Daily Express 9/9/13

[scissors]

Added Article authors and got rid of quoted text

Spoiler:

from calibre import browser
from calibre.web.feeds.news import BasicNewsRecipe
import mechanize
from calibre.constants import config_dir, CONFIG_DIR_MODE
import os, os.path, urllib
class AdvancedUserRecipe1376229553(BasicNewsRecipe):
    title          = u'Daily Express'
    __author__ = 'Dave Asbury'
    # 9-9-13 added article author and now use (re.compile(r'>[\w].+? News<'
    encoding    = 'utf-8'
    remove_empty_feeds = True
    #remove_javascript     = True
    no_stylesheets        = True
    oldest_article = 1
    max_articles_per_feed = 10
    #auto_cleanup = True
    compress_news_images = True
    compress_news_images_max_size = 30
    ignore_duplicate_articles = {'title', 'url'}
    masthead_url = 'http://cdn.images.dailyexpress.co.uk/img/page/express_logo.png'
    
    
    preprocess_regexps = [

		(re.compile(r'widget', re.IGNORECASE | re.DOTALL), lambda match: ''),
         		(re.compile(r'Related articles', re.IGNORECASE | re.DOTALL), lambda match: ''),
         		(re.compile(r'Add Your Comment<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
		(re.compile(r'>More [\w].+?<', re.IGNORECASE ), lambda match: '><'),
                                (re.compile(r'>[\w].+? News<', re.IGNORECASE ), lambda match: '><'),
                                #(re.compile(r'Health News<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
	                #(re.compile(r'Car News<', re.IGNORECASE | re.DOTALL), lambda match: '<'),  
         		#(re.compile(r'TV & Radio News<', re.IGNORECASE | re.DOTALL), lambda match: '<'),                       
         		#(re.compile(r'Food & Recipe News<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
         		#(re.compile(r'More City & Business<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
         		#(re.compile(r'Travel News<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
         		#(re.compile(r'Garden News<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
		#(re.compile(r'Fashion & Beauty News<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
		#(re.compile(r'More Personal Finance<', re.IGNORECASE | re.DOTALL), lambda match: '<'),
                                #(re.compile(r'<h3>More UK</h3>', re.IGNORECASE | re.DOTALL), lambda match: ''),
         			
		]


    remove_tags = [
                                dict(attrs={'class' : 'quote'}),
		#dict(attrs={'class' : 'author'}),
                                dict(name='footer'),
                                dict(attrs={'id' : 'header_addons'}),
		dict(attrs={'class' : 'hoverException'}),
                                dict(name='_li'),dict(name='li'),
          		dict(attrs={'class' : 'box related-articles clear'}),
                                dict(attrs={'class' : 'news-list'}),
                                dict(attrs={'class' : 'sponsored-section'}),
                                dict(attrs={'class' : 'pull-quote on-right'}),
                                dict(attrs={'class' : 'pull-quote on-left'}),
                                
          	             ]
    keep_only_tags = [   
		dict(name='h1'),
                                dict(attrs={'class' : 'publish-info'}),
                                dict(name='h3', limit=2),
                                dict(attrs={'class' : 'clearfix hR new-style'}),
                             ]
    
    

    
    feeds          = [(u'UK News', u'http://www.express.co.uk/posts/rss/1/uk'),
    	         (u'World News',u'http://www.express.co.uk/posts/rss/78/world'),
                         (u'Finance',u'http://www.express.co.uk/posts/rss/21/finance'),
	         (u'Sport',u'http://www.express.co.uk/posts/rss/65/sport'),
	         (u'Entertainment',u'http://www.express.co.uk/posts/rss/18/entertainment'),
                         (u'Lifestyle',u'http://www.express.co.uk/posts/rss/8/life&style'),
	         (u'Fun',u'http://www.express.co.uk/posts/rss/110/fun'),
                        ]

    def get_cover_url(self):
            soup = self.index_to_soup('http://www.express.co.uk/ourpaper/')
            cov = soup.find(attrs={'src' : re.compile('http://images.dailyexpress.co.uk/img/covers/')})
            cov=str(cov)
            cov2 =  re.findall('http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', cov)
            print '&&&&&&&& ',cov2,' ***'
            
            cov=str(cov2)
            cov=cov[2:len(cov)-2]
            print '&&&&&&&& ',cov,' ***'
            cover_url=cov
            return cover_url

    extra_css = '''
                    h1{font-weight:bold;font-size:175%;}
                    h2{font-weight:normal;font-size:75%;}
                    #p{font-size:14px;}
                    #body{font-size:14px;}
                    .photo-caption {display: block;margin-left: auto;margin-right: auto;width:100%;font-size:40%;}
	    .publish-info {font-size:50%;}
                    .photo img {display: block;margin-left: auto;margin-right: auto;width:100%;}
      '''