20minutes.recipe

# -*- coding: utf-8 -*-
__license__   = 'GPL v3'
__copyright__ = '2011 Aurélien Chabot <contact@aurelienchabot.fr>'
'''
20minutes.fr
'''
from calibre.web.feeds.recipes import BasicNewsRecipe

class Minutes(BasicNewsRecipe):

    title                  = '20 minutes'
    __author__             = 'calibre'
    description            = 'Actualités'
    encoding               = 'cp1252'
    publisher              = '20minutes.fr'
    category               = 'Actualités, France, Monde'
    language               = 'fr'

    use_embedded_content   = False
    timefmt                = ' [%d %b %Y]'
    max_articles_per_feed  = 15
    no_stylesheets         = True
    remove_empty_feeds     = True
    filterDuplicates       = True

    extra_css = '''
                    h1 {font-size:xx-large; font-family:Arial,Helvetica,sans-serif;}
                    .mna-details {font-size:xx-small; color:#4D4D4D; font-family:Arial,Helvetica,sans-serif;}
                    .mna-image {font-size:xx-small; color:#4D4D4D; font-family:Arial,Helvetica,sans-serif;}
                    .mna-body {font-size:medium; font-family:Arial,Helvetica,sans-serif;}
                '''

    remove_tags = [
            dict(name='iframe'),
            dict(name='div', attrs={'class':['mn-section-heading']}),
            dict(name='a', attrs={'href':['#commentaires']}),
            dict(name='div', attrs={'class':['mn-right']}),
            dict(name='div', attrs={'class':['mna-box']}),
            dict(name='div', attrs={'class':['mna-comment-call']}),
            dict(name='div', attrs={'class':['mna-tools']}),
            dict(name='div', attrs={'class':['mn-trilist']})
    ]

    keep_only_tags    = [dict(id='mn-article')]

    remove_tags_after  = dict(name='div', attrs={'class':['mna-body','mna-signature']})


    feeds = [
        ('France', 'http://www.20minutes.fr/rss/actu-france.xml'),
        ('International', 'http://www.20minutes.fr/rss/monde.xml'),
        ('Tech/Web', 'http://www.20minutes.fr/rss/hightech.xml'),
        ('Sciences', 'http://www.20minutes.fr/rss/sciences.xml'),
        ('Economie', 'http://www.20minutes.fr/rss/economie.xml'),
        ('Politique', 'http://www.20minutes.fr/rss/politique.xml'),
        (u'Médias', 'http://www.20minutes.fr/rss/media.xml'),
        ('Cinema', 'http://www.20minutes.fr/rss/cinema.xml'),
        ('People', 'http://www.20minutes.fr/rss/people.xml'),
        ('Culture', 'http://www.20minutes.fr/rss/culture.xml'),
        ('Sport', 'http://www.20minutes.fr/rss/sport.xml'),
        ('Paris', 'http://www.20minutes.fr/rss/paris.xml'),
        ('Lyon', 'http://www.20minutes.fr/rss/lyon.xml'),
        ('Toulouse', 'http://www.20minutes.fr/rss/toulouse.xml')
    ]


    def preprocess_html(self, soup):
        for item in soup.findAll(style=True):
            del item['style']
        return soup