Backup_Repos/FanFicFare
1
0
Fork 0
mirror of https://github.com/JimmXinu/FanFicFare.git synced 2026-01-15 20:55:33 +01:00
Code Issues Projects Releases Wiki Activity

Allow forums URLs to point to non-first posts for index.

Browse source
This commit is contained in:
Jim Miller 2015-06-10 23:44:36 -05:00
parent 92a60b5583
commit c3c4fb8344
1 changed files with 19 additions and 13 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

32
fanficfare/adapters/adapter_forumsspacebattlescom.py
View file

@ -51,9 +51,9 @@ class ForumsSpacebattlesComAdapter(BaseSiteAdapter):
m = re.match(self.getSiteURLPattern(),url)
if m:
self.story.setMetadata('storyId',m.group('id'))
# normalized story URL.
self._setURL(self.getURLPrefix() + '/threads/'+self.story.getMetadata('storyId')+'/')
self._setURL(self.getURLPrefix() + '/'+m.group('tp')+'/'+self.story.getMetadata('storyId')+'/')
else:
raise exceptions.InvalidStoryURL(url,
self.getSiteDomain(),
@ -81,7 +81,7 @@ class ForumsSpacebattlesComAdapter(BaseSiteAdapter):
return cls.getURLPrefix()+"/threads/some-story-name.123456/"
def getSiteURLPattern(self):
return r"https?://"+re.escape(self.getSiteDomain())+r"/threads/(.+\.)?(?P<id>\d+)/"
return r"https?://"+re.escape(self.getSiteDomain())+r"/(?P<tp>threads|posts)/(.+\.)?(?P<id>\d+)/"
def use_pagecache(self):
'''
@ -97,7 +97,9 @@ class ForumsSpacebattlesComAdapter(BaseSiteAdapter):
logger.info("url: "+url)
try:
data = self._fetchUrl(url)
(data,opened) = self._fetchUrlOpened(url)
url = opened.geturl()
logger.info("use url: "+url)
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(self.url)
@ -117,18 +119,22 @@ class ForumsSpacebattlesComAdapter(BaseSiteAdapter):
h1 = soup.find('div',{'class':'titleBar'}).h1
self.story.setMetadata('title',stripHTML(h1))
if '#' in url:
anchorid = url.split('#')[1]
soup = soup.find('li',id=anchorid)
else:
# try threadmarks if no '#' in , require at least 2.
threadmarksa = soup.find('a',{'class':'threadmarksTrigger'})
if threadmarksa:
soupmarks = self.make_soup(self._fetchUrl(self.getURLPrefix()+'/'+threadmarksa['href']))
markas = soupmarks.find('ol',{'class':'overlayScroll'}).find_all('a')
if len(markas) > 1:
for (url,name) in [ (x['href'],stripHTML(x)) for x in markas ]:
self.chapterUrls.append((name,self.getURLPrefix()+'/'+url))
# Now go hunting for the 'chapter list'.
firstpost = soup.find('blockquote') # assume first posting contains TOC urls.
# try threadmarks first, require at least 2.
threadmarksa = soup.find('a',{'class':'threadmarksTrigger'})
if threadmarksa:
soupmarks = self.make_soup(self._fetchUrl(self.getURLPrefix()+'/'+threadmarksa['href']))
markas = soupmarks.find('ol',{'class':'overlayScroll'}).find_all('a')
if len(markas) > 1:
for (url,name) in [ (x['href'],stripHTML(x)) for x in markas ]:
self.chapterUrls.append((name,self.getURLPrefix()+'/'+url))
# otherwise, use first post links--include first post since that's
if not self.chapterUrls:
#logger.debug("len(firstpost):%s"%len(unicode(firstpost)))