Read Elsevier.nl on your iPad or Kindle in no time. Click download to load the free ebook on your reader.

Check out all the available public recipes or write your own with these quick start guides. ReadBeam is built on calibre, so everything in the docs and the fora applies here as well.

Download for free »

News from Holland

Language: nl

Requires Subscription: No, it's available as free ebook

Schedule Every morning

			  __license__   = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
elsevier.nl
'''

from calibre.web.feeds.news import BasicNewsRecipe

class Pagina12(BasicNewsRecipe):
    title                 = 'Elsevier.nl'
    __author__            = 'Darko Miletic'
    description           = 'News from Holland'
    publisher             = 'elsevier.nl'
    category              = 'news, politics, Holland'
    oldest_article        = 2
    max_articles_per_feed = 200
    no_stylesheets        = True
    encoding              = 'utf-8'
    use_embedded_content  = False
    language              = 'nl'
    country               = 'NL'    
    remove_empty_feeds    = True
    masthead_url          = 'http://www.elsevier.nl/static/elsevier/stdimg/logo.gif'
    extra_css             = ' body{font-family: Arial,Helvetica,sans-serif } img{margin-bottom: 0.4em}  '

    conversion_options = {
                          'comment'   : description
                        , 'tags'      : category
                        , 'publisher' : publisher
                        , 'language'  : language
                        }
    
    keep_only_tags     = dict(attrs={'id':'artikel_container'})
    remove_tags_before = dict(attrs={'id':'breadcrumb_container'})
    remove_tags_after  = dict(attrs={'class':'author_link'})
    remove_tags        = [
                          dict(attrs={'id':'breadcrumb_container'})
                         ,dict(name='div',attrs={'class':'pullout_vak'})
                         ]
    remove_attributes  = ['width','height']

    feeds = [
               (u'Laatste nieuws'      , u'http://www.elsevier.nl/web/RSS/Homepage-RSS.htm?output=xml'         )
              ,(u'Nederland'           , u'http://www.elsevier.nl/web/RSS/Nederland-RSS.htm?output=xml'        )
              ,(u'Politiek'            , u'http://www.elsevier.nl/web/RSS/Politiek-RSS.htm?output=xml'         )
              ,(u'Europese Unie'       , u'http://www.elsevier.nl/web/RSS/Europese-Unie-RSS.htm?output=xml'    )
              ,(u'Buitenland'          , u'http://www.elsevier.nl/web/RSS/Buitenland-RSS.htm?output=xml'       )
              ,(u'Economie'            , u'http://www.elsevier.nl/web/RSS/Economie-RSS.htm?output=xml'         )
              ,(u'Wetenschap'          , u'http://www.elsevier.nl/web/RSS/Wetenschap-RSS.htm?output=xml'       )
              ,(u'Cultuur & Televisie' , u'http://www.elsevier.nl/web/RSS/Cultuur-Televisie-RSS.htm?output=xml')
              ,(u'Society'             , u'http://www.elsevier.nl/web/RSS/Society-RSS.htm?output=xml'          )
              ,(u'Internet&/Gadgets'   , u'http://www.elsevier.nl/web/RSS/Internet-Gadgets-RSS.htm?output=xml' )
              ,(u'Comentaren'          , u'http://www.elsevier.nl/web/RSS/Commentaren-RSS.htm?output=xml'      )              
            ]

    def print_version(self, url):
        return url + '?print=true'

    def get_article_url(self, article):
        return article.get('guid',  None).rpartition('?')[0]
        
    def preprocess_html(self, soup):
        for item in soup.findAll(style=True):
            del item['style']
        return soup