diff --git a/fanficdownloader/adapters/adapter_fanfiktionde.py b/fanficdownloader/adapters/adapter_fanfiktionde.py new file mode 100644 index 00000000..7a215282 --- /dev/null +++ b/fanficdownloader/adapters/adapter_fanfiktionde.py @@ -0,0 +1,154 @@ +# -*- 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 +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 FanFiktionDeAdapter + +# Class name has to be unique. Our convention is camel case the +# sitename with Adapter at the end. www is skipped. +class FanFiktionDeAdapter(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.path.split('/',)[2]) + logging.debug("storyId: (%s)"%self.story.getMetadata('storyId')) + + # normalized story URL. + self._setURL('http://' + self.getSiteDomain() + '/s/'+self.story.getMetadata('storyId') + '/1') + + # Each adapter needs to have a unique site abbreviation. + self.story.setMetadata('siteabbrev','ffde') + + # 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 'www.fanfiktion.de' + + def getSiteExampleURLs(self): + return "http://"+self.getSiteDomain()+"/s/46ccbef30000616306614050" + + def getSiteURLPattern(self): + return re.escape("http://"+self.getSiteDomain()+"/s/")+r"\w+(/\d+)?$" + + ## Getting the chapter list and the meta data, plus 'is adult' checking. + def extractChapterUrlsAndMetadata(self): + + url = self.url + logging.debug("URL: "+url) + + try: + data = self._fetchUrl(url) + except urllib2.HTTPError, e: + if e.code == 404: + raise exceptions.StoryDoesNotExist(self.url) + else: + raise e + + # use BeautifulSoup HTML parser to make everything easier to find. + soup = bs.BeautifulSoup(data) + # print data + + # Now go hunting for all the meta data and the chapter list. + + ## Title + a = soup.find('a', href=re.compile(r'/s/'+self.story.getMetadata('storyId')+"$")) + self.story.setMetadata('title',a.string) + + # Find authorid and URL from... author url. + head = soup.find('div', {'style' : 'width:85%;float:left;'}) + a = head.find('a') + self.story.setMetadata('authorId',a['href'].split('/')[2]) + self.story.setMetadata('authorUrl','http://'+self.host+'/'+a['href']) + self.story.setMetadata('author',a.string) + + # Find the chapters: + for chapter in soup.find('select').findAll('option'): + self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/s/'+self.story.getMetadata('storyId')+'/'+chapter['value'])) + + self.story.setMetadata('numChapters',len(self.chapterUrls)) + self.story.setMetadata('language','German') + + #find metadata on the story page + self.story.setMetadata('datePublished', makeDate(head.text.split('erstellt: ')[1].split('\n')[0], self.dateformat)) + + self.story.setMetadata('dateUpdated', makeDate(head.text.split('letztes Update: ')[1].split('\n')[0], self.dateformat)) + + for genre in head.text.split('   ')[3].split('/')[0].split(', '): + self.story.addToList('genre',genre) + + if 'fertiggestellt' in head.text: + self.story.setMetadata('status', 'Fertiggestellt') + else: + self.story.setMetadata('status', 'In Arbeit') + + #find metadata on the author's page + asoup = bs.BeautifulSoup(self._fetchUrl("http://"+self.getSiteDomain()+"?a=q&a1=v&t=nickdetailsstories&lbi=stories&ar=0&nick="+self.story.getMetadata('authorId'))) + tr=asoup.findAll('tr') + for i in range(1,len(tr)): + a = tr[i].find('a') + if a['href'] == '/s/'+self.story.getMetadata('storyId'): + break + self.setDescription(url,a['onmouseover'].split("', '")[1]) + + td = tr[i].findAll('td') + self.story.addToList('category',td[1].string) + self.story.setMetadata('rating', td[4].string) + self.story.setMetadata('numWords', td[5].string) + + + # grab the text for an individual chapter. + def getChapterText(self, url): + + logging.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' : 'storytext'}) + for a in div.findAll('script'): + a.extract() + + if None == div: + raise exceptions.FailedToDownload("Error downloading Chapter: %s! Missing required element!" % url) + + return self.utf8FromSoup(url,div) diff --git a/fanficdownloader/adapters/adapter_ficbooknet.py b/fanficdownloader/adapters/adapter_ficbooknet.py index 5e2154f2..4874db0c 100644 --- a/fanficdownloader/adapters/adapter_ficbooknet.py +++ b/fanficdownloader/adapters/adapter_ficbooknet.py @@ -94,7 +94,7 @@ class FicBookNetAdapter(BaseSiteAdapter): ## Title a = soup.find('h1') - self.story.setMetadata('title',a.string) + self.story.setMetadata('title',stripHTML(a)) logging.debug("Title: (%s)"%self.story.getMetadata('title')) # Find authorid and URL from... author url. diff --git a/fanficdownloader/adapters/adapter_ponyfictionarchivenet.py b/fanficdownloader/adapters/adapter_ponyfictionarchivenet.py new file mode 100644 index 00000000..47986c22 --- /dev/null +++ b/fanficdownloader/adapters/adapter_ponyfictionarchivenet.py @@ -0,0 +1,252 @@ +# -*- 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 +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 PonyFictionArchiveNetAdapter + +# Class name has to be unique. Our convention is camel case the +# sitename with Adapter at the end. www is skipped. +class PonyFictionArchiveNetAdapter(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')) + logging.info(self.parsedUrl.netloc) + # normalized story URL. + if "explicit" in self.parsedUrl.netloc: + self._setURL('http://explicit.' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId')) + self.dateformat = "%d/%b/%y" + else: + self._setURL('http://' + self.getSiteDomain() + '/viewstory.php?sid='+self.story.getMetadata('storyId')) + self.dateformat = "%d %b %Y" + + # Each adapter needs to have a unique site abbreviation. + self.story.setMetadata('siteabbrev','pffa') + + # 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","My Little Pony") + + @staticmethod # must be @staticmethod, don't remove it. + def getSiteDomain(): + # The site domain. Does have www here, if it uses it. + return 'ponyfictionarchive.net' + + @classmethod + def getAcceptDomains(cls): + return ['www.ponyfictionarchive.net','ponyfictionarchive.net','explicit.ponyfictionarchive.net'] + + def getSiteExampleURLs(self): + return "http://"+self.getSiteDomain()+"/viewstory.php?sid=1234" + + def getSiteURLPattern(self): + return re.escape("http://")+"(www\.|explicit\.)?"+re.escape(self.getSiteDomain()+"/viewstory.php?sid=")+r"\d+$" + + + ## Getting the chapter list and the meta data, plus 'is adult' checking. + def extractChapterUrlsAndMetadata(self): + + if self.is_adult or self.getConfig("is_adult"): + # Weirdly, different sites use different warning numbers. + # If the title search below fails, there's a good chance + # you need a different number. print data at that point + # and see what the 'click here to continue' url says. + addurl = "&warning=9" + else: + addurl="" + + # index=1 makes sure we see the story chapter index. Some + # sites skip that for one-chapter stories. + url = self.url+'&index=1'+addurl + logging.debug("URL: "+url) + + try: + data = self._fetchUrl(url) + except urllib2.HTTPError, e: + if e.code == 404: + raise exceptions.StoryDoesNotExist(self.url) + else: + raise e + + + m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data) + if m != None: + if self.is_adult or self.getConfig("is_adult"): + # We tried the default and still got a warning, so + # let's pull the warning number from the 'continue' + # link and reload data. + addurl = m.group(1) + # correct stupid & error in url. + addurl = addurl.replace("&","&") + url = self.url+'&index=1'+addurl + logging.debug("URL 2nd try: "+url) + + try: + data = self._fetchUrl(url) + except urllib2.HTTPError, e: + if e.code == 404: + raise exceptions.StoryDoesNotExist(self.url) + else: + raise e + else: + raise exceptions.AdultCheckRequired(self.url) + + if "Access denied. This story has not been validated by the adminstrators of this site." in data: + raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.") + + # use BeautifulSoup HTML parser to make everything easier to find. + soup = bs.BeautifulSoup(data) + # print data + + # Now go hunting for all the meta data and the chapter list. + + ## Title + a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$")) + 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 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 "" + + genres = soup.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=1')) + for genre in genres: + self.story.addToList('genre',genre.string) + + warnings = soup.findAll('a',href=re.compile(r'browse.php\?type=class&type_id=3')) + for warning in warnings: + self.story.addToList('warnings',warning.string) + + status = soup.find('a',href=re.compile(r'browse.php\?type=class&type_id=2')) + self.story.setMetadata('status',status.string) + + section = soup.findAll('span', {'class' : 'General'})[1] + + self.story.setMetadata('rating', section.previousSibling.previousSibling.string) + + value = section.nextSibling + svalue = "" + while not defaultGetattr(value,'class') == 'label': + svalue += str(value) + value = value.nextSibling + self.setDescription(url,svalue) + + # Rated: NC-17
etc + labels = soup.findAll('span',{'class':'label'}) + for labelspan in labels: + value = labelspan.nextSibling + label = labelspan.string + + if 'Word count' in label: + self.story.setMetadata('numWords', value) + + 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 '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)) + # 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) + 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) diff --git a/fanficdownloader/adapters/adapter_sg1heliopoliscom.py b/fanficdownloader/adapters/adapter_sg1heliopoliscom.py new file mode 100644 index 00000000..093443fd --- /dev/null +++ b/fanficdownloader/adapters/adapter_sg1heliopoliscom.py @@ -0,0 +1,255 @@ +# -*- 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 +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 SG1HeliopolisComAdapter + +# Class name has to be unique. Our convention is camel case the +# sitename with Adapter at the end. www is skipped. +class SG1HeliopolisComAdapter(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.story.setMetadata('section',self.parsedUrl.path.split('/',)[1]) + + # normalized story URL. + self._setURL('http://' + self.getSiteDomain() + '/'+self.story.getMetadata('section')+'/viewstory.php?sid='+self.story.getMetadata('storyId')) + + # Each adapter needs to have a unique site abbreviation. + self.story.setMetadata('siteabbrev','sghp') + + # 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. + if 'atlantis' in self.story.getMetadata('section'): + self.story.addToList("category","Stargate: Atlantis") + else: + self.story.addToList("category","Stargate: SG-1") + + # 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 'sg1-heliopolis.com' + + def getSiteExampleURLs(self): + return "http://"+self.getSiteDomain()+"/archive/viewstory.php?sid=1234 http://"+self.getSiteDomain()+"/adult/viewstory.php?sid=1234 http://"+self.getSiteDomain()+"/atlantis/viewstory.php?sid=1234" + + def getSiteURLPattern(self): + return r"http://sg1-heliopolis.com/(archive|adult|atlantis)?/viewstory.php\?sid=\d+$" + + + ## Getting the chapter list and the meta data, plus 'is adult' checking. + def extractChapterUrlsAndMetadata(self): + + if self.is_adult or self.getConfig("is_adult"): + # Weirdly, different sites use different warning numbers. + # If the title search below fails, there's a good chance + # you need a different number. print data at that point + # and see what the 'click here to continue' url says. + addurl = "&warning=4" + else: + addurl="" + + # index=1 makes sure we see the story chapter index. Some + # sites skip that for one-chapter stories. + url = self.url+'&index=1'+addurl + logging.debug("URL: "+url) + + try: + data = self._fetchUrl(url) + except urllib2.HTTPError, e: + if e.code == 404: + raise exceptions.StoryDoesNotExist(self.url) + else: + raise e + + m = re.search(r"'viewstory.php\?sid=\d+((?:&ageconsent=ok)?&warning=\d+)'",data) + if m != None: + if self.is_adult or self.getConfig("is_adult"): + # We tried the default and still got a warning, so + # let's pull the warning number from the 'continue' + # link and reload data. + addurl = m.group(1) + # correct stupid & error in url. + addurl = addurl.replace("&","&") + url = self.url+'&index=1'+addurl + logging.debug("URL 2nd try: "+url) + + try: + data = self._fetchUrl(url) + except urllib2.HTTPError, e: + if e.code == 404: + raise exceptions.StoryDoesNotExist(self.url) + else: + raise e + else: + raise exceptions.AdultCheckRequired(self.url) + + if "Access denied. This story has not been validated by the adminstrators of this site." in data: + raise exceptions.FailedToDownload(self.getSiteDomain() +" says: Access denied. This story has not been validated by the adminstrators of this site.") + + # use BeautifulSoup HTML parser to make everything easier to find. + soup = bs.BeautifulSoup(data) + # print data + + # Now go hunting for all the meta data and the chapter list. + + ## Title + a = soup.find('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"$")) + 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 in chapter titles. + self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+self.story.getMetadata('section')+'/'+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 "" + + # Rated: NC-17
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=2')) + 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+'/'+self.story.getMetadata('section')+'/'+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) + 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)