Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Spektrum der Wissenschaft

Browse Source
This commit is contained in:
Kovid Goyal 2018-02-27 23:13:16 +05:30
parent 700f61df36
commit 076bbc7dc7
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 28 additions and 40 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

68
recipes/spektrum.recipe
View File

@ -1,7 +1,7 @@
## ##
# Written: October 2012 (new coding) # Written: October 2012 (new coding)
# Version: 9.0 # Version: 9.0
# Last update: 2015-03-12 # Last update: 2018-02-22
## ##
__license__ = 'GPL v3' __license__ = 'GPL v3'
@ -9,12 +9,21 @@ __copyright__ = ''
''' '''
Fetch RSS-Feeds spektrum.de Fetch RSS-Feeds spektrum.de
''' '''
def classes(classes):
q = frozenset(classes.split(' '))
return dict(
attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}
)
from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.web.feeds.recipes import BasicNewsRecipe
class AdvancedUserRecipe1303841067(BasicNewsRecipe): class AdvancedUserRecipe1303841067(BasicNewsRecipe):
title = u'Spektrum der Wissenschaft' title = u'Spektrum der Wissenschaft'
__author__ = 'Armin Geller, Bratzzo, Rainer Zenz' # Update AGE 2014-02-25 __author__ = 'Armin Geller, Bratzzo, Rainer Zenz' # Update AGE 2014-02-25, UDe 2018-02-22
description = u'German online portal of Spektrum der Wissenschaft' description = u'German online portal of Spektrum der Wissenschaft'
publisher = 'Spektrum der Wissenschaft Verlagsgesellschaft mbH' publisher = 'Spektrum der Wissenschaft Verlagsgesellschaft mbH'
category = 'science news, Germany' category = 'science news, Germany'
@ -24,52 +33,31 @@ class AdvancedUserRecipe1303841067(BasicNewsRecipe):
remove_javascript = True remove_javascript = True
remove_empty_feeds = True remove_empty_feeds = True
language = 'de' language = 'de'
encoding = 'utf8' # AGe 2015-03-13 new, old encoding'cp1252' encoding = 'utf8'
# recursions = 0 # AGe 2014-08-21 new ignore_duplicate_articles = {'title'}
# Cover from Rainer Zenz cover_url = 'https://www.spektrum.de/fm/862/thumbnails/Cover_SdW01-2018.jpg.2786617.jpg'
# AGE 2015-03-12 new cover location
cover_url = 'http://www58.zippyshare.com/scaled/VISHzqJj/file.html'
masthead_url = 'http://www.spektrum.de/fm/861/spektrum.de.png' masthead_url = 'http://www.spektrum.de/fm/861/spektrum.de.png'
# AGE 2014-02-25 add .textbox-wide
extra_css = '''
h1 {font-size: 1.6em; text-align: left}
h2 {font-size: 1em; font-style: italic; font-weight: normal}
h3 {font-size: 1.3em;text-align: left}
h4, h5, h6, .heading, .hgroup {font-size: 1em;text-align: left}
.textbox-wide {font-size: 1.3em; font-style: italic}
'''
feeds = [ feeds = [
(u'Spektrum.de', u'http://www.spektrum.de/alias/rss/spektrum-de-rss-feed/996406'), (
(u'Spektrum der Wissenschaft', u'Spektrum.de',
u'http://www.spektrum.de/alias/rss/spektrum-der-wissenschaft-rss-feed/982623'), u'http://www.spektrum.de/alias/rss/spektrum-de-rss-feed/996406'
(u'Gehirn & Geist', ),
u'http://www.spektrum.de/alias/rss/gehirn-geist-rss-feed/982626'), # (u'Spektrum der Wissenschaft', u'http://www.spektrum.de/alias/rss/spektrum-der-wissenschaft-rss-feed/982623'),
(u'Sterne und Weltraum', # (u'Gehirn & Geist', u'http://www.spektrum.de/alias/rss/gehirn-geist-rss-feed/982626'),
u'http://www.spektrum.de/alias/rss/sterne-und-weltraum-rss-feed/865248'), (
# AGe 2014-08-21 available but empty u'Sterne und Weltraum',
(u'Pressemitteilungen', u'http://www.spektrum.de/alias/rss/sterne-und-weltraum-rss-feed/865248'
u'http://www.spektrum.de/alias/rss/pressemitteilungen/995265'), ),
# AGe 2014-08-21 new # (u'Meistgelesene Artikel',u'http://www.spektrum.de/alias/rss/spektrum-de-meistgelesene-artikel/1224665'), # AGe 2014-08-21 new
(u'Meistgelesene Artikel',
u'http://www.spektrum.de/alias/rss/spektrum-de-meistgelesene-artikel/1224665'),
] ]
keep_only_tags = [ keep_only_tags = [
dict(name='div', attrs={ dict(name='article', attrs={'class': 'content'}),
'class': 'border-h clearfix article-top relcontainer'}),
dict(name='article', attrs={'class': 'clearfix'}),
] ]
remove_tags = [ remove_tags = [
dict(name='aside', attrs={ classes('hide-for-print content__meta content__author content__video'),
'class': ['bilderrahmenlinks', 'bilderrahmenrechts']}), # AGE 2014-08-29 dict(name='div', attrs={'role': 'navigation'}),
# AGE 2014-08-29
dict(name='div', attrs={'class': 'textbox-wide clearfix'}),
# AGe 2015-03-13
dict(name='span', attrs={
'class': ['no-display', 'sprite-a sprite-lupe']}),
] ]