diff options
Diffstat (limited to 'youtube/playlist.py')
| -rw-r--r-- | youtube/playlist.py | 83 |
1 files changed, 43 insertions, 40 deletions
diff --git a/youtube/playlist.py b/youtube/playlist.py index 357a7ec..28b8149 100644 --- a/youtube/playlist.py +++ b/youtube/playlist.py @@ -12,12 +12,13 @@ from flask import request import flask -def playlist_ctoken(playlist_id, offset): +def playlist_ctoken(playlist_id, offset, include_shorts=True): 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)) @@ -26,47 +27,46 @@ def playlist_ctoken(playlist_id, offset): 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(content.decode('utf-8')) +def playlist_first_page(playlist_id, report_text="Retrieved playlist", + use_mobile=False): + if use_mobile: + url = 'https://m.youtube.com/playlist?list=' + playlist_id + '&pbj=1' + content = util.fetch_url( + url, util.mobile_xhr_headers, + report_text=report_text, debug_name='playlist_first_page' + ) + content = json.loads(content.decode('utf-8')) + else: + url = 'https://www.youtube.com/playlist?list=' + playlist_id + '&pbj=1' + content = util.fetch_url( + url, util.desktop_xhr_headers, + report_text=report_text, debug_name='playlist_first_page' + ) + content = json.loads(content.decode('utf-8')) return content -#https://m.youtube.com/playlist?itct=CBMQybcCIhMIptj9xJaJ2wIV2JKcCh3Idwu-&ctoken=4qmFsgI2EiRWTFBMT3kwajlBdmxWWlB0bzZJa2pLZnB1MFNjeC0tN1BHVEMaDmVnWlFWRHBEUWxFJTNE&pbj=1 -def get_videos(playlist_id, page): - - 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', - } +def get_videos(playlist_id, page, include_shorts=True, use_mobile=False, + report_text='Retrieved playlist'): + # mobile requests return 20 videos per page + if use_mobile: + page_size = 20 + headers = util.mobile_xhr_headers + # desktop requests return 100 videos per page + else: + page_size = 100 + headers = util.desktop_xhr_headers + url = "https://m.youtube.com/playlist?ctoken=" + url += playlist_ctoken(playlist_id, (int(page)-1)*page_size, + include_shorts=include_shorts) + url += "&pbj=1" content = util.fetch_url( - url, headers, - report_text="Retrieved playlist", debug_name='playlist_videos') + url, headers, report_text=report_text, + debug_name='playlist_videos' + ) info = json.loads(content.decode('utf-8')) return info @@ -85,7 +85,10 @@ 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", use_mobile=True + ), gevent.spawn(get_videos, playlist_id, page) ) gevent.joinall(tasks) @@ -104,7 +107,7 @@ def get_playlist_page(): util.prefix_urls(item) util.add_extra_html_info(item) if 'id' in item: - item['thumbnail'] = settings.img_prefix + 'https://i.ytimg.com/vi/' + item['id'] + '/default.jpg' + item['thumbnail'] = f"{settings.img_prefix}https://i.ytimg.com/vi/{item['id']}/hqdefault.jpg" item['url'] += '&list=' + playlist_id if item['index']: @@ -112,13 +115,13 @@ def get_playlist_page(): video_count = yt_data_extract.deep_get(info, 'metadata', 'video_count') if video_count is None: - video_count = 40 + video_count = 1000 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/20), + num_pages=math.ceil(video_count/100), parameters_dictionary=request.args, **info['metadata'] |