__license__ = 'GPL v3' __copyright__ = '2011, Darko Miletic ' ''' gulfnews.com ''' from calibre.web.feeds.news import BasicNewsRecipe class GulfNews(BasicNewsRecipe): title = 'Gulf News' __author__ = 'Darko Miletic' description = 'News from United Arab Emirrates, persian gulf and rest of the world' publisher = 'Al Nisr Publishing LLC' category = 'news, politics, UAE, world' oldest_article = 2 max_articles_per_feed = 200 no_stylesheets = True encoding = 'utf8' use_embedded_content = False language = 'en' remove_empty_feeds = True publication_type = 'newsportal' masthead_url = 'http://gulfnews.com/media/img/gulf_news_logo.jpg' extra_css = """ body{font-family: Arial,Helvetica,sans-serif } img{margin-bottom: 0.4em; display:block} h1{font-family: Georgia, 'Times New Roman', Times, serif} ol,ul{list-style: none} .synopsis{font-size: small} .details{font-size: x-small} .image{font-size: xx-small} """ conversion_options = { 'comment': description, 'tags': category, 'publisher': publisher, 'language': language } remove_tags = [ dict(name=['meta', 'link', 'object', 'embed']), dict( attrs={'class': ['quickLinks', 'ratings']}), dict(attrs={'id': 'imageSelector'}) ] remove_attributes = ['lang'] keep_only_tags = [ dict(name='h1'), dict( attrs={'class': ['synopsis', 'details', 'image', 'article']}) ] feeds = [ (u'UAE News', u'http://gulfnews.com/cmlink/1.446094'), (u'Business', u'http://gulfnews.com/cmlink/1.446098'), (u'Entertainment', u'http://gulfnews.com/cmlink/1.446095'), (u'Sport', u'http://gulfnews.com/cmlink/1.446096'), (u'Life', u'http://gulfnews.com/cmlink/1.446097') ] def preprocess_html(self, soup): for item in soup.findAll(style=True): del item['style'] return soup