home
***
CD-ROM
|
disk
|
FTP
|
other
***
search
/
Chip 2011 November
/
CHIP_2011_11.iso
/
Programy
/
Narzedzia
/
Calibre
/
calibre-0.8.18.msi
/
file_280
/
cbn.recipe
< prev
next >
Wrap
Text File
|
2011-09-09
|
3KB
|
74 lines
from calibre.web.feeds.news import BasicNewsRecipe
class CBN(BasicNewsRecipe):
title = u'CBN News'
__author__ = 'Roger'
# TODO: I just noticed this is downloading 25+ articles, while
# the online site is only publishing at most 7 articles daily.
# So, somehow this needs to be fixed it only downloads max 7 articles
oldest_article = 7
max_articles_per_feed = 100
description = 'The Christian Broadcasting Network'
publisher = 'http://www.cbn.com/'
category = 'news, religion, spiritual, christian'
language = 'en'
# Make article titles, author and date bold, italic or small font.
# TODO: Could use a smaller title text
# TODO: Italicize Author and Publisher?
#
# http://www.cbn.com/App_Themes/Common/base.css,
# http://www.cbn.com/App_Themes/CBNNews/article.css",
# ... and many more style sheets.
#extra_css = '''
# .story_item_headline { font-size: medium; font-weight: bold; }
# .story_item_author { font-size: small; font-style:italic; }
# .signature_line { font-size: small; }
# '''
remove_javascript = True
use_embedded_content = False
no_stylesheets = True
language = 'en'
encoding = 'iso-8859-1'
conversion_options = {'linearize_tables':True}
# TODO: No masterhead_url for CBN, using one I grepped from a news article
# (There's a better/higher contrast blue on white background image, but
# can't get it or it's too big -- embedded into a larger jpeg?)
masthead_url = 'http://www.cbn.com/templates/images/cbn_com_logo.jpg'
keep_only_tags = [
dict(name='h1', attrs={'id':'articleTitle'}),
dict(name='div', attrs={'class':'articleAuthor'}),
dict(name='div', attrs={'class':'articleDate'}),
dict(name='div', attrs={'class':'articleText'}),
]
remove_tags = [
# The article image is usually Adobe Flash Player Image
# The snapshot .jpg image files of the video are found
# within a URL folder named "PageFiles_Files"
# Filter this for now.
# (Majority of images seem to be Adobe Flash.)
dict(name='div', attrs={'class':'articleImage'}),
]
# Comment-out or uncomment any of the following RSS feeds according to your
# liking.
# A full list can be found here: http://www.cbn.com/rss.aspx
feeds = [
(u'World', u'http://www.cbn.com/cbnnews/world/feed/'),
(u'US', u'http://www.cbn.com/cbnnews/us/feed/'),
(u'Inside Israel', u'http://www.cbn.com/cbnnews/insideisrael/feed/'),
(u'Politics', u'http://www.cbn.com/cbnnews/politics/feed/'),
(u'Christian World News', u'http://www.cbn.com/cbnnews/shows/cwn/feed/'),
(u'Health and Science', u'http://www.cbn.com/cbnnews/healthscience/feed/'),
(u'Finance', u'http://www.cbn.com/cbnnews/finance/feed/'),
]