Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 10:44:09 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix #7958 (Business World - Lead article missing)

Browse Source
This commit is contained in:
Kovid Goyal 2010-12-31 15:21:11 -07:00
parent 565085dc95
commit ee97d92f30
1 changed files with 28 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
resources/recipes/businessworldin.recipe
View File

@ -1,7 +1,5 @@
#!/usr/bin/env python
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
''' '''
www.businessworld.in www.businessworld.in
''' '''
@ -22,7 +20,11 @@ class BusinessWorldMagazine(BasicNewsRecipe):
use_embedded_content = False use_embedded_content = False
encoding = 'utf-8' encoding = 'utf-8'
language = 'en_IN' language = 'en_IN'
extra_css = """
img{display: block; margin-bottom: 0.5em}
body{font-family: Arial,Helvetica,sans-serif}
h2{color: gray; display: block}
"""
conversion_options = { conversion_options = {
'comment' : description 'comment' : description
@ -42,7 +44,26 @@ class BusinessWorldMagazine(BasicNewsRecipe):
articles = [] articles = []
linklist = [] linklist = []
soup = self.index_to_soup(self.INDEX) soup = self.index_to_soup(self.INDEX)
tough = soup.find('div', attrs={'id':'tough'})
if tough:
for item in tough.findAll('h1'):
description = ''
title_prefix = ''
feed_link = item.find('a')
if feed_link and feed_link.has_key('href'):
url = self.ROOT + feed_link['href']
if not self.is_in_list(linklist,url):
title = title_prefix + self.tag_to_string(feed_link)
date = strftime(self.timefmt)
articles.append({
'title' :title
,'date' :date
,'url' :url
,'description':description
})
linklist.append(url)
for item in soup.findAll('div', attrs={'class':'nametitle'}): for item in soup.findAll('div', attrs={'class':'nametitle'}):
description = '' description = ''
title_prefix = '' title_prefix = ''
@ -62,8 +83,8 @@ class BusinessWorldMagazine(BasicNewsRecipe):
return [(soup.head.title.string, articles)] return [(soup.head.title.string, articles)]
keep_only_tags = [dict(name='div', attrs={'id':['register-panel','printwrapper']})] keep_only_tags = [dict(name='div', attrs={'id':'printwrapper'})]
remove_tags = [dict(name=['object','link'])] remove_tags = [dict(name=['object','link','meta','base','iframe','link','table'])]
def print_version(self, url): def print_version(self, url):
return url.replace('/bw/','/bw/storyContent/') return url.replace('/bw/','/bw/storyContent/')