home *** CD-ROM | disk | FTP | other *** search
/ Chip 2011 November / CHIP_2011_11.iso / Programy / Narzedzia / Calibre / calibre-0.8.18.msi / file_280 / people_daily.recipe < prev    next >
Encoding:
Text File  |  2011-09-09  |  2.3 KB  |  58 lines
  1. from calibre.web.feeds.news import BasicNewsRecipe
  2.  
  3. class AdvancedUserRecipe1277129332(BasicNewsRecipe):
  4.     title          = u'People Daily - China'
  5.     oldest_article = 2
  6.     max_articles_per_feed = 100
  7.     __author__            = 'rty'
  8.  
  9.     pubisher  = 'people.com.cn'
  10.     description           = 'People Daily Newspaper'
  11.     language = 'zh'
  12.     category              = 'News, China'
  13.     remove_javascript = True
  14.     use_embedded_content   = False
  15.     no_stylesheets = True
  16.     encoding               = 'GB2312'
  17.     conversion_options = {'linearize_tables':True}
  18.  
  19.     feeds          = [(u'\u56fd\u5185\u65b0\u95fb', u'http://www.people.com.cn/rss/politics.xml'),
  20.        (u'\u56fd\u9645\u65b0\u95fb', u'http://www.people.com.cn/rss/world.xml'),
  21.        (u'\u7ecf\u6d4e\u65b0\u95fb', u'http://www.people.com.cn/rss/finance.xml'),
  22.        (u'\u4f53\u80b2\u65b0\u95fb', u'http://www.people.com.cn/rss/sports.xml'),
  23.        (u'\u53f0\u6e7e\u65b0\u95fb', u'http://www.people.com.cn/rss/haixia.xml')]
  24.     keep_only_tags = [
  25.                               dict(name='div', attrs={'class':'left_content'}),
  26.                                ]
  27.     remove_tags = [
  28.                     dict(name='table', attrs={'class':'title'}),
  29.                          ]
  30.     remove_tags_after = [
  31.                   dict(name='table', attrs={'class':'bianji'}),
  32.                          ]
  33.  
  34.     def append_page(self, soup, appendtag, position):
  35.         pager = soup.find('img',attrs={'src':'/img/next_b.gif'})
  36.         if pager:
  37.            nexturl = self.INDEX + pager.a['href']
  38.            soup2 = self.index_to_soup(nexturl)
  39.            texttag = soup2.find('div', attrs={'class':'left_content'})
  40.            #for it in texttag.findAll(style=True):
  41.            #   del it['style']
  42.            newpos = len(texttag.contents)
  43.            self.append_page(soup2,texttag,newpos)
  44.            texttag.extract()
  45.            appendtag.insert(position,texttag)
  46.  
  47.  
  48.     def preprocess_html(self, soup):
  49.         mtag = '<meta http-equiv="content-type" content="text/html;charset=GB2312" />\n<meta http-equiv="content-language" content="utf-8" />'
  50.         soup.head.insert(0,mtag)
  51.         for item in soup.findAll(style=True):
  52.             del item['form']
  53.         self.append_page(soup, soup.body, 3)
  54.         #pager = soup.find('a',attrs={'class':'ab12'})
  55.         #if pager:
  56.         #   pager.extract()
  57.         return soup
  58.