Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-06-23 15:30:45 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update The Times of India

Browse Source
This commit is contained in:
Kovid Goyal 2016-05-01 07:37:26 +05:30
parent 78ddc2799d
commit 1f09ee2e97
1 changed files with 11 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
recipes/toi.recipe
View File

@ -9,7 +9,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class TheEconomicTimes(BasicNewsRecipe):
title = 'The Times of India'
__author__ = 'Karthik K'
__author__ = 'Karthik'
description = 'News from the Indian daily Times of India'
publisher = 'timesofindia.indiatimes.com'
category = 'news, finances, politics, sports, business, entertainment, India'
@ -38,7 +38,9 @@ class TheEconomicTimes(BasicNewsRecipe):
}
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'class':'storycontent'})
remove_attributes = ['xmlns']
remove_attributes = ['xmlns', 'style']
remove_tags = [dict(name='div', attrs={'class':'readalso'})]
feeds = [('Recent Stories', 'http://timesofindia.indiatimes.com/rssfeeds/1221656.cms'),
('India', 'http://timesofindia.indiatimes.com/rssfeeds/-2128936835.cms'),
('World', 'http://timesofindia.indiatimes.com/rssfeeds/296589292.cms'),
@ -51,22 +53,15 @@ class TheEconomicTimes(BasicNewsRecipe):
('Opinion', 'http://timesofindia.indiatimes.com/rssfeeds/784865811.cms'),
('Entertainment', 'http://timesofindia.indiatimes.com/rssfeeds/1081479906.cms')]
#Uses the mobile print version. For web print version use 'http://timesofindia.indiatimes.com/articleshow/<article_id>?prtpage=1'
def print_version(self, url):
rest, sep, article_id = url.rpartition('/articleshow/')
return 'http://m.timesofindia.com/PDAET/articleshow/' + article_id
return url.replace('/articleshow/', '/articleshowprint/')
# For mobile version
# return 'http://m.timesofindia.com/PDAET/articleshow/' + article_id
def get_article_url(self, article):
rurl = article.get('guid', None)
if (rurl.find('/quickieslist/') > 0) or (rurl.find('/quickiearticleshow/') > 0):
return None
if '/articleshow/' in rurl:
return rurl
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup
def postprocess_html(self, soup, first_fetch):
return self.adeify_images(soup)