From 5fdd39189e7be9423691b176decf3a619444fa7c Mon Sep 17 00:00:00 2001 From: mldytech Date: Tue, 22 Apr 2025 12:35:39 +0200 Subject: [PATCH] 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 --- recipes/tagesschau_de.recipe | 23 +++++++++++++++++++ recipes/taggeschau_de.recipe | 43 ------------------------------------ 2 files changed, 23 insertions(+), 43 deletions(-) create mode 100644 recipes/tagesschau_de.recipe delete mode 100644 recipes/taggeschau_de.recipe diff --git a/recipes/tagesschau_de.recipe b/recipes/tagesschau_de.recipe new file mode 100644 index 0000000000..ef9b02f3b6 --- /dev/null +++ b/recipes/tagesschau_de.recipe @@ -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')] \ No newline at end of file diff --git a/recipes/taggeschau_de.recipe b/recipes/taggeschau_de.recipe deleted file mode 100644 index 5dbacc2bfc..0000000000 --- a/recipes/taggeschau_de.recipe +++ /dev/null @@ -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