From ced9a68a3090f9f8d5c9d281c3cfed2640a6a226 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Thu, 25 Jul 2013 07:42:14 +0530 Subject: [PATCH] Update Scientific American --- recipes/scientific_american.recipe | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/recipes/scientific_american.recipe b/recipes/scientific_american.recipe index 2ea865517e..08f0a3b2b7 100644 --- a/recipes/scientific_american.recipe +++ b/recipes/scientific_american.recipe @@ -30,11 +30,13 @@ class ScientificAmerican(BasicNewsRecipe): ,dict(name='p', attrs={'id':'articleDek'}) ,dict(name='p', attrs={'class':'articleInfo'}) ,dict(name='div', attrs={'id':['articleContent']}) - ,dict(name='img', attrs={'src':re.compile(r'/media/inline/blog/Image/', re.DOTALL|re.IGNORECASE)}) + ,dict(name='img', attrs={'src':re.compile(r'/media/inline/blog/Image/', re.DOTALL|re.IGNORECASE)}) ] - remove_tags = [dict(name='a', attrs={'class':'tinyCommentCount'})] - + remove_tags = [dict(name='a', attrs={'class':'tinyCommentCount'}) + ,dict(name='div', attrs={'id':'bigCoverModule'}) + ,dict(name='div', attrs={'class':'addInfo'}) + ] def parse_index(self): soup = self.index_to_soup('http://www.scientificamerican.com/sciammag/') issuetag = soup.find('p',attrs={'id':'articleDek'}) @@ -43,8 +45,9 @@ class ScientificAmerican(BasicNewsRecipe): if img is not None: self.cover_url = img['src'] features, feeds = [], [] - for a in soup.find(attrs={'class':'primaryCol'}).findAll('a',attrs={'title':'Feature'}): - if a is None: continue + for a in soup.find(attrs={'class':'doubleWide'}).find(attrs={'class':'primaryCol'}).findAll('a',attrs={'title':'Feature'}): + if a is None: + continue desc = '' s = a.parent.parent.find(attrs={'class':'dek'}) desc = self.tag_to_string(s) @@ -89,3 +92,4 @@ class ScientificAmerican(BasicNewsRecipe): h2{font-size:large; font-family:Arial,Helvetica,sans-serif;} h3{font-size:x-small;font-family:Arial,Helvetica,sans-serif;} ''' +