| 1 |
__license__ = 'GPL v3' |
| 2 |
__copyright__ = '2010, Walt Anthony <workshop.northpole at gmail.com>' |
| 3 |
''' |
| 4 |
www.americanthinker.com |
| 5 |
''' |
| 6 |
import html5lib |
| 7 |
from lxml import etree |
| 8 |
|
| 9 |
from calibre.utils.cleantext import clean_xml_chars |
| 10 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 11 |
|
| 12 |
|
| 13 |
class AmericanThinker(BasicNewsRecipe): |
| 14 |
title = 'American Thinker' |
| 15 |
description = 'American Thinker is a daily internet publication devoted to the thoughtful exploration of issues of importance to Americans.' |
| 16 |
__author__ = 'Walt Anthony' |
| 17 |
publisher = 'Thomas Lifson' |
| 18 |
category = 'news, politics, USA' |
| 19 |
oldest_article = 7 # days |
| 20 |
max_articles_per_feed = 50 |
| 21 |
summary_length = 150 |
| 22 |
language = 'en_US' |
| 23 |
ignore_duplicate_articles = {'title', 'url'} |
| 24 |
|
| 25 |
remove_javascript = True |
| 26 |
auto_cleanup = True |
| 27 |
|
| 28 |
conversion_options = {'comment': description, 'tags': category, 'publisher': publisher, 'language': language, 'linearize_tables': True} |
| 29 |
|
| 30 |
def preprocess_raw_html(self, raw, url): |
| 31 |
root = html5lib.parse(clean_xml_chars(raw), treebuilder='lxml', namespaceHTMLElements=False) |
| 32 |
for x in root.xpath( |
| 33 |
"descendant-or-self::*[@class and contains(concat(' ', normalize-space(@class), ' '), ' article_body ')" |
| 34 |
" and (@class and contains(concat(' ', normalize-space(@class), ' '), ' bottom '))]" |
| 35 |
): |
| 36 |
x.getparent().remove(x) |
| 37 |
return etree.tostring(root, encoding='unicode') |
| 38 |
|
| 39 |
feeds = [('http://feeds.feedburner.com/americanthinker'), ('http://feeds.feedburner.com/AmericanThinkerBlog')] |