calibre/recipes/toi.recipe

75 lines
2.5 KiB
Plaintext

import re, urllib
from calibre.web.feeds.news import BasicNewsRecipe
class TimesOfIndia(BasicNewsRecipe):
title = u'Times of India'
language = 'en_IN'
__author__ = 'Kovid Goyal'
oldest_article = 1 #days
max_articles_per_feed = 25
no_stylesheets = True
remove_attributes = ['style']
keep_only_tags = [
{'class':re.compile(r'maintable12|prttabl')},
{'id':['mod-article-header',
'mod-a-body-after-first-para', 'mod-a-body-first-para']},
]
remove_tags = [
{'class':re.compile('tabsintbgshow|prvnxtbg')},
{'id':['fbrecommend', 'relmaindiv', 'shretxt', 'fbrecos', 'twtdiv',
'gpls', 'auim']},
{'class':['twitter-share-button', 'cmtmn']},
]
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 get_article_url(self, article):
try:
s = article.summary
return urllib.unquote(
re.search(r'href=".+?bookmark.cfm.+?link=(.+?)"', s).group(1))
except:
pass
link = article.get('link', None)
if link and link.split('/')[-1]=="story01.htm":
link=link.split('/')[-2]
encoding = {'0B': '.', '0C': '/', '0A': '0', '0F': '=', '0G': '&',
'0D': '?', '0E': '-', '0N': '.com', '0L': 'http://'}
for k, v in encoding.iteritems():
link = link.replace(k, v)
return link
def print_version(self, url):
return url + '?prtpage=1'
def preprocess_html(self, soup, *args):
byl = soup.find(attrs={'class':'byline'})
if byl is not None:
for l in byl.findAll('label'):
l.extract()
return soup