__license__ = 'GPL v3'
__copyright__ = '2009 Neil Grogan'
#
# Irish Independent Recipe
#

from calibre.web.feeds.news import BasicNewsRecipe


class IrishIndependent(BasicNewsRecipe):
    title = u'Irish Independent'
    description = 'Irish and World news from Irelands Bestselling Daily Broadsheet'
    __author__ = 'Neil Grogan'
    language = 'en_IE'
    oldest_article = 2
    max_articles_per_feed = 100
    no_stylesheets = True
    ignore_duplicate_articles = {'url'}

    keep_only_tags = [
        dict(name='div', attrs={'class':lambda x: x and '_contentwrapper' in x})
    ]

    remove_tags = [
        dict(name=['svg', 'button']),
        dict(name='div', attrs={'data-testid':['article-share', 'embed-video', 'inline-related-wrapper']})
    ]

    feeds = [
        ('Frontpage News', 'http://www.independent.ie/rss'),
        ('World News', 'http://www.independent.ie/world-news/rss'),
        ('Opinion', 'http://www.independent.ie/opinion/rss'),
        ('Business', 'http://www.independent.ie/business/rss'),
        ('Sport', 'http://www.independent.ie/sport/rss'),
        ('Life', 'http://www.independent.ie/life/rss'),
        ('Style', 'http://www.independent.ie/style/rss'),
        ('Entertainment', 'http://www.independent.ie/business/rss'),
    ]

    def preprocess_html(self, soup):
        for img in soup.findAll(attrs={'data-src': True}):
            img['src'] = img['data-src']
        return soup