calibre/recipes/lex_fridman_podcast.recipe
un-pogaz 19b9d979ab comment formating (auto-fix)
ruff 'E114,E115,E116,E261,E262,E265'
2025-01-24 11:14:21 +01:00

62 lines
2.0 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
from calibre.web.feeds.news import BasicNewsRecipe
class lexfridman(BasicNewsRecipe):
title = 'Lex Fridman Podcast'
description = (
'Transcripts from Lex Fridman Podcast. Conversations about science, technology, history, '
'philosophy and the nature of intelligence, consciousness, love, and power. Lex is an AI '
'researcher at MIT and beyond. Download monthly.'
)
oldest_article = 30 # days
__author__ = 'unkn0wn'
language = 'en'
encoding = 'utf-8'
remove_attributes = ['style', 'height', 'width']
no_stylesheets = True
ignore_duplicate_articles = {'url'}
use_embedded_content = False
timefmt = ' [%b, %Y]'
cover_url = 'https://i.scdn.co/image/ab6765630000ba8a563ebb538d297875b10114b7'
recipe_specific_options = {
'days': {
'short': 'Oldest article to download from this news source. In days ',
'long': 'For example, 0.5, gives you articles from the past 12 hours',
'default': str(oldest_article)
}
}
def __init__(self, *args, **kwargs):
BasicNewsRecipe.__init__(self, *args, **kwargs)
d = self.recipe_specific_options.get('days')
if d and isinstance(d, str):
self.oldest_article = float(d)
extra_css = '''
.ts-name { font-weight:bold; }
.ts-timestamp { font-size:small; }
'''
keep_only_tags = [dict(name='article')]
remove_tags = [
dict(name=['svg']),
dict(name='div', attrs={'class':'episode-player'})
]
feeds = [
('Transcripts', 'https://lexfridman.com/feed/podcast/')
]
def print_version(self, url):
return url.split('?')[0][:-1] + '-transcript/'
def preprocess_html(self, soup):
for div in soup.findAll('div', attrs={'class':'ts-segment'}):
div.name = 'p'
for name in soup.findAll('span', attrs={'class':'ts-name'}):
name.name = 'div'
return soup