Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix #7120 (GoComics.com)

Browse Source
This commit is contained in:
Kovid Goyal 2010-10-09 20:24:23 -06:00
parent 65a61bb0a8
commit 541a62398c
1 changed files with 11 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
resources/recipes/go_comics.recipe
View File

@ -11,8 +11,8 @@ import mechanize
class GoComics(BasicNewsRecipe):
title = 'GoComics'
__author__ = 'Starson17'
__version__ = '1.02'
__date__ = '14 August 2010'
__version__ = '1.03'
__date__ = '09 October 2010'
description = u'200+ Comics - Customize for more days/comics: Defaults to 7 days, 25 comics - 20 general, 5 editorial.'
category = 'news, comics'
language = 'en'
@ -273,6 +273,7 @@ class GoComics(BasicNewsRecipe):
# ("Wit of the World","http://www.gocomics.com/witoftheworld"),
# ("Don Wright","http://www.gocomics.com/donwright"),
]:
print 'Working on: ', title
articles = self.make_links(url)
if articles:
feeds.append((title, articles))
@ -286,28 +287,30 @@ class GoComics(BasicNewsRecipe):
page_soup = self.index_to_soup(url)
if page_soup:
try:
strip_title = page_soup.h1.a.string
strip_title = page_soup.find(name='div', attrs={'class':'top'}).h1.a.string
except:
strip_title = 'Error - no page_soup.h1.a.string'
strip_title = 'Error - no Title found'
try:
date_title = page_soup.find('ul', attrs={'class': 'feature-nav'}).li.string
if not date_title:
date_title = page_soup.find('ul', attrs={'class': 'feature-nav'}).li.string
except:
date_title = 'Error - no page_soup.h1.li.string'
date_title = 'Error - no Date found'
title = strip_title + ' - ' + date_title
for i in range(2):
try:
strip_url_date = page_soup.h1.a['href']
strip_url_date = page_soup.find(name='div', attrs={'class':'top'}).h1.a['href']
break #success - this is normal exit
except:
strip_url_date = None
continue #try to get strip_url_date again
continue # give up on this strip date
for i in range(2):
try:
prev_strip_url_date = page_soup.find('a', attrs={'class': 'prev'})['href']
break #success - this is normal exit
except:
prev_strip_url_date = None
continue #try to get prev_strip_url_date again
continue # give up on this prev strip date
if strip_url_date:
page_url = 'http://www.gocomics.com' + strip_url_date
else: