| 1 |
#!/usr/bin/env python |
| 2 |
|
| 3 |
__license__ = 'GPL v3' |
| 4 |
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>' |
| 5 |
''' |
| 6 |
www.tijd.be |
| 7 |
''' |
| 8 |
from calibre.ebooks.BeautifulSoup import Tag |
| 9 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 10 |
|
| 11 |
|
| 12 |
def new_tag(soup, name, attrs=()): |
| 13 |
impl = getattr(soup, 'new_tag', None) |
| 14 |
if impl is not None: |
| 15 |
return impl(name, attrs=dict(attrs)) |
| 16 |
return Tag(soup, name, attrs=attrs or None) |
| 17 |
|
| 18 |
|
| 19 |
class DeTijd(BasicNewsRecipe): |
| 20 |
title = 'De Tijd' |
| 21 |
__author__ = 'Darko Miletic' |
| 22 |
description = 'News from Belgium in Dutch' |
| 23 |
publisher = 'De Tijd' |
| 24 |
category = 'news, politics, Belgium' |
| 25 |
oldest_article = 2 |
| 26 |
max_articles_per_feed = 100 |
| 27 |
no_stylesheets = True |
| 28 |
use_embedded_content = False |
| 29 |
encoding = 'utf-8' |
| 30 |
language = 'nl_BE' |
| 31 |
|
| 32 |
lang = 'nl-BE' |
| 33 |
direction = 'ltr' |
| 34 |
|
| 35 |
keep_only_tags = [ |
| 36 |
dict(name='div', attrs={'id': 'lcol'}), |
| 37 |
dict(name='div', attrs={'class': 'l-main-container-article__asset-container'}), |
| 38 |
dict(name='div', attrs={'class': 'l-main-container-article__body clearfix highlightable '}), |
| 39 |
dict(name='div', attrs={'class': 'l-main-container-article__intro highlightable '}), |
| 40 |
dict(name='div', attrs={'class': 'l-main-container-article__sidebar-inline'}), |
| 41 |
dict(name='div', attrs={'class': 'l-main-container-article__title '}), |
| 42 |
] |
| 43 |
remove_tags = [dict(name=['embed', 'object']), dict(name='div', attrs={'id': 'art_reactwrap'})] |
| 44 |
remove_tags_after = dict(name='div', attrs={'id': 'art_author'}) |
| 45 |
|
| 46 |
feeds = [ |
| 47 |
('Volledig nieuwsaanbod', 'https://www.tijd.be/rss/nieuws.xml'), |
| 48 |
('Ondernemen', 'https://www.tijd.be/rss/ondernemen.xml'), |
| 49 |
('Politiek en Economie', 'https://www.tijd.be/rss/politiek.xml'), |
| 50 |
('Markten', 'https://www.tijd.be/rss/markten_live.xml'), |
| 51 |
('Opinie', 'https://www.tijd.be/rss/opinie.xml'), |
| 52 |
('Cultuur', 'https://www.tijd.be/rss/cultuur.xml'), |
| 53 |
('Netto', 'https://www.tijd.be/rss/netto.xml'), |
| 54 |
('Sabato', 'https://www.tijd.be/rss/sabato.xml'), |
| 55 |
] |
| 56 |
|
| 57 |
def preprocess_html(self, soup): |
| 58 |
del soup.body['onload'] |
| 59 |
for item in soup.findAll(style=True): |
| 60 |
del item['style'] |
| 61 |
soup.html['lang'] = self.lang |
| 62 |
soup.html['dir'] = self.direction |
| 63 |
mlang = new_tag(soup, 'meta', [('http-equiv', 'Content-Language'), ('content', self.lang)]) |
| 64 |
mcharset = new_tag(soup, 'meta', [('http-equiv', 'Content-Type'), ('content', 'text/html; charset=utf-8')]) |
| 65 |
soup.head.insert(0, mlang) |
| 66 |
soup.head.insert(1, mcharset) |
| 67 |
return soup |