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 LifeHacker

Browse Source
This commit is contained in:
Kovid Goyal 2011-02-13 20:13:20 -07:00
parent 95ee0429e0
commit 173bce9daa
1 changed files with 11 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
resources/recipes/lifehacker.recipe
View File

@ -8,7 +8,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
class Lifehacker(BasicNewsRecipe): class Lifehacker(BasicNewsRecipe):
title = 'Lifehacker' title = 'Lifehacker'
__author__ = 'NA' __author__ = 'Kovid Goyal'
description = "Computers make us more productive. Yeah, right. Lifehacker recommends the software downloads and web sites that actually save time. Don't live to geek; geek to live." description = "Computers make us more productive. Yeah, right. Lifehacker recommends the software downloads and web sites that actually save time. Don't live to geek; geek to live."
publisher = 'lifehacker.com' publisher = 'lifehacker.com'
category = 'news, IT, Internet, gadgets, tips and tricks, howto, diy' category = 'news, IT, Internet, gadgets, tips and tricks, howto, diy'
@ -32,14 +32,20 @@ class Lifehacker(BasicNewsRecipe):
, 'language' : language , 'language' : language
} }
remove_attributes = ['width','height'] remove_attributes = ['width', 'height', 'style']
keep_only_tags = [dict(attrs={'class':'content permalink'})]
remove_tags_before = dict(name='h1') remove_tags_before = dict(name='h1')
remove_tags = [dict(attrs={'class':'contactinfo'})] keep_only_tags = [dict(id='container')]
remove_tags_after = dict(attrs={'class':'contactinfo'}) remove_tags_after = dict(attrs={'class':'post-body'})
remove_tags = [
dict(id="sharemenu"),
{'class': 'related'},
]
feeds = [(u'Articles', u'http://feeds.gawker.com/lifehacker/full')] feeds = [(u'Articles', u'http://feeds.gawker.com/lifehacker/full')]
def preprocess_html(self, soup): def preprocess_html(self, soup):
return self.adeify_images(soup) return self.adeify_images(soup)
def print_version(self, url):
return url.replace('#!', '?_escaped_fragment_=')