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


class WashingtonPost(BasicNewsRecipe):

    title = 'Washington Post'
    description = 'US political news'
    __author__ = 'Kovid Goyal and Sujata Raman'
    use_embedded_content   = False
    max_articles_per_feed = 20
    language = 'en'


    remove_javascript = True
    no_stylesheets = True

    extra_css       = '''
                        #articleCopyright { font-family:Arial,helvetica,sans-serif ; font-weight:bold ; font-size:x-small ;}
                        p { font-family:"Times New Roman",times,serif ; font-weight:normal ; font-size:small ;}
                        body{font-family:arial,helvetica,sans-serif}
                            '''

    feeds = [    ('Today\'s Highlights', 'http://www.washingtonpost.com/wp-dyn/rss/linkset/2005/03/24/LI2005032400102.xml'),
     	         ('Politics', 'http://www.washingtonpost.com/wp-dyn/rss/politics/index.xml'),
     	         ('Nation', 'http://www.washingtonpost.com/wp-dyn/rss/nation/index.xml'),
     	         ('World', 'http://www.washingtonpost.com/wp-dyn/rss/world/index.xml'),
     	         ('Business', 'http://www.washingtonpost.com/wp-dyn/rss/business/index.xml'),
     	         ('Technology', 'http://www.washingtonpost.com/wp-dyn/rss/technology/index.xml'),
     	         ('Health', 'http://www.washingtonpost.com/wp-dyn/rss/health/index.xml'),
     	         ('Education', 'http://www.washingtonpost.com/wp-dyn/rss/education/index.xml'),
     	         ('Editorials', 'http://www.washingtonpost.com/wp-dyn/rss/linkset/2005/05/30/LI2005053000331.xml'),
     	]

    remove_tags = [{'id':['pfmnav', 'ArticleCommentsWrapper']}]


    def get_article_url(self, article):
        return article.get('guid', article.get('link', None))

    def print_version(self, url):
        return url.rpartition('.')[0] + '_pf.html'

    def postprocess_html(self, soup, first):
        for div in soup.findAll(name='div', style=re.compile('margin')):
            div['style'] = ''
        return soup

    def preprocess_html(self, soup):
        for tag in soup.findAll('font'):
            if tag.has_key('size'):
                if tag['size'] == '+2':
                    if tag.b:
                        return soup
        return None