__license__ = 'GPL v3'
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
'''
www.businessworld.in
'''

from calibre.web.feeds.news import BasicNewsRecipe


class BusinessWorldMagazine(BasicNewsRecipe):
    title = 'Business World Magazine'
    __author__ = 'Kovid Goyal'
    description = 'News from India'
    category = 'news, politics, finances, India, Asia'
    no_stylesheets = True
    encoding = 'utf-8'
    language = 'en_IN'
    oldest_article = 2

    keep_only_tags = [
        dict(attrs={'class': ['main-article']}),
    ]
    remove_tags = [
        dict(id='video_n_ad_div'),
        dict(attrs={'class': ['meta-tools', 'social-article']}),
    ]
    remove_tags_after = dict(attrs={'class': 'social-article'})

    feeds = ['http://www.businessworld.in/rss/all-article.xml']

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