mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-11-12 17:47:07 -05:00
ff63cbb75e
We cant use walrus operator in recipes as they can potentially run on very old versions of python.
52 lines
2.1 KiB
Python
52 lines
2.1 KiB
Python
#!/usr/bin/env python
|
|
# vim:fileencoding=utf-8
|
|
from calibre.web.feeds.news import BasicNewsRecipe, classes
|
|
|
|
|
|
class EpochTimes(BasicNewsRecipe):
|
|
title = 'The Epoch Times'
|
|
__author__ = 'Kovid Goyal'
|
|
description = 'US general news'
|
|
language = 'en'
|
|
encoding = 'utf-8'
|
|
oldest_article = 1.2
|
|
max_articles_per_feed = 20
|
|
ignore_duplicate_articles = {'url'}
|
|
remove_attributes = ['height', 'width', 'style']
|
|
remove_empty_feeds = True
|
|
no_stylesheets = True
|
|
resolve_internal_links = True
|
|
masthead_url = 'https://epochtimes-ny.newsmemory.com/eeLayout/epochtimes/1.0.a/images/webapp/banner.png'
|
|
extra_css = '.post_caption, .text-sm, .uppercase {font-size:small;}'
|
|
|
|
keep_only_tags = [
|
|
dict(name='article')
|
|
]
|
|
remove_tags = [
|
|
classes('print:hidden h-header shortcode aspect-square'),
|
|
dict(name=['button', 'svg']),
|
|
dict(name='img', attrs={'src':lambda x: x and x.endswith('svg')})
|
|
]
|
|
|
|
# feeds can be found at https://www.theepochtimes.com/rssfeeds
|
|
feeds = [
|
|
('Special Series', 'https://feed.theepochtimes.com/health/special-series/feed'),
|
|
('US', 'https://feed.theepochtimes.com/us/feed'),
|
|
('China News', 'https://feed.theepochtimes.com/china/feed'),
|
|
('World', 'https://feed.theepochtimes.com/world/feed'),
|
|
('Opinion', 'https://feed.theepochtimes.com/opinion/feed'),
|
|
('Business & Markets', 'https://feed.theepochtimes.com/business/feed'),
|
|
('Science', 'https://feed.theepochtimes.com/science/feed'),
|
|
('Tech', 'https://feed.theepochtimes.com/tech/feed'),
|
|
('Health & Wellness', 'https://feed.theepochtimes.com/wellness/feed'),
|
|
('Epoch Taste', 'https://feed.theepochtimes.com/epoch-taste/feed'),
|
|
('Entertainment', 'https://feed.theepochtimes.com/entertainment/feed'),
|
|
]
|
|
|
|
def preprocess_html(self, soup):
|
|
for img in soup.findAll('img', attrs={'data-src': True}):
|
|
img['src'] = img['data-src']
|
|
for fig_c in soup.findAll('figcaption'):
|
|
fig_c['class'] = 'post_caption'
|
|
return soup
|