| 1 |
""" |
| 2 |
focus.de |
| 3 |
""" |
| 4 |
|
| 5 |
from calibre.web.feeds.news import BasicNewsRecipe, classes |
| 6 |
|
| 7 |
|
| 8 |
class AdvancedUserRecipe1305567197(BasicNewsRecipe): |
| 9 |
title = 'Focus (DE)' |
| 10 |
__author__ = 'unkn0wn' |
| 11 |
description = 'RSS-Feeds von Focus.de, best downloaded at the end of the week.' |
| 12 |
language = 'de' |
| 13 |
|
| 14 |
oldest_article = 7 |
| 15 |
max_articles_per_feed = 25 |
| 16 |
no_stylesheets = True |
| 17 |
remove_javascript = True |
| 18 |
use_embedded_content = False |
| 19 |
remove_empty_feeds = True |
| 20 |
ignore_duplicate_articles = {'title', 'url'} |
| 21 |
remove_attributes = ['width', 'height', 'style'] |
| 22 |
masthead_url = 'https://www.focus-magazin.de/img/Focus_Logo.jpg' |
| 23 |
extra_css = ''' |
| 24 |
.posMarker_oh { font-size:small; color:#404040; } |
| 25 |
.posMarker_he { font-size:large; font-weight:bold; } |
| 26 |
.leadIn { font-style:italic; color:#202020; } |
| 27 |
.caption { text-align:center; font-size:small; } |
| 28 |
.authorMeta, .displayDate { font-size:small; } |
| 29 |
''' |
| 30 |
|
| 31 |
def get_cover_url(self): |
| 32 |
soup = self.index_to_soup('https://www.focus-magazin.de/') |
| 33 |
return soup.find('img', attrs={'class': 'main-cover'})['src'] |
| 34 |
|
| 35 |
feeds = [ |
| 36 |
('Politik', 'http://rss.focus.de/politik/'), |
| 37 |
('Finanzen', 'http://rss.focus.de/finanzen/'), |
| 38 |
('Gesundheit', 'http://rss.focus.de/gesundheit/'), |
| 39 |
('Panorama', 'http://rss.focus.de/panorama/'), |
| 40 |
('Digital', 'http://rss.focus.de/digital/'), |
| 41 |
('Reisen', 'http://rss.focus.de/reisen/'), |
| 42 |
('Andere', 'http://rss.focus.de'), |
| 43 |
] |
| 44 |
|
| 45 |
keep_only_tags = [classes('articleHead articleContent')] |
| 46 |
|
| 47 |
remove_tags = [dict(name=['svg', 'script']), classes('socFbLikeShare video social_frame'), dict(attrs={'id': 'article-social-holder'})] |
| 48 |
|
| 49 |
def preprocess_html(self, soup): |
| 50 |
if h1 := soup.find(attrs={'class': 'articleIdentH1'}): |
| 51 |
h1.name = 'h1' |
| 52 |
if he := soup.find(**classes('posMarker_he')): |
| 53 |
he.name = 'div' |
| 54 |
for img in soup.findAll('img', attrs={'data-src': True}): |
| 55 |
img['src'] = img['data-src'] |
| 56 |
return soup |