calibre/recipes/hindu.recipe
2013-03-25 15:25:29 +05:30

55 lines
1.8 KiB
Plaintext

from __future__ import with_statement
__license__ = 'GPL 3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
from calibre.web.feeds.news import BasicNewsRecipe
class TheHindu(BasicNewsRecipe):
title = u'The Hindu'
language = 'en_IN'
oldest_article = 7
__author__ = 'Kovid Goyal'
max_articles_per_feed = 100
no_stylesheets = True
auto_cleanup = True
extra_css = '.photo-caption { font-size: smaller }'
def parse_index(self):
soup = self.index_to_soup('http://www.thehindu.com/todays-paper/')
div = soup.find('div', attrs={'id':'left-column'})
soup.find(id='subnav-tpbar').extract()
current_section = None
current_articles = []
feeds = []
for x in div.findAll(['a', 'span']):
if x.name == 'span' and x['class'] == 's-link':
# Section heading found
if current_articles and current_section:
feeds.append((current_section, current_articles))
current_section = self.tag_to_string(x)
current_articles = []
self.log('\tFound section:', current_section)
elif x.name == 'a':
title = self.tag_to_string(x)
url = x.get('href', False)
if not url or not title:
continue
self.log('\t\tFound article:', title)
self.log('\t\t\t', url)
current_articles.append({'title': title, 'url':url,
'description':'', 'date':''})
if current_articles and current_section:
feeds.append((current_section, current_articles))
return feeds