mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-11-14 18:43:00 -05:00
38 lines
1.4 KiB
Python
38 lines
1.4 KiB
Python
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class newslaundry(BasicNewsRecipe):
|
|
title = 'Newslaundry'
|
|
__author__ = 'unkn0wn'
|
|
description = (
|
|
'Newslaundry is a reader-supported, independent news media company. In an industry driven by corporate'
|
|
' and government interests, we strongly believe in the need for an independent news model, and a free'
|
|
' and accountable press.'
|
|
)
|
|
language = 'en_IN'
|
|
masthead_url = 'https://images.assettype.com/newslaundry/2020-01/d91cad07-9650-47e9-8bdc-9a6247354d95/Header_logo_NL__2_New.png'
|
|
encoding = 'utf-8'
|
|
no_stylesheets = True
|
|
remove_javascript = True
|
|
oldest_article = 7 # days
|
|
resolve_internal_links = True
|
|
|
|
ignore_duplicate_articles = {'url'}
|
|
|
|
# keep_only_tags = [classes('headline subheadline authorWithTimeStamp story-card')]
|
|
|
|
feeds = [
|
|
('Articles', 'https://www.newslaundry.com/stories.rss?time-period=last-7-days')
|
|
]
|
|
|
|
# def preprocess_html(self, soup):
|
|
# if h1 := soup.find(**classes('headline')):
|
|
# h1.name = 'h1'
|
|
# if h3 := soup.find(**classes('subheadline')):
|
|
# h3.name = 'h3'
|
|
# return soup
|
|
|
|
def print_version(self, url):
|
|
if 'hindi.newslaundry' in url:
|
|
self.abort_article('Skipping hindi article') # remove this line if you want hindi articles.
|
|
return url
|