diff --git a/recipes/telegraph_uk.recipe b/recipes/telegraph_uk.recipe index 347352d424..57a2068b62 100644 --- a/recipes/telegraph_uk.recipe +++ b/recipes/telegraph_uk.recipe @@ -12,7 +12,8 @@ class TelegraphUK(BasicNewsRecipe): description = 'News from United Kingdom' oldest_article = 2 category = 'news, politics, UK' - publisher = 'Telegraph Media Group ltd.' + publisher = 'Telegraph Media Group ltd.' + compress_news_images = True max_articles_per_feed = 100 no_stylesheets = True language = 'en_GB' @@ -34,30 +35,30 @@ class TelegraphUK(BasicNewsRecipe): , 'publisher' : publisher , 'language' : language } - - + keep_only_tags = [ dict(name='div', attrs={'class':['storyHead','byline']}) - ,dict(name='div', attrs={'id':'mainBodyArea' }) + ,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']}) + 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/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' ) + ,(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'): @@ -70,3 +71,4 @@ class TelegraphUK(BasicNewsRecipe): if 'picture-galleries' in url or 'pictures' in url or 'picturegalleries' in url : url = None return url +