Fix #830060 (Houston Chronicle news fetch fails)

This commit is contained in:
Kovid Goyal 2011-08-20 21:12:50 -06:00
parent 2337570c9f
commit 2a80b4ac99

View File

@ -1,8 +1,6 @@
#!/usr/bin/env python
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
import string, pprint
from calibre.web.feeds.news import BasicNewsRecipe
class HoustonChronicle(BasicNewsRecipe):
@ -13,53 +11,28 @@ class HoustonChronicle(BasicNewsRecipe):
language = 'en'
timefmt = ' [%a, %d %b, %Y]'
no_stylesheets = True
use_embedded_content = False
remove_attributes = ['style']
keep_only_tags = [
dict(id=['story-head', 'story'])
]
remove_tags = [
dict(id=['share-module', 'resource-box',
'resource-box-header'])
]
extra_css = '''
h1{font-family :Arial,Helvetica,sans-serif; font-size:large;}
h2{font-family :Arial,Helvetica,sans-serif; font-size:medium; color:#666666;}
h3{font-family :Arial,Helvetica,sans-serif; font-size:medium; color:#000000;}
h4{font-family :Arial,Helvetica,sans-serif; font-size: x-small;}
p{font-family :Arial,Helvetica,sans-serif; font-size:x-small;}
#story-head h1{font-family :Arial,Helvetica,sans-serif; font-size: xx-large;}
#story-head h2{font-family :Arial,Helvetica,sans-serif; font-size: small; color:#000000;}
#story-head h3{font-family :Arial,Helvetica,sans-serif; font-size: xx-small;}
#story-head h4{font-family :Arial,Helvetica,sans-serif; font-size: xx-small;}
#story{font-family :Arial,Helvetica,sans-serif; font-size:xx-small;}
#Text-TextSubhed BoldCond PoynterAgateZero h3{color:#444444;font-family :Arial,Helvetica,sans-serif; font-size:small;}
.p260x p{font-family :Arial,Helvetica,serif; font-size:x-small;font-style:italic;}
.p260x h6{color:#777777;font-family :Arial,Helvetica,sans-serif; font-size:xx-small;}
'''
def parse_index(self):
categories = ['news', 'sports', 'business', 'entertainment', 'life',
'travel']
feeds = []
for cat in categories:
articles = []
soup = self.index_to_soup('http://www.chron.com/%s/'%cat)
for elem in soup.findAll(comptype='story', storyid=True):
a = elem.find('a', href=True)
if a is None: continue
url = a['href']
if not url.startswith('http://'):
url = 'http://www.chron.com'+url
articles.append({'title':self.tag_to_string(a), 'url':url,
'description':'', 'date':''})
pprint.pprint(articles[-1])
if articles:
feeds.append((string.capwords(cat), articles))
return feeds
oldest_article = 2.0
keep_only_tags = {'class':lambda x: x and ('hst-articletitle' in x or
'hst-articletext' in x or 'hst-galleryitem' in x)}
feeds = [
('News', "http://www.chron.com/rss/feed/News-270.php"),
('Sports',
'http://www.chron.com/sports/headlines/collectionRss/Sports-Headlines-Staff-Stories-10767.php'),
('Neighborhood',
'http://www.chron.com/rss/feed/Neighborhood-305.php'),
('Business', 'http://www.chron.com/rss/feed/Business-287.php'),
('Entertainment',
'http://www.chron.com/rss/feed/Entertainment-293.php'),
('Editorials',
'http://www.chron.com/opinion/editorials/collectionRss/Opinion-Editorials-Headline-List-10567.php'),
('Life', 'http://www.chron.com/rss/feed/Life-297.php'),
('Science & Tech',
'http://www.chron.com/rss/feed/AP-Technology-and-Science-266.php'),
]