calibre/recipes/twitchfilms.recipe

__license__ = 'GPL v3'
__copyright__ = '2009-2012, Darko Miletic <darko.miletic at gmail.com>'
'''
twitchfilm.net/news/
'''
from calibre.web.feeds.news import BasicNewsRecipe


class Twitchfilm(BasicNewsRecipe):
    title = 'Twitch Films'
    __author__ = 'Darko Miletic'
    description = 'Twitch specializes in spreading the news on strange little films from around the world.'
    oldest_article = 30
    max_articles_per_feed = 100
    no_stylesheets = True
    use_embedded_content = False
    encoding = 'utf-8'
    publisher = 'Twitch'
    category = 'twitch, twitchfilm, movie news, movie reviews, cult cinema, independent cinema, anime, foreign cinema, geek talk'
    language = 'en'

    conversion_options = {
        'comment': description, 'tags': category, 'publisher': publisher, 'language': language
    }

    keep_only_tags = [dict(attrs={'class': 'entry'})]
    remove_tags_after = dict(attrs={'class': 'text'})
    remove_tags = [dict(name='div', attrs={'class': ['social', 'categories']}), dict(attrs={'id': 'main-asset'}), dict(name=['meta', 'link', 'iframe', 'embed', 'object'])  # noqa
                   ]

    feeds = [(u'News', u'http://feeds.twitchfilm.net/TwitchEverything')]

    def preprocess_html(self, soup):
        for item in soup.findAll(style=True):
            del item['style']
        for item in soup.findAll('a'):
            limg = item.find('img')
            if item.string is not None:
                str = item.string
                item.replaceWith(str)
            else:
                if limg:
                    item.name = 'div'
                    item.attrs = []
                else:
                    str = self.tag_to_string(item)
                    item.replaceWith(str)
        for item in soup.findAll('img', alt=False):
            item['alt'] = 'image'
        return soup