calibre/resources/recipes/zeitde.recipe
Kovid Goyal c9343d1584 ...
2010-07-30 13:53:56 -06:00

111 lines
5.1 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
'''
Fetch Die Zeit.
'''
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag
class ZeitDe(BasicNewsRecipe):
title = 'ZEIT Online'
description = 'ZEIT Online'
language = 'de'
lang = 'de_DE'
__author__ = 'Martin Pitt, Sujata Raman and Ingo Paschke'
use_embedded_content = False
max_articles_per_feed = 40
remove_empty_feeds = True
no_stylesheets = True
no_javascript = True
encoding = 'utf-8'
feeds = [
('Seite 1', 'http://newsfeed.zeit.de/index_xml'),
('Politik', 'http://newsfeed.zeit.de/politik/index'),
('Wirtschaft', 'http://newsfeed.zeit.de/wirtschaft/index'),
('Meinung', 'http://newsfeed.zeit.de/meinung/index'),
('Gesellschaft', 'http://newsfeed.zeit.de/gesellschaft/index'),
('Kultur', 'http://newsfeed.zeit.de/kultur/index'),
('Wissen', 'http://newsfeed.zeit.de/wissen/index'),
('Digital', 'http://newsfeed.zeit.de/digital/index'),
('Studium', 'http://newsfeed.zeit.de/studium/index'),
('Karriere', 'http://newsfeed.zeit.de/karriere/index'),
('Lebensart', 'http://newsfeed.zeit.de/lebensart/index'),
('Reisen', 'http://newsfeed.zeit.de/reisen/index'),
('Auto', 'http://newsfeed.zeit.de/auto/index'),
('Sport', 'http://newsfeed.zeit.de/sport/index'),
]
extra_css = '''
.supertitle{color:#990000; font-family:Arial,Helvetica,sans-serif;font-size:xx-small;}
.excerpt{font-family:Georgia,Palatino,Palatino Linotype,FreeSerif,serif;font-size:small;}
.title{font-family:Arial,Helvetica,sans-serif;font-size:large;clear:right;}
.caption{color:#666666; font-family:Arial,Helvetica,sans-serif;font-size:xx-small;}
.copyright{color:#666666; font-family:Arial,Helvetica,sans-serif;font-size:xx-small;}
.article{font-family:Georgia,Palatino,Palatino Linotype,FreeSerif,serif;font-size:x-small}
.quote{font-family:Georgia,Palatino,Palatino Linotype,FreeSerif,serif;font-size:x-small}
.quote .cite{font-family:Georgia,Palatino,Palatino Linotype,FreeSerif,serif;font-size:xx-small}
.headline iconportrait_inline{font-family:Arial,Helvetica,sans-serif;font-size:x-small}
.inline{float:left;margin-top:0;margin-right:15px;position:relative;width:180px; }
img.inline{float:none}
.intertitle{font-family:Georgia,Palatino,Palatino Linotype,FreeSerif,serif;font-size:x-small;font-weight:700}
.ebinfobox{font-family:Georgia,Palatino,Palatino Linotype,FreeSerif,serif;font-size:xx-small;list-style-type:none;float:right;margin-top:0;border-left-style:solid;border-left-width:1px;padding-left:10px;}
.infobox {border-style: solid; border-width: 1px;padding:8px;}
.infobox dt {font-weight:700;}
'''
#filter_regexps = [r'ad.de.doubleclick.net/']
keep_only_tags = [
dict(name='div', attrs={'class':["article"]}) ,
dict(name='ul', attrs={'class':["tools"]}) ,
]
remove_tags = [
dict(name='link'), dict(name='iframe'),dict(name='style'),dict(name='meta'),
dict(name='div', attrs={'class':["pagination block","pagenav","inline link", "copyright"] }),
dict(name='p', attrs={'class':["ressortbacklink", "copyright"] }),
dict(name='div', attrs={'id':["place_5","place_4","comments"]})
]
remove_attributes = ['style', 'font']
def get_article_url(self, article):
ans = article.get('link',None)
ans += "?page=all"
if 'video' in ans or 'quiz' in ans :
ans = None
return ans
def get_cover_url(self):
try:
inhalt = self.index_to_soup('http://www.zeit.de/inhalt')
return inhalt.find('div', attrs={'class':'singlearchive clearfix'}).img['src'].replace('icon_','')
except:
return 'http://images.zeit.de/bilder/titelseiten_zeit/1946/001_001.jpg'
def preprocess_html(self, soup):
soup.html['xml:lang'] = self.lang
soup.html['lang'] = self.lang
mtag = '<meta http-equiv="Content-Type" content="text/html; charset=' + self.encoding + '">'
soup.head.insert(0,mtag)
title = soup.find('h2', attrs={'class':'title'})
if title is None:
print "no title"
return soup
info = Tag(soup,'ul',[('class','ebinfobox')])
tools = soup.find('ul', attrs={'class':'tools'})
#author = tools.find('li','author first')
for tag in ['author first', 'date', 'date first', 'author', 'source']:
line = tools.find('li', tag)
if line:
info.insert(0,line)
title.parent.insert(0,info)
tools.extract()
return soup