mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
45 lines
1.5 KiB
Plaintext
45 lines
1.5 KiB
Plaintext
__license__ = 'GPL v3'
|
|
__copyright__ = '2010, NA'
|
|
'''
|
|
gawker.com
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class Gawker(BasicNewsRecipe):
|
|
title = 'Gawker'
|
|
__author__ = 'NA'
|
|
description = "Gawker, Gossip from Manhattan and the Beltway to Hollywood and the Valley."
|
|
publisher = 'gawker.com'
|
|
category = 'news, gossip'
|
|
oldest_article = 2
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
encoding = 'utf-8'
|
|
use_embedded_content = False
|
|
language = 'en'
|
|
masthead_url = 'http://cache.gawkerassets.com/assets/gawker.com/img/logo.png'
|
|
extra_css = '''
|
|
body{font-family: "Lucida Grande",Helvetica,Arial,sans-serif}
|
|
img{margin-bottom: 1em}
|
|
h1{font-family :Arial,Helvetica,sans-serif; font-size:large}
|
|
'''
|
|
conversion_options = {
|
|
'comment' : description
|
|
, 'tags' : category
|
|
, 'publisher' : publisher
|
|
, 'language' : language
|
|
}
|
|
|
|
remove_attributes = ['width','height']
|
|
keep_only_tags = [dict(attrs={'class':'content permalink'})]
|
|
remove_tags_before = dict(name='h1')
|
|
remove_tags = [dict(attrs={'class':'contactinfo'})]
|
|
remove_tags_after = dict(attrs={'class':'contactinfo'})
|
|
|
|
feeds = [(u'Articles', u'http://feeds.gawker.com/gawker/full')]
|
|
|
|
def preprocess_html(self, soup):
|
|
return self.adeify_images(soup)
|
|
|