data):
@@ -163,7 +163,7 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r"^/works/\d+$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
 		
         # Find authorid and URL from... author url.
         alist = soup.findAll('a', href=re.compile(r"^/users/\w+/pseuds/\w+"))
@@ -177,19 +177,28 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
                 self.story.addToList('authorUrl','http://'+self.host+a['href'])
                 self.story.addToList('author',a.text)
 
+        newestChapter = None
+        self.newestChapterNum = None # save for comparing during update.
+        # Scan all chapters to find the oldest and newest, on AO3 it's
+        # possible for authors to insert new chapters out-of-order or
+        # change the dates of earlier ones by editing them--That WILL
+        # break epub update.
         # Find the chapters:
         chapters=soup.findAll('a', href=re.compile(r'/works/'+self.story.getMetadata('storyId')+"/chapters/\d+$"))
         self.story.setMetadata('numChapters',len(chapters))
         logger.debug("numChapters: (%s)"%self.story.getMetadata('numChapters'))
-        for x in range(0,len(chapters)):
-            # just in case there's tags, like <i> in chapter titles.
-            chapter=chapters[x]
-            if len(chapters)==1:
-                self.chapterUrls.append((self.story.getMetadata('title'),'http://'+self.host+chapter['href']+addurl))
-            else:
+        if len(chapters)==1:
+            self.chapterUrls.append((self.story.getMetadata('title'),'http://'+self.host+chapters[0]['href']+addurl))
+        else:
+            for index, chapter in enumerate(chapters):
+                # strip just in case there's tags, like <i> in chapter titles.
                 self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+chapter['href']+addurl))
-
-
+                # (2013-09-21)
+                date = stripHTML(chapter.findNext('span'))[1:-1]
+                chapterDate = makeDate(date,self.dateformat)
+                if newestChapter == None or chapterDate > newestChapter:
+                    newestChapter = chapterDate
+                    self.newestChapterNum = index
 
         a = metasoup.find('blockquote',{'class':'userstuff'})
         if a != None:
@@ -210,10 +219,7 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
         if a != None:
             warnings = a.findAll('a',{'class':"tag"})
             for warning in warnings:
-                if warning.string == "Author Chose Not To Use Archive Warnings":
-                    warning.string = "No Archive Warnings Apply"
-                if warning.string != "No Archive Warnings Apply":
-                    self.story.addToList('warnings',warning.string)
+                self.story.addToList('warnings',warning.string)
 		
         a = metasoup.find('dd',{'class':"freeform tags"})
         if a != None:
@@ -288,46 +294,58 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
                 self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
 
 		
-        try:
-            # Find Series name from series URL.
-            a = metasoup.find('dd',{'class':"series"})
-            b = a.find('a', href=re.compile(r"/series/\d+"))
-            series_name = b.string
-            series_url = 'http://'+self.host+b['href']
-            series_index = int(a.text.split(' ')[1])
-            self.setSeries(series_name, series_index)
-            self.story.setMetadata('seriesUrl',series_url)
-            
-        except:
-            # I find it hard to care if the series parsing fails
-            pass
+        # Find Series name from series URL.
+        ddseries = metasoup.find('dd',{'class':"series"})
 
+        if ddseries:
+            for i, a in enumerate(ddseries.findAll('a', href=re.compile(r"/series/\d+"))):
+                series_name = stripHTML(a)
+                series_url = 'http://'+self.host+a['href']
+                series_index = int(stripHTML(a.previousSibling).replace(', ','').split(' ')[1]) # "Part # of" or ", Part #"
+                self.story.setMetadata('series%02d'%i,"%s [%s]"%(series_name,series_index))
+                self.story.setMetadata('series%02dUrl'%i,series_url)
+                if i == 0:
+                    self.setSeries(series_name, series_index)
+                    self.story.setMetadata('seriesUrl',series_url)
+
+    def hookForUpdates(self,chaptercount):
+        if self.oldchapters and len(self.oldchapters) > self.newestChapterNum:
+            print("Existing epub has %s chapters\nNewest chapter is %s.  Discarding old chapters from there on."%(len(self.oldchapters), self.newestChapterNum+1))
+            self.oldchapters = self.oldchapters[:self.newestChapterNum]
+        return len(self.oldchapters)
+            
     # grab the text for an individual chapter.
     def getChapterText(self, url):
         logger.debug('Getting chapter text from: %s' % url)
 		
-        chapter=bs.BeautifulSoup('<div class="story"></div>')
+        chapter=bs.BeautifulSoup('<div class="story"></div>').find('div')
         data = self._fetchUrl(url)
         soup = bs.BeautifulSoup(data,selfClosingTags=('br','hr'))
-		
-        headnotes = soup.find('div', {'class' : "preface group"}).find('div', {'class' : "notes module"})
-        if headnotes != None:
-            headnotes = headnotes.find('blockquote', {'class' : "userstuff"})
+
+        exclude_notes=self.getConfigList('exclude_notes')
+
+        if 'authorheadnotes' not in exclude_notes:
+            headnotes = soup.find('div', {'class' : "preface group"}).find('div', {'class' : "notes module"})
             if headnotes != None:
-                chapter.append("<b>Author's Note:</b>")
-                chapter.append(headnotes)
+                headnotes = headnotes.find('blockquote', {'class' : "userstuff"})
+                if headnotes != None:
+                    chapter.append("<b>Author's Note:</b>")
+                    chapter.append(headnotes)
         
-        chapsumm = soup.find('div', {'id' : "summary"})
-        if chapsumm != None:
-            chapsumm = chapsumm.find('blockquote')
-            chapter.append("<b>Summary for the Chapter:</b>")
-            chapter.append(chapsumm)
-        chapnotes = soup.find('div', {'id' : "notes"})
-        if chapnotes != None:
-            chapnotes = chapnotes.find('blockquote')
+        if 'chaptersummary' not in exclude_notes:
+            chapsumm = soup.find('div', {'id' : "summary"})
+            if chapsumm != None:
+                chapsumm = chapsumm.find('blockquote')
+                chapter.append("<b>Summary for the Chapter:</b>")
+                chapter.append(chapsumm)
+                
+        if 'chapterheadnotes' not in exclude_notes:
+            chapnotes = soup.find('div', {'id' : "notes"})
             if chapnotes != None:
-                chapter.append("<b>Notes for the Chapter:</b>")
-                chapter.append(chapnotes)
+                chapnotes = chapnotes.find('blockquote')
+                if chapnotes != None:
+                    chapter.append("<b>Notes for the Chapter:</b>")
+                    chapter.append(chapnotes)
 		
         text = soup.find('div', {'class' : "userstuff module"})
         chtext = text.find('h3', {'class' : "landmark heading"})
@@ -335,17 +353,19 @@ class ArchiveOfOurOwnOrgAdapter(BaseSiteAdapter):
             chtext.extract()
         chapter.append(text)
 		
-        chapfoot = soup.find('div', {'class' : "end notes module", 'role' : "complementary"})
-        if chapfoot != None:
-            chapfoot = chapfoot.find('blockquote')
-            chapter.append("<b>Notes for the Chapter:</b>")
-            chapter.append(chapfoot)
+        if 'chapterfootnotes' not in exclude_notes:
+            chapfoot = soup.find('div', {'class' : "end notes module", 'role' : "complementary"})
+            if chapfoot != None:
+                chapfoot = chapfoot.find('blockquote')
+                chapter.append("<b>Notes for the Chapter:</b>")
+                chapter.append(chapfoot)
 		
-        footnotes = soup.find('div', {'id' : "work_endnotes"})
-        if footnotes != None:
-            footnotes = footnotes.find('blockquote')
-            chapter.append("<b>Author's Note:</b>")
-            chapter.append(footnotes)
+        if 'authorfootnotes' not in exclude_notes:
+            footnotes = soup.find('div', {'id' : "work_endnotes"})
+            if footnotes != None:
+                footnotes = footnotes.find('blockquote')
+                chapter.append("<b>Author's Note:</b>")
+                chapter.append(footnotes)
 			
         if None == soup:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)

fanficdownloader/adapters/adapter_archiveskyehawkecom.py

@@ -49,7 +49,7 @@ class ArchiveSkyeHawkeComAdapter(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() + '/story.php?no='+self.story.getMetadata('storyId'))
@@ -101,7 +101,7 @@ class ArchiveSkyeHawkeComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('div', {'class':"story border"}).find('span',{'class':'left'})
-        title=a.text.split('"')[1]
+        title=stripHTML(a).split('"')[1]
         self.story.setMetadata('title',title)
         
         # Find authorid and URL from... author url.

fanficdownloader/adapters/adapter_ashwindersycophanthexcom.py

@@ -48,7 +48,7 @@ class AshwinderSycophantHexComAdapter(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.
@@ -157,7 +157,7 @@ class AshwinderSycophantHexComAdapter(BaseSiteAdapter):
         for info in asoup.findAll('table', {'width' : '100%', 'bordercolor' : re.compile(r'#')}):
             a = info.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
             if a != None:
-                self.story.setMetadata('title',a.string)
+                self.story.setMetadata('title',stripHTML(a))
                 break
 		
 

fanficdownloader/adapters/adapter_asr3slashzoneorg.py

@@ -46,7 +46,7 @@ class Asr3SlashzoneOrgAdapter(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() + '/archive/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -128,7 +128,7 @@ class Asr3SlashzoneOrgAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_bloodtiesfancom.py

@@ -70,7 +70,7 @@ class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX
         
         # 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.
@@ -207,7 +207,7 @@ class BloodTiesFansComAdapter(BaseSiteAdapter): # XXX
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_buffynfaithnet.py

@@ -58,7 +58,7 @@ class BuffyNFaithNetAdapter(BaseSiteAdapter):
         m = re.match(self.getSiteURLPattern(),url)
         if m:
             self.story.setMetadata('storyId',m.group('id'))
-            logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+            
             # normalized story URL. gets rid of chapter if there, left with ch 1 URL on this site
             nurl = "http://"+self.getSiteDomain()+"/fanfictions/index.php?act=vie&id="+self.story.getMetadata('storyId')
             self._setURL(nurl)
@@ -69,7 +69,7 @@ class BuffyNFaithNetAdapter(BaseSiteAdapter):
             raise exceptions.InvalidStoryURL(url,
                                              self.getSiteDomain(),
                                              self.getSiteExampleURLs())
-        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
         
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','bnfnet')
@@ -87,7 +87,7 @@ class BuffyNFaithNetAdapter(BaseSiteAdapter):
     
     def setHeader(self):
         "buffynfaith.net wants a Referer for images.  Used both above and below(after cookieproc added)"
-        self.opener.addheaders = [('Referer', 'http://'+self.getSiteDomain()+'/')]
+        self.opener.addheaders.append(('Referer', 'http://'+self.getSiteDomain()+'/'))
         
     @classmethod
     def getSiteExampleURLs(self):

fanficdownloader/adapters/adapter_castlefansorg.py

@@ -72,7 +72,7 @@ class CastleFansOrgAdapter(BaseSiteAdapter): # XXX
         
         # 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.
@@ -180,7 +180,7 @@ class CastleFansOrgAdapter(BaseSiteAdapter): # XXX
         pagetitle = soup.find('div',{'id':'pagetitle'})
         ## Title
         a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_chaossycophanthexcom.py

@@ -48,7 +48,7 @@ class ChaosSycophantHexComAdapter(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.
@@ -116,7 +116,7 @@ class ChaosSycophantHexComAdapter(BaseSiteAdapter):
         ## Title
         pt = soup.find('div', {'id' : 'pagetitle'})
         a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.text)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = pt.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_checkmatedcom.py

@@ -48,7 +48,7 @@ class CheckmatedComAdapter(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'))
+        
 
         self._setURL('http://' + self.getSiteDomain() + '/story.php?story='+self.story.getMetadata('storyId'))
 
@@ -143,11 +143,11 @@ class CheckmatedComAdapter(BaseSiteAdapter):
         # Now go hunting for all the meta data and the chapter list.
 
         ## Title
-        a = soup.findAll('span', {'class' : 'storytitle'})
-        self.story.setMetadata('title',a[0].string)
+        a = soup.find('span', {'class' : 'storytitle'})
+        self.story.setMetadata('title',stripHTML(a))
 
         # Find authorid and URL from... author url.
-        a = a[1].find('a', href=re.compile(r"authors.php\?name\=\w+"))
+        a = a.parent.find('a', href=re.compile(r"authors.php\?name\=\w+"))
         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_darksolaceorg.py

@@ -48,7 +48,7 @@ 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'))
@@ -94,11 +94,10 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
         else:
             params['penname'] = self.getConfig("username")
             params['password'] = self.getConfig("password")
-        params['rememberme'] = '1'
         params['action'] = 'login'
         params['submit'] = 'Submit'
     
-        loginUrl = 'http://' + self.getSiteDomain() + '/elysian/user.php'
+        loginUrl = 'http://www.' + self.getSiteDomain() + '/elysian/user.php'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['penname']))
     
@@ -184,31 +183,31 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
         # 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+"&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')))
+        storylink = asoup.find('a', href=re.compile(r'viewstory.php\?sid='+
+                                                    self.story.getMetadata('storyId')+'($|[^\d])'))
+        # author's story list is paginated if there's a pagelinks div.
+        # Only need to look in it if the story wasn't on the first page.
+        pagelinks = asoup.find('div',{'id':'pagelinks'})
+        if pagelinks and storylink==None:
+            authpageslist = pagelinks.findAll('a',href=re.compile(r'action=storiesby'))
+            for page in authpageslist[1:]: # skip first, already checked above.
+                asoup = bs.BeautifulSoup(self._fetchUrl('http://'+self.host+'/elysian/'+page['href']))
+                storylink = asoup.find('a', href=re.compile(r'viewstory.php\?sid='+
+                                                            self.story.getMetadata('storyId')+'($|[^\d])'))
+                if storylink:
+                    break
+
+        if not storylink:
+            raise exceptions.FailedToDownload("Unable to find story metadata on author's page(s)")
         
-        # 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
-
+        metalist = storylink.parent.parent
         # eFiction sites don't help us out a lot with their meta data
         # formating, so it's a little ugly.
 
@@ -229,7 +228,7 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
             if 'Summary' in label:
                 ## Everything until the next span class='label'
                 svalue = ""
-                while not (defaultGetattr(value,'class') == 'label' or "Chapters: " in stripHTML(value)):
+                while value and not (defaultGetattr(value,'class') == 'label' or "Chapters: " in stripHTML(value)):
                     svalue += str(value)
                     value = value.nextSibling
                 self.setDescription(url,svalue)
@@ -284,20 +283,40 @@ class DarkSolaceOrgAdapter(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+'))
-            i=1
-            for a in storyas:
-                # skip 'report this' and 'TOC' links
-                if 'contact.php' not in a['href'] and 'index' not in a['href']:
-                    if ('viewstory.php?sid='+self.story.getMetadata('storyId')) in a['href']:
-                        self.setSeries(series_name, i)
-                        self.story.setMetadata('seriesUrl',series_url)
+            storylink = seriessoup.find('a', href=re.compile(r'viewstory.php\?sid='+
+                                                             self.story.getMetadata('storyId')+'($|[^\d])'))
+            if storylink and storylink.parent and storylink.parent['class'] != 'title': # in case of links inside story summaries.
+                storylink = None
+
+            offset = 0
+            # series story list is paginated if there's a pagelinks div.
+            # Only need to look in it if the story wasn't on the first page.
+            pagelinks = seriessoup.find('div',{'id':'pagelinks'})
+            if pagelinks and storylink==None:
+                authpageslist = pagelinks.findAll('a',href=re.compile(r'offset='))
+                for page in authpageslist[1:]: # skip first, already checked above.
+                    seriessoup = bs.BeautifulSoup(self._fetchUrl('http://'+self.host+'/elysian/'+page['href']))
+                    storylink = seriessoup.find('a', href=re.compile(r'viewstory.php\?sid='+
+                                                                     self.story.getMetadata('storyId')+'($|[^\d])'))
+                    if storylink and storylink.parent and storylink.parent['class'] != 'title': # in case of links inside story summaries.
+                        storylink = None
+                    if storylink:
+                        offset = int(page['href'].split('=')[-1]) # offset is last.
                         break
-                    i+=1
+
+            # for reasons I don't understand, searching for story
+            # links by regex wasn't working reliably.  It was missing
+            # the javascript links sometimes.  This is cleaner anyway.
+            for i, div in enumerate(seriessoup.findAll('div', {'class':'title'})):
+                a = div.find('a') # first a is story link.
+                # skip 'report this' and 'TOC' links
+                if a == storylink:
+                    self.setSeries(series_name, 1+i+offset)
+                    self.story.setMetadata('seriesUrl',series_url)
+                    break
             
-        except:
-            # I find it hard to care if the series parsing fails
-            pass
+        except Exception, e:
+            print("Series parsing failed: %s"%e)
             
     # grab the text for an individual chapter.
     def getChapterText(self, url):

fanficdownloader/adapters/adapter_destinysgatewaycom.py

@@ -48,7 +48,7 @@ class DestinysGatewayComAdapter(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() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -131,7 +131,7 @@ class DestinysGatewayComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_dokugacom.py

@@ -48,7 +48,7 @@ class DokugaComAdapter(BaseSiteAdapter):
         
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[3])
-        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
 
         # www.dokuga.com has two 'sections', shown in URL as
         # 'fanfiction' and 'spark' that change how things should be
@@ -164,7 +164,7 @@ class DokugaComAdapter(BaseSiteAdapter):
         aut.extract()
         
         a = a.string[:(len(a.string)-4)]
-        self.story.setMetadata('title',a)
+        self.story.setMetadata('title',stripHTML(a))
 
         # Find the chapters:
         chapters = soup.find('select').findAll('option')
@@ -205,7 +205,6 @@ class DokugaComAdapter(BaseSiteAdapter):
             
             a=div.text.split('Category: ')
             if len(a) == 2: self.story.addToList('category', a[1].split('&')[0])
-            self.story.addToList('category', 'Fanfiction')
         
             a=div.text.split('Created: ')
             if len(a) == 2: self.story.setMetadata('datePublished', makeDate(stripHTML(a[1].split('&')[0]), self.dateformat))

fanficdownloader/adapters/adapter_dotmoonnet.py

@@ -48,7 +48,7 @@ class DotMoonNetAdapter(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. www.dotmoon.net/library_view.php?storyid=3
         self._setURL('http://' + self.getSiteDomain() + '/library_view.php?storyid='+self.story.getMetadata('storyId'))
@@ -141,7 +141,7 @@ class DotMoonNetAdapter(BaseSiteAdapter):
         
         ## Title
         a = body.find('b')
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url. http://www.dotmoon.net/board/index.php?action=profile;u=1'
         a = body.find('a', href=re.compile(r"index.php\?action=profile;u=\d+"))

fanficdownloader/adapters/adapter_dracoandginnycom.py

@@ -48,7 +48,7 @@ class DracoAndGinnyComAdapter(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() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -170,7 +170,7 @@ class DracoAndGinnyComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_dramioneorg.py

@@ -48,7 +48,7 @@ class DramioneOrgAdapter(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() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -154,7 +154,7 @@ class DramioneOrgAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_efictionestelielde.py

@@ -48,7 +48,7 @@ class EfictionEstelielDeAdapter(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() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -104,7 +104,7 @@ class EfictionEstelielDeAdapter(BaseSiteAdapter):
         pagetitle = soup.find('div',{'id':'pagetitle'})
         ## Title
         a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_efpfanficnet.py

@@ -48,7 +48,7 @@ class EFPFanFicNet(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() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -166,7 +166,7 @@ class EFPFanFicNet(BaseSiteAdapter):
         logger.debug("Normalizing to URL: "+url)
         self._setURL(url)
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
-        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
 
         # eFiction sites don't help us out a lot with their meta data
         # formating, so it's a little ugly.

fanficdownloader/adapters/adapter_erosnsapphosycophanthexcom.py

@@ -48,7 +48,7 @@ class ErosnSapphoSycophantHexComAdapter(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.
@@ -132,7 +132,7 @@ class ErosnSapphoSycophantHexComAdapter(BaseSiteAdapter):
         ## Title
         pt = soup.find('div', {'id' : 'pagetitle'})
         a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.text)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = pt.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_fanfictionnet.py

@@ -16,6 +16,7 @@
 #
 
 import time
+from datetime import datetime
 import logging
 logger = logging.getLogger(__name__)
 import re
@@ -43,7 +44,7 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])
 
         # normalized story URL.
-        self._setURL("http://"+self.getSiteDomain()\
+        self._setURL("https://"+self.getSiteDomain()\
                          +"/s/"+self.story.getMetadata('storyId')+"/1/")
 
         # ffnet update emails have the latest chapter URL.
@@ -52,9 +53,11 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         # chapter list doesn't get the latest.  So save and use the
         # original URL given to pull chapter list & metadata.
         self.origurl = url
-        if "http://m." in self.origurl:
+        if "https://m." in self.origurl:
             ## accept m(mobile)url, but use www.
-            self.origurl = self.origurl.replace("http://m.","http://www.")
+            self.origurl = self.origurl.replace("https://m.","https://www.")
+
+        self.opener.addheaders.append(('Referer',self.origurl))
 
     @staticmethod
     def getSiteDomain():
@@ -66,10 +69,17 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
 
     @classmethod
     def getSiteExampleURLs(self):
-        return "http://www.fanfiction.net/s/1234/1/ http://www.fanfiction.net/s/1234/12/ http://www.fanfiction.net/s/1234/1/Story_Title http://m.fanfiction.net/s/1234/1/"
+        return "https://www.fanfiction.net/s/1234/1/ https://www.fanfiction.net/s/1234/12/ http://www.fanfiction.net/s/1234/1/Story_Title http://m.fanfiction.net/s/1234/1/"
 
     def getSiteURLPattern(self):
-        return r"http://(www|m)?\.fanfiction\.net/s/\d+(/\d+)?(/|/[^/]+)?/?$"
+        return r"https?://(www|m)?\.fanfiction\.net/s/\d+(/\d+)?(/|/[^/]+)?/?$"
+
+    def _fetchUrl(self,url):
+        time.sleep(1.0) ## ffnet(and, I assume, fpcom) tends to fail
+                        ## more if hit too fast.  This is in
+                        ## additional to what ever the
+                        ## slow_down_sleep_time setting is.
+        return BaseSiteAdapter._fetchUrl(self,url)
 
     def extractChapterUrlsAndMetadata(self):
 
@@ -97,32 +107,35 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         if "not found. Please check to see you are not using an outdated url." in data:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  'Chapter not found. Please check to see you are not using an outdated url.'" % url)
 
-        try:
-            # rather nasty way to check for a newer chapter.  ffnet has a
-            # tendency to send out update notices in email before all
-            # their servers are showing the update on the first chapter.
+        if self.getConfig('check_next_chapter'):
             try:
-                chapcount = len(soup.find('select', { 'name' : 'chapter' } ).findAll('option'))
-            # get chapter part of url.
+                ## ffnet used to have a tendency to send out update
+                ## notices in email before all their servers were
+                ## showing the update on the first chapter.  It
+                ## generates another server request and doesn't seem
+                ## to be needed lately, so now default it to off.
+                try:
+                    chapcount = len(soup.find('select', { 'name' : 'chapter' } ).findAll('option'))
+                # get chapter part of url.
+                except:
+                    chapcount = 1
+                chapter = url.split('/',)[5]
+                tryurl = "https://%s/s/%s/%d/"%(self.getSiteDomain(),
+                                                self.story.getMetadata('storyId'),
+                                                chapcount+1)
+                logger.debug('=Trying newer chapter: %s' % tryurl)
+                newdata = self._fetchUrl(tryurl)
+                if "not found. Please check to see you are not using an outdated url." \
+                        not in newdata:
+                    logger.debug('=======Found newer chapter: %s' % tryurl)
+                    soup = bs.BeautifulSoup(newdata)
             except:
-                chapcount = 1
-            chapter = url.split('/',)[5]
-            tryurl = "http://%s/s/%s/%d/"%(self.getSiteDomain(),
-                                           self.story.getMetadata('storyId'),
-                                           chapcount+1)
-            logger.debug('=Trying newer chapter: %s' % tryurl)
-            newdata = self._fetchUrl(tryurl)
-            if "not found. Please check to see you are not using an outdated url." \
-                    not in newdata:
-                logger.debug('=======Found newer chapter: %s' % tryurl)
-                soup = bs.BeautifulSoup(newdata)
-        except:
-            pass
-        
+                pass
+            
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"^/u/\d+"))
         self.story.setMetadata('authorId',a['href'].split('/')[2])
-        self.story.setMetadata('authorUrl','http://'+self.host+a['href'])
+        self.story.setMetadata('authorUrl','https://'+self.host+a['href'])
         self.story.setMetadata('author',a.string)
 
         ## Pull some additional data from html.
@@ -141,9 +154,9 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
             # 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'])
+            caturl = "https://%s%s"%(self.getSiteDomain(),categories[0]['href'])
             catsoup = bs.BeautifulSoup(self._fetchUrl(caturl))
-            for a in catsoup.findAll('a',href=re.compile(r"^/crossovers/")):
+            for a in catsoup.findAll('a',href=re.compile(r"^/crossovers/.+?/\d+/")):
                 self.story.addToList('category',stripHTML(a))
             else:
                 # Fall back.  I ran across a story with a Crossver
@@ -156,7 +169,7 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
                 
                 
             
-        a = soup.find('a', href='http://www.fictionratings.com/')
+        a = soup.find('a', href=re.compile(r'https?://www\.fictionratings\.com/'))
         rating = a.string
         if 'Fiction' in rating: # if rating has 'Fiction ', strip that out for consistency with past.
             rating = rating[8:]
@@ -165,7 +178,7 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
 
         # after Rating, the same bit of text containing id:123456 contains
         # Complete--if completed.
-        gui_table1i = soup.find('table',{'cellpadding':'5'})
+        gui_table1i = soup.find('div',{'id':'content_wrapper_inner'})
 
         self.story.setMetadata('title', stripHTML(gui_table1i.find('b'))) # title appears to be only(or at least first) bold tag in gui_table1i
 
@@ -199,15 +212,23 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         for g in genrelist:
             #logger.debug("g:(%s)"%g)
             if g.strip() not in ffnetgenres:
-                logger.info("g not in ffnetgenres")
+                #logger.info("g not in ffnetgenres")
                 goodgenres=False
         if goodgenres:
             self.story.extendList('genre',genrelist)
             metalist=metalist[1:]
 
+        # Updated: <span data-xutime='1368059198'>5/8</span> - Published: <span data-xutime='1278984264'>7/12/2010</span>
+        # Published: <span data-xutime='1384358726'>8m ago</span>
+        dates = soup.findAll('span',{'data-xutime':re.compile(r'^\d+$')})
+        if len(dates) > 1 :
+            # updated get set to the same as published upstream if not found.
+            self.story.setMetadata('dateUpdated',datetime.fromtimestamp(float(dates[0]['data-xutime'])))
+        self.story.setMetadata('datePublished',datetime.fromtimestamp(float(dates[-1]['data-xutime'])))
+            
         donechars = False
         while len(metalist) > 0:
-            if  metalist[0].startswith('Chapters') or metalist[0].startswith('Status') or metalist[0].startswith('id:'):
+            if  metalist[0].startswith('Chapters') or metalist[0].startswith('Status') or metalist[0].startswith('id:') or metalist[0].startswith('Updated:') or metalist[0].startswith('Published:'):
                 pass
             elif  metalist[0].startswith('Reviews'):
                 self.story.setMetadata('reviews',metalist[0].split(':')[1].strip())
@@ -215,21 +236,21 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
                 self.story.setMetadata('favs',metalist[0].split(':')[1].strip())
             elif  metalist[0].startswith('Follows:'):
                 self.story.setMetadata('follows',metalist[0].split(':')[1].strip())
-            elif  metalist[0].startswith('Updated'):
-                self.story.setMetadata('dateUpdated',makeDate(metalist[0].split(':')[1].strip(), '%m-%d-%y'))
-            elif  metalist[0].startswith('Published'):
-                self.story.setMetadata('datePublished',makeDate(metalist[0].split(':')[1].strip(), '%m-%d-%y'))
             elif  metalist[0].startswith('Words'):
                 self.story.setMetadata('numWords',metalist[0].split(':')[1].strip())
             elif not donechars:
-                self.story.extendList('characters',metalist[0].split('&'))
+                # with 'pairing' support, pairings are bracketed w/o comma after
+                # [Caspian X, Lucy Pevensie] Edmund Pevensie, Peter Pevensie
+                self.story.extendList('characters',metalist[0].replace('[','').replace(']',',').split(','))
+
+                l = metalist[0]
+                while '[' in l:
+                    self.story.addToList('ships',l[l.index('[')+1:l.index(']')].replace(', ','/'))
+                    l = l[l.index(']')+1:]
+
                 donechars = True
             metalist=metalist[1:]
 
-        # next might be characters, otherwise Reviews, Updated, Published, Words
-        # if not ( metalist[0].startswith('Reviews') or metalist[0].startswith('Updated') or metalist[0].startswith('Published') or metalist[0].startswith('Words') or metalist[0].startswith('Chapters') ):
-        #     self.story.extendList('characters',metalist[0].split('&'))
-        
         if 'Status: Complete' in metatext:
             self.story.setMetadata('status', 'Completed')
         else:
@@ -253,9 +274,9 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         else:
             allOptions = select.findAll('option')
             for o in allOptions:
-                url = u'http://%s/s/%s/%s/' % ( self.getSiteDomain(),
-                                            self.story.getMetadata('storyId'),
-                                            o['value'])
+                url = u'https://%s/s/%s/%s/' % ( self.getSiteDomain(),
+                                                 self.story.getMetadata('storyId'),
+                                                 o['value'])
                 # just in case there's tags, like <i> in chapter titles.
                 title = u"%s" % o
                 title = re.sub(r'<[^>]+>','',title)
@@ -266,11 +287,11 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         return
 
     def getChapterText(self, url):
-        logger.debug('Getting chapter text from: %s' % url)
-        time.sleep(0.5) ## ffnet(and, I assume, fpcom) tends to fail
+        time.sleep(4.0) ## ffnet(and, I assume, fpcom) tends to fail
                         ## more if hit too fast.  This is in
                         ## additional to what ever the
                         ## slow_down_sleep_time setting is.
+        logger.debug('Getting chapter text from: %s' % url)
         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:
@@ -281,10 +302,11 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         # 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.
-        if "<div class='storytextp" not in data:
+        divstr = "<div role='main'"
+        if divstr not in data:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
         else:
-            data = data[data.index("<div class='storytextp"):]
+            data = data[data.index(divstr):]
         data.replace("<body","<notbody").replace("<BODY","<NOTBODY")
         
         soup = bs.BeautifulSoup(data)

fanficdownloader/adapters/adapter_fanfiktionde.py

@@ -50,7 +50,7 @@ class FanFiktionDeAdapter(BaseSiteAdapter):
         
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])
-        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
         
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/s/'+self.story.getMetadata('storyId') + '/1')
@@ -173,7 +173,7 @@ class FanFiktionDeAdapter(BaseSiteAdapter):
         tr=asoup.findAll('tr')
         for i in range(1,len(tr)):
             a = tr[i].find('a')
-            if a['href'] == '/s/'+self.story.getMetadata('storyId'):
+            if '/s/'+self.story.getMetadata('storyId')+'/1/' in a['href']:
                 break
         self.setDescription(url,a['onmouseover'].split("', '")[1])
         

fanficdownloader/adapters/adapter_ficbooknet.py

@@ -52,7 +52,7 @@ class FicBookNetAdapter(BaseSiteAdapter):
         
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])
-        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
         
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/readfic/'+self.story.getMetadata('storyId'))

fanficdownloader/adapters/adapter_fictionalleyorg.py

@@ -45,7 +45,7 @@ class FictionAlleyOrgSiteAdapter(BaseSiteAdapter):
         if m:
             self.story.setMetadata('authorId',m.group('auth'))
             self.story.setMetadata('storyId',m.group('id'))
-            logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+            
             # normalized story URL.
             self._setURL(url)
         else:
@@ -111,7 +111,7 @@ class FictionAlleyOrgSiteAdapter(BaseSiteAdapter):
             url=self.url
             logger.debug("Normalizing to URL: "+url)
             ## title's right there...
-            self.story.setMetadata('title',storya.string)
+            self.story.setMetadata('title',stripHTML(storya))
             data = self._fetchUrl(url)
             soup = bs.BeautifulSoup(data)
             chapterlinklist = soup.findAll('a',{'class':'chapterlink'})
@@ -121,7 +121,7 @@ class FictionAlleyOrgSiteAdapter(BaseSiteAdapter):
             ## same way.
             chapsoup = bs.BeautifulSoup(chapterdata)
             storya = chapsoup.find('div',{'class':'breadcrumbs'}).findAll('a')[1]
-            self.story.setMetadata('title',storya.string)
+            self.story.setMetadata('title',stripHTML(storya))
             del chapsoup
 
         del chapterdata

fanficdownloader/adapters/adapter_fictionpadcom.py

@@ -0,0 +1,192 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2013 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+logger = logging.getLogger(__name__)
+import re
+import urllib2
+import time
+import json
+
+from .. import BeautifulSoup as bs
+#from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+class FictionPadSiteAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+        self.story.setMetadata('siteabbrev','fpad')
+        self.dateformat = "%Y-%m-%dT%H:%M:%SZ"
+        self.is_adult=False
+        self.username = None
+        self.password = None
+        # get storyId from url--url validation guarantees query correct
+        m = re.match(self.getSiteURLPattern(),url)
+        if m:
+            self.story.setMetadata('storyId',m.group('id'))
+            
+            # normalized story URL.
+            self._setURL("https://"+self.getSiteDomain()
+                         +"/author/"+m.group('author')
+                         +"/stories/"+self.story.getMetadata('storyId'))
+        else:
+            raise exceptions.InvalidStoryURL(url,
+                                             self.getSiteDomain(),
+                                             self.getSiteExampleURLs())
+
+    @staticmethod
+    def getSiteDomain():
+        return 'fictionpad.com'
+
+    @classmethod
+    def getSiteExampleURLs(self):
+        return "https://fictionpad.com/author/Author/stories/1234/Some-Title"
+    
+    def getSiteURLPattern(self):
+        # http://fictionpad.com/author/Serdd/stories/4275
+        return r"http(s)?://(www\.)?fictionpad\.com/author/(?P<author>[^/]+)/stories/(?P<id>\d+)"
+
+# <form method="post" action="/signin">
+#     <input name="authenticity_token" type="hidden" value="u+cfdXh46dRnwVnSlmE2B2BFmHgu760paqgBG6KQeos=" />
+#     <input type="hidden" name="remember" value="1">
+#     <strong class="help-start text-center">or with FictionPad</strong>
+#     <label class="control-label hidden-placeholder">Pseudonym or Email Address</label>
+#     <input name="login" class="input-block-level" type="text" placeholder="Pseudonym or Email Address" maxlength="50" required autofocus>
+#     <label class="control-label hidden-placeholder">Password</label>
+#     <input name="password" class="input-block-level" type="password" placeholder="Password" minlength="6" required>
+#     <button type="submit" class="btn btn-primary btn-block">Sign In</button>
+#     <p class="help-end">
+#         <a href="/passwordreset">Forgot your password?</a>
+#     </p>
+# </form>
+    def performLogin(self):
+        params = {}
+
+        if self.password:
+            params['login'] = self.username
+            params['password'] = self.password
+        else:
+            params['login'] = self.getConfig("username")
+            params['password'] = self.getConfig("password")
+        params['remember'] = '1'
+
+        loginUrl = 'http://' + self.getSiteDomain() + '/signin'
+        logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
+                                                              params['login']))
+
+        ## need to pull empty login page first to get authenticity_token
+        soup = bs.BeautifulSoup(self._fetchUrl(loginUrl))
+        params['authenticity_token']=soup.find('input', {'name':'authenticity_token'})['value']
+        
+        data = self._postUrl(loginUrl, params)
+
+        if "Invalid email/pseudonym and password combination." in data:
+            logger.info("Failed to login to URL %s as %s" % (loginUrl,
+                                                              params['login']))
+            raise exceptions.FailedToLogin(loginUrl,params['login'])
+            
+
+    def extractChapterUrlsAndMetadata(self):
+        # fetch the chapter.  From that we will get almost all the
+        # metadata and chapter list
+
+        url=self.url
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+            if "This is a mature story.  Please sign in to read it." in data:
+                self.performLogin()
+                data = self._fetchUrl(url)
+            
+            find = "wordyarn.config.page = "
+            data = data[data.index(find)+len(find):]
+            data = data[:data.index("</script>")]
+            data = data[:data.rindex(";")]
+            data = data.replace('tables:','"tables":')
+            tables = json.loads(data)['tables']
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(url)
+            else:
+                raise e
+
+        # looks like only one author per story allowed.
+        author = tables['users'][0]
+        story = tables['stories'][0]
+        story_ver = tables['story_versions'][0]
+        
+        self.story.setMetadata('authorId',author['id'])
+        self.story.setMetadata('author',author['display_name'])
+        self.story.setMetadata('authorUrl','https://'+self.host+'/author/'+author['display_name']+'/stories')
+
+        self.story.setMetadata('title',story_ver['title'])
+        self.setDescription(url,story_ver['description'])
+        
+        if not ('assets/story_versions/covers' in story_ver['profile_image_url@2x']):
+            self.setCoverImage(url,story_ver['profile_image_url@2x'])
+
+        self.story.setMetadata('datePublished',makeDate(story['published_at'], self.dateformat))
+        self.story.setMetadata('dateUpdated',makeDate(story['published_at'], self.dateformat))
+
+        self.story.setMetadata('followers',story['followers_count'])
+        self.story.setMetadata('comments',story['comments_count'])
+        self.story.setMetadata('views',story['views_count'])
+        self.story.setMetadata('likes',int(story['likes'])) # no idea why they floated these.
+        self.story.setMetadata('dislikes',int(story['dislikes']))
+
+        if story_ver['is_complete']:
+            self.story.setMetadata('status', 'Completed')
+        else:
+            self.story.setMetadata('status', 'In-Progress')
+
+        self.story.setMetadata('rating', story_ver['maturity_level'])
+        self.story.setMetadata('numWords', unicode(story_ver['word_count']))
+
+        for i in tables['fandoms']:
+            self.story.addToList('category',i['name'])
+        
+        for i in tables['genres']:
+            self.story.addToList('genre',i['name'])
+        
+        for i in tables['characters']:
+            self.story.addToList('characters',i['name'])
+
+        for c in tables['chapters']:
+            chtitle = "Chapter %d"%c['number']
+            if c['title']:
+                chtitle += " - %s"%c['title']
+            self.chapterUrls.append((chtitle,c['body_url']))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+            
+    def getChapterText(self, url):
+        logger.debug('Getting chapter text from: %s' % url)
+        if not url:
+            data = u"<em>This chapter has no text.</em>"
+        else:
+            data = self._fetchUrl(url)
+        soup = bs.BeautifulSoup(u"<div id='story'>"+data+u"</div>")
+        return self.utf8FromSoup(url,soup)
+    
+def getClass():
+    return FictionPadSiteAdapter
+

fanficdownloader/adapters/adapter_fictionpresscom.py

@@ -41,10 +41,10 @@ class FictionPressComSiteAdapter(FanFictionNetSiteAdapter):
 
     @classmethod
     def getSiteExampleURLs(self):
-        return "http://www.fictionpress.com/s/1234/1/ http://www.fictionpress.com/s/1234/12/ http://www.fictionpress.com/s/1234/1/Story_Title http://m.fictionpress.com/s/1234/1/"
+        return "https://www.fictionpress.com/s/1234/1/ https://www.fictionpress.com/s/1234/12/ http://www.fictionpress.com/s/1234/1/Story_Title http://m.fictionpress.com/s/1234/1/"
 
     def getSiteURLPattern(self):
-        return r"http://(www|m)?\.fictionpress\.com/s/\d+(/\d+)?(/|/[a-zA-Z0-9_-]+)?/?$"
+        return r"https?://(www|m)?\.fictionpress\.com/s/\d+(/\d+)?(/|/[a-zA-Z0-9_-]+)?/?$"
 
 def getClass():
     return FictionPressComSiteAdapter

fanficdownloader/adapters/adapter_ficwadcom.py

@@ -85,7 +85,11 @@ class FicwadComSiteAdapter(BaseSiteAdapter):
 
         # use BeautifulSoup HTML parser to make everything easier to find.
         try:
-            soup = bs.BeautifulSoup(self._fetchUrl(url))
+            data = self._fetchUrl(url)
+            # non-existent/removed story urls get thrown to the front page.
+            if "<h2>Welcome to FicWad</h2>" in data:
+                raise exceptions.StoryDoesNotExist(self.url)
+            soup = bs.BeautifulSoup(data)
         except urllib2.HTTPError, e:
             if e.code == 404:
                 raise exceptions.StoryDoesNotExist(self.url)
@@ -116,7 +120,7 @@ class FicwadComSiteAdapter(BaseSiteAdapter):
 
         # title - first h4 tag will be title.
         titleh4 = soup.find('h4')
-        self.story.setMetadata('title', titleh4.a.string)
+        self.story.setMetadata('title', stripHTML(titleh4.a))
 
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"^/author/\d+"))

fanficdownloader/adapters/adapter_fimfictionnet.py

@@ -21,7 +21,6 @@ logger = logging.getLogger(__name__)
 import re
 import urllib2
 import cookielib as cl
-from datetime import datetime
 import json
 
 from .. import BeautifulSoup as bs
@@ -42,6 +41,10 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
         self._setURL("http://"+self.getSiteDomain()+"/story/"+self.story.getMetadata('storyId')+"/")
         self.is_adult = False
         
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%d %b %Y"
+            
     @staticmethod
     def getSiteDomain():
         return 'www.fimfiction.net'
@@ -93,10 +96,12 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
         if "Warning: mysql_fetch_array(): supplied argument is not a valid MySQL result resource" in data:
             raise exceptions.StoryDoesNotExist(self.url)
 
-        if "/images/missing_story.png" in data:
-            raise exceptions.StoryDoesNotExist(self.url)
+        # Can cause problems if a missing story is referenced in a comment.
+        # Shouldn't be needed anyway.
+        # if "/images/missing_story.png" in data:
+        #     raise exceptions.StoryDoesNotExist(self.url)
         
-        if "This story has been marked as having adult content." in data:
+        if "This story has been marked as having adult content. Please click below to confirm you are of legal age to view adult material in your country." in data:
             raise exceptions.AdultCheckRequired(self.url)
         
         if self.password:
@@ -117,7 +122,7 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
             
         ## Title
         a = soup.find('a', href=re.compile(r'^/story/'+self.story.getMetadata('storyId')))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # self.story.setMetadata("title", storyMetadata["title"])
         # if not storyMetadata["title"]:
@@ -185,14 +190,42 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
         hrstr="<hr />"
         descdivstr = '<div class="description">'+descdivstr[descdivstr.index(hrstr)+len(hrstr):]
         self.setDescription(self.url,descdivstr)
-        
+
+        # Can't trust dates from API anymore I'm told.
         # Dates are in Unix time
         # Take the publish date from the first chapter posted
-        rawDatePublished = storyMetadata["chapters"][0]["date_modified"]
-        self.story.setMetadata("datePublished", datetime.fromtimestamp(rawDatePublished))
-        rawDateUpdated = storyMetadata["date_modified"]
-        self.story.setMetadata("dateUpdated", datetime.fromtimestamp(rawDateUpdated))
+        # rawDatePublished = storyMetadata["chapters"][0]["date_modified"]
+        # self.story.setMetadata("datePublished", datetime.fromtimestamp(rawDatePublished))
+        # rawDateUpdated = storyMetadata["date_modified"]
+        # self.story.setMetadata("dateUpdated", datetime.fromtimestamp(rawDateUpdated))
+        
+        oldestChapter = None
+        newestChapter = None
+        self.newestChapterNum = None # save for comparing during update.
+        # Scan all chapters to find the oldest and newest, on
+        # FiMFiction it's possible for authors to insert new chapters
+        # out-of-order or change the dates of earlier ones by editing
+        # them--That WILL break epub update.
+        for index, chapterDate in enumerate(soup.findAll('span', {'class':'date'})):
+            date=re.sub(r"(\d+)(st|nd|rd|th)",r"\1",chapterDate.contents[1].strip())
+            chapterDate = makeDate(date,self.dateformat)
+            if oldestChapter == None or chapterDate < oldestChapter:
+                oldestChapter = chapterDate
+            if newestChapter == None or chapterDate > newestChapter:
+                newestChapter = chapterDate
+                self.newestChapterNum = index
 
+        self.story.setMetadata("dateUpdated", newestChapter)
+        
+        pubdatetag = soup.find('span', {'class':'date_approved'})
+        if pubdatetag is None:
+            self.story.setMetadata("datePublished", oldestChapter)            
+        else:
+            pubdateraw = pubdatetag('span')[1].text
+            datestripped=re.sub(r"(\d+)(st|nd|rd|th)",r"\1",pubdateraw.strip())
+            pubDate = makeDate(datestripped,self.dateformat)
+            self.story.setMetadata("datePublished", pubDate)
+            
         chars = soup.find("div", {"class":"inner_data"})
         # fimfic stopped putting the char name on or around the char
         # icon now for some reason.  Pull it from the image name with
@@ -215,10 +248,46 @@ class FimFictionNetSiteAdapter(BaseSiteAdapter):
                 if not isinstance(value,basestring):
                     value = unicode(value)
                 self.story.setMetadata(metakey, value)
+
+        ## Groups and sequels code from FaceDeer
+        allGroupLists = soup.findAll('ul', {'id':'story_group_list'})
+        for groupList in allGroupLists:
+            for groupName in groupList.findAll('a', {'href':re.compile('^/group/')}):
+                self.story.addToList("groupsUrl", 'http://'+self.host+groupName["href"]) 
+                self.story.addToList("groups",stripHTML(groupName).replace(',', ';'))
+
+        sequelStoryHeader = soup.find('h1', {'class':'header-stories'}, text="Sequels")
+        if not sequelStoryHeader == None:
+            sequelContainer = sequelStoryHeader.parent.parent
+            for sequel in sequelContainer.findAll('a', {'class':'story_link'}):
+                self.story.addToList("sequelsUrl", 'http://'+self.host+sequel["href"]) 
+                self.story.addToList("sequels", stripHTML(sequel).replace(',', ';'))
+                
+        #The link to the prequel is embedded in the description text, so erring
+        #on the side of caution and wrapping this whole thing in a try block.
+        #If anything goes wrong this probably wasn't a valid prequel link.
+        try:
+            description = soup.find('div', {'class':'description'})
+            firstHR = description.find("hr")
+            nextSib = firstHR.nextSibling
+            if "This story is a sequel to" in nextSib.string:
+                link = nextSib.nextSibling
+                if link.name == "a":
+                    self.story.setMetadata("prequelUrl", 'http://'+self.host+link["href"])
+                    self.story.setMetadata("prequel", stripHTML(link))
+        except:
+            pass
         
+    def hookForUpdates(self,chaptercount):
+        if self.oldchapters and len(self.oldchapters) > self.newestChapterNum:
+            print("Existing epub has %s chapters\nNewest chapter is %s.  Discarding old chapters from there on."%(len(self.oldchapters), self.newestChapterNum+1))
+            self.oldchapters = self.oldchapters[:self.newestChapterNum]
+        return len(self.oldchapters)
             
+        
     def getChapterText(self, url):
         logger.debug('Getting chapter text from: %s' % url)
+        
         soup = bs.BeautifulSoup(self._fetchUrl(url),selfClosingTags=('br','hr')).find('div', {'class' : 'chapter_content'})
         if soup == None:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)

fanficdownloader/adapters/adapter_finestoriescom.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.
@@ -37,11 +37,6 @@ class FineStoriesComAdapter(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
@@ -50,7 +45,6 @@ class FineStoriesComAdapter(BaseSiteAdapter):
         self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2].split(':')[0])
         if 'storyInfo' in self.story.getMetadata('storyId'):
             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() + '/s/storyInfo.php?id='+self.story.getMetadata('storyId'))
@@ -93,7 +87,7 @@ class FineStoriesComAdapter(BaseSiteAdapter):
             params['theusername'] = self.getConfig("username")
             params['thepassword'] = self.getConfig("password")
         params['rememberMe'] = '1'
-        params['page'] = 'http://finestories.com/'
+        params['page'] = 'http://'+self.getSiteDomain()+'/'
         params['submit'] = 'Login'
     
         loginUrl = 'http://' + self.getSiteDomain() + '/login.php'
@@ -142,7 +136,7 @@ class FineStoriesComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'/s/'+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.text)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"/a/\w+"))
@@ -262,8 +256,6 @@ class FineStoriesComAdapter(BaseSiteAdapter):
                 last[len(last)-1]=last[len(last)-1].append(next)
                 div.append(div1)
             
-            
-            
         # removing all the left-over stuff    
         for a in div.findAll('span'):
             a.extract()

fanficdownloader/adapters/adapter_grangerenchantedcom.py

@@ -48,7 +48,7 @@ class GrangerEnchantedCom(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'))
+        
         self.section=self.parsedUrl.path.split('/',)[1]
              
         # normalized story URL.
@@ -182,7 +182,7 @@ class GrangerEnchantedCom(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_harrypotterfanfictioncom.py

@@ -42,7 +42,7 @@ class HarryPotterFanFictionComSiteAdapter(BaseSiteAdapter):
         
         # get storyId from url--url validation guarantees query is only psid=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?psid='+self.story.getMetadata('storyId'))
@@ -92,7 +92,7 @@ class HarryPotterFanFictionComSiteAdapter(BaseSiteAdapter):
 
         ## Title
         a = soup.find('a', href=re.compile(r'\?psid='+self.story.getMetadata('storyId')))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         ## javascript:if (confirm('Please note. This story may contain adult themes. By clicking here you are stating that you are over 17. Click cancel if you do not meet this requirement.')) location = '?psid=290995'
         if "This story may contain adult themes." in a['href'] and not (self.is_adult or self.getConfig("is_adult")):
             raise exceptions.AdultCheckRequired(self.url)
@@ -131,55 +131,55 @@ class HarryPotterFanFictionComSiteAdapter(BaseSiteAdapter):
 
         ## Finding the metadata is a bit of a pain.  Most of the meta
         ## data is in a center.table without a bgcolor.
-        for center in soup.findAll('center'):
-            table = center.find('table',{'bgcolor':None})
-            if table:
-                metastr = stripHTML(str(table)).replace('\n',' ').replace('\t',' ')
-                # Rating: 12+ Story Reviews: 3
-                # Chapters: 3
-                # Characters: Andromeda, Ted, Bellatrix, R. Lestrange, Lucius, Narcissa, OC
-                # Genre(s): Fluff, Romance, Young Adult Era: OtherPairings: Other Pairing, Lucius/Narcissa
-                # Status: Completed
-                # First Published: 2010.09.02
-                # Last Published Chapter: 2010.09.28
-                # Last Updated: 2010.09.28
-                # Favorite Story Of: 1 users
-                # Warnings: Scenes of a Mild Sexual Nature
+        #for center in soup.findAll('center'):
+        table = soup.find('table',{'class':'storymaininfo'})
+        if table:
+            metastr = stripHTML(str(table)).replace('\n',' ').replace('\t',' ')
+            # Rating: 12+ Story Reviews: 3
+            # Chapters: 3
+            # Characters: Andromeda, Ted, Bellatrix, R. Lestrange, Lucius, Narcissa, OC
+            # Genre(s): Fluff, Romance, Young Adult Era: OtherPairings: Other Pairing, Lucius/Narcissa
+            # Status: Completed
+            # First Published: 2010.09.02
+            # Last Published Chapter: 2010.09.28
+            # Last Updated: 2010.09.28
+            # Favorite Story Of: 1 users
+            # Warnings: Scenes of a Mild Sexual Nature
 
-                m = re.match(r".*?Status: Completed.*?",metastr)
-                if m:
-                    self.story.setMetadata('status','Completed')
-                else:
-                    self.story.setMetadata('status','In-Progress')
+            m = re.match(r".*?Status: Completed.*?",metastr)
+            if m:
+                self.story.setMetadata('status','Completed')
+            else:
+                self.story.setMetadata('status','In-Progress')
 
-                m = re.match(r".*?Rating: (.+?) Story Reviews.*?",metastr)
-                if m:
-                    self.story.setMetadata('rating', m.group(1))
+            m = re.match(r".*?Rating: (.+?) Story Reviews.*?",metastr)
+            if m:
+                self.story.setMetadata('rating', m.group(1))
 
-                m = re.match(r".*?Genre\(s\): (.+?) Era.*?",metastr)
-                if m:
-                    for g in m.group(1).split(','):
-                        self.story.addToList('genre',g)
-        
-                m = re.match(r".*?Characters: (.+?) Genre.*?",metastr)
-                if m:
-                    for g in m.group(1).split(','):
-                        self.story.addToList('characters',g)
-        
-                m = re.match(r".*?Warnings: (.+).*?",metastr)
-                if m:
-                    for w in m.group(1).split(','):
-                        if w != 'Now Warnings':
-                            self.story.addToList('warnings',w)
-        
-                m = re.match(r".*?First Published: ([0-9\.]+).*?",metastr)
-                if m:
-                    self.story.setMetadata('datePublished',makeDate(m.group(1), "%Y.%m.%d"))
+            m = re.match(r".*?Genre\(s\): (.+?) Era.*?",metastr)
+            if m:
+                for g in m.group(1).split(','):
+                    self.story.addToList('genre',g)
+    
+            m = re.match(r".*?Characters: (.+?) Genre.*?",metastr)
+            if m:
+                for g in m.group(1).split(','):
+                    self.story.addToList('characters',g)
+    
+            m = re.match(r".*?Warnings: (.+).*?",metastr)
+            if m:
+                for w in m.group(1).split(','):
+                    if w != 'Now Warnings':
+                        self.story.addToList('warnings',w)
+    
+            m = re.match(r".*?First Published: ([0-9\.]+).*?",metastr)
+            if m:
+                self.story.setMetadata('datePublished',makeDate(m.group(1), "%Y.%m.%d"))
 
-                # Updated can have more than one space after it. <shrug>
-                m = re.match(r".*?Last Updated: ([0-9\.]+).*?",metastr)
-                if m:
-                    self.story.setMetadata('dateUpdated',makeDate(m.group(1), "%Y.%m.%d"))
+            # Updated can have more than one space after it. <shrug>
+            m = re.match(r".*?Last Updated: ([0-9\.]+).*?",metastr)
+            if m:
+                self.story.setMetadata('dateUpdated',makeDate(m.group(1), "%Y.%m.%d"))
 
     def getChapterText(self, url):
 

fanficdownloader/adapters/adapter_hennethannunnet.py

@@ -48,7 +48,7 @@ class HennethAnnunNetAdapter(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() + '/stories/chapter.cfm?stid='+self.story.getMetadata('storyId'))
@@ -101,7 +101,7 @@ class HennethAnnunNetAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('h2', {'id':'page_heading'})
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
 
         # Find the chapters: chapter_view.cfm?stid=6663&spordinal=1" 
         for chapter in soup.findAll('a', href=re.compile(r'chapter_view.cfm\?stid='+self.story.getMetadata('storyId')+"&spordinal=\d+$")):

fanficdownloader/adapters/adapter_hlfictionnet.py

@@ -48,7 +48,7 @@ class HLFictionNetAdapter(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() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -106,7 +106,7 @@ class HLFictionNetAdapter(BaseSiteAdapter):
         self.story.setMetadata('author',aut.string)
         aut.extract()
         
-        self.story.setMetadata('title',a.string[:(len(a.string)-3)])
+        self.story.setMetadata('title',stripHTML(a)[:(len(a.string)-3)])
 
         # Find the chapters:
         chapters=soup.find('select')

fanficdownloader/adapters/adapter_hpfandomnet.py

@@ -52,7 +52,7 @@ class HPFandomNetAdapterAdapter(BaseSiteAdapter): # XXX
         
         # 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 /eff part.  Replace all to remove it usually.

fanficdownloader/adapters/adapter_hpfanficarchivecom.py

@@ -48,7 +48,7 @@ class HPFanficArchiveComAdapter(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() + '/stories/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -100,7 +100,7 @@ class HPFanficArchiveComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
@@ -128,23 +128,22 @@ class HPFanficArchiveComAdapter(BaseSiteAdapter):
         # <span class="label">Rated:</span> NC-17<br /> etc
         labels = soup.findAll('span',{'class':'label'})
         for labelspan in labels:
-            value = labelspan.nextSibling
+            val = labelspan.nextSibling
+            value = unicode('')
+            while val and not defaultGetattr(val,'class') == 'label':
+                value += unicode(val)
+                val = val.nextSibling
             label = labelspan.string
+            #print("label:%s\nvalue:%s"%(label,value))
 
             if 'Summary' in label:
-                ## Everything until the next span class='label'
-                svalue = ""
-                while not defaultGetattr(value,'class') == 'label':
-                    svalue += str(value)
-                    value = value.nextSibling
-                self.setDescription(url,svalue)
-                #self.story.setMetadata('description',stripHTML(svalue))
+                self.setDescription(url,value)
 
             if 'Rated' in label:
-                self.story.setMetadata('rating', value)
+                self.story.setMetadata('rating', stripHTML(value))
 
             if 'Word count' in label:
-                self.story.setMetadata('numWords', value)
+                self.story.setMetadata('numWords', stripHTML(value))
 
             if 'Categories' in label:
                 cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
@@ -161,13 +160,18 @@ class HPFanficArchiveComAdapter(BaseSiteAdapter):
                 for genre in genres:
                     self.story.addToList('genre',genre.string)
 
+            if 'Pairing' in label:
+                ships = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=4'))
+                for ship in ships:
+                    self.story.addToList('ships',ship.string)
+
             if 'Warnings' in label:
                 warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
                 for warning in warnings:
                     self.story.addToList('warnings',warning.string)
 
             if 'Completed' in label:
-                if 'Yes' in value:
+                if 'Yes' in stripHTML(value):
                     self.story.setMetadata('status', 'Completed')
                 else:
                     self.story.setMetadata('status', 'In-Progress')

fanficdownloader/adapters/adapter_iketernalnet.py

@@ -48,7 +48,7 @@ class IkEternalNetAdapter(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() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -183,7 +183,7 @@ class IkEternalNetAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_imagineeficcom.py

@@ -48,7 +48,7 @@ class ImagineEFicComAdapter(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() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -170,7 +170,7 @@ class ImagineEFicComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_indeathnet.py

@@ -46,12 +46,12 @@ class InDeathNetAdapter(BaseSiteAdapter):
         self.password = ""
         self.is_adult=False
         
-		
-		  # get storyId from url--url validation guarantees query correct
+        
+        # get storyId from url--url validation guarantees query correct
         m = re.match(self.getSiteURLPattern(),url)
         if m:
             self.story.setMetadata('storyId',m.group('id'))
-            logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+            
             # normalized story URL.
             self._setURL('http://www.' + self.getSiteDomain() + '/blog/archive/'+self.story.getMetadata('storyId')+'-'+m.group('name')+'/')
         else:
@@ -87,6 +87,34 @@ class InDeathNetAdapter(BaseSiteAdapter):
         postdate = makeDate(d.group('day')+' '+ym.group('mon')+' '+ym.group('year'),self.dateformat)
         return postdate
 
+    def getAuthorData(self):
+        
+        mainUrl = self.url.replace("/archive","")
+        
+        try:
+            maindata = self._fetchUrl(mainUrl)
+            
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.meta)
+            else:
+                raise e
+
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        mainsoup = bs.BeautifulSoup(maindata)
+
+        # find first entry
+        e = mainsoup.find('div',{'class':"entry"})
+        
+        # get post author as author
+        d = e.find('div',{'class':"desc"})
+        a = d.find('strong')
+        self.story.setMetadata('author',a.contents[0].string.strip())
+        
+        # Don't seem to be able to get author pages anymore
+        self.story.setMetadata('authorUrl','http://www.indeath.net/')
+        self.story.setMetadata('authorId','0')
+        
     ## Getting the chapter list and the meta data, plus 'is adult' checking.
     def extractChapterUrlsAndMetadata(self):
 
@@ -109,21 +137,14 @@ class InDeathNetAdapter(BaseSiteAdapter):
         ## Title
         h = soup.find('a', id="blog_title")
         t = h.find('span')
-        self.story.setMetadata('title',t.contents[0].string.strip())
-		
+        self.story.setMetadata('title',stripHTML(t.contents[0]).strip())
+        
         s = t.find('div')        
         if s != None:
             self.setDescription(url,s)
-		
-        # Find authorid and URL from first link in Recent Entries (don't yet reference 'recent entries' - let's see if that is required)
-        a = soup.find('a', href=re.compile(r"http://www.indeath.net/user/\d+\-[a-z0-9]+/$"))		#http://www.indeath.net/user/9083-cyrex/
-        m = re.search('http://www.indeath.net/user/(?P<id>\d+)\-(?P<name>[a-z0-9]*)/$',a['href'])
-        self.story.setMetadata('authorId',m.group('id'))
-        self.story.setMetadata('authorUrl',a['href'])
-        self.story.setMetadata('author',m.group('name'))
-
-
 
+        # Get Author from main blog page since it's not reliably on the archive page
+        self.getAuthorData()
 
         # Find the chapters:
         chapters=soup.findAll('a', title="View entry", href=re.compile(r'http://www.indeath.net/blog/'+self.story.getMetadata('storyId')+"/entry\-(\d+)\-([^/]*)/$"))
@@ -152,21 +173,20 @@ class InDeathNetAdapter(BaseSiteAdapter):
             if len(chapters)==1:
                 self.chapterUrls.append((self.story.getMetadata('title'),chapter['href']))
             else:
-            	ct = stripHTML(chapter)
-            	tnew = re.match("(?i)"+self.story.getMetadata('title')+r" - (?P<newtitle>.*)$",ct)
-            	if tnew:
-            		chaptertitle = tnew.group('newtitle')
-            	else:
-            		chaptertitle = ct
+                ct = stripHTML(chapter)
+                tnew = re.match("(?i)"+self.story.getMetadata('title')+r" - (?P<newtitle>.*)$",ct)
+                if tnew:
+                    chaptertitle = tnew.group('newtitle')
+                else:
+                    chaptertitle = ct
                 self.chapterUrls.append((chaptertitle,chapter['href']))
-	
-		
+
         
         
     # grab the text for an individual chapter.
     def getChapterText(self, url):
         logger.debug('Getting chapter text from: %s' % url)
-		
+        
         #chapter=bs.BeautifulSoup('<div class="story"></div>')
         data = self._fetchUrl(url)
         soup = bs.BeautifulSoup(data,selfClosingTags=('br','hr','span','center'))

fanficdownloader/adapters/adapter_ksarchivecom.py

@@ -52,7 +52,7 @@ class KSArchiveComAdapter(BaseSiteAdapter): # XXX
         
         # 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.

fanficdownloader/adapters/adapter_libraryofmoriacom.py

@@ -49,7 +49,7 @@ class LibraryOfMoriaComAdapter(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() + '/a/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -129,7 +129,7 @@ class LibraryOfMoriaComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_literotica.py

@@ -0,0 +1,237 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2013 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+logger = logging.getLogger(__name__)
+import re
+import urllib2
+import urlparse
+import time
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter, makeDate
+
+class LiteroticaSiteAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["utf8",
+                       "Windows-1252"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        
+        self.story.setMetadata('siteabbrev','litero')
+
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])
+        
+        self.origurl = url
+        if "http://www.i." in self.origurl:
+            ## accept m(mobile)url, but use www.
+            self.origurl = self.origurl.replace("http://www.i.","http://www.")
+
+        # normalized story URL.
+        self._setURL("http://"+self.getSiteDomain()\
+                         +"/s/"+self.story.getMetadata('storyId'))
+
+        # 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
+    def getSiteDomain():
+        return 'www.literotica.com'
+
+    @classmethod
+    def getAcceptDomains(cls):
+        return ['www.literotica.com', 'www.i.literotica.com']
+
+    @classmethod
+    def getSiteExampleURLs(self):
+        #return "http://www.literotica.com/s/story-title http://www.literotica.com/stories/showstory.php?id=1234 http://www.i.literotica.com/stories/showstory.php?id=1234"
+        return "http://www.literotica.com/s/story-title"
+
+    def getSiteURLPattern(self):
+        return r"http://www(\.i)?\.literotica\.com/s/([a-zA-Z0-9_-]+)"
+
+    def extractChapterUrlsAndMetadata(self):
+
+        if not (self.is_adult or self.getConfig("is_adult")):
+            raise exceptions.AdultCheckRequired(self.url)
+        
+        url1 = self.origurl
+        logger.debug("first page URL: "+url1)
+
+        try:
+            data1 = self._fetchUrl(url1)
+            soup1 = bs.BeautifulSoup(data1)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(url1)
+            else:
+                raise e
+
+        #strip comments from soup
+        [comment.extract() for comment in soup1.findAll(text=lambda text:isinstance(text, bs.Comment))]
+
+        # author
+        a = soup1.find("span", "b-story-user-y")
+        self.story.setMetadata('authorId', urlparse.parse_qs(a.a['href'].split('?')[1])['uid'])
+        self.story.setMetadata('authorUrl', a.a['href'])
+        self.story.setMetadata('author', a.text)
+
+        # get the author page
+        try:
+            dataAuth = self._fetchUrl(a.a['href'])
+            soupAuth = bs.BeautifulSoup(dataAuth)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(a.a['href'])
+            else:
+                raise e
+
+        storyLink = soupAuth.find('a', href=url1)
+
+        if storyLink is not None:
+            # pull the published date from the author page
+            # default values from single link.  Updated below if multiple chapter.
+            date = storyLink.parent.parent.findAll('td')[-1].text
+            self.story.setMetadata('datePublished', makeDate(date, self.dateformat))
+            self.story.setMetadata('dateUpdated',makeDate(date, self.dateformat))
+
+        # find num of pages
+        # find a "3 Pages:" string on the page and parse it
+        pgs = soup1.find("span", "b-pager-caption-t r-d45").string.split(' ')[0]
+
+        # If there are multiple pages, find and request the last page
+        if "1" != pgs:
+            logger.debug("last page number: "+pgs)
+            try:
+                data2 = self._fetchUrl(url1, {'page': pgs})
+                soup2 = bs.BeautifulSoup(data2)
+                [comment.extract() for comment in soup2.findAll(text=lambda text:isinstance(text, bs.Comment))]
+            except urllib2.HTTPError, e:
+                if e.code == 404:
+                    # TODO: Probably should reformat this
+                    raise exceptions.StoryDoesNotExist(url1, {'page': pgs})
+                else:
+                    raise e
+        else:
+            #If we're already on the last page, copy the soup
+            soup2 = soup1
+
+        # parse out the list of chapters
+        chaps = soup2.find('div', id='b-series')
+        if chaps:  # may be one post only
+            #self.chapterUrls = [(ch.a.text, ch.a['href']) for ch in chaps.findAll('li')]
+
+            # if there are chapters, lets pull them and title from the
+            # author page because *this* chapter is omitted from the
+            # list on the last page.
+            row = storyLink.parent.parent.previousSibling
+            while row['class'] != 'ser-ttl':
+                row = row.previousSibling
+
+            seriesTitle = stripHTML(row)
+            if seriesTitle:
+                # this regex is deliberately greedy. We want to get the biggest match before a ':'
+                self.story.setMetadata('title', re.match('(.*):[^:]*$', seriesTitle).group(1))
+            else:
+                self.story.setMetadata('title', soup1.h1.string)
+
+            # now chapter list.  Assumed oldest to newest.
+            self.chapterUrls = []
+            row = row.nextSibling
+                
+            self.story.setMetadata('datePublished',makeDate(stripHTML(row.find('td',{'class':'dt'})), self.dateformat))
+            while row['class'] == 'sl':
+                # pages include full URLs.
+                self.chapterUrls.append((row.a.string,row.a['href']))
+                if not row.nextSibling:
+                    break
+                row = row.nextSibling
+
+            row = row.previousSibling
+            self.story.setMetadata('dateUpdated',makeDate(stripHTML(row.find('td',{'class':'dt'})), self.dateformat))
+                
+        else:  # if one post only
+            self.chapterUrls = [(soup1.h1.string, url1)]
+            self.story.setMetadata('title', soup1.h1.string)
+
+        # normalize on first chapter URL.
+        self._setURL(self.chapterUrls[0][1])
+
+        # reset storyId to first chapter.
+        self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])
+
+        self.story.setMetadata('numChapters', len(self.chapterUrls))
+
+        self.story.setMetadata('category', soup1.find('div', 'b-breadcrumbs').findAll('a')[1].string)
+        self.story.setMetadata('description', soup1.find('meta', {'name': 'description'})['content'])
+
+        return
+
+    def getChapterText(self, url):
+        logger.debug('Getting chapter text from: %s' % url)
+        time.sleep(0.5)
+        data1 = self._fetchUrl(url)
+        soup1 = bs.BeautifulSoup(data1)
+
+        #strip comments from soup
+        [comment.extract() for comment in soup1.findAll(text=lambda text:isinstance(text, bs.Comment))]
+
+        # get story text
+        story1 = soup1.find('div', 'b-story-body-x').p
+        story1.name='div'
+        story1.append('<br>')
+        storytext = self.utf8FromSoup(url,story1)
+
+        # find num pages
+        pgs = int(soup1.find("span", "b-pager-caption-t r-d45").string.split(' ')[0])
+        logger.debug("pages: "+str(pgs))
+
+        # get all the pages
+        for i in xrange(2, pgs+1):
+            try:
+                logger.debug("fetching page "+str(i))
+                time.sleep(0.5)
+                data2 = self._fetchUrl(url, {'page': i})
+                soup2 = bs.BeautifulSoup(data2)
+                [comment.extract() for comment in soup2.findAll(text=lambda text:isinstance(text, bs.Comment))]
+                story2 = soup2.find('div', 'b-story-body-x').p
+                story2.name='div'
+                story2.append('<br>')
+                storytext += self.utf8FromSoup(url,story2)
+            except urllib2.HTTPError, e:
+                if e.code == 404:
+                    raise exceptions.StoryDoesNotExist(url)
+                else:
+                    raise e
+        return storytext
+
+
+def getClass():
+    return LiteroticaSiteAdapter
+
+
+

fanficdownloader/adapters/adapter_lumossycophanthexcom.py

@@ -48,7 +48,7 @@ class LumosSycophantHexComAdapter(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.
@@ -116,7 +116,7 @@ class LumosSycophantHexComAdapter(BaseSiteAdapter):
         ## Title
         pt = soup.find('div', {'id' : 'pagetitle'})
         a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.text)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = pt.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_mediaminerorg.py

@@ -43,7 +43,7 @@ class MediaMinerOrgSiteAdapter(BaseSiteAdapter):
         m = re.match(self.getSiteURLPattern(),url)
         if m:
             self.story.setMetadata('storyId',m.group('id'))
-            logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+            
             # normalized story URL.
             self._setURL('http://' + self.getSiteDomain() + '/fanfic/view_st.php/'+self.story.getMetadata('storyId'))
         else:
@@ -107,10 +107,10 @@ class MediaMinerOrgSiteAdapter(BaseSiteAdapter):
         for font in title.findAll('font'):
             font.extract() # removes 'font' tags from inside the td.        
         if title.has_key('colspan'):
-            titlet = title.text
+            titlet = stripHTML(title)
         else:
             ## No colspan, it's part chapter title--even if it's a one-shot.
-            titlet = ':'.join(title.text.split(':')[:-1]) # strip trailing 'Chapter X' or chapter title
+            titlet = ':'.join(stripHTML(title).split(':')[:-1]) # strip trailing 'Chapter X' or chapter title
         self.story.setMetadata('title',titlet)
         ## The story title is difficult to reliably parse from the
         ## story pages.  Getting it from the author page is, but costs

fanficdownloader/adapters/adapter_merlinficdtwinscouk.py

@@ -48,7 +48,7 @@ class MerlinFicDtwinsCoUk(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() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -170,7 +170,7 @@ class MerlinFicDtwinsCoUk(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_midnightwhispersca.py

@@ -52,7 +52,7 @@ class MidnightwhispersCaAdapter(BaseSiteAdapter): # XXX
         
         # 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.

fanficdownloader/adapters/adapter_mugglenetcom.py

@@ -52,7 +52,7 @@ class MuggleNetComAdapter(BaseSiteAdapter): # XXX
         
         # 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'))
@@ -193,7 +193,7 @@ class MuggleNetComAdapter(BaseSiteAdapter): # XXX
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_nationallibrarynet.py

@@ -48,7 +48,7 @@ class NationalLibraryNetAdapter(BaseSiteAdapter):
         
         # get storyId from url--url validation guarantees query is only storyid=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?storyid='+self.story.getMetadata('storyId'))
@@ -104,7 +104,7 @@ class NationalLibraryNetAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('h1')
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"authorresults.php\?author=\d+"))

fanficdownloader/adapters/adapter_ncisficcom.py

@@ -48,7 +48,7 @@ class NCISFicComAdapter(BaseSiteAdapter):
         
         # get storyId from url--url validation guarantees query is only storyid=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?storyid='+self.story.getMetadata('storyId'))
@@ -103,7 +103,7 @@ class NCISFicComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('h1')
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"authorresults.php\?author=\d+"))

fanficdownloader/adapters/adapter_ncisfictionnet.py

@@ -37,11 +37,6 @@ class NCISFictionNetAdapter(BaseSiteAdapter):
     def __init__(self, config, url):
         BaseSiteAdapter.__init__(self, config, url)
 
-        # ncisfiction.net blocks IPs the default user-agent.  However,
-        # when asked, they said it was just general anti-spam, not
-        # targeted at us.  That lets me do this in good conscience:
-        self.opener.addheaders = [('User-agent', 'FFDL/1.6')]
-        
         self.decode = ["iso-8859-1",
                        "Windows-1252"] # 1252 is a superset of iso-8859-1.
                                # Most sites that claim to be
@@ -53,7 +48,7 @@ class NCISFictionNetAdapter(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()\

fanficdownloader/adapters/adapter_netraptororg.py

@@ -46,7 +46,7 @@ class NetRaptorOrgAdapter(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() + '/fanfiction/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -97,7 +97,7 @@ class NetRaptorOrgAdapter(BaseSiteAdapter):
         ## Title
         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)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_nfacommunitycom.py

@@ -52,7 +52,7 @@ class NfaCommunityComAdapter(BaseSiteAdapter): # XXX
         
         # 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.
@@ -156,7 +156,7 @@ class NfaCommunityComAdapter(BaseSiteAdapter): # XXX
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_nhamagicalworldsus.py

@@ -48,7 +48,7 @@ class NHAMagicalWorldsUsAdapter(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.
@@ -115,7 +115,7 @@ class NHAMagicalWorldsUsAdapter(BaseSiteAdapter):
             a = info.find('a')
             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)
+                self.story.setMetadata('title',stripHTML(a))
                 break
 		
 

fanficdownloader/adapters/adapter_nickandgregnet.py

@@ -48,7 +48,7 @@ class NickAndGregNetAdapter(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.
         # XXX Most sites don't have the /fanfic part.  Replace all to remove it usually.
@@ -101,7 +101,7 @@ class NickAndGregNetAdapter(BaseSiteAdapter):
 
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
@@ -166,10 +166,11 @@ class NickAndGregNetAdapter(BaseSiteAdapter):
 
         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)
-    
+        # wrap a div around it.
+        divsoup = bs.BeautifulStoneSoup('<div class="story"></div>',
+                                        selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        div = divsoup.find('div')
+        div.append(soup.find('table', {'class' : 'tblborder6'}))
+
         return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_occlumencysycophanthexcom.py

@@ -48,7 +48,7 @@ class OcclumencySycophantHexComAdapter(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.
@@ -158,7 +158,7 @@ class OcclumencySycophantHexComAdapter(BaseSiteAdapter):
         for info in asoup.findAll('table', {'class' : 'border'}):
             a = info.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
             if a != None:
-                self.story.setMetadata('title',a.text)
+                self.story.setMetadata('title',stripHTML(a))
                 break
 		
 

fanficdownloader/adapters/adapter_onedirectionfanfictioncom.py

@@ -48,7 +48,7 @@ class OneDirectionFanfictionComAdapter(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() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -158,7 +158,7 @@ class OneDirectionFanfictionComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_phoenixsongnet.py

@@ -48,7 +48,7 @@ class PhoenixSongNetAdapter(BaseSiteAdapter):
         
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[3])
-        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
         
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/fanfiction/story/' +self.story.getMetadata('storyId')+'/')
@@ -136,7 +136,7 @@ class PhoenixSongNetAdapter(BaseSiteAdapter):
         ## Title
         b = soup.find('div', {'id' : 'nav25'})
         a = b.find('a', href=re.compile(r'fanfiction/story/'+self.story.getMetadata('storyId')+"/$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.  /fanfiction/stories.php?psid=125
         a = b.find('a', href=re.compile(r"/fanfiction/stories.php\?psid=\d+"))

fanficdownloader/adapters/adapter_pommedesangcom.py

@@ -48,7 +48,7 @@ class PommeDeSangComAdapter(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'))
+        
         
         # pommedesang.com has two 'sections', shown in URL as
         # 'efiction' and 'sds' that change how things should be
@@ -180,7 +180,7 @@ class PommeDeSangComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile('viewstory.php\?sid=\d+'))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_ponyfictionarchivenet.py

@@ -48,8 +48,7 @@ class PonyFictionArchiveNetAdapter(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'))
-        logger.info(self.parsedUrl.netloc)
+        
         # normalized story URL.
         if "explicit" in self.parsedUrl.netloc:
             self._setURL('http://explicit.' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -137,7 +136,7 @@ class PonyFictionArchiveNetAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_portkeyorg.py

@@ -55,7 +55,7 @@ class PortkeyOrgAdapter(BaseSiteAdapter): # XXX
         
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2])
-        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
         
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/story/'+self.story.getMetadata('storyId'))
@@ -251,8 +251,10 @@ class PortkeyOrgAdapter(BaseSiteAdapter): # XXX
 
         logger.debug('Getting chapter text from: %s' % url)
         data = self._fetchUrl(url)
-        soup = bs.BeautifulStoneSoup(data,
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+
+        data = data.replace("HTML>","div>")
+        
+        soup = bs.BeautifulSoup(data)
 
         #print("soup:%s"%soup)
         tag = soup.find('td', {'class' : 'story'})

fanficdownloader/adapters/adapter_potionsandsnitchesnet.py

@@ -41,7 +41,7 @@ class PotionsAndSnitchesNetSiteAdapter(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() + '/fanfiction/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -83,7 +83,7 @@ class PotionsAndSnitchesNetSiteAdapter(BaseSiteAdapter):
 
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
@@ -163,12 +163,11 @@ class PotionsAndSnitchesNetSiteAdapter(BaseSiteAdapter):
                     self.story.setMetadata('status', 'In-Progress')
 
             if 'Published' in label:
-                self.story.setMetadata('datePublished', makeDate(stripHTML(value), "%d %b %Y"))
+                # limit date values, there's some extra chars.
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value[:12]), "%d %b %Y"))
             
             if 'Updated' in label:
-                # there's a stray [ at the end.
-                #value = value[0:-1]
-                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), "%d %b %Y"))
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value[:12]), "%d %b %Y"))
 
         try:
             # Find Series name from series URL.

fanficdownloader/adapters/adapter_potterficscom.py

@@ -54,7 +54,7 @@ class PotterFicsComAdapter(BaseSiteAdapter):
         m = re.match(self.getSiteURLPattern(),url)
         if m:
             self.story.setMetadata('storyId',m.group('id'))
-            logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+            
             # normalized story URL. gets rid of chapter if there, left with chapter index URL
             nurl = "http://"+self.getSiteDomain()+"/historias/"+self.story.getMetadata('storyId')
             self._setURL(nurl)
@@ -62,7 +62,7 @@ class PotterFicsComAdapter(BaseSiteAdapter):
             raise exceptions.InvalidStoryURL(url,
                                              self.getSiteDomain(),
                                              self.getSiteExampleURLs())
-        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
         
         # Each adapter needs to have a unique site abbreviation.
         self.story.setMetadata('siteabbrev','potficscom')
@@ -147,7 +147,7 @@ class PotterFicsComAdapter(BaseSiteAdapter):
         #find first metadata block
         mb = cell.div.findNextSibling('div')
         #Get meta...
-        self.story.setMetadata('title', mb.b.string)
+        self.story.setMetadata('title', stripHTML(mb.b))
         #strip out brackets on rating
         self.story.setMetadata('rating', mb.span.string[1:-1])
         #Completion status is denoted by the presence of this image:

fanficdownloader/adapters/adapter_potterheadsanonymouscom.py

@@ -48,7 +48,7 @@ class PotterHeadsAnonymousComAdapter(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() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -181,7 +181,7 @@ class PotterHeadsAnonymousComAdapter(BaseSiteAdapter):
         
         ## Title
         a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_pretendercentrecom.py

@@ -48,7 +48,7 @@ class PretenderCenterComAdapter(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() + '/missingpieces/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -134,7 +134,7 @@ class PretenderCenterComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.text)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_psychficcom.py

@@ -48,7 +48,7 @@ class PsychFicComAdapter(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() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -130,7 +130,7 @@ class PsychFicComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_qafficcom.py

@@ -48,7 +48,7 @@ class QafFicComAdapter(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() + '/atp/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -138,7 +138,7 @@ class QafFicComAdapter(BaseSiteAdapter):
         self.story.setMetadata('author',aut.string)
         aut.extract()
         
-        self.story.setMetadata('title',a.string[:(len(a.string)-3)])
+        self.story.setMetadata('title',stripHTML(a)[:(len(a.string)-3)])
 
         # Find the chapters:
         chapters=soup.find('select')

fanficdownloader/adapters/adapter_restrictedsectionorg.py

@@ -22,7 +22,6 @@ import re
 import urllib2
 import cookielib as cl
 from datetime import datetime
-import json
 
 from .. import BeautifulSoup as bs
 from ..htmlcleanup import stripHTML
@@ -52,10 +51,9 @@ class RestrictedSectionOrgSiteAdapter(BaseSiteAdapter):
         m = re.match(self.getSiteURLPattern(),url)
         if m:
             self.story.setMetadata('storyId',m.group('id'))
-            logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+            
             # normalized story URL.
             self._setURL('http://' + self.getSiteDomain() + '/' + m.group('filestory') + '.php?' + m.group('filestory') + '=' + self.story.getMetadata('storyId'))
-            logger.debug("storyUrl: (%s)"%self.story.getMetadata('storyUrl'))
         else:
             raise exceptions.InvalidStoryURL(url,
                                              self.getSiteDomain(),
@@ -127,10 +125,12 @@ class RestrictedSectionOrgSiteAdapter(BaseSiteAdapter):
         
         self.story.setMetadata('authorId',ahref.split('=')[1])
         self.story.setMetadata('authorUrl','http://'+self.host+'/'+ahref)
-        self.story.setMetadata('author',a.string)
+        self.story.setMetadata('author',stripHTML(a))
 
         # title, remove byauthorname.
-        self.story.setMetadata('title',h2.text[:h2.text.index("by"+a.string)])
+        auth=stripHTML(a)
+        title=stripHTML(h2)
+        self.story.setMetadata('title',title[:title.index(" by "+auth)])
 
         dates = soup.findAll('span', {'class':'date'})
         if dates: # only for multi-chapter

fanficdownloader/adapters/adapter_samdeanarchivenu.py

@@ -48,7 +48,7 @@ class SamDeanArchiveNuAdapter(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() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -110,7 +110,7 @@ class SamDeanArchiveNuAdapter(BaseSiteAdapter):
         self.story.setMetadata('author',aut.string)
         aut.extract()
         
-        self.story.setMetadata('title',a.string[:(len(a.string)-3)])
+        self.story.setMetadata('title',stripHTML(a)[:(len(stripHTML(a))-3)])
 
         # Find the chapters:
         chapters=soup.find('select')

fanficdownloader/adapters/adapter_scarheadnet.py

@@ -48,7 +48,7 @@ class ScarHeadNetAdapter(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() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -181,7 +181,7 @@ class ScarHeadNetAdapter(BaseSiteAdapter):
         
         ## Title
         a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_scarvesandcoffeenet.py

@@ -48,7 +48,7 @@ class ScarvesAndCoffeeNetAdapter(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() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -139,7 +139,7 @@ class ScarvesAndCoffeeNetAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('div',{"id":"pagetitle"}).find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_sg1heliopoliscom.py

@@ -48,7 +48,7 @@ class SG1HeliopolisComAdapter(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'))
+        
         self.section=self.parsedUrl.path.split('/',)[1]
         
         # normalized story URL.
@@ -140,7 +140,7 @@ class SG1HeliopolisComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_simplyundeniablecom.py

@@ -48,7 +48,7 @@ class SimplyUndeniableComAdapter(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() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -143,7 +143,7 @@ class SimplyUndeniableComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('h1')
-        self.story.setMetadata('title',a.text)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
@@ -155,7 +155,7 @@ class SimplyUndeniableComAdapter(BaseSiteAdapter):
         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)
+                self.story.setMetadata('title',stripHTML(a))
                 break
                 
         # Find the chapters:
@@ -214,5 +214,6 @@ class SimplyUndeniableComAdapter(BaseSiteAdapter):
 
         if None == div:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+        div.name='div'
     
         return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_sinfuldesireorg.py

@@ -48,7 +48,7 @@ class SinfulDesireOrgAdapter(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() + '/archive/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -130,7 +130,7 @@ class SinfulDesireOrgAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_siyecouk.py

@@ -49,7 +49,7 @@ class SiyeCoUkAdapter(BaseSiteAdapter): # XXX
         
         # 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() + '/siye/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -241,5 +241,6 @@ class SiyeCoUkAdapter(BaseSiteAdapter): # XXX
         
         if None == story:
             raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+        story.name='div'
     
         return self.utf8FromSoup(url,story)

fanficdownloader/adapters/adapter_squidgeorgpeja.py

@@ -59,7 +59,7 @@ class SquidgeOrgPejaAdapter(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() + '/peja/cgi-bin/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -103,6 +103,9 @@ class SquidgeOrgPejaAdapter(BaseSiteAdapter):
                 raise e
 
         data = self._fetchUrl(url)
+
+        if "fatal MySQL error was encountered" in data:
+            raise exceptions.FailedToDownload("Site SQL Error--bad story")
             
         # use BeautifulSoup HTML parser to make everything easier to find.
         soup = bs.BeautifulSoup(data)
@@ -122,7 +125,7 @@ class SquidgeOrgPejaAdapter(BaseSiteAdapter):
         # formating, so it's a little ugly.
 
         title = authorSoup.find('a',{'href':'viewstory.php?sid='+self.story.getMetadata('storyId')})
-        self.story.setMetadata('title',title.string)
+        self.story.setMetadata('title',stripHTML(title))
         titleblock=title.parent.parent
         
         chapterselect=soup.find('select',{'name':'chapter'})

fanficdownloader/adapters/adapter_stargateatlantisorg.py

@@ -48,7 +48,7 @@ class StargateAtlantisOrgAdapter(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() + '/fanfics/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -106,7 +106,7 @@ class StargateAtlantisOrgAdapter(BaseSiteAdapter):
         self.story.setMetadata('author',aut.string)
         aut.extract()
         
-        self.story.setMetadata('title',a.string[:(len(a.string)-3)])
+        self.story.setMetadata('title',stripHTML(a)[:(len(stripHTML(a))-3)])
 
         # Find the chapters:
         chapters=soup.findAll('div', {'class' : 'content'})

fanficdownloader/adapters/adapter_storiesofardacom.py

@@ -48,7 +48,7 @@ class StoriesOfArdaComAdapter(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() + '/chapterlistview.asp?SID='+self.story.getMetadata('storyId'))
@@ -104,7 +104,7 @@ class StoriesOfArdaComAdapter(BaseSiteAdapter):
         asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
         
         a.find('em').extract()
-        self.story.setMetadata('title',a.text)
+        self.story.setMetadata('title',stripHTML(a))
 
         # Find the chapters: chapterview.asp?sid=7000&cid=30919
         chapters=soup.findAll('a', href=re.compile(r'chapterview.asp\?sid='+self.story.getMetadata('storyId')+"&cid=\d+$"))
@@ -137,8 +137,20 @@ class StoriesOfArdaComAdapter(BaseSiteAdapter):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+        if self.getConfig('is_adult'):
+            params = {'confirmAge':'1'}
+            data = self._postUrl(url,params)
+        else:
+            data = self._fetchUrl(url)
+
+        data = data[data.index('<table width="90%" align="center">'):]
+        data.replace("<body","<notbody").replace("<BODY","<NOTBODY")
+            
+        soup = bs.BeautifulStoneSoup(data,
                                      selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+
+        if "Please indicate that you are an adult by selecting the appropriate choice below" in data:
+            raise exceptions.FailedToDownload("Chapter requires you be an adult.  Set is_adult in personal.ini (chapter url:%s)" % url)
         
         div = soup.find('table', {'width' : '90%'}).find('td')
         div.name='div'

fanficdownloader/adapters/adapter_storiesonlinenet.py

@@ -0,0 +1,401 @@
+# -*- 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 StoriesOnlineNetAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class StoriesOnlineNetAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url
+        self.story.setMetadata('storyId',self.parsedUrl.path.split('/',)[2].split(':')[0])
+        if 'storyInfo' in self.story.getMetadata('storyId'):
+            self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/s/'+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','strol')
+
+        # 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 'storiesonline.net'
+
+    @classmethod
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/s/1234 http://"+self.getSiteDomain()+"/s/1234:4010"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain())+r"/s/\d+((:\d+)?(;\d+)?$|(:i)?$)"
+
+    ## Login seems to be reasonably standard across eFiction sites.
+    def needToLoginCheck(self, data):
+        if 'Free Registration' in data \
+                or "Invalid Password!" in data \
+                or "Invalid User Name!" in data \
+                or "Log In" in data \
+                or "Access to unlinked chapters requires" in data:
+            return True
+        else:
+            return False
+        
+    def performLogin(self, url):
+        params = {}
+
+        if self.password:
+            params['theusername'] = self.username
+            params['thepassword'] = self.password
+        else:
+            params['theusername'] = self.getConfig("username")
+            params['thepassword'] = self.getConfig("password")
+        params['rememberMe'] = '1'
+        params['page'] = 'http://'+self.getSiteDomain()+'/'
+        params['submit'] = 'Login'
+    
+        loginUrl = 'http://' + self.getSiteDomain() + '/login.php'
+        logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
+                                                              params['theusername']))
+    
+        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['theusername']))
+            raise exceptions.FailedToLogin(url,params['theusername'])
+            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+":i")
+        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+":i")
+        
+        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.")
+        elif "Error! The story you're trying to access is being filtered by your choice of contents filtering." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Error! The story you're trying to access is being filtered by your choice of contents filtering.")
+            
+        # 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',stripHTML(a))
+        
+        notice = soup.find('div', {'class' : 'notice'})
+        if notice:
+            self.story.setMetadata('notice',unicode(notice))
+
+        # Find authorid and URL from... author url.
+        a = soup.find('a', href=re.compile(r"/a/\w+"))
+        self.story.setMetadata('authorId',a['href'].split('/')[2])
+        self.story.setMetadata('authorUrl','http://'+self.host+a['href'])
+        self.story.setMetadata('author',stripHTML(a).replace("'s Page",""))
+
+        # Find the chapters:
+        chapters = soup.findAll('a', href=re.compile(r'^/s/'+self.story.getMetadata('storyId')+":\d+$"))
+        if len(chapters) != 0:
+            for chapter in chapters:
+                # just in case there's tags, like <i> in chapter titles.
+                self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+chapter['href']))
+        else:
+            self.chapterUrls.append((self.story.getMetadata('title'),'http://'+self.host+'/s/'+self.story.getMetadata('storyId')))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # surprisingly, the detailed page does not give enough details, so go to author's page
+        skip=0
+        i=0
+        while i == 0:
+            asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')+"&skip="+str(skip)))
+
+            a = asoup.findAll('td', {'class' : 'lc2'})
+            for lc2 in a:
+                if lc2.find('a')['href'] == '/s/'+self.story.getMetadata('storyId'):
+                    i=1
+                    break
+                if a[len(a)-1] == lc2:
+                    skip=skip+10
+
+        for cat in lc2.findAll('div', {'class' : 'typediv'}):
+            self.story.addToList('genre',cat.text)
+
+        # in lieu of word count.
+        self.story.setMetadata('size', lc2.findNext('td', {'class' : 'num'}).text)
+        
+        lc4 = lc2.findNext('td', {'class' : 'lc4'})        
+        desc = lc4.contents[0]
+
+        try:
+            a = lc4.find('a', href=re.compile(r"/library/show_series.php\?id=\d+"))
+            if a:
+                # if there's a number after the series name, series_contents is a two element list:
+                # [<a href="...">Title</a>, u' (2)']
+                series_contents = a.parent.contents
+                i = 0 if len(series_contents) == 1 else series_contents[1].strip(' ()')
+                seriesUrl = 'http://'+self.host+a['href']
+                self.story.setMetadata('seriesUrl',seriesUrl)
+                series_name = stripHTML(a)
+                logger.debug("Series name= %s" % series_name)
+                series_soup = bs.BeautifulSoup(self._fetchUrl(seriesUrl))
+                if series_soup:
+                    logger.debug("Retrieving Series - looking for name")
+                    series_name = series_soup.find('span', {'id' : 'ptitle'}).text.partition(' — ')[0]
+                    logger.debug("Series name: '{0}'".format(series_name))
+                self.setSeries(series_name, i)
+                desc = lc4.contents[2]
+                # Check if series is in a universe
+                universes_soup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')  + "&type=uni")) 
+#                logger.debug("Universe page=", universes_soup)
+                if universes_soup:
+                    universes = universes_soup.findAll('div', {'class' : 'ser-box'})
+                    logger.debug("Number of Universes: %d" % len(universes))
+                    for universe in universes:
+                        logger.debug("universe.find('a')={0}".format(universe.find('a')))
+                        # The universe id is in an "a" tag that has an id but nothing else. It is the first tag.
+                        # The id is prefixed with the letter "u".
+                        universe_id = universe.find('a')['id'][1:]
+                        logger.debug("universe_id='%s'" % universe_id)
+                        universe_name = universe.find('div', {'class' : 'ser-name'}).text.partition(' ')[2]
+                        logger.debug("universe_name='%s'" % universe_name)
+                        # If there is link to the story, we have the right universe
+                        story_a = universe.find('a', {'href' : '/s/'+self.story.getMetadata('storyId')})
+                        if story_a:
+                            logger.debug("Story is in a series that is in a universe! The universe is '%s'" % universe_name)
+                            self.story.setMetadata("universe", universe_name)
+                            self.story.setMetadata('universeUrl','http://'+self.host+ '/library/universe.php?id=' + universe_id)
+                            break
+        except:
+            pass
+        try:
+            a = lc4.find('a', href=re.compile(r"/library/universe.php\?id=\d+"))
+            if a:
+                self.story.setMetadata("universe",stripHTML(a))
+                desc = lc4.contents[2]
+                # Assumed only one universe, but it does have a URL--use universeHTML
+                universe_name = stripHTML(a)
+                universeUrl = 'http://'+self.host+a['href']
+                logger.debug("Retrieving Universe - about to get page")
+                universe_soup = bs.BeautifulSoup(self._fetchUrl(universeUrl))
+                logger.debug("Retrieving Universe - have page")
+                if universe_soup:
+                    logger.debug("Retrieving Universe - looking for name")
+                    universe_name = universe_soup.find('span', {'id' : 'ptitle'}).text.partition(' &mdash;')[0]
+                    logger.debug("Universes name: '{0}'".format(universe_name))
+
+                self.story.setMetadata('universeUrl',universeUrl)
+                logger.debug("Setting universe name: '{0}'".format(universe_name))
+                self.story.setMetadata('universe',universe_name)
+                if self.getConfig("universe_as_series"):
+                    self.setSeries(universe_name, 0)
+                    self.story.setMetadata('seriesUrl',universeUrl)
+        except:
+            pass
+
+        self.setDescription('http://'+self.host+'/s/'+self.story.getMetadata('storyId'),desc)
+            
+        for b in lc4.findAll('b'):
+            #logger.debug('Getting metadata: "%s"' % b)
+            label = b.text
+            if label in ['Posted:', 'Concluded:', 'Updated:']:
+                value = b.findNext('noscript').text
+                #logger.debug('Have a date field label: "%s", value: "%s"' % (label, value))
+            else:
+                value = b.nextSibling
+            #logger.debug('label: "%s", value: "%s"' % (label, value))
+            
+            if 'Sex' in label:
+                self.story.setMetadata('rating', value)
+                
+            if 'Codes' in label:
+                for code in value.split(' '):
+                    self.story.addToList('codes',code)
+                    
+            if 'Posted' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+                
+            if 'Concluded' in label:
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+                
+            if 'Updated' in label:
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+#                
+        status = lc4.find('span', {'class' : 'ab'})
+        if  status != None:
+            self.story.setMetadata('status', 'In-Progress')
+            if "Last Activity" in status.text:
+                # date is passed as a timestamp and converted in JS.
+                value = status.findNext('noscript').text
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+        else:
+            self.story.setMetadata('status', 'Completed')
+
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logger.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div', {'id' : 'story'})
+        
+        # some big chapters are split over several pages
+        pager = div.find('span', {'class' : 'pager'})
+        if pager != None:
+            a = pager.previousSibling
+            while a != None:
+                logger.debug("before pager: {0}".format(a))
+                b = a.previousSibling
+                a.extract()
+                a = b
+
+            urls=pager.findAll('a')
+            urls=urls[:len(urls)-1]
+            pager.extract()
+            div.contents = div.contents[2:]
+#            logger.debug(div)
+                        
+            for ur in urls:
+                soup = bs.BeautifulSoup(self._fetchUrl("http://"+self.getSiteDomain()+ur['href']),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+                div1 = soup.find('div', {'id' : 'story'})
+                
+                # Find the "Continues" marker on the current page and remove everything after that. 
+                continues = div.find('span', {'class' : 'conTag'})
+                if continues != None:
+                    while continues != None:
+#                        logger.debug("removing end: {0}".format(continues))
+                        b = continues.nextSibling
+                        continues.extract()
+                        continues = b
+
+                # Find the "Continued" marker and delete everything before that
+                continued = div1.find('span', {'class' : 'conTag'})
+                if continued != None:
+                    a = continued.previousSibling
+                    while a != None:
+#                        logger.debug("before conTag: {0}".format(a))
+                        b = a.previousSibling
+                        a.extract()
+                        a = b
+                # Remove the pager from the end if this is the last page
+                endPager = div1.find('span', {'class' : 'pager'})
+                if endPager != None:
+                    b = endPager.nextSibling
+                    while endPager != None:
+                        logger.debug("removing end: {0}".format(endPager))
+                        b = endPager.nextSibling
+                        endPager.extract()
+                        endPager = b
+                    div1.contents = div1.contents[:len(div1) - 2]
+#                logger.debug("after removing pager: {0}".format(div1))
+                for tag in div1.contents[2:]:
+                    div.append(tag)
+
+        # If it is a chapter, there are dates at the start for when it was posted or modified. These plus 
+        # everything before them can be discarded. 
+        postedDates = div.findAll('div', {'class' : 'date'})
+        if postedDates:
+            a = postedDates[0].previousSibling
+            while a != None:
+#                logger.debug("before dates: {0}".format(a))
+                b = a.previousSibling
+                a.extract()
+                a = b
+            for a in div.findAll('div', {'class' : 'date'}):
+                a.extract()
+
+        # For single chapter stories, there is a copyright statement. Remove this and everything
+        # before it.
+        copy = div.find('h4', {'class': 'copy'})
+        while copy != None:
+#            logger.debug("before copyright: {0}".format(copy))
+            b = copy.previousSibling
+            copy.extract()
+            copy = b
+
+        # For a story or the last chapter, remove voting form and the in library box
+        a = div.find('div', {'id' : 'vote-form'})
+        if a != None:
+            a.extract()
+        a = div.find('div', {'id' : 'b-man-div'})
+        if a != None:
+            a.extract()
+
+        # Kill the "The End" header and everything after it.
+        a = div.find(['h2', 'h3'], {'class' : 'end'})
+        logger.debug("Chapter end= '{0}'".format(a))
+        while a != None:
+            b = a.nextSibling
+            a.extract()
+            a=b
+
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_tenhawkpresentscom.py

@@ -44,7 +44,7 @@ class TenhawkPresentsComSiteAdapter(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() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -133,7 +133,7 @@ class TenhawkPresentsComSiteAdapter(BaseSiteAdapter):
 
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_test1.py

@@ -50,6 +50,7 @@ class TestSiteAdapter(BaseSiteAdapter):
     def extractChapterUrlsAndMetadata(self):
         idstr = self.story.getMetadata('storyId')
         idnum = int(idstr)
+        self.do_sleep()
 
         if idnum >= 1000:
             logger.warn("storyId:%s - Custom INI data will be used."%idstr)
@@ -296,6 +297,7 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
 
     def getChapterText(self, url):
         logger.debug('Getting chapter text from: %s' % url)
+        self.do_sleep()
         if self.story.getMetadata('storyId').startswith('670') or \
                 self.story.getMetadata('storyId').startswith('672'):
             time.sleep(1.0)
@@ -323,7 +325,7 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
 </div>
 '''
         elif self.story.getMetadata('storyId') == '0':
-            text=u'''
+            text=u'''<div>
 <h3>45. Pronglet Returns to Hogwarts: Chapter 7</h3>
 <br />
     eyes… but I’m not convinced we should automatically<br />
@@ -332,6 +334,7 @@ Some more longer description.  "I suck at summaries!"  "Better than it sounds!"
 <br /><br />
     “Sure, invite her along. Does she have children?”<br />
 <br />
+</div>
 '''
         else:
             if self.story.getMetadata('storyId') == '667':

fanficdownloader/adapters/adapter_thealphagatecom.py

@@ -48,7 +48,7 @@ class TheAlphaGateComAdapter(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() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -99,7 +99,7 @@ class TheAlphaGateComAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_thehexfilesnet.py

@@ -48,7 +48,7 @@ class TheHexFilesNetAdapter(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() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))

fanficdownloader/adapters/adapter_thehookupzonenet.py

@@ -72,7 +72,7 @@ class TheHookupZoneNetAdapter(BaseSiteAdapter): # XXX
         
         # 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.
@@ -179,7 +179,7 @@ class TheHookupZoneNetAdapter(BaseSiteAdapter): # XXX
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))

fanficdownloader/adapters/adapter_themasquenet.py

@@ -48,7 +48,7 @@ class TheMasqueNetAdapter(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'))
+        
         
         if self.parsedUrl.path.split('/',)[1] == 'wiktt':
             self.story.addToList("category","Harry Potter")
@@ -177,7 +177,7 @@ class TheMasqueNetAdapter(BaseSiteAdapter):
         
         ## Title
         a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        self.story.setMetadata('title',a.string)
+        self.story.setMetadata('title',stripHTML(a))
         
         # Find authorid and URL from... author url.
         a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))