Backup_Repos/FanFicFare
1
0
Fork 0
mirror of https://github.com/JimmXinu/FanFicFare.git synced 2026-01-15 12:42:31 +01:00
Code Issues Projects Releases Wiki Activity

Fix for grangerenchanted.com bad HTML summary causing crash.

Browse source
This commit is contained in:
Jim Miller 2015-05-05 13:38:57 -05:00
parent 4a2df36443
commit 2bc30444c8
1 changed files with 5 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
fanficfare/adapters/adapter_grangerenchantedcom.py
View file

@ -176,7 +176,7 @@ class GrangerEnchantedCom(BaseSiteAdapter):
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)
soup = self.make_soup(data)
# print data
# Now go hunting for all the meta data and the chapter list.
@ -217,11 +217,10 @@ class GrangerEnchantedCom(BaseSiteAdapter):
if 'Summary' in label:
## Everything until the next span class='label'
svalue = ""
while not defaultGetattr(value,'class') == 'label':
svalue += str(value)
while value and not defaultGetattr(value,'class') == 'label' and '<span class="label">' not in unicode(value):
svalue += unicode(value)
value = value.nextSibling
self.setDescription(url,svalue)
#self.story.setMetadata('description',stripHTML(svalue))
if 'Rated' in label:
self.story.setMetadata('rating', value)
@ -271,7 +270,7 @@ class GrangerEnchantedCom(BaseSiteAdapter):
series_url = 'http://'+self.host+'/'+self.section+'/'+a['href']
# use BeautifulSoup HTML parser to make everything easier to find.
seriessoup = bs.BeautifulSoup(self._fetchUrl(series_url))
seriessoup = self.make_soup(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
@ -300,8 +299,7 @@ class GrangerEnchantedCom(BaseSiteAdapter):
logger.debug('Getting chapter text from: %s' % url)
soup = bs.BeautifulSoup(self._fetchUrl(url),
selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
soup = self.make_soup(self._fetchUrl(url))
div = soup.find('div', {'id' : 'story1'})