@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/atvat.py

@@ -0,0 +1,108 @@
+import datetime
+
+from .common import InfoExtractor
+from ..utils import (
+    float_or_none,
+    jwt_encode_hs256,
+    try_get,
+    ExtractorError,
+)
+
+
+class ATVAtIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?atv\.at/tv/(?:[^/]+/){2,3}(?P<id>.*)'
+
+    _TESTS = [{
+        'url': 'https://www.atv.at/tv/bauer-sucht-frau/staffel-18/bauer-sucht-frau/bauer-sucht-frau-staffel-18-folge-3-die-hofwochen',
+        'md5': '3c3b4aaca9f63e32b35e04a9c2515903',
+        'info_dict': {
+            'id': 'v-ce9cgn1e70n5-1',
+            'ext': 'mp4',
+            'title': 'Bauer sucht Frau - Staffel 18 Folge 3 - Die Hofwochen',
+        }
+    }, {
+        'url': 'https://www.atv.at/tv/bauer-sucht-frau/staffel-18/episode-01/bauer-sucht-frau-staffel-18-vorstellungsfolge-1',
+        'only_matching': True,
+    }]
+
+    # extracted from bootstrap.js function (search for e.encryption_key and use your browser's debugger)
+    _ACCESS_ID = 'x_atv'
+    _ENCRYPTION_KEY = 'Hohnaekeishoogh2omaeghooquooshia'
+
+    def _extract_video_info(self, url, content, video):
+        clip_id = content.get('splitId', content['id'])
+        formats = []
+        clip_urls = video['urls']
+        for protocol, variant in clip_urls.items():
+            source_url = try_get(variant, lambda x: x['clear']['url'])
+            if not source_url:
+                continue
+            if protocol == 'dash':
+                formats.extend(self._extract_mpd_formats(
+                    source_url, clip_id, mpd_id=protocol, fatal=False))
+            elif protocol == 'hls':
+                formats.extend(self._extract_m3u8_formats(
+                    source_url, clip_id, 'mp4', 'm3u8_native',
+                    m3u8_id=protocol, fatal=False))
+            else:
+                formats.append({
+                    'url': source_url,
+                    'format_id': protocol,
+                })
+
+        return {
+            'id': clip_id,
+            'title': content.get('title'),
+            'duration': float_or_none(content.get('duration')),
+            'series': content.get('tvShowTitle'),
+            'formats': formats,
+        }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        json_data = self._parse_json(
+            self._search_regex(r'<script id="state" type="text/plain">(.*)</script>', webpage, 'json_data'),
+            video_id=video_id)
+
+        video_title = json_data['views']['default']['page']['title']
+        contentResource = json_data['views']['default']['page']['contentResource']
+        content_id = contentResource[0]['id']
+        content_ids = [{'id': id, 'subclip_start': content['start'], 'subclip_end': content['end']}
+                       for id, content in enumerate(contentResource)]
+
+        time_of_request = datetime.datetime.now()
+        not_before = time_of_request - datetime.timedelta(minutes=5)
+        expire = time_of_request + datetime.timedelta(minutes=5)
+        payload = {
+            'content_ids': {
+                content_id: content_ids,
+            },
+            'secure_delivery': True,
+            'iat': int(time_of_request.timestamp()),
+            'nbf': int(not_before.timestamp()),
+            'exp': int(expire.timestamp()),
+        }
+        jwt_token = jwt_encode_hs256(payload, self._ENCRYPTION_KEY, headers={'kid': self._ACCESS_ID})
+        videos = self._download_json(
+            'https://vas-v4.p7s1video.net/4.0/getsources',
+            content_id, 'Downloading videos JSON', query={
+                'token': jwt_token.decode('utf-8')
+            })
+
+        video_id, videos_data = list(videos['data'].items())[0]
+        error_msg = try_get(videos_data, lambda x: x['error']['title'])
+        if error_msg == 'Geo check failed':
+            self.raise_geo_restricted(error_msg)
+        elif error_msg:
+            raise ExtractorError(error_msg)
+        entries = [
+            self._extract_video_info(url, contentResource[video['id']], video)
+            for video in videos_data]
+
+        return {
+            '_type': 'multi_video',
+            'id': video_id,
+            'title': video_title,
+            'entries': entries,
+        }

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

@@ -0,0 +1,89 @@
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+)
+
+
+class AudiMediaIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?audi-mediacenter\.com/(?:en|de)/audimediatv/(?:video/)?(?P<id>[^/?#]+)'
+    _TESTS = [{
+        'url': 'https://www.audi-mediacenter.com/en/audimediatv/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test-1467',
+        'md5': '79a8b71c46d49042609795ab59779b66',
+        'info_dict': {
+            'id': '1565',
+            'ext': 'mp4',
+            'title': '60 Seconds of Audi Sport 104/2015 - WEC Bahrain, Rookie Test',
+            'description': 'md5:60e5d30a78ced725f7b8d34370762941',
+            'upload_date': '20151124',
+            'timestamp': 1448354940,
+            'duration': 74022,
+            'view_count': int,
+        }
+    }, {
+        'url': 'https://www.audi-mediacenter.com/en/audimediatv/video/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test-2991',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        raw_payload = self._search_regex([
+            r'class="amtv-embed"[^>]+id="([0-9a-z-]+)"',
+            r'id="([0-9a-z-]+)"[^>]+class="amtv-embed"',
+            r'class=\\"amtv-embed\\"[^>]+id=\\"([0-9a-z-]+)\\"',
+            r'id=\\"([0-9a-z-]+)\\"[^>]+class=\\"amtv-embed\\"',
+            r'id=(?:\\)?"(amtve-[a-z]-\d+-[a-z]{2})',
+        ], webpage, 'raw payload')
+        _, stage_mode, video_id, _ = raw_payload.split('-')
+
+        # TODO: handle s and e stage_mode (live streams and ended live streams)
+        if stage_mode not in ('s', 'e'):
+            video_data = self._download_json(
+                'https://www.audimedia.tv/api/video/v1/videos/' + video_id,
+                video_id, query={
+                    'embed[]': ['video_versions', 'thumbnail_image'],
+                })['results']
+            formats = []
+
+            stream_url_hls = video_data.get('stream_url_hls')
+            if stream_url_hls:
+                formats.extend(self._extract_m3u8_formats(
+                    stream_url_hls, video_id, 'mp4',
+                    entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
+
+            stream_url_hds = video_data.get('stream_url_hds')
+            if stream_url_hds:
+                formats.extend(self._extract_f4m_formats(
+                    stream_url_hds + '?hdcore=3.4.0',
+                    video_id, f4m_id='hds', fatal=False))
+
+            for video_version in video_data.get('video_versions', []):
+                video_version_url = video_version.get('download_url') or video_version.get('stream_url')
+                if not video_version_url:
+                    continue
+                f = {
+                    'url': video_version_url,
+                    'width': int_or_none(video_version.get('width')),
+                    'height': int_or_none(video_version.get('height')),
+                    'abr': int_or_none(video_version.get('audio_bitrate')),
+                    'vbr': int_or_none(video_version.get('video_bitrate')),
+                }
+                bitrate = self._search_regex(r'(\d+)k', video_version_url, 'bitrate', default=None)
+                if bitrate:
+                    f.update({
+                        'format_id': 'http-%s' % bitrate,
+                    })
+                formats.append(f)
+
+            return {
+                'id': video_id,
+                'title': video_data['title'],
+                'description': video_data.get('subtitle'),
+                'thumbnail': video_data.get('thumbnail_image', {}).get('file'),
+                'timestamp': parse_iso8601(video_data.get('publication_date')),
+                'duration': int_or_none(video_data.get('duration')),
+                'view_count': int_or_none(video_data.get('view_count')),
+                'formats': formats,
+            }

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

@@ -0,0 +1,57 @@
+from .common import InfoExtractor
+from ..utils import clean_html, float_or_none, traverse_obj, unescapeHTML
+
+
+class AudioBoomIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?audioboom\.com/(?:boos|posts)/(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'https://audioboom.com/posts/7398103-asim-chaudhry',
+        'md5': '4d68be11c9f9daf3dab0778ad1e010c3',
+        'info_dict': {
+            'id': '7398103',
+            'ext': 'mp3',
+            'title': 'Asim Chaudhry',
+            'description': 'md5:0ed714ae0e81e5d9119cac2f618ad679',
+            'duration': 4000.99,
+            'uploader': 'Sue Perkins: An hour or so with...',
+            'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channel/perkins',
+        }
+    }, {  # Direct mp3-file link
+        'url': 'https://audioboom.com/posts/8128496.mp3',
+        'md5': 'e329edf304d450def95c7f86a9165ee1',
+        'info_dict': {
+            'id': '8128496',
+            'ext': 'mp3',
+            'title': 'TCRNo8 / DAILY 03 - In Control',
+            'description': 'md5:44665f142db74858dfa21c5b34787948',
+            'duration': 1689.7,
+            'uploader': 'Lost Dot Podcast: The Trans Pyrenees and Transcontinental Race',
+            'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channels/5003904',
+        }
+    }, {
+        'url': 'https://audioboom.com/posts/4279833-3-09-2016-czaban-hour-3?t=0',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(f'https://audioboom.com/posts/{video_id}', video_id)
+
+        clip_store = self._search_json(
+            r'data-react-class="V5DetailPagePlayer"\s*data-react-props=["\']',
+            webpage, 'clip store', video_id, fatal=False, transform_source=unescapeHTML)
+        clip = traverse_obj(clip_store, ('clips', 0), expected_type=dict) or {}
+
+        return {
+            'id': video_id,
+            'url': clip.get('clipURLPriorToLoading') or self._og_search_property('audio', webpage, 'audio url'),
+            'title': clip.get('title') or self._html_search_meta(['og:title', 'og:audio:title', 'audio_title'], webpage),
+            'description': (clip.get('description') or clean_html(clip.get('formattedDescription'))
+                            or self._og_search_description(webpage)),
+            'duration': float_or_none(clip.get('duration') or self._html_search_meta('weibo:audio:duration', webpage)),
+            'uploader': clip.get('author') or self._html_search_meta(
+                ['og:audio:artist', 'twitter:audio:artist_name', 'audio_artist'], webpage, 'uploader'),
+            'uploader_url': clip.get('author_url') or self._html_search_regex(
+                r'<div class="avatar flex-shrink-0">\s*<a href="(?P<uploader_url>http[^"]+)"',
+                webpage, 'uploader url', fatal=False),
+        }

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

@@ -0,0 +1,93 @@
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class AudiodraftBaseIE(InfoExtractor):
+    def _audiodraft_extract_from_id(self, player_entry_id):
+        data_json = self._download_json(
+            'https://www.audiodraft.com/scripts/general/player/getPlayerInfoNew.php', player_entry_id,
+            headers={
+                'Content-type': 'application/x-www-form-urlencoded; charset=UTF-8',
+                'X-Requested-With': 'XMLHttpRequest',
+            }, data=f'id={player_entry_id}'.encode('utf-8'))
+
+        return {
+            'id': str(data_json['entry_id']),
+            'title': data_json.get('entry_title'),
+            'url': data_json['path'],
+            'vcodec': 'none',
+            'ext': 'mp3',
+            'uploader': data_json.get('designer_name'),
+            'uploader_id': data_json.get('designer_id'),
+            'webpage_url': data_json.get('entry_url'),
+            'like_count': int_or_none(data_json.get('entry_likes')),
+            'average_rating': int_or_none(data_json.get('entry_rating')),
+        }
+
+
+class AudiodraftCustomIE(AudiodraftBaseIE):
+    IE_NAME = 'Audiodraft:custom'
+    _VALID_URL = r'https?://(?:[-\w]+)\.audiodraft\.com/entry/(?P<id>\d+)'
+
+    _TESTS = [{
+        'url': 'http://nokiatune.audiodraft.com/entry/5874',
+        'info_dict': {
+            'id': '9485',
+            'ext': 'mp3',
+            'title': 'Hula Hula Calls',
+            'uploader': 'unclemaki',
+            'uploader_id': '13512',
+            'average_rating': 5,
+            'like_count': int,
+        },
+    }, {
+        'url': 'http://vikinggrace.audiodraft.com/entry/501',
+        'info_dict': {
+            'id': '22241',
+            'ext': 'mp3',
+            'title': 'MVG Happy',
+            'uploader': 'frog',
+            'uploader_id': '19142',
+            'average_rating': 5,
+            'like_count': int,
+        },
+    }, {
+        'url': 'http://timferriss.audiodraft.com/entry/765',
+        'info_dict': {
+            'id': '19710',
+            'ext': 'mp3',
+            'title': 'ferris03',
+            'uploader': 'malex',
+            'uploader_id': '17335',
+            'average_rating': 5,
+            'like_count': int,
+        },
+    }]
+
+    def _real_extract(self, url):
+        id = self._match_id(url)
+        webpage = self._download_webpage(url, id)
+        player_entry_id = self._search_regex(r'playAudio\(\'(player_entry_\d+)\'\);', webpage, id, 'play entry id')
+        return self._audiodraft_extract_from_id(player_entry_id)
+
+
+class AudiodraftGenericIE(AudiodraftBaseIE):
+    IE_NAME = 'Audiodraft:generic'
+    _VALID_URL = r'https?://www\.audiodraft\.com/contests/[^/#]+#entries&eid=(?P<id>\d+)'
+
+    _TESTS = [{
+        'url': 'https://www.audiodraft.com/contests/570-Score-A-Video-Surprise-Us#entries&eid=30138',
+        'info_dict': {
+            'id': '30138',
+            'ext': 'mp3',
+            'title': 'DROP in sound_V2',
+            'uploader': 'TiagoSilva',
+            'uploader_id': '19452',
+            'average_rating': 4,
+            'like_count': int,
+        },
+    }]
+
+    def _real_extract(self, url):
+        id = self._match_id(url)
+        return self._audiodraft_extract_from_id(f'player_entry_{id}')

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

@@ -0,0 +1,147 @@
+import itertools
+import time
+
+from .common import InfoExtractor
+from .soundcloud import SoundcloudIE
+from ..compat import compat_str
+from ..utils import (
+    ExtractorError,
+    url_basename,
+)
+
+
+class AudiomackIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?audiomack\.com/(?:song/|(?=.+/song/))(?P<id>[\w/-]+)'
+    IE_NAME = 'audiomack'
+    _TESTS = [
+        # hosted on audiomack
+        {
+            'url': 'http://www.audiomack.com/song/roosh-williams/extraordinary',
+            'info_dict':
+            {
+                'id': '310086',
+                'ext': 'mp3',
+                'uploader': 'Roosh Williams',
+                'title': 'Extraordinary'
+            }
+        },
+        # audiomack wrapper around soundcloud song
+        # Needs new test URL.
+        {
+            'add_ie': ['Soundcloud'],
+            'url': 'http://www.audiomack.com/song/hip-hop-daily/black-mamba-freestyle',
+            'info_dict': {
+                'id': '258901379',
+                'ext': 'mp3',
+                'description': 'mamba day freestyle for the legend Kobe Bryant ',
+                'title': 'Black Mamba Freestyle [Prod. By Danny Wolf]',
+                'uploader': 'ILOVEMAKONNEN',
+                'upload_date': '20160414',
+            },
+            'skip': 'Song has been removed from the site',
+        },
+    ]
+
+    def _real_extract(self, url):
+        # URLs end with [uploader name]/song/[uploader title]
+        # this title is whatever the user types in, and is rarely
+        # the proper song title.  Real metadata is in the api response
+        album_url_tag = self._match_id(url).replace('/song/', '/')
+
+        # Request the extended version of the api for extra fields like artist and title
+        api_response = self._download_json(
+            'http://www.audiomack.com/api/music/url/song/%s?extended=1&_=%d' % (
+                album_url_tag, time.time()),
+            album_url_tag)
+
+        # API is inconsistent with errors
+        if 'url' not in api_response or not api_response['url'] or 'error' in api_response:
+            raise ExtractorError('Invalid url %s' % url)
+
+        # Audiomack wraps a lot of soundcloud tracks in their branded wrapper
+        # if so, pass the work off to the soundcloud extractor
+        if SoundcloudIE.suitable(api_response['url']):
+            return self.url_result(api_response['url'], SoundcloudIE.ie_key())
+
+        return {
+            'id': compat_str(api_response.get('id', album_url_tag)),
+            'uploader': api_response.get('artist'),
+            'title': api_response.get('title'),
+            'url': api_response['url'],
+        }
+
+
+class AudiomackAlbumIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?audiomack\.com/(?:album/|(?=.+/album/))(?P<id>[\w/-]+)'
+    IE_NAME = 'audiomack:album'
+    _TESTS = [
+        # Standard album playlist
+        {
+            'url': 'http://www.audiomack.com/album/flytunezcom/tha-tour-part-2-mixtape',
+            'playlist_count': 11,
+            'info_dict':
+            {
+                'id': '812251',
+                'title': 'Tha Tour: Part 2 (Official Mixtape)'
+            }
+        },
+        # Album playlist ripped from fakeshoredrive with no metadata
+        {
+            'url': 'http://www.audiomack.com/album/fakeshoredrive/ppp-pistol-p-project',
+            'info_dict': {
+                'title': 'PPP (Pistol P Project)',
+                'id': '837572',
+            },
+            'playlist': [{
+                'info_dict': {
+                    'title': 'PPP (Pistol P Project) - 8. Real (prod by SYK SENSE  )',
+                    'id': '837576',
+                    'ext': 'mp3',
+                    'uploader': 'Lil Herb a.k.a. G Herbo',
+                }
+            }, {
+                'info_dict': {
+                    'title': 'PPP (Pistol P Project) - 10. 4 Minutes Of Hell Part 4 (prod by DY OF 808 MAFIA)',
+                    'id': '837580',
+                    'ext': 'mp3',
+                    'uploader': 'Lil Herb a.k.a. G Herbo',
+                }
+            }],
+        }
+    ]
+
+    def _real_extract(self, url):
+        # URLs end with [uploader name]/album/[uploader title]
+        # this title is whatever the user types in, and is rarely
+        # the proper song title.  Real metadata is in the api response
+        album_url_tag = self._match_id(url).replace('/album/', '/')
+        result = {'_type': 'playlist', 'entries': []}
+        # There is no one endpoint for album metadata - instead it is included/repeated in each song's metadata
+        # Therefore we don't know how many songs the album has and must infi-loop until failure
+        for track_no in itertools.count():
+            # Get song's metadata
+            api_response = self._download_json(
+                'http://www.audiomack.com/api/music/url/album/%s/%d?extended=1&_=%d'
+                % (album_url_tag, track_no, time.time()), album_url_tag,
+                note='Querying song information (%d)' % (track_no + 1))
+
+            # Total failure, only occurs when url is totally wrong
+            # Won't happen in middle of valid playlist (next case)
+            if 'url' not in api_response or 'error' in api_response:
+                raise ExtractorError('Invalid url for track %d of album url %s' % (track_no, url))
+            # URL is good but song id doesn't exist - usually means end of playlist
+            elif not api_response['url']:
+                break
+            else:
+                # Pull out the album metadata and add to result (if it exists)
+                for resultkey, apikey in [('id', 'album_id'), ('title', 'album_title')]:
+                    if apikey in api_response and resultkey not in result:
+                        result[resultkey] = compat_str(api_response[apikey])
+                song_id = url_basename(api_response['url']).rpartition('.')[0]
+                result['entries'].append({
+                    'id': compat_str(api_response.get('id', song_id)),
+                    'uploader': api_response.get('artist'),
+                    'title': api_response.get('title', song_id),
+                    'url': api_response['url'],
+                })
+        return result