2
__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>'
4
bighollywood.breitbart.com
7
from calibre.web.feeds.news import BasicNewsRecipe
9
class BigHollywood(BasicNewsRecipe):
10
title = 'Big Hollywood'
11
__author__ = 'Darko Miletic'
12
description = 'News and articles from the media world'
13
publisher = 'Big Hollywood'
14
category = 'news, media, art, literature, movies, politics, USA, Hollywood'
16
max_articles_per_feed = 200
19
use_embedded_content = False
21
remove_empty_feeds = True
22
publication_type = 'blog'
24
body{font-family: Arial,sans-serif }
27
conversion_options = {
28
'comment' : description
30
, 'publisher' : publisher
31
, 'language' : language
34
keep_only_tags=[dict(attrs={'class':'postcontent'})]
36
dict(name=['meta','link','link','iframe','embed','object'])
37
,dict(name='p', attrs={'class':['post_meta_links','postfooter']})
39
remove_attributes=['original','onclick']
41
feeds = [(u'Articles', u'http://bighollywood.breitbart.com/feed/')]
43
def preprocess_html(self, soup):
44
for item in soup.findAll(style=True):
46
for item in soup.findAll('a'):
47
limg = item.find('img')
48
if item.string is not None:
53
if limg['src'].endswith('BlogPrintButton.png'):
58
str = self.tag_to_string(item)
60
for item in soup.findAll('img'):
61
if not item.has_key('alt'):