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

class NatureNews(BasicNewsRecipe):
    title          = u'Nature News'
    language       = 'en'
    __author__     = 'Krittika Goyal'
    oldest_article = 31 #days
    max_articles_per_feed = 50
    #encoding = 'latin1'

    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='iframe'),
       #dict(name='div', attrs={'class':['pt-box-title', 'pt-box-content']}),
       #dict(name='div', attrs={'id':['block-td_search_160', 'block-cam_search_160']}),
       dict(name='h2', attrs={'id':'comments'}),
       dict(name='ul', attrs={'class':'toolsmenu xoxo'}),
    ]

    preprocess_regexps = [
      (re.compile(r'<script.*?</script>', re.DOTALL), lambda m: '')
    ]

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

    def get_article_url(self, article):
        return article.get('id')