mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
125 lines
4.7 KiB
Plaintext
125 lines
4.7 KiB
Plaintext
__license__ = 'GPL v3'
|
|
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
www.sueddeutsche.de/sz/
|
|
'''
|
|
# History
|
|
# 2015.01.02 Daily Cover from https://zeitung.sueddeutsche.de/webapp by lala-rob (web@lala-rob.de)
|
|
# 2014.12.15 Set Cover by lala-rob(web@lala-rob.de)
|
|
# 2014.10.02 Fixed url Problem by lala-rob(web@lala-rob.de)
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from calibre import strftime
|
|
import datetime
|
|
|
|
|
|
class SueddeutcheZeitung(BasicNewsRecipe):
|
|
title = u'Süddeutsche Zeitung'
|
|
__author__ = 'Darko Miletic'
|
|
description = 'News from Germany. Access to paid content.'
|
|
publisher = u'Süddeutsche Zeitung'
|
|
category = 'news, politics, Germany'
|
|
no_stylesheets = True
|
|
oldest_article = 2
|
|
encoding = 'iso-8859-1'
|
|
needs_subscription = True
|
|
remove_empty_feeds = True
|
|
delay = 1
|
|
cover_url = 'https://zeitung.sueddeutsche.de/szdigital/public/issue/previewimage?size=l&issueId=' + \
|
|
(datetime.datetime.utcnow() + datetime.timedelta(hours=1)
|
|
).strftime("%Y-%m-%d") + '&targetVersion=3&productId=sz'
|
|
PREFIX = 'http://epaper.sueddeutsche.de'
|
|
INDEX = PREFIX + '/app/epaper/textversion/'
|
|
use_embedded_content = False
|
|
masthead_url = 'http://pix.sueddeutsche.de/img/layout/header/SZ_solo288x31.gif'
|
|
language = 'de'
|
|
publication_type = 'newspaper'
|
|
extra_css = ' body{font-family: Arial,Helvetica,sans-serif} '
|
|
|
|
conversion_options = {
|
|
'comment': description, 'tags': category, 'publisher': publisher, 'language': language, 'linearize_tables': True
|
|
}
|
|
|
|
remove_attributes = ['height', 'width', 'style']
|
|
|
|
def get_browser(self):
|
|
browser = BasicNewsRecipe.get_browser(self)
|
|
|
|
# Login via fetching of Streiflicht -> Fill out login request
|
|
url = 'https://id.sueddeutsche.de/login'
|
|
browser.open(url)
|
|
|
|
browser.select_form(nr=0) # to select the first form
|
|
browser['login'] = self.username
|
|
browser['password'] = self.password
|
|
browser.submit()
|
|
|
|
return browser
|
|
|
|
remove_tags = [
|
|
dict(attrs={'class': 'hidePrint'}), dict(
|
|
name=['link', 'object', 'embed', 'base', 'iframe', 'br'])
|
|
]
|
|
keep_only_tags = [dict(attrs={'class': 'artikelBox'})]
|
|
remove_tags_before = dict(attrs={'class': 'artikelTitel'})
|
|
remove_tags_after = dict(attrs={'class': 'author'})
|
|
|
|
feeds = [
|
|
|
|
(u'Politik', INDEX + 'Politik/'),
|
|
(u'Seite drei', INDEX + 'Seite+drei/'),
|
|
(u'Thema des Tages', INDEX + 'Thema+des+Tages/'),
|
|
(u'Meinungsseite', INDEX + 'Meinungsseite/'),
|
|
(u'Wissen', INDEX + 'Wissen/'),
|
|
(u'Panorama', INDEX + 'Panorama/'),
|
|
(u'Feuilleton', INDEX + 'Feuilleton/'),
|
|
(u'Medien', INDEX + 'Medien/'),
|
|
(u'Wirtschaft', INDEX + 'Wirtschaft/'),
|
|
(u'Sport', INDEX + 'Sport/'),
|
|
(u'Bayern', INDEX + 'Bayern/'),
|
|
(u'Muenchen', INDEX + 'M%FCnchen/'),
|
|
(u'Muenchen City', INDEX + 'M%FCnchen+City/'),
|
|
(u'Jetzt.de', INDEX + 'Jetzt.de/'),
|
|
(u'Reise', INDEX + 'Reise/'),
|
|
(u'SZ Extra', INDEX + 'SZ+Extra/'),
|
|
(u'Wochenende', INDEX + 'SZ+am+Wochenende/'),
|
|
(u'Stellen-Markt', INDEX + 'Stellen-Markt/'),
|
|
(u'Motormarkt', INDEX + 'Motormarkt/'),
|
|
(u'Immobilien-Markt', INDEX + 'Immobilien-Markt/'),
|
|
(u'Thema', INDEX + 'Thema/'),
|
|
(u'Forum', INDEX + 'Forum/'),
|
|
(u'Leute', INDEX + 'Leute/'),
|
|
(u'Jugend', INDEX + 'Jugend/'),
|
|
(u'Beilage', INDEX + 'Beilage/')
|
|
]
|
|
|
|
def parse_index(self):
|
|
src = self.index_to_soup(self.INDEX)
|
|
id = ''
|
|
for itt in src.findAll('a', href=True):
|
|
if itt['href'].startswith('/app/epaper/textversion/inhalt/'):
|
|
id = itt['href'].rpartition('/inhalt/')[2]
|
|
totalfeeds = []
|
|
lfeeds = self.get_feeds()
|
|
for feedobj in lfeeds:
|
|
feedtitle, feedurl = feedobj
|
|
self.report_progress(0, ('Fetching feed') + ' %s...' %
|
|
(feedtitle if feedtitle else feedurl))
|
|
articles = []
|
|
soup = self.index_to_soup(feedurl + id)
|
|
tbl = soup.find(attrs={'class': 'szprintd'})
|
|
for item in tbl.findAll(name='td', attrs={'class': 'topthema'}):
|
|
atag = item.find(attrs={'class': 'Titel'}).a
|
|
ptag = item.find('p')
|
|
stag = ptag.find('script')
|
|
if stag:
|
|
stag.extract()
|
|
url = self.PREFIX + atag['href']
|
|
title = self.tag_to_string(atag)
|
|
description = self.tag_to_string(ptag)
|
|
articles.append({
|
|
'title': title, 'date': strftime(self.timefmt), 'url': url, 'description': description
|
|
})
|
|
totalfeeds.append((feedtitle, articles))
|
|
return totalfeeds
|