Fix #7776 (Updated recipe for NZZ site)

This commit is contained in:
Kovid Goyal 2010-12-03 09:20:56 -07:00
parent 40780b84ea
commit 72a41ea70c

View File

@ -1,6 +1,6 @@
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
''' '''
www.nzz.ch www.nzz.ch
@ -20,6 +20,19 @@ class Nzz(BasicNewsRecipe):
encoding = 'utf-8' encoding = 'utf-8'
use_embedded_content = False use_embedded_content = False
language = 'de' language = 'de'
extra_css = """
body{font-family: Georgia,"Times New Roman",Times,serif }
.artikel h3,.artikel h4,.bildLegende,.question,.autor{font-family: Arial,Verdana,Helvetica,sans-serif}
.bildLegende{font-size: small}
.autor{font-size: 0.9375em; color: #666666}
.quote{font-size: large !important;
font-style: italic;
font-weight: normal !important;
border-bottom: 1px dotted #BFBFBF;
border-top: 1px dotted #BFBFBF;
line-height: 1.25em}
.quelle{color: #666666; font-style: italic; white-space: nowrap}
"""
conversion_options = { conversion_options = {
'comments' : description 'comments' : description
@ -28,12 +41,14 @@ class Nzz(BasicNewsRecipe):
,'publisher' : publisher ,'publisher' : publisher
} }
keep_only_tags = [dict(name='div', attrs={'class':'article'})] keep_only_tags = [dict(name='div', attrs={'class':'zone'})]
remove_tags_before = dict(name='p', attrs={'class':'dachzeile'})
remove_tags_after=dict(name='p', attrs={'class':'fussnote'})
remove_attributes=['width','height','lang']
remove_tags = [ remove_tags = [
dict(name=['object','link','base']) dict(name=['object','link','base','meta','iframe'])
,dict(name='div',attrs={'class':['more','teaser','advXertXoriXals','legal']}) ,dict(attrs={'id':'content_rectangle_1'})
,dict(name='div',attrs={'id':['popup-src','readercomments','google-ad','advXertXoriXals']}) ,dict(attrs={'class':['weiterfuehrendeLinks','fussnote','video']})
] ]
feeds = [ feeds = [
@ -50,7 +65,7 @@ class Nzz(BasicNewsRecipe):
,(u'Reisen' , u'http://www.nzz.ch/magazin/reisen?rss=true') ,(u'Reisen' , u'http://www.nzz.ch/magazin/reisen?rss=true')
] ]
def print_version(self, url): def preprocess_html(self, soup):
return url + '?printview=true' for item in soup.findAll(style=True):
del item['style']
return self.adeify_images(soup)