@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/tele13.py

@@ -0,0 +1,84 @@
+from .common import InfoExtractor
+from .youtube import YoutubeIE
+from ..utils import (
+    js_to_json,
+    qualities,
+    determine_ext,
+)
+
+
+class Tele13IE(InfoExtractor):
+    _VALID_URL = r'^https?://(?:www\.)?t13\.cl/videos(?:/[^/]+)+/(?P<id>[\w-]+)'
+    _TESTS = [
+        {
+            'url': 'http://www.t13.cl/videos/actualidad/el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda',
+            'md5': '4cb1fa38adcad8fea88487a078831755',
+            'info_dict': {
+                'id': 'el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda',
+                'ext': 'mp4',
+                'title': 'El círculo de hierro de Michelle Bachelet en su regreso a La Moneda',
+            },
+            'params': {
+                # HTTP Error 404: Not Found
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://www.t13.cl/videos/mundo/tendencias/video-captan-misteriosa-bola-fuego-cielos-bangkok',
+            'md5': '867adf6a3b3fef932c68a71d70b70946',
+            'info_dict': {
+                'id': 'rOoKv2OMpOw',
+                'ext': 'mp4',
+                'title': 'Shooting star seen on 7-Sep-2015',
+                'description': 'md5:7292ff2a34b2f673da77da222ae77e1e',
+                'uploader': 'Porjai Jaturongkhakun',
+                'upload_date': '20150906',
+                'uploader_id': 'UCnLY_3ezwNcDSC_Wc6suZxw',
+            },
+            'add_ie': ['Youtube'],
+        }
+    ]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        setup_js = self._search_regex(
+            r"(?s)jwplayer\('player-vivo'\).setup\((\{.*?\})\)",
+            webpage, 'setup code')
+        sources = self._parse_json(self._search_regex(
+            r'sources\s*:\s*(\[[^\]]+\])', setup_js, 'sources'),
+            display_id, js_to_json)
+
+        preference = qualities(['Móvil', 'SD', 'HD'])
+        formats = []
+        urls = []
+        for f in sources:
+            format_url = f['file']
+            if format_url and format_url not in urls:
+                ext = determine_ext(format_url)
+                if ext == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        format_url, display_id, 'mp4', 'm3u8_native',
+                        m3u8_id='hls', fatal=False))
+                elif YoutubeIE.suitable(format_url):
+                    return self.url_result(format_url, 'Youtube')
+                else:
+                    formats.append({
+                        'url': format_url,
+                        'format_id': f.get('label'),
+                        'quality': preference(f.get('label')),
+                        'ext': ext,
+                    })
+                urls.append(format_url)
+
+        return {
+            'id': display_id,
+            'title': self._search_regex(
+                r'title\s*:\s*"([^"]+)"', setup_js, 'title'),
+            'description': self._html_search_meta(
+                'description', webpage, 'description'),
+            'thumbnail': self._search_regex(
+                r'image\s*:\s*"([^"]+)"', setup_js, 'thumbnail', default=None),
+            'formats': formats,
+        }

package/staging_area/micro projects/SD -Advanced Media Processing Toolkit Automated Downloader, Segmenter & Neural Dubber/.venv/Lib/site-packages/yt_dlp/extractor/tele5.py

@@ -0,0 +1,89 @@
+from .dplay import DPlayIE
+from ..compat import compat_urlparse
+from ..utils import (
+    ExtractorError,
+    extract_attributes,
+)
+
+
+class Tele5IE(DPlayIE):  # XXX: Do not subclass from concrete IE
+    _WORKING = False
+    _VALID_URL = r'https?://(?:www\.)?tele5\.de/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _GEO_COUNTRIES = ['DE']
+    _TESTS = [{
+        'url': 'https://www.tele5.de/mediathek/filme-online/videos?vid=1549416',
+        'info_dict': {
+            'id': '1549416',
+            'ext': 'mp4',
+            'upload_date': '20180814',
+            'timestamp': 1534290623,
+            'title': 'Pandorum',
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'skip': 'No longer available: "404 Seite nicht gefunden"',
+    }, {
+        # jwplatform, nexx unavailable
+        'url': 'https://www.tele5.de/filme/ghoul-das-geheimnis-des-friedhofmonsters/',
+        'info_dict': {
+            'id': 'WJuiOlUp',
+            'ext': 'mp4',
+            'upload_date': '20200603',
+            'timestamp': 1591214400,
+            'title': 'Ghoul - Das Geheimnis des Friedhofmonsters',
+            'description': 'md5:42002af1d887ff3d5b2b3ca1f8137d97',
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'skip': 'No longer available, redirects to Filme page',
+    }, {
+        'url': 'https://tele5.de/mediathek/angel-of-mine/',
+        'info_dict': {
+            'id': '1252360',
+            'ext': 'mp4',
+            'upload_date': '20220109',
+            'timestamp': 1641762000,
+            'title': 'Angel of Mine',
+            'description': 'md5:a72546a175e1286eb3251843a52d1ad7',
+        },
+        'params': {
+            'format': 'bestvideo',
+        },
+    }, {
+        'url': 'https://www.tele5.de/kalkofes-mattscheibe/video-clips/politik-und-gesellschaft?ve_id=1551191',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.tele5.de/video-clip/?ve_id=1609440',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.tele5.de/filme/schlefaz-dragon-crusaders/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.tele5.de/filme/making-of/avengers-endgame/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.tele5.de/star-trek/raumschiff-voyager/ganze-folge/das-vinculum/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.tele5.de/anders-ist-sevda/',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        player_element = self._search_regex(r'(<hyoga-player\b[^>]+?>)', webpage, 'video player')
+        player_info = extract_attributes(player_element)
+        asset_id, country, realm = (player_info[x] for x in ('assetid', 'locale', 'realm', ))
+        endpoint = compat_urlparse.urlparse(player_info['endpoint']).hostname
+        source_type = player_info.get('sourcetype')
+        if source_type:
+            endpoint = '%s-%s' % (source_type, endpoint)
+        try:
+            return self._get_disco_api_info(url, asset_id, endpoint, realm, country)
+        except ExtractorError as e:
+            if getattr(e, 'message', '') == 'Missing deviceId in context':
+                self.report_drm(video_id)
+            raise

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

@@ -0,0 +1,72 @@
+import re
+
+from .common import InfoExtractor
+
+
+class TeleBruxellesIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?(?:telebruxelles|bx1)\.be/(?:[^/]+/)*(?P<id>[^/#?]+)'
+    _TESTS = [{
+        'url': 'http://bx1.be/news/que-risque-lauteur-dune-fausse-alerte-a-la-bombe/',
+        'md5': 'a2a67a5b1c3e8c9d33109b902f474fd9',
+        'info_dict': {
+            'id': '158856',
+            'display_id': 'que-risque-lauteur-dune-fausse-alerte-a-la-bombe',
+            'ext': 'mp4',
+            'title': 'Que risque l’auteur d’une fausse alerte à la bombe ?',
+            'description': 'md5:3cf8df235d44ebc5426373050840e466',
+        },
+    }, {
+        'url': 'http://bx1.be/sport/futsal-schaerbeek-sincline-5-3-a-thulin/',
+        'md5': 'dfe07ecc9c153ceba8582ac912687675',
+        'info_dict': {
+            'id': '158433',
+            'display_id': 'futsal-schaerbeek-sincline-5-3-a-thulin',
+            'ext': 'mp4',
+            'title': 'Futsal : Schaerbeek s’incline 5-3 à Thulin',
+            'description': 'md5:fd013f1488d5e2dceb9cebe39e2d569b',
+        },
+    }, {
+        'url': 'http://bx1.be/emission/bxenf1-gastronomie/',
+        'only_matching': True,
+    }, {
+        'url': 'https://bx1.be/berchem-sainte-agathe/personnel-carrefour-de-berchem-sainte-agathe-inquiet/',
+        'only_matching': True,
+    }, {
+        'url': 'https://bx1.be/dernier-jt/',
+        'only_matching': True,
+    }, {
+        # live stream
+        'url': 'https://bx1.be/lives/direct-tv/',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        article_id = self._html_search_regex(
+            r'<article[^>]+\bid=["\']post-(\d+)', webpage, 'article ID', default=None)
+        title = self._html_search_regex(
+            r'<h1[^>]*>(.+?)</h1>', webpage, 'title',
+            default=None) or self._og_search_title(webpage)
+        description = self._og_search_description(webpage, default=None)
+
+        rtmp_url = self._html_search_regex(
+            r'file["\']?\s*:\s*"(r(?:tm|mt)ps?://[^/]+/(?:vod/mp4:"\s*\+\s*"[^"]+"\s*\+\s*"\.mp4|stream/live))"',
+            webpage, 'RTMP url')
+        # Yes, they have a typo in scheme name for live stream URLs (e.g.
+        # https://bx1.be/lives/direct-tv/)
+        rtmp_url = re.sub(r'^rmtp', 'rtmp', rtmp_url)
+        rtmp_url = re.sub(r'"\s*\+\s*"', '', rtmp_url)
+        formats = self._extract_wowza_formats(rtmp_url, article_id or display_id)
+
+        is_live = 'stream/live' in rtmp_url
+
+        return {
+            'id': article_id or display_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'formats': formats,
+            'is_live': is_live,
+        }

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

@@ -0,0 +1,91 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import traverse_obj
+
+
+class TelecaribePlayIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?play\.telecaribe\.co/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://www.play.telecaribe.co/breicok',
+        'info_dict': {
+            'id': 'breicok',
+            'title': 'Breicok',
+        },
+        'playlist_count': 7,
+    }, {
+        'url': 'https://www.play.telecaribe.co/si-fue-gol-de-yepes',
+        'info_dict': {
+            'id': 'si-fue-gol-de-yepes',
+            'title': 'Sí Fue Gol de Yepes',
+        },
+        'playlist_count': 6,
+    }, {
+        'url': 'https://www.play.telecaribe.co/ciudad-futura',
+        'info_dict': {
+            'id': 'ciudad-futura',
+            'title': 'Ciudad Futura',
+        },
+        'playlist_count': 10,
+    }, {
+        'url': 'https://www.play.telecaribe.co/live',
+        'info_dict': {
+            'id': 'live',
+            'title': r're:^Señal en vivo',
+            'live_status': 'is_live',
+            'ext': 'mp4',
+        },
+        'params': {
+            'skip_download': 'Livestream',
+        }
+    }, {
+        'url': 'https://www.play.telecaribe.co/liveplus',
+        'info_dict': {
+            'id': 'liveplus',
+            'title': r're:^Señal en vivo Plus',
+            'live_status': 'is_live',
+            'ext': 'mp4',
+        },
+        'params': {
+            'skip_download': 'Livestream',
+        },
+        'skip': 'Geo-restricted to Colombia',
+    }]
+
+    def _download_player_webpage(self, webpage, display_id):
+        page_id = self._search_regex(
+            (r'window\.firstPageId\s*=\s*["\']([^"\']+)', r'<div[^>]+id\s*=\s*"pageBackground_([^"]+)'),
+            webpage, 'page_id')
+
+        props = self._download_json(self._search_regex(
+            rf'<link[^>]+href\s*=\s*"([^"]+)"[^>]+id\s*=\s*"features_{page_id}"',
+            webpage, 'json_props_url'), display_id)['props']['render']['compProps']
+
+        return self._download_webpage(traverse_obj(props, (..., 'url'))[-1], display_id)
+
+    def _get_clean_title(self, title):
+        return re.sub(r'\s*\|\s*Telecaribe\s*VOD', '', title or '').strip() or None
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        player = self._download_player_webpage(webpage, display_id)
+
+        livestream_url = self._search_regex(
+            r'(?:let|const|var)\s+source\s*=\s*["\']([^"\']+)', player, 'm3u8 url', default=None)
+
+        if not livestream_url:
+            return self.playlist_from_matches(
+                re.findall(r'<a[^>]+href\s*=\s*"([^"]+\.mp4)', player), display_id,
+                self._get_clean_title(self._og_search_title(webpage)))
+
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+            livestream_url, display_id, 'mp4', live=True)
+
+        return {
+            'id': display_id,
+            'title': self._get_clean_title(self._og_search_title(webpage)),
+            'formats': formats,
+            'subtitles': subtitles,
+            'is_live': True,
+        }

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

@@ -0,0 +1,146 @@
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    int_or_none,
+    str_or_none,
+    try_get,
+)
+
+
+class TelecincoIE(InfoExtractor):
+    IE_DESC = 'telecinco.es, cuatro.com and mediaset.es'
+    _VALID_URL = r'https?://(?:www\.)?(?:telecinco\.es|cuatro\.com|mediaset\.es)/(?:[^/]+/)+(?P<id>.+?)\.html'
+
+    _TESTS = [{
+        'url': 'http://www.telecinco.es/robinfood/temporada-01/t01xp14/Bacalao-cocochas-pil-pil_0_1876350223.html',
+        'info_dict': {
+            'id': '1876350223',
+            'title': 'Bacalao con kokotxas al pil-pil',
+            'description': 'md5:716caf5601e25c3c5ab6605b1ae71529',
+        },
+        'playlist': [{
+            'md5': '7ee56d665cfd241c0e6d80fd175068b0',
+            'info_dict': {
+                'id': 'JEA5ijCnF6p5W08A1rNKn7',
+                'ext': 'mp4',
+                'title': 'Con Martín Berasategui, hacer un bacalao al pil-pil es fácil y divertido',
+                'duration': 662,
+            },
+        }]
+    }, {
+        'url': 'http://www.cuatro.com/deportes/futbol/barcelona/Leo_Messi-Champions-Roma_2_2052780128.html',
+        'md5': 'c86fe0d99e3bdb46b7950d38bf6ef12a',
+        'info_dict': {
+            'id': 'jn24Od1zGLG4XUZcnUnZB6',
+            'ext': 'mp4',
+            'title': '¿Quién es este ex futbolista con el que hablan Leo Messi y Luis Suárez?',
+            'description': 'md5:a62ecb5f1934fc787107d7b9a2262805',
+            'duration': 79,
+        },
+    }, {
+        'url': 'http://www.mediaset.es/12meses/campanas/doylacara/conlatratanohaytrato/Ayudame-dar-cara-trata-trato_2_1986630220.html',
+        'md5': 'eddb50291df704ce23c74821b995bcac',
+        'info_dict': {
+            'id': 'aywerkD2Sv1vGNqq9b85Q2',
+            'ext': 'mp4',
+            'title': '#DOYLACARA. Con la trata no hay trato',
+            'description': 'md5:2771356ff7bfad9179c5f5cd954f1477',
+            'duration': 50,
+        },
+    }, {
+        # video in opening's content
+        'url': 'https://www.telecinco.es/vivalavida/fiorella-sobrina-edmundo-arrocet-entrevista_18_2907195140.html',
+        'info_dict': {
+            'id': '2907195140',
+            'title': 'La surrealista entrevista a la sobrina de Edmundo Arrocet: "No puedes venir aquí y tomarnos por tontos"',
+            'description': 'md5:73f340a7320143d37ab895375b2bf13a',
+        },
+        'playlist': [{
+            'md5': 'adb28c37238b675dad0f042292f209a7',
+            'info_dict': {
+                'id': 'TpI2EttSDAReWpJ1o0NVh2',
+                'ext': 'mp4',
+                'title': 'La surrealista entrevista a la sobrina de Edmundo Arrocet: "No puedes venir aquí y tomarnos por tontos"',
+                'duration': 1015,
+            },
+        }],
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://www.telecinco.es/informativos/nacional/Pablo_Iglesias-Informativos_Telecinco-entrevista-Pedro_Piqueras_2_1945155182.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.telecinco.es/espanasinirmaslejos/Espana-gran-destino-turistico_2_1240605043.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.cuatro.com/chesterinlove/a-carta/chester-chester_in_love-chester_edu_2_2331030022.html',
+        'only_matching': True,
+    }]
+
+    def _parse_content(self, content, url):
+        video_id = content['dataMediaId']
+        config = self._download_json(
+            content['dataConfig'], video_id, 'Downloading config JSON')
+        title = config['info']['title']
+        services = config['services']
+        caronte = self._download_json(services['caronte'], video_id)
+        stream = caronte['dls'][0]['stream']
+        headers = self.geo_verification_headers()
+        headers.update({
+            'Content-Type': 'application/json;charset=UTF-8',
+            'Origin': re.match(r'https?://[^/]+', url).group(0),
+        })
+        cdn = self._download_json(
+            caronte['cerbero'], video_id, data=json.dumps({
+                'bbx': caronte['bbx'],
+                'gbx': self._download_json(services['gbx'], video_id)['gbx'],
+            }).encode(), headers=headers)['tokens']['1']['cdn']
+        formats = self._extract_m3u8_formats(
+            stream + '?' + cdn, video_id, 'mp4', 'm3u8_native', m3u8_id='hls')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': content.get('dataPoster') or config.get('poster', {}).get('imageUrl'),
+            'duration': int_or_none(content.get('dataDuration')),
+        }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        article = self._parse_json(self._search_regex(
+            r'window\.\$REACTBASE_STATE\.article(?:_multisite)?\s*=\s*({.+})',
+            webpage, 'article'), display_id)['article']
+        title = article.get('title')
+        description = clean_html(article.get('leadParagraph')) or ''
+        if article.get('editorialType') != 'VID':
+            entries = []
+            body = [article.get('opening')]
+            body.extend(try_get(article, lambda x: x['body'], list) or [])
+            for p in body:
+                if not isinstance(p, dict):
+                    continue
+                content = p.get('content')
+                if not content:
+                    continue
+                type_ = p.get('type')
+                if type_ == 'paragraph':
+                    content_str = str_or_none(content)
+                    if content_str:
+                        description += content_str
+                    continue
+                if type_ == 'video' and isinstance(content, dict):
+                    entries.append(self._parse_content(content, url))
+            return self.playlist_result(
+                entries, str_or_none(article.get('id')), title, description)
+        content = article['opening']['content']
+        info = self._parse_content(content, url)
+        info.update({
+            'description': description,
+        })
+        return info

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

@@ -0,0 +1,86 @@
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    int_or_none,
+    parse_iso8601,
+    try_get,
+)
+
+
+class TelegraafIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?telegraaf\.nl/video/(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://www.telegraaf.nl/video/734366489/historisch-scheepswrak-slaat-na-100-jaar-los',
+        'info_dict': {
+            'id': 'gaMItuoSeUg2',
+            'ext': 'mp4',
+            'title': 'Historisch scheepswrak slaat na 100 jaar los',
+            'description': 'md5:6f53b7c4f55596722ac24d6c0ec00cfb',
+            'thumbnail': r're:^https?://.*\.jpg',
+            'duration': 55,
+            'timestamp': 1572805527,
+            'upload_date': '20191103',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        article_id = self._match_id(url)
+
+        video_id = self._download_json(
+            'https://app.telegraaf.nl/graphql', article_id,
+            headers={'User-Agent': 'De Telegraaf/6.8.11 (Android 11; en_US)'},
+            query={
+                'query': '''{
+  article(uid: %s) {
+    videos {
+      videoId
+    }
+  }
+}''' % article_id,
+            })['data']['article']['videos'][0]['videoId']
+
+        item = self._download_json(
+            'https://content.tmgvideo.nl/playlist/item=%s/playlist.json' % video_id,
+            video_id)['items'][0]
+        title = item['title']
+
+        formats = []
+        locations = item.get('locations') or {}
+        for location in locations.get('adaptive', []):
+            manifest_url = location.get('src')
+            if not manifest_url:
+                continue
+            ext = determine_ext(manifest_url)
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    manifest_url, video_id, ext='mp4', m3u8_id='hls', fatal=False))
+            elif ext == 'mpd':
+                formats.extend(self._extract_mpd_formats(
+                    manifest_url, video_id, mpd_id='dash', fatal=False))
+            else:
+                self.report_warning('Unknown adaptive format %s' % ext)
+        for location in locations.get('progressive', []):
+            src = try_get(location, lambda x: x['sources'][0]['src'])
+            if not src:
+                continue
+            label = location.get('label')
+            formats.append({
+                'url': src,
+                'width': int_or_none(location.get('width')),
+                'height': int_or_none(location.get('height')),
+                'format_id': 'http' + ('-%s' % label if label else ''),
+            })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': item.get('description'),
+            'formats': formats,
+            'duration': int_or_none(item.get('duration')),
+            'thumbnail': item.get('poster'),
+            'timestamp': parse_iso8601(item.get('datecreated'), ' '),
+        }