Read The Scotsman 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 Scotland

Language: en

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

Schedule Every morning

			  
__license__   = 'GPL v3'
__copyright__ = '2008 - 2011, Darko Miletic <darko.miletic at gmail.com>'
'''
www.scotsman.com/the-scotsman
'''

from calibre.web.feeds.news import BasicNewsRecipe

class TheScotsman(BasicNewsRecipe):
    title                 = 'The Scotsman'
    __author__            = 'Darko Miletic'
    description           = 'News from Scotland'
    publisher             = 'Johnston Publishing Ltd.'
    category              = 'news, politics, Scotland, UK'    
    oldest_article        = 2
    max_articles_per_feed = 100
    no_stylesheets        = True
    use_embedded_content  = False
    language              = 'en_GB'
    encoding              = 'utf-8'
    publication_type      = 'newspaper'
    remove_empty_feeds    = True    
    masthead_url          = 'http://www.scotsman.com/webimage/swts_thescotsman_image_e_7_25526!image/3142543874.png_gen/derivatives/default/3142543874.png'
    extra_css             = 'body{font-family: Arial,Helvetica,sans-serif}'
    
    
    keep_only_tags    = [dict(attrs={'class':'editorialSection'})]
    remove_tags_after = dict(attrs={'class':'socialBookmarkPanel'})
    remove_tags       = [
                           dict(name=['meta','iframe','object','embed','link']),
                           dict(attrs={'class':['secondaryArticlesNav','socialBookmarkPanel']}),
                           dict(attrs={'id':'relatedArticles'})
                        ]
    remove_attributes = ['lang']
    
    conversion_options = {
                          'comment'   : description
                        , 'tags'      : category
                        , 'publisher' : publisher
                        , 'language'  : language
                        }
    
    feeds          = [
                        ('Latest News'  , 'http://www.scotsman.com/cmlink/1.957140' ),
                        ('UK'           , 'http://www.scotsman.com/cmlink/1.957142' ),
                        ('Scotland'     , 'http://www.scotsman.com/cmlink/1.957141' ),
                        ('International', 'http://www.scotsman.com/cmlink/1.957143' ),
                        ('Politics'     , 'http://www.scotsman.com/cmlink/1.957044' ),
                        ('Arts'         , 'http://www.scotsman.com/cmlink/1.1804825'),
                        ('Entertainment', 'http://www.scotsman.com/cmlink/1.957053' ),
                        ('Sports'       , 'http://www.scotsman.com/cmlink/1.957151' ),
                        ('Business'     , 'http://www.scotsman.com/cmlink/1.957156' ),                        
                        ('Features'     , 'http://www.scotsman.com/cmlink/1.957149' ),
                        ('Opinion'      , 'http://www.scotsman.com/cmlink/1.957054' )
                     ]
                     
    def preprocess_html(self, soup):
        for item in soup.findAll(style=True):
            del item['style']
        for item in soup.findAll('img'):
            if not item.has_key('alt'):
               item['alt'] = 'image'
        return soup