@tushar-br/desktop 1.0.283 → 1.0.284

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

@@ -1,136 +0,0 @@
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    clean_html,
-    format_field,
-    get_element_by_class,
-    parse_duration,
-    parse_qs,
-    traverse_obj,
-    unified_timestamp,
-    update_url_query,
-    url_basename,
-)
-
-
-class TelegramEmbedIE(InfoExtractor):
-    IE_NAME = 'telegram:embed'
-    _VALID_URL = r'https?://t\.me/(?P<channel_id>[^/]+)/(?P<id>\d+)'
-    _TESTS = [{
-        'url': 'https://t.me/europa_press/613',
-        'md5': 'dd707708aea958c11a590e8068825f22',
-        'info_dict': {
-            'id': '613',
-            'ext': 'mp4',
-            'title': 'md5:6ce2d7e8d56eda16d80607b23db7b252',
-            'description': 'md5:6ce2d7e8d56eda16d80607b23db7b252',
-            'channel_id': 'europa_press',
-            'channel': 'Europa Press ✔',
-            'thumbnail': r're:^https?://.+',
-            'timestamp': 1635631203,
-            'upload_date': '20211030',
-            'duration': 61,
-        },
-    }, {
-        # 2-video post
-        'url': 'https://t.me/vorposte/29342',
-        'info_dict': {
-            'id': 'vorposte-29342',
-            'title': 'Форпост 29342',
-            'description': 'md5:9d92e22169a3e136d5d69df25f82c3dc',
-        },
-        'playlist_count': 2,
-        'params': {
-            'skip_download': True,
-        },
-    }, {
-        # 2-video post with --no-playlist
-        'url': 'https://t.me/vorposte/29343',
-        'md5': '1724e96053c18e788c8464038876e245',
-        'info_dict': {
-            'id': '29343',
-            'ext': 'mp4',
-            'title': 'md5:9d92e22169a3e136d5d69df25f82c3dc',
-            'description': 'md5:9d92e22169a3e136d5d69df25f82c3dc',
-            'channel_id': 'vorposte',
-            'channel': 'Форпост',
-            'thumbnail': r're:^https?://.+',
-            'timestamp': 1666384480,
-            'upload_date': '20221021',
-            'duration': 35,
-        },
-        'params': {
-            'noplaylist': True,
-        }
-    }, {
-        # 2-video post with 'single' query param
-        'url': 'https://t.me/vorposte/29342?single',
-        'md5': 'd20b202f1e41400a9f43201428add18f',
-        'info_dict': {
-            'id': '29342',
-            'ext': 'mp4',
-            'title': 'md5:9d92e22169a3e136d5d69df25f82c3dc',
-            'description': 'md5:9d92e22169a3e136d5d69df25f82c3dc',
-            'channel_id': 'vorposte',
-            'channel': 'Форпост',
-            'thumbnail': r're:^https?://.+',
-            'timestamp': 1666384480,
-            'upload_date': '20221021',
-            'duration': 33,
-        },
-    }]
-
-    def _real_extract(self, url):
-        channel_id, msg_id = self._match_valid_url(url).group('channel_id', 'id')
-        embed = self._download_webpage(
-            url, msg_id, query={'embed': '1', 'single': []}, note='Downloading embed frame')
-
-        def clean_text(html_class, html):
-            text = clean_html(get_element_by_class(html_class, html))
-            return text.replace('\n', ' ') if text else None
-
-        description = clean_text('tgme_widget_message_text', embed)
-        message = {
-            'title': description or '',
-            'description': description,
-            'channel': clean_text('tgme_widget_message_author', embed),
-            'channel_id': channel_id,
-            'timestamp': unified_timestamp(self._search_regex(
-                r'<time[^>]*datetime="([^"]*)"', embed, 'timestamp', fatal=False)),
-        }
-
-        videos = []
-        for video in re.findall(r'<a class="tgme_widget_message_video_player(?s:.+?)</time>', embed):
-            video_url = self._search_regex(
-                r'<video[^>]+src="([^"]+)"', video, 'video URL', fatal=False)
-            webpage_url = self._search_regex(
-                r'<a class="tgme_widget_message_video_player[^>]+href="([^"]+)"',
-                video, 'webpage URL', fatal=False)
-            if not video_url or not webpage_url:
-                continue
-            formats = [{
-                'url': video_url,
-                'ext': 'mp4',
-            }]
-            videos.append({
-                'id': url_basename(webpage_url),
-                'webpage_url': update_url_query(webpage_url, {'single': True}),
-                'duration': parse_duration(self._search_regex(
-                    r'<time[^>]+duration[^>]*>([\d:]+)</time>', video, 'duration', fatal=False)),
-                'thumbnail': self._search_regex(
-                    r'tgme_widget_message_video_thumb"[^>]+background-image:url\(\'([^\']+)\'\)',
-                    video, 'thumbnail', fatal=False),
-                'formats': formats,
-                **message,
-            })
-
-        playlist_id = None
-        if len(videos) > 1 and 'single' not in parse_qs(url, keep_blank_values=True):
-            playlist_id = f'{channel_id}-{msg_id}'
-
-        if self._yes_playlist(playlist_id, msg_id):
-            return self.playlist_result(
-                videos, playlist_id, format_field(message, 'channel', f'%s {msg_id}'), description)
-        else:
-            return traverse_obj(videos, lambda _, x: x['id'] == msg_id, get_all=False)

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

@@ -1,75 +0,0 @@
-import re
-
-from .common import InfoExtractor
-from ..utils import remove_start
-
-
-class TeleMBIE(InfoExtractor):
-    _WORKING = False
-    _VALID_URL = r'https?://(?:www\.)?telemb\.be/(?P<display_id>.+?)_d_(?P<id>\d+)\.html'
-    _TESTS = [
-        {
-            'url': 'http://www.telemb.be/mons-cook-with-danielle-des-cours-de-cuisine-en-anglais-_d_13466.html',
-            'md5': 'f45ea69878516ba039835794e0f8f783',
-            'info_dict': {
-                'id': '13466',
-                'display_id': 'mons-cook-with-danielle-des-cours-de-cuisine-en-anglais-',
-                'ext': 'mp4',
-                'title': 'Mons - Cook with Danielle : des cours de cuisine en anglais ! - Les reportages',
-                'description': 'md5:bc5225f47b17c309761c856ad4776265',
-                'thumbnail': r're:^http://.*\.(?:jpg|png)$',
-            }
-        },
-        {
-            # non-ASCII characters in download URL
-            'url': 'http://telemb.be/les-reportages-havre-incendie-mortel_d_13514.html',
-            'md5': '6e9682736e5ccd4eab7f21e855350733',
-            'info_dict': {
-                'id': '13514',
-                'display_id': 'les-reportages-havre-incendie-mortel',
-                'ext': 'mp4',
-                'title': 'Havré - Incendie mortel - Les reportages',
-                'description': 'md5:5e54cb449acb029c2b7734e2d946bd4a',
-                'thumbnail': r're:^http://.*\.(?:jpg|png)$',
-            }
-        },
-    ]
-
-    def _real_extract(self, url):
-        mobj = self._match_valid_url(url)
-        video_id = mobj.group('id')
-        display_id = mobj.group('display_id')
-
-        webpage = self._download_webpage(url, display_id)
-
-        formats = []
-        for video_url in re.findall(r'file\s*:\s*"([^"]+)"', webpage):
-            fmt = {
-                'url': video_url,
-                'format_id': video_url.split(':')[0]
-            }
-            rtmp = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+))/(?P<playpath>mp4:.+)$', video_url)
-            if rtmp:
-                fmt.update({
-                    'play_path': rtmp.group('playpath'),
-                    'app': rtmp.group('app'),
-                    'player_url': 'http://p.jwpcdn.com/6/10/jwplayer.flash.swf',
-                    'page_url': 'http://www.telemb.be',
-                    'preference': -10,
-                })
-            formats.append(fmt)
-
-        title = remove_start(self._og_search_title(webpage), 'TéléMB : ')
-        description = self._html_search_regex(
-            r'<meta property="og:description" content="(.+?)" />',
-            webpage, 'description', fatal=False)
-        thumbnail = self._og_search_thumbnail(webpage)
-
-        return {
-            'id': video_id,
-            'display_id': display_id,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'formats': formats,
-        }

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

@@ -1,50 +0,0 @@
-from .common import InfoExtractor
-from ..networking import HEADRequest
-from ..utils import try_get, unified_timestamp
-
-
-class TelemundoIE(InfoExtractor):
-    _WORKING = False
-    _VALID_URL = r'https?:\/\/(?:www\.)?telemundo\.com\/.+?video\/[^\/]+(?P<id>tmvo\d{7})'
-    _TESTS = [{
-        'url': 'https://www.telemundo.com/noticias/noticias-telemundo-en-la-noche/empleo/video/esta-aplicacion-gratuita-esta-ayudando-los-latinos-encontrar-trabajo-en-estados-unidos-tmvo9829325',
-        'info_dict': {
-            'id': 'tmvo9829325',
-            'timestamp': 1621396800,
-            'title': 'Esta aplicación gratuita está ayudando a los latinos a encontrar trabajo en Estados Unidos',
-            'uploader': 'Telemundo',
-            'uploader_id': 'NBCU_Telemundo',
-            'ext': 'mp4',
-            'upload_date': '20210519',
-        },
-        'params': {
-            'skip_download': True,
-        }
-    }, {
-        'url': 'https://www.telemundo.com/shows/al-rojo-vivo/empleo/video/personajes-de-times-square-piden-que-la-ciudad-de-nueva-york-los-deje-volver-trabajar-tmvo9816272',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-        metadata = self._search_nextjs_data(webpage, video_id)
-        redirect_url = try_get(
-            metadata,
-            lambda x: x['props']['initialState']['video']['associatedPlaylists'][0]['videos'][0]['videoAssets'][0]['publicUrl'])
-
-        m3u8_url = self._request_webpage(HEADRequest(
-            redirect_url + '?format=redirect&manifest=m3u&format=redirect&Tracking=true&Embedded=true&formats=MPEG4'),
-            video_id, 'Processing m3u8').url
-        formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4')
-        date = unified_timestamp(try_get(
-            metadata, lambda x: x['props']['initialState']['video']['associatedPlaylists'][0]['videos'][0]['datePublished'].split(' ', 1)[1]))
-        return {
-            'url': url,
-            'id': video_id,
-            'title': self._search_regex(r'<h1[^>]+>([^<]+)', webpage, 'title', fatal=False),
-            'formats': formats,
-            'timestamp': date,
-            'uploader': 'Telemundo',
-            'uploader_id': self._search_regex(r'https?:\/\/(?:[^/]+\/){3}video\/(?P<id>[^\/]+)', m3u8_url, 'Akamai account', fatal=False)
-        }

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

@@ -1,237 +0,0 @@
-from .common import InfoExtractor
-from ..compat import compat_str
-from ..utils import (
-    int_or_none,
-    smuggle_url,
-    try_get,
-    unified_timestamp,
-)
-
-
-class TeleQuebecBaseIE(InfoExtractor):
-    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s'
-
-    @staticmethod
-    def _brightcove_result(brightcove_id, player_id, account_id='6150020952001'):
-        return {
-            '_type': 'url_transparent',
-            'url': smuggle_url(TeleQuebecBaseIE.BRIGHTCOVE_URL_TEMPLATE % (account_id, player_id, brightcove_id), {'geo_countries': ['CA']}),
-            'ie_key': 'BrightcoveNew',
-        }
-
-
-class TeleQuebecIE(TeleQuebecBaseIE):
-    _VALID_URL = r'''(?x)
-                    https?://
-                        (?:
-                            zonevideo\.telequebec\.tv/media|
-                            coucou\.telequebec\.tv/videos
-                        )/(?P<id>\d+)
-                    '''
-    _TESTS = [{
-        # available till 01.01.2023
-        'url': 'http://zonevideo.telequebec.tv/media/37578/un-petit-choc-et-puis-repart/un-chef-a-la-cabane',
-        'info_dict': {
-            'id': '6155972771001',
-            'ext': 'mp4',
-            'title': 'Un petit choc et puis repart!',
-            'description': 'md5:b04a7e6b3f74e32d7b294cffe8658374',
-            'timestamp': 1589262469,
-            'uploader_id': '6150020952001',
-            'upload_date': '20200512',
-        },
-        'add_ie': ['BrightcoveNew'],
-    }, {
-        'url': 'https://zonevideo.telequebec.tv/media/55267/le-soleil/passe-partout',
-        'info_dict': {
-            'id': '6167180337001',
-            'ext': 'mp4',
-            'title': 'Le soleil',
-            'description': 'md5:64289c922a8de2abbe99c354daffde02',
-            'uploader_id': '6150020952001',
-            'upload_date': '20200625',
-            'timestamp': 1593090307,
-        },
-        'add_ie': ['BrightcoveNew'],
-    }, {
-        # no description
-        'url': 'http://zonevideo.telequebec.tv/media/30261',
-        'only_matching': True,
-    }, {
-        'url': 'https://coucou.telequebec.tv/videos/41788/idee-de-genie/l-heure-du-bain',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        media_id = self._match_id(url)
-        media = self._download_json(
-            'https://mnmedias.api.telequebec.tv/api/v3/media/' + media_id,
-            media_id)['media']
-        source_id = next(source_info['sourceId'] for source_info in media['streamInfos'] if source_info.get('source') == 'Brightcove')
-        info = self._brightcove_result(source_id, '22gPKdt7f')
-        product = media.get('product') or {}
-        season = product.get('season') or {}
-        info.update({
-            'description': try_get(media, lambda x: x['descriptions'][-1]['text'], compat_str),
-            'series': try_get(season, lambda x: x['serie']['titre']),
-            'season': season.get('name'),
-            'season_number': int_or_none(season.get('seasonNo')),
-            'episode': product.get('titre'),
-            'episode_number': int_or_none(product.get('episodeNo')),
-        })
-        return info
-
-
-class TeleQuebecSquatIE(InfoExtractor):
-    _VALID_URL = r'https?://squat\.telequebec\.tv/videos/(?P<id>\d+)'
-    _TESTS = [{
-        'url': 'https://squat.telequebec.tv/videos/9314',
-        'info_dict': {
-            'id': 'd59ae78112d542e793d83cc9d3a5b530',
-            'ext': 'mp4',
-            'title': 'Poupeflekta',
-            'description': 'md5:2f0718f8d2f8fece1646ee25fb7bce75',
-            'duration': 1351,
-            'timestamp': 1569057600,
-            'upload_date': '20190921',
-            'series': 'Miraculous : Les Aventures de Ladybug et Chat Noir',
-            'season': 'Saison 3',
-            'season_number': 3,
-            'episode_number': 57,
-        },
-        'params': {
-            'skip_download': True,
-        },
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        video = self._download_json(
-            'https://squat.api.telequebec.tv/v1/videos/%s' % video_id,
-            video_id)
-
-        media_id = video['sourceId']
-
-        return {
-            '_type': 'url_transparent',
-            'url': 'http://zonevideo.telequebec.tv/media/%s' % media_id,
-            'ie_key': TeleQuebecIE.ie_key(),
-            'id': media_id,
-            'title': video.get('titre'),
-            'description': video.get('description'),
-            'timestamp': unified_timestamp(video.get('datePublication')),
-            'series': video.get('container'),
-            'season': video.get('saison'),
-            'season_number': int_or_none(video.get('noSaison')),
-            'episode_number': int_or_none(video.get('episode')),
-        }
-
-
-class TeleQuebecEmissionIE(InfoExtractor):
-    _VALID_URL = r'''(?x)
-                    https?://
-                        (?:
-                            [^/]+\.telequebec\.tv/emissions/|
-                            (?:www\.)?telequebec\.tv/
-                        )
-                        (?P<id>[^?#&]+)
-                    '''
-    _TESTS = [{
-        'url': 'http://lindicemcsween.telequebec.tv/emissions/100430013/des-soins-esthetiques-a-377-d-interets-annuels-ca-vous-tente',
-        'info_dict': {
-            'id': '6154476028001',
-            'ext': 'mp4',
-            'title': 'Des soins esthétiques à 377 % d’intérêts annuels, ça vous tente?',
-            'description': 'md5:cb4d378e073fae6cce1f87c00f84ae9f',
-            'upload_date': '20200505',
-            'timestamp': 1588713424,
-            'uploader_id': '6150020952001',
-        },
-    }, {
-        'url': 'http://bancpublic.telequebec.tv/emissions/emission-49/31986/jeunes-meres-sous-pression',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.telequebec.tv/masha-et-michka/epi059masha-et-michka-3-053-078',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.telequebec.tv/documentaire/bebes-sur-mesure/',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, display_id)
-
-        media_id = self._search_regex(
-            r'mediaId\s*:\s*(?P<id>\d+)', webpage, 'media id')
-
-        return self.url_result(
-            'http://zonevideo.telequebec.tv/media/' + media_id,
-            TeleQuebecIE.ie_key())
-
-
-class TeleQuebecLiveIE(TeleQuebecBaseIE):
-    _VALID_URL = r'https?://zonevideo\.telequebec\.tv/(?P<id>endirect)'
-    _TEST = {
-        'url': 'http://zonevideo.telequebec.tv/endirect/',
-        'info_dict': {
-            'id': '6159095684001',
-            'ext': 'mp4',
-            'title': 're:^Télé-Québec [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
-            'is_live': True,
-            'description': 'Canal principal de Télé-Québec',
-            'uploader_id': '6150020952001',
-            'timestamp': 1590439901,
-            'upload_date': '20200525',
-        },
-        'params': {
-            'skip_download': True,
-        },
-    }
-
-    def _real_extract(self, url):
-        return self._brightcove_result('6159095684001', 'skCsmi2Uw')
-
-
-class TeleQuebecVideoIE(TeleQuebecBaseIE):
-    _VALID_URL = r'https?://video\.telequebec\.tv/player(?:-live)?/(?P<id>\d+)'
-    _TESTS = [{
-        'url': 'https://video.telequebec.tv/player/31110/stream',
-        'info_dict': {
-            'id': '6202570652001',
-            'ext': 'mp4',
-            'title': 'Le coût du véhicule le plus vendu au Canada / Tous les frais liés à la procréation assistée',
-            'description': 'md5:685a7e4c450ba777c60adb6e71e41526',
-            'upload_date': '20201019',
-            'timestamp': 1603115930,
-            'uploader_id': '6101674910001',
-        },
-    }, {
-        'url': 'https://video.telequebec.tv/player-live/28527',
-        'only_matching': True,
-    }]
-
-    def _call_api(self, path, video_id):
-        return self._download_json(
-            'http://beacon.playback.api.brightcove.com/telequebec/api/assets/' + path,
-            video_id, query={'device_layout': 'web', 'device_type': 'web'})['data']
-
-    def _real_extract(self, url):
-        asset_id = self._match_id(url)
-        asset = self._call_api(asset_id, asset_id)['asset']
-        stream = self._call_api(
-            asset_id + '/streams/' + asset['streams'][0]['id'], asset_id)['stream']
-        stream_url = stream['url']
-        account_id = try_get(
-            stream, lambda x: x['video_provider_details']['account_id']) or '6101674910001'
-        info = self._brightcove_result(stream_url, 'default', account_id)
-        info.update({
-            'description': asset.get('long_description') or asset.get('short_description'),
-            'series': asset.get('series_original_name'),
-            'season_number': int_or_none(asset.get('season_number')),
-            'episode': asset.get('original_name'),
-            'episode_number': int_or_none(asset.get('episode_number')),
-        })
-        return info

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

@@ -1,52 +0,0 @@
-import re
-
-from .common import InfoExtractor
-from ..utils import unified_strdate
-
-
-class TeleTaskIE(InfoExtractor):
-    _WORKING = False
-    _VALID_URL = r'https?://(?:www\.)?tele-task\.de/archive/video/html5/(?P<id>[0-9]+)'
-    _TEST = {
-        'url': 'http://www.tele-task.de/archive/video/html5/26168/',
-        'info_dict': {
-            'id': '26168',
-            'title': 'Duplicate Detection',
-        },
-        'playlist': [{
-            'md5': '290ef69fb2792e481169c3958dbfbd57',
-            'info_dict': {
-                'id': '26168-speaker',
-                'ext': 'mp4',
-                'title': 'Duplicate Detection',
-                'upload_date': '20141218',
-            }
-        }, {
-            'md5': 'e1e7218c5f0e4790015a437fcf6c71b4',
-            'info_dict': {
-                'id': '26168-slides',
-                'ext': 'mp4',
-                'title': 'Duplicate Detection',
-                'upload_date': '20141218',
-            }
-        }]
-    }
-
-    def _real_extract(self, url):
-        lecture_id = self._match_id(url)
-        webpage = self._download_webpage(url, lecture_id)
-
-        title = self._html_search_regex(
-            r'itemprop="name">([^<]+)</a>', webpage, 'title')
-        upload_date = unified_strdate(self._html_search_regex(
-            r'Date:</td><td>([^<]+)</td>', webpage, 'date', fatal=False))
-
-        entries = [{
-            'id': '%s-%s' % (lecture_id, format_id),
-            'url': video_url,
-            'title': title,
-            'upload_date': upload_date,
-        } for format_id, video_url in re.findall(
-            r'<video class="([^"]+)"[^>]*>\s*<source src="([^"]+)"', webpage)]
-
-        return self.playlist_result(entries, lecture_id, title)