calibre/recipes/njuz_net.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

58 lines
1.9 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2011, Darko Miletic <darko.miletic at gmail.com>'
'''
njuz.net
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class NjuzNet(BasicNewsRecipe):
title = 'Njuz.net'
__author__ = 'Darko Miletic'
description = 'Iscasene vesti iz Srbije, regiona i sveta'
publisher = 'njuz.net'
category = 'news, politics, humor, Serbia'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
encoding = 'utf8'
language = 'sr'
publication_type = 'newsportal'
masthead_url = 'http://www.njuz.net/njuznet.jpg'
extra_css = """
@font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)}
body{font-family: serif1, serif}
.articledescription{font-family: serif1, serif}
.wp-caption-text{font-size: x-small}
"""
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language
}
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
keep_only_tags = [
dict(attrs={'id': 'entryMeta'}), dict(attrs={'class': 'post'})
]
remove_tags = [
dict(name=['embed', 'link', 'base', 'iframe', 'object', 'meta', 'fb:like']), dict(
name='div', attrs={'id': 'tagsandcats'})
]
remove_tags_after = dict(name='div', attrs={'id': 'tagsandcats'})
remove_attributes = ['lang']
feeds = [(u'Clanci', u'http://www.njuz.net/feed/')]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
for alink in soup.findAll('a'):
if alink.string is not None:
tstr = alink.string
alink.replaceWith(tstr)
return soup