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

class NatureNews(BasicNewsRecipe):
    title          = u'Nature News'
    language       = 'en'
    __author__     = 'Krittika Goyal, Starson17'
    oldest_article = 31 #days
    remove_empty_feeds    = True
    max_articles_per_feed = 50

    no_stylesheets = True
    remove_tags_before = dict(name='h1', attrs={'class':'heading entry-title'})
    remove_tags_after  = dict(name='h2', attrs={'id':'comments'})
    remove_tags = [
       dict(name='h2', attrs={'id':'comments'}),
       dict(attrs={'alt':'Advertisement'}),
       dict(name='div', attrs={'class':'ad'}),
    ] 

    preprocess_regexps = [
        (re.compile(r'<p>ADVERTISEMENT</p>', re.DOTALL|re.IGNORECASE), lambda match: ''),
        ]

    feeds = [('Nature News', 'http://feeds.nature.com/news/rss/most_recent')]