mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
80 lines
2.6 KiB
Plaintext
80 lines
2.6 KiB
Plaintext
__license__ = 'GPL v3'
|
|
__copyright__ = '2010-2012, Louis Gesbert <meta at antislash dot info>'
|
|
'''
|
|
Rue89
|
|
'''
|
|
|
|
__author__ = '2010-2012, Louis Gesbert <meta at antislash dot info>'
|
|
|
|
import re
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class Rue89(BasicNewsRecipe):
|
|
title = 'Rue89'
|
|
__author__ = 'Louis Gesbert'
|
|
description = 'Popular free french news website'
|
|
title = u'Rue89'
|
|
language = 'fr'
|
|
oldest_article = 7
|
|
max_articles_per_feed = 50
|
|
|
|
use_embedded_content = False
|
|
|
|
# From http://www.rue89.com/les-flux-rss-de-rue89
|
|
feeds = [
|
|
(u'La Une', u'http://www.rue89.com/feed'),
|
|
# Other feeds disabled, 'La Une' seems to include them all
|
|
# (u'Rue69', u'http://www.rue89.com/rue69/feed'),
|
|
# (u'Eco', u'http://www.rue89.com/rue89-eco/feed'),
|
|
# (u'Planète', u'http://www.rue89.com/rue89-planete/feed'),
|
|
# (u'Sport', u'http://www.rue89.com/rue89-sport/feed'),
|
|
# (u'Culture', u'http://www.rue89.com/culture/feed'),
|
|
# (u'Hi-tech', u'http://www.rue89.com/hi-tech/feed'),
|
|
# (u'Media', u'http://www.rue89.com/medias/feed'),
|
|
# (u'Monde', u'http://www.rue89.com/monde/feed'),
|
|
# (u'Politique', u'http://www.rue89.com/politique/feed'),
|
|
# (u'Societe', u'http://www.rue89.com/societe/feed'),
|
|
]
|
|
|
|
# Follow redirection from feedsportal.com
|
|
def get_article_url(self, article):
|
|
return self.browser.open_novisit(article.link).geturl()
|
|
|
|
def print_version(self, url):
|
|
return url + '?imprimer=1'
|
|
|
|
conversion_options = {'smarten_punctuation': True}
|
|
|
|
keep_only_tags = [
|
|
dict(name='div', attrs={'id': 'content'}),
|
|
]
|
|
|
|
remove_tags_after = [
|
|
dict(name='div', attrs={'id': 'plus_loin'}),
|
|
dict(name='div', attrs={'class': 'stats'}),
|
|
]
|
|
|
|
remove_tags = [
|
|
dict(name='div', attrs={'id': 'article_tools'}),
|
|
dict(name='div', attrs={'id': 'plus_loin'}),
|
|
dict(name='div', attrs={'class': 'stats'}),
|
|
dict(name='div', attrs={'class': 'tools'}),
|
|
]
|
|
|
|
extra_css = "#content { padding: 0 0; }"
|
|
|
|
# Without this, parsing of video articles returns strange results
|
|
preprocess_regexps = [
|
|
(re.compile(r'<script.*?</script>', re.IGNORECASE | re.DOTALL), ''),
|
|
]
|
|
|
|
def preprocess_html(self, soup):
|
|
# Remove whole article if it's a "zapnet" (video)
|
|
if soup.find('h1', {'class': 'zapnet_title'}):
|
|
return None
|
|
# Reduce h2 titles to h3
|
|
for title in soup.findAll('h2'):
|
|
title.name = 'h3'
|
|
return soup
|