Read Auto Prove on your iPad or Kindle in no time. Click download to load the free ebook on your reader.

Check out all the available public recipes or write your own with these quick start guides. ReadBeam is built on calibre, so everything in the docs and the fora applies here as well.

Download for free »

Auto and Formula 1

Language: it

Requires Subscription: No, it's available as free ebook

Schedule Every morning

			  #!/usr/bin/env  python
__license__     = 'GPL v3'
__author__      = 'GabrieleMarini, based on Darko Miletic'
__copyright__   = '2009, Darko Miletic <darko.miletic at gmail.com>, Gabriele Marini'
__version__     = 'v1.02 Marini Gabriele '
__date__        = '10, January 2010'
__description__ = 'Italian daily newspaper'

'''
http://www.corrieredellosport.it/
'''
from calibre.web.feeds.news import BasicNewsRecipe

class AutoPR(BasicNewsRecipe):
    __author__     = 'Gabriele Marini'
    description    = 'Auto and Formula 1'

    cover_url      = 'http://www.auto.it/res/imgs/logo_Auto.png'


    title          = u'Auto Prove'
    publisher      = 'CONTE Editore'
    category       = 'Sport'

    language       = 'it'
    timefmt        = '[%a, %d %b, %Y]'

    oldest_article = 60
    max_articles_per_feed = 20
    use_embedded_content  = False
    recursion             = 100

    remove_javascript = True
    no_stylesheets = True

    #html2lrf_options = [
    #                      '--comment', description
    #                    , '--category', category
    #                    , '--publisher', publisher
    #                    , '--ignore-tables'
    #                    ]

    #html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True'

    keep_only_tags = [
                      dict(name='h2', attrs={'class':['tit_Article y_Txt']}),
                      dict(name='h2', attrs={'class':['tit_Article']}),
                      dict(name='div', attrs={'class':['box_Img newsdet_new ']}),
                      dict(name='div', attrs={'class':['box_Img newsdet_as ']}),
                      dict(name='table', attrs={'class':['table_A']}),
                      dict(name='div', attrs={'class':['txt_Article txtBox_cms']}),
                      dict(name='testoscheda')]

    def parse_index(self):
        feeds = []
        for title, url in [
             ("Prove su Strada"  , "http://www.auto.it/rss/prove+6.xml")
            ]:
            soup = self.index_to_soup(url)
            soup = soup.find('channel')
            print soup

            for article in soup.findAllNext('item'):
                title =  self.tag_to_string(article.title)
                date = self.tag_to_string(article.pubDate)
                description = self.tag_to_string(article.description)
                link = self.tag_to_string(article.guid)
#               print article
                articles = self.create_links_append(link, date, description)
                if articles:
                   feeds.append((title, articles))
            return feeds

    def create_links_append(self, link, date, description):
        current_articles = []

        current_articles.append({'title': 'Generale', 'url': link,'description':description, 'date':date}),
        current_articles.append({'title': 'Design', 'url': link.replace('scheda','design'),'description':'scheda', 'date':''}),
        current_articles.append({'title': 'Interni', 'url': link.replace('scheda','interni'),'description':'Interni', 'date':''}),
        current_articles.append({'title': 'Tecnica', 'url': link.replace('scheda','tecnica'),'description':'Tecnica', 'date':''}),
        current_articles.append({'title': 'Su Strada', 'url': link.replace('scheda','su_strada'),'description':'Su Strada', 'date':''}),
        current_articles.append({'title': 'Pagella', 'url': link.replace('scheda','pagella'),'description':'Pagella', 'date':''}),
        current_articles.append({'title': 'Rilevamenti', 'url': link.replace('scheda','telemetria'),'description':'Rilevamenti', 'date':''})

        return current_articles