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

New recipe for The Times of India by Krittika Goyal

Browse Source
This commit is contained in:
Kovid Goyal 2009-12-30 20:34:16 -07:00
parent 81c5bc7d79
commit 7333cc7319
1 changed files with 54 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

54
resources/recipes/toi.recipe Normal file
View File

@ -0,0 +1,54 @@
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'
oldest_article = 1 #days
max_articles_per_feed = 25
remove_stylesheets = True
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=':'),
]
feeds = [
('Top Stories',
'http://timesofindia.indiatimes.com/rssfeedstopstories.cms'),
('India',
'http://timesofindia.indiatimes.com/rssfeeds/-2128936835.cms'),
('World',
'http://timesofindia.indiatimes.com/rssfeeds/296589292.cms'),
('Mumbai',
'http://timesofindia.indiatimes.com/rssfeeds/-2128838597.cms'),
('Entertainment',
'http://timesofindia.indiatimes.com/rssfeeds/1081479906.cms'),
('Cricket',
'http://timesofindia.indiatimes.com/rssfeeds/4719161.cms'),
('Sunday TOI',
'http://timesofindia.indiatimes.com/rssfeeds/1945062111.cms'),
('Life and Style',
'http://timesofindia.indiatimes.com/rssfeeds/2886704.cms'),
('Business',
'http://timesofindia.indiatimes.com/rssfeeds/1898055.cms'),
('Mad Mad World',
'http://timesofindia.indiatimes.com/rssfeeds/2178430.cms'),
('Most Read',
'http://timesofindia.indiatimes.com/rssfeedmostread.cms')
]
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