Backup_Repos/FanFicFare
1
0
Fork 0
mirror of https://github.com/JimmXinu/FanFicFare.git synced 2026-05-09 05:21:13 +02:00
Code Issues Projects Releases Wiki Activity

Fixes for QQ and AH changes.

Browse source
This commit is contained in:
Jim Miller 2017-09-11 12:28:31 -05:00
parent 53b75670b4
commit 6beb0bf2d3
1 changed files with 30 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

36
fanficfare/adapters/adapter_forumquestionablequestingcom.py
View file

@ -15,6 +15,7 @@
# limitations under the License. # limitations under the License.
# #
import re
from ..htmlcleanup import stripHTML from ..htmlcleanup import stripHTML
from base_xenforoforum_adapter import BaseXenForoForumAdapter from base_xenforoforum_adapter import BaseXenForoForumAdapter
@ -39,15 +40,38 @@ class QuestionablequestingComAdapter(BaseXenForoForumAdapter):
## and QQ enough to require some differentiation. ## and QQ enough to require some differentiation.
def extract_threadmarks(self,souptag): def extract_threadmarks(self,souptag):
# try threadmarks if no '#' in url # try threadmarks if no '#' in url
navdiv = souptag.find('div',{'class':'pageNavLinkGroup'}) navdiv = souptag.find('div',{'class':'threadmarkMenus'})
threadmarksa = navdiv.find('a',{'class':'threadmarksTrigger'}) # was class=threadmarksTrigger. thread cats are currently
# only OverlayTrigger <a>s in threadmarkMenus, but I wouldn't
# be surprised if that changed. Don't want to do use just
# href=re because there's more than one copy on the page; plus
# could be included in a post. Would be easier if <noscript>s
# weren't being stripped, but that's a different issue.
threadmarksas = navdiv.find_all('a',{'class':'OverlayTrigger','href':re.compile('threadmarks.*category_id=')})
## Loop on threadmark categories. ## Loop on threadmark categories.
threadmarks=[] threadmarks=[]
if threadmarksa: tmcat_num=None
for threadmarksa in threadmarksas:
tmcat_num = threadmarksa['href'].split('category_id=')[1]
# get from earlier <a> now.
tmcat_name = stripHTML(threadmarksa.find_previous('a',{'class':'threadmarksTrigger'}))
prepend = ""
if tmcat_name in self.getConfigList('skip_threadmarks_categories'):
continue
if tmcat_name == 'Apocrypha' and self.getConfig('apocrypha_to_omake'):
tmcat_name = 'Omake'
if tmcat_name != "Threadmarks":
prepend = tmcat_name+" - "
soupmarks = self.make_soup(self._fetchUrl(self.getURLPrefix()+'/'+threadmarksa['href'])) soupmarks = self.make_soup(self._fetchUrl(self.getURLPrefix()+'/'+threadmarksa['href']))
markas = [] markas = []
markas = soupmarks.find('div',{'class':'threadmarks'}).find_all('a',{'class':'PreviewTooltip'}) markas = soupmarks.find('div',{'class':'threadmarkList'}).find_all('a',{'class':'PreviewTooltip'})
for (atag,url,name) in [ (x,x['href'],stripHTML(x)) for x in markas ]: for tmcat_index, atag in enumerate(markas):
url,name = atag['href'],stripHTML(atag)
date = self.make_date(atag.find_next_sibling('div',{'class':'extra'})) date = self.make_date(atag.find_next_sibling('div',{'class':'extra'}))
threadmarks.append({'title':name,'url':self.getURLPrefix()+'/'+url,'date':date}) threadmarks.append({"tmcat_name":tmcat_name,"tmcat_num":tmcat_num,"tmcat_index":tmcat_index,'title':name,'url':self.getURLPrefix()+'/'+url,'date':date})
return threadmarks return threadmarks