@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/onet.py

@@ -0,0 +1,259 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    ExtractorError,
+    float_or_none,
+    get_element_by_class,
+    int_or_none,
+    js_to_json,
+    NO_DEFAULT,
+    parse_iso8601,
+    remove_start,
+    strip_or_none,
+    url_basename,
+)
+
+
+class OnetBaseIE(InfoExtractor):
+    _URL_BASE_RE = r'https?://(?:(?:www\.)?onet\.tv|onet100\.vod\.pl)/[a-z]/'
+
+    def _search_mvp_id(self, webpage):
+        return self._search_regex(
+            r'id=(["\'])mvp:(?P<id>.+?)\1', webpage, 'mvp id', group='id')
+
+    def _extract_from_id(self, video_id, webpage=None):
+        response = self._download_json(
+            'http://qi.ckm.onetapi.pl/', video_id,
+            query={
+                'body[id]': video_id,
+                'body[jsonrpc]': '2.0',
+                'body[method]': 'get_asset_detail',
+                'body[params][ID_Publikacji]': video_id,
+                'body[params][Service]': 'www.onet.pl',
+                'content-type': 'application/jsonp',
+                'x-onet-app': 'player.front.onetapi.pl',
+            })
+
+        error = response.get('error')
+        if error:
+            raise ExtractorError(
+                '%s said: %s' % (self.IE_NAME, error['message']), expected=True)
+
+        video = response['result'].get('0')
+
+        formats = []
+        for format_type, formats_dict in video['formats'].items():
+            if not isinstance(formats_dict, dict):
+                continue
+            for format_id, format_list in formats_dict.items():
+                if not isinstance(format_list, list):
+                    continue
+                for f in format_list:
+                    video_url = f.get('url')
+                    if not video_url:
+                        continue
+                    ext = determine_ext(video_url)
+                    if format_id.startswith('ism'):
+                        formats.extend(self._extract_ism_formats(
+                            video_url, video_id, 'mss', fatal=False))
+                    elif ext == 'mpd':
+                        formats.extend(self._extract_mpd_formats(
+                            video_url, video_id, mpd_id='dash', fatal=False))
+                    elif format_id.startswith('hls'):
+                        formats.extend(self._extract_m3u8_formats(
+                            video_url, video_id, 'mp4', 'm3u8_native',
+                            m3u8_id='hls', fatal=False))
+                    else:
+                        http_f = {
+                            'url': video_url,
+                            'format_id': format_id,
+                            'abr': float_or_none(f.get('audio_bitrate')),
+                        }
+                        if format_type == 'audio':
+                            http_f['vcodec'] = 'none'
+                        else:
+                            http_f.update({
+                                'height': int_or_none(f.get('vertical_resolution')),
+                                'width': int_or_none(f.get('horizontal_resolution')),
+                                'vbr': float_or_none(f.get('video_bitrate')),
+                            })
+                        formats.append(http_f)
+
+        meta = video.get('meta', {})
+
+        title = (self._og_search_title(
+            webpage, default=None) if webpage else None) or meta['title']
+        description = (self._og_search_description(
+            webpage, default=None) if webpage else None) or meta.get('description')
+        duration = meta.get('length') or meta.get('lenght')
+        timestamp = parse_iso8601(meta.get('addDate'), ' ')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'timestamp': timestamp,
+            'formats': formats,
+        }
+
+
+class OnetMVPIE(OnetBaseIE):
+    _VALID_URL = r'onetmvp:(?P<id>\d+\.\d+)'
+
+    _TEST = {
+        'url': 'onetmvp:381027.1509591944',
+        'only_matching': True,
+    }
+
+    def _real_extract(self, url):
+        return self._extract_from_id(self._match_id(url))
+
+
+class OnetIE(OnetBaseIE):
+    _VALID_URL = OnetBaseIE._URL_BASE_RE + r'[a-z]+/(?P<display_id>[0-9a-z-]+)/(?P<id>[0-9a-z]+)'
+    IE_NAME = 'onet.tv'
+
+    _TESTS = [{
+        'url': 'http://onet.tv/k/openerfestival/open-er-festival-2016-najdziwniejsze-wymagania-gwiazd/qbpyqc',
+        'md5': '436102770fb095c75b8bb0392d3da9ff',
+        'info_dict': {
+            'id': 'qbpyqc',
+            'display_id': 'open-er-festival-2016-najdziwniejsze-wymagania-gwiazd',
+            'ext': 'mp4',
+            'title': 'Open\'er Festival 2016: najdziwniejsze wymagania gwiazd',
+            'description': 'Trzy samochody, których nigdy nie użyto, prywatne spa, hotel dekorowany czarnym suknem czy nielegalne używki. Organizatorzy koncertów i festiwali muszą stawać przed nie lada wyzwaniem zapraszając gwia...',
+            'upload_date': '20160705',
+            'timestamp': 1467721580,
+        },
+    }, {
+        'url': 'https://onet100.vod.pl/k/openerfestival/open-er-festival-2016-najdziwniejsze-wymagania-gwiazd/qbpyqc',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = self._match_valid_url(url)
+        display_id, video_id = mobj.group('display_id', 'id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        mvp_id = self._search_mvp_id(webpage)
+
+        info_dict = self._extract_from_id(mvp_id, webpage)
+        info_dict.update({
+            'id': video_id,
+            'display_id': display_id,
+        })
+
+        return info_dict
+
+
+class OnetChannelIE(OnetBaseIE):
+    _VALID_URL = OnetBaseIE._URL_BASE_RE + r'(?P<id>[a-z]+)(?:[?#]|$)'
+    IE_NAME = 'onet.tv:channel'
+
+    _TESTS = [{
+        'url': 'http://onet.tv/k/openerfestival',
+        'info_dict': {
+            'id': 'openerfestival',
+            'title': "Open'er Festival",
+            'description': "Tak było na Open'er Festival 2016! Oglądaj nasze reportaże i wywiady z artystami.",
+        },
+        'playlist_mincount': 35,
+    }, {
+        'url': 'https://onet100.vod.pl/k/openerfestival',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        channel_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, channel_id)
+
+        current_clip_info = self._parse_json(self._search_regex(
+            r'var\s+currentClip\s*=\s*({[^}]+})', webpage, 'video info'), channel_id,
+            transform_source=lambda s: js_to_json(re.sub(r'\'\s*\+\s*\'', '', s)))
+        video_id = remove_start(current_clip_info['ckmId'], 'mvp:')
+        video_name = url_basename(current_clip_info['url'])
+
+        if not self._yes_playlist(channel_id, video_name, playlist_label='channel'):
+            return self._extract_from_id(video_id, webpage)
+
+        matches = re.findall(
+            r'<a[^>]+href=[\'"](%s[a-z]+/[0-9a-z-]+/[0-9a-z]+)' % self._URL_BASE_RE,
+            webpage)
+        entries = [
+            self.url_result(video_link, OnetIE.ie_key())
+            for video_link in matches]
+
+        channel_title = strip_or_none(get_element_by_class('o_channelName', webpage))
+        channel_description = strip_or_none(get_element_by_class('o_channelDesc', webpage))
+        return self.playlist_result(entries, channel_id, channel_title, channel_description)
+
+
+class OnetPlIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:[^/]+\.)?(?:onet|businessinsider\.com|plejada)\.pl/(?:[^/]+/)+(?P<id>[0-9a-z]+)'
+    IE_NAME = 'onet.pl'
+
+    _TESTS = [{
+        'url': 'http://eurosport.onet.pl/zimowe/skoki-narciarskie/ziobro-wygral-kwalifikacje-w-pjongczangu/9ckrly',
+        'md5': 'b94021eb56214c3969380388b6e73cb0',
+        'info_dict': {
+            'id': '1561707.1685479',
+            'ext': 'mp4',
+            'title': 'Ziobro wygrał kwalifikacje w Pjongczangu',
+            'description': 'md5:61fb0740084d2d702ea96512a03585b4',
+            'upload_date': '20170214',
+            'timestamp': 1487078046,
+        },
+    }, {
+        # embedded via pulsembed
+        'url': 'http://film.onet.pl/pensjonat-nad-rozlewiskiem-relacja-z-planu-serialu/y428n0',
+        'info_dict': {
+            'id': '501235.965429946',
+            'ext': 'mp4',
+            'title': '"Pensjonat nad rozlewiskiem": relacja z planu serialu',
+            'upload_date': '20170622',
+            'timestamp': 1498159955,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://film.onet.pl/zwiastuny/ghost-in-the-shell-drugi-zwiastun-pl/5q6yl3',
+        'only_matching': True,
+    }, {
+        'url': 'http://moto.onet.pl/jak-wybierane-sa-miejsca-na-fotoradary/6rs04e',
+        'only_matching': True,
+    }, {
+        'url': 'http://businessinsider.com.pl/wideo/scenariusz-na-koniec-swiata-wedlug-nasa/dwnqptk',
+        'only_matching': True,
+    }, {
+        'url': 'http://plejada.pl/weronika-rosati-o-swoim-domniemanym-slubie/n2bq89',
+        'only_matching': True,
+    }]
+
+    def _search_mvp_id(self, webpage, default=NO_DEFAULT):
+        return self._search_regex(
+            r'data-(?:params-)?mvp=["\'](\d+\.\d+)', webpage, 'mvp id',
+            default=default)
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        mvp_id = self._search_mvp_id(webpage, default=None)
+
+        if not mvp_id:
+            pulsembed_url = self._search_regex(
+                r'data-src=(["\'])(?P<url>(?:https?:)?//pulsembed\.eu/.+?)\1',
+                webpage, 'pulsembed url', group='url')
+            webpage = self._download_webpage(
+                pulsembed_url, video_id, 'Downloading pulsembed webpage')
+            mvp_id = self._search_mvp_id(webpage)
+
+        return self.url_result(
+            'onetmvp:%s' % mvp_id, OnetMVPIE.ie_key(), video_id=mvp_id)

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

@@ -0,0 +1,42 @@
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import js_to_json
+
+
+class OnionStudiosIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?onionstudios\.com/(?:video(?:s/[^/]+-|/)|embed\?.*\bid=)(?P<id>\d+)(?!-)'
+    _EMBED_REGEX = [r'(?s)<(?:iframe|bulbs-video)[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?onionstudios\.com/(?:embed.+?|video/\d+\.json))\1']
+
+    _TESTS = [{
+        'url': 'http://www.onionstudios.com/videos/hannibal-charges-forward-stops-for-a-cocktail-2937',
+        'md5': '5a118d466d62b5cd03647cf2c593977f',
+        'info_dict': {
+            'id': '3459881',
+            'ext': 'mp4',
+            'title': 'Hannibal charges forward, stops for a cocktail',
+            'description': 'md5:545299bda6abf87e5ec666548c6a9448',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'uploader': 'a.v. club',
+            'upload_date': '20150619',
+            'timestamp': 1434728546,
+        },
+    }, {
+        'url': 'http://www.onionstudios.com/embed?id=2855&autoplay=true',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.onionstudios.com/video/6139.json',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            'http://onionstudios.com/embed/dc94dc2899fe644c0e7241fa04c1b732.js',
+            video_id)
+        mcp_id = compat_str(self._parse_json(self._search_regex(
+            r'window\.mcpMapping\s*=\s*({.+?});', webpage,
+            'MCP Mapping'), video_id, js_to_json)[video_id]['mcp_id'])
+        return self.url_result(
+            'http://kinja.com/ajax/inset/iframe?id=mcp-' + mcp_id,
+            'KinjaEmbed', mcp_id)

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

@@ -0,0 +1,183 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    ExtractorError,
+    int_or_none,
+    parse_iso8601,
+    traverse_obj,
+    variadic,
+)
+
+
+class OpencastBaseIE(InfoExtractor):
+    _INSTANCES_RE = r'''(?:
+                            opencast\.informatik\.kit\.edu|
+                            electures\.uni-muenster\.de|
+                            oc-presentation\.ltcc\.tuwien\.ac\.at|
+                            medien\.ph-noe\.ac\.at|
+                            oc-video\.ruhr-uni-bochum\.de|
+                            oc-video1\.ruhr-uni-bochum\.de|
+                            opencast\.informatik\.uni-goettingen\.de|
+                            heicast\.uni-heidelberg\.de|
+                            opencast\.hawk\.de:8080|
+                            opencast\.hs-osnabrueck\.de|
+                            video[0-9]+\.virtuos\.uni-osnabrueck\.de|
+                            opencast\.uni-koeln\.de|
+                            media\.opencast\.hochschule-rhein-waal\.de|
+                            matterhorn\.dce\.harvard\.edu|
+                            hs-harz\.opencast\.uni-halle\.de|
+                            videocampus\.urz\.uni-leipzig\.de|
+                            media\.uct\.ac\.za|
+                            vid\.igb\.illinois\.edu|
+                            cursosabertos\.c3sl\.ufpr\.br|
+                            mcmedia\.missioncollege\.org|
+                            clases\.odon\.edu\.uy
+                        )'''
+    _UUID_RE = r'[\da-fA-F]{8}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{12}'
+
+    def _call_api(self, host, video_id, **kwargs):
+        return self._download_json(self._API_BASE % (host, video_id), video_id, **kwargs)
+
+    def _parse_mediapackage(self, video):
+        video_id = video.get('id')
+        if video_id is None:
+            raise ExtractorError('Video id was not found')
+
+        formats = []
+        for track in variadic(traverse_obj(video, ('media', 'track')) or []):
+            href = track.get('url')
+            if href is None:
+                continue
+            ext = determine_ext(href, None)
+
+            transport = track.get('transport')
+
+            if transport == 'DASH' or ext == 'mpd':
+                formats.extend(self._extract_mpd_formats(href, video_id, mpd_id='dash', fatal=False))
+            elif transport == 'HLS' or ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    href, video_id, m3u8_id='hls', entry_protocol='m3u8_native', fatal=False))
+            elif transport == 'HDS' or ext == 'f4m':
+                formats.extend(self._extract_f4m_formats(href, video_id, f4m_id='hds', fatal=False))
+            elif transport == 'SMOOTH':
+                formats.extend(self._extract_ism_formats(href, video_id, ism_id='smooth', fatal=False))
+            elif ext == 'smil':
+                formats.extend(self._extract_smil_formats(href, video_id, fatal=False))
+            else:
+                track_obj = {
+                    'url': href,
+                    'ext': ext,
+                    'format_note': track.get('transport'),
+                    'resolution': traverse_obj(track, ('video', 'resolution')),
+                    'fps': int_or_none(traverse_obj(track, ('video', 'framerate'))),
+                    'vbr': int_or_none(traverse_obj(track, ('video', 'bitrate')), scale=1000),
+                    'vcodec': traverse_obj(track, ('video', 'encoder', 'type')) if track.get('video') else 'none',
+                    'abr': int_or_none(traverse_obj(track, ('audio', 'bitrate')), scale=1000),
+                    'asr': int_or_none(traverse_obj(track, ('audio', 'samplingrate'))),
+                    'acodec': traverse_obj(track, ('audio', 'encoder', 'type')) if track.get('audio') else 'none',
+                }
+
+                if transport == 'RTMP':
+                    m_obj = re.search(r'(?:rtmp://[^/]+/(?P<app>[^/]+))/(?P<ext>.+):(?P<playpath>.+)', href)
+                    if not m_obj:
+                        continue
+                    track_obj.update({
+                        'app': m_obj.group('app'),
+                        'ext': m_obj.group('ext'),
+                        'play_path': m_obj.group('ext') + ':' + m_obj.group('playpath'),
+                        'rtmp_live': True,
+                        'preference': -2,
+                    })
+                formats.append(track_obj)
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': video.get('title'),
+            'series': video.get('seriestitle'),
+            'season_id': video.get('series'),
+            'creator': traverse_obj(video, ('creators', 'creator')),
+            'timestamp': parse_iso8601(video.get('start')),
+            'thumbnail': traverse_obj(video, ('attachments', 'attachment', ..., 'url'), get_all=False),
+        }
+
+
+class OpencastIE(OpencastBaseIE):
+    _VALID_URL = rf'''(?x)
+        https?://(?P<host>{OpencastBaseIE._INSTANCES_RE})/paella/ui/watch\.html\?
+        (?:[^#]+&)?id=(?P<id>{OpencastBaseIE._UUID_RE})'''
+
+    _API_BASE = 'https://%s/search/episode.json?id=%s'
+
+    _TESTS = [
+        {
+            'url': 'https://oc-video1.ruhr-uni-bochum.de/paella/ui/watch.html?id=ed063cd5-72c8-46b5-a60a-569243edcea8',
+            'md5': '554c8e99a90f7be7e874619fcf2a3bc9',
+            'info_dict': {
+                'id': 'ed063cd5-72c8-46b5-a60a-569243edcea8',
+                'ext': 'mp4',
+                'title': '11 - Kryptographie - 24.11.2015',
+                'thumbnail': r're:^https?://.*\.jpg$',
+                'timestamp': 1606208400,
+                'upload_date': '20201124',
+                'season_id': 'cf68a4a1-36b1-4a53-a6ba-61af5705a0d0',
+                'series': 'Kryptographie - WiSe 15/16',
+                'creator': 'Alexander May',
+            },
+        }
+    ]
+
+    def _real_extract(self, url):
+        host, video_id = self._match_valid_url(url).group('host', 'id')
+        return self._parse_mediapackage(
+            self._call_api(host, video_id)['search-results']['result']['mediapackage'])
+
+
+class OpencastPlaylistIE(OpencastBaseIE):
+    _VALID_URL = rf'''(?x)
+        https?://(?P<host>{OpencastBaseIE._INSTANCES_RE})(?:
+            /engage/ui/index\.html\?(?:[^#]+&)?epFrom=|
+            /ltitools/index\.html\?(?:[^#]+&)?series=
+        )(?P<id>{OpencastBaseIE._UUID_RE})'''
+
+    _API_BASE = 'https://%s/search/episode.json?sid=%s'
+
+    _TESTS = [
+        {
+            'url': 'https://oc-video1.ruhr-uni-bochum.de/engage/ui/index.html?epFrom=cf68a4a1-36b1-4a53-a6ba-61af5705a0d0',
+            'info_dict': {
+                'id': 'cf68a4a1-36b1-4a53-a6ba-61af5705a0d0',
+                'title': 'Kryptographie - WiSe 15/16',
+            },
+            'playlist_mincount': 29,
+        },
+        {
+            'url': 'https://oc-video1.ruhr-uni-bochum.de/ltitools/index.html?subtool=series&series=cf68a4a1-36b1-4a53-a6ba-61af5705a0d0&lng=de',
+            'info_dict': {
+                'id': 'cf68a4a1-36b1-4a53-a6ba-61af5705a0d0',
+                'title': 'Kryptographie - WiSe 15/16',
+            },
+            'playlist_mincount': 29,
+        },
+        {
+            'url': 'https://electures.uni-muenster.de/engage/ui/index.html?e=1&p=1&epFrom=39391d10-a711-4d23-b21d-afd2ed7d758c',
+            'info_dict': {
+                'id': '39391d10-a711-4d23-b21d-afd2ed7d758c',
+                'title': '021670 Theologische Themen bei Hans Blumenberg WiSe 2017/18',
+            },
+            'playlist_mincount': 13,
+        },
+    ]
+
+    def _real_extract(self, url):
+        host, video_id = self._match_valid_url(url).group('host', 'id')
+
+        entries = [
+            self._parse_mediapackage(episode['mediapackage'])
+            for episode in variadic(self._call_api(host, video_id)['search-results']['result'])
+            if episode.get('mediapackage')
+        ]
+
+        return self.playlist_result(entries, video_id, traverse_obj(entries, (0, 'series')))