Backup_Repos/FanFicFare
1
0
Fork 0
mirror of https://github.com/JimmXinu/FanFicFare.git synced 2025-12-29 20:24:55 +01:00
Code Issues Projects Releases Wiki Activity

Add author to chapter TOC for multi-author stories on TtH and WraithBait.

Browse source 
AO3 doesn't reliably report chapter author.
This commit is contained in:
Jim Miller 2013-03-28 12:19:32 -05:00
parent 73815bda43
commit 64866f7da6
2 changed files with 37 additions and 20 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

50
fanficdownloader/adapters/adapter_tthfanficorg.py
View file

@ -163,17 +163,44 @@ class TwistingTheHellmouthSiteAdapter(BaseSiteAdapter):
infodata = self._fetchUrl(infourl)
infosoup = bs.BeautifulSoup(infodata)
for a in infosoup.findAll('a',href=re.compile(r"^/Author-\d+")):
self.story.addToList('authorId',a['href'].split('/')[1].split('-')[1])
self.story.addToList('authorUrl','http://'+self.host+a['href'].replace("/Author-","/AuthorStories-"))
self.story.addToList('author',stripHTML(a))
# for a in infosoup.findAll('a',href=re.compile(r"^/Author-\d+")):
# self.story.addToList('authorId',a['href'].split('/')[1].split('-')[1])
# self.story.addToList('authorUrl','http://'+self.host+a['href'].replace("/Author-","/AuthorStories-"))
# self.story.addToList('author',stripHTML(a))
# second verticaltable is the chapter list.
table = infosoup.findAll('table',{'class':'verticaltable'})[1]
for a in table.findAll('a',href=re.compile(r"^/Story-"+self.story.getMetadata('storyId'))):
autha = a.findNext('a',href=re.compile(r"^/Author-\d+"))
self.story.addToList('authorId',autha['href'].split('/')[1].split('-')[1])
self.story.addToList('authorUrl','http://'+self.host+autha['href'].replace("/Author-","/AuthorStories-"))
self.story.addToList('author',stripHTML(autha))
# include leading number to match 1. ... 2. ...
self.chapterUrls.append(("%d. %s by %s"%(len(self.chapterUrls)+1,
stripHTML(a),
stripHTML(autha)),'http://'+self.host+a['href']))
except urllib2.HTTPError, e:
if e.code == 404:
raise exceptions.StoryDoesNotExist(url)
else:
raise e
else: # single author:
# Find the chapter selector
select = soup.find('select', { 'name' : 'chapnav' } )
if select is None:
# no selector found, so it's a one-chapter story.
self.chapterUrls.append((self.story.getMetadata('title'),url))
else:
allOptions = select.findAll('option')
for o in allOptions:
url = "http://"+self.host+o['value']
# just in case there's tags, like <i> in chapter titles.
self.chapterUrls.append((stripHTML(o),url))
self.story.setMetadata('numChapters',len(self.chapterUrls))
try:
# going to pull part of the meta data from *primary* author list page.
logger.debug("**AUTHOR** URL: "+authorurl)
@ -235,21 +262,6 @@ class TwistingTheHellmouthSiteAdapter(BaseSiteAdapter):
if BtVS:
self.story.addToList('category','Buffy: The Vampire Slayer')
# Find the chapter selector
select = soup.find('select', { 'name' : 'chapnav' } )
if select is None:
# no selector found, so it's a one-chapter story.
self.chapterUrls.append((self.story.getMetadata('title'),url))
else:
allOptions = select.findAll('option')
for o in allOptions:
url = "http://"+self.host+o['value']
# just in case there's tags, like <i> in chapter titles.
self.chapterUrls.append((stripHTML(o),url))
self.story.setMetadata('numChapters',len(self.chapterUrls))
pseries = soup.find('p', {'style':'margin-top:0px'})
m = re.match('This story is No\. (?P<num>\d+) in the series &quot;(?P<series>.+)&quot;\.',
pseries.text)

7
fanficdownloader/adapters/adapter_wraithbaitcom.py
View file

@ -126,8 +126,13 @@ class WraithBaitComAdapter(BaseSiteAdapter):
# Find the chapters:
for chapter in soup.findAll('a', href=re.compile(r'viewstory.php\?sid='+self.story.getMetadata('storyId')+"&chapter=\d+$")):
# include author on chapters if multiple authors.
if len(alist) > 1:
add = " by %s"%stripHTML(chapter.findNext('a', href=re.compile(r"viewuser.php\?uid=\d+")))
else:
add = ""
# just in case there's tags, like <i> in chapter titles.
self.chapterUrls.append((stripHTML(chapter),'http://'+self.host+'/'+chapter['href']+addurl))
self.chapterUrls.append((stripHTML(chapter)+add,'http://'+self.host+'/'+chapter['href']+addurl))
self.story.setMetadata('numChapters',len(self.chapterUrls))