Remove dead sites prisonbreakfic.net, svufiction.com; bump versions.

app.yaml

@@ -1,6 +1,6 @@
 # ffd-retief-hrd fanfictiondownloader
 application: fanfictiondownloader
-version: 4-4-53
+version: 4-4-55
 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, 7, 20)
+    version             = (1, 7, 22)
     minimum_calibre_version = (0, 8, 57)
 
     #: This field defines the GUI plugin class that contains all the code

calibre-plugin/common_utils.py

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

calibre-plugin/dialogs.py

@@ -258,8 +258,8 @@ class AddNewDialog(SizePersistedDialog):
 
     # invoke the 
     def ok_clicked(self):
+        self.dialog_closing(None) # save persistent size.
         self.hide()
-        print("ok_clicked called")
         self.go_signal.emit( self.get_ffdl_options(),
                              self.get_urlstext(),
                              self.merge,

defaults.ini

@@ -571,6 +571,11 @@ extraships:Spike/Buffy
 #username:YourName
 #password:yourpassword
 
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
+#is_adult:true
+
 [dramione.org]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter

fanficdownloader/adapters/__init__.py

@@ -71,7 +71,6 @@ import adapter_thehexfilesnet
 import adapter_dokugacom
 import adapter_iketernalnet
 import adapter_onedirectionfanfictioncom
-import adapter_prisonbreakficnet
 import adapter_storiesofardacom
 import adapter_samdeanarchivenu
 import adapter_destinysgatewaycom
@@ -88,7 +87,6 @@ import adapter_pretendercentrecom
 import adapter_darksolaceorg
 import adapter_finestoriescom
 import adapter_hpfanficarchivecom
-import adapter_svufictioncom
 import adapter_twilightarchivescom
 import adapter_wizardtalesnet
 import adapter_nhamagicalworldsus

fanficdownloader/adapters/adapter_archiveofourownorg.py

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

fanficdownloader/adapters/adapter_darksolaceorg.py

@@ -49,7 +49,6 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
         # get storyId from url--url validation guarantees query is only sid=1234
         self.story.setMetadata('storyId',self.parsedUrl.query.split('=',)[1])
         logger.debug("storyId: (%s)"%self.story.getMetadata('storyId'))
-		
         
         # normalized story URL.
         self._setURL('http://' + self.getSiteDomain() + '/elysian/viewstory.php?sid='+self.story.getMetadata('storyId'))
@@ -59,7 +58,7 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
 
         # The date format will vary from site to site.
         # http://docs.python.org/library/datetime.html#strftime-strptime-behavior
-        self.dateformat = "%d %B %Y"
+        self.dateformat = "%B %d, %Y"
             
     @staticmethod # must be @staticmethod, don't remove it.
     def getSiteDomain():
@@ -79,7 +78,8 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
     ## Login seems to be reasonably standard across eFiction sites.
     def needToLoginCheck(self, data):
         if 'This story contains adult content not suitable for children' in data \
-                or "That password doesn't match the one in our database" in data:
+                or "That password doesn't match the one in our database" in data \
+                or "Registered Users Only" in data:
             return True
         else:
             return False
@@ -94,17 +94,16 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
             params['penname'] = self.getConfig("username")
             params['password'] = self.getConfig("password")
         params['rememberme'] = '1'
-        params['sid'] = ''
-        params['intent'] = ''
+        params['action'] = 'login'
         params['submit'] = 'Submit'
     
         loginUrl = 'http://' + self.getSiteDomain() + '/elysian/user.php'
         logger.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
                                                               params['penname']))
     
-        d = self._fetchUrl(loginUrl, params)
+        d = self._postUrl(loginUrl, params)
     
-        if "User Account Page" not in d : #Member Account
+        if "Member Account" not in d : #User Account Page
             logger.info("Failed to login to URL %s as %s, or have no authorization to access the story" % (loginUrl, params['penname']))
             raise exceptions.FailedToLogin(url,params['penname'])
             return False
@@ -113,9 +112,19 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
 
     ## Getting the chapter list and the meta data, plus 'is adult' checking.
     def extractChapterUrlsAndMetadata(self):
+        
+        if self.is_adult or self.getConfig("is_adult"):
+            # Weirdly, different sites use different warning numbers.
+            # If the title search below fails, there's a good chance
+            # you need a different number.  print data at that point
+            # and see what the 'click here to continue' url says.
+            addurl = "&ageconsent=ok&warning=5"
+        else:
+            addurl=""
+
         # index=1 makes sure we see the story chapter index.  Some
         # sites skip that for one-chapter stories.
-        url = self.url
+        url = self.url+'&index=1'+addurl
         logger.debug("URL: "+url)
 
         try:
@@ -128,9 +137,30 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
 
         if self.needToLoginCheck(data):
             # need to log in for this one.
-            addurl="&ageconsent=ok"
             self.performLogin(url)
-            data = self._fetchUrl(url+addurl)
+            data = self._fetchUrl(url)
+            
+        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
+        if m != None:
+            if self.is_adult or self.getConfig("is_adult"):
+                # We tried the default and still got a warning, so
+                # let's pull the warning number from the 'continue'
+                # link and reload data.
+                addurl = m.group(1)
+                # correct stupid & error in url.
+                addurl = addurl.replace("&","&")
+                url = self.url+'&index=1'+addurl
+                logger.debug("URL 2nd try: "+url)
+
+                try:
+                    data = self._fetchUrl(url)
+                except urllib2.HTTPError, e:
+                    if e.code == 404:
+                        raise exceptions.StoryDoesNotExist(self.url)
+                    else:
+                        raise e    
+            else:
+                raise exceptions.AdultCheckRequired(self.url)
             
         if "Access denied. This story has not been validated by the adminstrators of this site." in data:
             raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
@@ -142,33 +172,41 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
         # Now go hunting for all the meta data and the chapter list.
         
         ## Title and author
-        a = soup.find('div', {'id' : 'pagetitle'})
+        div = soup.find('div', {'id' : 'pagetitle'})
         
-        aut = a.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
+        aut = div.find('a', href=re.compile(r"viewuser.php\?uid=\d+"))
         self.story.setMetadata('authorId',aut['href'].split('=')[1])
         self.story.setMetadata('authorUrl','http://'+self.host+'/elysian/'+aut['href'])
         self.story.setMetadata('author',aut.string)
         aut.extract()
-        
-        self.story.setMetadata('title',a.string[:(len(a.string)-3)])
+
+        # first a tag in pagetitle is title
+        self.story.setMetadata('title',stripHTML(div.find('a')))
 
         # Find the chapters:
-        chapters=soup.find('select', {'name' : 'chapter'})
-        if chapters != None:
-            for chapter in chapters.findAll('option'):
-                self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/elysian/viewstory.php?sid='+self.story.getMetadata('storyId')+'&chapter='+chapter['value']))
-        else:
-            self.chapterUrls.append((self.story.getMetadata('title'),url))
+        # chapters=soup.find('select', {'name' : 'chapter'})
+        # if chapters != None:
+        #     for chapter in chapters.findAll('option'):
+        #         self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/elysian/viewstory.php?sid='+self.story.getMetadata('storyId')+'&chapter='+chapter['value']))
+        # else:
+        #     self.chapterUrls.append((self.story.getMetadata('title'),url+"&chapter=1"))
 
+        for chapa in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+
+                                                       self.story.getMetadata('storyId')+'&chapter=\d+')):
+            self.chapterUrls.append((stripHTML(chapa),'http://'+self.host+'/elysian/'+chapa['href']))
+        
         self.story.setMetadata('numChapters',len(self.chapterUrls))
         
         asoup = bs.BeautifulSoup(self._fetchUrl(self.story.getMetadata('authorUrl')))
         
-        for list in asoup.findAll('div', {'class' : re.compile('listbox\s+')}):
-            a = list.find('a', href=re.compile(r'viewstory.php\?sid='))
-            if a != None:
-                if 'viewstory.php?sid='+self.story.getMetadata('storyId') in a['href']:
-                    break
+        # for metalist in asoup.findAll('div', {'class' : re.compile('listbox\s+')}):
+        #     a = metalist.find('a', href=re.compile(r'viewstory.php\?sid='))
+        #     if a != None:
+        #         if 'viewstory.php?sid='+self.story.getMetadata('storyId') in a['href']:
+        #             break
+
+        metalist = asoup.find('a', href=re.compile(r'viewstory.php\?sid='+
+                                                   self.story.getMetadata('storyId')+'($|[^\d])')).parent.parent
 
         # eFiction sites don't help us out a lot with their meta data
         # formating, so it's a little ugly.
@@ -182,7 +220,7 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
                 
 
         # <span class="label">Rated:</span> NC-17<br /> etc
-        labels = list.findAll('span', {'class' : 'classification'})
+        labels = metalist.findAll('span', {'class' : 'label'})
         for labelspan in labels:
             label = labelspan.text
             value = labelspan.nextSibling
@@ -190,7 +228,7 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
             if 'Summary' in label:
                 ## Everything until the next span class='label'
                 svalue = ""
-                while not (defaultGetattr(value,'class') == 'classification' or "Chapters: " in stripHTML(value)):
+                while not (defaultGetattr(value,'class') == 'label' or "Chapters: " in stripHTML(value)):
                     svalue += str(value)
                     value = value.nextSibling
                 self.setDescription(url,svalue)
@@ -238,7 +276,7 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
 
         try:
             # Find Series name from series URL.
-            a = list.find('a', href=re.compile(r"series.php\?seriesid=\d+"))
+            a = metalist.find('a', href=re.compile(r"series.php\?seriesid=\d+"))
             series_name = a.string
             series_url = 'http://'+self.host+'/elysian/'+a['href']
 
@@ -265,8 +303,7 @@ class DarkSolaceOrgAdapter(BaseSiteAdapter):
 
         logger.debug('Getting chapter text from: %s' % url)
 
-        soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
-                                     selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
+        soup = bs.BeautifulSoup(self._fetchUrl(url))
         
         div = soup.find('div', {'id' : 'story'})
 

fanficdownloader/adapters/adapter_prisonbreakficnet.py

@@ -1,217 +0,0 @@
-# -*- coding: utf-8 -*-
-
-# Copyright 2012 Fanficdownloader team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-#
-
-import time
-import logging
-logger = logging.getLogger(__name__)
-import re
-import urllib2
-
-from .. import BeautifulSoup as bs
-from ..htmlcleanup import stripHTML
-from .. import exceptions as exceptions
-
-from base_adapter import BaseSiteAdapter,  makeDate
-
-def getClass():
-    return PrisonBreakFicNetAdapter
-
-# Class name has to be unique.  Our convention is camel case the
-# sitename with Adapter at the end.  www is skipped.
-class PrisonBreakFicNetAdapter(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','pbf')
-
-        # 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.prisonbreakfic.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+$"
-
-    ## Getting the chapter list and the meta data, plus 'is adult' checking.
-    def extractChapterUrlsAndMetadata(self):
-
-        # index=1 makes sure we see the story chapter index.  Some
-        # sites skip that for one-chapter stories.
-        url = self.url+'&index=1'
-        logger.debug("URL: "+url)
-
-        try:
-            data = self._fetchUrl(url)
-        except urllib2.HTTPError, e:
-            if e.code == 404:
-                raise exceptions.StoryDoesNotExist(self.url)
-            else:
-                raise e
-            
-        # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
-        # print data
-
-        # Now go hunting for all the meta data and the chapter list.
-        
-        ## Title
-        a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        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+'/'+chapter['href']))
-
-        self.story.setMetadata('numChapters',len(self.chapterUrls))
-
-        # eFiction sites don't help us out a lot with their meta data
-        # formating, so it's a little ugly.
-
-        # utility method
-        def defaultGetattr(d,k):
-            try:
-                return d[k]
-            except:
-                return ""
-                
-# summary, rated, word count, categories, characters, genre, warnings, completed, published, updated, seires
-
-        # <span class="label">Rated:</span> NC-17<br /> etc
-        labels = soup.findAll('span',{'class':'label'})
-        for labelspan in labels:
-            value = labelspan.nextSibling
-            label = labelspan.string
-
-            if 'Summary' in label:
-                ## Everything until the next span class='label'
-                svalue = ""
-                while not defaultGetattr(value,'class') == 'label':
-                    svalue += str(value)
-                    value = value.nextSibling
-                self.setDescription(url,svalue)
-                #self.story.setMetadata('description',stripHTML(svalue))
-
-            if 'Rated' in label:
-                self.story.setMetadata('rating', value)
-
-            if 'Word count' in label:
-                self.story.setMetadata('numWords', value)
-
-            if 'Categories' in label:
-                cats = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=categories'))
-                for cat in cats:
-                    self.story.addToList('category',cat.string)
-
-            if 'Characters' in label:
-                chars = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=characters'))
-                for char in chars:
-                    self.story.addToList('characters',char.string)
-
-            if 'Pairing' in label:
-                ships = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=3')) # XXX
-                for ship in ships:
-                    self.story.addToList('ships',ship.string.replace(" and ","/"))
-
-            if 'Genre' in label:
-                genres = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1')) # XXX
-                for genre in genres:
-                    self.story.addToList('genre',genre.string)
-
-            if 'Warnings' in label:
-                warnings = labelspan.parent.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=2')) # XXX
-                for warning in warnings:
-                    self.story.addToList('warnings',warning.string)
-
-            if 'Completed' in label:
-                if 'Yes' in value:
-                    self.story.setMetadata('status', 'Completed')
-                else:
-                    self.story.setMetadata('status', 'In-Progress')
-
-            if 'Published' in label:
-                self.story.setMetadata('datePublished', makeDate(stripHTML(value), self.dateformat))
-            
-            if 'Updated' in label:
-                self.story.setMetadata('dateUpdated', makeDate(stripHTML(value), self.dateformat))
-
-        try:
-            # Find Series name from series URL.
-            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
-            series_name = a.string
-            series_url = 'http://'+self.host+'/'+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_svufictioncom.py

@@ -1,273 +0,0 @@
-# -*- coding: utf-8 -*-
-
-# Copyright 2012 Fanficdownloader team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-#
-
-import time
-import logging
-logger = logging.getLogger(__name__)
-import re
-import urllib2
-
-from .. import BeautifulSoup as bs
-from ..htmlcleanup import stripHTML
-from .. import exceptions as exceptions
-
-from base_adapter import BaseSiteAdapter,  makeDate
-
-def getClass():
-    return SVUFictionComAdapter
-
-# Class name has to be unique.  Our convention is camel case the
-# sitename with Adapter at the end.  www is skipped.
-class SVUFictionComAdapter(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','svuf')
-
-        # 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 'svufiction.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=6"
-        else:
-            addurl=""
-
-        # index=1 makes sure we see the story chapter index.  Some
-        # sites skip that for one-chapter stories.
-        url = self.url+'&index=1'+addurl
-        logger.debug("URL: "+url)
-
-        try:
-            data = self._fetchUrl(url)
-        except urllib2.HTTPError, e:
-            if e.code == 404:
-                raise exceptions.StoryDoesNotExist(self.url)
-            else:
-                raise e
-                
-        if self.needToLoginCheck(data):
-            # need to log in for this one.
-            self.performLogin(url)
-            data = self._fetchUrl(url)
-                
-        m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data)
-        if m != None:
-            if self.is_adult or self.getConfig("is_adult"):
-                # We tried the default and still got a warning, so
-                # let's pull the warning number from the 'continue'
-                # link and reload data.
-                addurl = m.group(1)
-                # correct stupid & error in url.
-                addurl = addurl.replace("&","&")
-                url = self.url+'&index=1'+addurl
-                logger.debug("URL 2nd try: "+url)
-
-                try:
-                    data = self._fetchUrl(url)
-                except urllib2.HTTPError, e:
-                    if e.code == 404:
-                        raise exceptions.StoryDoesNotExist(self.url)
-                    else:
-                        raise e    
-            else:
-                raise exceptions.AdultCheckRequired(self.url)
-            
-        if "Access denied. This story has not been validated by the adminstrators of this site." in data:
-            raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.")
-            
-        # use BeautifulSoup HTML parser to make everything easier to find.
-        soup = bs.BeautifulSoup(data)
-        # print data
-
-        # Now go hunting for all the meta data and the chapter list.
-        
-        ## Title
-        pt = soup.find('div', {'class' : 'title'})
-        a = pt.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$"))
-        if a.text != "":
-            self.story.setMetadata('title',a.text)
-        else:
-            self.story.setMetadata('title','Banner')
-        
-        # 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 ""
-
-        bottom=soup.find('div', {'class' : 'bottom'}).text
-        self.story.setMetadata('numWords', bottom.split('Word count: ')[1].split(' Read:')[0])
-        self.story.setMetadata('datePublished', makeDate(bottom.split('Published: ')[1].split(' Updated:')[0], self.dateformat))
-        self.story.setMetadata('dateUpdated', makeDate(bottom.split('Updated: ')[1], self.dateformat))
-
-        
-        content=soup.find('div', {'class' : 'content'})
-        value=content.find('h1').nextSibling
-        svalue = ""
-        while not defaultGetattr(value,'class') == 'smaller':
-            svalue += str(value)
-            value = value.nextSibling
-        self.setDescription(url,svalue)
-        
-        status = content.text.split('Completed: ')[1]
-        if 'Yes' in status:
-            self.story.setMetadata('status', 'Completed')
-        else:
-            self.story.setMetadata('status', 'In-Progress')
-        
-        cats = content.findAll('a',href=re.compile(r'browse.php\?type=categories'))
-        for cat in cats:
-            self.story.addToList('category',cat.string)
-            
-        chars = content.findAll('a',href=re.compile(r'browse.php\?type=characters'))
-        for char in chars:
-            self.story.addToList('characters',char.string)
-            
-        genres = content.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1'))
-        for genre in genres:
-            self.story.addToList('genre',genre.string)
-            
-        try:
-            # Find Series name from series URL.
-            a = soup.find('a', href=re.compile(r"viewseries.php\?seriesid=\d+"))
-            series_name = a.string
-            series_url = 'http://'+self.host+'/'+a['href']
-
-            # use BeautifulSoup HTML parser to make everything easier to find.
-            seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
-            # can't use ^viewstory...$ in case of higher rated stories with javascript href.
-            storyas = seriessoup.findAll('a', href=re.compile(r'viewstory.php\?sid=\d+'))
-            i=1
-            for a in storyas:
-                # skip 'report this' and 'TOC' links
-                if 'contact.php' not in a['href'] and 'index' not in a['href']:
-                    if a['href'] == ('viewstory.php?sid='+self.story.getMetadata('storyId')):
-                        self.setSeries(series_name, i)
-                        self.story.setMetadata('seriesUrl',series_url)
-                        break
-                    i+=1
-            
-        except:
-            # I find it hard to care if the series parsing fails
-            pass
-            
-    # 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_thewriterscoffeeshopcom.py

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

fanficdownloader/configurable.py

@@ -37,10 +37,20 @@ class Configuration(ConfigParser.SafeConfigParser):
     def __init__(self, site, fileform):
         ConfigParser.SafeConfigParser.__init__(self)
         self.sectionslist = ['defaults']
-        self.addConfigSection(site)
+
+        if site.startswith("www."):
+            sitewith = site
+            sitewithout = site.replace("www.","")
+        else:
+            sitewith = "www."+site
+            sitewithout = site
+        
+        self.addConfigSection(sitewith)
+        self.addConfigSection(sitewithout)
         if fileform:
             self.addConfigSection(fileform)
-            self.addConfigSection(site+":"+fileform)
+            self.addConfigSection(sitewith+":"+fileform)
+            self.addConfigSection(sitewithout+":"+fileform)
         self.addConfigSection("overrides")
         
         self.validEntries = [

fanficdownloader/geturls.py

@@ -105,9 +105,9 @@ def get_urls_from_text(data,configuration=None,normalize=False):
         # 'are you old enough' links, and 'Report This' links.
         # The 'normalized' set prevents duplicates.
         if 'story.php' in href:
-            m = re.search(r"(?P<sid>(view)?story\.php\?(sid|psid|no|story|stid)=\d+)",a['href'])
+            m = re.search(r"(?P<sid>(view)?story\.php\?(sid|psid|no|story|stid)=\d+)",href)
             if m != None:
-                href = form_url(None,m.group('sid'))
+                href = form_url(href,m.group('sid'))
         try:
             href = href.replace('&index=1','')
             adapter = adapters.getAdapter(configuration,href)

index.html

@@ -57,7 +57,10 @@
 	  <h3>Changes:</h3>
 	  <p>
 	    <ul>
-	      <li>Yet another fix for fanfiction.net changes.</li>
+	      <li>Fix for archiveofourown.org series URL.</li>
+	      <li>Include notes in chapter text on thewriterscoffeeshop.com.</li>
+	      <li>Remove support for site prisonbreakfic.net--site is no longer there.<li>
+	      <li>Remove support for site svufiction.com--site is no longer there.<li>
 	    </ul>
 	  </p>
 	  <p>
@@ -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://4-4-52.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
+	    <a href="http://4-4-54.fanfictiondownloader.appspot.com">Previous Version</a> is also available for you to use if necessary.
 	  </p>
 	  <div id='error'>
 	    {{ error_message }}
@@ -378,11 +381,6 @@
 	    Use the URL of the story's first chapter, such as
 	    <br /><a href="http://onedirectionfanfiction.com/viewstory.php?sid=1234">http://onedirectionfanfiction.com/viewstory.php?sid=1234</a>
 	  </dd>
-	  <dt>www.prisonbreakfic.net</dt>
-	  <dd>
-	    Use the URL of the story's first chapter, such as
-	    <br /><a href="http://www.prisonbreakfic.net/viewstory.php?sid=1234">http://www.prisonbreakfic.net/viewstory.php?sid=1234</a>
-	  </dd>
 	  <dt>www.storiesofarda.com</dt>
 	  <dd>
 	    Use the URL of the story's chapter list, such as
@@ -471,11 +469,6 @@
 	    Use the URL of the story's first chapter, such as
 	    <br /><a href="http://www.hpfanficarchive.com/stories/viewstory.php?sid=1234">http://www.hpfanficarchive.com/stories/viewstory.php?sid=1234</a>
 	  </dd>
-	  <dt>svufiction.com</dt>
-	  <dd>
-	    Use the URL of the story's first chapter, such as
-	    <br /><a href="http://svufiction.com/viewstory.php?sid=1234">http://svufiction.com/viewstory.php?sid=1234</a>
-	  </dd>
 	  <dt>www.twilightarchives.com</dt>
 	  <dd>
 	    Use the URL of the story's first chapter, such as

plugin-defaults.ini

@@ -537,6 +537,11 @@ extraships:Spike/Buffy
 #username:YourName
 #password:yourpassword
 
+## Some sites also require the user to confirm they are adult for
+## adult content.  In commandline version, this should go in your
+## personal.ini, not defaults.ini.
+#is_adult:true
+
 [dramione.org]
 ## Site dedicated to these categories/characters/ships
 extracategories:Harry Potter