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 recipe

Browse Source
This commit is contained in:
Kovid Goyal 2009-02-08 22:58:25 -08:00
parent ffee7f8da1
commit d97aaefd2c
2 changed files with 12 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/calibre/web/feeds/news.py
View File

@ -91,7 +91,7 @@ class BasicNewsRecipe(object, LoggingInterface):
#: If True stylesheets are not downloaded and processed
no_stylesheets = False
#: Convenient flag to strip all javascripts tags from the downloaded HTML
#: Convenient flag to strip all javascript tags from the downloaded HTML
remove_javascript = True
#: If True the GUI will ask the user for a username and password

25
src/calibre/web/feeds/recipes/recipe_wash_post.py
View File

@ -12,19 +12,7 @@ class WashingtonPost(BasicNewsRecipe):
language = _('English')
preprocess_regexps = [ (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
[
(r'<HEAD>.*?</HEAD>' , lambda match : '<HEAD></HEAD>'),
(r'<div id="apple-rss-sidebar-background">.*?<!-- start Entries -->', lambda match : ''),
(r'<!-- end apple-rss-content-area -->.*?</body>', lambda match : '</body>'),
(r'<script.*?>.*?</script>', lambda match : ''),
(r'<body.*?>.*?.correction {', lambda match : '<body><style>.correction {'),
(r'<span class="display:none;" name="pubDate".*?>.*?</body>', lambda match : '<body>'),
]
]
remove_javascript = True
feeds = [ ('Today\'s Highlights', 'http://www.washingtonpost.com/wp-dyn/rss/linkset/2005/03/24/LI2005032400102.xml'),
@ -37,9 +25,18 @@ class WashingtonPost(BasicNewsRecipe):
('Education', 'http://www.washingtonpost.com/wp-dyn/rss/education/index.xml'),
('Editorials', 'http://www.washingtonpost.com/wp-dyn/rss/linkset/2005/05/30/LI2005053000331.xml'),
]
remove_tags = [{'id':['pfmnav', 'ArticleCommentsWrapper']}]
def get_article_url(self, article):
return article.get('feedburner_origlink', article.get('link', None))
def print_version(self, url):
return (url.rpartition('.')[0] + '_pf.html')
return url.rpartition('.')[0] + '_pf.html'
def postprocess_html(self, soup, first):
for div in soup.findAll(name='div', style=re.compile('margin')):
div['style'] = ''
return soup