__license__ = 'GPL v3' __copyright__ = '2008-2010, Darko Miletic ' ''' telegraph.co.uk ''' from calibre.web.feeds.news import BasicNewsRecipe class TelegraphUK(BasicNewsRecipe): title = 'Telegraph.co.uk' __author__ = 'Darko Miletic and Sujata Raman' description = 'News from United Kingdom' oldest_article = 2 category = 'news, politics, UK' publisher = 'Telegraph Media Group ltd.' compress_news_images = True max_articles_per_feed = 100 no_stylesheets = True language = 'en_GB' remove_empty_feeds = True use_embedded_content = False extra_css = ''' h1{font-family :Arial,Helvetica,sans-serif; font-size:large; } h2{font-family :Arial,Helvetica,sans-serif; font-size:x-small; color:#444444;} .story{font-family :Arial,Helvetica,sans-serif; font-size: x-small;} .byline{color:#666666; font-family :Arial,Helvetica,sans-serif; font-size: xx-small;} a{color:#234B7B; } .imageExtras{color:#666666; font-family :Arial,Helvetica,sans-serif; font-size: xx-small;} ''' conversion_options = { 'comment' : description , 'tags' : category , 'publisher' : publisher , 'language' : language } keep_only_tags = [ dict(name='div', attrs={'class':['storyHead','byline']}) ,dict(name='div', attrs={'id':'mainBodyArea'}) ] remove_tags = [dict(name='div', attrs={ 'class':['related_links_inline',"imgindex","next","prev","gutterUnder",'ssImgHide','imageExtras','ssImg hide','related_links_video']}) ,dict(name='ul' , attrs={'class':['shareThis shareBottom']}) ,dict(name='span', attrs={'class':['num','placeComment']}) ] feeds = [ (u'UK News' , u'http://www.telegraph.co.uk/news/uknews/rss') ,(u'World News' , u'http://www.telegraph.co.uk/news/worldnews/rss') ,(u'Politics' , u'http://www.telegraph.co.uk/news/newstopics/politics/rss') ,(u'Finance' , u'http://www.telegraph.co.uk/finance/rss') ,(u'Technology News', u'http://www.telegraph.co.uk/scienceandtechnology/technology/technologynews/rss') ,(u'UK News' , u'http://www.telegraph.co.uk/scienceandtechnology/technology/technologyreviews/rss') ,(u'Science News' , u'http://www.telegraph.co.uk/scienceandtechnology/science/sciencenews/rss') ,(u'Sport' , u'http://www.telegraph.co.uk/sport/rss') ,(u'Earth News' , u'http://www.telegraph.co.uk/earth/earthnews/rss') ,(u'Comment' , u'http://www.telegraph.co.uk/comment/rss') ,(u'Travel' , u'http://www.telegraph.co.uk/travel/rss') ,(u'How about that?', u'http://www.telegraph.co.uk/news/newstopics/howaboutthat/rss') ] def populate_article_metadata(self, article, soup, first): if first and hasattr(self, 'add_toc_thumbnail'): picdiv = soup.find('img') if picdiv is not None: self.add_toc_thumbnail(article,picdiv['src']) def get_article_url(self, article): url = article.get('link', None) if 'picture-galleries' in url or 'pictures' in url or 'picturegalleries' in url : url = None return url