Hi readers of Süddeutsche Zeitung,
I made some modifications to the recipe to pull in a cover and add "Thema des Tages" which was missing. Hope the cover retrieval holds up, will test over the next week.
MB
Code:
__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 = 'Süddeutsche Zeitung'
__author__ = 'Darko Miletic'
description = 'News from Germany. Access to paid content.'
publisher = '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_source = 'http://www.sueddeutsche.de/verlag'
PREFIX = 'http://www.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):
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','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 get_cover_url(self):
cover_source_soup = self.index_to_soup(self.cover_source)
preview_image_div = cover_source_soup.find(attrs={'class':'preview-image'})
return preview_image_div.div.img['src']
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