calibre/recipes/1843.recipe
2023-10-16 16:21:10 +05:30

54 lines
1.7 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
# License: GPLv3 Copyright: 2016, Kovid Goyal <kovid at kovidgoyal.net>
from calibre.web.feeds.news import BasicNewsRecipe, classes
class E1843(BasicNewsRecipe):
title = '1843'
__author__ = 'Kovid Goyal'
description = 'The ideas, culture and lifestyle magazine from The Economist'
language = 'en_GB'
no_stylesheets = True
remove_javascript = True
encoding = 'utf-8'
# economist.com has started throttling after about 60% of the total has
# downloaded with connection reset by peer (104) errors.
delay = 1
keep_only_tags = [
dict(id='content')
]
remove_tags = [
classes('advert ad ds-share-list article__wordmark related-articles newsletter-signup'),
dict(attrs={'data-test-id':'sharing-modal'}),
]
def parse_index(self):
soup = self.index_to_soup('https://economist.com/1843')
ans = []
main = soup.find(id='content')
for h3 in main.find_all('h3'):
a = h3.find('a')
url = a['href']
if url.startswith('/'):
url = 'https://economist.com' + url
title = self.tag_to_string(a)
self.log(title, ' at ', url)
desc = ''
d = a.parent.findNextSibling('p')
if d is not None:
desc = self.tag_to_string(d)
ans.append({'title': title, 'url': url, 'description': desc})
return [('Articles', ans)]
def postprocess_html(self, soup, *a):
a = soup.find('a', string='More from 1843 magazine')
if a is not None:
more = a.parent.parent
more.extract()
return soup