mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
40 lines
1.3 KiB
Python
40 lines
1.3 KiB
Python
#!/usr/bin/env python2
|
|
# vim:fileencoding=utf-8
|
|
# License: GPLv3 Copyright: 2019, Kovid Goyal <kovid at kovidgoyal.net>
|
|
from __future__ import absolute_import, division, print_function, unicode_literals
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
def classes(classes):
|
|
q = frozenset(classes.split(' '))
|
|
return dict(attrs={
|
|
'class': lambda x: x and frozenset(x.split()).intersection(q)})
|
|
|
|
|
|
class BarronsMagazine(BasicNewsRecipe):
|
|
title = 'Barron\'s Magazine'
|
|
__author__ = 'Kovid Goyal'
|
|
description = 'Financial news from the publisher of the WSJ'
|
|
language = 'en'
|
|
|
|
keep_only_tags = [
|
|
dict(name='h1'),
|
|
dict(id='js-article__body'),
|
|
]
|
|
|
|
def parse_index(self):
|
|
soup = self.index_to_soup('https://www.barrons.com/magazine')
|
|
articles = []
|
|
for art in soup.findAll('article'):
|
|
h = art.find(['h2', 'h3'])
|
|
a = h.find('a')
|
|
title = self.tag_to_string(a)
|
|
url = a['href']
|
|
desc = ''
|
|
p = art.find('p', attrs={'class': lambda x: x and ('_summary_' in x or '_byline_' in x)})
|
|
if p:
|
|
desc += self.tag_to_string(p)
|
|
articles.append({'title': title, 'url': url, 'description': desc})
|
|
return [('Articles', articles)]
|