diff options
Diffstat (limited to 'youtube/playlist.py')
| -rw-r--r-- | youtube/playlist.py | 165 |
1 files changed, 100 insertions, 65 deletions
diff --git a/youtube/playlist.py b/youtube/playlist.py index 3e5b0d2..e1e1342 100644 --- a/youtube/playlist.py +++ b/youtube/playlist.py @@ -1,73 +1,88 @@ -from youtube import util, yt_data_extract, proto +from youtube import util, yt_data_extract, proto, local_playlist from youtube import yt_app +import settings import base64 -import urllib import json -import string import gevent import math -from flask import request +from flask import request, abort import flask +def playlist_ctoken(playlist_id, offset, include_shorts=True): - - -def playlist_ctoken(playlist_id, offset): - offset = proto.uint(1, offset) - # this is just obfuscation as far as I can tell. It doesn't even follow protobuf offset = b'PT:' + proto.unpadded_b64encode(offset) offset = proto.string(15, offset) + if not include_shorts: + offset += proto.string(104, proto.uint(2, 1)) - continuation_info = proto.string( 3, proto.percent_b64encode(offset) ) - - playlist_id = proto.string(2, 'VL' + playlist_id ) + continuation_info = proto.string(3, proto.percent_b64encode(offset)) + + playlist_id = proto.string(2, f'VL{playlist_id}') pointless_nest = proto.string(80226972, playlist_id + continuation_info) return base64.urlsafe_b64encode(pointless_nest).decode('ascii') -# initial request types: -# polymer_json: https://m.youtube.com/playlist?list=PLv3TTBr1W_9tppikBxAE_G6qjWdBljBHJ&pbj=1&lact=0 -# ajax json: https://m.youtube.com/playlist?list=PLv3TTBr1W_9tppikBxAE_G6qjWdBljBHJ&pbj=1&lact=0 with header X-YouTube-Client-Version: 1.20180418 - - -# continuation request types: -# polymer_json: https://m.youtube.com/playlist?&ctoken=[...]&pbj=1 -# ajax json: https://m.youtube.com/playlist?action_continuation=1&ajax=1&ctoken=[...] - - -headers_1 = ( - ('Accept', '*/*'), - ('Accept-Language', 'en-US,en;q=0.5'), - ('X-YouTube-Client-Name', '2'), - ('X-YouTube-Client-Version', '2.20180614'), -) -def playlist_first_page(playlist_id, report_text = "Retrieved playlist"): - url = 'https://m.youtube.com/playlist?list=' + playlist_id + '&pbj=1' - content = util.fetch_url(url, util.mobile_ua + headers_1, report_text=report_text, debug_name='playlist_first_page') - content = json.loads(util.uppercase_escape(content.decode('utf-8'))) - - return content - - -#https://m.youtube.com/playlist?itct=CBMQybcCIhMIptj9xJaJ2wIV2JKcCh3Idwu-&ctoken=4qmFsgI2EiRWTFBMT3kwajlBdmxWWlB0bzZJa2pLZnB1MFNjeC0tN1BHVEMaDmVnWlFWRHBEUWxFJTNE&pbj=1 -def get_videos(playlist_id, page): +def playlist_first_page(playlist_id, report_text="Retrieved playlist", + use_mobile=False): + # Use innertube API (pbj=1 no longer works for many playlists) + key = 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8' + url = f'https://www.youtube.com/youtubei/v1/browse?key={key}' + + data = { + 'context': { + 'client': { + 'hl': 'en', + 'gl': 'US', + 'clientName': 'WEB', + 'clientVersion': '2.20240327.00.00', + }, + }, + 'browseId': f'VL{playlist_id}', + } - url = "https://m.youtube.com/playlist?ctoken=" + playlist_ctoken(playlist_id, (int(page)-1)*20) + "&pbj=1" - headers = { - 'User-Agent': ' Mozilla/5.0 (iPhone; CPU iPhone OS 10_3_1 like Mac OS X) AppleWebKit/603.1.30 (KHTML, like Gecko) Version/10.0 Mobile/14E304 Safari/602.1', - 'Accept': '*/*', - 'Accept-Language': 'en-US,en;q=0.5', - 'X-YouTube-Client-Name': '2', - 'X-YouTube-Client-Version': '2.20180508', + content_type_header = (('Content-Type', 'application/json'),) + content = util.fetch_url( + url, util.desktop_xhr_headers + content_type_header, + data=json.dumps(data), + report_text=report_text, debug_name='playlist_first_page' + ) + return json.loads(content.decode('utf-8')) + + +def get_videos(playlist_id, page, include_shorts=True, use_mobile=False, + report_text='Retrieved playlist'): + page_size = 100 + + key = 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8' + url = f'https://www.youtube.com/youtubei/v1/browse?key={key}' + + ctoken = playlist_ctoken(playlist_id, (int(page)-1)*page_size, + include_shorts=include_shorts) + + data = { + 'context': { + 'client': { + 'hl': 'en', + 'gl': 'US', + 'clientName': 'WEB', + 'clientVersion': '2.20240327.00.00', + }, + }, + 'continuation': ctoken, } - content = util.fetch_url(url, headers, report_text="Retrieved playlist", debug_name='playlist_videos') + content_type_header = (('Content-Type', 'application/json'),) + content = util.fetch_url( + url, util.desktop_xhr_headers + content_type_header, + data=json.dumps(data), + report_text=report_text, debug_name='playlist_videos' + ) - info = json.loads(util.uppercase_escape(content.decode('utf-8'))) + info = json.loads(content.decode('utf-8')) return info @@ -77,6 +92,15 @@ def get_playlist_page(): abort(400) playlist_id = request.args.get('list') + + # Radio/Mix playlists (RD...) only work as watch page, not playlist page + if playlist_id.startswith('RD'): + first_video_id = playlist_id[2:] # video ID after 'RD' prefix + return flask.redirect( + f'{util.URL_ORIGIN}/watch?v={first_video_id}&list={playlist_id}', + 302 + ) + page = request.args.get('page', '1') if page == '1': @@ -84,33 +108,44 @@ def get_playlist_page(): this_page_json = first_page_json else: tasks = ( - gevent.spawn(playlist_first_page, playlist_id, report_text="Retrieved playlist info" ), + gevent.spawn( + playlist_first_page, playlist_id, + report_text="Retrieved playlist info" + ), gevent.spawn(get_videos, playlist_id, page) ) gevent.joinall(tasks) + util.check_gevent_exceptions(*tasks) first_page_json, this_page_json = tasks[0].value, tasks[1].value - - try: # first page - video_list = this_page_json['response']['contents']['singleColumnBrowseResultsRenderer']['tabs'][0]['tabRenderer']['content']['sectionListRenderer']['contents'][0]['itemSectionRenderer']['contents'][0]['playlistVideoListRenderer']['contents'] - except KeyError: # other pages - video_list = this_page_json['response']['continuationContents']['playlistVideoListContinuation']['contents'] - parsed_video_list = [yt_data_extract.parse_info_prepare_for_html(video_json) for video_json in video_list] + info = yt_data_extract.extract_playlist_info(this_page_json) + if info['error']: + return flask.render_template('error.html', error_message=info['error']) + if page != '1': + info['metadata'] = yt_data_extract.extract_playlist_metadata(first_page_json) - metadata = yt_data_extract.renderer_info(first_page_json['response']['header']) - yt_data_extract.prefix_urls(metadata) + util.prefix_urls(info['metadata']) + for item in info.get('items', ()): + util.prefix_urls(item) + util.add_extra_html_info(item) + if 'id' in item and not item.get('thumbnail'): + item['thumbnail'] = f"{settings.img_prefix}https://i.ytimg.com/vi/{item['id']}/hqdefault.jpg" - if 'description' not in metadata: - metadata['description'] = '' + item['url'] += f'&list={playlist_id}' + if item['index']: + item['url'] += f'&index={item["index"]}' - video_count = int(metadata['size'].replace(',', '')) - metadata['size'] += ' videos' + video_count = yt_data_extract.deep_get(info, 'metadata', 'video_count') + if video_count is None: + video_count = 1000 - return flask.render_template('playlist.html', - video_list = parsed_video_list, - num_pages = math.ceil(video_count/20), - parameters_dictionary = request.args, + return flask.render_template( + 'playlist.html', + header_playlist_names=local_playlist.get_playlist_names(), + video_list=info.get('items', []), + num_pages=math.ceil(video_count/100), + parameters_dictionary=request.args, - **metadata + **info['metadata'] ).encode('utf-8') |