@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/swearnet.py

@@ -0,0 +1,79 @@
+from .common import InfoExtractor
+from ..utils import ExtractorError, int_or_none, traverse_obj
+
+
+class SwearnetEpisodeIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.swearnet\.com/shows/(?P<id>[\w-]+)/seasons/(?P<season_num>\d+)/episodes/(?P<episode_num>\d+)'
+    _TESTS = [{
+        'url': 'https://www.swearnet.com/shows/gettin-learnt-with-ricky/seasons/1/episodes/1',
+        'info_dict': {
+            'id': '232819',
+            'ext': 'mp4',
+            'episode_number': 1,
+            'episode': 'Episode 1',
+            'duration': 719,
+            'description': 'md5:c48ef71440ce466284c07085cd7bd761',
+            'season': 'Season 1',
+            'title': 'Episode 1 - Grilled Cheese Sammich',
+            'season_number': 1,
+            'thumbnail': 'https://cdn.vidyard.com/thumbnails/232819/_RX04IKIq60a2V6rIRqq_Q_small.jpg',
+        }
+    }]
+
+    def _get_formats_and_subtitle(self, video_source, video_id):
+        video_source = video_source or {}
+        formats, subtitles = [], {}
+        for key, value in video_source.items():
+            if key == 'hls':
+                for video_hls in value:
+                    fmts, subs = self._extract_m3u8_formats_and_subtitles(video_hls.get('url'), video_id)
+                    formats.extend(fmts)
+                    self._merge_subtitles(subs, target=subtitles)
+            else:
+                formats.extend({
+                    'url': video_mp4.get('url'),
+                    'ext': 'mp4'
+                } for video_mp4 in value)
+
+        return formats, subtitles
+
+    def _get_direct_subtitle(self, caption_json):
+        subs = {}
+        for caption in caption_json:
+            subs.setdefault(caption.get('language') or 'und', []).append({
+                'url': caption.get('vttUrl'),
+                'name': caption.get('name')
+            })
+
+        return subs
+
+    def _real_extract(self, url):
+        display_id, season_number, episode_number = self._match_valid_url(url).group('id', 'season_num', 'episode_num')
+        webpage = self._download_webpage(url, display_id)
+
+        try:
+            external_id = self._search_regex(r'externalid\s*=\s*"([^"]+)', webpage, 'externalid')
+        except ExtractorError:
+            if 'Upgrade Now' in webpage:
+                self.raise_login_required()
+            raise
+
+        json_data = self._download_json(
+            f'https://play.vidyard.com/player/{external_id}.json', display_id)['payload']['chapters'][0]
+
+        formats, subtitles = self._get_formats_and_subtitle(json_data['sources'], display_id)
+        self._merge_subtitles(self._get_direct_subtitle(json_data.get('captions')), target=subtitles)
+
+        return {
+            'id': str(json_data['videoId']),
+            'title': json_data.get('name') or self._html_search_meta(['og:title', 'twitter:title'], webpage),
+            'description': (json_data.get('description')
+                            or self._html_search_meta(['og:description', 'twitter:description'], webpage)),
+            'duration': int_or_none(json_data.get('seconds')),
+            'formats': formats,
+            'subtitles': subtitles,
+            'season_number': int_or_none(season_number),
+            'episode_number': int_or_none(episode_number),
+            'thumbnails': [{'url': thumbnail_url}
+                           for thumbnail_url in traverse_obj(json_data, ('thumbnailUrls', ...))]
+        }

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

@@ -0,0 +1,58 @@
+from .adobepass import AdobePassIE
+from ..utils import (
+    update_url_query,
+    smuggle_url,
+)
+
+
+class SyfyIE(AdobePassIE):
+    _WORKING = False
+    _VALID_URL = r'https?://(?:www\.)?syfy\.com/(?:[^/]+/)?videos/(?P<id>[^/?#]+)'
+    _TESTS = [{
+        'url': 'http://www.syfy.com/theinternetruinedmylife/videos/the-internet-ruined-my-life-season-1-trailer',
+        'info_dict': {
+            'id': '2968097',
+            'ext': 'mp4',
+            'title': 'The Internet Ruined My Life: Season 1 Trailer',
+            'description': 'One tweet, one post, one click, can destroy everything.',
+            'uploader': 'NBCU-MPAT',
+            'upload_date': '20170113',
+            'timestamp': 1484345640,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+        'add_ie': ['ThePlatform'],
+        'skip': 'Redirects to main page',
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        syfy_mpx = list(self._parse_json(self._search_regex(
+            r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);', webpage, 'drupal settings'),
+            display_id)['syfy']['syfy_mpx'].values())[0]
+        video_id = syfy_mpx['mpxGUID']
+        title = syfy_mpx['episodeTitle']
+        query = {
+            'mbr': 'true',
+            'manifest': 'm3u',
+        }
+        if syfy_mpx.get('entitlement') == 'auth':
+            resource = self._get_mvpd_resource(
+                'syfy', title, video_id,
+                syfy_mpx.get('mpxRating', 'TV-14'))
+            query['auth'] = self._extract_mvpd_auth(
+                url, video_id, 'syfy', resource)
+
+        return {
+            '_type': 'url_transparent',
+            'ie_key': 'ThePlatform',
+            'url': smuggle_url(update_url_query(
+                self._proto_relative_url(syfy_mpx['releaseURL']), query),
+                {'force_smil_url': True}),
+            'title': title,
+            'id': video_id,
+            'display_id': display_id,
+        }

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

@@ -0,0 +1,33 @@
+from .common import InfoExtractor
+from ..utils import traverse_obj
+
+
+class SYVDKIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?24syv\.dk/episode/(?P<id>[\w-]+)'
+
+    _TESTS = [{
+        'url': 'https://24syv.dk/episode/isabella-arendt-stiller-op-for-de-konservative-2',
+        'md5': '429ce5a423dd4b1e1d0bf3a569558089',
+        'info_dict': {
+            'id': '12215',
+            'display_id': 'isabella-arendt-stiller-op-for-de-konservative-2',
+            'ext': 'mp3',
+            'title': 'Isabella Arendt stiller op for De Konservative',
+            'description': 'md5:f5fa6a431813bf37284f3412ad7c6c06'
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        info_data = self._search_nextjs_data(webpage, video_id)['props']['pageProps']['episodeDetails'][0]
+
+        return {
+            'id': str(info_data['id']),
+            'vcodec': 'none',
+            'ext': 'mp3',
+            'url': info_data['details']['enclosure'],
+            'display_id': video_id,
+            'title': traverse_obj(info_data, ('title', 'rendered')),
+            'description': traverse_obj(info_data, ('details', 'post_title')),
+        }

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

@@ -0,0 +1,38 @@
+from .common import InfoExtractor
+
+
+class SztvHuIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:(?:www\.)?sztv\.hu|www\.tvszombathely\.hu)/(?:[^/]+)/.+-(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://sztv.hu/hirek/cserkeszek-nepszerusitettek-a-kornyezettudatos-eletmodot-a-savaria-teren-20130909',
+        'md5': 'a6df607b11fb07d0e9f2ad94613375cb',
+        'info_dict': {
+            'id': '20130909',
+            'ext': 'mp4',
+            'title': 'Cserkészek népszerűsítették a környezettudatos életmódot a Savaria téren',
+            'description': 'A zöld nap játékos ismeretterjesztő programjait a Magyar Cserkész Szövetség szervezte, akik az ország nyolc városában adják át tudásukat az érdeklődőknek. A PET...',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        video_file = self._search_regex(
+            r'file: "...:(.*?)",', webpage, 'video file')
+        title = self._html_search_regex(
+            r'<meta name="title" content="([^"]*?) - [^-]*? - [^-]*?"',
+            webpage, 'video title')
+        description = self._html_search_regex(
+            r'<meta name="description" content="([^"]*)"/>',
+            webpage, 'video description', fatal=False)
+        thumbnail = self._og_search_thumbnail(webpage)
+
+        video_url = 'http://media.sztv.hu/vod/' + video_file
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+        }

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

@@ -0,0 +1,164 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    UnsupportedError,
+    extract_attributes,
+    int_or_none,
+    js_to_json,
+    parse_iso8601,
+    try_get,
+)
+
+
+class TagesschauIE(InfoExtractor):
+    _WORKING = False
+    _VALID_URL = r'https?://(?:www\.)?tagesschau\.de/(?P<path>[^/]+/(?:[^/]+/)*?(?P<id>[^/#?]+?(?:-?[0-9]+)?))(?:~_?[^/#?]+?)?\.html'
+
+    _TESTS = [{
+        'url': 'http://www.tagesschau.de/multimedia/video/video-102143.html',
+        'md5': 'ccb9359bf8c4795836e43759f3408a93',
+        'info_dict': {
+            'id': 'video-102143-1',
+            'ext': 'mp4',
+            'title': 'Regierungsumbildung in Athen: Neue Minister in Griechenland vereidigt',
+            'duration': 138,
+        },
+    }, {
+        'url': 'http://www.tagesschau.de/multimedia/sendung/ts-5727.html',
+        'md5': '5c15e8f3da049e48829ec9786d835536',
+        'info_dict': {
+            'id': 'ts-5727-1',
+            'ext': 'mp4',
+            'title': 'Ganze Sendung',
+            'duration': 932,
+        },
+    }, {
+        # exclusive audio
+        'url': 'http://www.tagesschau.de/multimedia/audio/audio-29417.html',
+        'md5': '4bff8f23504df56a0d86ed312d654182',
+        'info_dict': {
+            'id': 'audio-29417-1',
+            'ext': 'mp3',
+            'title': 'EU-Gipfel: Im Verbrennerstreit hat Deutschland maximalen Schaden angerichtet',
+        },
+    }, {
+        'url': 'http://www.tagesschau.de/inland/bnd-303.html',
+        'md5': 'f049fa1698d7564e9ca4c3325108f034',
+        'info_dict': {
+            'id': 'bnd-303-1',
+            'ext': 'mp3',
+            'title': 'Das Siegel des Bundesnachrichtendienstes | dpa',
+        },
+    }, {
+        'url': 'http://www.tagesschau.de/inland/afd-parteitag-135.html',
+        'info_dict': {
+            'id': 'afd-parteitag-135',
+            'title': 'AfD',
+        },
+        'playlist_mincount': 15,
+    }, {
+        'url': 'https://www.tagesschau.de/multimedia/audio/audio-29417~player.html',
+        'info_dict': {
+            'id': 'audio-29417-1',
+            'ext': 'mp3',
+            'title': 'EU-Gipfel: Im Verbrennerstreit hat Deutschland maximalen Schaden angerichtet',
+        },
+    }, {
+        'url': 'https://www.tagesschau.de/multimedia/audio/podcast-11km-327.html',
+        'info_dict': {
+            'id': 'podcast-11km-327',
+            'ext': 'mp3',
+            'title': 'Gewalt in der Kita – Wenn Erzieher:innen schweigen',
+            'upload_date': '20230322',
+            'timestamp': 1679482808,
+            'thumbnail': 'https://www.tagesschau.de/multimedia/audio/podcast-11km-329~_v-original.jpg',
+            'description': 'md5:dad059931fe4b3693e3656e93a249848',
+        },
+    }, {
+        'url': 'http://www.tagesschau.de/multimedia/sendung/tsg-3771.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.tagesschau.de/multimedia/sendung/tt-3827.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.tagesschau.de/multimedia/sendung/nm-3475.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.tagesschau.de/multimedia/sendung/weltspiegel-3167.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.tagesschau.de/multimedia/tsvorzwanzig-959.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.tagesschau.de/multimedia/sendung/bab/bab-3299~_bab-sendung-209.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.tagesschau.de/multimedia/video/video-102303~_bab-sendung-211.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.tagesschau.de/100sekunden/index.html',
+        'only_matching': True,
+    }, {
+        # playlist article with collapsing sections
+        'url': 'http://www.tagesschau.de/wirtschaft/faq-freihandelszone-eu-usa-101.html',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = self._match_valid_url(url)
+        video_id = mobj.group('id') or mobj.group('path')
+        display_id = video_id.lstrip('-')
+
+        webpage = self._download_webpage(url, display_id)
+
+        title = self._html_search_regex(
+            r'<span[^>]*class="headline"[^>]*>(.+?)</span>',
+            webpage, 'title', default=None) or self._og_search_title(webpage, fatal=False)
+
+        entries = []
+        videos = re.findall(r'<div[^>]+>', webpage)
+        num = 0
+        for video in videos:
+            video = extract_attributes(video).get('data-config')
+            if not video:
+                continue
+            video = self._parse_json(video, video_id, transform_source=js_to_json, fatal=False)
+            video_formats = try_get(video, lambda x: x['mc']['_mediaArray'][0]['_mediaStreamArray'])
+            if not video_formats:
+                continue
+            num += 1
+            for video_format in video_formats:
+                media_url = video_format.get('_stream') or ''
+                formats = []
+                if media_url.endswith('master.m3u8'):
+                    formats = self._extract_m3u8_formats(media_url, video_id, 'mp4', m3u8_id='hls')
+                elif media_url.endswith('.mp3'):
+                    formats = [{
+                        'url': media_url,
+                        'vcodec': 'none',
+                    }]
+                if not formats:
+                    continue
+                entries.append({
+                    'id': '%s-%d' % (display_id, num),
+                    'title': try_get(video, lambda x: x['mc']['_title']),
+                    'duration': int_or_none(try_get(video, lambda x: x['mc']['_duration'])),
+                    'formats': formats
+                })
+
+        if not entries:
+            raise UnsupportedError(url)
+
+        if len(entries) > 1:
+            return self.playlist_result(entries, display_id, title)
+
+        return {
+            'id': display_id,
+            'title': title,
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'formats': entries[0]['formats'],
+            'timestamp': parse_iso8601(self._html_search_meta('date', webpage)),
+            'description': self._og_search_description(webpage),
+            'duration': entries[0]['duration'],
+        }

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

@@ -0,0 +1,59 @@
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    js_to_json,
+    qualities,
+)
+
+
+class TassIE(InfoExtractor):
+    _WORKING = False
+    _VALID_URL = r'https?://(?:tass\.ru|itar-tass\.com)/[^/]+/(?P<id>\d+)'
+    _TESTS = [
+        {
+            'url': 'http://tass.ru/obschestvo/1586870',
+            'md5': '3b4cdd011bc59174596b6145cda474a4',
+            'info_dict': {
+                'id': '1586870',
+                'ext': 'mp4',
+                'title': 'Посетителям московского зоопарка показали красную панду',
+                'description': 'Приехавшую из Дублина Зейну можно увидеть в павильоне "Кошки тропиков"',
+                'thumbnail': r're:^https?://.*\.jpg$',
+            },
+        },
+        {
+            'url': 'http://itar-tass.com/obschestvo/1600009',
+            'only_matching': True,
+        },
+    ]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        sources = json.loads(js_to_json(self._search_regex(
+            r'(?s)sources\s*:\s*(\[.+?\])', webpage, 'sources')))
+
+        quality = qualities(['sd', 'hd'])
+
+        formats = []
+        for source in sources:
+            video_url = source.get('file')
+            if not video_url or not video_url.startswith('http') or not video_url.endswith('.mp4'):
+                continue
+            label = source.get('label')
+            formats.append({
+                'url': video_url,
+                'format_id': label,
+                'quality': quality(label),
+            })
+
+        return {
+            'id': video_id,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'formats': formats,
+        }

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

@@ -0,0 +1,89 @@
+import re
+
+from .turner import TurnerBaseIE
+from ..compat import (
+    compat_urllib_parse_urlparse,
+    compat_parse_qs,
+)
+from ..utils import (
+    float_or_none,
+    int_or_none,
+    strip_or_none,
+)
+
+
+class TBSIE(TurnerBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?(?P<site>tbs|tntdrama)\.com(?P<path>/(?:movies|watchtnt|watchtbs|shows/[^/]+/(?:clips|season-\d+/episode-\d+))/(?P<id>[^/?#]+))'
+    _TESTS = [{
+        'url': 'http://www.tntdrama.com/shows/the-alienist/clips/monster',
+        'info_dict': {
+            'id': '8d384cde33b89f3a43ce5329de42903ed5099887',
+            'ext': 'mp4',
+            'title': 'Monster',
+            'description': 'Get a first look at the theatrical trailer for TNT’s highly anticipated new psychological thriller The Alienist, which premieres January 22 on TNT.',
+            'timestamp': 1508175329,
+            'upload_date': '20171016',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
+    }, {
+        'url': 'http://www.tbs.com/shows/search-party/season-1/episode-1/explicit-the-mysterious-disappearance-of-the-girl-no-one-knew',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.tntdrama.com/movies/star-wars-a-new-hope',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        site, path, display_id = self._match_valid_url(url).groups()
+        webpage = self._download_webpage(url, display_id)
+        drupal_settings = self._parse_json(self._search_regex(
+            r'<script[^>]+?data-drupal-selector="drupal-settings-json"[^>]*?>({.+?})</script>',
+            webpage, 'drupal setting'), display_id)
+        isLive = 'watchtnt' in path or 'watchtbs' in path
+        video_data = next(v for v in drupal_settings['turner_playlist'] if isLive or v.get('url') == path)
+
+        media_id = video_data['mediaID']
+        title = video_data['title']
+        tokenizer_query = compat_parse_qs(compat_urllib_parse_urlparse(
+            drupal_settings['ngtv_token_url']).query)
+
+        info = self._extract_ngtv_info(
+            media_id, tokenizer_query, {
+                'url': url,
+                'site_name': site[:3].upper(),
+                'auth_required': video_data.get('authRequired') == '1' or isLive,
+                'is_live': isLive
+            })
+
+        thumbnails = []
+        for image_id, image in video_data.get('images', {}).items():
+            image_url = image.get('url')
+            if not image_url or image.get('type') != 'video':
+                continue
+            i = {
+                'id': image_id,
+                'url': image_url,
+            }
+            mobj = re.search(r'(\d+)x(\d+)', image_url)
+            if mobj:
+                i.update({
+                    'width': int(mobj.group(1)),
+                    'height': int(mobj.group(2)),
+                })
+            thumbnails.append(i)
+
+        info.update({
+            'id': media_id,
+            'title': title,
+            'description': strip_or_none(video_data.get('descriptionNoTags') or video_data.get('shortDescriptionNoTags')),
+            'duration': float_or_none(video_data.get('duration')) or info.get('duration'),
+            'timestamp': int_or_none(video_data.get('created')),
+            'season_number': int_or_none(video_data.get('season')),
+            'episode_number': int_or_none(video_data.get('episode')),
+            'thumbnails': thumbnails,
+            'is_live': isLive
+        })
+        return info