[scissors]

image tags changed

Spoiler:

import re

from calibre.web.feeds.news import BasicNewsRecipe
from calibre import browser
class AdvancedUserRecipe1390132023(BasicNewsRecipe):
    title          = u'Daily Express'
    __author__ = 'Dave Asbury'
   # 21.11.14 written due to website changes
    oldest_article = 1
    max_articles_per_feed = 10
    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'
    auto_cleanup_keep = '//*[@class="author"]|//section[@class="photo changeSpace"]'
    auto_cleanup = True
    no_stylesheets        = False
    
    preprocess_regexps = [
		 (re.compile(r'\| [\w].+?\| [\w].+?\| Daily Express', re.IGNORECASE | re.DOTALL), lambda match: ''),
         	
         		]
    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):
        print '============Cover ================='
        print
        soup = self.index_to_soup('http://www.express.co.uk/ourpaper/')
        cov = soup.find(attrs={'src' : re.compile('http://cdn.images.express.co.uk/img/covers/')})
        cov=str(cov)
        print '^^^^^^^', cov
        cov2 =  re.findall('http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', cov)

        cov=str(cov2)
        cov=cov[2:len(cov)-2]

        print '&&&&&&&&',cov,'***'
        #cover_url=cov
        br = browser()
        br.set_handle_redirect(False)
        try:
            br.open_novisit(cov)
            cover_url = cov
        except:
            cover_url ='http://cdn.images.express.co.uk/img/static/ourpaper/header-back-issue-papers.jpg'

        return cover_url


    extra_css = '''
                    #h1{font-weight:bold;font-size:175%;}
                    h2{display: block;margin-left: auto;margin-right: auto;width:100%;font-weight:bold;font-size:175%;}
                    #p{font-size:14px;}
                    #body{font-size:14px;}
                    .newsCaption {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%;}
      '''