update Dilbert recipe

This commit is contained in:
intromatyk 2013-07-24 22:32:54 +02:00
parent 9a6073fcfb
commit f555ab5279

View File

@ -16,7 +16,7 @@ class DilbertBig(BasicNewsRecipe):
oldest_article = 15
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = True
use_embedded_content = False
encoding = 'utf-8'
publisher = 'UNITED FEATURE SYNDICATE, INC.'
category = 'comic'
@ -30,25 +30,13 @@ class DilbertBig(BasicNewsRecipe):
,'publisher' : publisher
}
feeds = [(u'Dilbert', u'http://feed.dilbert.com/dilbert/daily_strip' )]
def get_article_url(self, article):
return article.get('feedburner_origlink', None)
feeds = [(u'Dilbert', u'http://feed.dilbert.com/dilbert/daily_strip')]
preprocess_regexps = [
(re.compile('strip\..*\.gif', re.DOTALL|re.IGNORECASE), lambda match: 'strip.zoom.gif')
]
def preprocess_html(self, soup):
for tag in soup.findAll(name='a'):
if tag['href'].find('http://feedads') >= 0:
tag.extract()
return soup
extra_css = '''
h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;}
h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;}
img {max-width:100%; min-width:100%;}
p{font-family:Arial,Helvetica,sans-serif;font-size:small;}
body{font-family:Helvetica,Arial,sans-serif;font-size:small;}
'''
for tag in soup.findAll(name='input'):
image = BeautifulSoup('<img src=' + tag['value'] + '></img>')
return image