Update Washington Post. Fixes #786609 (Updated recipe for The Washington Post)

This commit is contained in:
Kovid Goyal 2011-05-22 10:48:45 -06:00
parent f97bcfb1a8
commit 8336bd6e49
2 changed files with 65 additions and 54 deletions

BIN
recipes/icons/wash_post.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.1 KiB

View File

@ -1,64 +1,75 @@
__license__ = 'GPL v3'
__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>'
'''
www.washingtonpost.com
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class WashingtonPost(BasicNewsRecipe):
title = 'Washington Post'
description = 'US political news'
__author__ = 'Kovid Goyal'
use_embedded_content = False
max_articles_per_feed = 20
language = 'en'
encoding = 'utf-8'
remove_javascript = True
class TheWashingtonPost(BasicNewsRecipe):
title = 'The Washington Post'
__author__ = 'Darko Miletic'
description = 'Leading source for news, video and opinion on politics, business, world and national news, science, travel, entertainment and more. Our local coverage includes reporting on education, crime, weather, traffic, real estate, jobs and cars for DC, Maryland and Virginia. Offering award-winning opinion writing, entertainment information and restaurant reviews.'
publisher = 'The Washington Post Company'
category = 'news, politics, USA'
oldest_article = 2
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'utf8'
delay = 1
use_embedded_content = False
language = 'en'
remove_empty_feeds = True
publication_type = 'newspaper'
masthead_url = 'http://www.washingtonpost.com/rw/sites/twpweb/img/logos/twp_logo_300.gif'
cover_url = strftime('http://www.washingtonpost.com/rw/WashingtonPost/Content/Epaper/%Y-%m-%d/Ax1.pdf')
extra_css = """
body{font-family: Georgia,serif }
"""
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
keep_only_tags = [dict(attrs={'id':['content','entryhead','entrytext']})]
remove_tags = [
dict(name=['meta','link','iframe','base'])
,dict(attrs={'id':'multimedia-leaf-page'})
]
remove_attributes= ['lang','property','epochtime','datetitle','pagetype','contenttype','comparetime']
feeds = [
('Politics', 'http://www.washingtonpost.com/rss/politics'),
('Nation', 'http://www.washingtonpost.com/rss/national'),
('World', 'http://www.washingtonpost.com/rss/world'),
('Business', 'http://www.washingtonpost.com/rss/business'),
('Lifestyle', 'http://www.washingtonpost.com/rss/lifestyle'),
('Sports', 'http://www.washingtonpost.com/rss/sports'),
('Redskins', 'http://www.washingtonpost.com/rss/sports/redskins'),
('Opinions', 'http://www.washingtonpost.com/rss/opinions'),
('Entertainment', 'http://www.washingtonpost.com/rss/entertainment'),
('Local', 'http://www.washingtonpost.com/rss/local'),
('Investigations',
'http://www.washingtonpost.com/rss/investigations'),
(u'World' , u'http://feeds.washingtonpost.com/rss/world' )
,(u'National' , u'http://feeds.washingtonpost.com/rss/national' )
,(u'White House' , u'http://feeds.washingtonpost.com/rss/politics/whitehouse' )
,(u'Business' , u'http://feeds.washingtonpost.com/rss/business' )
,(u'Opinions' , u'http://feeds.washingtonpost.com/rss/opinions' )
,(u'Investigations' , u'http://feeds.washingtonpost.com/rss/investigations' )
,(u'Local' , u'http://feeds.washingtonpost.com/rss/local' )
,(u'Entertainment' , u'http://feeds.washingtonpost.com/rss/entertainment' )
,(u'Sports' , u'http://feeds.washingtonpost.com/rss/sports' )
,(u'Redskins' , u'http://feeds.washingtonpost.com/rss/sports/redskins' )
,(u'Special Reports', u'http://feeds.washingtonpost.com/rss/national/special-reports')
]
remove_tags = [
{'class':lambda x: x and 'article-toolbar' in x},
{'class':lambda x: x and 'quick-comments' in x},
{'class':lambda x: x and 'tweet' in x},
{'class':lambda x: x and 'article-related' in x},
{'class':lambda x: x and 'hidden' in x.split()},
{'class':lambda x: x and 'also-read' in x.split()},
{'class':lambda x: x and 'partners-content' in x.split()},
{'class':['module share', 'module ads', 'comment-vars', 'hidden',
'share-icons-wrap', 'comments', 'flipper']},
{'id':['right-rail', 'save-and-share']},
{'width':'1', 'height':'1'},
]
keep_only_tags = dict(id=['content', 'article'])
def get_article_url(self, *args):
ans = BasicNewsRecipe.get_article_url(self, *args)
ans = ans.rpartition('?')[0]
if ans.endswith('_video.html'):
return None
if 'ads.pheedo.com' in ans:
return None
#if not ans.endswith('_blog.html'):
# return None
return ans
def print_version(self, url):
return url.replace('_story.html', '_singlePage.html')
if '_story.html' in url:
return url.replace('_story.html','_print.html')
return url
def get_article_url(self, article):
link = BasicNewsRecipe.get_article_url(self,article)
if not 'washingtonpost.com' in link:
self.log('Skipping adds:', link)
return None
for it in ['_video.html','_gallery.html','_links.html']:
if it in link:
self.log('Skipping non-article:', link)
return None
return link