@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/wistia.py

@@ -0,0 +1,394 @@
+import re
+import urllib.parse
+from base64 import b64decode
+
+from .common import InfoExtractor
+from ..networking import HEADRequest
+from ..networking.exceptions import HTTPError
+from ..utils import (
+    ExtractorError,
+    determine_ext,
+    float_or_none,
+    int_or_none,
+    parse_qs,
+    traverse_obj,
+    try_get,
+    update_url_query,
+    urlhandle_detect_ext,
+)
+
+
+class WistiaBaseIE(InfoExtractor):
+    _VALID_ID_REGEX = r'(?P<id>[a-z0-9]{10})'
+    _VALID_URL_BASE = r'https?://(?:\w+\.)?wistia\.(?:net|com)/(?:embed/)?'
+    _EMBED_BASE_URL = 'http://fast.wistia.net/embed/'
+
+    def _download_embed_config(self, config_type, config_id, referer):
+        base_url = self._EMBED_BASE_URL + '%s/%s' % (config_type, config_id)
+        embed_config = self._download_json(
+            base_url + '.json', config_id, headers={
+                'Referer': referer if referer.startswith('http') else base_url,  # Some videos require this.
+            })
+
+        error = traverse_obj(embed_config, 'error')
+        if error:
+            raise ExtractorError(
+                f'Error while getting the playlist: {error}', expected=True)
+
+        return embed_config
+
+    def _get_real_ext(self, url):
+        ext = determine_ext(url, default_ext='bin')
+        if ext == 'bin':
+            urlh = self._request_webpage(
+                HEADRequest(url), None, note='Checking media extension',
+                errnote='HEAD request returned error', fatal=False)
+            if urlh:
+                ext = urlhandle_detect_ext(urlh, default='bin')
+        return 'mp4' if ext == 'mov' else ext
+
+    def _extract_media(self, embed_config):
+        data = embed_config['media']
+        video_id = data['hashedId']
+        title = data['name']
+
+        formats = []
+        thumbnails = []
+        for a in data['assets']:
+            aurl = a.get('url')
+            if not aurl:
+                continue
+            astatus = a.get('status')
+            atype = a.get('type')
+            if (astatus is not None and astatus != 2) or atype in ('preview', 'storyboard'):
+                continue
+            elif atype in ('still', 'still_image'):
+                thumbnails.append({
+                    'url': aurl.replace('.bin', f'.{self._get_real_ext(aurl)}'),
+                    'width': int_or_none(a.get('width')),
+                    'height': int_or_none(a.get('height')),
+                    'filesize': int_or_none(a.get('size')),
+                })
+            else:
+                aext = a.get('ext') or self._get_real_ext(aurl)
+                display_name = a.get('display_name')
+                format_id = atype
+                if atype and atype.endswith('_video') and display_name:
+                    format_id = '%s-%s' % (atype[:-6], display_name)
+                f = {
+                    'format_id': format_id,
+                    'url': aurl,
+                    'tbr': int_or_none(a.get('bitrate')) or None,
+                    'quality': 1 if atype == 'original' else None,
+                }
+                if display_name == 'Audio':
+                    f.update({
+                        'vcodec': 'none',
+                    })
+                else:
+                    f.update({
+                        'width': int_or_none(a.get('width')),
+                        'height': int_or_none(a.get('height')),
+                        'vcodec': a.get('codec'),
+                    })
+                if a.get('container') == 'm3u8' or aext == 'm3u8':
+                    ts_f = f.copy()
+                    ts_f.update({
+                        'ext': 'ts',
+                        'format_id': f['format_id'].replace('hls-', 'ts-'),
+                        'url': f['url'].replace('.bin', '.ts'),
+                    })
+                    formats.append(ts_f)
+                    f.update({
+                        'ext': 'mp4',
+                        'protocol': 'm3u8_native',
+                    })
+                else:
+                    f.update({
+                        'container': a.get('container'),
+                        'ext': aext,
+                        'filesize': int_or_none(a.get('size')),
+                    })
+                formats.append(f)
+
+        subtitles = {}
+        for caption in data.get('captions', []):
+            language = caption.get('language')
+            if not language:
+                continue
+            subtitles[language] = [{
+                'url': self._EMBED_BASE_URL + 'captions/' + video_id + '.vtt?language=' + language,
+            }]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': data.get('seoDescription'),
+            'formats': formats,
+            'thumbnails': thumbnails,
+            'duration': float_or_none(data.get('duration')),
+            'timestamp': int_or_none(data.get('createdAt')),
+            'subtitles': subtitles,
+        }
+
+    @classmethod
+    def _extract_from_webpage(cls, url, webpage):
+        from .teachable import TeachableIE
+
+        if list(TeachableIE._extract_embed_urls(url, webpage)):
+            return
+
+        yield from super()._extract_from_webpage(url, webpage)
+
+    @classmethod
+    def _extract_wistia_async_embed(cls, webpage):
+        # https://wistia.com/support/embed-and-share/video-on-your-website
+        # https://wistia.com/support/embed-and-share/channel-embeds
+        yield from re.finditer(
+            r'''(?sx)
+                <(?:div|section)[^>]+class=([\"'])(?:(?!\1).)*?(?P<type>wistia[a-z_0-9]+)\s*\bwistia_async_(?P<id>[a-z0-9]{10})\b(?:(?!\1).)*?\1
+            ''', webpage)
+
+    @classmethod
+    def _extract_url_media_id(cls, url):
+        mobj = re.search(r'(?:wmediaid|wvideo(?:id)?)]?=(?P<id>[a-z0-9]{10})', urllib.parse.unquote_plus(url))
+        if mobj:
+            return mobj.group('id')
+
+
+class WistiaIE(WistiaBaseIE):
+    _VALID_URL = r'(?:wistia:|%s(?:iframe|medias)/)%s' % (WistiaBaseIE._VALID_URL_BASE, WistiaBaseIE._VALID_ID_REGEX)
+    _EMBED_REGEX = [
+        r'''(?x)
+            <(?:meta[^>]+?content|(?:iframe|script)[^>]+?src)=["\']
+            (?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/[a-z0-9]{10})
+            ''']
+    _TESTS = [{
+        # with hls video
+        'url': 'wistia:807fafadvk',
+        'md5': 'daff0f3687a41d9a71b40e0e8c2610fe',
+        'info_dict': {
+            'id': '807fafadvk',
+            'ext': 'mp4',
+            'title': 'Drip Brennan Dunn Workshop',
+            'description': 'a JV Webinars video',
+            'upload_date': '20160518',
+            'timestamp': 1463607249,
+            'duration': 4987.11,
+        },
+        'skip': 'video unavailable',
+    }, {
+        'url': 'wistia:a6ndpko1wg',
+        'md5': '10c1ce9c4dde638202513ed17a3767bd',
+        'info_dict': {
+            'id': 'a6ndpko1wg',
+            'ext': 'mp4',
+            'title': 'Episode 2: Boxed Water\'s retention is thirsty',
+            'upload_date': '20210324',
+            'description': 'md5:da5994c2c2d254833b412469d9666b7a',
+            'duration': 966.0,
+            'timestamp': 1616614369,
+            'thumbnail': 'https://embed-ssl.wistia.com/deliveries/53dc60239348dc9b9fba3755173ea4c2.png',
+        }
+    }, {
+        'url': 'wistia:5vd7p4bct5',
+        'md5': 'b9676d24bf30945d97060638fbfe77f0',
+        'info_dict': {
+            'id': '5vd7p4bct5',
+            'ext': 'mp4',
+            'title': 'md5:eaa9f64c4efd7b5f098b9b6118597679',
+            'description': 'md5:a9bea0315f0616aa5df2dc413ddcdd0f',
+            'upload_date': '20220915',
+            'timestamp': 1663258727,
+            'duration': 623.019,
+            'thumbnail': r're:https?://embed(?:-ssl)?.wistia.com/.+\.jpg$',
+        },
+    }, {
+        'url': 'wistia:sh7fpupwlt',
+        'only_matching': True,
+    }, {
+        'url': 'http://fast.wistia.net/embed/iframe/sh7fpupwlt',
+        'only_matching': True,
+    }, {
+        'url': 'http://fast.wistia.com/embed/iframe/sh7fpupwlt',
+        'only_matching': True,
+    }, {
+        'url': 'http://fast.wistia.net/embed/medias/sh7fpupwlt.json',
+        'only_matching': True,
+    }]
+
+    _WEBPAGE_TESTS = [{
+        'url': 'https://www.weidert.com/blog/wistia-channels-video-marketing-tool',
+        'info_dict': {
+            'id': 'cqwukac3z1',
+            'ext': 'mp4',
+            'title': 'How Wistia Channels Can Help Capture Inbound Value From Your Video Content',
+            'duration': 158.125,
+            'timestamp': 1618974400,
+            'description': 'md5:27abc99a758573560be72600ef95cece',
+            'upload_date': '20210421',
+            'thumbnail': 'https://embed-ssl.wistia.com/deliveries/6c551820ae950cdee2306d6cbe9ef742.jpg',
+        }
+    }, {
+        'url': 'https://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
+        'md5': 'b9676d24bf30945d97060638fbfe77f0',
+        'info_dict': {
+            'id': '5vd7p4bct5',
+            'ext': 'mp4',
+            'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
+            'upload_date': '20220915',
+            'timestamp': 1663258727,
+            'duration': 623.019,
+            'thumbnail': 'https://embed-ssl.wistia.com/deliveries/83e6ec693e2c05a0ce65809cbaead86a.jpg',
+            'description': 'a Paywall Videos video',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        embed_config = self._download_embed_config('medias', video_id, url)
+        return self._extract_media(embed_config)
+
+    @classmethod
+    def _extract_embed_urls(cls, url, webpage):
+        urls = list(super()._extract_embed_urls(url, webpage))
+        for match in cls._extract_wistia_async_embed(webpage):
+            if match.group('type') != 'wistia_channel':
+                urls.append('wistia:%s' % match.group('id'))
+        for match in re.finditer(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P<id>[a-z0-9]{10})',
+                                 webpage):
+            urls.append('wistia:%s' % match.group('id'))
+        if not WistiaChannelIE._extract_embed_urls(url, webpage):  # Fallback
+            media_id = cls._extract_url_media_id(url)
+            if media_id:
+                urls.append('wistia:%s' % match.group('id'))
+        return urls
+
+
+class WistiaPlaylistIE(WistiaBaseIE):
+    _VALID_URL = r'%splaylists/%s' % (WistiaBaseIE._VALID_URL_BASE, WistiaBaseIE._VALID_ID_REGEX)
+
+    _TEST = {
+        'url': 'https://fast.wistia.net/embed/playlists/aodt9etokc',
+        'info_dict': {
+            'id': 'aodt9etokc',
+        },
+        'playlist_count': 3,
+    }
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        playlist = self._download_embed_config('playlists', playlist_id, url)
+
+        entries = []
+        for media in (try_get(playlist, lambda x: x[0]['medias']) or []):
+            embed_config = media.get('embed_config')
+            if not embed_config:
+                continue
+            entries.append(self._extract_media(embed_config))
+
+        return self.playlist_result(entries, playlist_id)
+
+
+class WistiaChannelIE(WistiaBaseIE):
+    _VALID_URL = r'(?:wistiachannel:|%schannel/)%s' % (WistiaBaseIE._VALID_URL_BASE, WistiaBaseIE._VALID_ID_REGEX)
+
+    _TESTS = [{
+        # JSON Embed API returns 403, should fall back to webpage
+        'url': 'https://fast.wistia.net/embed/channel/yvyvu7wjbg?wchannelid=yvyvu7wjbg',
+        'info_dict': {
+            'id': 'yvyvu7wjbg',
+            'title': 'Copysmith Tutorials and Education!',
+            'description': 'Learn all things Copysmith via short and informative videos!'
+        },
+        'playlist_mincount': 7,
+        'expected_warnings': ['falling back to webpage'],
+    }, {
+        'url': 'https://fast.wistia.net/embed/channel/3802iirk0l',
+        'info_dict': {
+            'id': '3802iirk0l',
+            'title': 'The Roof',
+        },
+        'playlist_mincount': 20,
+    }, {
+        # link to popup video, follow --no-playlist
+        'url': 'https://fast.wistia.net/embed/channel/3802iirk0l?wchannelid=3802iirk0l&wmediaid=sp5dqjzw3n',
+        'info_dict': {
+            'id': 'sp5dqjzw3n',
+            'ext': 'mp4',
+            'title': 'The Roof S2: The Modern CRO',
+            'thumbnail': 'https://embed-ssl.wistia.com/deliveries/dadfa9233eaa505d5e0c85c23ff70741.png',
+            'duration': 86.487,
+            'description': 'A sales leader on The Roof? Man, they really must be letting anyone up here this season.\n',
+            'timestamp': 1619790290,
+            'upload_date': '20210430',
+        },
+        'params': {'noplaylist': True, 'skip_download': True},
+    }]
+    _WEBPAGE_TESTS = [{
+        'url': 'https://www.profitwell.com/recur/boxed-out',
+        'info_dict': {
+            'id': '6jyvmqz6zs',
+            'title': 'Boxed Out',
+            'description': 'md5:14a8a93a1dbe236718e6a59f8c8c7bae',
+        },
+        'playlist_mincount': 30,
+    }, {
+        # section instead of div
+        'url': 'https://360learning.com/studio/onboarding-joei/',
+        'info_dict': {
+            'id': 'z874k93n2o',
+            'title': 'Onboarding Joei.',
+            'description': 'Coming to you weekly starting Feb 19th.',
+        },
+        'playlist_mincount': 20,
+    }, {
+        'url': 'https://amplitude.com/amplify-sessions?amp%5Bwmediaid%5D=pz0m0l0if3&amp%5Bwvideo%5D=pz0m0l0if3&wchannelid=emyjmwjf79&wmediaid=i8um783bdt',
+        'info_dict': {
+            'id': 'pz0m0l0if3',
+            'title': 'A Framework for Improving Product Team Performance',
+            'ext': 'mp4',
+            'timestamp': 1653935275,
+            'upload_date': '20220530',
+            'description': 'Learn how to help your company improve and achieve your product related goals.',
+            'duration': 1854.39,
+            'thumbnail': 'https://embed-ssl.wistia.com/deliveries/12fd19e56413d9d6f04e2185c16a6f8854e25226.png',
+        },
+        'params': {'noplaylist': True, 'skip_download': True},
+    }]
+
+    def _real_extract(self, url):
+        channel_id = self._match_id(url)
+        media_id = self._extract_url_media_id(url)
+        if not self._yes_playlist(channel_id, media_id, playlist_label='channel'):
+            return self.url_result(f'wistia:{media_id}', 'Wistia')
+
+        try:
+            data = self._download_embed_config('channel', channel_id, url)
+        except (ExtractorError, HTTPError):
+            # Some channels give a 403 from the JSON API
+            self.report_warning('Failed to download channel data from API, falling back to webpage.')
+            webpage = self._download_webpage(f'https://fast.wistia.net/embed/channel/{channel_id}', channel_id)
+            data = self._parse_json(
+                self._search_regex(r'wchanneljsonp-%s\'\]\s*=[^\"]*\"([A-Za-z0-9=/]*)' % channel_id, webpage, 'jsonp', channel_id),
+                channel_id, transform_source=lambda x: urllib.parse.unquote_plus(b64decode(x).decode('utf-8')))
+
+        # XXX: can there be more than one series?
+        series = traverse_obj(data, ('series', 0), default={})
+
+        entries = [
+            self.url_result(f'wistia:{video["hashedId"]}', WistiaIE, title=video.get('name'))
+            for video in traverse_obj(series, ('sections', ..., 'videos', ...)) or []
+            if video.get('hashedId')
+        ]
+
+        return self.playlist_result(
+            entries, channel_id, playlist_title=series.get('title'), playlist_description=series.get('description'))
+
+    @classmethod
+    def _extract_embed_urls(cls, url, webpage):
+        yield from super()._extract_embed_urls(url, webpage)
+        for match in cls._extract_wistia_async_embed(webpage):
+            if match.group('type') == 'wistia_channel':
+                # original url may contain wmediaid query param
+                yield update_url_query(f'wistiachannel:{match.group("id")}', parse_qs(url))

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

@@ -0,0 +1,154 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    extract_attributes,
+    get_elements_by_class,
+    get_elements_text_and_html_by_attribute,
+    int_or_none,
+    parse_duration,
+    traverse_obj,
+)
+
+
+# https://codex.wordpress.org/Playlist_Shortcode
+class WordpressPlaylistEmbedIE(InfoExtractor):
+    _VALID_URL = False
+    IE_NAME = 'wordpress:playlist'
+    _WEBPAGE_TESTS = [{
+        # 5 WordPress playlists. This is using wpse-playlist, which is similar.
+        # See: https://github.com/birgire/wpse-playlist
+        'url': 'https://xlino.com/wordpress-playlist-shortcode-with-external-audio-or-video-files/',
+        'info_dict': {
+            'id': 'wordpress-playlist-shortcode-with-external-audio-or-video-files',
+            'title': 'WordPress: Playlist shortcode with external audio or video files – Birgir Erlendsson (birgire)',
+            'age_limit': 0,
+        },
+        'playlist_count': 5,
+    }, {
+        'url': 'https://pianoadventures.com/products/piano-adventures-level-1-lesson-book-enhanced-cd/',
+        'info_dict': {
+            'id': 'piano-adventures-level-1-lesson-book-enhanced-cd-wp-playlist-1',
+            'title': 'Wordpress Playlist',
+            'thumbnail': 'https://pianoadventures.com/wp-content/uploads/sites/13/2022/01/CD1002cover.jpg',
+            'age_limit': 0,
+        },
+        'playlist': [{
+            'info_dict': {
+                'id': 'CD1002-21',
+                'ext': 'mp3',
+                'title': '21 Half-Time Show',
+                'thumbnail': 'https://pianoadventures.com/wp-content/plugins/media-library-assistant/images/crystal/audio.png',
+                'album': 'Piano Adventures Level 1 Lesson Book (2nd Edition)',
+                'genre': 'Classical',
+                'duration': 49.0,
+                'artist': 'Nancy and Randall Faber',
+                'description': 'md5:a9f8e9aeabbd2912bc13cc0fab1a4ce8',
+            }
+        }],
+        'playlist_count': 6,
+        'params': {'skip_download': True}
+    }]
+
+    def _extract_from_webpage(self, url, webpage):
+        # class should always be "wp-playlist-script"
+        # See: https://core.trac.wordpress.org/browser/trunk/src/wp-includes/media.php#L2930
+        for i, j in enumerate(get_elements_by_class('wp-playlist-script', webpage)):
+            playlist_json = self._parse_json(j, self._generic_id(url), fatal=False, ignore_extra=True, errnote='') or {}
+            if not playlist_json:
+                continue
+            entries = [{
+                'id': self._generic_id(track['src']),
+                'title': track.get('title'),
+                'url': track.get('src'),
+                'thumbnail': traverse_obj(track, ('thumb', 'src')),
+                'album': traverse_obj(track, ('meta', 'album')),
+                'artist': traverse_obj(track, ('meta', 'artist')),
+                'genre': traverse_obj(track, ('meta', 'genre')),
+                'duration': parse_duration(traverse_obj(track, ('meta', 'length_formatted'))),
+                'description': track.get('description'),
+                'height': int_or_none(traverse_obj(track, ('dimensions', 'original', 'height'))),
+                'width': int_or_none(traverse_obj(track, ('dimensions', 'original', 'width'))),
+            } for track in traverse_obj(playlist_json, ('tracks', ...), expected_type=dict)]
+            yield self.playlist_result(entries, self._generic_id(url) + f'-wp-playlist-{i + 1}', 'Wordpress Playlist')
+
+
+class WordpressMiniAudioPlayerEmbedIE(InfoExtractor):
+    # WordPress MB Mini Player Plugin
+    # https://wordpress.org/plugins/wp-miniaudioplayer/
+    # Note: This is for the WordPress plugin version only.
+    _VALID_URL = False
+    IE_NAME = 'wordpress:mb.miniAudioPlayer'
+    _WEBPAGE_TESTS = [{
+        # Version 1.8.10: https://plugins.trac.wordpress.org/browser/wp-miniaudioplayer/tags/1.8.10
+        'url': 'https://news.samsung.com/global/over-the-horizon-the-evolution-of-the-samsung-galaxy-brand-sound',
+        'info_dict': {
+            'id': 'over-the-horizon-the-evolution-of-the-samsung-galaxy-brand-sound',
+            'title': 'Over the Horizon: The Evolution of the Samsung Galaxy Brand Sound',
+            'age_limit': 0,
+            'thumbnail': 'https://img.global.news.samsung.com/global/wp-content/uploads/2015/04/OTH_Main_Title-e1429612467870.jpg',
+            'description': 'md5:bc3dd738d1f11d9232e94e6629983bf7',
+        },
+        'playlist': [{
+            'info_dict': {
+                'id': 'over_the_horizon_2013',
+                'ext': 'mp3',
+                'title': 'Over the Horizon 2013',
+                'url': 'http://news.samsung.com/global/wp-content/uploads/ringtones/over_the_horizon_2013.mp3'
+            }
+        }],
+        'playlist_count': 6,
+        'params': {'skip_download': True}
+    }, {
+        # Version 1.9.3: https://plugins.trac.wordpress.org/browser/wp-miniaudioplayer/tags/1.9.3
+        'url': 'https://www.booksontape.com/collections/audiobooks-with-teacher-guides/',
+        'info_dict': {
+            'id': 'audiobooks-with-teacher-guides',
+            'title': 'Audiobooks with Teacher Guides | Books on Tape',
+            'age_limit': 0,
+            'thumbnail': 'https://www.booksontape.com/wp-content/uploads/2016/09/bot-logo-1200x630.jpg',
+        },
+        'playlist_mincount': 12
+    }, {
+        # Version 1.9.7: https://plugins.trac.wordpress.org/browser/wp-miniaudioplayer/tags/1.9.7
+        # But has spaces around href filter
+        'url': 'https://www.estudiords.com.br/temas/',
+        'info_dict': {
+            'id': 'temas',
+            'title': 'Temas Variados',
+            'age_limit': 0,
+            'timestamp': float,
+            'upload_date': str,
+            'thumbnail': 'https://www.estudiords.com.br/wp-content/uploads/2021/03/LOGO-TEMAS.png',
+            'description': 'md5:ab24d6a7ed0312ad2d466e721679f5a0',
+        },
+        'playlist_mincount': 30
+    }]
+
+    def _extract_from_webpage(self, url, webpage):
+        # Common function for the WordPress plugin version only.
+        mb_player_params = self._search_regex(
+            r'function\s*initializeMiniAudioPlayer\(\){[^}]+jQuery([^;]+)\.mb_miniPlayer',
+            webpage, 'mb player params', default=None)
+        if not mb_player_params:
+            return
+        # v1.55 - 1.9.3 has "a[href*='.mp3'] ,a[href*='.m4a']"
+        # v1.9.4+ has "a[href*='.mp3']" only
+        file_exts = re.findall(r'a\[href\s*\*=\s*\'\.([a-zA-Z\d]+)\'', mb_player_params)
+        if not file_exts:
+            return
+
+        candidates = get_elements_text_and_html_by_attribute(
+            'href', rf'(?:[^\"\']+\.(?:{"|".join(file_exts)}))', webpage, escape_value=False, tag='a')
+
+        for title, html in candidates:
+            attrs = extract_attributes(html)
+            # XXX: not tested - have not found any example of it being used
+            if any(c in (attrs.get('class') or '') for c in re.findall(r'\.not\("\.([^"]+)', mb_player_params)):
+                continue
+            href = attrs['href']
+            yield {
+                'id': self._generic_id(href),
+                'title': title or self._generic_title(href),
+                'url': href,
+            }

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

@@ -0,0 +1,38 @@
+from .common import InfoExtractor
+
+
+class WorldStarHipHopIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/(?:videos|android)/video\.php\?.*?\bv=(?P<id>[^&]+)'
+    _TESTS = [{
+        'url': 'http://www.worldstarhiphop.com/videos/video.php?v=wshh6a7q1ny0G34ZwuIO',
+        'md5': '9d04de741161603bf7071bbf4e883186',
+        'info_dict': {
+            'id': 'wshh6a7q1ny0G34ZwuIO',
+            'ext': 'mp4',
+            'title': 'KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!'
+        }
+    }, {
+        'url': 'http://m.worldstarhiphop.com/android/video.php?v=wshh6a7q1ny0G34ZwuIO',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        entries = self._parse_html5_media_entries(url, webpage, video_id)
+
+        if not entries:
+            return self.url_result(url, 'Generic')
+
+        title = self._html_search_regex(
+            [r'(?s)<div class="content-heading">\s*<h1>(.*?)</h1>',
+             r'<span[^>]+class="tc-sp-pinned-title">(.*)</span>'],
+            webpage, 'title')
+
+        info = entries[0]
+        info.update({
+            'id': video_id,
+            'title': title,
+        })
+        return info