@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/japandiet.py

@@ -0,0 +1,274 @@
+import re
+
+from ..utils import (
+    ExtractorError,
+    clean_html,
+    int_or_none,
+    join_nonempty,
+    parse_qs,
+    smuggle_url,
+    traverse_obj,
+    try_call,
+    unsmuggle_url
+)
+from .common import InfoExtractor
+
+
+def _parse_japanese_date(text):
+    if not text:
+        return None
+    ERA_TABLE = {
+        '明治': 1868,
+        '大正': 1912,
+        '昭和': 1926,
+        '平成': 1989,
+        '令和': 2019,
+    }
+    ERA_RE = '|'.join(map(re.escape, ERA_TABLE.keys()))
+    mobj = re.search(rf'({ERA_RE})?(\d+)年(\d+)月(\d+)日', re.sub(r'[\s\u3000]+', '', text))
+    if not mobj:
+        return None
+    era, year, month, day = mobj.groups()
+    year, month, day = map(int, (year, month, day))
+    if era:
+        # example input: 令和5年3月34日
+        # even though each era have their end, don't check here
+        year += ERA_TABLE[era]
+    return '%04d%02d%02d' % (year, month, day)
+
+
+def _parse_japanese_duration(text):
+    mobj = re.search(r'(?:(\d+)日間?)?(?:(\d+)時間?)?(?:(\d+)分)?(?:(\d+)秒)?', re.sub(r'[\s\u3000]+', '', text or ''))
+    if not mobj:
+        return
+    days, hours, mins, secs = [int_or_none(x, default=0) for x in mobj.groups()]
+    return secs + mins * 60 + hours * 60 * 60 + days * 24 * 60 * 60
+
+
+class ShugiinItvBaseIE(InfoExtractor):
+    _INDEX_ROOMS = None
+
+    @classmethod
+    def _find_rooms(cls, webpage):
+        return [{
+            '_type': 'url',
+            'id': x.group(1),
+            'title': clean_html(x.group(2)).strip(),
+            'url': smuggle_url(f'https://www.shugiintv.go.jp/jp/index.php?room_id={x.group(1)}', {'g': x.groups()}),
+            'ie_key': ShugiinItvLiveIE.ie_key(),
+        } for x in re.finditer(r'(?s)<a\s+href="[^"]+\?room_id=(room\d+)"\s*class="play_live".+?class="s12_14">(.+?)</td>', webpage)]
+
+    def _fetch_rooms(self):
+        if not self._INDEX_ROOMS:
+            webpage = self._download_webpage(
+                'https://www.shugiintv.go.jp/jp/index.php', None,
+                encoding='euc-jp', note='Downloading proceedings info')
+            ShugiinItvBaseIE._INDEX_ROOMS = self._find_rooms(webpage)
+        return self._INDEX_ROOMS
+
+
+class ShugiinItvLiveIE(ShugiinItvBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?shugiintv\.go\.jp/(?:jp|en)(?:/index\.php)?$'
+    IE_DESC = '衆議院インターネット審議中継'
+
+    _TESTS = [{
+        'url': 'https://www.shugiintv.go.jp/jp/index.php',
+        'info_dict': {
+            '_type': 'playlist',
+            'title': 'All proceedings for today',
+        },
+        # expect at least one proceedings is running
+        'playlist_mincount': 1,
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return super().suitable(url) and not any(x.suitable(url) for x in (ShugiinItvLiveRoomIE, ShugiinItvVodIE))
+
+    def _real_extract(self, url):
+        self.to_screen(
+            'Downloading all running proceedings. To specify one proceeding, use direct link from the website')
+        return self.playlist_result(self._fetch_rooms(), playlist_title='All proceedings for today')
+
+
+class ShugiinItvLiveRoomIE(ShugiinItvBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?shugiintv\.go\.jp/(?:jp|en)/index\.php\?room_id=(?P<id>room\d+)'
+    IE_DESC = '衆議院インターネット審議中継 (中継)'
+
+    _TESTS = [{
+        'url': 'https://www.shugiintv.go.jp/jp/index.php?room_id=room01',
+        'info_dict': {
+            'id': 'room01',
+            'title': '内閣委員会',
+        },
+        'skip': 'this runs for a time and not every day',
+    }, {
+        'url': 'https://www.shugiintv.go.jp/jp/index.php?room_id=room11',
+        'info_dict': {
+            'id': 'room11',
+            'title': '外務委員会',
+        },
+        'skip': 'this runs for a time and not every day',
+    }]
+
+    def _real_extract(self, url):
+        url, smug = unsmuggle_url(url, default={})
+        if smug.get('g'):
+            room_id, title = smug['g']
+        else:
+            room_id = self._match_id(url)
+            title = traverse_obj(self._fetch_rooms(), (lambda k, v: v['id'] == room_id, 'title'), get_all=False)
+
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+            f'https://hlslive.shugiintv.go.jp/{room_id}/amlst:{room_id}/playlist.m3u8',
+            room_id, ext='mp4')
+
+        return {
+            'id': room_id,
+            'title': title,
+            'formats': formats,
+            'subtitles': subtitles,
+            'is_live': True,
+        }
+
+
+class ShugiinItvVodIE(ShugiinItvBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?shugiintv\.go\.jp/(?:jp|en)/index\.php\?ex=VL(?:\&[^=]+=[^&]*)*\&deli_id=(?P<id>\d+)'
+    IE_DESC = '衆議院インターネット審議中継 (ビデオライブラリ)'
+    _TESTS = [{
+        'url': 'https://www.shugiintv.go.jp/jp/index.php?ex=VL&media_type=&deli_id=53846',
+        'info_dict': {
+            'id': '53846',
+            'title': 'ウクライナ大統領国会演説（オンライン）',
+            'release_date': '20220323',
+            'chapters': 'count:4',
+        }
+    }, {
+        'url': 'https://www.shugiintv.go.jp/en/index.php?ex=VL&media_type=&deli_id=53846',
+        'only_matching': True
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(
+            f'https://www.shugiintv.go.jp/jp/index.php?ex=VL&media_type=&deli_id={video_id}', video_id,
+            encoding='euc-jp')
+
+        m3u8_url = self._search_regex(
+            r'id="vtag_src_base_vod"\s*value="(http.+?\.m3u8)"', webpage, 'm3u8 url')
+        m3u8_url = re.sub(r'^http://', 'https://', m3u8_url)
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+            m3u8_url, video_id, ext='mp4')
+
+        title = self._html_search_regex(
+            (r'<td\s+align="left">(.+)\s*\(\d+分\)',
+             r'<TD.+?<IMG\s*src=".+?/spacer\.gif".+?height="15">(.+?)<IMG'), webpage, 'title', fatal=False)
+
+        release_date = _parse_japanese_date(self._html_search_regex(
+            r'開会日</td>\s*<td.+?/td>\s*<TD>(.+?)</TD>',
+            webpage, 'title', fatal=False))
+
+        chapters = []
+        for chp in re.finditer(r'(?i)<A\s+HREF="([^"]+?)"\s*class="play_vod">(?!<img)(.+)</[Aa]>', webpage):
+            chapters.append({
+                'title': clean_html(chp.group(2)).strip(),
+                'start_time': try_call(lambda: float(parse_qs(chp.group(1))['time'][0].strip())),
+            })
+        # NOTE: there are blanks at the first and the end of the videos,
+        # so getting/providing the video duration is not possible
+        # also, the exact end_time for the last chapter is unknown (we can get at most minutes of granularity)
+        last_tr = re.findall(r'(?s)<TR\s*class="s14_24">(.+?)</TR>', webpage)[-1]
+        if last_tr and chapters:
+            last_td = re.findall(r'<TD.+?</TD>', last_tr)[-1]
+            if last_td:
+                chapters[-1]['end_time'] = chapters[-1]['start_time'] + _parse_japanese_duration(clean_html(last_td))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'release_date': release_date,
+            'chapters': chapters,
+            'formats': formats,
+            'subtitles': subtitles,
+        }
+
+
+class SangiinInstructionIE(InfoExtractor):
+    _VALID_URL = r'^https?://www\.webtv\.sangiin\.go\.jp/webtv/index\.php'
+    IE_DESC = False  # this shouldn't be listed as a supported site
+
+    def _real_extract(self, url):
+        raise ExtractorError('Copy the link from the botton below the video description or player, and use the link to download. If there are no button in the frame, get the URL of the frame showing the video.', expected=True)
+
+
+class SangiinIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.webtv\.sangiin\.go\.jp/webtv/detail\.php\?sid=(?P<id>\d+)'
+    IE_DESC = '参議院インターネット審議中継 (archive)'
+
+    _TESTS = [{
+        'url': 'https://www.webtv.sangiin.go.jp/webtv/detail.php?sid=7052',
+        'info_dict': {
+            'id': '7052',
+            'title': '2022年10月7日 本会議',
+            'description': 'md5:0a5fed523f95c88105a0b0bf1dd71489',
+            'upload_date': '20221007',
+            'ext': 'mp4',
+        },
+    }, {
+        'url': 'https://www.webtv.sangiin.go.jp/webtv/detail.php?sid=7037',
+        'info_dict': {
+            'id': '7037',
+            'title': '2022年10月3日 開会式',
+            'upload_date': '20221003',
+            'ext': 'mp4',
+        },
+    }, {
+        'url': 'https://www.webtv.sangiin.go.jp/webtv/detail.php?sid=7076',
+        'info_dict': {
+            'id': '7076',
+            'title': '2022年10月27日 法務委員会',
+            'upload_date': '20221027',
+            'ext': 'mp4',
+            'is_live': True,
+        },
+        'skip': 'this live is turned into archive after it ends',
+    }, ]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        date = self._html_search_regex(
+            r'<dt[^>]*>\s*開会日\s*</dt>\s*<dd[^>]*>\s*(.+?)\s*</dd>', webpage,
+            'date', fatal=False)
+        upload_date = _parse_japanese_date(date)
+
+        title = self._html_search_regex(
+            r'<dt[^>]*>\s*会議名\s*</dt>\s*<dd[^>]*>\s*(.+?)\s*</dd>', webpage,
+            'date', fatal=False)
+
+        # some videos don't have the elements, so assume it's missing
+        description = self._html_search_regex(
+            r'会議の経過\s*</h3>\s*<span[^>]*>(.+?)</span>', webpage,
+            'description', default=None)
+
+        # this row appears only when it's livestream
+        is_live = bool(self._html_search_regex(
+            r'<dt[^>]*>\s*公報掲載時刻\s*</dt>\s*<dd[^>]*>\s*(.+?)\s*</dd>', webpage,
+            'is_live', default=None))
+
+        m3u8_url = self._search_regex(
+            r'var\s+videopath\s*=\s*(["\'])([^"\']+)\1', webpage,
+            'm3u8 url', group=2)
+
+        formats, subs = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, 'mp4')
+
+        return {
+            'id': video_id,
+            'title': join_nonempty(date, title, delim=' '),
+            'description': description,
+            'upload_date': upload_date,
+            'formats': formats,
+            'subtitles': subs,
+            '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/jeuxvideo.py

@@ -0,0 +1,52 @@
+from .common import InfoExtractor
+
+
+class JeuxVideoIE(InfoExtractor):
+    _WORKING = False
+    _ENABLED = None  # XXX: pass through to GenericIE
+    _VALID_URL = r'https?://.*?\.jeuxvideo\.com/.*/(.*?)\.htm'
+
+    _TESTS = [{
+        'url': 'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm',
+        'md5': '046e491afb32a8aaac1f44dd4ddd54ee',
+        'info_dict': {
+            'id': '114765',
+            'ext': 'mp4',
+            'title': 'Tearaway : GC 2013 : Tearaway nous présente ses papiers d\'identité',
+            'description': 'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.',
+        },
+    }, {
+        'url': 'http://www.jeuxvideo.com/videos/chroniques/434220/l-histoire-du-jeu-video-la-saturn.htm',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = self._match_valid_url(url)
+        title = mobj.group(1)
+        webpage = self._download_webpage(url, title)
+        title = self._html_search_meta('name', webpage) or self._og_search_title(webpage)
+        config_url = self._html_search_regex(
+            r'data-src(?:set-video)?="(/contenu/medias/video\.php.*?)"',
+            webpage, 'config URL')
+        config_url = 'http://www.jeuxvideo.com' + config_url
+
+        video_id = self._search_regex(
+            r'id=(\d+)',
+            config_url, 'video ID')
+
+        config = self._download_json(
+            config_url, title, 'Downloading JSON config')
+
+        formats = [{
+            'url': source['file'],
+            'format_id': source['label'],
+            'resolution': source['label'],
+        } for source in reversed(config['sources'])]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'description': self._og_search_description(webpage),
+            'thumbnail': config.get('image'),
+        }

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

@@ -0,0 +1,105 @@
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    js_to_json,
+    url_or_none,
+    urlencode_postdata,
+    urljoin,
+)
+from ..utils.traversal import traverse_obj
+
+
+class JioSaavnBaseIE(InfoExtractor):
+    def _extract_initial_data(self, url, audio_id):
+        webpage = self._download_webpage(url, audio_id)
+        return self._search_json(
+            r'window\.__INITIAL_DATA__\s*=', webpage,
+            'init json', audio_id, transform_source=js_to_json)
+
+
+class JioSaavnSongIE(JioSaavnBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?(?:jiosaavn\.com/song/[^/?#]+/|saavn\.com/s/song/(?:[^/?#]+/){3})(?P<id>[^/?#]+)'
+    _TESTS = [{
+        'url': 'https://www.jiosaavn.com/song/leja-re/OQsEfQFVUXk',
+        'md5': '3b84396d15ed9e083c3106f1fa589c04',
+        'info_dict': {
+            'id': 'OQsEfQFVUXk',
+            'ext': 'mp4',
+            'title': 'Leja Re',
+            'album': 'Leja Re',
+            'thumbnail': 'https://c.saavncdn.com/258/Leja-Re-Hindi-2018-20181124024539-500x500.jpg',
+            'duration': 205,
+            'view_count': int,
+            'release_year': 2018,
+        },
+    }, {
+        'url': 'https://www.saavn.com/s/song/hindi/Saathiya/O-Humdum-Suniyo-Re/KAMiazoCblU',
+        'only_matching': True,
+    }]
+
+    _VALID_BITRATES = ('16', '32', '64', '128', '320')
+
+    def _real_extract(self, url):
+        audio_id = self._match_id(url)
+        extract_bitrates = self._configuration_arg('bitrate', ['128', '320'], ie_key='JioSaavn')
+        if invalid_bitrates := [br for br in extract_bitrates if br not in self._VALID_BITRATES]:
+            raise ValueError(
+                f'Invalid bitrate(s): {", ".join(invalid_bitrates)}. '
+                + f'Valid bitrates are: {", ".join(self._VALID_BITRATES)}')
+
+        song_data = self._extract_initial_data(url, audio_id)['song']['song']
+        formats = []
+        for bitrate in extract_bitrates:
+            media_data = self._download_json(
+                'https://www.jiosaavn.com/api.php', audio_id, f'Downloading format info for {bitrate}',
+                fatal=False, data=urlencode_postdata({
+                    '__call': 'song.generateAuthToken',
+                    '_format': 'json',
+                    'bitrate': bitrate,
+                    'url': song_data['encrypted_media_url'],
+                }))
+            if not media_data.get('auth_url'):
+                self.report_warning(f'Unable to extract format info for {bitrate}')
+                continue
+            formats.append({
+                'url': media_data['auth_url'],
+                'ext': media_data.get('type'),
+                'format_id': bitrate,
+                'abr': int(bitrate),
+                'vcodec': 'none',
+            })
+
+        return {
+            'id': audio_id,
+            'formats': formats,
+            **traverse_obj(song_data, {
+                'title': ('title', 'text'),
+                'album': ('album', 'text'),
+                'thumbnail': ('image', 0, {url_or_none}),
+                'duration': ('duration', {int_or_none}),
+                'view_count': ('play_count', {int_or_none}),
+                'release_year': ('year', {int_or_none}),
+            }),
+        }
+
+
+class JioSaavnAlbumIE(JioSaavnBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?(?:jio)?saavn\.com/album/[^/?#]+/(?P<id>[^/?#]+)'
+    _TESTS = [{
+        'url': 'https://www.jiosaavn.com/album/96/buIOjYZDrNA_',
+        'info_dict': {
+            'id': 'buIOjYZDrNA_',
+            'title': '96',
+        },
+        'playlist_count': 10,
+    }]
+
+    def _real_extract(self, url):
+        album_id = self._match_id(url)
+        album_view = self._extract_initial_data(url, album_id)['albumView']
+
+        return self.playlist_from_matches(
+            traverse_obj(album_view, (
+                'modules', lambda _, x: x['key'] == 'list', 'data', ..., 'title', 'action', {str})),
+            album_id, traverse_obj(album_view, ('album', 'title', 'text', {str})), ie=JioSaavnSongIE,
+            getter=lambda x: urljoin('https://www.jiosaavn.com/', x))

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

@@ -0,0 +1,47 @@
+from .common import InfoExtractor
+from ..utils import clean_html, float_or_none, traverse_obj, try_call
+
+
+class JixieBaseIE(InfoExtractor):
+    """
+    API Reference:
+        https://jixie.atlassian.net/servicedesk/customer/portal/2/article/1339654214?src=-1456335525,
+        https://scripts.jixie.media/jxvideo.3.1.min.js
+    """
+
+    def _extract_data_from_jixie_id(self, display_id, video_id, webpage):
+        json_data = self._download_json(
+            'https://apidam.jixie.io/api/public/stream', display_id,
+            query={'metadata': 'full', 'video_id': video_id})['data']
+
+        formats, subtitles = [], {}
+        for stream in json_data['streams']:
+            if stream.get('type') == 'HLS':
+                fmt, sub = self._extract_m3u8_formats_and_subtitles(stream.get('url'), display_id, ext='mp4')
+                if json_data.get('drm'):
+                    for f in fmt:
+                        f['has_drm'] = True
+                formats.extend(fmt)
+                self._merge_subtitles(sub, target=subtitles)
+            else:
+                formats.append({
+                    'url': stream.get('url'),
+                    'width': stream.get('width'),
+                    'height': stream.get('height'),
+                    'ext': 'mp4',
+                })
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'formats': formats,
+            'subtitles': subtitles,
+            'title': json_data.get('title') or self._html_search_meta(['og:title', 'twitter:title'], webpage),
+            'description': (clean_html(traverse_obj(json_data, ('metadata', 'description')))
+                            or self._html_search_meta(['description', 'og:description', 'twitter:description'], webpage)),
+            'thumbnails': traverse_obj(json_data, ('metadata', 'thumbnails')),
+            'duration': float_or_none(traverse_obj(json_data, ('metadata', 'duration'))),
+            'tags': try_call(lambda: (json_data['metadata']['keywords'] or None).split(',')),
+            'categories': try_call(lambda: (json_data['metadata']['categories'] or None).split(',')),
+            'uploader_id': json_data.get('owner_id'),
+        }

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

@@ -0,0 +1,108 @@
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    format_field,
+    int_or_none,
+    js_to_json,
+    try_get,
+)
+
+
+class JojIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                    (?:
+                        joj:|
+                        https?://media\.joj\.sk/embed/
+                    )
+                    (?P<id>[^/?#^]+)
+                '''
+    _EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//media\.joj\.sk/embed/(?:(?!\1).)+)\1']
+    _TESTS = [{
+        'url': 'https://media.joj.sk/embed/a388ec4c-6019-4a4a-9312-b1bee194e932',
+        'info_dict': {
+            'id': 'a388ec4c-6019-4a4a-9312-b1bee194e932',
+            'ext': 'mp4',
+            'title': 'NOVÉ BÝVANIE',
+            'thumbnail': r're:^https?://.*?$',
+            'duration': 3118,
+        }
+    }, {
+        'url': 'https://media.joj.sk/embed/CSM0Na0l0p1',
+        'info_dict': {
+            'id': 'CSM0Na0l0p1',
+            'ext': 'mp4',
+            'height': 576,
+            'title': 'Extrémne rodiny 2 - POKRAČOVANIE (2012/04/09 21:30:00)',
+            'duration': 3937,
+            'thumbnail': r're:^https?://.*?$',
+        }
+    }, {
+        'url': 'https://media.joj.sk/embed/9i1cxv',
+        'only_matching': True,
+    }, {
+        'url': 'joj:a388ec4c-6019-4a4a-9312-b1bee194e932',
+        'only_matching': True,
+    }, {
+        'url': 'joj:9i1cxv',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            'https://media.joj.sk/embed/%s' % video_id, video_id)
+
+        title = (self._search_json(r'videoTitle\s*:', webpage, 'title', video_id,
+                                   contains_pattern=r'["\'].+["\']', default=None)
+                 or self._html_extract_title(webpage, default=None)
+                 or self._og_search_title(webpage))
+
+        bitrates = self._parse_json(
+            self._search_regex(
+                r'(?s)(?:src|bitrates)\s*=\s*({.+?});', webpage, 'bitrates',
+                default='{}'),
+            video_id, transform_source=js_to_json, fatal=False)
+
+        formats = []
+        for format_url in try_get(bitrates, lambda x: x['mp4'], list) or []:
+            if isinstance(format_url, compat_str):
+                height = self._search_regex(
+                    r'(\d+)[pP]|(pal)\.', format_url, 'height', default=None)
+                if height == 'pal':
+                    height = 576
+                formats.append({
+                    'url': format_url,
+                    'format_id': format_field(height, None, '%sp'),
+                    'height': int_or_none(height),
+                })
+        if not formats:
+            playlist = self._download_xml(
+                'https://media.joj.sk/services/Video.php?clip=%s' % video_id,
+                video_id)
+            for file_el in playlist.findall('./files/file'):
+                path = file_el.get('path')
+                if not path:
+                    continue
+                format_id = file_el.get('id') or file_el.get('label')
+                formats.append({
+                    'url': 'http://n16.joj.sk/storage/%s' % path.replace(
+                        'dat/', '', 1),
+                    'format_id': format_id,
+                    'height': int_or_none(self._search_regex(
+                        r'(\d+)[pP]', format_id or path, 'height',
+                        default=None)),
+                })
+
+        thumbnail = self._og_search_thumbnail(webpage)
+
+        duration = int_or_none(self._search_regex(
+            r'videoDuration\s*:\s*(\d+)', webpage, 'duration', fatal=False))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+        }