Bump versions.

meta section, fix highbyte chars in description.

app.yaml

@@ -1,6 +1,6 @@
 # ffd-retief-hrd fanfictiondownloader
 application: fanfictiondownloader
-version: 4-4-58
+version: 4-4-63
 runtime: python27
 api_version: 1
 threadsafe: true

calibre-plugin/__init__.py

@@ -26,7 +26,7 @@ class FanFictionDownLoaderBase(InterfaceActionBase):
     description         = 'UI plugin to download FanFiction stories from various sites.'
     supported_platforms = ['windows', 'osx', 'linux']
     author              = 'Jim Miller'
-    version             = (1, 7, 25)
+    version             = (1, 7, 30)
     minimum_calibre_version = (0, 8, 57)
 
     #: This field defines the GUI plugin class that contains all the code

calibre-plugin/config.py

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

calibre-plugin/dialogs.py

@@ -17,7 +17,8 @@ from PyQt4 import QtGui
 from PyQt4.Qt import (QDialog, QTableWidget, QVBoxLayout, QHBoxLayout, QGridLayout,
                       QPushButton, QString, QLabel, QCheckBox, QIcon, QLineEdit,
                       QComboBox, QVariant, QProgressDialog, QTimer, QDialogButtonBox,
-                      QPixmap, Qt, QAbstractItemView, SIGNAL, QTextEdit, pyqtSignal)
+                      QPixmap, Qt, QAbstractItemView, SIGNAL, QTextEdit, pyqtSignal,
+                      QGroupBox, QFrame)
 
 from calibre.gui2.dialogs.confirm_delete import confirm
 from calibre.gui2.complete2 import EditWithComplete
@@ -48,6 +49,8 @@ anthology_collision_order=[UPDATE,
                            UPDATEALWAYS,
                            OVERWRITEALWAYS]
 
+gpstyle='QGroupBox {border:0; padding-top:10px; padding-bottom:0px; margin-bottom:0px;}' #  background-color:red;
+
 class RejectUrlEntry:
 
     matchpat=re.compile(r"^(?P<url>[^,]+)(,(?P<fullnote>(((?P<title>.+) by (?P<auth>.+?)( - (?P<note>.+))?)|.*)))?$")
@@ -200,6 +203,24 @@ class AddNewDialog(SizePersistedDialog):
         # elements to show again when doing *update* merge
         self.mergeupdateshow = []
 
+        self.groupbox = QGroupBox("Show Download Options")
+        self.groupbox.setCheckable(True)
+        self.groupbox.setChecked(False)
+        self.groupbox.setFlat(True)
+        print("style:%s"%self.groupbox.styleSheet())
+        self.groupbox.setStyleSheet(gpstyle);
+
+        self.gbf = QFrame()
+        self.gbl = QVBoxLayout()
+        self.gbl.addWidget(self.gbf)
+        self.groupbox.setLayout(self.gbl)
+        self.gbl = QVBoxLayout()
+        self.gbf.setLayout(self.gbl)
+        self.l.addWidget(self.groupbox)
+
+        self.gbf.setVisible(False)
+        self.groupbox.toggled.connect(self.gbf.setVisible)
+        
         horz = QHBoxLayout()
         label = QLabel('Output &Format:')
         self.mergehide.append(label)
@@ -215,7 +236,7 @@ class AddNewDialog(SizePersistedDialog):
         horz.addWidget(label)
         label.setBuddy(self.fileform)
         horz.addWidget(self.fileform)
-        self.l.addLayout(horz)
+        self.gbl.addLayout(horz)
         self.mergehide.append(self.fileform)
 
         horz = QHBoxLayout()
@@ -230,7 +251,7 @@ class AddNewDialog(SizePersistedDialog):
             self.collision.setCurrentIndex(i)
         self.collisionlabel.setBuddy(self.collision)
         horz.addWidget(self.collision)
-        self.l.addLayout(horz)
+        self.gbl.addLayout(horz)
         self.mergehide.append(self.collisionlabel)
         self.mergehide.append(self.collision)
         self.mergeupdateshow.append(self.collisionlabel)
@@ -250,7 +271,7 @@ class AddNewDialog(SizePersistedDialog):
         horz.addWidget(self.updateepubcover)
         self.mergehide.append(self.updateepubcover)
         
-        self.l.addLayout(horz)
+        self.gbl.addLayout(horz)
 
         self.button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
         self.button_box.accepted.connect(self.ok_clicked)
@@ -288,6 +309,8 @@ class AddNewDialog(SizePersistedDialog):
         self.newmerge = newmerge
         self.extraoptions = extraoptions
         self.extrapayload = extrapayload
+
+        self.groupbox.setVisible(not(self.merge and self.newmerge))
         
         if self.merge:
             self.toplabel.setText('Story URL(s) for anthology, one per line:')
@@ -625,8 +648,25 @@ class UpdateExistingDialog(SizePersistedDialog):
 
         options_layout = QHBoxLayout()
 
+        groupbox = QGroupBox("Show Download Options")
+        groupbox.setCheckable(True)
+        groupbox.setChecked(False)
+        groupbox.setFlat(True)
+        groupbox.setStyleSheet(gpstyle)
+
+        gbf = QFrame()
+        gbl = QVBoxLayout()
+        gbl.addWidget(gbf)
+        groupbox.setLayout(gbl)
+        gbl = QHBoxLayout()
+        gbf.setLayout(gbl)
+        options_layout.addWidget(groupbox)
+
+        gbf.setVisible(False)
+        groupbox.toggled.connect(gbf.setVisible)
+        
         label = QLabel('Output &Format:')
-        options_layout.addWidget(label)
+        gbl.addWidget(label)
         self.fileform = QComboBox(self)
         self.fileform.addItem('epub')
         self.fileform.addItem('mobi')
@@ -636,10 +676,10 @@ class UpdateExistingDialog(SizePersistedDialog):
         self.fileform.setToolTip('Choose output format to create.  May set default from plugin configuration.')
         self.fileform.activated.connect(self.set_collisions)
         label.setBuddy(self.fileform)
-        options_layout.addWidget(self.fileform)
+        gbl.addWidget(self.fileform)
         
         label = QLabel('Update Mode:')
-        options_layout.addWidget(label)
+        gbl.addWidget(label)
         self.collision = QComboBox(self)
         self.collision.setToolTip("What sort of update to perform.  May set default from plugin configuration.")
         # add collision options
@@ -648,17 +688,19 @@ class UpdateExistingDialog(SizePersistedDialog):
         if i > -1:
             self.collision.setCurrentIndex(i)
         label.setBuddy(self.collision)
-        options_layout.addWidget(self.collision)
+        gbl.addWidget(self.collision)
 
         self.updatemeta = QCheckBox('Update Calibre &Metadata?',self)
         self.updatemeta.setToolTip("Update metadata for existing stories in Calibre from web site?\n(Columns set to 'New Only' in the column tabs will only be set for new books.)")
         self.updatemeta.setChecked(prefs['updatemeta'])
-        options_layout.addWidget(self.updatemeta)
+        gbl.addWidget(self.updatemeta)
                 
         self.updateepubcover = QCheckBox('Update EPUB Cover?',self)
         self.updateepubcover.setToolTip('Update book cover image from site or defaults (if found) <i>inside</i> the EPUB when EPUB is updated.')
         self.updateepubcover.setChecked(prefs['updateepubcover'])
-        options_layout.addWidget(self.updateepubcover)
+        gbl.addWidget(self.updateepubcover)
+
+
         
         button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
         button_box.accepted.connect(self.accept)

calibre-plugin/ffdl_plugin.py

@@ -862,11 +862,25 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                                                "<p>Click '<b>Yes</b>' to %se book with new URL.</p>"%updat+
                                                "<p>Click '<b>No</b>' to skip %sing this book.</p>"%updat,
                                                show_copy_button=False):
-                            book['comment'] = "Update declined by user due to differing story URL(%s)"%liburl
-                            book['good']=False
-                            book['icon']='rotate-right.png'
-                            book['status'] = 'Different URL'
-                            return
+                            if question_dialog(self.gui, 'Download as New Book?',
+                                               '<h3>Download as New Book?</h3>'+
+                                               '<p><b>%s</b> by <b>%s</b> is already in your library with a different source URL.</p>'%
+                                               (mi.title,', '.join(mi.author))+
+                                               '<p>You chose not to update the existing book.  Do you want to add a new book for this URL?</p>'+
+                                               '<p>New URL: <a href="%(newurl)s">%(newurl)s</a></p>'%
+                                               {'newurl':book['url']}+
+                                               "<p>Click '<b>Yes</b>' to a new book with new URL.</p>"+
+                                               "<p>Click '<b>No</b>' to skip URL.</p>",
+                                               show_copy_button=False):
+                                book_id = None
+                                mi = None
+                                book['calibre_id'] = None
+                            else:
+                                book['comment'] = "Update declined by user due to differing story URL(%s)"%liburl
+                                book['good']=False
+                                book['icon']='rotate-right.png'
+                                book['status'] = 'Different URL'
+                                return
         
             if book_id != None and collision != ADDNEW:
                 if collision in (CALIBREONLY):
@@ -1309,15 +1323,6 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                 except:
                     print("Failed to set_cover, skipping")
 
-        # set author link if found.  All current adapters have authorUrl, except anonymous on AO3.
-        if 'authorUrl' in book['all_metadata']:
-            authurls = book['all_metadata']['authorUrl'].split(", ")
-            for i, auth in enumerate(book['author']):
-                #print("===Update author url for %s to %s"%(auth,authurls[i]))
-                autid=db.get_author_id(auth)
-                db.set_link_field_for_author(autid, unicode(authurls[i]),
-                                             commit=False, notify=False)
-
         # implement 'newonly' flags here by setting to the current
         # value again.
         if not book['added']:
@@ -1395,7 +1400,11 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
 
                     if flag == 'r' or book['added']: # flag 'n' isn't actually needed--*always* set if configured and new book.
                         if coldef['datatype'] in ('int','float'): # for favs, etc--site specific metadata.
-                            val = unicode(book['all_metadata'][meta]).replace(",","")
+                            if 'anthology_meta_list' in book and meta in book['anthology_meta_list']:
+                                # re-split list, strip commas, convert to floats, sum up.
+                                val = sum([ float(x.replace(",","")) for x in book['all_metadata'][meta].split(", ") ])
+                            else:
+                                val = unicode(book['all_metadata'][meta]).replace(",","")
                         else:
                             val = book['all_metadata'][meta]
                         db.set_custom(book_id, val, label=label, commit=False)
@@ -1416,6 +1425,16 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                             
                         db.set_custom(book_id, ", ".join(vallist), label=label, commit=False)
 
+        # set author link if found.  All current adapters have authorUrl, except anonymous on AO3.
+        # Moved down so author's already in the DB.
+        if 'authorUrl' in book['all_metadata']:
+            authurls = book['all_metadata']['authorUrl'].split(", ")
+            for i, auth in enumerate(book['author']):
+                #print("===Update author url for %s to %s"%(auth,authurls[i]))
+                autid=db.get_author_id(auth)
+                db.set_link_field_for_author(autid, unicode(authurls[i]),
+                                             commit=False, notify=False)
+
         db.commit()
 
         if 'Generate Cover' in self.gui.iactions and (book['added'] or not prefs['gcnewonly']):
@@ -1649,7 +1668,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                     # identifiers have :->| in uri.
                     # print("uri from ident uri:%s"%identifiers['uri'].replace('|',':'))
                     return identifiers['uri'].replace('|',':')
-            elif path.lower().endswith('.epub'):
+            elif path and path.lower().endswith('.epub'):
                 existingepub = path
                 
             ## only epub has URL in it--at least where I can easily find it.
@@ -1674,6 +1693,7 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
         book['tags'] = []
         book['url'] = ''
         book['all_metadata'] = {}
+        book['anthology_meta_list'] = {}
         book['comment'] = ''
         book['added'] = True
         book['good'] = True
@@ -1740,6 +1760,10 @@ class FanFictionDownLoaderPlugin(InterfaceAction):
                         book['all_metadata'][k]=book['all_metadata'][k]+"\n\n"+v
                     else:
                         book['all_metadata'][k]=book['all_metadata'][k]+", "+v
+                        # flag psuedo list element.  Used so numeric
+                        # cust cols can convert back to numbers and
+                        # add.
+                        book['anthology_meta_list'][k]=True
     
         if existingbook:
             book['title'] = deftitle = existingbook['title']

defaults.ini

@@ -622,7 +622,7 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 ## composite metadata entries.  dramione.org, for example, adds
 ## 'cliches' and then defines as the composite of hermiones,dracos in
 ## include_in_cliches.
-extra_valid_entries:themes,hermiones,dracos,timeline,cliches
+extra_valid_entries:themes,hermiones,dracos,timeline,cliches,read,reviews
 include_in_cliches:hermiones,dracos
 
 ## For another example, you could, by uncommenting this line, include
@@ -667,6 +667,11 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
 
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
 ## commandline version, this should go in your personal.ini, not
@@ -674,11 +679,22 @@ extracategories:Harry Potter
 #username:YourName
 #password:yourpassword
 
-## Some sites also require the user to confirm they are adult for
-## adult content.  In commandline version, this should go in your
-## personal.ini, not defaults.ini.
+[fanfic.potterheadsanonymous.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
 [fanfiction.portkey.org]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
@@ -722,6 +738,10 @@ extracharacters:Hermione Granger
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+## Extra metadata that this adapter knows about.  See [dramione.org]
+## for examples of how to use them.
+extra_valid_entries:read,reviews
+
 [hlfiction.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:Highlander
@@ -866,6 +886,22 @@ extracategories:Supernatural
 extracharacters:Sam,Dean
 extraships:Sam/Dean
 
+[scarhead.net]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
+#is_adult:true
+
 [sg1-heliopolis.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
@@ -1179,6 +1215,11 @@ cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
 ## Site dedicated to these categories/characters/ships
 extracategories:NCIS
 
+[www.nickandgreg.net]
+## Site dedicated to these categories/characters/ships
+extracategories:CSI
+extraships:Nick Stokes/Greg Sanders
+
 [www.phoenixsong.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
@@ -1191,6 +1232,12 @@ extraships:Harry Potter/Ginny Weasley
 #username:YourName
 #password:yourpassword
 
+## phoenixsong.net, oddly, can have high rated chapters (login
+## required) in the middle of a lower rated story.  Use this to force
+## FFDL to always login to phoenixsong.net so those stories download
+## correctly.
+#force_login:true
+
 [www.potionsandsnitches.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
@@ -1241,6 +1288,17 @@ extracharacters:Kurt Hummel,Blaine Anderson
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[www.simplyundeniable.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
 [www.sinful-desire.org]
 ## Site dedicated to these categories/characters/ships
 extracategories:Supernatural

fanficdownloader/adapters/__init__.py

@@ -115,6 +115,10 @@ import adapter_hennethannunnet
 import adapter_tokrafandomnetcom
 import adapter_netraptororg
 import adapter_asr3slashzoneorg
+import adapter_nickandgregnet
+import adapter_potterheadsanonymouscom
+import adapter_simplyundeniablecom
+import adapter_scarheadnet
 
 ## This bit of complexity allows adapters to be added by just adding
 ## importing.  It eliminates the long if/else clauses we used to need

fanficdownloader/adapters/adapter_dramioneorg.py

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

fanficdownloader/adapters/adapter_fanfictionnet.py

@@ -135,12 +135,25 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
         categories = soup.find('div',{'id':'pre_story_links'}).findAll('a',{'class':'xcontrast_txt'})
         #print("xcontrast_txt a:%s"%categories)
         if len(categories) > 1:
+            # Strangely, the ones with *two* links are the
+            # non-crossover categories.  Each is in a category itself
+            # of Book, Movie, etc.
             self.story.addToList('category',stripHTML(categories[1]))
         elif 'Crossover' in categories[0]['href']:
             caturl = "http://%s%s"%(self.getSiteDomain(),categories[0]['href'])
             catsoup = bs.BeautifulSoup(self._fetchUrl(caturl))
             for a in catsoup.findAll('a',href=re.compile(r"^/crossovers/")):
                 self.story.addToList('category',stripHTML(a))
+            else:
+                # Fall back.  I ran across a story with a Crossver
+                # category link to a broken page once.
+                # http://www.fanfiction.net/s/2622060/1/
+                # Naruto + Harry Potter Crossover
+                logger.info("Fall back category collection")
+                for c in stripHTML(categories[0]).replace(" Crossover","").split(' + '):
+                    self.story.addToList('category',c)
+                
+                
             
         a = soup.find('a', href='http://www.fictionratings.com/')
         rating = a.string
@@ -259,12 +272,18 @@ class FanFictionNetSiteAdapter(BaseSiteAdapter):
                         ## slow_down_sleep_time setting is.
         data = self._fetchUrl(url)
 
+        if "Please email this error message in full to <a href='mailto:support@fanfiction.com'>support@fanfiction.com</a>" in data:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  FanFiction.net Site Error!" % url)
+        
         # some ancient stories have body tags inside them that cause
         # soup parsing to discard the content.  For story text we
         # don't care about anything before "<div class='storytextp"
         # (there's a space after storytextp, so no close quote(')) and
         # this kills any body tags.
-        data = data[data.index("<div class='storytextp"):]
+        if "<div class='storytextp" not in data:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+        else:
+            data = data[data.index("<div class='storytextp"):]
         data.replace("<body","<notbody").replace("<BODY","<NOTBODY")
         
         soup = bs.BeautifulSoup(data)

fanficdownloader/adapters/adapter_grangerenchantedcom.py

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

fanficdownloader/adapters/adapter_mugglenetcom.py

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

fanficdownloader/adapters/adapter_nhamagicalworldsus.py

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

fanficdownloader/adapters/adapter_nickandgregnet.py

@@ -0,0 +1,174 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2013 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+logger = logging.getLogger(__name__)
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return NickAndGregNetAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class NickAndGregNetAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        # XXX Most sites don't have the /fanfic part.  Replace all to remove it usually.
+        self._setURL('http://' + self.getSiteDomain() + '/desert_archive/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','nag')
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%Y/%m/%d"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'www.nickandgreg.net'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/desert_archive/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/desert_archive/viewstory.php?sid=")+r"\d+$"
+    
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&i=1'
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+
+        ## Title
+        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',a.string)
+        
+        # Find authorid and URL from... author url.
+        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/desert_archive/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # Find the chapters:
+        chapters = soup.find('select')
+        for chapter in chapters.findAll('option'):
+            if chapter.text != 'Story Index' and chapter.text != 'Chapters':
+                self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/desert_archive/'+chapter['value']))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+        
+        asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
+        
+        for div in asoup.findAll('td', {'class' : 'tblborder6'}):
+            a = div.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+            if a != None:
+                break
+        
+        self.setDescription(url,div.find('br').nextSibling)
+        
+        a=div.text.split('Rating:')
+        if len(a) == 2: self.story.setMetadata('rating', a[1].split(' -')[0])
+        
+        a=div.text.split('Characters:')
+        if len(a) == 2: 
+        	for char in a[1].split(' -')[0].split(', '):
+        	    self.story.addToList('characters',char)
+        	    
+        a=div.text.split('Genres:')
+        if len(a) == 2: 
+        	for genre in a[1].split(' -')[0].split(', '):
+        	    self.story.addToList('genre',genre)
+        	    
+        a=div.text.split('Warnings:')
+        if len(a) == 2: 
+        	for warn in a[1].split(' -')[0].split(', '):
+        	    if 'none' not in warn:
+        	        self.story.addToList('warnings',warn)
+        	    
+        a=div.text.split('Completed:')
+        if len(a) ==2:
+            if 'Yes' in a[1]:
+                self.story.setMetadata('status', 'Completed')
+            else:
+                self.story.setMetadata('status', 'In-Progress')
+                
+        a=div.text.split('Published:')
+        if len(a) == 2: self.story.setMetadata('datePublished', makeDate(stripHTML(a[1].split(' -')[0]), self.dateformat))
+        
+        a=div.text.split('Updated:')
+        if len(a) == 2: self.story.setMetadata('dateUpdated', makeDate(stripHTML(a[1].split(' -')[0]), self.dateformat))
+
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logger.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('table', {'class' : 'tblborder6'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_phoenixsongnet.py

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

fanficdownloader/adapters/adapter_potterheadsanonymouscom.py

@@ -0,0 +1,297 @@
+# -*- 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 PotterHeadsAnonymousComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class PotterHeadsAnonymousComAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','pha')
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%d %b %Y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'fanfic.potterheadsanonymous.com'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+
+    ## Login seems to be reasonably standard across eFiction sites.
+    def needToLoginCheck(self, data):
+        if 'Registered Users Only' in data \
+                or 'There is no such account on our website' in data \
+                or "That password doesn't match the one in our database" in data:
+            return True
+        else:
+            return False
+        
+    def performLogin(self, url):
+        params = {}
+
+        if self.password:
+            params['penname'] = self.username
+            params['password'] = self.password
+        else:
+            params['penname'] = self.getConfig("username")
+            params['password'] = self.getConfig("password")
+        params['cookiecheck'] = '1'
+        params['submit'] = 'Submit'
+    
+        loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login'
+        logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
+                                                              params['penname']))
+    
+        d = self._fetchUrl(loginUrl, params)
+    
+        if "Member Account" not in d : #Member Account
+            logger.info("Failed to login to URL %s as %s" % (loginUrl,
+                                                              params['penname']))
+            raise exceptions.FailedToLogin(url,params['penname'])
+            return False
+        else:
+            return True
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        if self.is_adult or self.getConfig("is_adult"):
+            # Weirdly, different sites use different warning numbers.
+            # If the title search below fails, there's a good chance
+            # you need a different number.  print data at that point
+            # and see what the 'click here to continue' url says.
+            addurl = "&ageconsent=ok&warning=4"
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'+addurl
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        if self.needToLoginCheck(data):
+            # need to log in for this one.
+            self.performLogin(url)
+            data = self._fetchUrl(url)
+            
+        # Since the warning text can change by warning level, let's
+        # look for the warning pass url.  ksarchive uses
+        # &warning= -- actually, so do other sites.  Must be an
+        # eFiction book.
+            
+        # viewstory.php?sid=1882&warning=4
+        # viewstory.php?sid=1654&ageconsent=ok&warning=5
+        #print data
+        #m = re.search(r"'viewstory.php\?sid=1882(&warning=4)'",data)
+        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
+        if m != None:
+            if self.is_adult or self.getConfig("is_adult"):
+                # We tried the default and still got a warning, so
+                # let's pull the warning number from the 'continue'
+                # link and reload data.
+                addurl = m.group(1)
+                # correct stupid & error in url.
+                addurl = addurl.replace("&","&")
+                url = self.url+'&index=1'+addurl
+                logger.debug("URL 2nd try: "+url)
+
+                try:
+                    data = self._fetchUrl(url)
+                except urllib2.HTTPError, e:
+                    if e.code == 404:
+                        raise exceptions.StoryDoesNotExist(self.url)
+                    else:
+                        raise e    
+            else:
+                raise exceptions.AdultCheckRequired(self.url)
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+
+        pagetitle = soup.find('div',{'id':'pagetitle'})
+        
+        ## Title
+        a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',a.string)
+        
+        # Find authorid and URL from... author url.
+        a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # Find the chapters:
+        for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
+            # just in case there's tags, like <i> in chapter titles.
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        # utility method
+        def defaultGetattr(d,k):
+            try:
+                return d[k]
+            except:
+                return ""
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        labels = soup.findAll('span',{'class':'label'})
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+
+            if 'Summary' in label:
+                ## Everything until the next span class='label'
+                svalue = ""
+                while not defaultGetattr(value,'class') == 'label':
+                    svalue += str(value)
+                    value = value.nextSibling
+                self.setDescription(url,svalue)
+                #self.story.setMetadata('description',stripHTML(svalue))
+
+            if 'Rated' in label:
+                self.story.setMetadata('rating', value)
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Categories' in label:
+                cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+                for cat in cats:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+                for char in chars:
+                    self.story.addToList('characters',char.string)
+
+            if 'Genre' in label:
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
+                for genre in genres:
+                    self.story.addToList('genre',genre.string)
+
+            if 'Warnings' in label:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=3'))
+                for warning in warnings:
+                    self.story.addToList('warnings',warning.string)
+
+            if 'Completed' in label:
+                if 'Yes' in value:
+                    self.story.setMetadata('status', 'Completed')
+                else:
+                    self.story.setMetadata('status', 'In-Progress')
+
+            if 'Published' in label:
+                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
+            
+            if 'Updated' in label:
+                # there's a stray [ at the end.
+                #value = value[0:-1]
+                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
+
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    self.story.setMetadata('seriesUrl',series_url)
+                    break
+                i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logger.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div', {'id' : 'story'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_scarheadnet.py

@@ -0,0 +1,298 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2013 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+logger = logging.getLogger(__name__)
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return ScarHeadNetAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class ScarHeadNetAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','shn')
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%d/%m/%y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'scarhead.net'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+
+    ## Login seems to be reasonably standard across eFiction sites.
+    def needToLoginCheck(self, data):
+        if 'Registered Users Only' in data \
+                or 'There is no such account on our website' in data \
+                or "That password doesn't match the one in our database" in data:
+            return True
+        else:
+            return False
+        
+    def performLogin(self, url):
+        params = {}
+
+        if self.password:
+            params['penname'] = self.username
+            params['password'] = self.password
+        else:
+            params['penname'] = self.getConfig("username")
+            params['password'] = self.getConfig("password")
+        params['cookiecheck'] = '1'
+        params['submit'] = 'Submit'
+    
+        loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login'
+        logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
+                                                              params['penname']))
+    
+        d = self._fetchUrl(loginUrl, params)
+    
+        if "Member Account" not in d : #Member Account
+            logger.info("Failed to login to URL %s as %s" % (loginUrl,
+                                                              params['penname']))
+            raise exceptions.FailedToLogin(url,params['penname'])
+            return False
+        else:
+            return True
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        if self.is_adult or self.getConfig("is_adult"):
+            # Weirdly, different sites use different warning numbers.
+            # If the title search below fails, there's a good chance
+            # you need a different number.  print data at that point
+            # and see what the 'click here to continue' url says.
+            addurl = "&ageconsent=ok&warning=5"
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'+addurl
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        if self.needToLoginCheck(data):
+            # need to log in for this one.
+            self.performLogin(url)
+            data = self._fetchUrl(url)
+            
+        # Since the warning text can change by warning level, let's
+        # look for the warning pass url.  ksarchive uses
+        # &warning= -- actually, so do other sites.  Must be an
+        # eFiction book.
+            
+        # viewstory.php?sid=1882&warning=4
+        # viewstory.php?sid=1654&ageconsent=ok&warning=5
+        #print data
+        #m = re.search(r"'viewstory.php\?sid=1882(&warning=4)'",data)
+        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
+        if m != None:
+            if self.is_adult or self.getConfig("is_adult"):
+                # We tried the default and still got a warning, so
+                # let's pull the warning number from the 'continue'
+                # link and reload data.
+                addurl = m.group(1)
+                # correct stupid & error in url.
+                addurl = addurl.replace("&","&")
+                url = self.url+'&index=1'+addurl
+                logger.debug("URL 2nd try: "+url)
+
+                try:
+                    data = self._fetchUrl(url)
+                except urllib2.HTTPError, e:
+                    if e.code == 404:
+                        raise exceptions.StoryDoesNotExist(self.url)
+                    else:
+                        raise e    
+            else:
+                raise exceptions.AdultCheckRequired(self.url)
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+
+        pagetitle = soup.find('tr',{'valign':'top'})
+        
+        ## Title
+        a = pagetitle.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',a.string)
+        
+        # Find authorid and URL from... author url.
+        a = pagetitle.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # Find the chapters:
+        for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
+            # just in case there's tags, like <i> in chapter titles.
+            self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+        
+        cats = soup.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+        for cat in cats:
+            if '/' == cat.string[0]:
+                self.story.addToList('ships','Harry Potter'+cat.string.split('(')[0])
+            elif 'Harry' in cat.string:
+                self.story.addToList('ships',cat.string.split('(')[0])
+            else:
+                self.story.addToList('category',cat.string)
+            if '(' in cat.string:
+                self.story.addToList('category',cat.string.split('(')[1].split(')')[0])
+            
+                
+            
+
+        chars = soup.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+        for char in chars:
+            self.story.addToList('characters',char.string)
+
+        genres = soup.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
+        for genre in genres:
+            self.story.addToList('genre',genre.string)
+
+        warnings = soup.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
+        for warning in warnings:
+            self.story.addToList('warnings',warning.string)
+            
+        textsoup = stripHTML(soup)
+
+        a = textsoup.split('Published: ')[1].split(' ')[0]
+        self.story.setMetadata('datePublished', makeDate(stripHTML(a), self.dateformat))
+        a = textsoup.split('Updated: ')[1].split(' ')[0]
+        self.story.setMetadata('dateUpdated', makeDate(stripHTML(a), self.dateformat))
+        a = textsoup.split('Rating: ')[1].split(' ')[0]
+        self.story.setMetadata('rating', a)
+        a = textsoup.split('Length: ')[1].split('(')[1].split(' ')[0]
+        self.story.setMetadata('numWords', a)
+        a = textsoup.split('Completed: ')[1].split(' ')[0]
+        if 'Yes' in a:
+            self.story.setMetadata('status', 'Completed')
+        else:
+            self.story.setMetadata('status', 'In-Progress')
+        #a = textsoup.split('Summary: ')[1].split('Add Story to Favorites')[0]
+        #self.setDescription(url,a)
+        
+
+        
+        a=soup.find(text=re.compile("Summary: "))
+        i=0
+        svalue = ""
+        while i == 0:
+            try:
+                b = str(a)
+                svalue += b.split('Summary: ')[1]
+            except:
+                svalue += str(a)
+            if a.nextSibling != None:
+                a = a.nextSibling
+            else:
+                a = a.parent.nextSibling
+            if 'Disclaimer: ' in stripHTML(a):
+                i=1
+        self.setDescription(url,svalue)
+
+        try:
+            # Find Series name from series URL.
+            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    self.story.setMetadata('seriesUrl',series_url)
+                    break
+                i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logger.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('div', {'id' : 'story'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_scarvesandcoffeenet.py

@@ -141,7 +141,7 @@ class ScarvesAndCoffeeNetAdapter(BaseSiteAdapter):
         self.story.setMetadata('title',a.string)
         
         # Find authorid and URL from... author url.
-        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        a = soup.find('div',{"id":"pagetitle"}).find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',a['href'].split('=')[1])
         self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
         self.story.setMetadata('author',a.string)

fanficdownloader/adapters/adapter_simplyundeniablecom.py

@@ -0,0 +1,217 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2013 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+logger = logging.getLogger(__name__)
+import re
+import urllib2
+
+from .. import BeautifulSoup as bs
+from ..htmlcleanup import stripHTML
+from .. import exceptions as exceptions
+
+from base_adapter import BaseSiteAdapter,  makeDate
+
+def getClass():
+    return SimplyUndeniableComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class SimplyUndeniableComAdapter(BaseSiteAdapter):
+
+    def __init__(self, config, url):
+        BaseSiteAdapter.__init__(self, config, url)
+
+        self.decode = ["Windows-1252",
+                       "utf8"] # 1252 is a superset of iso-8859-1.
+                               # Most sites that claim to be
+                               # iso-8859-1 (and some that claim to be
+                               # utf8) are really windows-1252.
+        self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
+        self.password = ""
+        self.is_adult=False
+        
+        # get storyId from url--url validation guarantees query is only sid=1234
+        self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
+        logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','sud')
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%m/%d/%Y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'www.simplyundeniable.com'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+
+    ## Login seems to be reasonably standard across eFiction sites.
+    def needToLoginCheck(self, data):
+        if 'Please log in now' in data \
+                or 'There is no such account on our website' in data \
+                or "That password doesn't match the one in our database" in data:
+            return True
+        else:
+            return False
+        
+    def performLogin(self, url):
+        params = {}
+
+        if self.password:
+            params['penname'] = self.username
+            params['password'] = self.password
+        else:
+            params['penname'] = self.getConfig("username")
+            params['password'] = self.getConfig("password")
+        params['cookiecheck'] = '1'
+        params['submit'] = 'Submit'
+    
+        loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login'
+        logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
+                                                              params['penname']))
+    
+        d = self._fetchUrl(loginUrl, params)
+    
+        if "My Account" not in d : #Member Account
+            logger.info("Failed to login to URL %s as %s" % (loginUrl,
+                                                              params['penname']))
+            raise exceptions.FailedToLogin(url,params['penname'])
+            return False
+        else:
+            return True
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url
+        logger.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        if self.needToLoginCheck(data):
+            # need to log in for this one.
+            self.performLogin(url)
+            data = self._fetchUrl(url)
+
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        if "Please log in now" in data:
+                raise exceptions.FailedToDownload(self.getSiteDomain() +" says: You need to have access to the restricted section.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        a = soup.find('h1')
+        self.story.setMetadata('title',a.text)
+        
+        # Find authorid and URL from... author url.
+        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+        asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
+        
+        for info in asoup.findAll('table', {'cellpadding' : '5'}):
+            a = info.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+            if a != None:
+                self.story.setMetadata('title',a.string)
+                break
+                
+        # Find the chapters:
+        if "Disclaimer" in data:
+            self.chapterUrls.append((self.story.getMetadata('title'),url))
+        else:
+            for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+&i=1$')):
+            # just in case there's tags, like <i> in chapter titles.
+                self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+        
+        a = info.find('td', {'valign' : 'top'}).find('p')
+        self.setDescription(url,a)
+        
+        a = info.find('td', {'class' : 'greysm'}).findAll('b')
+        self.story.setMetadata('datePublished', makeDate(stripHTML(a[0].nextSibling), self.dateformat))
+        self.story.setMetadata('dateUpdated', makeDate(stripHTML(a[1].nextSibling), self.dateformat))
+        if 'Yes' in a[2].nextSibling:
+            self.story.setMetadata('status', 'Completed')
+        else:
+            self.story.setMetadata('status', 'In-Progress')
+        self.story.setMetadata('rating', a[3].nextSibling)
+        self.story.setMetadata('numWords', a[4].nextSibling)
+        
+        
+        warnings = info.find('td', {'width' : '45'}).nextSibling.nextSibling.text.split(', ')
+        for warning in warnings:
+            if 'none' not in warning:
+                self.story.addToList('warnings',warning)
+        chars = info.find('td', {'width' : '51'}).nextSibling.nextSibling.text.split(', ')
+        for char in chars:
+            if '&' in char:
+                self.story.addToList('ships',char)
+            else:
+                self.story.addToList('characters',char)
+        genres = info.find('td', {'width' : '36'}).nextSibling.nextSibling.text.split(', ')
+        for genre in genres:
+            self.story.addToList('genre',genre)
+            
+        cat = info.find('a', href=re.compile(r'categories.php'))
+        self.story.addToList('category',cat.string)
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logger.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        div = soup.find('span', {'class' : 'style'})
+
+        if None == div:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,div)

fanficdownloader/adapters/adapter_siyecouk.py

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

fanficdownloader/geturls.py

@@ -54,9 +54,14 @@ def get_urls_from_page(url,configuration=None,normalize=False):
         opener = u2.build_opener(u2.HTTPCookieProcessor(),GZipProcessor())
         data = opener.open(url).read()
 
-    return get_urls_from_html(data,url,configuration,normalize)
+    # kludge because I don't see it on enough sites to be worth generalizing yet.
+    restrictsearch=None
+    if 'scarvesandcoffee.net' in url:
+        restrictsearch=('div',{'id':'mainpage'})
 
-def get_urls_from_html(data,url=None,configuration=None,normalize=False):
+    return get_urls_from_html(data,url,configuration,normalize,restrictsearch)
+
+def get_urls_from_html(data,url=None,configuration=None,normalize=False,restrictsearch=None):
 
     normalized = [] # normalized url
     retlist = [] # orig urls.
@@ -65,6 +70,9 @@ def get_urls_from_html(data,url=None,configuration=None,normalize=False):
         configuration = Configuration("test1.com","EPUB")
 
     soup = BeautifulSoup(data)
+    if restrictsearch:
+        soup = soup.find(*restrictsearch)
+        print("restrict search:%s"%soup)
     
     for a in soup.findAll('a'):
         if a.has_key('href'):

index.html

@@ -57,9 +57,12 @@
 	  <h3>Changes:</h3>
 	  <p>
 	    <ul>
-	      <li>Don't strip lead/trail whitespace from replace_metadata, add feature \s->' ' in replace_metadata replacements.</li>
+              <li>New Site: scarhead.net -- Thanks, Ida!</li>
+	      <li>Improved error reporting of fanfiction.net site errors</li>
+	      <li>New force_login parameter for phoenixsong.net site.</li>
 	    </ul>
 	  </p>
+	  
 	  <p>
 	    Questions?  Check out our 
 	    <a href="http://code.google.com/p/fanficdownloader/wiki/FanFictionDownloaderFAQs">FAQs</a>.
@@ -68,7 +71,7 @@
 	    If you have any problems with this application, please
 	    report them in
 	    the <a href="http://groups.google.com/group/fanfic-downloader">FanFictionDownLoader Google Group</a>.  The
-	    <a href="http://4-4-56.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
+	    <a href="http://4-4-59.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
 	  </p>
 	  <div id='error'>
 	    {{ error_message }}
@@ -612,6 +615,26 @@
 	    Use the URL of the story's chapter list, such as
 	    <br /><a href="http://netraptor.org/archive/viewstory.php?sid=1234">http://netraptor.org/archive/viewstory.php?sid=1234</a>
 	  </dd>
+	  <dt>nickandgreg.net</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://www.nickandgreg.net/desert_archive/viewstory.php?sid=1234">http://www.nickandgreg.net/desert_archive/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>fanfic.potterheadsanonymous.com</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://fanfic.potterheadsanonymous.com/viewstory.php?sid=1234">http://fanfic.potterheadsanonymous.com/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>www.simplyundeniable.com</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://www.simplyundeniable.com/viewstory.php?sid=1234">http://www.simplyundeniable.com/viewstory.php?sid=1234</a>
+	  </dd>
+	  <dt>scarhead.net</dt>
+	  <dd>
+	    Use the URL of the story's chapter list, such as
+	    <br /><a href="http://scarhead.net/viewstory.php?sid=1234">http://scarhead.net/viewstory.php?sid=1234</a>
+	  </dd>
 	</dl>
 
 	<p>

plugin-defaults.ini

@@ -593,7 +593,7 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 ## composite metadata entries.  dramione.org, for example, adds
 ## 'cliches' and then defines as the composite of hermiones,dracos in
 ## include_in_cliches.
-extra_valid_entries:themes,hermiones,dracos,timeline,cliches
+extra_valid_entries:themes,hermiones,dracos,timeline,cliches,read,reviews
 include_in_cliches:hermiones,dracos
 
 ## For another example, you could, by uncommenting this line, include
@@ -654,6 +654,11 @@ cover_exclusion_regexp:/images/.*?ribbon.gif
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
 
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
 ## commandline version, this should go in your personal.ini, not
@@ -661,11 +666,22 @@ extracategories:Harry Potter
 #username:YourName
 #password:yourpassword
 
-## Some sites also require the user to confirm they are adult for
-## adult content.  In commandline version, this should go in your
-## personal.ini, not defaults.ini.
+[fanfic.potterheadsanonymous.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
 [fanfiction.portkey.org]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
@@ -709,6 +725,10 @@ extracharacters:Hermione Granger
 ## personal.ini, not defaults.ini.
 #is_adult:true
 
+## Extra metadata that this adapter knows about.  See [dramione.org]
+## for examples of how to use them.
+extra_valid_entries:read,reviews
+
 [hlfiction.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:Highlander
@@ -853,6 +873,22 @@ extracategories:Supernatural
 extracharacters:Sam,Dean
 extraships:Sam/Dean
 
+[scarhead.net]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
+#is_adult:true
+
 [sg1-heliopolis.com]
 ## Some sites do not require a login, but do require the user to
 ## confirm they are adult for adult content.  In commandline version,
@@ -1163,6 +1199,11 @@ cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
 ## Site dedicated to these categories/characters/ships
 extracategories:NCIS
 
+[www.nickandgreg.net]
+## Site dedicated to these categories/characters/ships
+extracategories:CSI
+extraships:Nick Stokes/Greg Sanders
+
 [www.phoenixsong.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
@@ -1175,6 +1216,12 @@ extraships:Harry Potter/Ginny Weasley
 #username:YourName
 #password:yourpassword
 
+## phoenixsong.net, oddly, can have high rated chapters (login
+## required) in the middle of a lower rated story.  Use this to force
+## FFDL to always login to phoenixsong.net so those stories download
+## correctly.
+#force_login:true
+
 [www.potionsandsnitches.net]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter
@@ -1225,6 +1272,17 @@ extracharacters:Kurt Hummel,Blaine Anderson
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[www.simplyundeniable.com]
+## Site dedicated to these categories/characters/ships
+extracategories:Harry Potter
+
+## Some sites require login (or login for some rated stories) The
+## program can prompt you, or you can save it in config.  In
+## commandline version, this should go in your personal.ini, not
+## defaults.ini.
+#username:YourName
+#password:yourpassword
+
 [www.sinful-desire.org]
 ## Site dedicated to these categories/characters/ships
 extracategories:Supernatural