mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
89 lines
3.3 KiB
Python
89 lines
3.3 KiB
Python
#!/usr/bin/env python
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
www.tijd.be
|
|
'''
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from calibre.ebooks.BeautifulSoup import Tag
|
|
|
|
|
|
def new_tag(soup, name, attrs=()):
|
|
impl = getattr(soup, 'new_tag', None)
|
|
if impl is not None:
|
|
return impl(name, attrs=dict(attrs))
|
|
return Tag(soup, name, attrs=attrs or None)
|
|
|
|
|
|
class DeTijd(BasicNewsRecipe):
|
|
title = 'De Tijd'
|
|
__author__ = 'Darko Miletic'
|
|
description = 'News from Belgium in Dutch'
|
|
publisher = 'De Tijd'
|
|
category = 'news, politics, Belgium'
|
|
oldest_article = 2
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
use_embedded_content = False
|
|
encoding = 'utf-8'
|
|
language = 'nl_BE'
|
|
|
|
lang = 'nl-BE'
|
|
direction = 'ltr'
|
|
|
|
keep_only_tags = [
|
|
dict(name='div', attrs={'id': 'lcol'}), dict(
|
|
name='div', attrs={'class': 'l-main-container-article__asset-container'}
|
|
), dict(
|
|
name='div',
|
|
attrs={
|
|
'class': 'l-main-container-article__body clearfix highlightable '
|
|
}
|
|
), dict(
|
|
name='div',
|
|
attrs={'class': 'l-main-container-article__intro highlightable '}
|
|
), dict(
|
|
name='div', attrs={'class': 'l-main-container-article__sidebar-inline'}
|
|
), dict(name='div', attrs={'class': 'l-main-container-article__title '})
|
|
]
|
|
remove_tags = [
|
|
dict(name=['embed', 'object']),
|
|
dict(name='div', attrs={'id': 'art_reactwrap'})
|
|
]
|
|
remove_tags_after = dict(name='div', attrs={'id': 'art_author'})
|
|
|
|
feeds = [(u'Volledig nieuwsaanbod', u'http://www.tijd.be/rss/nieuws.xml'),
|
|
(u'Markten', u'http://www.tijd.be/rss/markten.xml'),
|
|
(u'Ondernemingen', u'http://www.tijd.be/rss/ondernemingen.xml'),
|
|
(u'Chemie-Farma', u'http://www.tijd.be/rss/chemie_farma.xml'),
|
|
(u'Consumptie', u'http://www.tijd.be/rss/consumptie.xml'),
|
|
(u'Diensten', u'http://www.tijd.be/rss/diensten.xml'),
|
|
(u'Energie', u'http://www.tijd.be/rss/energie.xml'),
|
|
(u'Financen', u'http://www.tijd.be/rss/financien.xml'),
|
|
(u'Industrie', u'http://www.tijd.be/rss/industrie.xml'),
|
|
(u'Media', u'http://www.tijd.be/rss/media_telecom.xml'),
|
|
(u'Technologie', u'http://www.tijd.be/rss/technologie.xml'),
|
|
(u'Economie & Financien', u'http://www.tijd.be/rss/economie.xml'),
|
|
(u'Binnenland', u'http://www.tijd.be/rss/binnenland.xml'),
|
|
(u'Buitenland', u'http://www.tijd.be/rss/buitenland.xml'),
|
|
(u'De wijde wereld', u'http://www.tijd.be/rss/cultuur.xml')]
|
|
|
|
def preprocess_html(self, soup):
|
|
del soup.body['onload']
|
|
for item in soup.findAll(style=True):
|
|
del item['style']
|
|
soup.html['lang'] = self.lang
|
|
soup.html['dir'] = self.direction
|
|
mlang = new_tag(
|
|
soup, 'meta', [("http-equiv", "Content-Language"),
|
|
("content", self.lang)]
|
|
)
|
|
mcharset = new_tag(
|
|
soup, 'meta', [("http-equiv", "Content-Type"),
|
|
("content", "text/html; charset=utf-8")]
|
|
)
|
|
soup.head.insert(0, mlang)
|
|
soup.head.insert(1, mcharset)
|
|
return soup
|