Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 18:24:30 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Spektrum der Wissenschaft

Browse Source
This commit is contained in:
Kovid Goyal 2020-03-28 08:55:04 +05:30
parent d8fd9b8bc6
commit 2e9259fc3b
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 27 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
recipes/spektrum.recipe
View File

@ -1,10 +1,12 @@
#!/usr/bin/env python2
##!/usr/bin/env python2
# vim:fileencoding=utf-8
##
# Written: October 2012 (new coding)
# Version: 9.0
# Last update: 2019-02-02
# Last update: 2018-02-22
##
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3'
__copyright__ = ''
'''
@ -24,7 +26,7 @@ from calibre.web.feeds.recipes import BasicNewsRecipe
class Spektrum(BasicNewsRecipe):
title = u'Spektrum der Wissenschaft'
__author__ = 'Armin Geller, Bratzzo, Rainer Zenz' # Update AGE 2014-02-25, UDe 2019-02-02
__author__ = 'Armin Geller, Bratzzo, Rainer Zenz, update epubli'
description = u'German online portal of Spektrum der Wissenschaft'
publisher = 'Spektrum der Wissenschaft Verlagsgesellschaft mbH'
category = 'science news, Germany'
@ -59,11 +61,32 @@ class Spektrum(BasicNewsRecipe):
]
remove_tags = [
classes('hide-for-print content__meta content__author content__video'),
classes('hide-for-print'),
classes('content__meta'),
classes('content__author'),
classes('content__video'),
dict(name='div', attrs={'role': 'navigation'}),
dict(name='span', attrs={'class': 'sr-only'}),
]
def parse_feeds(self):
# Call parent's method.
feeds = BasicNewsRecipe.parse_feeds(self)
# Loop through all feeds.
for feed in feeds:
# Loop through all articles in feed.
for article in feed.articles[:]:
if 'VIDEO' in article.title:
feed.articles.remove(article)
# Remove articles with 'video','podcast' or 'rezension' in the url.
elif 'podcast' in article.url:
feed.articles.remove(article)
elif 'video' in article.url:
feed.articles.remove(article)
elif 'rezension' in article.url:
feed.articles.remove(article)
return feeds
def preprocess_html(self, soup, *a):
for img in soup.findAll('img', attrs={'data-src': True}):
img['src'] = img['data-src']