home *** CD-ROM | disk | FTP | other *** search
/ Maximum CD 2010 November / maximum-cd-2010-11.iso / DiscContents / calibre-0.7.13.msi / file_3707 < prev    next >
Encoding:
Text File  |  2009-10-14  |  2.6 KB  |  70 lines
  1. #!/usr/bin/env  python
  2.  
  3. __license__   = 'GPL v3'
  4. __copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
  5.  
  6. '''
  7. dnevniavaz.ba
  8. '''
  9.  
  10. import re
  11. from calibre.web.feeds.recipes import BasicNewsRecipe
  12. from calibre.ebooks.BeautifulSoup import Tag
  13.  
  14. class DnevniAvaz(BasicNewsRecipe):
  15.     title                 = 'Dnevni Avaz'
  16.     __author__            = 'Darko Miletic'
  17.     description           = 'Latest news from Bosnia'
  18.     publisher             = 'Dnevni Avaz'
  19.     category              = 'news, politics, Bosnia and Herzegovina'
  20.     oldest_article        = 2
  21.     max_articles_per_feed = 100
  22.     no_stylesheets        = True
  23.     encoding              = 'utf-8'
  24.     use_embedded_content  = False
  25.     remove_javascript     = True
  26.     cover_url             = 'http://www.dnevniavaz.ba/img/logo.gif'
  27.     lang                  = 'bs-BA'
  28.     language = 'bs'
  29.  
  30.     direction             = 'ltr'
  31.  
  32.     extra_css = '@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)} body{font-family: serif1, serif} .article_description{font-family: serif1, serif}'
  33.  
  34.     conversion_options = {
  35.                           'comment'          : description
  36.                         , 'tags'             : category
  37.                         , 'publisher'        : publisher
  38.                         , 'language'         : lang
  39.                         , 'pretty_print'     : True
  40.                         }
  41.  
  42.     preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
  43.  
  44.     keep_only_tags = [dict(name='div', attrs={'id':['fullarticle-title','fullarticle-leading','fullarticle-date','fullarticle-text','articleauthor']})]
  45.  
  46.     remove_tags = [dict(name=['object','link','base'])]
  47.  
  48.     feeds = [
  49.                (u'Najnovije'     , u'http://www.dnevniavaz.ba/rss/novo'     )
  50.               ,(u'Najpopularnije', u'http://www.dnevniavaz.ba/rss/popularno')
  51.             ]
  52.  
  53.     def replace_tagname(self,soup,tagname,tagid,newtagname):
  54.         headtag = soup.find(tagname,attrs={'id':tagid})
  55.         if headtag:
  56.            headtag.name = newtagname
  57.         return
  58.  
  59.     def preprocess_html(self, soup):
  60.         soup.html['xml:lang'] = self.lang
  61.         soup.html['lang']     = self.lang
  62.         mlang = Tag(soup,'meta',[("http-equiv","Content-Language"),("content",self.lang)])
  63.         mcharset = Tag(soup,'meta',[("http-equiv","Content-Type"),("content","text/html; charset=UTF-8")])
  64.         soup.head.insert(0,mlang)
  65.         soup.head.insert(1,mcharset)
  66.         self.replace_tagname(soup,'div','fullarticle-title'  ,'h1')
  67.         self.replace_tagname(soup,'div','fullarticle-leading','h3')
  68.         self.replace_tagname(soup,'div','fullarticle-date'   ,'h5')
  69.         return self.adeify_images(soup)
  70.