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.de

Browse Source
This commit is contained in:
Kovid Goyal 2025-02-01 09:23:29 +05:30
parent d9845f1f45
commit 9920446eb8
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 37 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

60
recipes/spektrum.recipe
View File

@ -1,9 +1,9 @@
#!/usr/bin/env python #!/usr/bin/env python
# vim:fileencoding=utf-8 # vim:fileencoding=utf-8
## ##
# Written: October 2012 (new coding) ## Written: October 2012 (new coding)
# Version: 9.0 ## Version: 10.0
# Last update: 2018-02-22 ## Last update: 2025-01-15
## ##
from __future__ import absolute_import, division, print_function, unicode_literals from __future__ import absolute_import, division, print_function, unicode_literals
@ -31,7 +31,7 @@ class Spektrum(BasicNewsRecipe):
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'
oldest_article = 7 oldest_article = 3
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
remove_javascript = True remove_javascript = True
@ -39,26 +39,18 @@ class Spektrum(BasicNewsRecipe):
language = 'de' language = 'de'
encoding = 'utf8' encoding = 'utf8'
ignore_duplicate_articles = {'title'} ignore_duplicate_articles = {'title'}
scale_news_images_to_device = True
compress_news_images = True
cover_url = 'https://www.spektrum.de/js_css/sde/assets/img/svg/sdw_dark.svg' cover_url = 'https://upload.wikimedia.org/wikipedia/commons/thumb/1/1d/Spektrum_der_Wissenschaft_Logo_seit_2016.svg/640px-Spektrum_der_Wissenschaft_Logo_seit_2016.svg.png'
masthead_url = 'http://www.spektrum.de/fm/861/spektrum.de.png' masthead_url = 'http://www.spektrum.de/fm/861/spektrum.de.png'
feeds = [ feeds = [
( (u'Spektrum.de', u'http://www.spektrum.de/alias/rss/spektrum-de-rss-feed/996406'),
u'Spektrum.de',
u'http://www.spektrum.de/alias/rss/spektrum-de-rss-feed/996406'
),
# (u'Spektrum der Wissenschaft', u'http://www.spektrum.de/alias/rss/spektrum-der-wissenschaft-rss-feed/982623'),
# (u'Gehirn & Geist', u'http://www.spektrum.de/alias/rss/gehirn-geist-rss-feed/982626'),
(
u'Sterne und Weltraum',
u'http://www.spektrum.de/alias/rss/sterne-und-weltraum-rss-feed/865248'
),
# (u'Meistgelesene Artikel',u'http://www.spektrum.de/alias/rss/spektrum-de-meistgelesene-artikel/1224665'), # AGe 2014-08-21 new
] ]
keep_only_tags = [ keep_only_tags = [
dict(name='article', attrs={'class': 'content'}), dict(name='article', attrs={'class':'content'}),classes('callout-box')
] ]
remove_tags = [ remove_tags = [
@ -71,6 +63,15 @@ class Spektrum(BasicNewsRecipe):
] ]
def parse_feeds(self): def parse_feeds(self):
unwanted_article_types = [
'podcast',
'video',
'raetsel',
'leseprobe',
# 'kolumne',
# 'rezension',
# 'news',
]
# Call parent's method. # Call parent's method.
feeds = BasicNewsRecipe.parse_feeds(self) feeds = BasicNewsRecipe.parse_feeds(self)
# Loop through all feeds. # Loop through all feeds.
@ -79,16 +80,23 @@ class Spektrum(BasicNewsRecipe):
for article in feed.articles[:]: for article in feed.articles[:]:
if 'VIDEO' in article.title: if 'VIDEO' in article.title:
feed.articles.remove(article) feed.articles.remove(article)
# Remove articles with 'video','podcast' or 'rezension' in the url. continue
elif 'podcast' in article.url: # Remove articles with '..' in the url.
feed.articles.remove(article) for keyword in unwanted_article_types:
elif 'video' in article.url: if keyword in article.url:
feed.articles.remove(article)
elif 'rezension' in article.url:
feed.articles.remove(article) feed.articles.remove(article)
continue
return feeds return feeds
def preprocess_html(self, soup, *a): def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-src': True}): for noscript in soup.findAll('noscript'):
img['src'] = img['data-src'] noscript.name = 'div'
return soup return soup
def preprocess_raw_html(self, raw, url):
# remove articles requiring login and advertisements
unwantedtag = 'content pw-premium'
if unwantedtag in raw:
self.abort_article('Skipping unwanted article with tag:' + unwantedtag)
return raw