0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-05 04:17:27 +00:00
yt-dlp/yt_dlp/extractor/pyvideo.py
sepro add96eb9f8
[cleanup] Add more ruff rules (#10149)
Authored by: seproDev

Reviewed-by: bashonly <88596187+bashonly@users.noreply.github.com>
Reviewed-by: Simon Sawicki <contact@grub4k.xyz>
2024-06-12 01:09:58 +02:00

69 lines
2.6 KiB
Python

import re
from .common import InfoExtractor
from ..utils import int_or_none
class PyvideoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?pyvideo\.org/(?P<category>[^/]+)/(?P<id>[^/?#&.]+)'
_TESTS = [{
'url': 'http://pyvideo.org/pycon-us-2013/become-a-logging-expert-in-30-minutes.html',
'info_dict': {
'id': 'become-a-logging-expert-in-30-minutes',
},
'playlist_count': 2,
}, {
'url': 'http://pyvideo.org/pygotham-2012/gloriajw-spotifywitherikbernhardsson182m4v.html',
'md5': '5fe1c7e0a8aa5570330784c847ff6d12',
'info_dict': {
'id': '2542',
'ext': 'm4v',
'title': 'Gloriajw-SpotifyWithErikBernhardsson182.m4v',
},
}]
def _real_extract(self, url):
mobj = self._match_valid_url(url)
category = mobj.group('category')
video_id = mobj.group('id')
entries = []
data = self._download_json(
f'https://raw.githubusercontent.com/pyvideo/data/master/{category}/videos/{video_id}.json',
video_id, fatal=False)
if data:
for video in data['videos']:
video_url = video.get('url')
if video_url:
if video.get('type') == 'youtube':
entries.append(self.url_result(video_url, 'Youtube'))
else:
entries.append({
'id': str(data.get('id') or video_id),
'url': video_url,
'title': data['title'],
'description': data.get('description') or data.get('summary'),
'thumbnail': data.get('thumbnail_url'),
'duration': int_or_none(data.get('duration')),
})
else:
webpage = self._download_webpage(url, video_id)
title = self._og_search_title(webpage)
media_urls = self._search_regex(
r'(?s)Media URL:(.+?)</li>', webpage, 'media urls')
for m in re.finditer(
r'<a[^>]+href=(["\'])(?P<url>http.+?)\1', media_urls):
media_url = m.group('url')
if re.match(r'https?://www\.youtube\.com/watch\?v=.*', media_url):
entries.append(self.url_result(media_url, 'Youtube'))
else:
entries.append({
'id': video_id,
'url': media_url,
'title': title,
})
return self.playlist_result(entries, video_id)