import re

from calibre.web.feeds.news import BasicNewsRecipe


class Winsupersite(BasicNewsRecipe):
    title = u'Supersite for Windows'
    description = u'Paul Thurrott SuperSite for Windows'
    publisher = 'Paul Thurrott'
    __author__ = 'Hypernova'
    language = 'en'

    oldest_article = 30
    max_articles_per_feed = 100
    no_stylesheets = True
    use_embedded_content = False
    remove_javascript = True
    conversion_options = {'linearize_tables': True}
    remove_tags_before = dict(name='h1')
    preprocess_regexps = [
        (re.compile(r'<p>--Paul Thurrott.*</body>', re.DOTALL | re.IGNORECASE),
         lambda match: '</body>'),
    ]

    def get_browser(self):
        br = BasicNewsRecipe.get_browser(self)
        br.open('http://www.winsupersite.com')
        return br

    feeds = [(u'Supersite for Windows',
              u'http://www.winsupersite.com/supersite.xml')]