Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-06-23 15:30:45 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix Wired recipe

Browse Source
This commit is contained in:
Kovid Goyal 2009-07-23 09:01:48 -06:00
parent e89c1392a1
commit 3829b4c20f
1 changed files with 13 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -2,35 +2,24 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'
import re
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
class Wired(BasicNewsRecipe): class Wired(BasicNewsRecipe):
title = 'Wired.com' title = 'Wired.com'
__author__ = 'David Chen <SonyReader<at>DaveChen<dot>org>' __author__ = 'Kovid Goyal'
description = 'Technology news' description = 'Technology news'
timefmt = ' [%Y%b%d %H%M]' timefmt = ' [%Y%b%d %H%M]'
language = _('English') language = _('English')
no_stylesheets = True no_stylesheets = True
#html2lrf_options = ['--base-font-size', '16']
preprocess_regexps = [(re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in remove_tags_before = dict(name='div', id='content')
remove_tags = [dict(id=['social_tools', 'outerWrapper', 'sidebar',
[ 'footer', 'advertisement', 'blog_subscription_unit',
'brightcove_component']),
## Remove any banners/links/ads/cruft before the body of the article. {'class':'entryActions'},
(r'<body.*?((<div id="article_body">)|(<div id="st-page-maincontent">)|(<div id="containermain">)|(<p class="ap-story-p">)|(<!-- img_nav -->))', lambda match: '<body><div>'), dict(name=['noscript', 'script'])]
## Remove any links/ads/comments/cruft from the end of the body of the article.
(r'((<!-- end article content -->)|(<div id="st-custom-afterpagecontent">)|(<p class="ap-story-p">&copy;)|(<div class="entry-footer">)|(<div id="see_also">)|(<p>Via <a href=)|(<div id="ss_nav">)).*?</html>', lambda match : '</div></body></html>'),
## Correctly embed in-line images by removing the surrounding javascript that will be ignored in the conversion
(r'<a.*?onclick.*?>.*?(<img .*?>)', lambda match: match.group(1),),
]
]
feeds = [ feeds = [
('Top News', 'http://feeds.wired.com/wired/index'), ('Top News', 'http://feeds.wired.com/wired/index'),