New Musical Express update 9/6/12

[scissors]

added cover
reviews and blogs via feed43 (feeds not working?)

Spoiler:

from calibre.web.feeds.news import BasicNewsRecipe
from calibre import browser
from calibre.utils.magick import Image
import re
class AdvancedUserRecipe1306061239(BasicNewsRecipe):
    title          = u'New Musical Express Magazine'
    description = 'Author D.Asbury. UK Rock & Pop Mag. '
    __author__ = 'Dave Asbury'
    # last updated 9/6/12
    remove_empty_feeds = True
    remove_javascript     = True
    no_stylesheets = True
    oldest_article = 7
    max_articles_per_feed = 20
    #auto_cleanup = True
    language = 'en_GB'

    def get_cover_url(self):
          soup = self.index_to_soup('http://www.magazinesdirect.com/categories/mens/tv-and-music/')
          cov = soup.find(attrs={'title' : 'NME magazine subscriptions'})
          cov2 = 'http://www.magazinesdirect.com'+cov['src']
          print '***cov =  ',cov2,' ***'
          
          cover_url = str(cov2)
         # print '**** Cov url =*', cover_url,'***'
          #print '**** Cov url =*','http://www.magazinesdirect.com/article_images/articledir_3138/1569221/1_largelisting.jpg','***'
          
          br = browser()
          br.set_handle_redirect(False)
          try:
               br.open_novisit(cov2)
               cover_url = str(cov2)
          except:
                    cover_url = 'http://tawanda3000.files.wordpress.com/2011/02/nme-logo.jpg'
          return cover_url
          masthead_url   = 'http://tawanda3000.files.wordpress.com/2011/02/nme-logo.jpg'

          
          remove_tags = [
	    dict( attrs={'class':'clear_icons'}),
	    dict( attrs={'class':'share_links'}),
                        dict( attrs={'id':'right_panel'}),
	    dict( attrs={'class':'today box'}),
	                          

                      ]	

    keep_only_tags = [

	dict(name='h1'),
	#dict(name='h3'),
	dict(attrs={'class' :  'BText'}),
	dict(attrs={'class' :  'Bmore'}),
	dict(attrs={'class' : 'bPosts'}),
	dict(attrs={'class' :  'text'}),
	dict(attrs={'id' :  'article_gallery'}),
                    #dict(attrs={'class' :  'image'}),
	dict(attrs={'class' :  'article_text'})

]


	         

    feeds          = [
	(u'NME News', u'http://feeds2.feedburner.com/nmecom/rss/newsxml'),
	#(u'Reviews', u'http://feeds2.feedburner.com/nme/SdML'),
	(u'Reviews',u'http://feed43.com/4138608576351646.xml'),
                    (u'Bloggs',u'http://feed43.com/3326754333186048.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;}
		'''