@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/wppilot.py

@@ -0,0 +1,173 @@
+from .common import InfoExtractor
+from ..utils import (
+    try_get,
+    ExtractorError,
+)
+
+import json
+import random
+import re
+
+
+class WPPilotBaseIE(InfoExtractor):
+    _VIDEO_URL = 'https://pilot.wp.pl/api/v1/channel/%s'
+    _VIDEO_GUEST_URL = 'https://pilot.wp.pl/api/v1/guest/channel/%s'
+
+    _HEADERS_WEB = {
+        'Content-Type': 'application/json; charset=UTF-8',
+        'Referer': 'https://pilot.wp.pl/tv/',
+    }
+
+    def _get_channel_list(self, cache=True):
+        if cache is True:
+            cache_res = self.cache.load('wppilot', 'channel-list')
+            if cache_res:
+                return cache_res, True
+        webpage = self._download_webpage('https://pilot.wp.pl/tv/', None, 'Downloading webpage')
+        page_data_base_url = self._search_regex(
+            r'<script src="(https://wp-pilot-gatsby\.wpcdn\.pl/v[\d.-]+/desktop)',
+            webpage, 'gatsby build version') + '/page-data'
+        page_data = self._download_json(f'{page_data_base_url}/tv/page-data.json', None, 'Downloading page data')
+        for qhash in page_data['staticQueryHashes']:
+            qhash_content = self._download_json(
+                f'{page_data_base_url}/sq/d/{qhash}.json', None,
+                'Searching for channel list')
+            channel_list = try_get(qhash_content, lambda x: x['data']['allChannels']['nodes'])
+            if channel_list is None:
+                continue
+            self.cache.store('wppilot', 'channel-list', channel_list)
+            return channel_list, False
+        raise ExtractorError('Unable to find the channel list')
+
+    def _parse_channel(self, chan):
+        return {
+            'id': str(chan['id']),
+            'title': chan['name'],
+            'is_live': True,
+            'thumbnails': [{
+                'id': key,
+                'url': chan[key],
+            } for key in ('thumbnail', 'thumbnail_mobile', 'icon') if chan.get(key)],
+        }
+
+
+class WPPilotIE(WPPilotBaseIE):
+    _VALID_URL = r'(?:https?://pilot\.wp\.pl/tv/?#|wppilot:)(?P<id>[a-z\d-]+)'
+    IE_NAME = 'wppilot'
+
+    _TESTS = [{
+        'url': 'https://pilot.wp.pl/tv/#telewizja-wp-hd',
+        'info_dict': {
+            'id': '158',
+            'ext': 'mp4',
+            'title': 'Telewizja WP HD',
+        },
+        'params': {
+            'format': 'bestvideo',
+        },
+    }, {
+        # audio only
+        'url': 'https://pilot.wp.pl/tv/#radio-nowy-swiat',
+        'info_dict': {
+            'id': '238',
+            'ext': 'm4a',
+            'title': 'Radio Nowy Świat',
+        },
+        'params': {
+            'format': 'bestaudio',
+        },
+    }, {
+        'url': 'wppilot:9',
+        'only_matching': True,
+    }]
+
+    def _get_channel(self, id_or_slug):
+        video_list, is_cached = self._get_channel_list(cache=True)
+        key = 'id' if re.match(r'^\d+$', id_or_slug) else 'slug'
+        for video in video_list:
+            if video.get(key) == id_or_slug:
+                return self._parse_channel(video)
+        # if cached channel not found, download and retry
+        if is_cached:
+            video_list, _ = self._get_channel_list(cache=False)
+            for video in video_list:
+                if video.get(key) == id_or_slug:
+                    return self._parse_channel(video)
+        raise ExtractorError('Channel not found')
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        channel = self._get_channel(video_id)
+        video_id = str(channel['id'])
+
+        is_authorized = next((c for c in self.cookiejar if c.name == 'netviapisessid'), None)
+        # cookies starting with "g:" are assigned to guests
+        is_authorized = True if is_authorized is not None and not is_authorized.value.startswith('g:') else False
+
+        video = self._download_json(
+            (self._VIDEO_URL if is_authorized else self._VIDEO_GUEST_URL) % video_id,
+            video_id, query={
+                'device_type': 'web',
+            }, headers=self._HEADERS_WEB,
+            expected_status=(200, 422))
+
+        stream_token = try_get(video, lambda x: x['_meta']['error']['info']['stream_token'])
+        if stream_token:
+            close = self._download_json(
+                'https://pilot.wp.pl/api/v1/channels/close', video_id,
+                'Invalidating previous stream session', headers=self._HEADERS_WEB,
+                data=json.dumps({
+                    'channelId': video_id,
+                    't': stream_token,
+                }).encode('utf-8'))
+            if try_get(close, lambda x: x['data']['status']) == 'ok':
+                return self.url_result(url, ie=WPPilotIE.ie_key())
+
+        formats = []
+
+        for fmt in video['data']['stream_channel']['streams']:
+            # live DASH does not work for now
+            # if fmt['type'] == 'dash@live:abr':
+            #     formats.extend(
+            #         self._extract_mpd_formats(
+            #             random.choice(fmt['url']), video_id))
+            if fmt['type'] == 'hls@live:abr':
+                formats.extend(
+                    self._extract_m3u8_formats(
+                        random.choice(fmt['url']),
+                        video_id, live=True))
+
+        channel['formats'] = formats
+        return channel
+
+
+class WPPilotChannelsIE(WPPilotBaseIE):
+    _VALID_URL = r'(?:https?://pilot\.wp\.pl/(?:tv/?)?(?:\?[^#]*)?#?|wppilot:)$'
+    IE_NAME = 'wppilot:channels'
+
+    _TESTS = [{
+        'url': 'wppilot:',
+        'info_dict': {
+            'id': 'wppilot',
+            'title': 'WP Pilot',
+        },
+        'playlist_mincount': 100,
+    }, {
+        'url': 'https://pilot.wp.pl/',
+        'only_matching': True,
+    }]
+
+    def _entries(self):
+        channel_list, _ = self._get_channel_list()
+        for chan in channel_list:
+            entry = self._parse_channel(chan)
+            entry.update({
+                '_type': 'url_transparent',
+                'url': f'wppilot:{chan["id"]}',
+                'ie_key': WPPilotIE.ie_key(),
+            })
+            yield entry
+
+    def _real_extract(self, url):
+        return self.playlist_result(self._entries(), 'wppilot', 'WP Pilot')

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

@@ -0,0 +1,304 @@
+import base64
+import binascii
+import json
+import time
+import uuid
+
+from .common import InfoExtractor
+from ..dependencies import Cryptodome
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    jwt_decode_hs256,
+    traverse_obj,
+    try_call,
+    url_or_none,
+    urlencode_postdata,
+    variadic,
+)
+
+
+class WrestleUniverseBaseIE(InfoExtractor):
+    _NETRC_MACHINE = 'wrestleuniverse'
+    _VALID_URL_TMPL = r'https?://(?:www\.)?wrestle-universe\.com/(?:(?P<lang>\w{2})/)?%s/(?P<id>\w+)'
+    _API_HOST = 'api.wrestle-universe.com'
+    _API_PATH = None
+    _REAL_TOKEN = None
+    _TOKEN_EXPIRY = None
+    _REFRESH_TOKEN = None
+    _DEVICE_ID = None
+    _LOGIN_QUERY = {'key': 'AIzaSyCaRPBsDQYVDUWWBXjsTrHESi2r_F3RAdA'}
+    _LOGIN_HEADERS = {
+        'Accept': '*/*',
+        'Content-Type': 'application/json',
+        'X-Client-Version': 'Chrome/JsCore/9.9.4/FirebaseCore-web',
+        'X-Firebase-gmpid': '1:307308870738:web:820f38fe5150c8976e338b',
+        'Referer': 'https://www.wrestle-universe.com/',
+        'Origin': 'https://www.wrestle-universe.com',
+    }
+
+    @property
+    def _TOKEN(self):
+        if not self._REAL_TOKEN or not self._TOKEN_EXPIRY:
+            token = try_call(lambda: self._get_cookies('https://www.wrestle-universe.com/')['token'].value)
+            if not token and not self._REFRESH_TOKEN:
+                self.raise_login_required()
+            self._TOKEN = token
+
+        if not self._REAL_TOKEN or self._TOKEN_EXPIRY <= int(time.time()):
+            if not self._REFRESH_TOKEN:
+                raise ExtractorError(
+                    'Expired token. Refresh your cookies in browser and try again', expected=True)
+            self._refresh_token()
+
+        return self._REAL_TOKEN
+
+    @_TOKEN.setter
+    def _TOKEN(self, value):
+        self._REAL_TOKEN = value
+
+        expiry = traverse_obj(value, ({jwt_decode_hs256}, 'exp', {int_or_none}))
+        if not expiry:
+            raise ExtractorError('There was a problem with the auth token')
+        self._TOKEN_EXPIRY = expiry
+
+    def _perform_login(self, username, password):
+        login = self._download_json(
+            'https://identitytoolkit.googleapis.com/v1/accounts:signInWithPassword', None,
+            'Logging in', query=self._LOGIN_QUERY, headers=self._LOGIN_HEADERS, data=json.dumps({
+                'returnSecureToken': True,
+                'email': username,
+                'password': password,
+            }, separators=(',', ':')).encode(), expected_status=400)
+        token = traverse_obj(login, ('idToken', {str}))
+        if not token:
+            raise ExtractorError(
+                f'Unable to log in: {traverse_obj(login, ("error", "message"))}', expected=True)
+        self._REFRESH_TOKEN = traverse_obj(login, ('refreshToken', {str}))
+        if not self._REFRESH_TOKEN:
+            self.report_warning('No refresh token was granted')
+        self._TOKEN = token
+
+    def _real_initialize(self):
+        if self._DEVICE_ID:
+            return
+
+        self._DEVICE_ID = self._configuration_arg('device_id', [None], ie_key=self._NETRC_MACHINE)[0]
+        if not self._DEVICE_ID:
+            self._DEVICE_ID = self.cache.load(self._NETRC_MACHINE, 'device_id')
+            if self._DEVICE_ID:
+                return
+            self._DEVICE_ID = str(uuid.uuid4())
+
+        self.cache.store(self._NETRC_MACHINE, 'device_id', self._DEVICE_ID)
+
+    def _refresh_token(self):
+        refresh = self._download_json(
+            'https://securetoken.googleapis.com/v1/token', None, 'Refreshing token',
+            query=self._LOGIN_QUERY, data=urlencode_postdata({
+                'grant_type': 'refresh_token',
+                'refresh_token': self._REFRESH_TOKEN,
+            }), headers={
+                **self._LOGIN_HEADERS,
+                'Content-Type': 'application/x-www-form-urlencoded',
+            })
+        if traverse_obj(refresh, ('refresh_token', {str})):
+            self._REFRESH_TOKEN = refresh['refresh_token']
+        token = traverse_obj(refresh, 'access_token', 'id_token', expected_type=str)
+        if not token:
+            raise ExtractorError('No auth token returned from refresh request')
+        self._TOKEN = token
+
+    def _call_api(self, video_id, param='', msg='API', auth=True, data=None, query={}, fatal=True):
+        headers = {'CA-CID': ''}
+        if data:
+            headers['Content-Type'] = 'application/json;charset=utf-8'
+            data = json.dumps(data, separators=(',', ':')).encode()
+        if auth and self._TOKEN:
+            headers['Authorization'] = f'Bearer {self._TOKEN}'
+        return self._download_json(
+            f'https://{self._API_HOST}/v1/{self._API_PATH}/{video_id}{param}', video_id,
+            note=f'Downloading {msg} JSON', errnote=f'Failed to download {msg} JSON',
+            data=data, headers=headers, query=query, fatal=fatal)
+
+    def _call_encrypted_api(self, video_id, param='', msg='API', data={}, query={}, fatal=True):
+        if not Cryptodome.RSA:
+            raise ExtractorError('pycryptodomex not found. Please install', expected=True)
+        private_key = Cryptodome.RSA.generate(2048)
+        cipher = Cryptodome.PKCS1_OAEP.new(private_key, hashAlgo=Cryptodome.SHA1)
+
+        def decrypt(data):
+            if not data:
+                return None
+            try:
+                return cipher.decrypt(base64.b64decode(data)).decode()
+            except (ValueError, binascii.Error) as e:
+                raise ExtractorError(f'Could not decrypt data: {e}')
+
+        token = base64.b64encode(private_key.public_key().export_key('DER')).decode()
+        api_json = self._call_api(video_id, param, msg, data={
+            'deviceId': self._DEVICE_ID,
+            'token': token,
+            **data,
+        }, query=query, fatal=fatal)
+        return api_json, decrypt
+
+    def _download_metadata(self, url, video_id, lang, props_keys):
+        metadata = self._call_api(video_id, msg='metadata', query={'al': lang or 'ja'}, auth=False, fatal=False)
+        if not metadata:
+            webpage = self._download_webpage(url, video_id)
+            nextjs_data = self._search_nextjs_data(webpage, video_id)
+            metadata = traverse_obj(nextjs_data, (
+                'props', 'pageProps', *variadic(props_keys, (str, bytes, dict, set)), {dict})) or {}
+        return metadata
+
+    def _get_formats(self, data, path, video_id=None):
+        hls_url = traverse_obj(data, path, get_all=False)
+        if not hls_url and not data.get('canWatch'):
+            self.raise_no_formats(
+                'This account does not have access to the requested content', expected=True)
+        elif not hls_url:
+            self.raise_no_formats('No supported formats found')
+        return self._extract_m3u8_formats(hls_url, video_id, 'mp4', m3u8_id='hls', live=True)
+
+
+class WrestleUniverseVODIE(WrestleUniverseBaseIE):
+    _VALID_URL = WrestleUniverseBaseIE._VALID_URL_TMPL % 'videos'
+    _TESTS = [{
+        'url': 'https://www.wrestle-universe.com/en/videos/dp8mpjmcKfxzUhEHM2uFws',
+        'info_dict': {
+            'id': 'dp8mpjmcKfxzUhEHM2uFws',
+            'ext': 'mp4',
+            'title': 'The 3rd “Futari wa Princess” Max Heart Tournament',
+            'description': 'md5:318d5061e944797fbbb81d5c7dd00bf5',
+            'location': '埼玉・春日部ふれあいキューブ',
+            'channel': 'tjpw',
+            'duration': 7119,
+            'timestamp': 1674979200,
+            'upload_date': '20230129',
+            'thumbnail': 'https://image.asset.wrestle-universe.com/8FjD67P8rZc446RBQs5RBN/8FjD67P8rZc446RBQs5RBN',
+            'chapters': 'count:7',
+            'cast': 'count:21',
+        },
+        'params': {
+            'skip_download': 'm3u8',
+        },
+    }]
+
+    _API_PATH = 'videoEpisodes'
+
+    def _real_extract(self, url):
+        lang, video_id = self._match_valid_url(url).group('lang', 'id')
+        metadata = self._download_metadata(url, video_id, lang, 'videoEpisodeFallbackData')
+        video_data = self._call_api(video_id, ':watch', 'watch', data={'deviceId': self._DEVICE_ID})
+
+        return {
+            'id': video_id,
+            'formats': self._get_formats(video_data, (
+                (('protocolHls', 'url'), ('chromecastUrls', ...)), {url_or_none}), video_id),
+            **traverse_obj(metadata, {
+                'title': ('displayName', {str}),
+                'description': ('description', {str}),
+                'channel': ('labels', 'group', {str}),
+                'location': ('labels', 'venue', {str}),
+                'timestamp': ('watchStartTime', {int_or_none}),
+                'thumbnail': ('keyVisualUrl', {url_or_none}),
+                'cast': ('casts', ..., 'displayName', {str}),
+                'duration': ('duration', {int}),
+                'chapters': ('videoChapters', lambda _, v: isinstance(v.get('start'), int), {
+                    'title': ('displayName', {str}),
+                    'start_time': ('start', {int}),
+                    'end_time': ('end', {int}),
+                }),
+            }),
+        }
+
+
+class WrestleUniversePPVIE(WrestleUniverseBaseIE):
+    _VALID_URL = WrestleUniverseBaseIE._VALID_URL_TMPL % 'lives'
+    _TESTS = [{
+        'note': 'HLS AES-128 key obtained via API',
+        'url': 'https://www.wrestle-universe.com/en/lives/buH9ibbfhdJAY4GKZcEuJX',
+        'info_dict': {
+            'id': 'buH9ibbfhdJAY4GKZcEuJX',
+            'ext': 'mp4',
+            'title': '【PPV】Beyond the origins, into the future',
+            'description': 'md5:9a872db68cd09be4a1e35a3ee8b0bdfc',
+            'channel': 'tjpw',
+            'location': '東京・Twin Box AKIHABARA',
+            'duration': 10098,
+            'timestamp': 1675076400,
+            'upload_date': '20230130',
+            'thumbnail': 'https://image.asset.wrestle-universe.com/rJs2m7cBaLXrwCcxMdQGRM/rJs2m7cBaLXrwCcxMdQGRM',
+            'thumbnails': 'count:3',
+            'hls_aes': {
+                'key': '5633184acd6e43f1f1ac71c6447a4186',
+                'iv': '5bac71beb33197d5600337ce86de7862',
+            },
+        },
+        'params': {
+            'skip_download': 'm3u8',
+        },
+        'skip': 'No longer available',
+    }, {
+        'note': 'unencrypted HLS',
+        'url': 'https://www.wrestle-universe.com/en/lives/wUG8hP5iApC63jbtQzhVVx',
+        'info_dict': {
+            'id': 'wUG8hP5iApC63jbtQzhVVx',
+            'ext': 'mp4',
+            'title': 'GRAND PRINCESS \'22',
+            'description': 'md5:e4f43d0d4262de3952ff34831bc99858',
+            'channel': 'tjpw',
+            'location': '東京・両国国技館',
+            'duration': 18044,
+            'timestamp': 1647665400,
+            'upload_date': '20220319',
+            'thumbnail': 'https://image.asset.wrestle-universe.com/i8jxSTCHPfdAKD4zN41Psx/i8jxSTCHPfdAKD4zN41Psx',
+            'thumbnails': 'count:3',
+        },
+        'params': {
+            'skip_download': 'm3u8',
+        },
+    }]
+
+    _API_PATH = 'events'
+
+    def _real_extract(self, url):
+        lang, video_id = self._match_valid_url(url).group('lang', 'id')
+        metadata = self._download_metadata(url, video_id, lang, 'eventFallbackData')
+
+        info = {
+            'id': video_id,
+            **traverse_obj(metadata, {
+                'title': ('displayName', {str}),
+                'description': ('description', {str}),
+                'channel': ('labels', 'group', {str}),
+                'location': ('labels', 'venue', {str}),
+                'timestamp': ('startTime', {int_or_none}),
+                'thumbnails': (('keyVisualUrl', 'alterKeyVisualUrl', 'heroKeyVisualUrl'), {'url': {url_or_none}}),
+            }),
+        }
+
+        ended_time = traverse_obj(metadata, ('endedTime', {int_or_none}))
+        if info.get('timestamp') and ended_time:
+            info['duration'] = ended_time - info['timestamp']
+
+        video_data, decrypt = self._call_encrypted_api(
+            video_id, ':watchArchive', 'watch archive', data={'method': 1})
+        info['formats'] = self._get_formats(video_data, (
+            ('hls', None), ('urls', 'chromecastUrls'), ..., {url_or_none}), video_id)
+        for f in info['formats']:
+            # bitrates are exaggerated in PPV playlists, so avoid wrong/huge filesize_approx values
+            if f.get('tbr'):
+                f['tbr'] = int(f['tbr'] / 2.5)
+
+        hls_aes_key = traverse_obj(video_data, ('hls', 'key', {decrypt}))
+        if hls_aes_key:
+            info['hls_aes'] = {
+                'key': hls_aes_key,
+                'iv': traverse_obj(video_data, ('hls', 'iv', {decrypt})),
+            }
+        elif traverse_obj(video_data, ('hls', 'encryptType', {int})):
+            self.report_warning('HLS AES-128 key was not found in API response')
+
+        return info

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

@@ -0,0 +1,120 @@
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    float_or_none,
+    unified_strdate,
+)
+
+
+class WSJIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                        (?:
+                            https?://video-api\.wsj\.com/api-video/player/iframe\.html\?.*?\bguid=|
+                            https?://(?:www\.)?(?:wsj|barrons)\.com/video/(?:[^/]+/)+|
+                            wsj:
+                        )
+                        (?P<id>[a-fA-F0-9-]{36})
+                    '''
+    IE_DESC = 'Wall Street Journal'
+    _TESTS = [{
+        'url': 'http://video-api.wsj.com/api-video/player/iframe.html?guid=1BD01A4C-BFE8-40A5-A42F-8A8AF9898B1A',
+        'md5': 'e230a5bb249075e40793b655a54a02e4',
+        'info_dict': {
+            'id': '1BD01A4C-BFE8-40A5-A42F-8A8AF9898B1A',
+            'ext': 'mp4',
+            'upload_date': '20150202',
+            'uploader_id': 'jdesai',
+            'creator': 'jdesai',
+            'categories': list,  # a long list
+            'duration': 90,
+            'title': 'Bills Coach Rex Ryan Updates His Old Jets Tattoo',
+        },
+    }, {
+        'url': 'http://www.wsj.com/video/can-alphabet-build-a-smarter-city/359DDAA8-9AC1-489C-82E6-0429C1E430E0.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.barrons.com/video/capitalism-deserves-more-respect-from-millennials/F301217E-6F46-43AE-B8D2-B7180D642EE9.html',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.wsj.com/video/series/a-brief-history-of/the-modern-cell-carrier-how-we-got-here/980E2187-401D-48A1-B82B-1486CEE06CB9',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        info = self._download_json(
+            'http://video-api.wsj.com/api-video/find_all_videos.asp', video_id,
+            query={
+                'type': 'guid',
+                'count': 1,
+                'query': video_id,
+                'fields': ','.join((
+                    'type', 'hls', 'videoMP4List', 'thumbnailList', 'author',
+                    'description', 'name', 'duration', 'videoURL', 'titletag',
+                    'formattedCreationDate', 'keywords', 'editor')),
+            })['items'][0]
+        title = info.get('name', info.get('titletag'))
+
+        formats = []
+
+        f4m_url = info.get('videoURL')
+        if f4m_url:
+            formats.extend(self._extract_f4m_formats(
+                f4m_url, video_id, f4m_id='hds', fatal=False))
+
+        m3u8_url = info.get('hls')
+        if m3u8_url:
+            formats.extend(self._extract_m3u8_formats(
+                info['hls'], video_id, ext='mp4',
+                entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
+
+        for v in info.get('videoMP4List', []):
+            mp4_url = v.get('url')
+            if not mp4_url:
+                continue
+            tbr = int_or_none(v.get('bitrate'))
+            formats.append({
+                'url': mp4_url,
+                'format_id': 'http' + ('-%d' % tbr if tbr else ''),
+                'tbr': tbr,
+                'width': int_or_none(v.get('width')),
+                'height': int_or_none(v.get('height')),
+                'fps': float_or_none(v.get('fps')),
+            })
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            # Thumbnails are conveniently in the correct format already
+            'thumbnails': info.get('thumbnailList'),
+            'creator': info.get('author'),
+            'uploader_id': info.get('editor'),
+            'duration': int_or_none(info.get('duration')),
+            'upload_date': unified_strdate(info.get(
+                'formattedCreationDate'), day_first=False),
+            'title': title,
+            'categories': info.get('keywords'),
+        }
+
+
+class WSJArticleIE(InfoExtractor):
+    _VALID_URL = r'(?i)https?://(?:www\.)?wsj\.com/articles/(?P<id>[^/?#&]+)'
+    _TEST = {
+        'url': 'https://www.wsj.com/articles/dont-like-china-no-pandas-for-you-1490366939?',
+        'info_dict': {
+            'id': '4B13FA62-1D8C-45DB-8EA1-4105CB20B362',
+            'ext': 'mp4',
+            'upload_date': '20170221',
+            'uploader_id': 'ralcaraz',
+            'title': 'Bao Bao the Panda Leaves for China',
+        }
+    }
+
+    def _real_extract(self, url):
+        article_id = self._match_id(url)
+        webpage = self._download_webpage(url, article_id)
+        video_id = self._search_regex(
+            r'(?:id=["\']video|video-|iframe\.html\?guid=|data-src=["\'])([a-fA-F0-9-]{36})',
+            webpage, 'video id')
+        return self.url_result('wsj:%s' % video_id, WSJIE.ie_key(), video_id)