Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Updated Newsweek recipe

Browse Source
This commit is contained in:
Tom Scholl 2011-05-10 11:17:39 +00:00
parent 0744534b2d
commit 87f281cf4d
1 changed files with 17 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
recipes/newsweek.recipe
View File

@ -11,7 +11,20 @@ class Newsweek(BasicNewsRecipe):
no_stylesheets = True no_stylesheets = True
BASE_URL = 'http://www.newsweek.com' BASE_URL = 'http://www.newsweek.com'
INDEX = BASE_URL+'/topics.html'
topics = {
'Culture' : '/tag/culture.html',
'Business' : '/tag/business.html',
'Society' : '/tag/society.html',
'Science' : '/tag/science.html',
'Education' : '/tag/education.html',
'Politics' : '/tag/politics.html',
'Health' : '/tag/health.html',
'World' : '/tag/world.html',
'Nation' : '/tag/nation.html',
'Technology' : '/tag/technology.html',
'Game Changers' : '/tag/game-changers.html',
}
keep_only_tags = dict(name='article', attrs={'class':'article-text'}) keep_only_tags = dict(name='article', attrs={'class':'article-text'})
remove_tags = [dict(attrs={'data-dartad':True})] remove_tags = [dict(attrs={'data-dartad':True})]
@ -23,10 +36,9 @@ class Newsweek(BasicNewsRecipe):
return soup return soup
def newsweek_sections(self): def newsweek_sections(self):
soup = self.index_to_soup(self.INDEX) for topic_name, topic_url in self.topics.iteritems():
for a in soup.findAll('a', title='Primary tag', href=True): yield (topic_name,
yield (string.capitalize(self.tag_to_string(a)), self.BASE_URL+topic_url)
self.BASE_URL+a['href'])
def newsweek_parse_section_page(self, soup): def newsweek_parse_section_page(self, soup):