home *** CD-ROM | disk | FTP | other *** search
/ Maximum CD 2010 November / maximum-cd-2010-11.iso / DiscContents / calibre-0.7.13.msi / file_3618 < prev    next >
Encoding:
Text File  |  2010-06-19  |  3.6 KB  |  91 lines
  1. #!/usr/bin/env  python
  2. __license__     = 'GPL v3'
  3. __author__      = 'GabrieleMarini, based on Darko Miletic'
  4. __copyright__   = '2009, Darko Miletic <darko.miletic at gmail.com>, Gabriele Marini'
  5. __version__     = 'v1.02 Marini Gabriele '
  6. __date__        = '10, January 2010'
  7. __description__ = 'Italian daily newspaper'
  8.  
  9. '''
  10. http://www.corrieredellosport.it/
  11. '''
  12. from calibre.web.feeds.news import BasicNewsRecipe
  13.  
  14. class AutoPR(BasicNewsRecipe):
  15.     __author__     = 'Gabriele Marini'
  16.     description    = 'Auto and Formula 1'
  17.  
  18.     cover_url      = 'http://www.auto.it/res/imgs/logo_Auto.png'
  19.  
  20.  
  21.     title          = u'Auto Prove'
  22.     publisher      = 'CONTE Editore'
  23.     category       = 'Sport'
  24.  
  25.     language       = 'it'
  26.     timefmt        = '[%a, %d %b, %Y]'
  27.  
  28.     oldest_article = 60
  29.     max_articles_per_feed = 20
  30.     use_embedded_content  = False
  31.     recursion             = 100
  32.  
  33.     remove_javascript = True
  34.     no_stylesheets = True
  35.  
  36.     #html2lrf_options = [
  37.     #                      '--comment', description
  38.     #                    , '--category', category
  39.     #                    , '--publisher', publisher
  40.     #                    , '--ignore-tables'
  41.     #                    ]
  42.  
  43.     #html2epub_options = 'publisher="' + publisher + '"\ncomments="' + description + '"\ntags="' + category + '"\nlinearize_tables=True'
  44.  
  45.     keep_only_tags = [
  46.                       dict(name='h2', attrs={'class':['tit_Article y_Txt']}),
  47.                       dict(name='h2', attrs={'class':['tit_Article']}),
  48.                       dict(name='div', attrs={'class':['box_Img newsdet_new ']}),
  49.                       dict(name='div', attrs={'class':['box_Img newsdet_as ']}),
  50.                       dict(name='table', attrs={'class':['table_A']}),
  51.                       dict(name='div', attrs={'class':['txt_Article txtBox_cms']}),
  52.                       dict(name='testoscheda')]
  53.  
  54.     def parse_index(self):
  55.         feeds = []
  56.         for title, url in [
  57.              ("Prove su Strada"  , "http://www.auto.it/rss/prove+6.xml")
  58.             ]:
  59.             soup = self.index_to_soup(url)
  60.             soup = soup.find('channel')
  61.             print soup
  62.  
  63.             for article in soup.findAllNext('item'):
  64.                 title =  self.tag_to_string(article.title)
  65.                 date = self.tag_to_string(article.pubDate)
  66.                 description = self.tag_to_string(article.description)
  67.                 link = self.tag_to_string(article.guid)
  68. #               print article
  69.                 articles = self.create_links_append(link, date, description)
  70.                 if articles:
  71.                    feeds.append((title, articles))
  72.             return feeds
  73.  
  74.     def create_links_append(self, link, date, description):
  75.         current_articles = []
  76.  
  77.         current_articles.append({'title': 'Generale', 'url': link,'description':description, 'date':date}),
  78.         current_articles.append({'title': 'Design', 'url': link.replace('scheda','design'),'description':'scheda', 'date':''}),
  79.         current_articles.append({'title': 'Interni', 'url': link.replace('scheda','interni'),'description':'Interni', 'date':''}),
  80.         current_articles.append({'title': 'Tecnica', 'url': link.replace('scheda','tecnica'),'description':'Tecnica', 'date':''}),
  81.         current_articles.append({'title': 'Su Strada', 'url': link.replace('scheda','su_strada'),'description':'Su Strada', 'date':''}),
  82.         current_articles.append({'title': 'Pagella', 'url': link.replace('scheda','pagella'),'description':'Pagella', 'date':''}),
  83.         current_articles.append({'title': 'Rilevamenti', 'url': link.replace('scheda','telemetria'),'description':'Rilevamenti', 'date':''})
  84.  
  85.         return current_articles
  86.  
  87.  
  88.  
  89.  
  90.  
  91.