Backup_Repos/FanFicFare
1
0
Fork 0
mirror of https://github.com/JimmXinu/FanFicFare.git synced 2025-12-31 05:03:34 +01:00
Code Issues Projects Releases Wiki Activity

adapter_literotica: Allow for empty div.aa_ht tags, remove extra None

Browse source 
from text
This commit is contained in:
Jim Miller 2024-02-05 10:36:41 -06:00
parent e03f65332a
commit 581d6f6657
1 changed files with 7 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
fanficfare/adapters/adapter_literotica.py
View file

@ -341,13 +341,13 @@ class LiteroticaSiteAdapter(BaseSiteAdapter):
[comment.extract() for comment in page_soup.findAll(string=lambda text:isinstance(text, Comment))]
fullhtml = ""
for aa_ht_div in page_soup.find_all('div', 'aa_ht'):
html = unicode(aa_ht_div.div)
# logger.debug(html)
# Strip some starting and ending tags,
html = re.sub(r'^<div.*?>', r'', html)
html = re.sub(r'</div>$', r'', html)
html = re.sub(r'<p></p>$', r'', html)
fullhtml = fullhtml + html
if aa_ht_div.div:
html = unicode(aa_ht_div.div)
# Strip some starting and ending tags,
html = re.sub(r'^<div.*?>', r'', html)
html = re.sub(r'</div>$', r'', html)
html = re.sub(r'<p></p>$', r'', html)
fullhtml = fullhtml + html
# logger.debug('getPageText - fullhtml: %s' % fullhtml)
return fullhtml