Backup_Repos/FanFicFare
1
0
Fork 0
mirror of https://github.com/JimmXinu/FanFicFare.git synced 2025-12-25 10:14:56 +01:00
Code Issues Projects Releases Wiki Activity

adapter_adultfanfictionorg: Fixes for site changes.

Browse source
This commit is contained in:
Jim Miller 2022-09-27 09:58:44 -05:00
parent c78ff37f56
commit a7ced3d78a
1 changed files with 15 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

24
fanficfare/adapters/adapter_adultfanfictionorg.py
View file

@ -258,18 +258,23 @@ class AdultFanFictionOrgAdapter(BaseSiteAdapter):
asoup = self.make_soup(adata)
##Getting the number of pages
pages=asoup.find('div',{'class' : 'pagination'}).findAll('li')[-1].find('a')
if not pages == None:
pages = pages['href'].split('=')[-1]
else:
pages = 0
##Getting the number of author pages
pages = 0
pagination=asoup.find('ul',{'class' : 'pagination'})
if pagination:
pages = pagination.findAll('li')[-1].find('a')
if not pages == None:
pages = pages['href'].split('=')[-1]
else:
pages = 0
storya = None
##If there is only 1 page of stories, check it to get the Metadata,
if pages == 0:
a = asoup.findAll('li')
for lc2 in a:
if lc2.find('a', href=re.compile(r'story.php\?no='+self.story.getMetadata('storyId')+"$")):
storya = lc2
break
## otherwise go through the pages
else:
@ -293,6 +298,7 @@ class AdultFanFictionOrgAdapter(BaseSiteAdapter):
for lc2 in a:
if lc2.find('a', href=re.compile(r'story.php\?no='+self.story.getMetadata('storyId')+"$")):
i=1
storya = lc2
break
page = page + 1
if page > int(pages):
@ -305,14 +311,14 @@ class AdultFanFictionOrgAdapter(BaseSiteAdapter):
##There is also a double <br/>, so we have to fix that, then remove the leading and trailing '-:-'.
##They are always in the same order.
## EDIT 09/26/2016: Had some trouble with unicode errors... so I had to put in the decode/encode parts to fix it
liMetadata = unicode(lc2).replace('\n','').replace('\r','').replace('\t',' ').replace(' ',' ').replace(' ',' ').replace(' ',' ')
liMetadata = unicode(storya).replace('\n','').replace('\r','').replace('\t',' ').replace(' ',' ').replace(' ',' ').replace(' ',' ')
liMetadata = stripHTML(liMetadata.replace(r'<br/>','-:-').replace('<!-- <br /-->','-:-'))
liMetadata = liMetadata.strip('-:-').strip('-:-').encode('utf-8')
for i, value in enumerate(liMetadata.decode('utf-8').split('-:-')):
if i == 0:
# The value for the title has been manipulated, so may not be the same as gotten at the start.
# I'm going to use the href from the lc2 retrieved from the author's page to determine if it is correct.
if lc2.find('a', href=re.compile(r'story.php\?no='+self.story.getMetadata('storyId')+"$"))['href'] != url:
# I'm going to use the href from the storya retrieved from the author's page to determine if it is correct.
if storya.find('a', href=re.compile(r'story.php\?no='+self.story.getMetadata('storyId')+"$"))['href'] != url:
raise exceptions.StoryDoesNotExist('Did not find story in author story list: {0}'.format(author_Url))
elif i == 1:
##Get the description