[scissors]

24/3/12

Uses soup to get correct cover
have set oldest article to 7 days as site updates weekly
Max articles per feed set to 10

Spoiler:

import urllib, re, mechanize
from calibre import __appname__
from calibre.utils.magick import Image, PixelWand
class AdvancedUserRecipe1324663493(BasicNewsRecipe):
    title          = u'Shortlist'
    description = 'Articles From Shortlist.com using feed43.'
    # I've set oldest article to 7 days as the website updates weekly
    oldest_article = 7
    max_articles_per_feed = 10
    remove_empty_feeds = True
    remove_javascript     = True
    no_stylesheets = True
    __author__ = 'Dave Asbury'
    # last updated 24/03/12
    language = 'en_GB'
    def get_cover_url(self):
            soup = self.index_to_soup('http://www.newsstand.co.uk/512-Weekly-Mens-Magazines/13810-Subscribe-to-SHORTLIST-Magazine-Subscription.aspx')
            #cov = soup.findl('img', attrs : alt= '"SHORTLIST Magazine UK')
            cov = soup.find(attrs={'id' : 'ContentPlaceHolder1_ctl00_imgCoverShot'}) 
            #print '******** ',cov,' ***'
            cover_url = 'http://www.newsstand.co.uk'+cov['src']
            return cover_url

    masthead_url = 'http://www.mediauk.com/logos/100/344096.png'

    #auto_cleanup_keep = '//*[@class="hero-image"]'
    #auto_cleanup_keep = '//*[@class="article "]'

    #auto_cleanup = True
    preprocess_regexps = [
    (re.compile(r'…or.*?email to your friends</a>.', re.IGNORECASE | re.DOTALL), lambda match: '')]

    keep_only_tags = [
	          dict(name='h1'),
	          dict(name='h2',attrs={'class' : 'title'}),
                              dict(name='h3',atts={'class' : 'subheading'}),
	          dict(attrs={'class' : [ 'hero-static','stand-first']}), 
                              dict(attrs={'class' : 'hero-image'}),
       	          dict(name='div',attrs={'id' : ['list','article','article alternate']}),
	          dict(name='div',attrs={'class' : 'stand-first'}),
          #dict(name='p')

        ]
    remove_tags = [dict(name='h2',attrs={'class' : 'graphic-header'}),
	       dict(attrs={'id' : ['share','twitter','facebook','digg','delicious','facebook-like']}),
	       dict(atts={'class' : ['related-content','related-content-item','related-content horizontal','more']}),

	]

    remove_tags_after = [dict(name='p',attrs={'id' : 'tags'})
	]

    feeds          = [
                               (u'This Weeks Issue', u'http://feed43.com/0323588208751786.xml'),
	     (u'Instant Improver', u'http://feed43.com/1236541026275417.xml'),
	     (u'Cool Stuff',u'http://feed43.com/6253845228768456.xml'),
                                (u'Style',u'http://feed43.com/7217107577215678.xml'),
                                (u'Films',u'http://feed43.com/3101308515277265.xml'),
	     (u'Music',u'http://feed43.com/2416400550560162.xml'),
	     (u'TV',u'http://feed43.com/4781172470717123.xml'),
	     (u'Sport',u'http://feed43.com/5303151885853308.xml'),
	     (u'Gaming',u'http://feed43.com/8883764600355347.xml'),
                                (u'Women',u'http://feed43.com/2648221746514241.xml'),
	#(u'Articles', u'http://feed43.com/3428534448355545.xml')
	]