calibre/recipes/focus_de.recipe
2024-03-30 13:03:29 +05:30

63 lines
2.0 KiB
Python

'''
focus.de
'''
from calibre.web.feeds.news import BasicNewsRecipe, classes
class AdvancedUserRecipe1305567197(BasicNewsRecipe):
title = 'Focus (DE)'
__author__ = 'unkn0wn'
description = 'RSS-Feeds von Focus.de, best downloaded at the end of the week.'
language = 'de'
oldest_article = 7
max_articles_per_feed = 25
no_stylesheets = True
remove_javascript = True
use_embedded_content = False
remove_empty_feeds = True
ignore_duplicate_articles = {'title', 'url'}
remove_attributes = ['width', 'height', 'style']
masthead_url = 'https://www.focus-magazin.de/img/Focus_Logo.jpg'
extra_css = '''
.posMarker_oh { font-size:small; color:#404040; }
.posMarker_he { font-size:large; font-weight:bold; }
.leadIn { font-style:italic; color:#202020; }
.caption { text-align:center; font-size:small; }
.authorMeta, .displayDate { font-size:small; }
'''
def get_cover_url(self):
soup = self.index_to_soup('https://www.focus-magazin.de/')
return soup.find('img', attrs={'class':'main-cover'})['src']
feeds = [
('Politik', 'http://rss.focus.de/politik/'),
('Finanzen', 'http://rss.focus.de/finanzen/'),
('Gesundheit', 'http://rss.focus.de/gesundheit/'),
('Panorama', 'http://rss.focus.de/panorama/'),
('Digital', 'http://rss.focus.de/digital/'),
('Reisen', 'http://rss.focus.de/reisen/'),
('Andere', 'http://rss.focus.de')
]
keep_only_tags = [
classes('articleHead articleContent')
]
remove_tags = [
dict(name=['svg', 'script']),
classes('socFbLikeShare video social_frame'),
dict(attrs={'id': 'article-social-holder'})
]
def preprocess_html(self, soup):
if h1 := soup.find(attrs={'class':'articleIdentH1'}):
h1.name = 'h1'
if he := soup.find(**classes('posMarker_he')):
he.name = 'div'
for img in soup.findAll('img', attrs={'data-src':True}):
img['src'] = img['data-src']
return soup