Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix Washington Post

Browse Source
This commit is contained in:
Kovid Goyal 2011-03-20 11:18:18 -06:00
parent 3de3f3d4fb
commit 517a3e3975
1 changed files with 30 additions and 38 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

68
recipes/wash_post.recipe
View File

@ -1,4 +1,3 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
@ -6,55 +5,48 @@ class WashingtonPost(BasicNewsRecipe):
title = 'Washington Post' title = 'Washington Post'
description = 'US political news' description = 'US political news'
__author__ = 'Kovid Goyal and Sujata Raman' __author__ = 'Kovid Goyal'
use_embedded_content = False use_embedded_content = False
max_articles_per_feed = 20 max_articles_per_feed = 20
language = 'en' language = 'en'
encoding = 'utf-8'
remove_javascript = True remove_javascript = True
no_stylesheets = True no_stylesheets = True
extra_css = ''' feeds = [
#articleCopyright { font-family:Arial,helvetica,sans-serif ; font-weight:bold ; font-size:x-small ;} ('Politics', 'http://www.washingtonpost.com/rss/politics'),
p { font-family:"Times New Roman",times,serif ; font-weight:normal ; font-size:small ;} ('Nation', 'http://www.washingtonpost.com/rss/national'),
body{font-family:arial,helvetica,sans-serif} ('World', 'http://www.washingtonpost.com/rss/world'),
''' ('Business', 'http://www.washingtonpost.com/rss/business'),
('Lifestyle', 'http://www.washingtonpost.com/rss/lifestyle'),
feeds = [ ('Today\'s Highlights', 'http://www.washingtonpost.com/wp-dyn/rss/linkset/2005/03/24/LI2005032400102.xml'), ('Sports', 'http://www.washingtonpost.com/rss/sports'),
('Politics', 'http://www.washingtonpost.com/wp-dyn/rss/politics/index.xml'), ('Redskins', 'http://www.washingtonpost.com/rss/sports/redskins'),
('Nation', 'http://www.washingtonpost.com/wp-dyn/rss/nation/index.xml'), ('Opinions', 'http://www.washingtonpost.com/rss/opinions'),
('World', 'http://www.washingtonpost.com/wp-dyn/rss/world/index.xml'), ('Entertainment', 'http://www.washingtonpost.com/rss/entertainment'),
('Business', 'http://www.washingtonpost.com/wp-dyn/rss/business/index.xml'), ('Local', 'http://www.washingtonpost.com/rss/local'),
('Technology', 'http://www.washingtonpost.com/wp-dyn/rss/technology/index.xml'), ('Investigations',
('Health', 'http://www.washingtonpost.com/wp-dyn/rss/health/index.xml'), 'http://www.washingtonpost.com/rss/investigations'),
('Education', 'http://www.washingtonpost.com/wp-dyn/rss/education/index.xml'),
('Style',
'http://www.washingtonpost.com/wp-dyn/rss/print/style/index.xml'),
('NFL Sports',
'http://www.washingtonpost.com/wp-dyn/rss/sports/index/nfl/index.xml'),
('Redskins', 'http://www.washingtonpost.com/wp-dyn/rss/sports/redskins/index.xml'),
('Editorials', 'http://www.washingtonpost.com/wp-dyn/rss/linkset/2005/05/30/LI2005053000331.xml'),
] ]
remove_tags = [{'id':['pfmnav', 'ArticleCommentsWrapper']}] 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']},
{'id':['right-rail']},
]
keep_only_tags = dict(id=['content', 'article'])
def get_article_url(self, article):
return article.get('guid', article.get('link', None))
def print_version(self, url): def print_version(self, url):
return url.rpartition('.')[0] + '_pf.html' url = url.rpartition('?')[0]
return url.replace('_story.html', '_singlePage.html')
def postprocess_html(self, soup, first):
for div in soup.findAll(name='div', style=re.compile('margin')):
div['style'] = ''
return soup
def preprocess_html(self, soup):
for tag in soup.findAll('font'):
if tag.has_key('size'):
if tag['size'] == '+2':
if tag.b:
return soup
return None