Backup_Repos/FanFicFare
1
0
Fork 0
mirror of https://github.com/JimmXinu/FanFicFare.git synced 2026-05-08 12:36:11 +02:00
Code Issues Projects Releases Wiki Activity

Add xenforoforum Categorized threadmarks after regular threadmarks.

Browse source
This commit is contained in:
Jim Miller 2017-05-24 20:24:11 -05:00
parent 622f4d7dd1
commit 6f149521c3
1 changed files with 16 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

19
fanficfare/adapters/base_xenforoforum_adapter.py
View file

@ -233,9 +233,17 @@ class BaseXenForoForumAdapter(BaseSiteAdapter):
souptag = souptag.find('li',id=anchorid)
else:
# try threadmarks if no '#' in , require at least 2.
threadmarksa = souptag.find('a',{'class':'threadmarksTrigger'})
if threadmarksa:
navdiv = souptag.find('div',{'class':'pageNavLinkGroup'}) # first navdiv only.
threadmarksas = navdiv.find_all('a',{'class':'threadmarksTrigger'})
## Loop on threadmark categories.
for threadmarksa in threadmarksas:
soupmarks = self.make_soup(self._fetchUrl(self.getURLPrefix()+'/'+threadmarksa['href']))
## prepend threadmark category name if not 'Threadmarks'
prepend = ""
tmcat_name = stripHTML(threadmarksa)
if tmcat_name != "Threadmarks":
prepend = tmcat_name+" - "
markas = []
ol = soupmarks.find('ol',{'class':'overlayScroll'})
if ol:
@ -259,7 +267,7 @@ class BaseXenForoForumAdapter(BaseSiteAdapter):
if not self.story.getMetadataRaw('dateUpdated') or date > self.story.getMetadataRaw('dateUpdated'):
self.story.setMetadata('dateUpdated', date)
self.chapterUrls.append((name,self.getURLPrefix()+'/'+url))
self.chapterUrls.append((prepend+name,self.getURLPrefix()+'/'+url))
souptag = souptag.find('li',{'class':'message'}) # limit first post for date stuff below. ('#' posts above)
@ -397,6 +405,11 @@ class BaseXenForoForumAdapter(BaseSiteAdapter):
data = self._fetchUrl(reader_url)
topsoup = self.make_soup(data)
# if no posts at all, break out of loop, we're off the end.
# don't need to remember this, the page is cached.
if not topsoup.find_all('li',id=re.compile(r'post-[0-9]+')):
break
# assumed normalized to /posts/1234/
anchorid = "post-"+url.split('/')[-2]
logger.debug("anchorid: %s"%anchorid)