uk paper The Mirror Updated 8/6/12

[scissors]

Removed spurious hyperlinks in main artical text.
removed Gallery pics from article

Spoiler:

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

class AdvancedUserRecipe1306061239(BasicNewsRecipe):
    title          = u'The Daily Mirror'
    description = 'News as provided by The Daily Mirror -UK'

    __author__ = 'Dave Asbury'
    # last updated 8/6/12
    language = 'en_GB'
    #cover_url = 'http://yookeo.com/screens/m/i/mirror.co.uk.jpg'

    masthead_url = 'http://www.nmauk.co.uk/nma/images/daily_mirror.gif'


    oldest_article = 1
    max_articles_per_feed = 12
    remove_empty_feeds = True
    remove_javascript     = True
    no_stylesheets = True
   # auto_cleanup = True
    #conversion_options = { 'linearize_tables' : True }



    keep_only_tags = [         dict(name='h1'),
                         dict(name='div',attrs={'class' : 'lead-text'}),
                         dict(name='div',attrs={'class' : 'styleGroup clearfix'}),
                         dict(name='div',attrs={'class' : 'widget relatedContents pictures widget-editable viziwyg-section-245 inpage-widget-158123'}),
                        # dict(name='figure',attrs={'class' : 'clearfix'}),
                         dict(name='div',attrs={'class' :'body '}),

       #dict(attrs={'class' : ['article-attr','byline append-1','published']}),
       #dict(name='p'),
        ]


    remove_tags = [
           dict(attrs={'class' : ['article sa-teaser type-opinion','image-gallery','gallery-caption']}),
           dict(attrs={'class' : 'comment'}),
           dict(name='title'),
           dict(name='ul',attrs={'class' :  'clearfix breadcrumbs '}),
           dict(name='ul',attrs={'id' : 'login-201109171215'}),
           dict(name='div',attrs={'class' : ['inline-ad span-16 last','caption']}),#'widget navigation breadcrumb widget-editable viziwyg-section-198 inpage-widget-80721 span-17','image-credit'
                    ]

    preprocess_regexps = [
        (re.compile(r'- mirror.co.uk', re.IGNORECASE | re.DOTALL), lambda match: '')]


    feeds          = [
        (u'News',u'http://www.mirror.co.uk/news/rss.xml'),
        (u'Sports',u'http://www.mirror.co.uk/sport/rss.xml'),
        (u'3AM',u'http://www.mirror.co.uk/3am/rss.xml'),
        (u'Lifestyle',u'http://www.mirror.co.uk/lifestyle/rss.xml')




           # example of commented out feed not needed ,(u'Travel','http://www.mirror.co.uk/advice/travel/rss.xml')
  ]
    extra_css = '''
                    h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
                    h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
                    p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
                    body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
		'''

    def get_cover_url(self):
        soup = self.index_to_soup('http://www.politicshome.com/uk/latest_frontpage.html')
# look for the block containing the mirror button and url
        cov = soup.find(attrs={'style' : 'background-image: url(http://www.politicshome.com/images/sources/source_frontpage_button_92.gif);'})
        cov2 = str(cov)
        cov2='http://www.politicshome.com'+cov2[9:-142]
#cov2 now contains url of the page containing pic
        soup = self.index_to_soup(cov2)
        cov = soup.find(attrs={'id' : 'large'})
        cov2 = str(cov)
        cov2=cov2[27:-18]
        #cov2 now is pic url, now  go back to original function
        br = browser()
        br.set_handle_redirect(False)
        try:
            br.open_novisit(cov2)
            cover_url = cov2
        except:
            cover_url ='http://profile.ak.fbcdn.net/hprofile-ak-snc4/373019_6149699161_1710984811_n.jpg'

        # print '******** string is  ', cov2,' ***'
        #cover_url = cov2
        #cover_url = 'http://www.thesun.co.uk/img/global/new-masthead-logo.png'
        return cover_url