calibre/recipes/tagespost.recipe
unkn0w7n 6c9b8d286d Update tagespost.recipe
Included .datetime and .autor-name classes in the extra_css.
2025-08-11 18:47:50 +05:30

77 lines
2.4 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
'''
Recipe for Die Tagespost
'''
from calibre.web.feeds.news import BasicNewsRecipe, classes
class Tagespost(BasicNewsRecipe):
title = 'Tagespost'
language = 'de'
__author__ = 'unkn0wn'
description = (
'Die Tagespost trägt den Untertitel Katholische Wochenzeitung für Politik, Gesellschaft'
' und Kultur und ist eine überregionale, wöchentlich im Johann Wilhelm Naumann Verlag '
'in Würzburg erscheinende Zeitung.'
)
oldest_article = 2
encoding = 'utf-8'
ignore_duplicate_articles = {'url'}
masthead_url = 'https://www.die-tagespost.de/design2020/images/tp_logo_small.webp'
remove_javascript = True
keep_only_tags = [
classes('topline headline description datetime autor-name article_main')
]
remove_tags = [
dict(name=['source', 'svg', 'aside', 'clearfix', 'footer']),
classes('content-box extras jwnIconTeaser behindWall'),
]
remove_tags_after = [classes('abbinder-text')]
no_stylesheets = True
use_embedded_content = False
remove_attributes = ['style', 'height', 'width']
recipe_specific_options = {
'days': {
'short': 'Oldest article to download from this news source. In days ',
'long': 'For example, 0.5, gives you articles from the past 12 hours',
'default': str(oldest_article),
},
}
def __init__(self, *args, **kwargs):
BasicNewsRecipe.__init__(self, *args, **kwargs)
d = self.recipe_specific_options.get('days')
if d and isinstance(d, str):
self.oldest_article = float(d)
def get_cover_url(self):
soup = self.index_to_soup('https://www.ikiosk.de/shop/epaper/die-tagespost.html')
return soup.find('a', attrs={'class': 'preview-cover'})['href']
feeds = [
(
'Tagespost',
'https://www.die-tagespost.de/storage/rss/rss/die-tagespost-komplett.xml',
),
]
extra_css = '''
.abbinder-text,
.calibre-nuked-tag-figcaption,
.datetime,
.autor-name,
.topline {
font-size:small;
}
.description { font-style: italic; }
'''
def preprocess_html(self, soup):
desc = soup.find(**classes('description'))
if desc:
desc.name = 'p'
for h2 in soup.findAll(['h2', 'h3']):
h2.name = 'h4'
return soup