calibre/recipes/kamerabild.recipe
Kovid Goyal 567040ee1e Perform PEP8 compliance checks on the entire codebase
Some bits of PEP 8 are turned off via setup.cfg
2016-07-29 21:25:17 +05:30

44 lines
1.5 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
www.kamerabild.se
'''
from calibre.web.feeds.news import BasicNewsRecipe
class Kamerabild(BasicNewsRecipe):
title = 'Kamera & Bild'
__author__ = 'Darko Miletic'
description = 'Photo News from Sweden'
publisher = 'politiken.dk'
category = 'news, photograph, Sweden'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
remove_empty_feeds = True
use_embedded_content = False
encoding = 'utf8'
language = 'sv'
extra_css = ' body{font-family: Verdana,Arial,Helvetica,sans-serif } .title{font-weight: bold} .pricerunnerAdContainer{border-bottom: 1px solid; border-top: 1px solid; margin-top: 0.5em; margin-bottom: 0.5em} .elementTeaserKicker{font-weight: bold; color: #AE0A10} ' # noqa
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
}
feeds = [
(u'Articles', u'http://www.kamerabild.se/cmlink/Nyheter-fran-KAMERA-BILD-1.43315.xml')]
keep_only_tags = [dict(name='div', attrs={'class': 'container'})]
remove_tags_after = dict(name='div', attrs={'class': 'editor'})
remove_tags = [
dict(name=['object', 'link', 'iframe']), dict(name='div',
attrs={'class': ['pricerunner_head', 'sideBar', 'img']})
]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return self.adeify_images(soup)