[BuzzKill]

http://skepticblog.org

Ok, I tried to get this one to work, but it doesn't seem to work. Somewhere in the details during processing a HTTP 403 error seems to pop up, but I will appreciate if someone can check it.

#!/usr/bin/env  python

import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag

class SkepticBlog(BasicNewsRecipe):
    title                 = 'Skepticblog'
    __author__            = 'Multiple Authors'
    description           = 'A collaboration among some of the most recognized names in promoting science, critical thinking, and skepticism'
    oldest_article        = 5
    max_articles_per_feed = 15
    no_stylesheets        = True
    use_embedded_content  = False
    encoding              = 'utf-8'
    publisher             = 'Skeptic Magazine'
    category              = 'science, pseudoscience'
    language              = 'en'

    lang                  = 'en-US'

    conversion_options = {
                          'comment'          : description
                        , 'tags'             : category
                        , 'publisher'        : publisher
                        , 'language'         : lang
                        , 'pretty_print'     : True
                        }

    keep_only_tags = [dict(name='div', attrs={'class':'post'})]
    remove_tags_after  = [dict(name='div', attrs={'class':'ratingblock'})]

    feeds = [(u'SkepticBlog', u'http://skepticblog.org/feed')]

    def preprocess_html(self, soup):
        mtag = Tag(soup,'meta',[('http-equiv','Content-Type'),('context','text/html; charset=utf-8')])
        soup.head.insert(0,mtag)
        soup.html['lang'] = self.lang
        return self.adeify_images(soup)