Update Scientific American

This commit is contained in:
Kovid Goyal 2013-07-25 07:42:14 +05:30
parent 114e5cf3a7
commit ced9a68a30

View File

@ -30,11 +30,13 @@ class ScientificAmerican(BasicNewsRecipe):
,dict(name='p', attrs={'id':'articleDek'}) ,dict(name='p', attrs={'id':'articleDek'})
,dict(name='p', attrs={'class':'articleInfo'}) ,dict(name='p', attrs={'class':'articleInfo'})
,dict(name='div', attrs={'id':['articleContent']}) ,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): def parse_index(self):
soup = self.index_to_soup('http://www.scientificamerican.com/sciammag/') soup = self.index_to_soup('http://www.scientificamerican.com/sciammag/')
issuetag = soup.find('p',attrs={'id':'articleDek'}) issuetag = soup.find('p',attrs={'id':'articleDek'})
@ -43,8 +45,9 @@ class ScientificAmerican(BasicNewsRecipe):
if img is not None: if img is not None:
self.cover_url = img['src'] self.cover_url = img['src']
features, feeds = [], [] features, feeds = [], []
for a in soup.find(attrs={'class':'primaryCol'}).findAll('a',attrs={'title':'Feature'}): for a in soup.find(attrs={'class':'doubleWide'}).find(attrs={'class':'primaryCol'}).findAll('a',attrs={'title':'Feature'}):
if a is None: continue if a is None:
continue
desc = '' desc = ''
s = a.parent.parent.find(attrs={'class':'dek'}) s = a.parent.parent.find(attrs={'class':'dek'})
desc = self.tag_to_string(s) desc = self.tag_to_string(s)
@ -89,3 +92,4 @@ class ScientificAmerican(BasicNewsRecipe):
h2{font-size:large; font-family:Arial,Helvetica,sans-serif;} h2{font-size:large; font-family:Arial,Helvetica,sans-serif;}
h3{font-size:x-small;font-family:Arial,Helvetica,sans-serif;} h3{font-size:x-small;font-family:Arial,Helvetica,sans-serif;}
''' '''