mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
41 lines
1.5 KiB
Plaintext
41 lines
1.5 KiB
Plaintext
import re
|
|
from lxml.html import parse
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class Counterpunch(BasicNewsRecipe):
|
|
'''
|
|
Parses counterpunch.com for articles
|
|
'''
|
|
title = 'Counterpunch'
|
|
description = 'Daily political opinion from www.Counterpunch.com'
|
|
language = 'en'
|
|
__author__ = 'O. Emmerson'
|
|
keep_only_tags = [dict(name='td', attrs={'width': '522'})]
|
|
max_articles_per_feed = 10
|
|
|
|
def parse_index(self):
|
|
feeds = []
|
|
title, url = 'Counterpunch', 'http://www.counterpunch.com'
|
|
articles = self.parse_page(url)
|
|
if articles:
|
|
feeds.append((title, articles))
|
|
return feeds
|
|
|
|
def parse_page(self, url):
|
|
parsed_page = parse(url).getroot()
|
|
articles = []
|
|
unwanted_text = re.compile('Website\ of\ the|I\ urge\ you|Subscribe\ now|DONATE|\@asis\.com|donation\ button|click\ over\ to\ our')
|
|
parsed_articles = [a for a in parsed_page.cssselect("html>body>table tr>td>p[class='style2']") if not unwanted_text.search(a.text_content())]
|
|
for art in parsed_articles:
|
|
try:
|
|
author = art.text
|
|
title = art.cssselect("a")[0].text + ' by {0}'.format(author)
|
|
art_url = 'http://www.counterpunch.com/' + art.cssselect("a")[0].attrib['href']
|
|
articles.append({'title': title, 'url': art_url})
|
|
except Exception as e:
|
|
e
|
|
#print('Handler Error: ', e, 'title :', a.text_content())
|
|
pass
|
|
return articles
|
|
|