calibre/recipes/theeconomictimes_india.recipe

55 lines
2.0 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2008-2010, Darko Miletic <darko.miletic at gmail.com>'
'''
economictimes.indiatimes.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class TheEconomicTimes(BasicNewsRecipe):
title = 'The Economic Times India'
__author__ = 'Darko Miletic'
description = 'Financial news from India'
publisher = 'economictimes.indiatimes.com'
category = 'news, finances, politics, India'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
simultaneous_downloads = 1
encoding = 'utf-8'
language = 'en_IN'
publication_type = 'newspaper'
masthead_url = 'http://economictimes.indiatimes.com/photo/2676871.cms'
extra_css = """
body{font-family: Arial,Helvetica,sans-serif}
"""
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
remove_tags_before = dict(name='h1')
feeds = [(u'All articles', u'http://economictimes.indiatimes.com/rssfeedsdefault.cms')]
def print_version(self, url):
rest, sep, art = url.rpartition('/articleshow/')
return 'http://m.economictimes.com/PDAET/articleshow/' + art
return 'http://economictimes.indiatimes.com/articleshow/' + art + '?prtpage=1'
def get_article_url(self, article):
rurl = article.get('guid', None)
if (rurl.find('/quickieslist/') > 0) or (rurl.find('/quickiearticleshow/') > 0):
return None
return rurl
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return self.adeify_images(soup)