@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/duboku.py

@@ -0,0 +1,247 @@
+import base64
+import re
+import urllib.parse
+
+from .common import InfoExtractor
+from ..compat import compat_urlparse
+from ..utils import (
+    clean_html,
+    extract_attributes,
+    ExtractorError,
+    get_elements_by_class,
+    int_or_none,
+    js_to_json,
+    smuggle_url,
+    unescapeHTML,
+)
+
+
+def _get_elements_by_tag_and_attrib(html, tag=None, attribute=None, value=None, escape_value=True):
+    """Return the content of the tag with the specified attribute in the passed HTML document"""
+
+    if tag is None:
+        tag = '[a-zA-Z0-9:._-]+'
+    if attribute is None:
+        attribute = ''
+    else:
+        attribute = r'\s+(?P<attribute>%s)' % re.escape(attribute)
+    if value is None:
+        value = ''
+    else:
+        value = re.escape(value) if escape_value else value
+        value = '=[\'"]?(?P<value>%s)[\'"]?' % value
+
+    retlist = []
+    for m in re.finditer(r'''(?xs)
+        <(?P<tag>%s)
+         (?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'|))*?
+         %s%s
+         (?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'|))*?
+        \s*>
+        (?P<content>.*?)
+        </\1>
+    ''' % (tag, attribute, value), html):
+        retlist.append(m)
+
+    return retlist
+
+
+def _get_element_by_tag_and_attrib(html, tag=None, attribute=None, value=None, escape_value=True):
+    retval = _get_elements_by_tag_and_attrib(html, tag, attribute, value, escape_value)
+    return retval[0] if retval else None
+
+
+class DubokuIE(InfoExtractor):
+    IE_NAME = 'duboku'
+    IE_DESC = 'www.duboku.io'
+
+    _VALID_URL = r'(?:https?://[^/]+\.duboku\.io/vodplay/)(?P<id>[0-9]+-[0-9-]+)\.html.*'
+    _TESTS = [{
+        'url': 'https://w.duboku.io/vodplay/1575-1-1.html',
+        'info_dict': {
+            'id': '1575-1-1',
+            'ext': 'mp4',
+            'series': '白色月光',
+            'title': 'contains:白色月光',
+            'season_number': 1,
+            'episode_number': 1,
+            'season': 'Season 1',
+            'episode_id': '1',
+            'season_id': '1',
+            'episode': 'Episode 1',
+        },
+        'params': {
+            'skip_download': 'm3u8 download',
+        },
+    }, {
+        'url': 'https://w.duboku.io/vodplay/1588-1-1.html',
+        'info_dict': {
+            'id': '1588-1-1',
+            'ext': 'mp4',
+            'series': '亲爱的自己',
+            'title': 'contains:第1集',
+            'season_number': 1,
+            'episode_number': 1,
+            'episode': 'Episode 1',
+            'season': 'Season 1',
+            'episode_id': '1',
+            'season_id': '1',
+        },
+        'params': {
+            'skip_download': 'm3u8 download',
+        },
+    }]
+
+    _PLAYER_DATA_PATTERN = r'player_data\s*=\s*(\{\s*(.*)})\s*;?\s*</script'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        temp = video_id.split('-')
+        series_id = temp[0]
+        season_id = temp[1]
+        episode_id = temp[2]
+
+        webpage_url = 'https://w.duboku.io/vodplay/%s.html' % video_id
+        webpage_html = self._download_webpage(webpage_url, video_id)
+
+        # extract video url
+
+        player_data = self._search_regex(
+            self._PLAYER_DATA_PATTERN, webpage_html, 'player_data')
+        player_data = self._parse_json(player_data, video_id, js_to_json)
+
+        # extract title
+
+        temp = get_elements_by_class('title', webpage_html)
+        series_title = None
+        title = None
+        for html in temp:
+            mobj = re.search(r'<a\s+.*>(.*)</a>', html)
+            if mobj:
+                href = extract_attributes(mobj.group(0)).get('href')
+                if href:
+                    mobj1 = re.search(r'/(\d+)\.html', href)
+                    if mobj1 and mobj1.group(1) == series_id:
+                        series_title = clean_html(mobj.group(0))
+                        series_title = re.sub(r'[\s\r\n\t]+', ' ', series_title)
+                        title = clean_html(html)
+                        title = re.sub(r'[\s\r\n\t]+', ' ', title)
+                        break
+
+        data_url = player_data.get('url')
+        if not data_url:
+            raise ExtractorError('Cannot find url in player_data')
+        player_encrypt = player_data.get('encrypt')
+        if player_encrypt == 1:
+            data_url = urllib.parse.unquote(data_url)
+        elif player_encrypt == 2:
+            data_url = urllib.parse.unquote(base64.b64decode(data_url).decode('ascii'))
+
+        # if it is an embedded iframe, maybe it's an external source
+        headers = {'Referer': webpage_url}
+        if player_data.get('from') == 'iframe':
+            # use _type url_transparent to retain the meaningful details
+            # of the video.
+            return {
+                '_type': 'url_transparent',
+                'url': smuggle_url(data_url, {'referer': webpage_url}),
+                'id': video_id,
+                'title': title,
+                'series': series_title,
+                'season_number': int_or_none(season_id),
+                'season_id': season_id,
+                'episode_number': int_or_none(episode_id),
+                'episode_id': episode_id,
+            }
+
+        formats = self._extract_m3u8_formats(data_url, video_id, 'mp4', headers=headers)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'series': series_title,
+            'season_number': int_or_none(season_id),
+            'season_id': season_id,
+            'episode_number': int_or_none(episode_id),
+            'episode_id': episode_id,
+            'formats': formats,
+            'http_headers': headers
+        }
+
+
+class DubokuPlaylistIE(InfoExtractor):
+    IE_NAME = 'duboku:list'
+    IE_DESC = 'www.duboku.io entire series'
+
+    _VALID_URL = r'(?:https?://[^/]+\.duboku\.io/voddetail/)(?P<id>[0-9]+)\.html.*'
+    _TESTS = [{
+        'url': 'https://w.duboku.io/voddetail/1575.html',
+        'info_dict': {
+            'id': 'startswith:1575',
+            'title': '白色月光',
+        },
+        'playlist_count': 12,
+    }, {
+        'url': 'https://w.duboku.io/voddetail/1554.html',
+        'info_dict': {
+            'id': 'startswith:1554',
+            'title': '以家人之名',
+        },
+        'playlist_mincount': 30,
+    }]
+
+    def _real_extract(self, url):
+        mobj = self._match_valid_url(url)
+        if mobj is None:
+            raise ExtractorError('Invalid URL: %s' % url)
+        series_id = mobj.group('id')
+        fragment = compat_urlparse.urlparse(url).fragment
+
+        webpage_url = 'https://w.duboku.io/voddetail/%s.html' % series_id
+        webpage_html = self._download_webpage(webpage_url, series_id)
+
+        # extract title
+
+        title = _get_element_by_tag_and_attrib(webpage_html, 'h1', 'class', 'title')
+        title = unescapeHTML(title.group('content')) if title else None
+        if not title:
+            title = self._html_search_meta('keywords', webpage_html)
+        if not title:
+            title = _get_element_by_tag_and_attrib(webpage_html, 'title')
+            title = unescapeHTML(title.group('content')) if title else None
+
+        # extract playlists
+
+        playlists = {}
+        for div in _get_elements_by_tag_and_attrib(
+                webpage_html, attribute='id', value='playlist\\d+', escape_value=False):
+            playlist_id = div.group('value')
+            playlist = []
+            for a in _get_elements_by_tag_and_attrib(
+                    div.group('content'), 'a', 'href', value='[^\'"]+?', escape_value=False):
+                playlist.append({
+                    'href': unescapeHTML(a.group('value')),
+                    'title': unescapeHTML(a.group('content'))
+                })
+            playlists[playlist_id] = playlist
+
+        # select the specified playlist if url fragment exists
+        playlist = None
+        playlist_id = None
+        if fragment:
+            playlist = playlists.get(fragment)
+            playlist_id = fragment
+        else:
+            first = next(iter(playlists.items()), None)
+            if first:
+                (playlist_id, playlist) = first
+        if not playlist:
+            raise ExtractorError(
+                'Cannot find %s' % fragment if fragment else 'Cannot extract playlist')
+
+        # return url results
+        return self.playlist_result([
+            self.url_result(
+                compat_urlparse.urljoin('https://w.duboku.io', x['href']),
+                ie=DubokuIE.ie_key(), video_title=x.get('title'))
+            for x in playlist], series_id + '#' + playlist_id, title)

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

@@ -0,0 +1,114 @@
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    int_or_none,
+    qualities,
+)
+
+
+class DumpertIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+        (?P<protocol>https?)://(?:(?:www|legacy)\.)?dumpert\.nl/(?:
+            (?:mediabase|embed|item)/|
+            [^#]*[?&]selectedId=
+        )(?P<id>[0-9]+[/_][0-9a-zA-Z]+)'''
+    _TESTS = [{
+        'url': 'https://www.dumpert.nl/item/6646981_951bc60f',
+        'md5': '1b9318d7d5054e7dcb9dc7654f21d643',
+        'info_dict': {
+            'id': '6646981/951bc60f',
+            'ext': 'mp4',
+            'title': 'Ik heb nieuws voor je',
+            'description': 'Niet schrikken hoor',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 9,
+            'view_count': int,
+            'like_count': int,
+        }
+    }, {
+        'url': 'https://www.dumpert.nl/embed/6675421_dc440fe7',
+        'only_matching': True,
+    }, {
+        'url': 'http://legacy.dumpert.nl/mediabase/6646981/951bc60f',
+        'only_matching': True,
+    }, {
+        'url': 'http://legacy.dumpert.nl/embed/6675421/dc440fe7',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.dumpert.nl/item/100031688_b317a185',
+        'info_dict': {
+            'id': '100031688/b317a185',
+            'ext': 'mp4',
+            'title': 'Epic schijnbeweging',
+            'description': '<p>Die zag je niet eh</p>',
+            'thumbnail': r're:^https?://.*\.(?:jpg|png)$',
+            'duration': 12,
+            'view_count': int,
+            'like_count': int,
+        },
+        'params': {'skip_download': 'm3u8'}
+    }, {
+        'url': 'https://www.dumpert.nl/toppers?selectedId=100031688_b317a185',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.dumpert.nl/latest?selectedId=100031688_b317a185',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.dumpert.nl/?selectedId=100031688_b317a185',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.dumpert.nl/toppers/dag?selectedId=100086074_f5cef3ac',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url).replace('_', '/')
+        item = self._download_json(
+            'http://api-live.dumpert.nl/mobile_api/json/info/' + video_id.replace('/', '_'),
+            video_id)['items'][0]
+        title = item['title']
+        media = next(m for m in item['media'] if m.get('mediatype') == 'VIDEO')
+
+        quality = qualities(['flv', 'mobile', 'tablet', '720p', '1080p'])
+        formats = []
+        for variant in media.get('variants', []):
+            uri = variant.get('uri')
+            if not uri:
+                continue
+            version = variant.get('version')
+            preference = quality(version)
+            if determine_ext(uri) == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    uri, video_id, 'mp4', m3u8_id=version, quality=preference))
+            else:
+                formats.append({
+                    'url': uri,
+                    'format_id': version,
+                    'quality': preference,
+                })
+
+        thumbnails = []
+        stills = item.get('stills') or {}
+        for t in ('thumb', 'still'):
+            for s in ('', '-medium', '-large'):
+                still_id = t + s
+                still_url = stills.get(still_id)
+                if not still_url:
+                    continue
+                thumbnails.append({
+                    'id': still_id,
+                    'url': still_url,
+                })
+
+        stats = item.get('stats') or {}
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': item.get('description'),
+            'thumbnails': thumbnails,
+            'formats': formats,
+            'duration': int_or_none(media.get('duration')),
+            'like_count': int_or_none(stats.get('kudos_total')),
+            'view_count': int_or_none(stats.get('views_total')),
+        }

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

@@ -0,0 +1,104 @@
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    extract_attributes,
+    get_element_text_and_html_by_tag,
+    int_or_none,
+    join_nonempty,
+    str_or_none,
+    try_call,
+    unified_timestamp,
+)
+from ..utils.traversal import traverse_obj
+
+
+class DuoplayIE(InfoExtractor):
+    _VALID_URL = r'https?://duoplay\.ee/(?P<id>\d+)/[\w-]+/?(?:\?(?:[^#]+&)?ep=(?P<ep>\d+))?'
+    _TESTS = [{
+        'note': 'Siberi võmm S02E12',
+        'url': 'https://duoplay.ee/4312/siberi-vomm?ep=24',
+        'md5': '1ff59d535310ac9c5cf5f287d8f91b2d',
+        'info_dict': {
+            'id': '4312_24',
+            'ext': 'mp4',
+            'title': 'Operatsioon "Öö"',
+            'thumbnail': r're:https://.+\.jpg(?:\?c=\d+)?$',
+            'description': 'md5:8ef98f38569d6b8b78f3d350ccc6ade8',
+            'upload_date': '20170523',
+            'timestamp': 1495567800,
+            'series': 'Siberi võmm',
+            'series_id': '4312',
+            'season': 'Season 2',
+            'season_number': 2,
+            'episode': 'Operatsioon "Öö"',
+            'episode_number': 12,
+            'episode_id': '24',
+        },
+    }, {
+        'note': 'Empty title',
+        'url': 'https://duoplay.ee/17/uhikarotid?ep=14',
+        'md5': '6aca68be71112314738dd17cced7f8bf',
+        'info_dict': {
+            'id': '17_14',
+            'ext': 'mp4',
+            'title': 'Ühikarotid',
+            'thumbnail': r're:https://.+\.jpg(?:\?c=\d+)?$',
+            'description': 'md5:4719b418e058c209def41d48b601276e',
+            'upload_date': '20100916',
+            'timestamp': 1284661800,
+            'series': 'Ühikarotid',
+            'series_id': '17',
+            'season': 'Season 2',
+            'season_number': 2,
+            'episode_id': '14',
+            'release_year': 2010,
+        },
+    }, {
+        'note': 'Movie without expiry',
+        'url': 'https://duoplay.ee/5501/pilvede-all.-neljas-ode',
+        'md5': '7abf63d773a49ef7c39f2c127842b8fd',
+        'info_dict': {
+            'id': '5501',
+            'ext': 'mp4',
+            'title': 'Pilvede all. Neljas õde',
+            'thumbnail': r're:https://.+\.jpg(?:\?c=\d+)?$',
+            'description': 'md5:d86a70f8f31e82c369d4d4f4c79b1279',
+            'cast': 'count:9',
+            'upload_date': '20221214',
+            'timestamp': 1671054000,
+            'release_year': 2018,
+        },
+    }]
+
+    def _real_extract(self, url):
+        telecast_id, episode = self._match_valid_url(url).group('id', 'ep')
+        video_id = join_nonempty(telecast_id, episode, delim='_')
+        webpage = self._download_webpage(url, video_id)
+        video_player = try_call(lambda: extract_attributes(
+            get_element_text_and_html_by_tag('video-player', webpage)[1]))
+        if not video_player or not video_player.get('manifest-url'):
+            raise ExtractorError('No video found', expected=True)
+
+        episode_attr = self._parse_json(video_player.get(':episode') or '', video_id, fatal=False) or {}
+
+        return {
+            'id': video_id,
+            'formats': self._extract_m3u8_formats(video_player['manifest-url'], video_id, 'mp4'),
+            **traverse_obj(episode_attr, {
+                'title': 'title',
+                'description': 'synopsis',
+                'thumbnail': ('images', 'original'),
+                'timestamp': ('airtime', {lambda x: unified_timestamp(x + ' +0200')}),
+                'cast': ('cast', {lambda x: x.split(', ')}),
+                'release_year': ('year', {int_or_none}),
+            }),
+            **(traverse_obj(episode_attr, {
+                'title': (None, ('subtitle', ('episode_nr', {lambda x: f'Episode {x}' if x else None}))),
+                'series': 'title',
+                'series_id': ('telecast_id', {str_or_none}),
+                'season_number': ('season_id', {int_or_none}),
+                'episode': 'subtitle',
+                'episode_number': ('episode_nr', {int_or_none}),
+                'episode_id': ('episode_id', {str_or_none}),
+            }, get_all=False) if episode_attr.get('category') != 'movies' else {}),
+        }

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

@@ -0,0 +1,177 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    ExtractorError,
+    int_or_none,
+    join_nonempty,
+    js_to_json,
+    mimetype2ext,
+    try_get,
+    unescapeHTML,
+    parse_iso8601,
+)
+
+
+class DVTVIE(InfoExtractor):
+    IE_NAME = 'dvtv'
+    IE_DESC = 'http://video.aktualne.cz/'
+    _VALID_URL = r'https?://video\.aktualne\.cz/(?:[^/]+/)+r~(?P<id>[0-9a-f]{32})'
+    _TESTS = [{
+        'url': 'http://video.aktualne.cz/dvtv/vondra-o-ceskem-stoleti-pri-pohledu-na-havla-mi-bylo-trapne/r~e5efe9ca855511e4833a0025900fea04/',
+        'md5': '67cb83e4a955d36e1b5d31993134a0c2',
+        'info_dict': {
+            'id': 'dc0768de855511e49e4b0025900fea04',
+            'ext': 'mp4',
+            'title': 'Vondra o Českém století: Při pohledu na Havla mi bylo trapně',
+            'duration': 1484,
+            'upload_date': '20141217',
+            'timestamp': 1418792400,
+        }
+    }, {
+        'url': 'http://video.aktualne.cz/dvtv/dvtv-16-12-2014-utok-talibanu-boj-o-kliniku-uprchlici/r~973eb3bc854e11e498be002590604f2e/',
+        'info_dict': {
+            'title': r'DVTV 16. 12. 2014: útok Talibanu, boj o kliniku, uprchlíci',
+            'id': '973eb3bc854e11e498be002590604f2e',
+        },
+        'playlist': [{
+            'md5': 'da7ca6be4935532241fa9520b3ad91e4',
+            'info_dict': {
+                'id': 'b0b40906854d11e4bdad0025900fea04',
+                'ext': 'mp4',
+                'title': 'Drtinová Veselovský TV 16. 12. 2014: Témata dne',
+                'description': 'md5:0916925dea8e30fe84222582280b47a0',
+                'timestamp': 1418760010,
+                'upload_date': '20141216',
+            }
+        }, {
+            'md5': '5f7652a08b05009c1292317b449ffea2',
+            'info_dict': {
+                'id': '420ad9ec854a11e4bdad0025900fea04',
+                'ext': 'mp4',
+                'title': 'Školní masakr možná změní boj s Talibanem, říká novinářka',
+                'description': 'md5:ff2f9f6de73c73d7cef4f756c1c1af42',
+                'timestamp': 1418760010,
+                'upload_date': '20141216',
+            }
+        }, {
+            'md5': '498eb9dfa97169f409126c617e2a3d64',
+            'info_dict': {
+                'id': '95d35580846a11e4b6d20025900fea04',
+                'ext': 'mp4',
+                'title': 'Boj o kliniku: Veřejný zájem, nebo právo na majetek?',
+                'description': 'md5:889fe610a70fee5511dc3326a089188e',
+                'timestamp': 1418760010,
+                'upload_date': '20141216',
+            }
+        }, {
+            'md5': 'b8dc6b744844032dab6ba3781a7274b9',
+            'info_dict': {
+                'id': '6fe14d66853511e4833a0025900fea04',
+                'ext': 'mp4',
+                'title': 'Pánek: Odmítání syrských uprchlíků je ostudou české vlády',
+                'description': 'md5:544f86de6d20c4815bea11bf2ac3004f',
+                'timestamp': 1418760010,
+                'upload_date': '20141216',
+            }
+        }],
+    }, {
+        'url': 'https://video.aktualne.cz/dvtv/zeman-si-jen-leci-mindraky-sobotku-nenavidi-a-babis-se-mu-te/r~960cdb3a365a11e7a83b0025900fea04/',
+        'md5': 'f8efe9656017da948369aa099788c8ea',
+        'info_dict': {
+            'id': '3c496fec365911e7a6500025900fea04',
+            'ext': 'mp4',
+            'title': 'Zeman si jen léčí mindráky, Sobotku nenávidí a Babiš se mu teď hodí, tvrdí Kmenta',
+            'duration': 1103,
+            'upload_date': '20170511',
+            'timestamp': 1494514200,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://video.aktualne.cz/v-cechach-poprve-zazni-zelenkova-zrestaurovana-mse/r~45b4b00483ec11e4883b002590604f2e/',
+        'only_matching': True,
+    }, {
+        # Test live stream video (liveStarter) parsing
+        'url': 'https://video.aktualne.cz/dvtv/zive-mistryne-sveta-eva-samkova-po-navratu-ze-sampionatu/r~182654c2288811e990fd0cc47ab5f122/',
+        'md5': '2e552e483f2414851ca50467054f9d5d',
+        'info_dict': {
+            'id': '8d116360288011e98c840cc47ab5f122',
+            'ext': 'mp4',
+            'title': 'Živě: Mistryně světa Eva Samková po návratu ze šampionátu',
+            'upload_date': '20190204',
+            'timestamp': 1549289591,
+        },
+        'params': {
+            # Video content is no longer available
+            'skip_download': True,
+        },
+    }]
+
+    def _parse_video_metadata(self, js, video_id, timestamp):
+        data = self._parse_json(js, video_id, transform_source=js_to_json)
+        title = unescapeHTML(data['title'])
+
+        live_starter = try_get(data, lambda x: x['plugins']['liveStarter'], dict)
+        if live_starter:
+            data.update(live_starter)
+
+        formats = []
+        for tracks in data.get('tracks', {}).values():
+            for video in tracks:
+                video_url = video.get('src')
+                if not video_url:
+                    continue
+                video_type = video.get('type')
+                ext = determine_ext(video_url, mimetype2ext(video_type))
+                if video_type == 'application/vnd.apple.mpegurl' or ext == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        video_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                        m3u8_id='hls', fatal=False))
+                elif video_type == 'application/dash+xml' or ext == 'mpd':
+                    formats.extend(self._extract_mpd_formats(
+                        video_url, video_id, mpd_id='dash', fatal=False))
+                else:
+                    label = video.get('label')
+                    height = self._search_regex(
+                        r'^(\d+)[pP]', label or '', 'height', default=None)
+                    formats.append({
+                        'url': video_url,
+                        'format_id': join_nonempty('http', ext, label),
+                        'height': int_or_none(height),
+                    })
+
+        return {
+            'id': data.get('mediaid') or video_id,
+            'title': title,
+            'description': data.get('description'),
+            'thumbnail': data.get('image'),
+            'duration': int_or_none(data.get('duration')),
+            'timestamp': int_or_none(timestamp),
+            'formats': formats
+        }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        timestamp = parse_iso8601(self._html_search_meta(
+            'article:published_time', webpage, 'published time', default=None))
+
+        items = re.findall(r'(?s)playlist\.push\(({.+?})\);', webpage)
+        if items:
+            return self.playlist_result(
+                [self._parse_video_metadata(i, video_id, timestamp) for i in items],
+                video_id, self._html_search_meta('twitter:title', webpage))
+
+        item = self._search_regex(
+            r'(?s)BBXPlayer\.setup\((.+?)\);',
+            webpage, 'video', default=None)
+        if item:
+            # remove function calls (ex. htmldeentitize)
+            # TODO this should be fixed in a general way in the js_to_json
+            item = re.sub(r'\w+?\((.+)\)', r'\1', item)
+            return self._parse_video_metadata(item, video_id, timestamp)
+
+        raise ExtractorError('Could not find neither video nor playlist')