mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
Update Zeit Online
This commit is contained in:
Kovid Goyal
parent
eeeba5e40f
commit
aadbe9b01e
@ -2,74 +2,52 @@ __license__ = 'GPL v3'
|
||||
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
|
||||
|
||||
'''
|
||||
Fetch Die Zeit.
|
||||
Fetch Zeit-Online.de
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
from datetime import date
|
||||
|
||||
class ZeitDe(BasicNewsRecipe):
|
||||
|
||||
title = 'Zeit Online'
|
||||
description = 'Zeit Online'
|
||||
language = 'de'
|
||||
encoding = 'UTF-8'
|
||||
__author__ = 'Armin Geller' # AGe 2012-10-13
|
||||
title = u'Zeit Online'
|
||||
description = u'German online portal of newspaper Die Zeit'
|
||||
publisher = 'ZEIT ONLINE GmbH'
|
||||
category = 'news, Germany'
|
||||
timefmt = ' [%a, %d %b %Y]'
|
||||
publication_type = 'newspaper'
|
||||
language = 'de_DE'
|
||||
encoding = 'UTF-8'
|
||||
|
||||
__author__ = 'Martin Pitt, Sujata Raman, Ingo Paschke and Marc Toensing'
|
||||
no_stylesheets = True
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
remove_empty_feeds = True
|
||||
auto_cleanup = True
|
||||
# no_stylesheets = True
|
||||
# conversion_options = {'base_font_size': 10}
|
||||
|
||||
max_articles_per_feed = 40
|
||||
masthead_url = 'http://images.zeit.de/static/img/logo_247x30.png'
|
||||
|
||||
remove_tags = [
|
||||
dict(name='iframe'),
|
||||
dict(name='div', attrs={'class':["response","pagination block","pagenav","inline link", "copyright"] }),
|
||||
dict(name='p', attrs={'class':["ressortbacklink", "copyright"] }),
|
||||
dict(name='div', attrs={'id':["place_5","place_4","comments"]})
|
||||
]
|
||||
|
||||
keep_only_tags = [dict(id=['main'])]
|
||||
year = str(date.today().isocalendar()[0]) # [0]=year [1]=week number [2]=week day
|
||||
week = str(date.today().isocalendar()[1]+1)
|
||||
cover_url = 'http://images.zeit.de/bilder/titelseiten_zeit/titelfluss/' + year + '/0'+ week + '_001.jpg'
|
||||
|
||||
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'),
|
||||
(u'Startseite – Die wichtigsten Themen auf einen Blick', u'http://newsfeed.zeit.de/index_xml'),
|
||||
(u'Politik – Ausland und Deutschland', u'http://newsfeed.zeit.de/politik/index'),
|
||||
(u'Wirtschaft – Wirtschaft und Unternehmen', u'http://newsfeed.zeit.de/wirtschaft/index'),
|
||||
(u'Meinung – Autoren kommentieren', u'http://newsfeed.zeit.de/meinung/index'),
|
||||
(u'Gesellschaft – Gesellschaft und soziales Leben', u'http://newsfeed.zeit.de/gesellschaft/index'),
|
||||
(u'Kultur – Literatur, Kunst, Film und Musik', u'http://newsfeed.zeit.de/kultur/index'),
|
||||
(u'Wissen – Wissenschaft, Gesundheit, Umwelt und Geschichte', u'http://newsfeed.zeit.de/wissen/index'),
|
||||
(u'Digital – Hardware, Software, Internet, Datenschutz', u'http://newsfeed.zeit.de/digital/index'),
|
||||
(u'Studium – ZEIT ONLINE für Studenten', u'http://newsfeed.zeit.de/studium/index'),
|
||||
(u'Karriere – Für Ein-, Um- und Aufsteiger', u'http://newsfeed.zeit.de/karriere/index'),
|
||||
(u'Lebensart – Freizeit und Leben', u'http://newsfeed.zeit.de/lebensart/index'),
|
||||
(u'Reisen – All inclusive und individuell', u'http://newsfeed.zeit.de/reisen/index'),
|
||||
(u'Auto – Modelle und Trends', u'http://newsfeed.zeit.de/auto/index'),
|
||||
(u'Sport – Sieg und Niederlage', u'http://newsfeed.zeit.de/sport/index')
|
||||
]
|
||||
|
||||
extra_css = '.excerpt{font-size:1em}.reaktion,.taglist,.comments,.reponse,.responsetitle,.responsebody,.reponse,.inline,.date{display:none;}li.date{display:block}'
|
||||
|
||||
#filter_regexps = [r'ad.de.doubleclick.net/']
|
||||
|
||||
def get_article_url(self, article):
|
||||
ans = article.get('link',None)
|
||||
ans += "?page=all&print=true"
|
||||
|
||||
if 'video' in ans or 'quiz' in ans or 'blog' in ans :
|
||||
ans = None
|
||||
return ans
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for tag in soup.findAll(name=['ul','li']):
|
||||
tag.name = 'div'
|
||||
|
||||
soup.html['xml:lang'] = self.language.replace('_', '-')
|
||||
soup.html['lang'] = self.language.replace('_', '-')
|
||||
mtag = '<meta http-equiv="Content-Type" content="text/html; charset=' + self.encoding + '">'
|
||||
soup.head.insert(0,mtag)
|
||||
return soup
|
||||
|
||||
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 print_version(self, url):
|
||||
return url + '/komplettansicht?print=true'
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user