home
***
CD-ROM
|
disk
|
FTP
|
other
***
search
/
Chip 2011 November
/
CHIP_2011_11.iso
/
Programy
/
Narzedzia
/
Calibre
/
calibre-0.8.18.msi
/
file_280
/
nrc.nl.recipe
< prev
next >
Wrap
Text File
|
2011-09-09
|
3KB
|
77 lines
__license__ = 'GPL v3'
__copyright__ = '2010-2011, Darko Miletic <darko.miletic at gmail.com>'
'''
nrc.nl
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Pagina12(BasicNewsRecipe):
title = 'NRC'
__author__ = 'Darko Miletic'
description = 'News from Netherlands'
publisher = 'nrc.nl'
category = 'news, politics, Netherlands'
oldest_article = 2
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'utf8'
use_embedded_content = False
language = 'nl'
country = 'NL'
remove_empty_feeds = True
masthead_url = 'http://www.nrc.nl/nrc.nl/images/logo_nrc.png'
extra_css = """
body{font-family: Georgia,serif }
img{margin-bottom: 0.4em; display: block}
.bijschrift,.sectie{font-size: x-small}
.sectie{color: gray}
"""
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
keep_only_tags = [dict(attrs={'class':'uitstekendekeus'})]
remove_tags = [
dict(name=['meta','base','link','object','embed'])
,dict(attrs={'class':['reclamespace','tags-and-sharing','sharing-is-caring']})
]
remove_attributes=['lang']
feeds = [
(u'Voor nieuws', u'http://www.nrc.nl/nieuws/categorie/nieuws/rss.php' )
,(u'Binnenland' , u'http://www.nrc.nl/nieuws/categorie/binnenland/rss.php' )
,(u'Buitenland' , u'http://www.nrc.nl/nieuws/categorie/buitenland/rss.php' )
,(u'Economie' , u'http://www.nrc.nl/nieuws/categorie/economie/rss.php' )
,(u'Cultuur' , u'http://www.nrc.nl/nieuws/categorie/cultuur/rss.php' )
,(u'Sport' , u'http://www.nrc.nl/nieuws/categorie/sport/rss.php' )
,(u'Wetenschap ', u'http://www.nrc.nl/nieuws/categorie/wetenschap-nieuws/rss.php')
]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
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'
atritems =['href','target','rel']
for atit in atritems:
if item.has_key(atit):
del item[atit]
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