mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
Fix #6303 (enhanced "Die Zeit Nachrichten"-recipe)
This commit is contained in:
Kovid Goyal
parent
2a39e43655
commit
e8cd782399
@ -6,88 +6,105 @@ Fetch Die Zeit.
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
from calibre.ebooks.BeautifulSoup import Tag
|
||||
|
||||
class ZeitDe(BasicNewsRecipe):
|
||||
|
||||
title = 'Die Zeit Nachrichten'
|
||||
description = 'Die Zeit - Online Nachrichten'
|
||||
title = 'ZEIT Online Reader Edition'
|
||||
description = 'ZEIT Online'
|
||||
language = 'de'
|
||||
lang = 'de_DE'
|
||||
|
||||
__author__ = 'Martin Pitt and Sujata Raman'
|
||||
__author__ = 'Martin Pitt, Sujata Raman and Ingo Paschke'
|
||||
use_embedded_content = False
|
||||
max_articles_per_feed = 40
|
||||
max_articles_per_feed = 100
|
||||
remove_empty_feeds = True
|
||||
no_stylesheets = True
|
||||
no_javascript = True
|
||||
encoding = 'utf-8'
|
||||
|
||||
delay = 0
|
||||
|
||||
feeds = [
|
||||
('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'),
|
||||
('Seite 1', 'http://newsfeed.zeit.de/index'),
|
||||
('Politik', 'http://www.zeit.de/solr/select/?q=ressort:%22Politik%22%20type:article&version=2.2&start=0&rows=50&sort=date-first-released%20desc&indent=on&wt=xslt&tr=solr2rss.xsl'),
|
||||
('Wirtschaft', 'http://www.zeit.de/solr/select/?q=ressort:%22Wirtschaft%22%20type:article&version=2.2&start=0&rows=50&sort=date-first-released%20desc&indent=on&wt=xslt&tr=solr2rss.xsl'),
|
||||
('Meinung', 'http://www.zeit.de/solr/select/?q=ressort:%22Meinung%22%20type:article&version=2.2&start=0&rows=50&sort=date-first-released%20desc&indent=on&wt=xslt&tr=solr2rss.xsl'),
|
||||
('Gesellschaft', 'http://www.zeit.de/solr/select/?q=ressort:%22Gesellschaft%22%20type:article&version=2.2&start=0&rows=50&sort=date-first-released%20desc&indent=on&wt=xslt&tr=solr2rss.xsl'),
|
||||
('Kultur', 'http://www.zeit.de/solr/select/?q=ressort:%22Kultur%22%20type:article&version=2.2&start=0&rows=50&sort=date-first-released%20desc&indent=on&wt=xslt&tr=solr2rss.xsl'),
|
||||
('Wissen', 'http://www.zeit.de/solr/select/?q=ressort:%22Wissen%22%20type:article&version=2.2&start=0&rows=50&sort=date-first-released%20desc&indent=on&wt=xslt&tr=solr2rss.xsl'),
|
||||
('Digital', 'http://www.zeit.de/solr/select/?q=ressort:%22Digital%22%20type:article&version=2.2&start=0&rows=50&sort=date-first-released%20desc&indent=on&wt=xslt&tr=solr2rss.xsl'),
|
||||
('Studium', 'http://www.zeit.de/solr/select/?q=ressort:%22Studium%22%20type:article&version=2.2&start=0&rows=50&sort=date-first-released%20desc&indent=on&wt=xslt&tr=solr2rss.xsl'),
|
||||
('Karriere', 'http://www.zeit.de/solr/select/?q=ressort:%22Karriere%22%20type:article&version=2.2&start=0&rows=50&sort=date-first-released%20desc&indent=on&wt=xslt&tr=solr2rss.xsl'),
|
||||
('Lebensart', 'http://www.zeit.de/solr/select/?q=ressort:%22Lebensart%22%20type:article&version=2.2&start=0&rows=50&sort=date-first-released%20desc&indent=on&wt=xslt&tr=solr2rss.xsl'),
|
||||
('Reisen', 'http://www.zeit.de/solr/select/?q=ressort:%22Reisen%22%20type:article&version=2.2&start=0&rows=50&sort=date-first-released%20desc&indent=on&wt=xslt&tr=solr2rss.xsl'),
|
||||
('Auto', 'http://www.zeit.de/solr/select/?q=ressort:%22Auto%22%20type:article&version=2.2&start=0&rows=50&sort=date-first-released%20desc&indent=on&wt=xslt&tr=solr2rss.xsl'),
|
||||
('Sport', 'http://www.zeit.de/solr/select/?q=ressort:%22Sport%22%20type:article&version=2.2&start=0&rows=50&sort=date-first-released%20desc&indent=on&wt=xslt&tr=solr2rss.xsl'),
|
||||
]
|
||||
|
||||
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:large;}
|
||||
.title{font-family:Arial,Helvetica,sans-serif;font-size:large}
|
||||
.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='div', attrs={'class':["pagination block","pagenav","inline link"] }),
|
||||
dict(name='div', attrs={'id':["place_5","place_4"]})
|
||||
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"
|
||||
|
||||
ans = article.get('guid',None)
|
||||
|
||||
try:
|
||||
self.log('Looking for full story link in', ans)
|
||||
soup = self.index_to_soup(ans)
|
||||
x = soup.find(text="Auf einer Seite lesen")
|
||||
|
||||
if x is not None:
|
||||
|
||||
a = x.parent
|
||||
if a and a.has_key('href'):
|
||||
ans = a['href']
|
||||
self.log('Found full story link', ans)
|
||||
except:
|
||||
pass
|
||||
|
||||
if 'video' in ans or 'quiz' in ans :
|
||||
|
||||
if 'video' in ans or 'quiz' or 'blog.zeit.de/' 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
|
||||
|
||||
|
||||
#def print_version(self,url):
|
||||
# return url.replace('http://www.zeit.de/', 'http://images.zeit.de/text/').replace('?from=rss', '')
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user