@tushar-br/desktop 1.0.282 → 1.0.283

package/staging_area/micro projects/SD -Advanced Media Processing Toolkit Automated Downloader, Segmenter & Neural Dubber/.venv/Lib/site-packages/yt_dlp/extractor/stageplus.py

@@ -0,0 +1,515 @@
+import json
+import uuid
+
+from .common import InfoExtractor
+from ..utils import (
+    float_or_none,
+    traverse_obj,
+    try_call,
+    unified_timestamp,
+    url_or_none,
+)
+
+
+class StagePlusVODConcertIE(InfoExtractor):
+    _NETRC_MACHINE = 'stageplus'
+    _VALID_URL = r'https?://(?:www\.)?stage-plus\.com/video/(?P<id>vod_concert_\w+)'
+    _TESTS = [{
+        'url': 'https://www.stage-plus.com/video/vod_concert_APNM8GRFDPHMASJKBSPJACG',
+        'playlist_count': 6,
+        'info_dict': {
+            'id': 'vod_concert_APNM8GRFDPHMASJKBSPJACG',
+            'title': 'Yuja Wang plays Rachmaninoff\'s Piano Concerto No. 2 – from Odeonsplatz',
+            'description': 'md5:50f78ec180518c9bdb876bac550996fc',
+            'artists': ['Yuja Wang', 'Lorenzo Viotti'],
+            'upload_date': '20230331',
+            'timestamp': 1680249600,
+            'release_date': '20210709',
+            'release_timestamp': 1625788800,
+            'thumbnails': 'count:3',
+        },
+        'playlist': [{
+            'info_dict': {
+                'id': 'performance_work_A1IN4PJFE9MM2RJ3CLBMUSJBBSOJAD9O',
+                'ext': 'mp4',
+                'title': 'Piano Concerto No. 2 in C Minor, Op. 18',
+                'description': 'md5:50f78ec180518c9bdb876bac550996fc',
+                'upload_date': '20230331',
+                'timestamp': 1680249600,
+                'release_date': '20210709',
+                'release_timestamp': 1625788800,
+                'duration': 2207,
+                'chapters': 'count:5',
+                'artists': ['Yuja Wang'],
+                'composers': ['Sergei Rachmaninoff'],
+                'album': 'Yuja Wang plays Rachmaninoff\'s Piano Concerto No. 2 – from Odeonsplatz',
+                'album_artists': ['Yuja Wang', 'Lorenzo Viotti'],
+                'track': 'Piano Concerto No. 2 in C Minor, Op. 18',
+                'track_number': 1,
+                'genre': 'Instrumental Concerto',
+            },
+        }],
+        'params': {'skip_download': 'm3u8'},
+    }]
+
+    # TODO: Prune this after livestream and/or album extractors are added
+    _GRAPHQL_QUERY = '''query videoDetailPage($videoId: ID!, $sliderItemsFirst: Int = 24) {
+  node(id: $videoId) {
+    __typename
+    ...LiveConcertFields
+    ... on LiveConcert {
+      artists {
+        edges {
+          role {
+            ...RoleFields
+          }
+          node {
+            id
+            name
+            sortName
+          }
+        }
+      }
+      isAtmos
+      maxResolution
+      groups {
+        id
+        name
+        typeDisplayName
+      }
+      shortDescription
+      performanceWorks {
+        ...livePerformanceWorkFields
+      }
+      totalDuration
+      sliders {
+        ...contentContainerFields
+      }
+      vodConcert {
+        __typename
+        id
+      }
+    }
+    ...VideoFields
+    ... on Video {
+      artists {
+        edges {
+          role {
+            ...RoleFields
+          }
+          node {
+            id
+            name
+            sortName
+          }
+        }
+      }
+      isAtmos
+      maxResolution
+      isLossless
+      description
+      productionDate
+      takedownDate
+      sliders {
+        ...contentContainerFields
+      }
+    }
+    ...VodConcertFields
+    ... on VodConcert {
+      artists {
+        edges {
+          role {
+            ...RoleFields
+          }
+          node {
+            id
+            name
+            sortName
+          }
+        }
+      }
+      isAtmos
+      maxResolution
+      groups {
+        id
+        name
+        typeDisplayName
+      }
+      performanceWorks {
+        ...PerformanceWorkFields
+      }
+      shortDescription
+      productionDate
+      takedownDate
+      sliders {
+        ...contentContainerFields
+      }
+    }
+  }
+}
+
+fragment LiveConcertFields on LiveConcert {
+  endTime
+  id
+  pictures {
+    ...PictureFields
+  }
+  reruns {
+    ...liveConcertRerunFields
+  }
+  publicationLevel
+  startTime
+  streamStartTime
+  subtitle
+  title
+  typeDisplayName
+  stream {
+    ...liveStreamFields
+  }
+  trailerStream {
+    ...streamFields
+  }
+  geoAccessCountries
+  geoAccessMode
+}
+
+fragment PictureFields on Picture {
+  id
+  url
+  type
+}
+
+fragment liveConcertRerunFields on LiveConcertRerun {
+  streamStartTime
+  endTime
+  startTime
+  stream {
+    ...rerunStreamFields
+  }
+}
+
+fragment rerunStreamFields on RerunStream {
+  publicationLevel
+  streamType
+  url
+}
+
+fragment liveStreamFields on LiveStream {
+  publicationLevel
+  streamType
+  url
+}
+
+fragment streamFields on Stream {
+  publicationLevel
+  streamType
+  url
+}
+
+fragment RoleFields on Role {
+  __typename
+  id
+  type
+  displayName
+}
+
+fragment livePerformanceWorkFields on LivePerformanceWork {
+  __typename
+  id
+  artists {
+    ...artistWithRoleFields
+  }
+  groups {
+    edges {
+      node {
+        id
+        name
+        typeDisplayName
+      }
+    }
+  }
+  work {
+    ...workFields
+  }
+}
+
+fragment artistWithRoleFields on ArtistWithRoleConnection {
+  edges {
+    role {
+      ...RoleFields
+    }
+    node {
+      id
+      name
+      sortName
+    }
+  }
+}
+
+fragment workFields on Work {
+  id
+  title
+  movements {
+    id
+    title
+  }
+  composers {
+    id
+    name
+  }
+  genre {
+    id
+    title
+  }
+}
+
+fragment contentContainerFields on CuratedContentContainer {
+  __typename
+  ...SliderFields
+  ...BannerFields
+}
+
+fragment SliderFields on Slider {
+  id
+  headline
+  items(first: $sliderItemsFirst) {
+    edges {
+      node {
+        id
+        __typename
+        ...AlbumFields
+        ...ArtistFields
+        ...EpochFields
+        ...GenreFields
+        ...GroupFields
+        ...LiveConcertFields
+        ...PartnerFields
+        ...PerformanceWorkFields
+        ...VideoFields
+        ...VodConcertFields
+      }
+    }
+  }
+}
+
+fragment AlbumFields on Album {
+  artistAndGroupDisplayInfo
+  id
+  pictures {
+    ...PictureFields
+  }
+  title
+}
+
+fragment ArtistFields on Artist {
+  id
+  name
+  roles {
+    ...RoleFields
+  }
+  pictures {
+    ...PictureFields
+  }
+}
+
+fragment EpochFields on Epoch {
+  id
+  endYear
+  pictures {
+    ...PictureFields
+  }
+  startYear
+  title
+}
+
+fragment GenreFields on Genre {
+  id
+  pictures {
+    ...PictureFields
+  }
+  title
+}
+
+fragment GroupFields on Group {
+  id
+  name
+  typeDisplayName
+  pictures {
+    ...PictureFields
+  }
+}
+
+fragment PartnerFields on Partner {
+  id
+  name
+  typeDisplayName
+  subtypeDisplayName
+  pictures {
+    ...PictureFields
+  }
+}
+
+fragment PerformanceWorkFields on PerformanceWork {
+  __typename
+  id
+  artists {
+    ...artistWithRoleFields
+  }
+  groups {
+    edges {
+      node {
+        id
+        name
+        typeDisplayName
+      }
+    }
+  }
+  work {
+    ...workFields
+  }
+  stream {
+    ...streamFields
+  }
+  vodConcert {
+    __typename
+    id
+  }
+  duration
+  cuePoints {
+    mark
+    title
+  }
+}
+
+fragment VideoFields on Video {
+  id
+  archiveReleaseDate
+  title
+  subtitle
+  pictures {
+    ...PictureFields
+  }
+  stream {
+    ...streamFields
+  }
+  trailerStream {
+    ...streamFields
+  }
+  duration
+  typeDisplayName
+  duration
+  geoAccessCountries
+  geoAccessMode
+  publicationLevel
+  takedownDate
+}
+
+fragment VodConcertFields on VodConcert {
+  id
+  archiveReleaseDate
+  pictures {
+    ...PictureFields
+  }
+  subtitle
+  title
+  typeDisplayName
+  totalDuration
+  geoAccessCountries
+  geoAccessMode
+  trailerStream {
+   ...streamFields
+  }
+  publicationLevel
+  takedownDate
+}
+
+fragment BannerFields on Banner {
+  description
+  link
+  pictures {
+    ...PictureFields
+  }
+  title
+}'''
+
+    _TOKEN = None
+
+    def _perform_login(self, username, password):
+        auth = self._download_json('https://audience.api.stageplus.io/oauth/token', None, headers={
+            'Content-Type': 'application/json',
+            'Origin': 'https://www.stage-plus.com',
+        }, data=json.dumps({
+            'grant_type': 'password',
+            'username': username,
+            'password': password,
+            'device_info': 'Chrome (Windows)',
+            'client_device_id': str(uuid.uuid4()),
+        }, separators=(',', ':')).encode(), note='Logging in')
+
+        if auth.get('access_token'):
+            self._TOKEN = auth['access_token']
+
+    def _real_initialize(self):
+        if self._TOKEN:
+            return
+
+        self._TOKEN = try_call(
+            lambda: self._get_cookies('https://www.stage-plus.com/')['dgplus_access_token'].value)
+        if not self._TOKEN:
+            self.raise_login_required()
+
+    def _real_extract(self, url):
+        concert_id = self._match_id(url)
+
+        data = self._download_json('https://audience.api.stageplus.io/graphql', concert_id, headers={
+            'authorization': f'Bearer {self._TOKEN}',
+            'content-type': 'application/json',
+            'Origin': 'https://www.stage-plus.com',
+        }, data=json.dumps({
+            'query': self._GRAPHQL_QUERY,
+            'variables': {'videoId': concert_id},
+            'operationName': 'videoDetailPage'
+        }, separators=(',', ':')).encode())['data']['node']
+
+        metadata = traverse_obj(data, {
+            'title': 'title',
+            'description': ('shortDescription', {str}),
+            'artists': ('artists', 'edges', ..., 'node', 'name'),
+            'timestamp': ('archiveReleaseDate', {unified_timestamp}),
+            'release_timestamp': ('productionDate', {unified_timestamp}),
+        })
+
+        thumbnails = traverse_obj(data, ('pictures', lambda _, v: url_or_none(v['url']), {
+            'id': 'name',
+            'url': 'url',
+        })) or None
+
+        entries = []
+        for idx, video in enumerate(traverse_obj(data, (
+                'performanceWorks', lambda _, v: v['id'] and url_or_none(v['stream']['url']))), 1):
+            formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+                video['stream']['url'], video['id'], 'mp4', m3u8_id='hls', query={'token': self._TOKEN})
+            entries.append({
+                'id': video['id'],
+                'formats': formats,
+                'subtitles': subtitles,
+                'album': metadata.get('title'),
+                'album_artists': metadata.get('artist'),
+                'track_number': idx,
+                **metadata,
+                **traverse_obj(video, {
+                    'title': ('work', 'title'),
+                    'track': ('work', 'title'),
+                    'duration': ('duration', {float_or_none}),
+                    'chapters': (
+                        'cuePoints', lambda _, v: float_or_none(v['mark']) is not None, {
+                            'title': 'title',
+                            'start_time': ('mark', {float_or_none}),
+                        }),
+                    'artists': ('artists', 'edges', ..., 'node', 'name'),
+                    'composers': ('work', 'composers', ..., 'name'),
+                    'genre': ('work', 'genre', 'title'),
+                }),
+            })
+
+        return self.playlist_result(entries, concert_id, thumbnails=thumbnails, **metadata)

package/staging_area/micro projects/SD -Advanced Media Processing Toolkit Automated Downloader, Segmenter & Neural Dubber/.venv/Lib/site-packages/yt_dlp/extractor/stanfordoc.py

@@ -0,0 +1,89 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    orderedSet,
+    unescapeHTML,
+)
+
+
+class StanfordOpenClassroomIE(InfoExtractor):
+    IE_NAME = 'stanfordoc'
+    IE_DESC = 'Stanford Open ClassRoom'
+    _VALID_URL = r'https?://openclassroom\.stanford\.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
+    _TEST = {
+        'url': 'http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100',
+        'md5': '544a9468546059d4e80d76265b0443b8',
+        'info_dict': {
+            'id': 'PracticalUnix_intro-environment',
+            'ext': 'mp4',
+            'title': 'Intro Environment',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = self._match_valid_url(url)
+
+        if mobj.group('course') and mobj.group('video'):  # A specific video
+            course = mobj.group('course')
+            video = mobj.group('video')
+            info = {
+                'id': course + '_' + video,
+                'uploader': None,
+                'upload_date': None,
+            }
+
+            baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/'
+            xmlUrl = baseUrl + video + '.xml'
+            mdoc = self._download_xml(xmlUrl, info['id'])
+            try:
+                info['title'] = mdoc.findall('./title')[0].text
+                info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text
+            except IndexError:
+                raise ExtractorError('Invalid metadata XML file')
+            return info
+        elif mobj.group('course'):  # A course page
+            course = mobj.group('course')
+            info = {
+                'id': course,
+                '_type': 'playlist',
+                'uploader': None,
+                'upload_date': None,
+            }
+
+            coursepage = self._download_webpage(
+                url, info['id'],
+                note='Downloading course info page',
+                errnote='Unable to download course info page')
+
+            info['title'] = self._html_search_regex(
+                r'<h1>([^<]+)</h1>', coursepage, 'title', default=info['id'])
+
+            info['description'] = self._html_search_regex(
+                r'(?s)<description>([^<]+)</description>',
+                coursepage, 'description', fatal=False)
+
+            links = orderedSet(re.findall(r'<a href="(VideoPage\.php\?[^"]+)">', coursepage))
+            info['entries'] = [self.url_result(
+                'http://openclassroom.stanford.edu/MainFolder/%s' % unescapeHTML(l)
+            ) for l in links]
+            return info
+        else:  # Root page
+            info = {
+                'id': 'Stanford OpenClassroom',
+                '_type': 'playlist',
+                'uploader': None,
+                'upload_date': None,
+            }
+            info['title'] = info['id']
+
+            rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php'
+            rootpage = self._download_webpage(rootURL, info['id'],
+                                              errnote='Unable to download course info page')
+
+            links = orderedSet(re.findall(r'<a href="(CoursePage\.php\?[^"]+)">', rootpage))
+            info['entries'] = [self.url_result(
+                'http://openclassroom.stanford.edu/MainFolder/%s' % unescapeHTML(l)
+            ) for l in links]
+            return info

package/staging_area/micro projects/SD -Advanced Media Processing Toolkit Automated Downloader, Segmenter & Neural Dubber/.venv/Lib/site-packages/yt_dlp/extractor/startrek.py

@@ -0,0 +1,76 @@
+from .common import InfoExtractor
+from ..utils import int_or_none, urljoin
+
+
+class StarTrekIE(InfoExtractor):
+    _WORKING = False
+    _VALID_URL = r'(?P<base>https?://(?:intl|www)\.startrek\.com)/videos/(?P<id>[^/]+)'
+    _TESTS = [{
+        'url': 'https://intl.startrek.com/videos/watch-welcoming-jess-bush-to-the-ready-room',
+        'md5': '491df5035c9d4dc7f63c79caaf9c839e',
+        'info_dict': {
+            'id': 'watch-welcoming-jess-bush-to-the-ready-room',
+            'ext': 'mp4',
+            'title': 'WATCH: Welcoming Jess Bush to The Ready Room',
+            'duration': 1888,
+            'timestamp': 1655388000,
+            'upload_date': '20220616',
+            'description': 'md5:1ffee884e3920afbdd6dd04e926a1221',
+            'thumbnail': r're:https://(?:intl|www)\.startrek\.com/sites/default/files/styles/video_1920x1080/public/images/2022-06/pp_14794_rr_thumb_107_yt_16x9\.jpg(?:\?.+)?',
+            'subtitles': {'en-US': [{
+                'url': r're:https://(?:intl|www)\.startrek\.com/sites/default/files/video/captions/2022-06/TRR_SNW_107_v4\.vtt',
+            }, {
+                'url': 'https://media.startrek.com/2022/06/16/2043801155561/1069981_hls/trr_snw_107_v4-c4bfc25d/stream_vtt.m3u8',
+            }]},
+        }
+    }, {
+        'url': 'https://www.startrek.com/videos/watch-ethan-peck-and-gia-sandhu-beam-down-to-the-ready-room',
+        'md5': 'f5ad74fbb86e91e0882fc0a333178d1d',
+        'info_dict': {
+            'id': 'watch-ethan-peck-and-gia-sandhu-beam-down-to-the-ready-room',
+            'ext': 'mp4',
+            'title': 'WATCH: Ethan Peck and Gia Sandhu Beam Down to The Ready Room',
+            'duration': 1986,
+            'timestamp': 1654221600,
+            'upload_date': '20220603',
+            'description': 'md5:b3aa0edacfe119386567362dec8ed51b',
+            'thumbnail': r're:https://www\.startrek\.com/sites/default/files/styles/video_1920x1080/public/images/2022-06/pp_14792_rr_thumb_105_yt_16x9_1.jpg(?:\?.+)?',
+            'subtitles': {'en-US': [{
+                'url': r're:https://(?:intl|www)\.startrek\.com/sites/default/files/video/captions/2022-06/TRR_SNW_105_v5\.vtt',
+            }]},
+        }
+    }]
+
+    def _real_extract(self, url):
+        urlbase, video_id = self._match_valid_url(url).group('base', 'id')
+        webpage = self._download_webpage(url, video_id)
+
+        player = self._search_regex(
+            r'(<\s*div\s+id\s*=\s*"cvp-player-[^<]+<\s*/div\s*>)', webpage, 'player')
+
+        hls = self._html_search_regex(r'\bdata-hls\s*=\s*"([^"]+)"', player, 'HLS URL')
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(hls, video_id, 'mp4')
+
+        captions = self._html_search_regex(
+            r'\bdata-captions-url\s*=\s*"([^"]+)"', player, 'captions URL', fatal=False)
+        if captions:
+            subtitles.setdefault('en-US', [])[:0] = [{'url': urljoin(urlbase, captions)}]
+
+        # NB: Most of the data in the json_ld is undesirable
+        json_ld = self._search_json_ld(webpage, video_id, fatal=False)
+
+        return {
+            'id': video_id,
+            'title': self._html_search_regex(
+                r'\bdata-title\s*=\s*"([^"]+)"', player, 'title', json_ld.get('title')),
+            'description': self._html_search_regex(
+                r'(?s)<\s*div\s+class\s*=\s*"header-body"\s*>(.+?)<\s*/div\s*>',
+                webpage, 'description', fatal=False),
+            'duration': int_or_none(self._html_search_regex(
+                r'\bdata-duration\s*=\s*"(\d+)"', player, 'duration', fatal=False)),
+            'formats': formats,
+            'subtitles': subtitles,
+            'thumbnail': urljoin(urlbase, self._html_search_regex(
+                r'\bdata-poster-url\s*=\s*"([^"]+)"', player, 'thumbnail', fatal=False)),
+            'timestamp': json_ld.get('timestamp'),
+        }