mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
84 lines
2.9 KiB
Python
84 lines
2.9 KiB
Python
#!/usr/bin/env python
|
|
'''
|
|
https://www.economist.com/the-world-in-brief
|
|
'''
|
|
|
|
import re
|
|
|
|
from calibre.ebooks.BeautifulSoup import Tag
|
|
from calibre.web.feeds.news import BasicNewsRecipe, classes
|
|
|
|
|
|
def new_tag(soup, name, attrs=()):
|
|
impl = getattr(soup, 'new_tag', None)
|
|
if impl is not None:
|
|
return impl(name, attrs=dict(attrs))
|
|
return Tag(soup, name, attrs=attrs or None)
|
|
|
|
|
|
class Espresso(BasicNewsRecipe):
|
|
title = 'The Economist Espresso'
|
|
language = 'en_GB'
|
|
__author__ = 'unkn0wn'
|
|
description = (
|
|
'Espresso is a rich, full-flavoured shot of daily global analysis '
|
|
'from the editors of The Economist to get you up to speed, fast. '
|
|
'Maximise your understanding of the most significant business, '
|
|
'economic, political and cultural developments globally.'
|
|
)
|
|
cover_url = (
|
|
'https://downloadr2.apkmirror.com/wp-content/uploads/2021/10/75/615777cc6611b.png'
|
|
)
|
|
no_stylesheets = True
|
|
remove_attributes = ['height', 'width', 'style']
|
|
use_embedded_content = False
|
|
masthead_url = 'https://www.livemint.com/lm-img/dev/economist-logo-oneline.png'
|
|
browser_type = 'webengine'
|
|
|
|
extra_css = '''
|
|
h1 { text-align:center; }
|
|
._main-image, ._description, .sub, .calibre-nuked-tag-figcaption { text-align:center; font-size:small; }
|
|
blockquote { font-size:x-large; font-style:italic; color:#202020; }
|
|
'''
|
|
|
|
keep_only_tags = [dict(name='main', attrs={'id': 'content'})]
|
|
|
|
remove_tags = [
|
|
classes('_podcast-promo _newsletter-promo-container _time-last-updated'),
|
|
]
|
|
|
|
def parse_index(self):
|
|
return [
|
|
(
|
|
'Espresso',
|
|
[
|
|
{
|
|
'title': 'The World in Brief',
|
|
'url': 'https://www.economist.com/the-world-in-brief',
|
|
'description': 'Catch up quickly on the global stories that matter',
|
|
},
|
|
],
|
|
),
|
|
]
|
|
|
|
def preprocess_html(self, soup):
|
|
if h1 := soup.find('h1'):
|
|
if p := h1.find_next_sibling('p'):
|
|
p['class'] = 'sub'
|
|
for hr in soup.findAll(attrs={'class': ['_gobbet', '_article']}):
|
|
nt = new_tag(soup, 'hr')
|
|
hr.append(nt)
|
|
for img in soup.findAll('img', src=True):
|
|
img['src'] = re.sub(r'width=\d+', 'width=600', img['src'])
|
|
if aud := soup.find(attrs={'data-test-id': 'twib-audio-player'}):
|
|
if div := aud.find_next_sibling('div'):
|
|
div.extract()
|
|
aud.extract()
|
|
return soup
|
|
|
|
def get_browser(self, *args, **kwargs):
|
|
kwargs['user_agent'] = (
|
|
'Mozilla/5.0 (Linux; Android 14) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.6533.103 Mobile Safari/537.36 Liskov'
|
|
)
|
|
return BasicNewsRecipe.get_browser(self, *args, **kwargs)
|