mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
Fixes #1945569 [Fetching news from Entrepreneur Magazine fails](https://bugs.launchpad.net/calibre/+bug/1945569)
54 lines
1.6 KiB
Python
54 lines
1.6 KiB
Python
#!/usr/bin/env python
|
|
# vim:fileencoding=utf-8
|
|
from __future__ import absolute_import, division, print_function, unicode_literals
|
|
|
|
__license__ = 'GPL v3'
|
|
__copyright__ = '2015, Kovid Goyal <kovid at kovidgoyal.net>'
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class EntrepeneurMagRecipe(BasicNewsRecipe):
|
|
__author__ = 'Kovid Goyal'
|
|
language = 'en'
|
|
|
|
title = u'Entrepeneur Magazine'
|
|
publisher = u'Entrepreneur Media, Inc'
|
|
category = u'Business'
|
|
description = u'Online magazine on business, small business, management and economy'
|
|
|
|
encoding = 'utf-8'
|
|
|
|
no_stylesheets = True
|
|
remove_javascript = True
|
|
|
|
keep_only_tags = [
|
|
dict(attrs={'data-word-count': True}),
|
|
]
|
|
remove_tags = [
|
|
dict(attrs={'class': ['related-content']}),
|
|
]
|
|
remove_attributes = ['style']
|
|
|
|
INDEX = 'https://www.entrepreneur.com'
|
|
|
|
def parse_index(self):
|
|
soup = self.index_to_soup(self.INDEX + '/latest')
|
|
articles = []
|
|
for h3 in soup.findAll('h3'):
|
|
a = h3.parent
|
|
if a.name == 'a' and a.get('href'):
|
|
url = self.INDEX + a['href']
|
|
title = self.tag_to_string(h3)
|
|
desc = ''
|
|
if a.next_sibling and a.next_sibling.name == 'p':
|
|
desc = self.tag_to_string(a.next_sibling)
|
|
articles.append({'title': title, 'url': url, 'description': desc})
|
|
self.log(title, url)
|
|
return [('Articles', articles)]
|
|
|
|
def preprocess_html(self, soup):
|
|
for img in soup.findAll('img', attrs={'data-src': True}):
|
|
img['src'] = img['data-src']
|
|
return soup
|