new version of the courrier-international recipe for calibre

courrierinternational.recipe

#!/usr/bin/env  python

__license__   = 'GPL v3'
__copyright__ = '2009, Mathieu Godlewski <mathieu at godlewski.fr>\
2015, Rémi Vanicat <vanicat at debian.org'
'''
Courrier International
'''

import re
from calibre.web.feeds.news import BasicNewsRecipe

class CourrierInternational(BasicNewsRecipe):
    title          = 'Courrier International'
    __author__ = 'Mathieu Godlewski <mathieu at godlewski.fr>'
    description = 'Global news in french from international newspapers'
    oldest_article = 7
    language = 'fr'

    max_articles_per_feed = 50
    no_stylesheets = True

    ignore_duplicate_articles = {'title', 'url'}

    html2lrf_options = ['--base-font-size', '10']

    keep_only_tags   = [
        dict(name='div', attrs={'class':'article-content'}),
    ]

    remove_tags      = [
        dict(name='aside', attrs={'class':re.compile('article-sitesocial|article-ad|article-tertiary|view-ci-service-article')}),
        dict(name='button', attrs={'id':re.compile('action-zen-off-(top|bottom)')}),
    ]

    needs_subscription = "optional"
    login_url          = 'http://www.courrierinternational.com/login'

    def get_browser(self):
        def is_form_login(form):
            return "id" in form.attrs and form.attrs['id'] == "user-login-form"
        br = BasicNewsRecipe.get_browser(self)
        if self.username:
            br.open(self.login_url)
            br.select_form(predicate=is_form_login)
            br['name'] = self.username
            br['pass'] = self.password
            br.submit()
        return br

    def preprocess_html(self, soup):
        for link in soup.findAll("a",href=re.compile('^/')):
            link["href"]='http://www.courrierinternational.com' + link["href"]
        return soup

    feeds =  [
        # Some articles requiring subscription fails on download.
        ('Tous', 'http://www.courrierinternational.com/feed/all/rss.xml'),
#        ('France', 'http://courrierint.com/rss/rp/14/0/rss.xml'),
#        ('Europe', 'http://courrierint.com/rss/rp/15/0/rss.xml'),
#        ('Amerique', 'http://courrierint.com/rss/rp/16/0/rss.xml'),
#        ('Asie', 'http://courrierint.com/rss/rp/17/0/rss.xml'),
#        ('Afrique', 'http://courrierint.com/rss/rp/18/0/rss.xml'),
#        ('Moyen-Orient', 'http://courrierint.com/rss/rp/19/0/rss.xml'),
#        ('Economie', 'http://courrierint.com/rss/rp/20/0/rss.xml'),
#        ('Multimedia', 'http://courrierint.com/rss/rp/23/0/rss.xml'),
#        ('Sciences', 'http://courrierint.com/rss/rp/22/0/rss.xml'),
#        ('Culture', 'http://courrierint.com/rss/rp/24/0/rss.xml'),
#        ('Insolites', 'http://courrierint.com/rss/rp/26/0/rss.xml'),
#        ('Cartoons', 'http://cs.courrierint.com/rss/all/rss.xml'),
#        ('Environnement', 'http://vt.courrierint.com/rss/all/rss.xml'),
#        ('Cinema', 'http://ca.courrierint.com/rss/all/rss.xml'),
#        ('Sport', 'http://st.courrierint.com/rss/all/rss.xml'),
    ]