calibre/resources/recipes/dilbert.recipe
2010-02-10 11:09:41 -07:00

49 lines
1.5 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
http://www.dilbert.com
'''
import re
from calibre.web.feeds.recipes import BasicNewsRecipe
class DosisDiarias(BasicNewsRecipe):
title = 'Dilbert'
__author__ = 'Darko Miletic'
description = 'Dilbert'
oldest_article = 5
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = True
encoding = 'utf-8'
publisher = 'UNITED FEATURE SYNDICATE, INC.'
category = 'comic'
language = 'en'
conversion_options = {
'comments' : description
,'tags' : category
,'language' : language
,'publisher' : publisher
}
feeds = [(u'Dilbert', u'http://feeds.dilbert.com/DilbertDailyStrip' )]
preprocess_regexps = [
(re.compile('strip\..*\.gif', re.DOTALL|re.IGNORECASE),
lambda match: 'strip.zoom.gif')
]
def get_article_url(self, article):
return article.get('feedburner_origlink', None)
def preprocess_html(self, soup):
for tag in soup.findAll(name='a'):
if tag['href'].find('http://feedads') >= 0:
tag.extract()
return soup