From 29a45f967051a4829af56aecdc848988ce038601 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Fri, 15 Feb 2013 09:15:26 +0530 Subject: [PATCH] Fix #1119685 (new yorker magazine only has web links, no text) --- recipes/new_yorker.recipe | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/recipes/new_yorker.recipe b/recipes/new_yorker.recipe index c5f1b0aff2..2730b45d6d 100644 --- a/recipes/new_yorker.recipe +++ b/recipes/new_yorker.recipe @@ -1,5 +1,5 @@ __license__ = 'GPL v3' -__copyright__ = '2008-2011, Darko Miletic ' +__copyright__ = '2008-2013, Darko Miletic ' ''' newyorker.com ''' @@ -44,20 +44,18 @@ class NewYorker(BasicNewsRecipe): , 'language' : language } - keep_only_tags = [ - dict(name='div', attrs={'class':'headers'}) - ,dict(name='div', attrs={'id':['articleheads','items-container','articleRail','articletext','photocredits']}) - ] + keep_only_tags = [dict(name='div', attrs={'id':'pagebody'})] remove_tags = [ dict(name=['meta','iframe','base','link','embed','object']) - ,dict(attrs={'class':['utils','socialUtils','articleRailLinks','icons'] }) + ,dict(attrs={'class':['utils','socialUtils','articleRailLinks','icons','social-utils-top','entry-keywords','entry-categories','utilsPrintEmail'] }) ,dict(attrs={'id':['show-header','show-footer'] }) ] + remove_tags_after = dict(attrs={'class':'entry-content'}) remove_attributes = ['lang'] feeds = [(u'The New Yorker', u'http://www.newyorker.com/services/mrss/feeds/everything.xml')] def print_version(self, url): - return url + '?printable=true' + return url + '?printable=true¤tPage=all' def image_url_processor(self, baseurl, url): return url.strip()