From 4c09d25062fff9ca208744ca2545ec11fd886170 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Fri, 11 Jan 2013 12:41:52 +0530 Subject: [PATCH] ... --- recipes/bwmagazine2.recipe | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/recipes/bwmagazine2.recipe b/recipes/bwmagazine2.recipe index 77143bbefc..2c714d91c7 100644 --- a/recipes/bwmagazine2.recipe +++ b/recipes/bwmagazine2.recipe @@ -11,16 +11,15 @@ class BusinessWeekMagazine(BasicNewsRecipe): category = 'news' encoding = 'UTF-8' keep_only_tags = [ - dict(name='div', attrs={'id':'article_body_container'}), - ] - remove_tags = [dict(name='ui'),dict(name='li')] + dict(name='div', attrs={'id':'article_body_container'}), + ] + remove_tags = [dict(name='ui'),dict(name='li'),dict(name='div', attrs={'id':['share-email']})] no_javascript = True no_stylesheets = True cover_url = 'http://images.businessweek.com/mz/covers/current_120x160.jpg' def parse_index(self): - #Go to the issue soup = self.index_to_soup('http://www.businessweek.com/magazine/news/articles/business_news.htm') @@ -47,7 +46,6 @@ class BusinessWeekMagazine(BasicNewsRecipe): if section_title not in feeds: feeds[section_title] = [] feeds[section_title] += articles - div1 = soup.find ('div', attrs={'class':'column center'}) section_title = '' for div in div1.findAll('h5'):