calibre/recipes/countryfile.recipe
2012-12-16 17:14:59 +05:30

52 lines
2 KiB
Text

from calibre import browser
from calibre.web.feeds.news import BasicNewsRecipe
import re
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 8/12/12
language = 'en_GB'
oldest_article = 30
max_articles_per_feed = 25
remove_empty_feeds = True
no_stylesheets = True
auto_cleanup = True
ignore_duplicate_articles = {'title', 'url'}
#articles_are_obfuscated = True
#article_already_exists = False
#feed_hash = ''
def get_cover_url(self):
soup = self.index_to_soup('http://www.countryfile.com/magazine')
cov = soup.find(attrs={'class' : re.compile('imagecache imagecache-250px_wide')})#'width' : '160',
print '&&&&&&&& ',cov,' ***'
cov=str(cov)
#cov2 = re.findall('http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', cov)
cov2 = re.findall('/(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', cov)
cov2 = str(cov2)
cov2= "http://www.countryfile.com"+cov2[2:len(cov2)-8]
print '******** ',cov2,' ***'
# try to get cover - if can't get known cover
br = 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'),
]