mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
104 lines
4.3 KiB
Plaintext
104 lines
4.3 KiB
Plaintext
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
www.sueddeutsche.de/sz/
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from calibre import strftime
|
|
|
|
class SueddeutcheZeitung(BasicNewsRecipe):
|
|
title = 'Sueddeutche Zeitung'
|
|
__author__ = 'Darko Miletic'
|
|
description = 'News from Germany. Access to paid content.'
|
|
publisher = 'Sueddeutche Zeitung'
|
|
category = 'news, politics, Germany'
|
|
no_stylesheets = True
|
|
oldest_article = 2
|
|
encoding = 'cp1252'
|
|
needs_subscription = True
|
|
remove_empty_feeds = True
|
|
delay = 2
|
|
PREFIX = 'http://www.sueddeutsche.de'
|
|
INDEX = PREFIX + '/app/epaper/textversion/'
|
|
use_embedded_content = False
|
|
masthead_url = 'http://pix.sueddeutsche.de/img/layout/header/logo.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']
|
|
|
|
def get_browser(self):
|
|
br = BasicNewsRecipe.get_browser()
|
|
if self.username is not None and self.password is not None:
|
|
br.open(self.INDEX)
|
|
br.select_form(name='lbox')
|
|
br['login_name' ] = self.username
|
|
br['login_passwort'] = self.password
|
|
br.submit()
|
|
return br
|
|
|
|
remove_tags =[
|
|
dict(attrs={'class':'hidePrint'})
|
|
,dict(name=['link','object','embed','base','iframe'])
|
|
]
|
|
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'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/' )
|
|
]
|
|
|
|
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
|