calibre/recipes/rue89.recipe

54 lines
2.0 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2010, Louis Gesbert <meta at antislash dot info>'
'''
Rue89
'''
__author__ = '2010, Louis Gesbert <meta at antislash dot info>'
import re
from calibre.ebooks.BeautifulSoup import Tag
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
feeds = [(u'La Une', u'http://www.rue89.com/homepage/feed')]
no_stylesheets = True
preprocess_regexps = [
(re.compile(r'<(/?)h2>', re.IGNORECASE|re.DOTALL),
lambda match : '<'+match.group(1)+'h3>'),
(re.compile(r'<div class="print-title">([^>]+)</div>', re.IGNORECASE|re.DOTALL),
lambda match : '<h2>'+match.group(1)+'</h2>'),
(re.compile(r'<img[^>]+src="[^"]*/numeros/(\d+)[^0-9.">]*.gif"[^>]*/>', re.IGNORECASE|re.DOTALL),
lambda match : '<span style="font-family: Sans-serif; color: red; font-size:24pt; padding=2pt;">'+match.group(1)+'</span>'),
(re.compile(r'\''), lambda match: '&rsquo;'),
]
def preprocess_html(self,soup):
body = Tag(soup, 'body')
title = soup.find('h1', {'class':'title'})
content = soup.find('div', {'class':'content'})
soup.body.replaceWith(body)
body.insert(0, title)
body.insert(1, content)
return soup
remove_tags = [ #dict(name='div', attrs={'class':'print-source_url'}),
#dict(name='div', attrs={'class':'print-links'}),
#dict(name='img', attrs={'class':'print-logo'}),
dict(name='div', attrs={'class':'content_top'}),
dict(name='div', attrs={'id':'sidebar-left'}), ]
# -- print-version has poor quality on this website, better do the conversion ourselves
# def print_version(self, url):
# return re.sub('^.*-([0-9]+)$', 'http://www.rue89.com/print/\\1',url)