Integrate new adapters www.wraithbait.com and www.libraryofmoria.com.

allow config section [www.squidge.org/peja].  More needed to support other sites
under www.squidge.org.

app.yaml

@@ -1,6 +1,6 @@
 # ffd-retief-hrd fanfictiondownloader
 application: fanfictiondownloader
-version: 4-4-8
+version: 4-4-9
 runtime: python27
 api_version: 1
 threadsafe: true

calibre-plugin/__init__.py

@@ -27,7 +27,7 @@ class FanFictionDownLoaderBase(InterfaceActionBase):
     description         = 'UI plugin to download FanFiction stories from various sites.'
     supported_platforms = ['windows', 'osx', 'linux']
     author              = 'Jim Miller'
-    version             = (1, 5, 18)
+    version             = (1, 5, 20)
     minimum_calibre_version = (0, 8, 30)
 
     #: This field defines the GUI plugin class that contains all the code

calibre-plugin/config.py

@@ -19,7 +19,7 @@ from calibre.gui2.ui import get_gui
 from calibre_plugins.fanfictiondownloader_plugin.dialogs \
     import (UPDATE, UPDATEALWAYS, OVERWRITE, collision_order)
 
-from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.adapters import getSiteDomains
+from calibre_plugins.fanfictiondownloader_plugin.fanficdownloader.adapters import getConfigSections
 
 from calibre_plugins.fanfictiondownloader_plugin.common_utils \
     import ( get_library_uuid, KeyboardConfigDialog )
@@ -486,7 +486,7 @@ class GenerateCoverTab(QWidget):
         
         self.gc_dropdowns = {}
 
-        sitelist = getSiteDomains()
+        sitelist = getConfigSections()
         sitelist.sort()
         sitelist.insert(0,u"Default")
         for site in sitelist:

defaults.ini

@@ -430,6 +430,12 @@ extratags:
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[www.libraryofmoria.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
 [www.mediaminer.org]
 
 [www.midnightwhispers.ca]
@@ -446,6 +452,17 @@ cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
 
 [www.siye.co.uk]
 
+[www.squidge.org/peja]
+# www.squidge.org/peja calls it Fandom <shrug>
+category_label:Fandom
+# Remove numWords -- www.squidge.org/peja word counts are inaccurate
+titlepage_entries: series,category,genre,language,characters,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,description
+
+[www.squidge.org/peja:txt]
+## Add URLs since there aren't links.
+# Remove numWords -- www.squidge.org/peja word counts are inaccurate
+titlepage_entries: series,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,storyUrl, authorUrl, description
+
 [www.thewriterscoffeeshop.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -499,6 +516,12 @@ collect_series: false
 
 [www.whofic.com]
 
+[www.wraithbait.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
 [overrides]
 ## It may sometimes be useful to override all of the specific format,
 ## site and site:format sections in your private configuration.  For

fanficdownloader/adapters/__init__.py

@@ -52,6 +52,9 @@ import adapter_nfacommunitycom
 import adapter_midnightwhispersca
 import adapter_ksarchivecom
 import adapter_archiveskyehawkecom
+import adapter_squidgeorgpeja
+import adapter_libraryofmoriacom
+import adapter_wraithbaitcom
 
 ## This bit of complexity allows adapters to be added by just adding
 ## importing.  It eliminates the long if/else clauses we used to need
@@ -95,13 +98,13 @@ def getAdapter(config,url,fileform=None):
         fixedurl = fixedurl.replace("http://","http://www.")
     if cls:
         adapter = cls(config,fixedurl) # raises InvalidStoryURL
-        adapter.setSectionOrder(adapter.getSiteDomain(),fileform)
+        adapter.setSectionOrder(adapter.getConfigSection(),fileform)
         return adapter
     # No adapter found.
     raise exceptions.UnknownSite( url, [cls.getSiteDomain() for cls in __class_list] )
 
-def getSiteDomains():
-    return [cls.getSiteDomain() for cls in __class_list]
+def getConfigSections():
+    return [cls.getConfigSection() for cls in __class_list]
 
 def getClassFor(domain):
     for cls in __class_list:

fanficdownloader/adapters/adapter_libraryofmoriacom.py

@@ -0,0 +1,250 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2011 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+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 LibraryOfMoriaComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class LibraryOfMoriaComAdapter(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])
+        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+        # normalized story URL.
+        self._setURL('http://' + self.getSiteDomain() + '/a/viewstory.php?sid='+self.story.getMetadata('storyId'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','lom')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        self.story.addToList("category","Lord of the Rings")
+
+        # The date format will vary from site to site.
+        # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
+        self.dateformat = "%B %d, %Y"
+            
+    @staticmethod # must be @staticmethod, don't remove it.
+    def getSiteDomain():
+        # The site domain.  Does have www here, if it uses it.
+        return 'www.libraryofmoria.com'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/a/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/a/viewstory.php?sid=")+r"\d+$"
+
+
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        if self.is_adult or self.getConfig("is_adult"):
+            addurl = "&ageconsent=ok&warning=3"
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+addurl
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
+        if m != None:
+            if self.is_adult or self.getConfig("is_adult"):
+                # We tried the default and still got a warning, so
+                # let's pull the warning number from the 'continue'
+                # link and reload data.
+                addurl = m.group(1)
+                # correct stupid & error in url.
+                addurl = addurl.replace("&","&")
+                url = self.url+'&index=1'+addurl
+                logging.debug("URL 2nd try: "+url)
+
+                try:
+                    data = self._fetchUrl(url)
+                except urllib2.HTTPError, e:
+                    if e.code == 404:
+                        raise exceptions.StoryDoesNotExist(self.url)
+                    else:
+                        raise e    
+            else:
+                raise exceptions.AdultCheckRequired(self.url)
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',a.string)
+        
+        # Find authorid and URL from... author url.
+        a = soup.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        # 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+'/a/'+chapter['href']+addurl))
+
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # formating, so it's a little ugly.
+
+        # utility method
+        def defaultGetattr(d,k):
+            try:
+                return d[k]
+            except:
+                return ""
+
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        labels = soup.findAll('span',{'class':'label'})
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+
+            if 'Summary' in label:
+                ## Everything until the next span class='label'
+                svalue = ""
+                while not defaultGetattr(value,'class') == 'label':
+                    svalue += str(value)
+                    value = value.nextSibling
+                self.setDescription(url,svalue)
+                #self.story.setMetadata('description',stripHTML(svalue))
+
+            if 'Rated' in label:
+                self.story.setMetadata('rating', value)
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Categories' in label:
+                cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
+                catstext = [cat.string for cat in cats]
+                for cat in catstext:
+                    self.story.addToList('category',cat.string)
+
+            if 'Characters' in label:
+                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
+                charstext = [char.string for char in chars]
+                for char in charstext:
+                    self.story.addToList('characters',char.string)
+
+            if 'Type' 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 'Warning' in label:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=5'))
+                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/'+a['href']
+
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    break
+                i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.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_squidgeorgpeja.py

@@ -0,0 +1,234 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2011 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+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 SquidgeOrgPejaAdapter
+
+## XXX IMPORTANT NOTE!!  This adapter is for squidge.org/peja ONLY!
+## There are lots of other sites and stuff under squidge.org that
+## we're not supporting.  If/When we ever want to support more
+## sections of squidge.org, FFDL will need to be changed more
+## fundamentally to find different adapters under the same domain.
+##
+## For now, I've only implemented the part for ini section names so
+## if/when more adapters under squidge.org come along, existing ini
+## files will still work correctly.
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class SquidgeOrgPejaAdapter(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.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])
+        logging.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'))
+        
+        # Each adapter needs to have a unique site abbreviation.
+        self.story.setMetadata('siteabbrev','wwomb')
+        
+        # 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.squidge.org'
+    
+    @classmethod # must be @staticmethod, don't remove it.
+    def getConfigSection(cls):
+        # The config section name.  Only override if != site domain.
+        return cls.getSiteDomain()+'/peja'
+    
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/peja/cgi-bin/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/peja/cgi-bin/viewstory.php?sid=")+r"\d+$"        
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        url = self.url
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+
+        data = self._fetchUrl(url)
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        # Find authorid and URL from... author url.
+        author = soup.find('div', {'id':"pagetitle"}).find('a')
+        self.story.setMetadata('authorId',author['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/peja/cgi-bin/'+author['href'])
+        self.story.setMetadata('author',author.string)
+		
+        authorSoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
+
+        # eFiction sites don't help us out a lot with their meta data
+        # 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)
+        titleblock=title.parent.parent
+        
+        chapterselect=soup.find('select',{'name':'chapter'})
+        if chapterselect:
+            for ch in chapterselect.findAll('option'):
+                self.chapterUrls.append((stripHTML(ch),'http://'+self.host+'/peja/cgi-bin/viewstory.php?sid='+self.story.getMetadata('storyId')+'&chapter='+ch['value']))
+        else:
+            self.chapterUrls.append((title,url))
+		
+        self.story.setMetadata('numChapters',len(self.chapterUrls))
+
+        
+        # utility method
+        def defaultGetattr(d,k):
+            try:
+                return d[k]
+            except:
+                return ""
+
+        # <span class="classification">Rated:</span> NC-17<br /> etc
+        labels = titleblock.findAll('span',{'class':'classification'})
+        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') == 'classification':
+                    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 'Characters' in label:
+                for char in value.split(','):
+                    self.story.addToList('characters',char.strip())
+
+            if 'Genre' in label:
+                for genre in value.split(','):
+                    if genre.strip() != "None":
+                        self.story.addToList('genre',genre.strip())
+
+            if 'Warnings' in label:
+                for warning in value.split(','):
+                    if warning.strip() != 'None':
+                        self.story.addToList('warnings',warning.strip())
+
+            if 'Word count' in label:
+                self.story.setMetadata('numWords', value)
+
+            if 'Fandoms' in label:
+                cats = labelspan.parent.findAll('a',href=re.compile(r'categories.php'))
+                catstext = [cat.string for cat in cats]
+                for cat in catstext:
+                    self.story.addToList('category',cat.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.
+            # http://www.squidge.org/peja/cgi-bin/series.php?seriesid=254
+            a = titleblock.find('a', href=re.compile(r"series.php\?seriesid=\d+"))
+            series_name = a.string
+            series_url = 'http://'+self.host+'/peja/cgi-bin/'+a['href']
+    
+            # use BeautifulSoup HTML parser to make everything easier to find.
+            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
+            storyas = seriessoup.findAll('a', href=re.compile(r'^viewstory.php\?sid=\d+$'))
+            i=1
+            for a in storyas:
+                if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
+                    self.setSeries(series_name, i)
+                    break
+                i+=1
+                
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+            
+	
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.debug('Getting chapter text from: %s' % url)
+
+        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
+                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        
+        chaptext = soup.find('div',{'id':"story"}).find('span')
+
+        if None == chaptext:
+            raise exceptions.FailedToDownload("Error downloading Chapter: %s!  Missing required element!" % url)
+    
+        return self.utf8FromSoup(url,chaptext)

fanficdownloader/adapters/adapter_wraithbaitcom.py

@@ -0,0 +1,227 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2011 Fanficdownloader team
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+import logging
+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 WraithBaitComAdapter
+
+# Class name has to be unique.  Our convention is camel case the
+# sitename with Adapter at the end.  www is skipped.
+class WraithBaitComAdapter(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])
+        logging.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
+        
+
+        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','wb')
+
+        # If all stories from the site fall into the same category,
+        # the site itself isn't likely to label them as such, so we
+        # do.
+        self.story.addToList("category","Stargate")
+
+        # 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 'www.wraithbait.com'
+
+    def getSiteExampleURLs(self):
+        return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234"
+
+    def getSiteURLPattern(self):
+        return re.escape("http://"+self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$"
+
+    ## Getting the chapter list and the meta data, plus 'is adult' checking.
+    def extractChapterUrlsAndMetadata(self):
+
+        if self.is_adult or self.getConfig("is_adult"):
+            # Weirdly, different sites use different warning numbers.
+            # If the title search below fails, there's a good chance
+            # you need a different number.  print data at that point
+            # and see what the 'click here to continue' url says.
+            addurl = "&ageconsent=ok&warning=12"
+        else:
+            addurl=""
+
+        # index=1 makes sure we see the story chapter index.  Some
+        # sites skip that for one-chapter stories.
+        url = self.url+'&index=1'+addurl
+        logging.debug("URL: "+url)
+
+        try:
+            data = self._fetchUrl(url)
+        except urllib2.HTTPError, e:
+            if e.code == 404:
+                raise exceptions.StoryDoesNotExist(self.url)
+            else:
+                raise e
+				
+        if "for adults only" in data:
+            raise exceptions.AdultCheckRequired(self.url)
+            
+        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
+            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
+            
+        # use BeautifulSoup HTML parser to make everything easier to find.
+        soup = bs.BeautifulSoup(data)
+        # print data
+
+        # Now go hunting for all the meta data and the chapter list.
+        
+        ## Title
+        pt = soup.find('div', {'id' : 'pagetitle'})
+        a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
+        self.story.setMetadata('title',a.string)
+        
+        # Find authorid and URL from... author url.
+        a = pt.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        self.story.setMetadata('authorId',a['href'].split('=')[1])
+        self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href'])
+        self.story.setMetadata('author',a.string)
+
+        rating=pt.text.split('[')[1].split(']')[0]
+        self.story.setMetadata('rating', rating)
+
+        # Find the chapters:
+        for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
+            # just in case there's tags, like <i> in chapter titles.
+            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 ""
+		
+        info = soup.find('div', {'class' : 'small'})
+		
+        word=info.find(text=re.compile("Word count:")).split(':')
+        self.story.setMetadata('numWords', word[1])
+		
+        cats = info.findAll('a',href=re.compile(r'browse.php\?type=categories&id=\d'))
+        for cat in cats:
+            if "General" != cat.string:
+                self.story.addToList('category',cat.string)
+				
+        chars = info.findAll('a',href=re.compile(r'browse.php\?type=characters&charid=\d'))
+        for char in chars:
+            self.story.addToList('characters',char.string)
+			
+        completed=info.find(text=re.compile("Completed: Yes"))
+        if completed != None:
+            self.story.setMetadata('status', 'Completed')
+        else:
+            self.story.setMetadata('status', 'In-Progress')
+			
+        date=soup.find('div',{'class' : 'bottom'})
+        pd=date.find(text=re.compile("Published:")).string.split(': ')
+        self.story.setMetadata('datePublished', makeDate(stripHTML(pd[1].split(' U')[0]), self.dateformat))
+        self.story.setMetadata('dateUpdated', makeDate(stripHTML(pd[2]), self.dateformat))
+		
+        # <span class="label">Rated:</span> NC-17<br /> etc
+        labels = soup.findAll('span',{'class':'label'})
+        pub=0
+        for labelspan in labels:
+            value = labelspan.nextSibling
+            label = labelspan.string
+
+            if 'Genres' in label:
+                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
+                for genre in genres:
+                    self.story.addToList('genre',genre.string)
+
+            if 'Warnings' in label:
+                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2'))
+                for warning in warnings:
+                    self.story.addToList('warnings',warning.string)
+
+        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)
+                    break
+                i+=1
+            
+        except:
+            # I find it hard to care if the series parsing fails
+            pass
+			
+        info.extract()
+        summary = soup.find('div', {'class' : 'content'})
+        self.setDescription(url,summary)
+            
+    # grab the text for an individual chapter.
+    def getChapterText(self, url):
+
+        logging.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/base_adapter.py

@@ -70,9 +70,7 @@ class BaseSiteAdapter(Configurable):
     def __init__(self, config, url):
         self.config = config
         Configurable.__init__(self, config)
-        self.setSectionOrder(self.getSiteDomain())
-        # self.addConfigSection(self.getSiteDomain())
-        # self.addConfigSection("overrides")
+        self.setSectionOrder(self.getConfigSection())
         
         self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
         self.password = ""
@@ -82,7 +80,7 @@ class BaseSiteAdapter(Configurable):
         self.storyDone = False
         self.metadataDone = False
         self.story = Story()
-        self.story.setMetadata('site',self.getSiteDomain())
+        self.story.setMetadata('site',self.getConfigSection())
         self.story.setMetadata('dateCreated',datetime.datetime.now())
         self.chapterUrls = [] # tuples of (chapter title,chapter url)
         self.chapterFirst = None
@@ -235,6 +233,11 @@ class BaseSiteAdapter(Configurable):
         "Needs to be overriden in each adapter class."
         return 'no such domain'
     
+    @classmethod
+    def getConfigSection(cls):
+        "Only needs to be overriden if != site domain."
+        return cls.getSiteDomain()
+    
     ## URL pattern validation is done *after* picking an adaptor based
     ## on domain instead of *as* the adaptor selector so we can offer
     ## the user example(s) for that particular site.

fanficdownloader/writers/base_writer.py

@@ -38,11 +38,7 @@ class BaseStoryWriter(Configurable):
 
     def __init__(self, config, adapter):
         Configurable.__init__(self, config)
-        self.setSectionOrder(adapter.getSiteDomain(),self.getFormatName())
-        # self.addConfigSection(adapter.getSiteDomain())
-        # self.addConfigSection(self.getFormatName())
-        # self.addConfigSection(adapter.getSiteDomain()+":"+self.getFormatName())
-        # self.addConfigSection("overrides")
+        self.setSectionOrder(adapter.getConfigSection(),self.getFormatName())
         
         self.adapter = adapter
         self.story = adapter.getStoryMetadataOnly() # only cache the metadata initially.

index.html

@@ -54,14 +54,18 @@
 	      much easier. </p>
 	  </div>
 	  <!-- put announcements here, h3 is a good title size. -->
-	  <h3>Latest Changes</h3>
+	  <h3>New Sites</h3>
 	  <p>
-	    Fix for 'Hide this banner' title issue on Archive of Our
-	    Own.
+	    We now support www.wraithbait.com and
+	    www.libraryofmoria.com, thanks to Ida for adding these!
 	  </p>
 	  <p>
-	    Changed implementation of fimfiction to use provided API,
-	    thanks to Althaine.
+	    Support for the Wonderful World of MakeBelieve(WWOMB)
+	    archive at
+	    <a href="http://www.squidge.org/peja/cgi-bin/index.php">http://www.squidge.org/peja/cgi-bin/index.php</a>
+	    has also been added.  This does not support other sections of
+	    www.squidge.org, or the other files under www.squidge.org/peja that
+	    aren't in the eFiction instance.
 	  </p>
 	  <p>
 	    Questions?  Check out our 
@@ -71,7 +75,7 @@
 	    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://4-4-7.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
+	    <a href="http://4-4-8.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
 	  </p>
 	  <div id='error'>
 	    {{ error_message }}
@@ -296,6 +300,22 @@
 	    Use the URL of the story's summary, such as
 	    <br /><a href="http://archive.skyehawke.com/story.php?no=17466">http://archive.skyehawke.com/story.php?no=17466</a>.
 	  </dd>
+	  <dt>www.libraryofmoria.com</dt>
+	  <dd>
+	    Use the URL of the story's summary, such as
+	    <br /><a href="http://www.libraryofmoria.com/a/viewstory.php?sid=434">http://www.libraryofmoria.com/a/viewstory.php?sid=434</a>.
+	  </dd>
+	  <dt>www.wraithbait.com</dt>
+	  <dd>
+	    Use the URL of the story's summary, such as
+	    <br /><a href="http://www.wraithbait.com/viewstory.php?sid=14305">http://www.wraithbait.com/viewstory.php?sid=14305</a>.
+	  </dd>
+	  <dt>www.squidge.org/peja (WWOMB)</dt>
+	  <dd>
+	    Use the URL of the story's summary, such as
+	    <br /><a href="http://www.squidge.org/peja/cgi-bin/viewstory.php?sid=1234">http://www.squidge.org/peja/cgi-bin/viewstory.php?sid=1234</a>.<br />
+	    This is <i>only</i> for squidge.org/peja, not other parts of squidge.org.
+	  </dd>
 	</dl>
 	<p>
 	  A few additional things to know, which will make your life substantially easier:

main.py

@@ -418,7 +418,7 @@ class FanfictionDownloader(UserConfigServer):
             template_values = dict(nickname = user.nickname(),
                                    url = url,
                                    format = format,
-                                   site = adapter.getSiteDomain(),
+                                   site = adapter.getConfigSection(),
                                    fic = download,
                                    is_login=is_login,
                                    )

plugin-defaults.ini

@@ -413,6 +413,12 @@ extratags:
 ## this should go in your personal.ini, not defaults.ini.
 #is_adult:true
 
+[www.libraryofmoria.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
 [www.mediaminer.org]
 
 [www.midnightwhispers.ca]
@@ -429,6 +435,17 @@ cover_exclusion_regexp:/stories/999/images/.*?_trophy.png
 
 [www.siye.co.uk]
 
+[www.squidge.org/peja]
+# www.squidge.org/peja calls it Fandom <shrug>
+category_label:Fandom
+# Remove numWords -- www.squidge.org/peja word counts are inaccurate
+titlepage_entries: series,category,genre,language,characters,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,description
+
+[www.squidge.org/peja:txt]
+## Add URLs since there aren't links.
+# Remove numWords -- www.squidge.org/peja word counts are inaccurate
+titlepage_entries: series,category,genre,language,status,datePublished,dateUpdated,dateCreated,rating,warnings,numChapters,site,storyUrl, authorUrl, description
+
 [www.thewriterscoffeeshop.com]
 ## Some sites require login (or login for some rated stories) The
 ## program can prompt you, or you can save it in config.  In
@@ -482,6 +499,12 @@ collect_series: false
 
 [www.whofic.com]
 
+[www.wraithbait.com]
+## Some sites do not require a login, but do require the user to
+## confirm they are adult for adult content.  In commandline version,
+## this should go in your personal.ini, not defaults.ini.
+#is_adult:true
+
 [overrides]
 ## It may sometimes be useful to override all of the specific format,
 ## site and site:format sections in your private configuration.  For