home *** CD-ROM | disk | FTP | other *** search
/ Chip 2011 November / CHIP_2011_11.iso / Programy / Narzedzia / Calibre / calibre-0.8.18.msi / file_280 / freeway.recipe < prev    next >
Encoding:
Text File  |  2011-09-09  |  3.9 KB  |  101 lines
  1. #!/usr/bin/env  python
  2.  
  3. __license__   = 'GPL v3'
  4. __author__ = '2010, Gustavo Azambuja <hola at gazambuja.com>'
  5. '''
  6. http://freeway.com.uy
  7. '''
  8.  
  9. from calibre.web.feeds.news import BasicNewsRecipe
  10.  
  11. class General(BasicNewsRecipe):
  12.     title                 = 'freeway.com.uy'
  13.     __author__            = 'Gustavo Azambuja'
  14.     description           = 'Revista Freeway, Montevideo, Uruguay'
  15.     language       = 'es_UY'
  16.     timefmt        = '[%a, %d %b, %Y]'
  17.     use_embedded_content  = False
  18.     recursion             = 1
  19.     encoding = 'utf8'
  20.     remove_javascript = True
  21.     no_stylesheets = True
  22.     conversion_options = {'linearize_tables': True}
  23.  
  24.     oldest_article        = 180
  25.     max_articles_per_feed = 100
  26.     keep_only_tags = [
  27.              dict(id=['contenido']),
  28.              dict(name='a', attrs={'class':'titulo_art_ppal'}),
  29.              dict(name='img', attrs={'class':'recuadro'}),
  30.              dict(name='td', attrs={'class':'txt_art_ppal'})
  31.                      ]
  32.     remove_tags = [
  33.              dict(name=['object','link'])
  34.                   ]
  35.     remove_attributes = ['width','height', 'style', 'font', 'color']
  36.  
  37.     extra_css = '''
  38.                 h1{font-family:Geneva, Arial, Helvetica, sans-serif;color:#154B7A;}
  39.                 h3{font-size: 14px;color:#999999; font-family:Geneva, Arial, Helvetica, sans-serif;font-weight: bold;}
  40.                 h2{color:#666666; font-family:Geneva, Arial, Helvetica, sans-serif;font-size:small;}
  41.                 img {float:left; clear:both; margin:10px}
  42.                 p {font-family:Arial,Helvetica,sans-serif;}
  43.                 '''
  44.  
  45.     def parse_index(self):
  46.             feeds = []
  47.             for title, url in [('Articulos', 'http://freeway.com.uy/revista/')]:
  48.                articles = self.art_parse_section(url)
  49.                if articles:
  50.                    feeds.append((title, articles))
  51.             return feeds
  52.  
  53.     def art_parse_section(self, url):
  54.             soup = self.index_to_soup(url)
  55.             div = soup.find(attrs={'id': 'tbl_1'})
  56.  
  57.             current_articles = []
  58.             for tag in div.findAllNext(attrs = {'class': 'ancho_articulos'}):
  59.                 if tag.get('class') == 'link-list-heading':
  60.                     break
  61.                 for td in tag.findAll('td'):
  62.                     a = td.find('a', attrs= {'class': 'titulo_articulos'})
  63.                     if a is None:
  64.                         continue
  65.                     title = self.tag_to_string(a)
  66.                     url = a.get('href', False)
  67.                     if not url or not title:
  68.                         continue
  69.                     if url.startswith('/'):
  70.                          url = 'http://freeway.com.uy'+url
  71.                     p = td.find('p', attrs= {'class': 'txt_articulos'})
  72.                     description = self.tag_to_string(p)
  73.                     self.log('\t\tFound article:', title)
  74.                     self.log('\t\t\t', url)
  75.                     self.log('\t\t\t', description)
  76.                     current_articles.append({'title': title, 'url': url, 'description':description, 'date':''})
  77.  
  78.             return current_articles
  79.  
  80.     def preprocess_html(self, soup):
  81.         attribs = [  'style','font','valign'
  82.                     ,'colspan','width','height'
  83.                     ,'rowspan','summary','align'
  84.                     ,'cellspacing','cellpadding'
  85.                     ,'frames','rules','border'
  86.                   ]
  87.         for item in soup.body.findAll(name=['table','td','tr','th','caption','thead','tfoot','tbody','colgroup','col']):
  88.             item.name = 'div'
  89.             for attrib in attribs:
  90.                 if item.has_key(attrib):
  91.                    del item[attrib]
  92.         return soup
  93.  
  94.     def get_cover_url(self):
  95.         #index = 'http://www.cosmohispano.com/revista'
  96.         #soup = self.index_to_soup(index)
  97.         #link_item = soup.find('img',attrs={'class':'img_portada'})
  98.         #if link_item:
  99.         #    cover_url = "http://www.cosmohispano.com"+link_item['src']
  100.         return 'http://freeway.com.uy/_upload/_n_foto_grande/noticia_1792_tapanoviembre2010.jpg'
  101.