| 1 |
#!/usr/bin/env python |
| 2 |
# vim:fileencoding=utf-8 |
| 3 |
""" |
| 4 |
Fetch sueddeutsche.de |
| 5 |
""" |
| 6 |
|
| 7 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 8 |
|
| 9 |
|
| 10 |
class Sueddeutsche(BasicNewsRecipe): |
| 11 |
title = 'Süddeutsche Zeitung' |
| 12 |
__author__ = 'unkn0wn' |
| 13 |
oldest_article = 1.2 |
| 14 |
masthead_url = 'https://upload.wikimedia.org/wikipedia/commons/4/42/S%C3%BCddeutsche_Zeitung_Logo.svg' |
| 15 |
description = 'Deutschlands führende Nachrichtenseite. Alles Wichtige aus Politik, Wirtschaft, Sport, Kultur, Wissenschaft, Technik und mehr.' |
| 16 |
encoding = 'utf-8' |
| 17 |
language = 'de' |
| 18 |
remove_attributes = ['style', 'height', 'width'] |
| 19 |
ignore_duplicate_articles = {'url'} |
| 20 |
resolve_internal_links = True |
| 21 |
remove_empty_feeds = True |
| 22 |
no_javascript = True |
| 23 |
no_stylesheets = True |
| 24 |
|
| 25 |
recipe_specific_options = { |
| 26 |
'days': { |
| 27 |
'short': 'Oldest article to download from this news source. In days ', |
| 28 |
'long': 'For example, 0.5, gives you articles from the past 12 hours', |
| 29 |
'default': str(oldest_article), |
| 30 |
} |
| 31 |
} |
| 32 |
|
| 33 |
def __init__(self, *args, **kwargs): |
| 34 |
BasicNewsRecipe.__init__(self, *args, **kwargs) |
| 35 |
d = self.recipe_specific_options.get('days') |
| 36 |
if d and isinstance(d, str): |
| 37 |
self.oldest_article = float(d) |
| 38 |
|
| 39 |
extra_css = ''' |
| 40 |
[data-manual="overline"] { font-size:small; color: #404040; } |
| 41 |
[data-manual="date"], [data-manual^="headerImageCaption"], [data-manual="author"] { font-size:small; } |
| 42 |
[data-manual="teaserText"] { font-style:italic; color:#202020; } |
| 43 |
blockquote, em { color: #202020; } |
| 44 |
''' |
| 45 |
|
| 46 |
def get_cover_url(self): |
| 47 |
soup = self.index_to_soup('https://www.frontpages.com/germany-newspapers/') |
| 48 |
for img in soup.findAll('img', src=True): |
| 49 |
if 'suddeutsche-zeitung' in img['src']: |
| 50 |
return 'https://www.frontpages.com' + img['src'] |
| 51 |
|
| 52 |
keep_only_tags = [ |
| 53 |
dict(attrs={'data-manual': ['overline', 'title', 'date', 'headerImage', 'teaserText', 'author', 'body']}), |
| 54 |
] |
| 55 |
remove_tags = [dict(name=['svg', 'button', 'meta']), dict(attrs={'data-manual-remove': 'true'})] |
| 56 |
|
| 57 |
# https://www.sueddeutsche.de/service/updates-mit-rss-uebersicht-aller-rss-feeds-fuer-sz-de-sz-magazin-und-jetzt-de-1.393950 |
| 58 |
feeds = [ |
| 59 |
('Politik', 'http://rss.sueddeutsche.de/rss/Politik'), |
| 60 |
('Wirtschaft', 'http://rss.sueddeutsche.de/rss/Wirtschaft'), |
| 61 |
('Geld', 'http://rss.sueddeutsche.de/rss/Geld'), |
| 62 |
('Kultur', 'http://rss.sueddeutsche.de/rss/Kultur'), |
| 63 |
('Sport', 'http://rss.sueddeutsche.de/rss/Sport'), |
| 64 |
('Leben', 'http://rss.sueddeutsche.de/rss/Leben'), |
| 65 |
('Karriere', 'http://rss.sueddeutsche.de/rss/Karriere'), |
| 66 |
('Bildung', 'http://rss.sueddeutsche.de/rss/Bildung'), |
| 67 |
('Gesundheit', 'http://rss.sueddeutsche.de/rss/gesundheit'), |
| 68 |
('Stil', 'http://rss.sueddeutsche.de/rss/stil'), |
| 69 |
('München & Region', 'http://rss.sueddeutsche.de/rss/muenchen'), |
| 70 |
('Bayern', 'http://rss.sueddeutsche.de/rss/Bayern'), |
| 71 |
('Medien', 'http://rss.sueddeutsche.de/rss/Medien'), |
| 72 |
('Digital', 'http://rss.sueddeutsche.de/rss/Digital'), |
| 73 |
('Auto', 'http://rss.sueddeutsche.de/rss/Auto'), |
| 74 |
('Wissen', 'http://rss.sueddeutsche.de/rss/Wissen'), |
| 75 |
('Panorama', 'http://rss.sueddeutsche.de/rss/Panorama'), |
| 76 |
('Reise', 'http://rss.sueddeutsche.de/rss/Reise'), |
| 77 |
('Alles', 'https://rss.sueddeutsche.de/alles'), |
| 78 |
] |
| 79 |
|
| 80 |
def get_article_url(self, article): |
| 81 |
url = BasicNewsRecipe.get_article_url(self, article) |
| 82 |
url = url.split('?')[0] |
| 83 |
if 'sz-magazin.sueddeutsche.de/' not in url and 'artikel' not in url: |
| 84 |
return url |
| 85 |
|
| 86 |
def preprocess_html(self, soup): |
| 87 |
sub = soup.find(attrs={'data-manual': ['overline', 'date']}) |
| 88 |
if sub: |
| 89 |
sub.name = 'div' |
| 90 |
h1 = soup.find(attrs={'data-manual': 'title'}) |
| 91 |
if h1: |
| 92 |
h1.name = 'h1' |
| 93 |
for img in soup.findAll('img', attrs={'data-src': True}): |
| 94 |
img['src'] = img['data-src'] |
| 95 |
return soup |
| 96 |
|
| 97 |
def print_version(self, url): |
| 98 |
return 'https://och.to/unlock/' + url |