Recipe for NRC Handelsblad (RSS feeds)

[veezh]

__license__   = 'GPL v3'
__copyright__ = '2012'
'''
nrc.nl
'''
import re
from calibre.web.feeds.recipes import BasicNewsRecipe

class NRC(BasicNewsRecipe):
    title                  = 'NRC Handelsblad'
    __author__             = 'veezh'
    description            = 'Nieuws'
    oldest_article         = 1
    max_articles_per_feed  = 100
    no_stylesheets         = True
    #delay                  = 1
    use_embedded_content   = False
    encoding               = 'utf-8'
    publisher              = 'nrc.nl'
    category               = 'news, Netherlands, world'
    language               = 'nl_NL'
    timefmt = ''
    #publication_type       = 'newsportal'
    extra_css = '''
                    h1{font-size:130%;}
                    #h2{font-size:100%;font-weight:normal;}
                    #.href{font-size:xx-small;}
                    .bijschrift{color:#666666; font-size:x-small;}
                    #.main-article-info{font-family:Arial,Helvetica,sans-serif;}
                    #full-contents{font-size:small; font-family:Arial,Helvetica,sans-serif;font-weight:normal;}
                    #match-stats-summary{font-size:small; font-family:Arial,Helvetica,sans-serif;font-weight:normal;}
                '''
    #preprocess_regexps     = [(re.compile(r'<!--.*?-->', re.DOTALL), lambda m: '')]
    conversion_options = {
                              'comments'        : description
                             ,'tags'            : category
                             ,'language'        : language
                             ,'publisher'       : publisher
                             ,'linearize_tables': True
                          }

    remove_empty_feeds = True

    filterDuplicates = True

    def preprocess_html(self, soup):
        for alink in soup.findAll('a'):
            if alink.string is not None:
               tstr = alink.string
               alink.replaceWith(tstr)
        return soup

    keep_only_tags = [dict(name='div', attrs={'class':'article'})]
    remove_tags_after = [dict(id='broodtekst')]

#    keep_only_tags    = [
#                       dict(name='div', attrs={'class':['label']})
#                        ]

#    remove_tags_after = [dict(name='dl', attrs={'class':['tags']})]

#    def get_article_url(self, article):
#        link = article.get('link')
#        if 'blog' not in link and ('chat' not in link):
#             return link

    feeds          = [
#                      ('Nieuws', 'http://www.nrc.nl/rss.php'),
                      ('Binnenland', 'http://www.nrc.nl/nieuws/categorie/binnenland/rss.php'),
                      ('Buitenland', 'http://www.nrc.nl/nieuws/categorie/buitenland/rss.php'),
                      ('Economie', 'http://www.nrc.nl/nieuws/categorie/economie/rss.php'),
                      ('Wetenschap', 'http://www.nrc.nl/nieuws/categorie/wetenschap/rss.php'),
                      ('Cultuur', 'http://www.nrc.nl/nieuws/categorie/cultuur/rss.php'),
                      ('Boeken', 'http://www.nrc.nl/boeken/rss.php'),
                      ('Tech', 'http://www.nrc.nl/tech/rss.php/'),
                      ('Klimaat', 'http://www.nrc.nl/klimaat/rss.php/'),
                    ]

[kovidgoyal]

Isn't there already a recipe for NRC Handelblad?

[veezh]

Yes, but as far as I know, it hasn't worked for quite some time because of major changes to the website.

[kovidgoyal]

Isn't the current recipe a subscription based one that downloads the epub published by Handlesblad? You saying that doesn't work?

[veezh]

Sorry for the confusion. AFAIK, neither the RSS recipe by Darko Miletic (the built-in recipe called NRC) nor the epub recipe works now. The first one stopped working quite some time ago when the website changed, and I'm guessing the epub one doesn't work any more, since the epub version of the paper is now behind a pay wall.

[kovidgoyal]

Ah OK