Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 02:34:06 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Hindustan Times

Browse Source
This commit is contained in:
Kovid Goyal 2014-04-20 09:13:53 +05:30
parent 6a5833ddc7
commit 1ac8f8147f
1 changed files with 30 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

59
recipes/hindustan_times.recipe
View File

@ -1,11 +1,10 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
import urllib, re
class HindustanTimes(BasicNewsRecipe): class HindustanTimes(BasicNewsRecipe):
title = u'Hindustan Times' title = u'Hindustan Times'
language = 'en_IN' language = 'en_IN'
__author__ = 'Krittika Goyal' __author__ = 'Krittika Goyal'
oldest_article = 1 #days oldest_article = 1 # days
max_articles_per_feed = 25 max_articles_per_feed = 25
use_embedded_content = False use_embedded_content = False
@ -13,38 +12,40 @@ class HindustanTimes(BasicNewsRecipe):
auto_cleanup = True auto_cleanup = True
feeds = [ feeds = [
('News', ('News',
'http://feeds.hindustantimes.com/HT-NewsSectionPage-Topstories'), 'http://feeds.hindustantimes.com/HT-HomePage-TopStories'),
('Views', ('India',
'http://feeds.hindustantimes.com/HT-ViewsSectionpage-Topstories'), 'http://feeds.hindustantimes.com/HT-India'),
('Cricket', ('World',
'http://feeds.hindustantimes.com/HT-Cricket-TopStories'), 'http://feeds.hindustantimes.com/HT-World'),
('Business', ('Business',
'http://feeds.hindustantimes.com/HT-BusinessSectionpage-TopStories'), 'http://feeds.hindustantimes.com/HT-Business'),
('Entertainment', ('Fashion',
'http://feeds.hindustantimes.com/HT-HomePage-Entertainment'), 'http://feeds.hindustantimes.com/HT-Fashion'),
('Lifestyle', ('Sex & Relationships',
'http://feeds.hindustantimes.com/HT-Homepage-LifestyleNews'), 'http://feeds.hindustantimes.com/HT-Sexandrelationships'),
('Travel',
'http://feeds.hindustantimes.com/HT-Travel'),
('Books',
'http://feeds.hindustantimes.com/HT-Books'),
] ]
def get_article_url(self, article): def get_article_url(self, article):
''' '''
HT uses a variant of the feedportal RSS ad display mechanism HT uses a variant of the feedportal RSS ad display mechanism
''' '''
try: url = article.get('feedburner_origlink', None)
s = article.summary if url is not None:
return urllib.unquote( idx = url.find('0L0S')
re.search(r'href=".+?bookmark.cfm.+?link=(.+?)"', s).group(1)) url = url[idx:]
except: encoding = {'0B': '.', '0C': '/', '0A': '0', '0F': '=', '0G': '&',
pass '0D': '?', '0E': '-', '0N': '.com', '0L': 'http://', '0S':
url = BasicNewsRecipe.get_article_url(self, article) 'www.'}
res = self.browser.open_novisit(url) for k, v in encoding.iteritems():
url = res.geturl().split('/')[-2] url = url.replace(k, v)
encoding = {'0B': '.', '0C': '/', '0A': '0', '0F': '=', '0G': '&', if url.endswith('/story01.htm'):
'0D': '?', '0E': '-', '0N': '.com', '0L': 'http://', '0S': url = url.rpartition('/')[0]
'www.'} return url
for k, v in encoding.iteritems(): return article.get('link', None)
url = url.replace(k, v)
return url