home *** CD-ROM | disk | FTP | other *** search
/ Chip 2011 November / CHIP_2011_11.iso / Programy / Narzedzia / Calibre / calibre-0.8.18.msi / file_280 / mainichi.recipe < prev    next >
Text File  |  2011-09-09  |  1KB  |  41 lines
  1. __license__   = 'GPL v3'
  2. __copyright__ = '2010, Hiroshi Miura <miurahr@linux.com>'
  3. '''
  4. www.mainichi.jp
  5. '''
  6.  
  7. import re
  8. from calibre.web.feeds.news import BasicNewsRecipe
  9.  
  10. class MainichiDailyNews(BasicNewsRecipe):
  11.     title          = u'\u6bce\u65e5\u65b0\u805e'
  12.     __author__     = 'Hiroshi Miura'
  13.     oldest_article = 2
  14.     max_articles_per_feed = 20
  15.     description    = 'Japanese traditional newspaper Mainichi Daily News'
  16.     publisher      = 'Mainichi Daily News'
  17.     category       = 'news, japan'
  18.     language       = 'ja'
  19.  
  20.     feeds          = [(u'daily news', u'http://mainichi.jp/rss/etc/flash.rss')]
  21.  
  22.     remove_tags_before = {'class':"NewsTitle"}
  23.     remove_tags = [{'class':"RelatedArticle"}]
  24.     remove_tags_after = {'class':"Credit"}
  25.  
  26.     def parse_feeds(self):
  27.  
  28.         feeds = BasicNewsRecipe.parse_feeds(self)
  29.  
  30.         for curfeed in feeds:
  31.             delList = []
  32.             for a,curarticle in enumerate(curfeed.articles):
  33.                 if re.search(r'pheedo.jp', curarticle.url):
  34.                     delList.append(curarticle)
  35.             if len(delList)>0:
  36.                 for d in delList:
  37.                     index = curfeed.articles.index(d)
  38.                     curfeed.articles[index:index+1] = []
  39.  
  40.         return feeds
  41.