Update Chicago Tribune

This commit is contained in:
Kovid Goyal 2014-01-02 11:06:30 +05:30
parent bea02304ee
commit db07598b69

View File

@ -3,13 +3,12 @@ __license__ = 'GPL 3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
import urllib, re
from calibre.web.feeds.news import BasicNewsRecipe
class ChicagoTribune(BasicNewsRecipe):
title = 'Chicago Tribune'
__author__ = 'Kovid Goyal and Sujata Raman, a.peter'
__author__ = 'Kovid Goyal, Sujata Raman and a.peter'
description = 'Politics, local and business news from Chicago'
language = 'en'
version = 2
@ -23,11 +22,16 @@ class ChicagoTribune(BasicNewsRecipe):
dict(name='div', attrs={'id':["pagebody","story","maincontentcontainer"]}),
]
remove_tags_after = [{'class':['photo_article',]}]
remove_empty_feeds = True
match_regexps = [r'page=[0-9]+']
remove_tags = [{'id':["moduleArticleTools","content-bottom","rail","articleRelates module","toolSet","relatedrailcontent","div-wrapper","beta","atp-comments","footer",'gallery-subcontent','subFooter']},
{'class':["clearfix","relatedTitle","articleRelates module","asset-footer","tools","comments","featurePromo","featurePromo fp-topjobs brownBackground","clearfix fullSpan brownBackground","curvedContent",'nextgen-share-tools','outbrainTools', 'google-ad-story-bottom']},
remove_tags = [
{'id':["moduleArticleTools","content-bottom","rail","articleRelates module","toolSet",
"relatedrailcontent","div-wrapper","beta","atp-comments","footer",'gallery-subcontent','subFooter']},
{'class':["clearfix","relatedTitle","articleRelates module",
"asset-footer","tools","comments","featurePromo","featurePromo fp-topjobs brownBackground", 'ndn_embed',
"clearfix fullSpan brownBackground","curvedContent",'nextgen-share-tools','outbrainTools', 'google-ad-story-bottom']},
dict(name='font',attrs={'id':["cr-other-headlines"]})]
extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
@ -51,7 +55,7 @@ class ChicagoTribune(BasicNewsRecipe):
('Most E-mailed stories', 'http://feeds.chicagotribune.com/chicagotribune/email/'),
('Opinion', 'http://feeds.chicagotribune.com/chicagotribune/opinion/'),
('Off Topic', 'http://feeds.chicagotribune.com/chicagotribune/offtopic/'),
#('Politics', 'http://feeds.chicagotribune.com/chicagotribune/politics/'),
('Politics', 'http://feeds.feedburner.com/chicagotribune/cloutstreet/'),
#('Special Reports', 'http://feeds.chicagotribune.com/chicagotribune/special/'),
#('Religion News', 'http://feeds.chicagotribune.com/chicagotribune/religion/'),
('Business news', 'http://feeds.chicagotribune.com/chicagotribune/business/'),
@ -76,19 +80,15 @@ class ChicagoTribune(BasicNewsRecipe):
('Julie\'s Health Club', 'http://feeds.chicagotribune.com/chicagotribune_julieshealthclub/'),
]
def get_article_url(self, article):
ans = None
try:
s = article.summary
ans = urllib.unquote(
re.search(r'href=".+?bookmark.cfm.+?link=(.+?)"', s).group(1))
except:
pass
if ans is None:
ans = article.get('feedburner_origlink', article.get('guid', article.get('link')))
if ans is not None:
return ans.replace('?track=rss', '')
url = BasicNewsRecipe.get_article_url(self, article)
url = url.split('/')[-2]
encoding = {'0B': '.', '0C': '/', '0A': '0', '0F': '=', '0G': '&',
'0D': '?', '0E': '-', '0N': '.com', '0L': 'http://', '0S':
'www.', '0I': '_', '0H': ','}
for k, v in encoding.iteritems():
url = url.replace(k, v)
return url.partition('?')[0]
def skip_ad_pages(self, soup):
text = soup.find(text='click here to continue to article')