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 TOI

Browse Source
This commit is contained in:
Kovid Goyal 2010-06-27 11:59:23 -06:00
parent 1c278e59c0
commit e52d734038
1 changed files with 6 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
resources/recipes/toi.recipe
View File

@ -1,21 +1,16 @@
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
class TimesOfIndia(BasicNewsRecipe):
title = u'Times of India'
language = 'en_IN'
__author__ = 'Krittika Goyal'
__author__ = 'Kovid Goyal'
oldest_article = 1 #days
max_articles_per_feed = 25
remove_stylesheets = True
no_stylesheets = True
keep_only_tags = [dict(attrs={'class':'prttabl'})]
remove_tags = [
dict(name='iframe'),
dict(name='td', attrs={'class':'newptool1'}),
dict(name='div', attrs={'id':'newptool'}),
dict(name='ul', attrs={'class':'newtabcontent_tabs_new'}),
dict(name='b', text='Topics'),
dict(name='span', text=':'),
dict(style=lambda x: x and 'float' in x)
]
feeds = [
@ -42,13 +37,8 @@ class TimesOfIndia(BasicNewsRecipe):
('Most Read',
'http://timesofindia.indiatimes.com/rssfeedmostread.cms')
]
def print_version(self, url):
return url + '?prtpage=1'
def preprocess_html(self, soup):
heading = soup.find(name='h1', attrs={'class':'heading'})
td = heading.findParent(name='td')
td.extract()
soup = BeautifulSoup('<html><head><title>t</title></head><body></body></html>')
body = soup.find(name='body')
body.insert(0, td)
td.name = 'div'
return soup