yt_dlp/extractor/panopto.py

   1 import re
   2 import calendar
   3 import json
   4 import functools
   5 from datetime import datetime
   6 from random import random
   7
   8 from .common import InfoExtractor
   9 from ..compat import (
  10     compat_urllib_parse_urlparse,
  11     compat_urlparse
  12 )
  13
  14 from ..utils import (
  15     bug_reports_message,
  16     ExtractorError,
  17     get_first,
  18     int_or_none,
  19     OnDemandPagedList,
  20     parse_qs,
  21     srt_subtitles_timecode,
  22     traverse_obj,
  23 )
  24
  25
  26 class PanoptoBaseIE(InfoExtractor):
  27     BASE_URL_RE = r'(?P<base_url>https?://[\w.-]+\.panopto.(?:com|eu)/Panopto)'
  28
  29     # see panopto core.js
  30     _SUB_LANG_MAPPING = {
  31         0: 'en-US',
  32         1: 'en-GB',
  33         2: 'es-MX',
  34         3: 'es-ES',
  35         4: 'de-DE',
  36         5: 'fr-FR',
  37         6: 'nl-NL',
  38         7: 'th-TH',
  39         8: 'zh-CN',
  40         9: 'zh-TW',
  41         10: 'ko-KR',
  42         11: 'ja-JP',
  43         12: 'ru-RU',
  44         13: 'pt-PT',
  45         14: 'pl-PL',
  46         15: 'en-AU',
  47         16: 'da-DK',
  48         17: 'fi-FI',
  49         18: 'hu-HU',
  50         19: 'nb-NO',
  51         20: 'sv-SE',
  52         21: 'it-IT'
  53     }
  54
  55     def _call_api(self, base_url, path, video_id, data=None, fatal=True, **kwargs):
  56         response = self._download_json(
  57             base_url + path, video_id, data=json.dumps(data).encode('utf8') if data else None,
  58             fatal=fatal, headers={'accept': 'application/json', 'content-type': 'application/json'}, **kwargs)
  59         if not response:
  60             return
  61         error_code = traverse_obj(response, 'ErrorCode')
  62         if error_code == 2:
  63             self.raise_login_required(method='cookies')
  64         elif error_code is not None:
  65             msg = f'Panopto said: {response.get("ErrorMessage")}'
  66             if fatal:
  67                 raise ExtractorError(msg, video_id=video_id, expected=True)
  68             else:
  69                 self.report_warning(msg, video_id=video_id)
  70         return response
  71
  72     @staticmethod
  73     def _parse_fragment(url):
  74         return {k: json.loads(v[0]) for k, v in compat_urlparse.parse_qs(compat_urllib_parse_urlparse(url).fragment).items()}
  75
  76     @staticmethod
  77     def _extract_urls(webpage):
  78         return [m.group('url') for m in re.finditer(
  79             r'<iframe[^>]+src=["\'](?P<url>%s/Pages/(Viewer|Embed|Sessions/List)\.aspx[^"\']+)' % PanoptoIE.BASE_URL_RE,
  80             webpage)]
  81
  82
  83 class PanoptoIE(PanoptoBaseIE):
  84     _VALID_URL = PanoptoBaseIE.BASE_URL_RE + r'/Pages/(Viewer|Embed)\.aspx.*(?:\?|&)id=(?P<id>[a-f0-9-]+)'
  85     _TESTS = [
  86         {
  87             'url': 'https://demo.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=26b3ae9e-4a48-4dcc-96ba-0befba08a0fb',
  88             'info_dict': {
  89                 'id': '26b3ae9e-4a48-4dcc-96ba-0befba08a0fb',
  90                 'title': 'Panopto for Business - Use Cases',
  91                 'timestamp': 1459184200,
  92                 'thumbnail': r're:https://demo\.hosted\.panopto\.com/.+',
  93                 'upload_date': '20160328',
  94                 'ext': 'mp4',
  95                 'cast': [],
  96                 'chapters': [],
  97                 'duration': 88.17099999999999,
  98                 'average_rating': int,
  99                 'uploader_id': '2db6b718-47a0-4b0b-9e17-ab0b00f42b1e',
 100                 'channel_id': 'e4c6a2fc-1214-4ca0-8fb7-aef2e29ff63a',
 101                 'channel': 'Showcase Videos'
 102             },
 103         },
 104         {
 105             'url': 'https://demo.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=ed01b077-c9e5-4c7b-b8ff-15fa306d7a59',
 106             'info_dict': {
 107                 'id': 'ed01b077-c9e5-4c7b-b8ff-15fa306d7a59',
 108                 'title': 'Overcoming Top 4 Challenges of Enterprise Video',
 109                 'uploader': 'Panopto Support',
 110                 'timestamp': 1449409251,
 111                 'thumbnail': r're:https://demo\.hosted\.panopto\.com/.+',
 112                 'upload_date': '20151206',
 113                 'ext': 'mp4',
 114                 'chapters': 'count:12',
 115                 'cast': ['Panopto Support'],
 116                 'uploader_id': 'a96d1a31-b4de-489b-9eee-b4a5b414372c',
 117                 'average_rating': int,
 118                 'description': 'md5:4391837802b3fc856dadf630c4b375d1',
 119                 'duration': 1088.2659999999998,
 120                 'channel_id': '9f3c1921-43bb-4bda-8b3a-b8d2f05a8546',
 121                 'channel': 'Webcasts',
 122             },
 123         },
 124         {
 125             # Extra params in URL
 126             'url': 'https://howtovideos.hosted.panopto.com/Panopto/Pages/Viewer.aspx?randomparam=thisisnotreal&id=5fa74e93-3d87-4694-b60e-aaa4012214ed&advance=true',
 127             'info_dict': {
 128                 'id': '5fa74e93-3d87-4694-b60e-aaa4012214ed',
 129                 'ext': 'mp4',
 130                 'duration': 129.513,
 131                 'cast': ['Kathryn Kelly'],
 132                 'uploader_id': '316a0a58-7fa2-4cd9-be1c-64270d284a56',
 133                 'timestamp': 1569845768,
 134                 'tags': ['Viewer', 'Enterprise'],
 135                 'chapters': [],
 136                 'upload_date': '20190930',
 137                 'thumbnail': r're:https://howtovideos\.hosted\.panopto\.com/.+',
 138                 'description': 'md5:2d844aaa1b1a14ad0e2601a0993b431f',
 139                 'title': 'Getting Started: View a Video',
 140                 'average_rating': int,
 141                 'uploader': 'Kathryn Kelly',
 142                 'channel_id': 'fb93bc3c-6750-4b80-a05b-a921013735d3',
 143                 'channel': 'Getting Started',
 144             }
 145         },
 146         {
 147             # Does not allow normal Viewer.aspx. AUDIO livestream has no url, so should be skipped and only give one stream.
 148             'url': 'https://unisa.au.panopto.com/Panopto/Pages/Embed.aspx?id=9d9a0fa3-e99a-4ebd-a281-aac2017f4da4',
 149             'info_dict': {
 150                 'id': '9d9a0fa3-e99a-4ebd-a281-aac2017f4da4',
 151                 'ext': 'mp4',
 152                 'cast': ['LTS CLI Script'],
 153                 'chapters': [],
 154                 'duration': 2178.45,
 155                 'description': 'md5:ee5cf653919f55b72bce2dbcf829c9fa',
 156                 'channel_id': 'b23e673f-c287-4cb1-8344-aae9005a69f8',
 157                 'average_rating': int,
 158                 'uploader_id': '38377323-6a23-41e2-9ff6-a8e8004bf6f7',
 159                 'uploader': 'LTS CLI Script',
 160                 'timestamp': 1572458134,
 161                 'title': 'WW2 Vets Interview 3 Ronald Stanley George',
 162                 'thumbnail': r're:https://unisa\.au\.panopto\.com/.+',
 163                 'channel': 'World War II Veteran Interviews',
 164                 'upload_date': '20191030',
 165             },
 166         },
 167         {
 168             # Slides/storyboard
 169             'url': 'https://demo.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=a7f12f1d-3872-4310-84b0-f8d8ab15326b',
 170             'info_dict': {
 171                 'id': 'a7f12f1d-3872-4310-84b0-f8d8ab15326b',
 172                 'ext': 'mhtml',
 173                 'timestamp': 1448798857,
 174                 'duration': 4712.681,
 175                 'title': 'Cache Memory - CompSci 15-213, Lecture 12',
 176                 'channel_id': 'e4c6a2fc-1214-4ca0-8fb7-aef2e29ff63a',
 177                 'uploader_id': 'a96d1a31-b4de-489b-9eee-b4a5b414372c',
 178                 'upload_date': '20151129',
 179                 'average_rating': 0,
 180                 'uploader': 'Panopto Support',
 181                 'channel': 'Showcase Videos',
 182                 'description': 'md5:55e51d54233ddb0e6c2ed388ca73822c',
 183                 'cast': ['ISR Videographer', 'Panopto Support'],
 184                 'chapters': 'count:28',
 185                 'thumbnail': r're:https://demo\.hosted\.panopto\.com/.+',
 186             },
 187             'params': {'format': 'mhtml', 'skip_download': True}
 188         },
 189         {
 190             'url': 'https://na-training-1.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=8285224a-9a2b-4957-84f2-acb0000c4ea9',
 191             'info_dict': {
 192                 'id': '8285224a-9a2b-4957-84f2-acb0000c4ea9',
 193                 'ext': 'mp4',
 194                 'chapters': [],
 195                 'title': 'Company Policy',
 196                 'average_rating': 0,
 197                 'timestamp': 1615058901,
 198                 'channel': 'Human Resources',
 199                 'tags': ['HumanResources'],
 200                 'duration': 1604.243,
 201                 'thumbnail': r're:https://na-training-1\.hosted\.panopto\.com/.+',
 202                 'uploader_id': '8e8ba0a3-424f-40df-a4f1-ab3a01375103',
 203                 'uploader': 'Cait M.',
 204                 'upload_date': '20210306',
 205                 'cast': ['Cait M.'],
 206                 'subtitles': {'en-US': [{'ext': 'srt', 'data': 'md5:a3f4d25963fdeace838f327097c13265'}],
 207                               'es-ES': [{'ext': 'srt', 'data': 'md5:57e9dad365fd0fbaf0468eac4949f189'}]},
 208             },
 209             'params': {'writesubtitles': True, 'skip_download': True}
 210         }, {
 211             # On Panopto there are two subs: "Default" and en-US. en-US is blank and should be skipped.
 212             'url': 'https://na-training-1.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=940cbd41-f616-4a45-b13e-aaf1000c915b',
 213             'info_dict': {
 214                 'id': '940cbd41-f616-4a45-b13e-aaf1000c915b',
 215                 'ext': 'mp4',
 216                 'subtitles': 'count:1',
 217                 'title': 'HR Benefits Review Meeting*',
 218                 'cast': ['Panopto Support'],
 219                 'chapters': [],
 220                 'timestamp': 1575024251,
 221                 'thumbnail': r're:https://na-training-1\.hosted\.panopto\.com/.+',
 222                 'channel': 'Zoom',
 223                 'description': 'md5:04f90a9c2c68b7828144abfb170f0106',
 224                 'uploader': 'Panopto Support',
 225                 'average_rating': 0,
 226                 'duration': 409.34499999999997,
 227                 'uploader_id': 'b6ac04ad-38b8-4724-a004-a851004ea3df',
 228                 'upload_date': '20191129',
 229
 230             },
 231             'params': {'writesubtitles': True, 'skip_download': True}
 232         },
 233         {
 234             'url': 'https://ucc.cloud.panopto.eu/Panopto/Pages/Viewer.aspx?id=0e8484a4-4ceb-4d98-a63f-ac0200b455cb',
 235             'only_matching': True
 236         },
 237         {
 238             'url': 'https://brown.hosted.panopto.com/Panopto/Pages/Embed.aspx?id=0b3ff73b-36a0-46c5-8455-aadf010a3638',
 239             'only_matching': True
 240         },
 241     ]
 242
 243     @classmethod
 244     def suitable(cls, url):
 245         return False if PanoptoPlaylistIE.suitable(url) else super().suitable(url)
 246
 247     def _mark_watched(self, base_url, video_id, delivery_info):
 248         duration = traverse_obj(delivery_info, ('Delivery', 'Duration'), expected_type=float)
 249         invocation_id = delivery_info.get('InvocationId')
 250         stream_id = traverse_obj(delivery_info, ('Delivery', 'Streams', ..., 'PublicID'), get_all=False, expected_type=str)
 251         if invocation_id and stream_id and duration:
 252             timestamp_str = f'/Date({calendar.timegm(datetime.utcnow().timetuple())}000)/'
 253             data = {
 254                 'streamRequests': [
 255                     {
 256                         'ClientTimeStamp': timestamp_str,
 257                         'ID': 0,
 258                         'InvocationID': invocation_id,
 259                         'PlaybackSpeed': 1,
 260                         'SecondsListened': duration - 1,
 261                         'SecondsRejected': 0,
 262                         'StartPosition': 0,
 263                         'StartReason': 2,
 264                         'StopReason': None,
 265                         'StreamID': stream_id,
 266                         'TimeStamp': timestamp_str,
 267                         'UpdatesRejected': 0
 268                     },
 269                 ]}
 270
 271             self._download_webpage(
 272                 base_url + '/Services/Analytics.svc/AddStreamRequests', video_id,
 273                 fatal=False, data=json.dumps(data).encode('utf8'), headers={'content-type': 'application/json'},
 274                 note='Marking watched', errnote='Unable to mark watched')
 275
 276     @staticmethod
 277     def _extract_chapters(timestamps):
 278         chapters = []
 279         for timestamp in timestamps or []:
 280             caption = timestamp.get('Caption')
 281             start, duration = int_or_none(timestamp.get('Time')), int_or_none(timestamp.get('Duration'))
 282             if not caption or start is None or duration is None:
 283                 continue
 284             chapters.append({
 285                 'start_time': start,
 286                 'end_time': start + duration,
 287                 'title': caption
 288             })
 289         return chapters
 290
 291     @staticmethod
 292     def _extract_mhtml_formats(base_url, timestamps):
 293         image_frags = {}
 294         for timestamp in timestamps or []:
 295             duration = timestamp.get('Duration')
 296             obj_id, obj_sn = timestamp.get('ObjectIdentifier'), timestamp.get('ObjectSequenceNumber'),
 297             if timestamp.get('EventTargetType') == 'PowerPoint' and obj_id is not None and obj_sn is not None:
 298                 image_frags.setdefault('slides', []).append({
 299                     'url': base_url + f'/Pages/Viewer/Image.aspx?id={obj_id}&number={obj_sn}',
 300                     'duration': duration
 301                 })
 302
 303             obj_pid, session_id, abs_time = timestamp.get('ObjectPublicIdentifier'), timestamp.get('SessionID'), timestamp.get('AbsoluteTime')
 304             if None not in (obj_pid, session_id, abs_time):
 305                 image_frags.setdefault('chapter', []).append({
 306                     'url': base_url + f'/Pages/Viewer/Thumb.aspx?eventTargetPID={obj_pid}&sessionPID={session_id}&number={obj_sn}&isPrimary=false&absoluteTime={abs_time}',
 307                     'duration': duration,
 308                 })
 309         for name, fragments in image_frags.items():
 310             yield {
 311                 'format_id': name,
 312                 'ext': 'mhtml',
 313                 'protocol': 'mhtml',
 314                 'acodec': 'none',
 315                 'vcodec': 'none',
 316                 'url': 'about:invalid',
 317                 'fragments': fragments
 318             }
 319
 320     @staticmethod
 321     def _json2srt(data, delivery):
 322         def _gen_lines():
 323             for i, line in enumerate(data):
 324                 start_time = line['Time']
 325                 duration = line.get('Duration')
 326                 if duration:
 327                     end_time = start_time + duration
 328                 else:
 329                     end_time = traverse_obj(data, (i + 1, 'Time')) or delivery['Duration']
 330                 yield f'{i + 1}\n{srt_subtitles_timecode(start_time)} --> {srt_subtitles_timecode(end_time)}\n{line["Caption"]}'
 331         return '\n\n'.join(_gen_lines())
 332
 333     def _get_subtitles(self, base_url, video_id, delivery):
 334         subtitles = {}
 335         for lang in delivery.get('AvailableLanguages') or []:
 336             response = self._call_api(
 337                 base_url, '/Pages/Viewer/DeliveryInfo.aspx', video_id, fatal=False,
 338                 note='Downloading captions JSON metadata', query={
 339                     'deliveryId': video_id,
 340                     'getCaptions': True,
 341                     'language': str(lang),
 342                     'responseType': 'json'
 343                 }
 344             )
 345             if not isinstance(response, list):
 346                 continue
 347             subtitles.setdefault(self._SUB_LANG_MAPPING.get(lang) or 'default', []).append({
 348                 'ext': 'srt',
 349                 'data': self._json2srt(response, delivery),
 350             })
 351         return subtitles
 352
 353     def _extract_streams_formats_and_subtitles(self, video_id, streams, **fmt_kwargs):
 354         formats = []
 355         subtitles = {}
 356         for stream in streams or []:
 357             stream_formats = []
 358             http_stream_url = stream.get('StreamHttpUrl')
 359             stream_url = stream.get('StreamUrl')
 360
 361             if http_stream_url:
 362                 stream_formats.append({'url': http_stream_url})
 363
 364             if stream_url:
 365                 media_type = stream.get('ViewerMediaFileTypeName')
 366                 if media_type in ('hls', ):
 367                     m3u8_formats, stream_subtitles = self._extract_m3u8_formats_and_subtitles(stream_url, video_id)
 368                     stream_formats.extend(m3u8_formats)
 369                     subtitles = self._merge_subtitles(subtitles, stream_subtitles)
 370                 else:
 371                     stream_formats.append({
 372                         'url': stream_url
 373                     })
 374             for fmt in stream_formats:
 375                 fmt.update({
 376                     'format_note': stream.get('Tag'),
 377                     **fmt_kwargs
 378                 })
 379             formats.extend(stream_formats)
 380
 381         return formats, subtitles
 382
 383     def _real_extract(self, url):
 384         base_url, video_id = self._match_valid_url(url).group('base_url', 'id')
 385         delivery_info = self._call_api(
 386             base_url, '/Pages/Viewer/DeliveryInfo.aspx', video_id,
 387             query={
 388                 'deliveryId': video_id,
 389                 'invocationId': '',
 390                 'isLiveNotes': 'false',
 391                 'refreshAuthCookie': 'true',
 392                 'isActiveBroadcast': 'false',
 393                 'isEditing': 'false',
 394                 'isKollectiveAgentInstalled': 'false',
 395                 'isEmbed': 'false',
 396                 'responseType': 'json',
 397             }
 398         )
 399
 400         delivery = delivery_info['Delivery']
 401         session_start_time = int_or_none(delivery.get('SessionStartTime'))
 402         timestamps = delivery.get('Timestamps')
 403
 404         # Podcast stream is usually the combined streams. We will prefer that by default.
 405         podcast_formats, podcast_subtitles = self._extract_streams_formats_and_subtitles(
 406             video_id, delivery.get('PodcastStreams'), format_note='PODCAST')
 407
 408         streams_formats, streams_subtitles = self._extract_streams_formats_and_subtitles(
 409             video_id, delivery.get('Streams'), preference=-10)
 410
 411         formats = podcast_formats + streams_formats
 412         formats.extend(self._extract_mhtml_formats(base_url, timestamps))
 413         subtitles = self._merge_subtitles(
 414             podcast_subtitles, streams_subtitles, self.extract_subtitles(base_url, video_id, delivery))
 415
 416         self._sort_formats(formats)
 417         self.mark_watched(base_url, video_id, delivery_info)
 418
 419         return {
 420             'id': video_id,
 421             'title': delivery.get('SessionName'),
 422             'cast': traverse_obj(delivery, ('Contributors', ..., 'DisplayName'), default=[], expected_type=lambda x: x or None),
 423             'timestamp': session_start_time - 11640000000 if session_start_time else None,
 424             'duration': delivery.get('Duration'),
 425             'thumbnail': base_url + f'/Services/FrameGrabber.svc/FrameRedirect?objectId={video_id}&mode=Delivery&random={random()}',
 426             'average_rating': delivery.get('AverageRating'),
 427             'chapters': self._extract_chapters(timestamps),
 428             'uploader': delivery.get('OwnerDisplayName') or None,
 429             'uploader_id': delivery.get('OwnerId'),
 430             'description': delivery.get('SessionAbstract'),
 431             'tags': traverse_obj(delivery, ('Tags', ..., 'Content')),
 432             'channel_id': delivery.get('SessionGroupPublicID'),
 433             'channel': traverse_obj(delivery, 'SessionGroupLongName', 'SessionGroupShortName', get_all=False),
 434             'formats': formats,
 435             'subtitles': subtitles
 436         }
 437
 438
 439 class PanoptoPlaylistIE(PanoptoBaseIE):
 440     _VALID_URL = PanoptoBaseIE.BASE_URL_RE + r'/Pages/(Viewer|Embed)\.aspx.*(?:\?|&)pid=(?P<id>[a-f0-9-]+)'
 441     _TESTS = [
 442         {
 443             'url': 'https://howtovideos.hosted.panopto.com/Panopto/Pages/Viewer.aspx?pid=f3b39fcf-882f-4849-93d6-a9f401236d36&id=5fa74e93-3d87-4694-b60e-aaa4012214ed&advance=true',
 444             'info_dict': {
 445                 'title': 'Featured Video Tutorials',
 446                 'id': 'f3b39fcf-882f-4849-93d6-a9f401236d36',
 447                 'description': '',
 448             },
 449             'playlist_mincount': 36
 450         },
 451         {
 452             'url': 'https://utsa.hosted.panopto.com/Panopto/Pages/Viewer.aspx?pid=e2900555-3ad4-4bdb-854d-ad2401686190',
 453             'info_dict': {
 454                 'title': 'Library Website Introduction Playlist',
 455                 'id': 'e2900555-3ad4-4bdb-854d-ad2401686190',
 456                 'description': 'md5:f958bca50a1cbda15fdc1e20d32b3ecb',
 457             },
 458             'playlist_mincount': 4
 459         },
 460
 461     ]
 462
 463     def _entries(self, base_url, playlist_id, session_list_id):
 464         session_list_info = self._call_api(
 465             base_url, f'/Api/SessionLists/{session_list_id}?collections[0].maxCount=500&collections[0].name=items', playlist_id)
 466
 467         items = session_list_info['Items']
 468         for item in items:
 469             if item.get('TypeName') != 'Session':
 470                 self.report_warning('Got an item in the playlist that is not a Session' + bug_reports_message(), only_once=True)
 471                 continue
 472             yield {
 473                 '_type': 'url',
 474                 'id': item.get('Id'),
 475                 'url': item.get('ViewerUri'),
 476                 'title': item.get('Name'),
 477                 'description': item.get('Description'),
 478                 'duration': item.get('Duration'),
 479                 'channel': traverse_obj(item, ('Parent', 'Name')),
 480                 'channel_id': traverse_obj(item, ('Parent', 'Id'))
 481             }
 482
 483     def _real_extract(self, url):
 484         base_url, playlist_id = self._match_valid_url(url).group('base_url', 'id')
 485
 486         video_id = get_first(parse_qs(url), 'id')
 487         if video_id:
 488             if self.get_param('noplaylist'):
 489                 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
 490                 return self.url_result(base_url + f'/Pages/Viewer.aspx?id={video_id}', ie_key=PanoptoIE.ie_key(), video_id=video_id)
 491             else:
 492                 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
 493
 494         playlist_info = self._call_api(base_url, f'/Api/Playlists/{playlist_id}', playlist_id)
 495         return self.playlist_result(
 496             self._entries(base_url, playlist_id, playlist_info['SessionListId']),
 497             playlist_id=playlist_id, playlist_title=playlist_info.get('Name'),
 498             playlist_description=playlist_info.get('Description'))
 499
 500
 501 class PanoptoListIE(PanoptoBaseIE):
 502     _VALID_URL = PanoptoBaseIE.BASE_URL_RE + r'/Pages/Sessions/List\.aspx'
 503     _PAGE_SIZE = 250
 504     _TESTS = [
 505         {
 506             'url': 'https://demo.hosted.panopto.com/Panopto/Pages/Sessions/List.aspx#folderID=%22e4c6a2fc-1214-4ca0-8fb7-aef2e29ff63a%22',
 507             'info_dict': {
 508                 'id': 'e4c6a2fc-1214-4ca0-8fb7-aef2e29ff63a',
 509                 'title': 'Showcase Videos'
 510             },
 511             'playlist_mincount': 140
 512
 513         },
 514         {
 515             'url': 'https://demo.hosted.panopto.com/Panopto/Pages/Sessions/List.aspx#view=2&maxResults=250',
 516             'info_dict': {
 517                 'id': 'panopto_list',
 518                 'title': 'panopto_list'
 519             },
 520             'playlist_mincount': 300
 521         },
 522         {
 523             # Folder that contains 8 folders and a playlist
 524             'url': 'https://howtovideos.hosted.panopto.com/Panopto/Pages/Sessions/List.aspx?noredirect=true#folderID=%224b9de7ae-0080-4158-8496-a9ba01692c2e%22',
 525             'info_dict': {
 526                 'id': '4b9de7ae-0080-4158-8496-a9ba01692c2e',
 527                 'title': 'Video Tutorials'
 528             },
 529             'playlist_mincount': 9
 530         }
 531
 532     ]
 533
 534     def _fetch_page(self, base_url, query_params, display_id, page):
 535
 536         params = {
 537             'sortColumn': 1,
 538             'getFolderData': True,
 539             'includePlaylists': True,
 540             **query_params,
 541             'page': page,
 542             'maxResults': self._PAGE_SIZE,
 543         }
 544
 545         response = self._call_api(
 546             base_url, '/Services/Data.svc/GetSessions', f'{display_id} page {page+1}',
 547             data={'queryParameters': params}, fatal=False)
 548
 549         for result in get_first(response, 'Results', default=[]):
 550             # This could be a video, playlist (or maybe something else)
 551             item_id = result.get('DeliveryID')
 552             yield {
 553                 '_type': 'url',
 554                 'id': item_id,
 555                 'title': result.get('SessionName'),
 556                 'url': traverse_obj(result, 'ViewerUrl', 'EmbedUrl', get_all=False) or (base_url + f'/Pages/Viewer.aspx?id={item_id}'),
 557                 'duration': result.get('Duration'),
 558                 'channel': result.get('FolderName'),
 559                 'channel_id': result.get('FolderID'),
 560             }
 561
 562         for folder in get_first(response, 'Subfolders', default=[]):
 563             folder_id = folder.get('ID')
 564             yield self.url_result(
 565                 base_url + f'/Pages/Sessions/List.aspx#folderID="{folder_id}"',
 566                 ie_key=PanoptoListIE.ie_key(), video_id=folder_id, title=folder.get('Name'))
 567
 568     def _extract_folder_metadata(self, base_url, folder_id):
 569         response = self._call_api(
 570             base_url, '/Services/Data.svc/GetFolderInfo', folder_id,
 571             data={'folderID': folder_id}, fatal=False)
 572         return {
 573             'title': get_first(response, 'Name', default=[])
 574         }
 575
 576     def _real_extract(self, url):
 577         mobj = self._match_valid_url(url)
 578         base_url = mobj.group('base_url')
 579
 580         query_params = self._parse_fragment(url)
 581         folder_id, display_id = query_params.get('folderID'), 'panopto_list'
 582
 583         if query_params.get('isSubscriptionsPage'):
 584             display_id = 'subscriptions'
 585             if not query_params.get('subscribableTypes'):
 586                 query_params['subscribableTypes'] = [0, 1, 2]
 587         elif query_params.get('isSharedWithMe'):
 588             display_id = 'sharedwithme'
 589         elif folder_id:
 590             display_id = folder_id
 591
 592         query = query_params.get('query')
 593         if query:
 594             display_id += f': query "{query}"'
 595
 596         info = {
 597             '_type': 'playlist',
 598             'id': display_id,
 599             'title': display_id,
 600         }
 601         if folder_id:
 602             info.update(self._extract_folder_metadata(base_url, folder_id))
 603
 604         info['entries'] = OnDemandPagedList(
 605             functools.partial(self._fetch_page, base_url, query_params, display_id), self._PAGE_SIZE)
 606
 607         return info