#!/usr/bin/env python

__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
www.mercurynews.com
'''

from calibre.web.feeds.news import BasicNewsRecipe


class MercuryNews(BasicNewsRecipe):
    title = 'San Jose Mercury News'
    __author__ = 'Darko Miletic'
    description = 'News from San Jose'
    cover_url = 'http://webmedia.newseum.org/newseum-multimedia/dfp/jpg12/lg/CA_SJMN.jpg'
    publisher = 'San Jose Mercury News'
    category = 'news, politics, USA, San Jose, California'
    oldest_article = 2
    max_articles_per_feed = 100
    no_stylesheets = True
    use_embedded_content = False
    encoding = 'utf-8'
    language = 'en'

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

    keep_only_tags = [
        dict(name='h1'),
        dict(attrs={'class':['byline', 'time', 'article-body']}),
        dict(attrs={'class':lambda x: x and 'header-features' in x.split()}),
    ]

    feeds = [
        ('News', 'http://www.mercurynews.com/feed/')
    ]

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