home *** CD-ROM | disk | FTP | other *** search
/ Chip 2011 November / CHIP_2011_11.iso / Programy / Narzedzia / Calibre / calibre-0.8.18.msi / file_280 / bwmagazine.recipe < prev    next >
Text File  |  2011-09-09  |  5KB  |  103 lines
  1. __license__   = 'GPL v3'
  2. __copyright__ = '2008 Kovid Goyal kovid@kovidgoyal.net, 2010 Darko Miletic <darko.miletic at gmail.com>'
  3. '''
  4. www.businessweek.com
  5. '''
  6.  
  7. from calibre.web.feeds.news import BasicNewsRecipe
  8.  
  9. class BusinessWeek(BasicNewsRecipe):
  10.     title                 = 'Business Week'
  11.     __author__            = 'Kovid Goyal and Darko Miletic'
  12.     description           = 'Read the latest international business news & stock market news. Get updated company profiles, financial advice, global economy and technology news.'
  13.     publisher             = 'Bloomberg L.P.'
  14.     category              = 'Business, business news, stock market, stock market news, financial advice, company profiles, financial advice, global economy, technology news'
  15.     oldest_article        = 7
  16.     max_articles_per_feed = 200
  17.     no_stylesheets        = True
  18.     encoding              = 'utf8'
  19.     use_embedded_content  = False
  20.     language              = 'en'
  21.     remove_empty_feeds    = True
  22.     publication_type      = 'magazine'
  23.     cover_url             = 'http://images.businessweek.com/mz/covers/current_120x160.jpg'
  24.     masthead_url          = 'http://assets.businessweek.com/images/bw-logo.png'
  25.     extra_css             = """
  26.                                body{font-family: Helvetica,Arial,sans-serif }
  27.                                img{margin-bottom: 0.4em; display:block}
  28.                                .tagline{color: gray; font-style: italic}
  29.                                .photoCredit{font-size: small; color: gray}
  30.                             """
  31.  
  32.     conversion_options = {
  33.                           'comment'   : description
  34.                         , 'tags'      : category
  35.                         , 'publisher' : publisher
  36.                         , 'language'  : language
  37.                         }
  38.  
  39.     remove_tags       = [
  40.                            dict(attrs={'class':'inStory'})
  41.                           ,dict(name=['meta','link','iframe','base','embed','object','table','th','tr','td'])
  42.                           ,dict(attrs={'id':['inset','videoDisplay']})
  43.                         ]
  44.     keep_only_tags    = [dict(name='div', attrs={'id':['story-body','storyBody']})]
  45.     remove_attributes = ['lang']
  46.     match_regexps     = [r'http://www.businessweek.com/.*_page_[1-9].*']
  47.  
  48.  
  49.     feeds = [
  50.               (u'Top Stories', u'http://www.businessweek.com/topStories/rss/topStories.rss'),
  51.               (u'Top News'   , u'http://www.businessweek.com/rss/bwdaily.rss'              ),
  52.               (u'Asia', u'http://www.businessweek.com/rss/asia.rss'),
  53.               (u'Autos', u'http://www.businessweek.com/rss/autos/index.rss'),
  54.               (u'Classic Cars', u'http://rss.businessweek.com/bw_rss/classiccars'),
  55.               (u'Hybrids', u'http://rss.businessweek.com/bw_rss/hybrids'),
  56.               (u'Europe', u'http://www.businessweek.com/rss/europe.rss'),
  57.               (u'Auto Reviews', u'http://rss.businessweek.com/bw_rss/autoreviews'),
  58.               (u'Innovation & Design', u'http://www.businessweek.com/rss/innovate.rss'),
  59.               (u'Architecture', u'http://www.businessweek.com/rss/architecture.rss'),
  60.               (u'Brand Equity', u'http://www.businessweek.com/rss/brandequity.rss'),
  61.               (u'Auto Design', u'http://www.businessweek.com/rss/carbuff.rss'),
  62.               (u'Game Room', u'http://rss.businessweek.com/bw_rss/gameroom'),
  63.               (u'Technology', u'http://www.businessweek.com/rss/technology.rss'),
  64.               (u'Investing', u'http://rss.businessweek.com/bw_rss/investor'),
  65.               (u'Small Business', u'http://www.businessweek.com/rss/smallbiz.rss'),
  66.               (u'Careers', u'http://rss.businessweek.com/bw_rss/careers'),
  67.               (u'B-Schools', u'http://www.businessweek.com/rss/bschools.rss'),
  68.               (u'Magazine Selections', u'http://www.businessweek.com/rss/magazine.rss'),
  69.               (u'CEO Guide to Tech', u'http://www.businessweek.com/rss/ceo_guide_tech.rss'),
  70.             ]
  71.  
  72.     def get_article_url(self, article):
  73.         url = article.get('guid', None)
  74.         if 'podcasts' in url:
  75.             return None
  76.         if 'surveys' in url:
  77.             return None
  78.         if 'images' in url:
  79.             return None
  80.         if 'feedroom' in url:
  81.             return None
  82.         if '/magazine/toc/' in url:
  83.             return None
  84.         rurl, sep, rest = url.rpartition('?')
  85.         if rurl:
  86.            return rurl
  87.         return rest
  88.  
  89.     def print_version(self, url):
  90.         if '/news/' in url or '/blog/ in url':
  91.            return url
  92.         rurl = url.replace('http://www.businessweek.com/','http://www.businessweek.com/print/')
  93.         return rurl.replace('/investing/','/investor/')
  94.  
  95.     def preprocess_html(self, soup):
  96.         for item in soup.findAll(style=True):
  97.             del item['style']
  98.         for alink in soup.findAll('a'):
  99.             if alink.string is not None:
  100.                tstr = alink.string
  101.                alink.replaceWith(tstr)
  102.         return soup
  103.