countryfile.com

[scissors]

Correction to string slicing - get current cover off webpage

Spoiler:

from calibre import browser
from calibre.web.feeds.news import BasicNewsRecipe
import mechanize
class AdvancedUserRecipe1325006965(BasicNewsRecipe):
    title          = u'Countryfile.com'
    #cover_url = 'http://www.countryfile.com/sites/default/files/imagecache/160px_wide/cover/2_1.jpg'
    __author__ = 'Dave Asbury'
    description           = 'The official website of Countryfile Magazine'
    # last updated 9/9//12
    language = 'en_GB'
    oldest_article = 30
    max_articles_per_feed = 25
    remove_empty_feeds = True
    no_stylesheets = True
    auto_cleanup = True
    #articles_are_obfuscated = True
    def get_cover_url(self):
            soup = self.index_to_soup('http://www.countryfile.com/')
            cov = soup.find(attrs={'class' : 'imagecache imagecache-160px_wide imagecache-linked imagecache-160px_wide_linked'})
            print '******** ',cov,' ***'
            cov2 = str(cov)
            cov2=cov2[140:223]
            print '******** ',cov2,' ***'
            #cov2='http://www.countryfile.com/sites/default/files/imagecache/160px_wide/cover/1b_0.jpg'
            # try to get cover - if can't get known cover
            br = mechanize.Browser()
            
            br.set_handle_redirect(False)
            try:
                br.open_novisit(cov2)
                cover_url = cov2
            except:
                  cover_url = 'http://www.countryfile.com/sites/default/files/imagecache/160px_wide/cover/2_1.jpg'
            return cover_url
    remove_tags    = [
                             # dict(attrs={'class' : ['player']}),

    ]
    feeds          = [
    (u'Homepage', u'http://www.countryfile.com/rss/home'),
    (u'Country News', u'http://www.countryfile.com/rss/news'),
            (u'Countryside', u'http://www.countryfile.com/rss/countryside'),
            ]