@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/rts.py

@@ -0,0 +1,232 @@
+import re
+
+from .srgssr import SRGSSRIE
+from ..compat import compat_str
+from ..utils import (
+    determine_ext,
+    int_or_none,
+    parse_duration,
+    parse_iso8601,
+    unescapeHTML,
+    urljoin,
+)
+
+
+class RTSIE(SRGSSRIE):  # XXX: Do not subclass from concrete IE
+    _WORKING = False
+    IE_DESC = 'RTS.ch'
+    _VALID_URL = r'rts:(?P<rts_id>\d+)|https?://(?:.+?\.)?rts\.ch/(?:[^/]+/){2,}(?P<id>[0-9]+)-(?P<display_id>.+?)\.html'
+
+    _TESTS = [
+        {
+            'url': 'http://www.rts.ch/archives/tv/divers/3449373-les-enfants-terribles.html',
+            'md5': '753b877968ad8afaeddccc374d4256a5',
+            'info_dict': {
+                'id': '3449373',
+                'display_id': 'les-enfants-terribles',
+                'ext': 'mp4',
+                'duration': 1488,
+                'title': 'Les Enfants Terribles',
+                'description': 'France Pommier et sa soeur Luce Feral, les deux filles de ce groupe de 5.',
+                'uploader': 'Divers',
+                'upload_date': '19680921',
+                'timestamp': -40280400,
+                'thumbnail': r're:^https?://.*\.image',
+                'view_count': int,
+            },
+            'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
+        },
+        {
+            'url': 'http://www.rts.ch/emissions/passe-moi-les-jumelles/5624067-entre-ciel-et-mer.html',
+            'info_dict': {
+                'id': '5624065',
+                'title': 'Passe-moi les jumelles',
+            },
+            'playlist_mincount': 4,
+        },
+        {
+            'url': 'http://www.rts.ch/video/sport/hockey/5745975-1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski.html',
+            'info_dict': {
+                'id': '5745975',
+                'display_id': '1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski',
+                'ext': 'mp4',
+                'duration': 48,
+                'title': '1/2, Kloten - Fribourg (5-2): second but pour Gottéron par Kwiatowski',
+                'description': 'Hockey - Playoff',
+                'uploader': 'Hockey',
+                'upload_date': '20140403',
+                'timestamp': 1396556882,
+                'thumbnail': r're:^https?://.*\.image',
+                'view_count': int,
+            },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },
+            'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
+            'skip': 'Blocked outside Switzerland',
+        },
+        {
+            'url': 'http://www.rts.ch/video/info/journal-continu/5745356-londres-cachee-par-un-epais-smog.html',
+            'md5': '9bb06503773c07ce83d3cbd793cebb91',
+            'info_dict': {
+                'id': '5745356',
+                'display_id': 'londres-cachee-par-un-epais-smog',
+                'ext': 'mp4',
+                'duration': 33,
+                'title': 'Londres cachée par un épais smog',
+                'description': 'Un important voile de smog recouvre Londres depuis mercredi, provoqué par la pollution et du sable du Sahara.',
+                'uploader': 'L\'actu en vidéo',
+                'upload_date': '20140403',
+                'timestamp': 1396537322,
+                'thumbnail': r're:^https?://.*\.image',
+                'view_count': int,
+            },
+            'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
+        },
+        {
+            'url': 'http://www.rts.ch/audio/couleur3/programmes/la-belle-video-de-stephane-laurenceau/5706148-urban-hippie-de-damien-krisl-03-04-2014.html',
+            'md5': 'dd8ef6a22dff163d063e2a52bc8adcae',
+            'info_dict': {
+                'id': '5706148',
+                'display_id': 'urban-hippie-de-damien-krisl-03-04-2014',
+                'ext': 'mp3',
+                'duration': 123,
+                'title': '"Urban Hippie", de Damien Krisl',
+                'description': 'Des Hippies super glam.',
+                'upload_date': '20140403',
+                'timestamp': 1396551600,
+            },
+        },
+        {
+            # article with videos on rhs
+            'url': 'http://www.rts.ch/sport/hockey/6693917-hockey-davos-decroche-son-31e-titre-de-champion-de-suisse.html',
+            'info_dict': {
+                'id': '6693917',
+                'title': 'Hockey: Davos décroche son 31e titre de champion de Suisse',
+            },
+            'playlist_mincount': 5,
+        },
+        {
+            'url': 'http://pages.rts.ch/emissions/passe-moi-les-jumelles/5624065-entre-ciel-et-mer.html',
+            'only_matching': True,
+        }
+    ]
+
+    def _real_extract(self, url):
+        m = self._match_valid_url(url)
+        media_id = m.group('rts_id') or m.group('id')
+        display_id = m.group('display_id') or media_id
+
+        def download_json(internal_id):
+            return self._download_json(
+                'http://www.rts.ch/a/%s.html?f=json/article' % internal_id,
+                display_id)
+
+        all_info = download_json(media_id)
+
+        # media_id extracted out of URL is not always a real id
+        if 'video' not in all_info and 'audio' not in all_info:
+            entries = []
+
+            for item in all_info.get('items', []):
+                item_url = item.get('url')
+                if not item_url:
+                    continue
+                entries.append(self.url_result(item_url, 'RTS'))
+
+            if not entries:
+                page, urlh = self._download_webpage_handle(url, display_id)
+                if re.match(self._VALID_URL, urlh.url).group('id') != media_id:
+                    return self.url_result(urlh.url, 'RTS')
+
+                # article with videos on rhs
+                videos = re.findall(
+                    r'<article[^>]+class="content-item"[^>]*>\s*<a[^>]+data-video-urn="urn:([^"]+)"',
+                    page)
+                if not videos:
+                    videos = re.findall(
+                        r'(?s)<iframe[^>]+class="srg-player"[^>]+src="[^"]+urn:([^"]+)"',
+                        page)
+                if videos:
+                    entries = [self.url_result('srgssr:%s' % video_urn, 'SRGSSR') for video_urn in videos]
+
+            if entries:
+                return self.playlist_result(entries, media_id, all_info.get('title'))
+
+            internal_id = self._html_search_regex(
+                r'<(?:video|audio) data-id="([0-9]+)"', page,
+                'internal video id')
+            all_info = download_json(internal_id)
+
+        media_type = 'video' if 'video' in all_info else 'audio'
+
+        # check for errors
+        self._get_media_data('rts', media_type, media_id)
+
+        info = all_info['video']['JSONinfo'] if 'video' in all_info else all_info['audio']
+
+        title = info['title']
+
+        def extract_bitrate(url):
+            return int_or_none(self._search_regex(
+                r'-([0-9]+)k\.', url, 'bitrate', default=None))
+
+        formats = []
+        streams = info.get('streams', {})
+        for format_id, format_url in streams.items():
+            if format_id == 'hds_sd' and 'hds' in streams:
+                continue
+            if format_id == 'hls_sd' and 'hls' in streams:
+                continue
+            ext = determine_ext(format_url)
+            if ext in ('m3u8', 'f4m'):
+                format_url = self._get_tokenized_src(format_url, media_id, format_id)
+                if ext == 'f4m':
+                    formats.extend(self._extract_f4m_formats(
+                        format_url + ('?' if '?' not in format_url else '&') + 'hdcore=3.4.0',
+                        media_id, f4m_id=format_id, fatal=False))
+                else:
+                    formats.extend(self._extract_m3u8_formats(
+                        format_url, media_id, 'mp4', 'm3u8_native', m3u8_id=format_id, fatal=False))
+            else:
+                formats.append({
+                    'format_id': format_id,
+                    'url': format_url,
+                    'tbr': extract_bitrate(format_url),
+                })
+
+        download_base = 'http://rtsww%s-d.rts.ch/' % ('-a' if media_type == 'audio' else '')
+        for media in info.get('media', []):
+            media_url = media.get('url')
+            if not media_url or re.match(r'https?://', media_url):
+                continue
+            rate = media.get('rate')
+            ext = media.get('ext') or determine_ext(media_url, 'mp4')
+            format_id = ext
+            if rate:
+                format_id += '-%dk' % rate
+            formats.append({
+                'format_id': format_id,
+                'url': urljoin(download_base, media_url),
+                'tbr': rate or extract_bitrate(media_url),
+            })
+
+        self._check_formats(formats, media_id)
+
+        duration = info.get('duration') or info.get('cutout') or info.get('cutduration')
+        if isinstance(duration, compat_str):
+            duration = parse_duration(duration)
+
+        return {
+            'id': media_id,
+            'display_id': display_id,
+            'formats': formats,
+            'title': title,
+            'description': info.get('intro'),
+            'duration': duration,
+            'view_count': int_or_none(info.get('plays')),
+            'uploader': info.get('programName'),
+            'timestamp': parse_iso8601(info.get('broadcast_date')),
+            'thumbnail': unescapeHTML(info.get('preview_image_url')),
+        }

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

@@ -0,0 +1,285 @@
+import re
+
+from .common import InfoExtractor, ExtractorError
+from ..utils import (
+    clean_html,
+    determine_ext,
+    int_or_none,
+    float_or_none,
+    js_to_json,
+    mimetype2ext,
+    traverse_obj,
+    urljoin,
+    url_or_none,
+)
+
+
+class RTVCPlayBaseIE(InfoExtractor):
+    _BASE_VALID_URL = r'https?://(?:www\.)?rtvcplay\.co'
+
+    def _extract_player_config(self, webpage, video_id):
+        return self._search_json(
+            r'<script\b[^>]*>[^<]*(?:var|let|const)\s+config\s*=', re.sub(r'"\s*\+\s*"', '', webpage),
+            'player_config', video_id, transform_source=js_to_json)
+
+    def _extract_formats_and_subtitles_player_config(self, player_config, video_id):
+        formats, subtitles = [], {}
+        for source in traverse_obj(player_config, ('sources', ..., lambda _, v: url_or_none(v['url']))):
+            ext = mimetype2ext(source.get('mimetype'), default=determine_ext(source['url']))
+            if ext == 'm3u8':
+                fmts, subs = self._extract_m3u8_formats_and_subtitles(
+                    source['url'], video_id, 'mp4', fatal=False)
+                formats.extend(fmts)
+                self._merge_subtitles(subs, target=subtitles)
+            else:
+                formats.append({
+                    'url': source['url'],
+                    'ext': ext,
+                })
+
+        return formats, subtitles
+
+
+class RTVCPlayIE(RTVCPlayBaseIE):
+    _VALID_URL = RTVCPlayBaseIE._BASE_VALID_URL + r'/(?P<category>(?!embed)[^/]+)/(?:[^?#]+/)?(?P<id>[\w-]+)'
+
+    _TESTS = [{
+        'url': 'https://www.rtvcplay.co/en-vivo/canal-institucional',
+        'info_dict': {
+            'id': 'canal-institucional',
+            'title': r're:^Canal Institucional',
+            'description': 'md5:eff9e548394175928059320c006031ea',
+            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
+            'live_status': 'is_live',
+            'ext': 'mp4',
+        },
+        'params': {
+            'skip_download': 'Livestream',
+        },
+    }, {
+        'url': 'https://www.rtvcplay.co/en-vivo/senal-colombia',
+        'info_dict': {
+            'id': 'senal-colombia',
+            'title': r're:^Señal Colombia',
+            'description': 'md5:799f16a401d97f40c33a2c6a3e2a507b',
+            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
+            'live_status': 'is_live',
+            'ext': 'mp4',
+        },
+        'params': {
+            'skip_download': 'Livestream',
+        },
+    }, {
+        'url': 'https://www.rtvcplay.co/en-vivo/radio-nacional',
+        'info_dict': {
+            'id': 'radio-nacional',
+            'title': r're:^Radio Nacional',
+            'description': 'md5:5de009bc6a9fa79d2a6cf0b73f977d53',
+            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
+            'live_status': 'is_live',
+            'ext': 'mp4',
+        },
+        'params': {
+            'skip_download': 'Livestream',
+        },
+    }, {
+        'url': 'https://www.rtvcplay.co/peliculas-ficcion/senoritas',
+        'md5': '1288ee6f6d1330d880f98bff2ed710a3',
+        'info_dict': {
+            'id': 'senoritas',
+            'title': 'Señoritas',
+            'description': 'md5:f095a2bb52cb6cf279daf6302f86fb32',
+            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
+            'ext': 'mp4',
+        },
+    }, {
+        'url': 'https://www.rtvcplay.co/competencias-basicas-ciudadanas-y-socioemocionales/profe-en-tu-casa/james-regresa-clases-28022022',
+        'md5': 'f040a7380a269ad633cf837384d5e9fc',
+        'info_dict': {
+            'id': 'james-regresa-clases-28022022',
+            'title': 'James regresa a clases - 28/02/2022',
+            'description': 'md5:c5dcdf757c7ab29305e8763c6007e675',
+            'ext': 'mp4',
+        },
+    }, {
+        'url': 'https://www.rtvcplay.co/peliculas-documentales/llinas-el-cerebro-y-el-universo',
+        'info_dict': {
+            'id': 'llinas-el-cerebro-y-el-universo',
+            'title': 'Llinás, el cerebro y el universo',
+            'description': 'md5:add875bf2309bb52b3e8b9b06116d9b0',
+            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
+        },
+        'playlist_mincount': 3,
+    }, {
+        'url': 'https://www.rtvcplay.co/competencias-basicas-ciudadanas-y-socioemocionales/profe-en-tu-casa',
+        'info_dict': {
+            'id': 'profe-en-tu-casa',
+            'title': 'Profe en tu casa',
+            'description': 'md5:47dbe20e263194413b1db2a2805a4f2e',
+            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
+        },
+        'playlist_mincount': 537,
+    }, {
+        'url': 'https://www.rtvcplay.co/series-al-oido/relato-de-un-naufrago-una-travesia-del-periodismo-a-la-literatura',
+        'info_dict': {
+            'id': 'relato-de-un-naufrago-una-travesia-del-periodismo-a-la-literatura',
+            'title': 'Relato de un náufrago: una travesía del periodismo a la literatura',
+            'description': 'md5:6da28fdca4a5a568ea47ef65ef775603',
+            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
+        },
+        'playlist_mincount': 5,
+    }, {
+        'url': 'https://www.rtvcplay.co/series-al-oido/diez-versiones',
+        'info_dict': {
+            'id': 'diez-versiones',
+            'title': 'Diez versiones',
+            'description': 'md5:997471ed971cb3fd8e41969457675306',
+            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
+        },
+        'playlist_mincount': 20,
+    }]
+
+    def _real_extract(self, url):
+        video_id, category = self._match_valid_url(url).group('id', 'category')
+        webpage = self._download_webpage(url, video_id)
+
+        hydration = self._search_json(
+            r'window\.__RTVCPLAY_STATE__\s*=', webpage, 'hydration',
+            video_id, transform_source=js_to_json)['content']['currentContent']
+
+        asset_id = traverse_obj(hydration, ('video', 'assetid'))
+        if asset_id:
+            hls_url = hydration['base_url_hls'].replace('[node:field_asset_id]', asset_id)
+        else:
+            hls_url = traverse_obj(hydration, ('channel', 'hls'))
+
+        metadata = traverse_obj(hydration, {
+            'title': 'title',
+            'description': 'description',
+            'thumbnail': ((('channel', 'image', 'logo'), ('resource', 'image', 'cover_desktop')), 'path'),
+        }, get_all=False)
+
+        # Probably it's a program's page
+        if not hls_url:
+            seasons = traverse_obj(
+                hydration, ('widgets', lambda _, y: y['type'] == 'seasonList', 'contents'),
+                get_all=False)
+            if not seasons:
+                podcast_episodes = hydration.get('audios')
+                if not podcast_episodes:
+                    raise ExtractorError('Could not find asset_id nor program playlist nor podcast episodes')
+
+                return self.playlist_result([
+                    self.url_result(episode['file'], url_transparent=True, **traverse_obj(episode, {
+                        'title': 'title',
+                        'description': ('description', {clean_html}),
+                        'episode_number': ('chapter_number', {float_or_none}, {int_or_none}),
+                        'season_number': ('season', {int_or_none}),
+                    })) for episode in podcast_episodes], video_id, **metadata)
+
+            entries = [self.url_result(
+                urljoin(url, episode['slug']), url_transparent=True,
+                **traverse_obj(season, {
+                    'season': 'title',
+                    'season_number': ('season', {int_or_none}),
+                }), **traverse_obj(episode, {
+                    'title': 'title',
+                    'thumbnail': ('image', 'cover', 'path'),
+                    'episode_number': ('chapter_number', {int_or_none}),
+                })) for season in seasons for episode in traverse_obj(season, ('contents', ...))]
+
+            return self.playlist_result(entries, video_id, **metadata)
+
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(hls_url, video_id, 'mp4')
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'subtitles': subtitles,
+            'is_live': category == 'en-vivo',
+            **metadata,
+        }
+
+
+class RTVCPlayEmbedIE(RTVCPlayBaseIE):
+    _VALID_URL = RTVCPlayBaseIE._BASE_VALID_URL + r'/embed/(?P<id>[\w-]+)'
+
+    _TESTS = [{
+        'url': 'https://www.rtvcplay.co/embed/72b0e699-248b-4929-a4a8-3782702fa7f9',
+        'md5': 'ed529aeaee7aa2a72afe91ac7d1177a8',
+        'info_dict': {
+            'id': '72b0e699-248b-4929-a4a8-3782702fa7f9',
+            'title': 'Tráiler: Señoritas',
+            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
+            'ext': 'mp4',
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        player_config = self._extract_player_config(webpage, video_id)
+        formats, subtitles = self._extract_formats_and_subtitles_player_config(player_config, video_id)
+
+        asset_id = traverse_obj(player_config, ('rtvcplay', 'assetid'))
+        metadata = {} if not asset_id else self._download_json(
+            f'https://cms.rtvcplay.co/api/v1/video/asset-id/{asset_id}', video_id, fatal=False)
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'subtitles': subtitles,
+            **traverse_obj(metadata, {
+                'title': 'title',
+                'description': 'description',
+                'thumbnail': ('image', ..., 'thumbnail', 'path'),
+            }, get_all=False)
+        }
+
+
+class RTVCKalturaIE(RTVCPlayBaseIE):
+    _VALID_URL = r'https?://media\.rtvc\.gov\.co/kalturartvc/(?P<id>[\w-]+)'
+
+    _TESTS = [{
+        'url': 'https://media.rtvc.gov.co/kalturartvc/indexSC.html',
+        'info_dict': {
+            'id': 'indexSC',
+            'title': r're:^Señal Colombia',
+            'description': 'md5:799f16a401d97f40c33a2c6a3e2a507b',
+            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
+            'live_status': 'is_live',
+            'ext': 'mp4',
+        },
+        'params': {
+            'skip_download': 'Livestream',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        player_config = self._extract_player_config(webpage, video_id)
+        formats, subtitles = self._extract_formats_and_subtitles_player_config(player_config, video_id)
+
+        channel_id = traverse_obj(player_config, ('rtvcplay', 'channelId'))
+        metadata = {} if not channel_id else self._download_json(
+            f'https://cms.rtvcplay.co/api/v1/taxonomy_term/streaming/{channel_id}', video_id, fatal=False)
+
+        fmts, subs = self._extract_m3u8_formats_and_subtitles(
+            traverse_obj(metadata, ('channel', 'hls')), video_id, 'mp4', fatal=False)
+        formats.extend(fmts)
+        self._merge_subtitles(subs, target=subtitles)
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'subtitles': subtitles,
+            'is_live': True,
+            **traverse_obj(metadata, {
+                'title': 'title',
+                'description': 'description',
+                'thumbnail': ('channel', 'image', 'logo', 'path'),
+            })
+        }