[Sambit]

I think Times of India Recipe is trying to aggregate way too much info and now the Times of India site presents articles, videos and blogs all interspersed leading to a painful content for Kindle.

Moreover, the print article URLs have changed.

Here is my update for articles only:

__license__   = 'GPL v3'
__copyright__ = '2008-2014, Karthik <hashkendistro@gmail.com>'
'''
timesofindia.indiatimes.com
'''


from calibre.web.feeds.news import BasicNewsRecipe

class TheEconomicTimes(BasicNewsRecipe):
    title                  = 'The Times of India'
    __author__             = 'Sambit Kumar Dash'
    description            = 'News from the Indian daily Times of India'
    publisher              = 'timesofindia.indiatimes.com'
    category               = 'news, finances, politics, sports, business, entertainment, India'
    oldest_article         = 1
    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://timesofindia.indiatimes.com/photo.cms?msid=2419189'
    extra_css              = """
                                 body{font-family: Arial,Helvetica,sans-serif}
                                 .foto_mg{font-size: 60%; 
                                          font-weight: 700;}
                                 h1{font-size: 150%;}
                                 artdate{font-size: 60%}
                                 artag{font-size: 60%}
                                 div.storycontent{padding-top: 10px}
                             """
    conversion_options     = {'comment'          : description, 
                              'tags'             : category,
                              'publisher'        : publisher,
                              'language'         : language
                             }
    remove_tags_before     = dict(name='h1')
    remove_tags_after      = dict(name='div', attrs={'class':'storycontent'})
    remove_attributes      = ['xmlns']
    remove_tags			   = [dict(name='div', attrs={'class':'readalso'})]
    
    feeds                  = [('Recent Stories', 'http://timesofindia.indiatimes.com/rssfeeds/1221656.cms'),
                              ('India', 'http://timesofindia.indiatimes.com/rssfeeds/-2128936835.cms'),
                              ('World', 'http://timesofindia.indiatimes.com/rssfeeds/296589292.cms'),
                              ('Business', 'http://timesofindia.indiatimes.com/rssfeeds/1898055.cms'),
                              ('Cricket', 'http://timesofindia.indiatimes.com/rssfeeds/4719161.cms'),
                              ('Sports', 'http://timesofindia.indiatimes.com/rssfeeds/4719148.cms'),
                              ('Tech', 'http://timesofindia.indiatimes.com/rssfeeds/5880659.cms'),
                              ('Education', 'http://timesofindia.indiatimes.com/rssfeeds/913168846.cms'),
                              ('Science', 'http://timesofindia.indiatimes.com/rssfeeds/-2128672765.cms'),
                              ('Opinion', 'http://timesofindia.indiatimes.com/rssfeeds/784865811.cms'),
                              ('Entertainment', 'http://timesofindia.indiatimes.com/rssfeeds/1081479906.cms')]


    #Uses the mobile print version. For web print version use 'http://timesofindia.indiatimes.com/articleshow/<article_id>?prtpage=1'
    def print_version(self, url):
        #rest, sep, article_id = url.rpartition('/articleshow/')
        found = url.find('/articleshow/');
        
        # If /articleshow/ is not found it's not an article and can be ignored. 
        # If found replace the URL for print. 
        if found == -1:
            return ' '
        else:
            url = url.replace('/articleshow/', '/articleshowprint/')
        #return 'http://m.timesofindia.com/PDAET/articleshow/' + article_id
        return url

    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 soup

    def postprocess_html(self, soup, first_fetch):
        return self.adeify_images(soup)