Set Cover Url

Fix Login (httperror_seek_wrapper: HTTP Error 404: Not Found)
This commit is contained in:
lala-rob 2014-12-18 09:55:17 +01:00
parent ea222f75be
commit 54553d8a21
2 changed files with 6 additions and 18 deletions

View File

@ -4,6 +4,7 @@ __copyright__ = '2012, 2013 Andreas Zeiser <andreas.zeiser@web.de>'
szmobil.sueddeutsche.de/ szmobil.sueddeutsche.de/
''' '''
# History # History
# 2014.12.18 Fixing URL set Cover by lala-rob (web@lala-rob.de)
# 2014.10.06 Fixing Login URL and Article URL by lala-rob (web@lala-rob.de) # 2014.10.06 Fixing Login URL and Article URL by lala-rob (web@lala-rob.de)
# #
# 2013.01.09 Fixed bugs in article titles containing "strong" and # 2013.01.09 Fixed bugs in article titles containing "strong" and
@ -19,17 +20,17 @@ class SZmobil(BasicNewsRecipe):
__author__ = u'Andreas Zeiser' __author__ = u'Andreas Zeiser'
description = u'Nachrichten aus Deutschland. Zugriff auf kostenpflichtiges Abo SZ mobil.' description = u'Nachrichten aus Deutschland. Zugriff auf kostenpflichtiges Abo SZ mobil.'
publisher = u'Sueddeutsche Zeitung' publisher = u'Sueddeutsche Zeitung'
masthead_url = 'http://pix.sueddeutsche.de/img/layout/header/SZ_solo288x31.gif'
language = u'de' language = u'de'
publication_type = u'newspaper' publication_type = u'newspaper'
category = u'news, politics, Germany' category = u'news, politics, Germany'
cover_url = 'http://upload.wikimedia.org/wikipedia/commons/d/d3/Suddeutsche_Zeitung_090520_M.jpg'
no_stylesheets = True no_stylesheets = True
oldest_article = 2 oldest_article = 2
encoding = 'iso-8859-1' encoding = 'iso-8859-1'
needs_subscription = True needs_subscription = True
remove_empty_feeds = True remove_empty_feeds = True
delay = 1 delay = 1
cover_source = 'http://www.sueddeutsche.de/verlag'
# if you want to get rid of the date on the title page use # if you want to get rid of the date on the title page use
# timefmt = '' # timefmt = ''
@ -38,25 +39,17 @@ class SZmobil(BasicNewsRecipe):
root_url ='http://epaper.sueddeutsche.de/app/service/epaper-mobil/' root_url ='http://epaper.sueddeutsche.de/app/service/epaper-mobil/'
keep_only_tags = [dict(name='div', attrs={'class':'article'})] keep_only_tags = [dict(name='div', attrs={'class':'article'})]
def get_cover_url(self):
src = self.index_to_soup(self.cover_source)
image_url = src.find(attrs={'class':'preview-image'})
return image_url.div.img['src']
def get_browser(self): def get_browser(self):
browser = BasicNewsRecipe.get_browser(self) browser = BasicNewsRecipe.get_browser(self)
# Login via fetching of Streiflicht -> Fill out login request # Login via fetching of Streiflicht -> Fill out login request
url = 'https://id.sueddeutsche.de/login' url = 'https://id.sueddeutsche.de/login'
url2 = 'https://id.sueddeutsche.de/login/ticket?redirect_uri=http%3A%2F%2Fepaper.sueddeutsche.de%2Fapp%2Fservice%2Fepaper-mobil%2Flanding.php%3Fid%3Dstreif%26etag%3D1&service_id=epapermobile'
browser.open(url) browser.open(url)
browser.select_form(nr=0) # to select the first form browser.select_form(nr=0) # to select the first form
browser['login'] = self.username browser['login'] = self.username
browser['password'] = self.password browser['password'] = self.password
browser.submit() browser.submit()
browser.open(url2)
return browser return browser
def parse_index(self): def parse_index(self):

View File

@ -1,11 +1,11 @@
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
__license__ = 'GPL v3' __license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>' __copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
''' '''
www.sueddeutsche.de/sz/ www.sueddeutsche.de/sz/
''' '''
# History # History
# 2014.10.02 Fixed url Problem von 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.web.feeds.news import BasicNewsRecipe
from calibre import strftime from calibre import strftime
@ -22,7 +22,7 @@ class SueddeutcheZeitung(BasicNewsRecipe):
needs_subscription = True needs_subscription = True
remove_empty_feeds = True remove_empty_feeds = True
delay = 1 delay = 1
cover_source = 'http://www.sueddeutsche.de/verlag' cover_url = 'http://upload.wikimedia.org/wikipedia/commons/d/d3/Suddeutsche_Zeitung_090520_M.jpg'
PREFIX = 'http://epaper.sueddeutsche.de' PREFIX = 'http://epaper.sueddeutsche.de'
INDEX = PREFIX + '/app/epaper/textversion/' INDEX = PREFIX + '/app/epaper/textversion/'
use_embedded_content = False use_embedded_content = False
@ -94,11 +94,6 @@ class SueddeutcheZeitung(BasicNewsRecipe):
,(u'Beilage' , INDEX + 'Beilage/' ) ,(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): def parse_index(self):
src = self.index_to_soup(self.INDEX) src = self.index_to_soup(self.INDEX)
id = '' id = ''