[kiklop74]

Originally Posted by mccande

This is a great program.

My early attempts at writing recipes in Python were not a great success.

Could anyone help with a recipe for the following publications

http://www.timesonline.co.uk/tol/news/

Here goes:

#!/usr/bin/env  python

__license__   = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
'''
timesonline.co.uk
'''

from calibre.web.feeds.news import BasicNewsRecipe

class Timesonline(BasicNewsRecipe):
    title                 = u'The Times Online'
    __author__            = 'Darko Miletic'
    description           = 'UK news'    
    oldest_article        = 7
    max_articles_per_feed = 100
    no_stylesheets        = True
    use_embedded_content  = False
    simultaneous_downloads = 1

    remove_tags_after  = dict(name='div', attrs={'class':'bg-666'})
    remove_tags = [
                     dict(name='div'  , attrs={'class':'hide-from-print padding-bottom-7' })
                  ]

    feeds          = [
                        (u'Top stories from Times Online', u'http://www.timesonline.co.uk/tol/feeds/rss/topstories.xml'     )
                     ]

    def print_version(self, url):
        main, split, rest = url.partition('#')
        return main + '?print=yes'

Originally Posted by mccande

http://thescotsman.scotsman.com/

#!/usr/bin/env  python

__license__   = 'GPL v3'
__copyright__ = '2008, Darko Miletic <darko.miletic at gmail.com>'
'''
thescotsman.scotsman.com
'''

from calibre.web.feeds.news import BasicNewsRecipe

class Thescotsman(BasicNewsRecipe):
    title                 = u'The Scotsman'
    __author__            = 'Darko Miletic'
    description           = 'News from Scotland'    
    oldest_article        = 7
    max_articles_per_feed = 100
    no_stylesheets        = True
    use_embedded_content  = False
    simultaneous_downloads = 1

    keep_only_tags = [dict(name='div', attrs={'id':'viewarticle'})]
    remove_tags = [
                     dict(name='div'  , attrs={'class':'viewarticlepanel' })
                  ]

    feeds          = [
                        (u'Latest National News', u'http://thescotsman.scotsman.com/getFeed.aspx?Format=rss&sectionid=4068')
                     ]