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_it_news.recipe < prev    next >
Text File  |  2011-09-09  |  1KB  |  35 lines
  1. from calibre.web.feeds.news import BasicNewsRecipe
  2. import re
  3.  
  4. class MainichiDailyITNews(BasicNewsRecipe):
  5.     title          = u'\u6bce\u65e5\u65b0\u805e(IT&\u5bb6\u96fb)'
  6.     __author__     = 'Hiroshi Miura'
  7.     oldest_article = 2
  8.     max_articles_per_feed = 100
  9.     description    = 'Japanese traditional newspaper Mainichi Daily News - IT and electronics'
  10.     publisher      = 'Mainichi Daily News'
  11.     category       = 'news, Japan, IT, Electronics'
  12.     language       = 'ja'
  13.  
  14.     feeds          = [(u'IT News', u'http://mainichi.pheedo.jp/f/mainichijp_electronics')]
  15.  
  16.     remove_tags_before = {'class':"NewsTitle"}
  17.     remove_tags = [{'class':"RelatedArticle"}]
  18.     remove_tags_after = {'class':"Credit"}
  19.  
  20.     def parse_feeds(self):
  21.  
  22.         feeds = BasicNewsRecipe.parse_feeds(self)
  23.  
  24.         for curfeed in feeds:
  25.             delList = []
  26.             for a,curarticle in enumerate(curfeed.articles):
  27.                 if re.search(r'pheedo.jp', curarticle.url):
  28.                     delList.append(curarticle)
  29.             if len(delList)>0:
  30.                 for d in delList:
  31.                     index = curfeed.articles.index(d)
  32.                     curfeed.articles[index:index+1] = []
  33.  
  34.         return feeds
  35.