update daily mirror uk

[scissors]

Well no-one seems to read the mirror apart from me :-)

But for anyone else who may be wondering why it's stopped working - they pulled the rss feeds.

anyway - here's a modded recipe using feed43 that works

Spoiler:

from calibre.web.feeds.news import BasicNewsRecipe
import re
from calibre.utils.magick import Image, PixelWand
class AdvancedUserRecipe1306061239(BasicNewsRecipe):
    title          = u'The Daily Mirror'
    description = 'News as provide by The Daily Mirror -UK'

    __author__ = 'Dave Asbury'
    # last updated 11/2/12
    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 = 5
    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={'id' : 'body-content'}),
       #dict(name='div',atts={'class' : 'article-body'}),
       #dict(attrs={'class' : ['article-attr','byline append-1','published']}),
       #dict(name='p'),
       # ]

    #remove_tags_after = [dict (name='div',attrs={'class' : 'related'})]

    remove_tags = [
           dict(name='title'),
           dict(name='div',attrs={'class' : ['inline-ad span-16 last','caption']}),
          # dict(name='div',attrs={'id' : ['sidebar','menu','search-box','roffers-top']}),
           #dict(name='div',attrs={'class' :['inline-ad span-16 last','article-resize','related','list teasers']}),
           #dict(attrs={'class' : ['channellink','article-tags','replace','append-html']}),
          ]
    
   # preprocess_regexps = [
    #(re.compile(r'<dl class="q-search">.*?</dl>', re.IGNORECASE | re.DOTALL), lambda match: '')]
    preprocess_regexps = [
    (re.compile(r'- mirror.co.uk', re.IGNORECASE | re.DOTALL), lambda match: '')]
    
    preprocess_regexps = [
    (re.compile(r'Advertisement >>', re.IGNORECASE | re.DOTALL), lambda match: '')]
    
    #preprocess_regexps = [
    #(re.compile(r'Sponsored Links', re.IGNORECASE | re.DOTALL), lambda match: '')]
    
    feeds          = [

        (u'UK News', u'http://feed43.com/0287771688643868.xml')
        ,(u'Tech News', u'http://feed43.com/2455520588350501.xml')
        ,(u'Weird World','http://feed43.com/0863800333634654.xml')
        ,(u'Sport','http://feed43.com/7713243036546130.xml')
        ,(u'Sport : Boxing ','http://feed43.com/0414732220804255.xml')
        ,(u'Sport : Rugby Union','http://feed43.com/4710138762362383.xml')
        ,(u'Sport : Other','http://feed43.com/4501416886323415.xml')
        ,(u'TV and Film','http://feed43.com/5238302853765104.xml')
        ,(u'Celebs','http://feed43.com/8770061048844683.xml')        
        ,(u'Life Style : Family','http://feed43.com/4356170742410338.xml')
         ,(u'Travel','http://feed43.com/1436576006476607.xml')



           # example of commented out feed not needed ,(u'Travel','http://www.mirror.co.uk/advice/travel/rss.xml')
  ]
    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;}
                    h1{ font-size:18px;}
                    img { display:block}
                	 '''
    def postprocess_html(self, soup, first):
        #process all the images
        for tag in soup.findAll(lambda tag: tag.name.lower()=='img' and tag.has_key('src')):
            iurl = tag['src']
            img = Image()
            img.open(iurl)
            if img < 0:
                raise RuntimeError('Out of memory')
            img.type = "GrayscaleType"
            img.save(iurl)
        return soup