Read The Sun 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 The Sun

Language: en

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

Schedule Every morning

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

class AdvancedUserRecipe1325006965(BasicNewsRecipe):

    title          = u'The Sun UK'
    cover_url = 'http://www.thesun.co.uk/img/global/new-masthead-logo.png'

    description = 'A Recipe for The Sun tabloid UK - uses feed43'
    __author__ = 'Dave Asbury'
    # last updated 20/2/12
    language = 'en_GB'
    oldest_article = 1
    max_articles_per_feed = 15
    remove_empty_feeds = True
    no_stylesheets = True

    masthead_url = 'http://www.thesun.co.uk/sol/img/global/Sun-logo.gif'
    encoding = 'cp1251'

    encoding = 'cp1252'
    remove_empty_feeds = True
    remove_javascript     = True
    no_stylesheets = True

    extra_css  = '''
    body{ text-align: justify; font-family:Arial,Helvetica,sans-serif; font-size:11px; font-size-adjust:none; font-stretch:normal; font-style:normal; font-variant:normal; font-weight:normal;}
                     '''

    preprocess_regexps = [
        (re.compile(r'<div class="foot-copyright".*?</div>', re.IGNORECASE | re.DOTALL), lambda match: '')]

    keep_only_tags = [
                               dict(name='h1'),dict(name='h2',attrs={'class' : 'medium centered'}),
               dict(name='div',attrs={'class' : 'text-center'}),
               dict(name='div',attrs={'id' : 'bodyText'})
               # dict(name='p')
               ]

    remove_tags=[
           #dict(name='head'),
           dict(attrs={'class' : ['mystery-meat-link','ltbx-container','ltbx-var ltbx-hbxpn','ltbx-var ltbx-nav-loop','ltbx-var ltbx-url']}),
                           dict(name='div',attrs={'class' : 'cf'}),
           dict(attrs={'title' : 'download flash'}),
                           dict(attrs={'style' : 'padding: 5px'})

           ]

    feeds          = [
        (u'News','http://feed43.com/2517447382644748.xml'),
        (u'Sport', u'http://feed43.com/4283846255668687.xml'),
        (u'Bizarre', u'http://feed43.com/0233840304242011.xml'),
        (u'Film',u'http://feed43.com/1307545221226200.xml'),
        (u'Music',u'http://feed43.com/1701513435064132.xml'),
        (u'Sun Woman',u'http://feed43.com/0022626854226453.xml'),
    ]