wassname/FanFicFare
1
0
Fork 0
mirror of https://github.com/wassname/FanFicFare.git synced 2026-09-10 11:40:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

twiwrite adult stories broke Soup in Plugin only. Suspect different SGMLParsers.

Browse Source 
Removing all the headers first works around it.
This commit is contained in:
Jim Miller
2012-01-08 10:59:29 -06:00
parent fbcc582541
commit f7c321a36e
1 changed files with 7 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fanficdownloader/adapters/adapter_twiwritenet.py
+7 -2
View File
@@ -84,7 +84,7 @@ class TwiwriteNetSiteAdapter(BaseSiteAdapter):
params['submit'] = 'Submit'
loginUrl = 'http://' + self.getSiteDomain() + '/user.php?action=login'
logging.debug("Will now login to URL (%s) as (%s)" % (loginUrl,
logging.info("Will now login to URL (%s) as (%s)" % (loginUrl,
params['penname']))
d = self._fetchUrl(loginUrl, params)
@@ -119,6 +119,8 @@ class TwiwriteNetSiteAdapter(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.
data = data[data.index("<body"):] # desperate--strip before <body
# in calibre plugin only, soup wasn't parsing the html properly.
soup = bs.BeautifulSoup(data)
## Title
@@ -211,7 +213,10 @@ class TwiwriteNetSiteAdapter(BaseSiteAdapter):
logging.debug('Getting chapter text from: %s' % url)
soup = bs.BeautifulStoneSoup(self._fetchUrl(url),
data = self._fetchUrl(url)
data = data[data.index("<body"):] # desperate--strip before <body
# in calibre plugin only, soup wasn't parsing the html properly.
soup = bs.BeautifulStoneSoup(data,
selfClosingTags=('br','hr')) # otherwise soup eats the br/hr tags.
span = soup.find('div', {'id' : 'story'})