View Single Post
Old 05-17-2013, 10:41 AM   #1
scissors
Addict
scissors ought to be getting tired of karma fortunes by now.scissors ought to be getting tired of karma fortunes by now.scissors ought to be getting tired of karma fortunes by now.scissors ought to be getting tired of karma fortunes by now.scissors ought to be getting tired of karma fortunes by now.scissors ought to be getting tired of karma fortunes by now.scissors ought to be getting tired of karma fortunes by now.scissors ought to be getting tired of karma fortunes by now.scissors ought to be getting tired of karma fortunes by now.scissors ought to be getting tired of karma fortunes by now.scissors ought to be getting tired of karma fortunes by now.
 
Posts: 241
Karma: 1001369
Join Date: Sep 2010
Device: prs300, kindle keyboard 3g
NME recipe URL correction

News section wasn't getting stories

Spoiler:
Code:
from calibre.web.feeds.news import BasicNewsRecipe
from calibre import browser
import mechanize
import re
class AdvancedUserRecipe1306061239(BasicNewsRecipe):
    title          = u'New Musical Express Magazine'
    description = 'Author D.Asbury. UK Rock & Pop Mag. '
    __author__ = 'Dave Asbury'
    # last updated 17/5/13 News feed url altered
    remove_empty_feeds = True
    remove_javascript     = True
    no_stylesheets = True
    oldest_article = 7
    max_articles_per_feed = 20
    #auto_cleanup = True
    language = 'en_GB'
    compress_news_images = True
    def get_cover_url(self):
          soup = self.index_to_soup('http://www.nme.com/component/subscribe')
          cov = soup.find(attrs={'id' : 'magazine_cover'})
          
          print'&&&&&&&&&&',str(cov),'$$$$$$$$$$'
          print'SRC = ', str(cov['src'])
          print
          print
          cov2 = str(cov['src'])
          # print '**** Cov url =*', cover_url,'***'
          #print '**** Cov url =*','http://www.magazinesdirect.com/article_images/articledir_3138/1569221/1_largelisting.jpg','***'
          
          
          br = mechanize.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://www.nme.com/news?alt=rss' ), #http://feeds.feedburner.com/nmecom/rss/newsxml?format=xml'),
	#(u'Reviews', u'http://feeds2.feedburner.com/nme/SdML'),
	(u'Reviews',u'http://feed43.com/1817687144061333.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;}
		'''
scissors is offline   Reply With Quote