home *** CD-ROM | disk | FTP | other *** search
- from calibre.web.feeds.news import BasicNewsRecipe
- from calibre.ebooks.BeautifulSoup import BeautifulSoup
-
- class CourierPress(BasicNewsRecipe):
- title = u'Courier Press'
- language = 'en'
- __author__ = 'Krittika Goyal'
- oldest_article = 1 #days
- max_articles_per_feed = 25
-
- remove_stylesheets = True
- remove_tags = [
- dict(name='iframe'),
- ]
-
- feeds = [
- ('Courier Press',
- 'http://www.courierpress.com/rss/headlines/news/'),
- ]
-
- def preprocess_html(self, soup):
- story = soup.find(name='div', attrs={'id':'article_body'})
- soup = BeautifulSoup('<html><head><title>t</title></head><body></body></html>')
- body = soup.find(name='body')
- body.insert(0, story)
- return soup
-