Read Interia.pl - Sport 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 »

Sport ze strony interia.pl

Language: pl

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

Schedule Every morning

			  #!/usr/bin/env  python

__license__   = 'GPL v3'
__copyright__ = u'2010, Tomasz Dlugosz <tomek3d@gmail.com>'
'''
sport.interia.pl
'''

import re
from calibre.web.feeds.news import BasicNewsRecipe

class InteriaSport(BasicNewsRecipe):
    title          = u'Interia.pl - Sport'
    description    = u'Sport ze strony interia.pl'
    language = 'pl'
    oldest_article = 7
    __author__ = u'Tomasz D\u0142ugosz'
    simultaneous_downloads = 3
    no_stylesheets = True
    remove_javascript = True
    max_articles_per_feed = 100

    feeds          = [(u'Wydarzenia sportowe', u'http://kanaly.rss.interia.pl/sport.xml'), 
                      (u'Pi\u0142ka no\u017cna', u'http://kanaly.rss.interia.pl/pilka_nozna.xml'), 
                      (u'Siatk\xf3wka', u'http://kanaly.rss.interia.pl/siatkowka.xml'), 
                      (u'Koszyk\xf3wka', u'http://kanaly.rss.interia.pl/koszykowka.xml'), 
                      (u'NBA', u'http://kanaly.rss.interia.pl/nba.xml'), 
                      (u'Kolarstwo', u'http://kanaly.rss.interia.pl/kolarstwo.xml'), 
                      (u'\u017bu\u017cel', u'http://kanaly.rss.interia.pl/zuzel.xml'), 
                      (u'Tenis', u'http://kanaly.rss.interia.pl/tenis.xml')]

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

    remove_tags = [dict(name='div', attrs={'class':'object gallery'}),
                   dict(name='div', attrs={'class':'box fontSizeSwitch'})]

    extra_css = '''
        .articleDate {
        font-size: 0.5em;
        color: black;
        }

        .articleFoto {
        display: block;
        font-family: sans;
        font-size: 0.5em;
        text-indent: 0
        color: black;
        }

        .articleText {
        display: block;
        margin-bottom: 1em;
        margin-left: 0;
        margin-right: 0;
        margin-top: 1em
        color: black;
        }

        .articleLead {
        font-size: 1.2em;
        }
        '''

    preprocess_regexps = [
        (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in 
        [
            (r'<p><a href.*?</a></p>', lambda match: ''),
           # FIXME
           #(r'(<div id="newsAddContent">)(.*?)(<a href=".*">)(.*?)(</a>)', lambda match: '\1\2\4'),
            (r'<p>(<i>)?<b>(ZOBACZ|CZYTAJ) T.*?</div>', lambda match: '</div>')
        ]
    ]