home *** CD-ROM | disk | FTP | other *** search
/ Chip 2011 November / CHIP_2011_11.iso / Programy / Narzedzia / Calibre / calibre-0.8.18.msi / file_280 / globaltimes.recipe < prev    next >
Encoding:
Text File  |  2011-09-09  |  2.0 KB  |  47 lines
  1. from calibre.web.feeds.news import BasicNewsRecipe
  2. import re
  3.  
  4. class globaltimes(BasicNewsRecipe):
  5.     title          = u'Global Times'
  6.     __author__ = 'malfi'
  7.     language = 'zh'
  8.     oldest_article = 7
  9.     max_articles_per_feed = 100
  10.     no_stylesheets = True
  11.     cover_url = 'http://enhimg2.huanqiu.com/images/logo.png'
  12.     language = 'en'
  13.     keep_only_tags = []
  14.     keep_only_tags.append(dict(name = 'div', attrs = {'id': 'content'}))
  15.     remove_tags = []
  16.     remove_tags.append(dict(name = 'div', attrs = {'class': 'location'}))
  17.     remove_tags.append(dict(name = 'div', attrs = {'class': 'contentpage'}))
  18.     remove_tags.append(dict(name = 'li', attrs = {'id': 'pl'}))
  19.  
  20.     extra_css = '''
  21.         h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
  22.         h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
  23.         p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
  24.         body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
  25.         '''
  26.     def parse_index(self):
  27.         catnames = {}
  28.         catnames["http://china.globaltimes.cn/chinanews/"] = "China Politics"
  29.         catnames["http://china.globaltimes.cn/diplomacy/"] = "China Diplomacy"
  30.         catnames["http://military.globaltimes.cn/china/"] = "China Military"
  31.         catnames["http://business.globaltimes.cn/china-economy/"] = "China Economy"
  32.         catnames["http://world.globaltimes.cn/asia-pacific/"] = "Asia Pacific"
  33.         feeds = []
  34.  
  35.         for cat in catnames.keys():
  36.             articles = []
  37.             soup = self.index_to_soup(cat)
  38.             for a in soup.findAll('a',attrs={'href' : re.compile(cat+"201[0-9]-[0-1][0-9]/[0-9][0-9][0-9][0-9][0-9][0-9].html")}):
  39.                 url = a['href'].strip()
  40.                 myarticle=({'title':self.tag_to_string(a), 'url':url, 'description':'', 'date':''})
  41.                 self.log("found %s" % url)
  42.                 articles.append(myarticle)
  43.                 self.log("Adding URL %s\n" %url)
  44.             if articles:
  45.                 feeds.append((catnames[cat], articles))
  46.         return feeds
  47.