yt_dlp/extractor/panopto.py

   1 import calendar
   2 import datetime as dt
   3 import functools
   4 import json
   5 import random
   6 import urllib.parse
   7
   8 from .common import InfoExtractor
   9 from ..utils import (
  10     ExtractorError,
  11     OnDemandPagedList,
  12     bug_reports_message,
  13     get_first,
  14     int_or_none,
  15     parse_qs,
  16     srt_subtitles_timecode,
  17     traverse_obj,
  18 )
  19
  20
  21 class PanoptoBaseIE(InfoExtractor):
  22     BASE_URL_RE = r'(?P<base_url>https?://[\w.-]+\.panopto.(?:com|eu)/Panopto)'
  23
  24     # see panopto core.js
  25     _SUB_LANG_MAPPING = {
  26         0: 'en-US',
  27         1: 'en-GB',
  28         2: 'es-MX',
  29         3: 'es-ES',
  30         4: 'de-DE',
  31         5: 'fr-FR',
  32         6: 'nl-NL',
  33         7: 'th-TH',
  34         8: 'zh-CN',
  35         9: 'zh-TW',
  36         10: 'ko-KR',
  37         11: 'ja-JP',
  38         12: 'ru-RU',
  39         13: 'pt-PT',
  40         14: 'pl-PL',
  41         15: 'en-AU',
  42         16: 'da-DK',
  43         17: 'fi-FI',
  44         18: 'hu-HU',
  45         19: 'nb-NO',
  46         20: 'sv-SE',
  47         21: 'it-IT',
  48     }
  49
  50     def _call_api(self, base_url, path, video_id, data=None, fatal=True, **kwargs):
  51         response = self._download_json(
  52             base_url + path, video_id, data=json.dumps(data).encode('utf8') if data else None,
  53             fatal=fatal, headers={'accept': 'application/json', 'content-type': 'application/json'}, **kwargs)
  54         if not response:
  55             return
  56         error_code = traverse_obj(response, 'ErrorCode')
  57         if error_code == 2:
  58             self.raise_login_required(method='cookies')
  59         elif error_code is not None:
  60             msg = f'Panopto said: {response.get("ErrorMessage")}'
  61             if fatal:
  62                 raise ExtractorError(msg, video_id=video_id, expected=True)
  63             else:
  64                 self.report_warning(msg, video_id=video_id)
  65         return response
  66
  67     @staticmethod
  68     def _parse_fragment(url):
  69         return {k: json.loads(v[0]) for k, v in urllib.parse.parse_qs(urllib.parse.urlparse(url).fragment).items()}
  70
  71
  72 class PanoptoIE(PanoptoBaseIE):
  73     _VALID_URL = PanoptoBaseIE.BASE_URL_RE + r'/Pages/(Viewer|Embed)\.aspx.*(?:\?|&)id=(?P<id>[a-f0-9-]+)'
  74     _EMBED_REGEX = [rf'<iframe[^>]+src=["\'](?P<url>{PanoptoBaseIE.BASE_URL_RE}/Pages/(Viewer|Embed|Sessions/List)\.aspx[^"\']+)']
  75     _TESTS = [
  76         {
  77             'url': 'https://demo.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=26b3ae9e-4a48-4dcc-96ba-0befba08a0fb',
  78             'info_dict': {
  79                 'id': '26b3ae9e-4a48-4dcc-96ba-0befba08a0fb',
  80                 'title': 'Panopto for Business - Use Cases',
  81                 'timestamp': 1459184200,
  82                 'thumbnail': r're:https://demo\.hosted\.panopto\.com/.+',
  83                 'upload_date': '20160328',
  84                 'ext': 'mp4',
  85                 'cast': [],
  86                 'chapters': [],
  87                 'duration': 88.17099999999999,
  88                 'average_rating': int,
  89                 'uploader_id': '2db6b718-47a0-4b0b-9e17-ab0b00f42b1e',
  90                 'channel_id': 'e4c6a2fc-1214-4ca0-8fb7-aef2e29ff63a',
  91                 'channel': 'Showcase Videos',
  92             },
  93         },
  94         {
  95             'url': 'https://demo.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=ed01b077-c9e5-4c7b-b8ff-15fa306d7a59',
  96             'info_dict': {
  97                 'id': 'ed01b077-c9e5-4c7b-b8ff-15fa306d7a59',
  98                 'title': 'Overcoming Top 4 Challenges of Enterprise Video',
  99                 'uploader': 'Panopto Support',
 100                 'timestamp': 1449409251,
 101                 'thumbnail': r're:https://demo\.hosted\.panopto\.com/.+',
 102                 'upload_date': '20151206',
 103                 'ext': 'mp4',
 104                 'chapters': 'count:12',
 105                 'cast': ['Panopto Support'],
 106                 'uploader_id': 'a96d1a31-b4de-489b-9eee-b4a5b414372c',
 107                 'average_rating': int,
 108                 'description': 'md5:4391837802b3fc856dadf630c4b375d1',
 109                 'duration': 1088.2659999999998,
 110                 'channel_id': '9f3c1921-43bb-4bda-8b3a-b8d2f05a8546',
 111                 'channel': 'Webcasts',
 112             },
 113         },
 114         {
 115             # Extra params in URL
 116             'url': 'https://howtovideos.hosted.panopto.com/Panopto/Pages/Viewer.aspx?randomparam=thisisnotreal&id=5fa74e93-3d87-4694-b60e-aaa4012214ed&advance=true',
 117             'info_dict': {
 118                 'id': '5fa74e93-3d87-4694-b60e-aaa4012214ed',
 119                 'ext': 'mp4',
 120                 'duration': 129.513,
 121                 'cast': ['Kathryn Kelly'],
 122                 'uploader_id': '316a0a58-7fa2-4cd9-be1c-64270d284a56',
 123                 'timestamp': 1569845768,
 124                 'tags': ['Viewer', 'Enterprise'],
 125                 'chapters': [],
 126                 'upload_date': '20190930',
 127                 'thumbnail': r're:https://howtovideos\.hosted\.panopto\.com/.+',
 128                 'description': 'md5:2d844aaa1b1a14ad0e2601a0993b431f',
 129                 'title': 'Getting Started: View a Video',
 130                 'average_rating': int,
 131                 'uploader': 'Kathryn Kelly',
 132                 'channel_id': 'fb93bc3c-6750-4b80-a05b-a921013735d3',
 133                 'channel': 'Getting Started',
 134             },
 135         },
 136         {
 137             # Does not allow normal Viewer.aspx. AUDIO livestream has no url, so should be skipped and only give one stream.
 138             'url': 'https://unisa.au.panopto.com/Panopto/Pages/Embed.aspx?id=9d9a0fa3-e99a-4ebd-a281-aac2017f4da4',
 139             'info_dict': {
 140                 'id': '9d9a0fa3-e99a-4ebd-a281-aac2017f4da4',
 141                 'ext': 'mp4',
 142                 'cast': ['LTS CLI Script'],
 143                 'chapters': [],
 144                 'duration': 2178.45,
 145                 'description': 'md5:ee5cf653919f55b72bce2dbcf829c9fa',
 146                 'channel_id': 'b23e673f-c287-4cb1-8344-aae9005a69f8',
 147                 'average_rating': int,
 148                 'uploader_id': '38377323-6a23-41e2-9ff6-a8e8004bf6f7',
 149                 'uploader': 'LTS CLI Script',
 150                 'timestamp': 1572458134,
 151                 'title': 'WW2 Vets Interview 3 Ronald Stanley George',
 152                 'thumbnail': r're:https://unisa\.au\.panopto\.com/.+',
 153                 'channel': 'World War II Veteran Interviews',
 154                 'upload_date': '20191030',
 155             },
 156         },
 157         {
 158             # Slides/storyboard
 159             'url': 'https://demo.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=a7f12f1d-3872-4310-84b0-f8d8ab15326b',
 160             'info_dict': {
 161                 'id': 'a7f12f1d-3872-4310-84b0-f8d8ab15326b',
 162                 'ext': 'mhtml',
 163                 'timestamp': 1448798857,
 164                 'duration': 4712.681,
 165                 'title': 'Cache Memory - CompSci 15-213, Lecture 12',
 166                 'channel_id': 'e4c6a2fc-1214-4ca0-8fb7-aef2e29ff63a',
 167                 'uploader_id': 'a96d1a31-b4de-489b-9eee-b4a5b414372c',
 168                 'upload_date': '20151129',
 169                 'average_rating': 0,
 170                 'uploader': 'Panopto Support',
 171                 'channel': 'Showcase Videos',
 172                 'description': 'md5:55e51d54233ddb0e6c2ed388ca73822c',
 173                 'cast': ['ISR Videographer', 'Panopto Support'],
 174                 'chapters': 'count:28',
 175                 'thumbnail': r're:https://demo\.hosted\.panopto\.com/.+',
 176             },
 177             'params': {'format': 'mhtml', 'skip_download': True},
 178         },
 179         {
 180             'url': 'https://na-training-1.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=8285224a-9a2b-4957-84f2-acb0000c4ea9',
 181             'info_dict': {
 182                 'id': '8285224a-9a2b-4957-84f2-acb0000c4ea9',
 183                 'ext': 'mp4',
 184                 'chapters': [],
 185                 'title': 'Company Policy',
 186                 'average_rating': 0,
 187                 'timestamp': 1615058901,
 188                 'channel': 'Human Resources',
 189                 'tags': ['HumanResources'],
 190                 'duration': 1604.243,
 191                 'thumbnail': r're:https://na-training-1\.hosted\.panopto\.com/.+',
 192                 'uploader_id': '8e8ba0a3-424f-40df-a4f1-ab3a01375103',
 193                 'uploader': 'Cait M.',
 194                 'upload_date': '20210306',
 195                 'cast': ['Cait M.'],
 196                 'subtitles': {'en-US': [{'ext': 'srt', 'data': 'md5:a3f4d25963fdeace838f327097c13265'}],
 197                               'es-ES': [{'ext': 'srt', 'data': 'md5:57e9dad365fd0fbaf0468eac4949f189'}]},
 198             },
 199             'params': {'writesubtitles': True, 'skip_download': True},
 200         }, {
 201             # On Panopto there are two subs: "Default" and en-US. en-US is blank and should be skipped.
 202             'url': 'https://na-training-1.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=940cbd41-f616-4a45-b13e-aaf1000c915b',
 203             'info_dict': {
 204                 'id': '940cbd41-f616-4a45-b13e-aaf1000c915b',
 205                 'ext': 'mp4',
 206                 'subtitles': 'count:1',
 207                 'title': 'HR Benefits Review Meeting*',
 208                 'cast': ['Panopto Support'],
 209                 'chapters': [],
 210                 'timestamp': 1575024251,
 211                 'thumbnail': r're:https://na-training-1\.hosted\.panopto\.com/.+',
 212                 'channel': 'Zoom',
 213                 'description': 'md5:04f90a9c2c68b7828144abfb170f0106',
 214                 'uploader': 'Panopto Support',
 215                 'average_rating': 0,
 216                 'duration': 409.34499999999997,
 217                 'uploader_id': 'b6ac04ad-38b8-4724-a004-a851004ea3df',
 218                 'upload_date': '20191129',
 219
 220             },
 221             'params': {'writesubtitles': True, 'skip_download': True},
 222         },
 223         {
 224             'url': 'https://ucc.cloud.panopto.eu/Panopto/Pages/Viewer.aspx?id=0e8484a4-4ceb-4d98-a63f-ac0200b455cb',
 225             'only_matching': True,
 226         },
 227         {
 228             'url': 'https://brown.hosted.panopto.com/Panopto/Pages/Embed.aspx?id=0b3ff73b-36a0-46c5-8455-aadf010a3638',
 229             'only_matching': True,
 230         },
 231     ]
 232
 233     @classmethod
 234     def suitable(cls, url):
 235         return False if PanoptoPlaylistIE.suitable(url) else super().suitable(url)
 236
 237     def _mark_watched(self, base_url, video_id, delivery_info):
 238         duration = traverse_obj(delivery_info, ('Delivery', 'Duration'), expected_type=float)
 239         invocation_id = delivery_info.get('InvocationId')
 240         stream_id = traverse_obj(delivery_info, ('Delivery', 'Streams', ..., 'PublicID'), get_all=False, expected_type=str)
 241         if invocation_id and stream_id and duration:
 242             timestamp_str = f'/Date({calendar.timegm(dt.datetime.now(dt.timezone.utc).timetuple())}000)/'
 243             data = {
 244                 'streamRequests': [
 245                     {
 246                         'ClientTimeStamp': timestamp_str,
 247                         'ID': 0,
 248                         'InvocationID': invocation_id,
 249                         'PlaybackSpeed': 1,
 250                         'SecondsListened': duration - 1,
 251                         'SecondsRejected': 0,
 252                         'StartPosition': 0,
 253                         'StartReason': 2,
 254                         'StopReason': None,
 255                         'StreamID': stream_id,
 256                         'TimeStamp': timestamp_str,
 257                         'UpdatesRejected': 0,
 258                     },
 259                 ]}
 260
 261             self._download_webpage(
 262                 base_url + '/Services/Analytics.svc/AddStreamRequests', video_id,
 263                 fatal=False, data=json.dumps(data).encode('utf8'), headers={'content-type': 'application/json'},
 264                 note='Marking watched', errnote='Unable to mark watched')
 265
 266     @staticmethod
 267     def _extract_chapters(timestamps):
 268         chapters = []
 269         for timestamp in timestamps or []:
 270             caption = timestamp.get('Caption')
 271             start, duration = int_or_none(timestamp.get('Time')), int_or_none(timestamp.get('Duration'))
 272             if not caption or start is None or duration is None:
 273                 continue
 274             chapters.append({
 275                 'start_time': start,
 276                 'end_time': start + duration,
 277                 'title': caption,
 278             })
 279         return chapters
 280
 281     @staticmethod
 282     def _extract_mhtml_formats(base_url, timestamps):
 283         image_frags = {}
 284         for timestamp in timestamps or []:
 285             duration = timestamp.get('Duration')
 286             obj_id, obj_sn = timestamp.get('ObjectIdentifier'), timestamp.get('ObjectSequenceNumber')
 287             if timestamp.get('EventTargetType') == 'PowerPoint' and obj_id is not None and obj_sn is not None:
 288                 image_frags.setdefault('slides', []).append({
 289                     'url': base_url + f'/Pages/Viewer/Image.aspx?id={obj_id}&number={obj_sn}',
 290                     'duration': duration,
 291                 })
 292
 293             obj_pid, session_id, abs_time = timestamp.get('ObjectPublicIdentifier'), timestamp.get('SessionID'), timestamp.get('AbsoluteTime')
 294             if None not in (obj_pid, session_id, abs_time):
 295                 image_frags.setdefault('chapter', []).append({
 296                     'url': base_url + f'/Pages/Viewer/Thumb.aspx?eventTargetPID={obj_pid}&sessionPID={session_id}&number={obj_sn}&isPrimary=false&absoluteTime={abs_time}',
 297                     'duration': duration,
 298                 })
 299         for name, fragments in image_frags.items():
 300             yield {
 301                 'format_id': name,
 302                 'ext': 'mhtml',
 303                 'protocol': 'mhtml',
 304                 'acodec': 'none',
 305                 'vcodec': 'none',
 306                 'url': 'about:invalid',
 307                 'fragments': fragments,
 308             }
 309
 310     @staticmethod
 311     def _json2srt(data, delivery):
 312         def _gen_lines():
 313             for i, line in enumerate(data):
 314                 start_time = line['Time']
 315                 duration = line.get('Duration')
 316                 if duration:
 317                     end_time = start_time + duration
 318                 else:
 319                     end_time = traverse_obj(data, (i + 1, 'Time')) or delivery['Duration']
 320                 yield f'{i + 1}\n{srt_subtitles_timecode(start_time)} --> {srt_subtitles_timecode(end_time)}\n{line["Caption"]}'
 321         return '\n\n'.join(_gen_lines())
 322
 323     def _get_subtitles(self, base_url, video_id, delivery):
 324         subtitles = {}
 325         for lang in delivery.get('AvailableLanguages') or []:
 326             response = self._call_api(
 327                 base_url, '/Pages/Viewer/DeliveryInfo.aspx', video_id, fatal=False,
 328                 note='Downloading captions JSON metadata', query={
 329                     'deliveryId': video_id,
 330                     'getCaptions': True,
 331                     'language': str(lang),
 332                     'responseType': 'json',
 333                 },
 334             )
 335             if not isinstance(response, list):
 336                 continue
 337             subtitles.setdefault(self._SUB_LANG_MAPPING.get(lang) or 'default', []).append({
 338                 'ext': 'srt',
 339                 'data': self._json2srt(response, delivery),
 340             })
 341         return subtitles
 342
 343     def _extract_streams_formats_and_subtitles(self, video_id, streams, **fmt_kwargs):
 344         formats = []
 345         subtitles = {}
 346         for stream in streams or []:
 347             stream_formats = []
 348             http_stream_url = stream.get('StreamHttpUrl')
 349             stream_url = stream.get('StreamUrl')
 350
 351             if http_stream_url:
 352                 stream_formats.append({'url': http_stream_url})
 353
 354             if stream_url:
 355                 media_type = stream.get('ViewerMediaFileTypeName')
 356                 if media_type in ('hls', ):
 357                     m3u8_formats, stream_subtitles = self._extract_m3u8_formats_and_subtitles(stream_url, video_id)
 358                     stream_formats.extend(m3u8_formats)
 359                     subtitles = self._merge_subtitles(subtitles, stream_subtitles)
 360                 else:
 361                     stream_formats.append({
 362                         'url': stream_url,
 363                     })
 364             for fmt in stream_formats:
 365                 fmt.update({
 366                     'format_note': stream.get('Tag'),
 367                     **fmt_kwargs,
 368                 })
 369             formats.extend(stream_formats)
 370
 371         return formats, subtitles
 372
 373     def _real_extract(self, url):
 374         base_url, video_id = self._match_valid_url(url).group('base_url', 'id')
 375         delivery_info = self._call_api(
 376             base_url, '/Pages/Viewer/DeliveryInfo.aspx', video_id,
 377             query={
 378                 'deliveryId': video_id,
 379                 'invocationId': '',
 380                 'isLiveNotes': 'false',
 381                 'refreshAuthCookie': 'true',
 382                 'isActiveBroadcast': 'false',
 383                 'isEditing': 'false',
 384                 'isKollectiveAgentInstalled': 'false',
 385                 'isEmbed': 'false',
 386                 'responseType': 'json',
 387             },
 388         )
 389
 390         delivery = delivery_info['Delivery']
 391         session_start_time = int_or_none(delivery.get('SessionStartTime'))
 392         timestamps = delivery.get('Timestamps')
 393
 394         # Podcast stream is usually the combined streams. We will prefer that by default.
 395         podcast_formats, podcast_subtitles = self._extract_streams_formats_and_subtitles(
 396             video_id, delivery.get('PodcastStreams'), format_note='PODCAST')
 397
 398         streams_formats, streams_subtitles = self._extract_streams_formats_and_subtitles(
 399             video_id, delivery.get('Streams'), preference=-10)
 400
 401         formats = podcast_formats + streams_formats
 402         formats.extend(self._extract_mhtml_formats(base_url, timestamps))
 403         subtitles = self._merge_subtitles(
 404             podcast_subtitles, streams_subtitles, self.extract_subtitles(base_url, video_id, delivery))
 405
 406         self.mark_watched(base_url, video_id, delivery_info)
 407
 408         return {
 409             'id': video_id,
 410             'title': delivery.get('SessionName'),
 411             'cast': traverse_obj(delivery, ('Contributors', ..., 'DisplayName'), expected_type=lambda x: x or None),
 412             'timestamp': session_start_time - 11640000000 if session_start_time else None,
 413             'duration': delivery.get('Duration'),
 414             'thumbnail': base_url + f'/Services/FrameGrabber.svc/FrameRedirect?objectId={video_id}&mode=Delivery&random={random.random()}',
 415             'average_rating': delivery.get('AverageRating'),
 416             'chapters': self._extract_chapters(timestamps),
 417             'uploader': delivery.get('OwnerDisplayName') or None,
 418             'uploader_id': delivery.get('OwnerId'),
 419             'description': delivery.get('SessionAbstract'),
 420             'tags': traverse_obj(delivery, ('Tags', ..., 'Content')),
 421             'channel_id': delivery.get('SessionGroupPublicID'),
 422             'channel': traverse_obj(delivery, 'SessionGroupLongName', 'SessionGroupShortName', get_all=False),
 423             'formats': formats,
 424             'subtitles': subtitles,
 425         }
 426
 427
 428 class PanoptoPlaylistIE(PanoptoBaseIE):
 429     _VALID_URL = PanoptoBaseIE.BASE_URL_RE + r'/Pages/(Viewer|Embed)\.aspx.*(?:\?|&)pid=(?P<id>[a-f0-9-]+)'
 430     _TESTS = [
 431         {
 432             'url': 'https://howtovideos.hosted.panopto.com/Panopto/Pages/Viewer.aspx?pid=f3b39fcf-882f-4849-93d6-a9f401236d36&id=5fa74e93-3d87-4694-b60e-aaa4012214ed&advance=true',
 433             'info_dict': {
 434                 'title': 'Featured Video Tutorials',
 435                 'id': 'f3b39fcf-882f-4849-93d6-a9f401236d36',
 436                 'description': '',
 437             },
 438             'playlist_mincount': 36,
 439         },
 440         {
 441             'url': 'https://utsa.hosted.panopto.com/Panopto/Pages/Viewer.aspx?pid=e2900555-3ad4-4bdb-854d-ad2401686190',
 442             'info_dict': {
 443                 'title': 'Library Website Introduction Playlist',
 444                 'id': 'e2900555-3ad4-4bdb-854d-ad2401686190',
 445                 'description': 'md5:f958bca50a1cbda15fdc1e20d32b3ecb',
 446             },
 447             'playlist_mincount': 4,
 448         },
 449
 450     ]
 451
 452     def _entries(self, base_url, playlist_id, session_list_id):
 453         session_list_info = self._call_api(
 454             base_url, f'/Api/SessionLists/{session_list_id}?collections[0].maxCount=500&collections[0].name=items', playlist_id)
 455
 456         items = session_list_info['Items']
 457         for item in items:
 458             if item.get('TypeName') != 'Session':
 459                 self.report_warning('Got an item in the playlist that is not a Session' + bug_reports_message(), only_once=True)
 460                 continue
 461             yield {
 462                 '_type': 'url',
 463                 'id': item.get('Id'),
 464                 'url': item.get('ViewerUri'),
 465                 'title': item.get('Name'),
 466                 'description': item.get('Description'),
 467                 'duration': item.get('Duration'),
 468                 'channel': traverse_obj(item, ('Parent', 'Name')),
 469                 'channel_id': traverse_obj(item, ('Parent', 'Id')),
 470             }
 471
 472     def _real_extract(self, url):
 473         base_url, playlist_id = self._match_valid_url(url).group('base_url', 'id')
 474
 475         video_id = get_first(parse_qs(url), 'id')
 476         if video_id:
 477             if self.get_param('noplaylist'):
 478                 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
 479                 return self.url_result(base_url + f'/Pages/Viewer.aspx?id={video_id}', ie_key=PanoptoIE.ie_key(), video_id=video_id)
 480             else:
 481                 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
 482
 483         playlist_info = self._call_api(base_url, f'/Api/Playlists/{playlist_id}', playlist_id)
 484         return self.playlist_result(
 485             self._entries(base_url, playlist_id, playlist_info['SessionListId']),
 486             playlist_id=playlist_id, playlist_title=playlist_info.get('Name'),
 487             playlist_description=playlist_info.get('Description'))
 488
 489
 490 class PanoptoListIE(PanoptoBaseIE):
 491     _VALID_URL = PanoptoBaseIE.BASE_URL_RE + r'/Pages/Sessions/List\.aspx'
 492     _PAGE_SIZE = 250
 493     _TESTS = [
 494         {
 495             'url': 'https://demo.hosted.panopto.com/Panopto/Pages/Sessions/List.aspx#folderID=%22e4c6a2fc-1214-4ca0-8fb7-aef2e29ff63a%22',
 496             'info_dict': {
 497                 'id': 'e4c6a2fc-1214-4ca0-8fb7-aef2e29ff63a',
 498                 'title': 'Showcase Videos',
 499             },
 500             'playlist_mincount': 140,
 501
 502         },
 503         {
 504             'url': 'https://demo.hosted.panopto.com/Panopto/Pages/Sessions/List.aspx#view=2&maxResults=250',
 505             'info_dict': {
 506                 'id': 'panopto_list',
 507                 'title': 'panopto_list',
 508             },
 509             'playlist_mincount': 300,
 510         },
 511         {
 512             # Folder that contains 8 folders and a playlist
 513             'url': 'https://howtovideos.hosted.panopto.com/Panopto/Pages/Sessions/List.aspx?noredirect=true#folderID=%224b9de7ae-0080-4158-8496-a9ba01692c2e%22',
 514             'info_dict': {
 515                 'id': '4b9de7ae-0080-4158-8496-a9ba01692c2e',
 516                 'title': 'Video Tutorials',
 517             },
 518             'playlist_mincount': 9,
 519         },
 520
 521     ]
 522
 523     def _fetch_page(self, base_url, query_params, display_id, page):
 524
 525         params = {
 526             'sortColumn': 1,
 527             'getFolderData': True,
 528             'includePlaylists': True,
 529             **query_params,
 530             'page': page,
 531             'maxResults': self._PAGE_SIZE,
 532         }
 533
 534         response = self._call_api(
 535             base_url, '/Services/Data.svc/GetSessions', f'{display_id} page {page + 1}',
 536             data={'queryParameters': params}, fatal=False)
 537
 538         for result in get_first(response, 'Results', default=[]):
 539             # This could be a video, playlist (or maybe something else)
 540             item_id = result.get('DeliveryID')
 541             yield {
 542                 '_type': 'url',
 543                 'id': item_id,
 544                 'title': result.get('SessionName'),
 545                 'url': traverse_obj(result, 'ViewerUrl', 'EmbedUrl', get_all=False) or (base_url + f'/Pages/Viewer.aspx?id={item_id}'),
 546                 'duration': result.get('Duration'),
 547                 'channel': result.get('FolderName'),
 548                 'channel_id': result.get('FolderID'),
 549             }
 550
 551         for folder in get_first(response, 'Subfolders', default=[]):
 552             folder_id = folder.get('ID')
 553             yield self.url_result(
 554                 base_url + f'/Pages/Sessions/List.aspx#folderID="{folder_id}"',
 555                 ie_key=PanoptoListIE.ie_key(), video_id=folder_id, title=folder.get('Name'))
 556
 557     def _extract_folder_metadata(self, base_url, folder_id):
 558         response = self._call_api(
 559             base_url, '/Services/Data.svc/GetFolderInfo', folder_id,
 560             data={'folderID': folder_id}, fatal=False)
 561         return {
 562             'title': get_first(response, 'Name'),
 563         }
 564
 565     def _real_extract(self, url):
 566         mobj = self._match_valid_url(url)
 567         base_url = mobj.group('base_url')
 568
 569         query_params = self._parse_fragment(url)
 570         folder_id, display_id = query_params.get('folderID'), 'panopto_list'
 571
 572         if query_params.get('isSubscriptionsPage'):
 573             display_id = 'subscriptions'
 574             if not query_params.get('subscribableTypes'):
 575                 query_params['subscribableTypes'] = [0, 1, 2]
 576         elif query_params.get('isSharedWithMe'):
 577             display_id = 'sharedwithme'
 578         elif folder_id:
 579             display_id = folder_id
 580
 581         query = query_params.get('query')
 582         if query:
 583             display_id += f': query "{query}"'
 584
 585         info = {
 586             '_type': 'playlist',
 587             'id': display_id,
 588             'title': display_id,
 589         }
 590         if folder_id:
 591             info.update(self._extract_folder_metadata(base_url, folder_id))
 592
 593         info['entries'] = OnDemandPagedList(
 594             functools.partial(self._fetch_page, base_url, query_params, display_id), self._PAGE_SIZE)
 595
 596         return info