calibre/recipes/american_thinker.recipe
2019-04-13 09:17:31 +05:30

42 lines
1.6 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2010, Walt Anthony <workshop.northpole at gmail.com>'
'''
www.americanthinker.com
'''
import html5lib
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.utils.cleantext import clean_xml_chars
from lxml import etree
class AmericanThinker(BasicNewsRecipe):
title = u'American Thinker'
description = "American Thinker is a daily internet publication devoted to the thoughtful exploration of issues of importance to Americans."
__author__ = 'Walt Anthony'
publisher = 'Thomas Lifson'
category = 'news, politics, USA'
oldest_article = 7 # days
max_articles_per_feed = 50
summary_length = 150
language = 'en'
ignore_duplicate_articles = {'title', 'url'}
remove_javascript = True
auto_cleanup = True
conversion_options = {
'comment': description, 'tags': category, 'publisher': publisher, 'language': language, 'linearize_tables': True
}
def preprocess_raw_html(self, raw, url):
root = html5lib.parse(
clean_xml_chars(raw), treebuilder='lxml',
namespaceHTMLElements=False)
for x in root.xpath('''descendant-or-self::*[@class and contains(concat(' ', normalize-space(@class), ' '), ' article_body ') and (@class and contains(concat(' ', normalize-space(@class), ' '), ' bottom '))]'''): # noqa
x.getparent().remove(x)
return etree.tostring(root, encoding='unicode')
feeds = [(u'http://feeds.feedburner.com/americanthinker'),
(u'http://feeds.feedburner.com/AmericanThinkerBlog')
]