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

Improve The Week

Browse Source
This commit is contained in:
Kovid Goyal 2011-11-19 08:59:01 +05:30
parent 5701c1990a
commit 70d3065b08
1 changed files with 1 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
recipes/the_week_magazine_free.recipe
View File

@ -5,7 +5,6 @@ www.theweek.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
import re
class TheWeek(BasicNewsRecipe):
title = 'The Week Magazine'
@ -21,23 +20,7 @@ class TheWeek(BasicNewsRecipe):
encoding = 'utf-8'
use_embedded_content = False
language = 'en'
preprocess_regexps = [(re.compile(r'<h3><a href=.*</body>', re.DOTALL), lambda match: '</body>')]
remove_tags_before = dict(name='h1')
remove_tags_after = dict(name='div', attrs={'class':'articleSubscribe4free'})
remove_tags = [
dict(name='div', attrs={'class':['floatLeft','imageCaption','slideshowImageAttribution','postDate','utilities','cartoonInfo','left','middle','col300','articleSubscribe4free',' articleFlyout','articleFlyout floatRight','fourFreeBar']})
,dict(name='div', attrs={'id':['cartoonThumbs','rightColumn','header','partners']})
,dict(name='ul', attrs={'class':['slideshowNav','hotTopicsList topicList']})
]
remove_attributes = ['width','height', 'style', 'font', 'color']
extra_css = '''
h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
p {font-family:Arial,Helvetica,sans-serif;}
'''
filter_regexps = [r'www\.palmcoastdata\.com']
auto_cleanup = True
feeds = [
(u'News-Opinion', u'http://theweek.com/section/index/news_opinion.rss'),
(u'Business', u'http://theweek.com/section/index/business.rss'),