Updated Vecernje Novosti. Fixes #759058 (Updated recipe for site Vecernje Novosti)

This commit is contained in:
Kovid Goyal 2011-04-12 14:20:05 -06:00
parent a404e9827d
commit 9dc0e77a25

View File

@ -1,6 +1,6 @@
__license__ = 'GPL v3'
__copyright__ = '2008-2010, Darko Miletic <darko.miletic at gmail.com>'
__copyright__ = '2008-2011, Darko Miletic <darko.miletic at gmail.com>'
'''
novosti.rs
'''
@ -21,34 +21,71 @@ class Novosti(BasicNewsRecipe):
encoding = 'utf-8'
language = 'sr'
publication_type = 'newspaper'
masthead_url = 'http://www.novosti.rs/images/basic/logo-print.png'
extra_css = """ @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)}
.article_description,body{font-family: Arial,Helvetica,sans1,sans-serif}
.author{font-size: small}
.articleLead{font-size: large; font-weight: bold}
img{display: block; margin-bottom: 1em; margin-top: 1em}
"""
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
, 'pretty_print' : True
}
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
keep_only_tags = [dict(attrs={'class':['articleTitle','author','articleLead','articleBody']})]
remove_tags = [dict(name=['embed','object','iframe','base','link','meta'])]
feeds = [(u'Vesti', u'http://www.novosti.rs/rss/rss-vesti')]
keep_only_tags = [dict(attrs={'class':['articleTitle','articleInfo','articleLead','singlePhoto fl','articleBody']})]
remove_tags = [
dict(name=['embed','object','iframe','base','link','meta'])
,dict(name='a', attrs={'class':'loadComments topCommentsLink'})
]
remove_attributes = ['lang','xmlns:fb']
feeds = [
(u'Politika' , u'http://www.novosti.rs/rss/2-Sve%20vesti')
,(u'Drustvo' , u'http://www.novosti.rs/rss/1-Sve%20vesti')
,(u'Ekonomija' , u'http://www.novosti.rs/rss/3-Sve%20vesti')
,(u'Hronika' , u'http://www.novosti.rs/rss/4-Sve%20vesti')
,(u'Dosije' , u'http://www.novosti.rs/rss/5-Sve%20vesti')
,(u'Reportaze' , u'http://www.novosti.rs/rss/6-Sve%20vesti')
,(u'Tehnologije' , u'http://www.novosti.rs/rss/35-Sve%20vesti')
,(u'Zanimljivosti', u'http://www.novosti.rs/rss/26-Sve%20vesti')
,(u'Auto' , u'http://www.novosti.rs/rss/50-Sve%20vesti')
,(u'Sport' , u'http://www.novosti.rs/rss/11|47|12|14|13-Sve%20vesti')
,(u'Svet' , u'http://www.novosti.rs/rss/7-Sve%20vesti')
,(u'Region' , u'http://www.novosti.rs/rss/8-Sve%20vesti')
,(u'Dijaspora' , u'http://www.novosti.rs/rss/9-Sve%20vesti')
,(u'Spektakl' , u'http://www.novosti.rs/rss/10-Sve%20vesti')
,(u'Kultura' , u'http://www.novosti.rs/rss/31-Sve%20vesti')
,(u'Srbija' , u'http://www.novosti.rs/rss/15-Sve%20vesti')
,(u'Beograd' , u'http://www.novosti.rs/rss/16-Sve%20vesti')
,(u'Zivot+' , u'http://www.novosti.rs/rss/24|33|34|25|20|18|32|19-Sve%20vesti')
,(u'Turizam' , u'http://www.novosti.rs/rss/36-Sve%20vesti')
]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
for item in soup.findAll('span', attrs={'class':'author'}):
item.name='p'
for item in soup.findAll('a'):
limg = item.find('img')
if item.string is not None:
str = item.string
item.replaceWith(str)
else:
if limg:
item.name = 'div'
item.attrs = []
else:
str = self.tag_to_string(item)
item.replaceWith(str)
for item in soup.findAll('img'):
if not item.has_key('alt'):
item['alt'] = 'image'
return soup