Zive.sk and iliterature.cz by Abelturd

This commit is contained in:
Kovid Goyal 2010-02-06 21:20:11 -07:00
parent 411b796ba1
commit 3ae86efb6f
2 changed files with 92 additions and 0 deletions

View File

@ -0,0 +1,45 @@
from calibre.web.feeds.news import BasicNewsRecipe
import re
class ZiveRecipe(BasicNewsRecipe):
__license__ = 'GPL v3'
__author__ = 'Abelturd'
language = 'sk'
version = 1
title = u'ZIVE.sk'
publisher = u''
category = u'News, Newspaper'
description = u'Naj\u010d\xedtanej\u0161\xed denn\xedk opo\u010d\xedta\u010doch, IT a internete. '
encoding = 'UTF-8'
oldest_article = 7
max_articles_per_feed = 100
use_embedded_content = False
remove_empty_feeds = True
no_stylesheets = True
remove_javascript = True
cover_url = 'http://www.zive.sk/Client.Images/Logos/logo-zive-sk.gif'
feeds = []
feeds.append((u'V\u0161etky \u010dl\xe1nky', u'http://www.zive.sk/rss/sc-47/default.aspx'))
preprocess_regexps = [
(re.compile(r'<p><p><strong>Pokra.*ie</strong></p>', re.DOTALL|re.IGNORECASE),
lambda match: ''),
]
remove_tags = []
keep_only_tags = [dict(name='h1'), dict(name='span', attrs={'class':'arlist-data-info-author'}), dict(name='div', attrs={'class':'bbtext font-resizer-area'}),]
extra_css = '''
h1 {font-size:140%;font-family:georgia,serif; font-weight:bold}
h3 {font-size:115%;font-family:georgia,serif; font-weight:bold}
'''

View File

@ -0,0 +1,47 @@
from calibre.web.feeds.news import BasicNewsRecipe
import re
class SmeRecipe(BasicNewsRecipe):
__license__ = 'GPL v3'
__author__ = 'Abelturd'
language = 'cz'
version = 1
title = u'iLiteratura.cz'
publisher = u''
category = u'News, Newspaper'
description = u'O LITERATU\u0158E V CEL\xc9M SV\u011aT\u011a A DOMA'
cover_url = 'http://www.iliteratura.cz/1_vzhled/1/iliteratura.gif'
oldest_article = 7
max_articles_per_feed = 100
use_embedded_content = False
remove_empty_feeds = True
no_stylesheets = True
remove_javascript = True
feeds = []
feeds.append((u'\u010cl\xe1nky', u'http://www.iliteratura.cz/rss.asp'))
keep_only_tags = []
remove_tags = [dict(name='table'),dict(name='h3')]
preprocess_regexps = [
(re.compile(r'<h3>Souvisej.*</body>', re.DOTALL|re.IGNORECASE),
lambda match: ''),
]
def print_version(self, url):
m = re.search('(?<=ID=)[0-9]*', url)
return u'http://www.iliteratura.cz/clanek.asp?polozkaID=' + str(m.group(0)) + '&c=tisk'
extra_css = '''
h1 {font-size:140%;font-family:georgia,serif; font-weight:bold}
h3 {font-size:115%;font-family:georgia,serif; font-weight:bold}
'''