diff --git a/recipes/linux_magazine.recipe b/recipes/linux_magazine.recipe index da1e40c651..41bb323d81 100644 --- a/recipes/linux_magazine.recipe +++ b/recipes/linux_magazine.recipe @@ -1,38 +1,42 @@ #!/usr/bin/env python2 __license__ = 'GPL v3' -__copyright__ = '2008, Darko Miletic ' +__copyright__ = '2008-2015 , Darko Miletic ' ''' linux-magazine.com ''' -from calibre.ebooks.BeautifulSoup import BeautifulSoup from calibre.web.feeds.news import BasicNewsRecipe class LinuxMagazine(BasicNewsRecipe): - title = u'Linux Magazine' + title = 'Linux Magazine' __author__ = 'Darko Miletic' - description = 'Linux news' - language = 'en' - - oldest_article = 7 + description = 'Linux news' + publisher = 'Linux Magazine' + category = 'news, linux, open source, software' + language = 'en' + encoding = 'utf-8' + oldest_article = 35 max_articles_per_feed = 100 no_stylesheets = True use_embedded_content = False - remove_tags_after = dict(name='div', attrs={'class':'end_intro'}) + conversion_options = { + 'comment' : description + , 'tags' : category + , 'publisher' : publisher + , 'language' : language + } + + + keep_only_tags=dict(name='div', attrs={'class':lambda x:'full' in (x or '').split()}) + + remove_tags_after = dict(name='div', attrs={'id':'disqus_thread'}) remove_tags = [ - dict(name='div' , attrs={'class':'end_intro' }) - ,dict(name='table' , attrs={'width':'100%'}) + dict(name='div' , attrs={'class':['attribute-relatedcontent', + 'social_bookmarks', + 'paginate'] }) + ,dict(name='div' , attrs={'id':'articlebox'}) ] feeds = [(u'Linux Magazine Full Feed', u'http://www.linux-magazine.com/rss/feed/lmi_full')] - - def print_version(self, url): - raw = self.browser.open(url).read() - soup = BeautifulSoup(raw.decode('utf8', 'replace')) - print_link = soup.find('a', {'title':'Print this page'}) - if print_link is None: - return url - return 'http://www.linux-magazine.com'+print_link['href'] -