yt_dlp/extractor/sharepoint.py

   1 import json
   2 import urllib.parse
   3
   4 from .common import InfoExtractor
   5 from ..utils import determine_ext, int_or_none, url_or_none
   6 from ..utils.traversal import traverse_obj
   7
   8
   9 class SharePointIE(InfoExtractor):
  10     _BASE_URL_RE = r'https?://[\w-]+\.sharepoint\.com/'
  11     _VALID_URL = [
  12         rf'{_BASE_URL_RE}:v:/[a-z]/(?:[^/?#]+/)*(?P<id>[^/?#]{{46}})/?(?:$|[?#])',
  13         rf'{_BASE_URL_RE}(?!:v:)(?:[^/?#]+/)*stream\.aspx\?(?:[^#]+&)?id=(?P<id>[^&#]+)',
  14     ]
  15     _TESTS = [{
  16         'url': 'https://lut-my.sharepoint.com/:v:/g/personal/juha_eerola_student_lab_fi/EUrAmrktb4ZMhUcY9J2PqMEBD_9x_l0DyYWVgAvp-TTOMw?e=ZpQOOw',
  17         'md5': '2950821d0d4937a0a76373782093b435',
  18         'info_dict': {
  19             'id': '01EQRS7EKKYCNLSLLPQZGIKRYY6SOY7KGB',
  20             'display_id': 'EUrAmrktb4ZMhUcY9J2PqMEBD_9x_l0DyYWVgAvp-TTOMw',
  21             'ext': 'mp4',
  22             'title': 'CmvpJST',
  23             'duration': 54.567,
  24             'thumbnail': r're:https://.+/thumbnail',
  25             'uploader_id': '8dcec565-a956-4b91-95e5-bacfb8bc015f',
  26         },
  27     }, {
  28         'url': 'https://greaternyace.sharepoint.com/:v:/s/acementornydrive/ETski5eAfNVEoPRZUAyy1wEBpLgVFYWso5bjbZjfBLlPUg?e=PQUfVb',
  29         'md5': 'c496a01644223273bff12e93e501afd1',
  30         'info_dict': {
  31             'id': '01QI4AVTZ3ESFZPAD42VCKB5CZKAGLFVYB',
  32             'display_id': 'ETski5eAfNVEoPRZUAyy1wEBpLgVFYWso5bjbZjfBLlPUg',
  33             'ext': 'mp4',
  34             'title': '930103681233985536',
  35             'duration': 3797.326,
  36             'thumbnail': r're:https://.+/thumbnail',
  37         },
  38     }, {
  39         'url': 'https://lut-my.sharepoint.com/personal/juha_eerola_student_lab_fi/_layouts/15/stream.aspx?id=%2Fpersonal%2Fjuha_eerola_student_lab_fi%2FDocuments%2FM-DL%2FCmvpJST.mp4&ga=1&referrer=StreamWebApp.Web&referrerScenario=AddressBarCopied.view',
  40         'info_dict': {
  41             'id': '01EQRS7EKKYCNLSLLPQZGIKRYY6SOY7KGB',
  42             'display_id': '/personal/juha_eerola_student_lab_fi/Documents/M-DL/CmvpJST.mp4',
  43             'ext': 'mp4',
  44             'title': 'CmvpJST',
  45             'duration': 54.567,
  46             'thumbnail': r're:https://.+/thumbnail',
  47             'uploader_id': '8dcec565-a956-4b91-95e5-bacfb8bc015f',
  48         },
  49         'skip': 'Session cookies needed',
  50     }, {
  51         'url': 'https://izoobasisschool.sharepoint.com/:v:/g/Eaqleq8COVBIvIPvod0U27oBypC6aWOkk8ptuDpmJ6arHw',
  52         'only_matching': True,
  53     }, {
  54         'url': 'https://uskudaredutr-my.sharepoint.com/:v:/g/personal/songul_turkaydin_uskudar_edu_tr/EbTf-VRUIbtGuIN73tx1MuwBCHBOmNcWNqSLw61Fd2_o0g?e=n5Vkof',
  55         'only_matching': True,
  56     }, {
  57         'url': 'https://epam-my.sharepoint.com/:v:/p/dzmitry_tamashevich/Ec4ZOs-rATZHjFYZWVxjczEB649FCoYFKDV_x3RxZiWAGA?e=4hswgA',
  58         'only_matching': True,
  59     }, {
  60         'url': 'https://microsoft.sharepoint.com/:v:/t/MicrosoftSPARKRecordings-MSFTInternal/EWCyeqByVWBAt8wDvNZdV-UB0BvU5YVbKm0UHgdrUlI6dg?e=QbPck6',
  61         'only_matching': True,
  62     }]
  63
  64     def _real_extract(self, url):
  65         display_id = urllib.parse.unquote(self._match_id(url))
  66         webpage, urlh = self._download_webpage_handle(url, display_id)
  67         if urllib.parse.urlparse(urlh.url).hostname == 'login.microsoftonline.com':
  68             self.raise_login_required(
  69                 'Session cookies are required for this URL and can be passed '
  70                 'with the --cookies option. The --cookies-from-browser option will not work', method=None)
  71
  72         video_data = self._search_json(r'g_fileInfo\s*=', webpage, 'player config', display_id)
  73         video_id = video_data['VroomItemId']
  74
  75         parsed_url = urllib.parse.urlparse(video_data['.transformUrl'])
  76         base_media_url = urllib.parse.urlunparse(parsed_url._replace(
  77             path=urllib.parse.urljoin(f'{parsed_url.path}/', '../videomanifest'),
  78             query=urllib.parse.urlencode({
  79                 **urllib.parse.parse_qs(parsed_url.query),
  80                 'cTag': video_data['.ctag'],
  81                 'action': 'Access',
  82                 'part': 'index',
  83             }, doseq=True)))
  84
  85         # Web player adds more params to the format URLs but we still get all formats without them
  86         formats = self._extract_mpd_formats(
  87             base_media_url, video_id, mpd_id='dash', query={'format': 'dash'}, fatal=False)
  88         for hls_type in ('hls', 'hls-vnext'):
  89             formats.extend(self._extract_m3u8_formats(
  90                 base_media_url, video_id, 'mp4', m3u8_id=hls_type,
  91                 query={'format': hls_type}, fatal=False, quality=-2))
  92
  93         if video_url := traverse_obj(video_data, ('downloadUrl', {url_or_none})):
  94             formats.append({
  95                 'url': video_url,
  96                 'ext': determine_ext(video_data.get('extension') or video_data.get('name')),
  97                 'quality': 1,
  98                 'format_id': 'source',
  99                 'filesize': int_or_none(video_data.get('size')),
 100                 'vcodec': 'none' if video_data.get('isAudio') is True else None,
 101             })
 102
 103         return {
 104             'id': video_id,
 105             'formats': formats,
 106             'title': video_data.get('title') or video_data.get('displayName'),
 107             'display_id': display_id,
 108             'uploader_id': video_data.get('authorId'),
 109             'duration': traverse_obj(video_data, (
 110                 'MediaServiceFastMetadata', {json.loads}, 'media', 'duration', {lambda x: x / 10000000})),
 111             'thumbnail': url_or_none(video_data.get('thumbnailUrl')),
 112         }