fixed and simplified tagesschau recipe:

* fixed typo in recipe name
* changed rss feed url to https version (previous one was linked to that one)
* added cover and masthead images
* added auto_cleanup
This commit is contained in:
mldytech 2025-04-22 12:35:39 +02:00
parent 6e4a865a25
commit 5fdd39189e
2 changed files with 23 additions and 43 deletions

View File

@ -0,0 +1,23 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe
class Tagesschau(BasicNewsRecipe):
title = 'Tagesschau'
description = 'Nachrichten der ARD'
publisher = 'ARD'
language = 'de'
version = 1
__author__ = 'mldytech'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
remove_javascript = True
use_embedded_content = False
encoding = 'utf-8'
auto_cleanup = True
masthead_url = 'https://upload.wikimedia.org/wikipedia/commons/thumb/3/3c/Tagesschau_Logo_2015.svg/1920px-Tagesschau_Logo_2015.svg.png'
cover_url = 'https://www.ardmediathek.de/img?imwidth=2560&url=https%3A%2F%2Fapi.ardmediathek.de%2Fimage-service%2Fimages%2Furn%3Aard%3Aimage%3A2e8eb9029b7f4684%3Fw%3D%7Bwidth%7D%26ch%3D657e32f8ff8614b2'
feeds = [('Tagesschau', 'https://www.tagesschau.de/infoservices/alle-meldungen-100~rss2.xml')]

View File

@ -1,43 +0,0 @@
import re
from calibre.web.feeds.news import BasicNewsRecipe
# History:
# 1: Base Version
# 2: Added rules for wdr.de, ndr.de, br-online.de
# 3: Added rules for rbb-online.de, boerse.ard.de, sportschau.de
# 4: New design of tagesschau.de implemented. Simplified.
# 5: Taken out the pictures.
class Tagesschau(BasicNewsRecipe):
title = 'Tagesschau'
description = 'Nachrichten der ARD'
publisher = 'ARD'
language = 'de'
version = 5
__author__ = 'Florian Andreas Pfaff, a.peter'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
remove_javascript = True
feeds = [('Tagesschau', 'http://www.tagesschau.de/xml/rss2')]
remove_tags = [
dict(attrs={'class': ['socialMedia', 'mediaLink', 'mediaInfo',
'linklist teaserImTeaser', 'modCon modConComments']}),
]
keep_only_tags = [
dict(name='div', attrs={
'class': ['section sectionZ', 'section sectionZ sectionArticle']}),
dict(name='div', attrs={'class': re.compile(r'.*containerArticle.*')})
]
def get_article_url(self, article):
ans = BasicNewsRecipe.get_article_url(self, article)
if '/multimedia/' in ans:
ans = None
return ans