[ie/Vbox7] Fix extractor (#9100)

Closes #1098, Closes #5661
Authored by: seproDev

yt_dlp/extractor/_extractors.py

@@ -138,6 +138,10 @@ from .ard import (
     ARDMediathekCollectionIE,
     ARDIE,
 )
+from .art19 import (
+    Art19IE,
+    Art19ShowIE,
+)
 from .arte import (
     ArteTVIE,
     ArteTVEmbedIE,

yt_dlp/extractor/art19.py

@@ -0,0 +1,303 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import float_or_none, int_or_none, parse_iso8601, url_or_none
+from ..utils.traversal import traverse_obj
+
+
+class Art19IE(InfoExtractor):
+    _UUID_REGEX = r'[\da-f]{8}-?[\da-f]{4}-?[\da-f]{4}-?[\da-f]{4}-?[\da-f]{12}'
+    _VALID_URL = [
+        rf'https?://(?:www\.)?art19\.com/shows/[^/#?]+/episodes/(?P<id>{_UUID_REGEX})',
+        rf'https?://rss\.art19\.com/episodes/(?P<id>{_UUID_REGEX})\.mp3',
+    ]
+    _EMBED_REGEX = [rf'<iframe[^>]+\bsrc=[\'"](?P<url>{_VALID_URL[0]})']
+
+    _TESTS = [{
+        'url': 'https://rss.art19.com/episodes/5ba1413c-48b8-472b-9cc3-cfd952340bdb.mp3',
+        'info_dict': {
+            'id': '5ba1413c-48b8-472b-9cc3-cfd952340bdb',
+            'ext': 'mp3',
+            'title': 'Why Did DeSantis Drop Out?',
+            'series': 'The Daily Briefing',
+            'release_timestamp': 1705941275,
+            'description': 'md5:da38961da4a3f7e419471365e3c6b49f',
+            'episode': 'Episode 582',
+            'thumbnail': r're:^https?://content\.production\.cdn\.art19\.com.*\.jpeg$',
+            'series_id': 'ed52a0ab-08b1-4def-8afc-549e4d93296d',
+            'upload_date': '20240122',
+            'timestamp': 1705940815,
+            'episode_number': 582,
+            'modified_date': '20240122',
+            'episode_id': '5ba1413c-48b8-472b-9cc3-cfd952340bdb',
+            'modified_timestamp': 1705941275,
+            'release_date': '20240122',
+            'duration': 527.4,
+        },
+    }, {
+        'url': 'https://art19.com/shows/scamfluencers/episodes/8319b776-4153-4d22-8630-631f204a03dd',
+        'info_dict': {
+            'id': '8319b776-4153-4d22-8630-631f204a03dd',
+            'ext': 'mp3',
+            'title': 'Martha Stewart: The Homemaker Hustler Part 2',
+            'modified_date': '20240116',
+            'upload_date': '20240105',
+            'modified_timestamp': 1705435802,
+            'episode_id': '8319b776-4153-4d22-8630-631f204a03dd',
+            'series_id': 'd3c9b8ca-26b3-42f4-9bd8-21d1a9031e75',
+            'thumbnail': r're:^https?://content\.production\.cdn\.art19\.com.*\.jpeg$',
+            'description': 'md5:4aa7cfd1358dc57e729835bc208d7893',
+            'release_timestamp': 1705305660,
+            'release_date': '20240115',
+            'timestamp': 1704481536,
+            'episode_number': 88,
+            'series': 'Scamfluencers',
+            'duration': 2588.37501,
+            'episode': 'Episode 88',
+        },
+    }]
+    _WEBPAGE_TESTS = [{
+        'url': 'https://www.nu.nl/formule-1/6291456/verstappen-wordt-een-synoniem-voor-formule-1.html',
+        'info_dict': {
+            'id': '7d42626a-7301-47db-bb8a-3b6f054d77d7',
+            'ext': 'mp3',
+            'title': "'Verstappen wordt een synoniem voor Formule 1'",
+            'season': 'Seizoen 6',
+            'description': 'md5:39a7159a31c4cda312b2e893bdd5c071',
+            'episode_id': '7d42626a-7301-47db-bb8a-3b6f054d77d7',
+            'duration': 3061.82111,
+            'series_id': '93f4e113-2a60-4609-a564-755058fa40d8',
+            'release_date': '20231126',
+            'modified_timestamp': 1701156004,
+            'thumbnail': r're:^https?://content\.production\.cdn\.art19\.com.*\.jpeg$',
+            'season_number': 6,
+            'episode_number': 52,
+            'modified_date': '20231128',
+            'upload_date': '20231126',
+            'timestamp': 1701025981,
+            'season_id': '36097c1e-7455-490d-a2fe-e2f10b4d5f26',
+            'series': 'De Boordradio',
+            'release_timestamp': 1701026308,
+            'episode': 'Episode 52',
+        },
+    }, {
+        'url': 'https://www.wishtv.com/podcast-episode/larry-bucshon-announces-retirement-from-congress/',
+        'info_dict': {
+            'id': '8da368bd-08d1-46d0-afaa-c134a4af7dc0',
+            'ext': 'mp3',
+            'title': 'Larry Bucshon announces retirement from congress',
+            'upload_date': '20240115',
+            'episode_number': 148,
+            'episode': 'Episode 148',
+            'thumbnail': r're:^https?://content\.production\.cdn\.art19\.com.*\.jpeg$',
+            'release_date': '20240115',
+            'timestamp': 1705328205,
+            'release_timestamp': 1705329275,
+            'series': 'All INdiana Politics',
+            'modified_date': '20240117',
+            'modified_timestamp': 1705458901,
+            'series_id': 'c4af6c27-b10f-4ff2-9f84-0f407df86ff1',
+            'episode_id': '8da368bd-08d1-46d0-afaa-c134a4af7dc0',
+            'description': 'md5:53b5239e4d14973a87125c217c255b2a',
+            'duration': 1256.18848,
+        },
+    }]
+
+    @classmethod
+    def _extract_embed_urls(cls, url, webpage):
+        yield from super()._extract_embed_urls(url, webpage)
+        for episode_id in re.findall(
+                rf'<div[^>]+\bclass=[\'"][^\'"]*art19-web-player[^\'"]*[\'"][^>]+\bdata-episode-id=[\'"]({cls._UUID_REGEX})[\'"]', webpage):
+            yield f'https://rss.art19.com/episodes/{episode_id}.mp3'
+
+    def _real_extract(self, url):
+        episode_id = self._match_id(url)
+
+        player_metadata = self._download_json(
+            f'https://art19.com/episodes/{episode_id}', episode_id,
+            note='Downloading player metadata', fatal=False,
+            headers={'Accept': 'application/vnd.art19.v0+json'})
+        rss_metadata = self._download_json(
+            f'https://rss.art19.com/episodes/{episode_id}.json', episode_id, fatal=False,
+            note='Downloading RSS metadata')
+
+        formats = [{
+            'format_id': 'direct',
+            'url': f'https://rss.art19.com/episodes/{episode_id}.mp3',
+            'vcodec': 'none',
+            'acodec': 'mp3',
+        }]
+        for fmt_id, fmt_data in traverse_obj(rss_metadata, ('content', 'media', {dict.items}, ...)):
+            if fmt_id == 'waveform_bin':
+                continue
+            fmt_url = traverse_obj(fmt_data, ('url', {url_or_none}))
+            if not fmt_url:
+                continue
+            formats.append({
+                'format_id': fmt_id,
+                'url': fmt_url,
+                'vcodec': 'none',
+                'acodec': fmt_id,
+                'quality': -2 if fmt_id == 'ogg' else -1,
+            })
+
+        return {
+            'id': episode_id,
+            'formats': formats,
+            **traverse_obj(player_metadata, ('episode', {
+                'title': ('title', {str}),
+                'description': ('description_plain', {str}),
+                'episode_id': ('id', {str}),
+                'episode_number': ('episode_number', {int_or_none}),
+                'season_id': ('season_id', {str}),
+                'series_id': ('series_id', {str}),
+                'timestamp': ('created_at', {parse_iso8601}),
+                'release_timestamp': ('released_at', {parse_iso8601}),
+                'modified_timestamp': ('updated_at', {parse_iso8601})
+            })),
+            **traverse_obj(rss_metadata, ('content', {
+                'title': ('episode_title', {str}),
+                'description': ('episode_description_plain', {str}),
+                'episode_id': ('episode_id', {str}),
+                'episode_number': ('episode_number', {int_or_none}),
+                'season': ('season_title', {str}),
+                'season_id': ('season_id', {str}),
+                'season_number': ('season_number', {int_or_none}),
+                'series': ('series_title', {str}),
+                'series_id': ('series_id', {str}),
+                'thumbnail': ('cover_image', {url_or_none}),
+                'duration': ('duration', {float_or_none}),
+            })),
+        }
+
+
+class Art19ShowIE(InfoExtractor):
+    _VALID_URL_BASE = r'https?://(?:www\.)?art19\.com/shows/(?P<id>[\w-]+)(?:/embed)?/?'
+    _VALID_URL = [
+        rf'{_VALID_URL_BASE}(?:$|[#?])',
+        r'https?://rss\.art19\.com/(?P<id>[\w-]+)/?(?:$|[#?])',
+    ]
+    _EMBED_REGEX = [rf'<iframe[^>]+\bsrc=[\'"](?P<url>{_VALID_URL_BASE}[^\'"])']
+
+    _TESTS = [{
+        'url': 'https://www.art19.com/shows/5898c087-a14f-48dc-b6fc-a2280a1ff6e0/',
+        'info_dict': {
+            '_type': 'playlist',
+            'id': '5898c087-a14f-48dc-b6fc-a2280a1ff6e0',
+            'display_id': 'echt-gebeurd',
+            'title': 'Echt Gebeurd',
+            'description': 'md5:5fd11dc80b76e51ffd34b6067fd5e560',
+            'timestamp': 1492642167,
+            'upload_date': '20170419',
+            'modified_timestamp': int,
+            'modified_date': str,
+            'tags': 'count:7',
+        },
+        'playlist_mincount': 425,
+    }, {
+        'url': 'https://www.art19.com/shows/echt-gebeurd',
+        'info_dict': {
+            '_type': 'playlist',
+            'id': '5898c087-a14f-48dc-b6fc-a2280a1ff6e0',
+            'display_id': 'echt-gebeurd',
+            'title': 'Echt Gebeurd',
+            'description': 'md5:5fd11dc80b76e51ffd34b6067fd5e560',
+            'timestamp': 1492642167,
+            'upload_date': '20170419',
+            'modified_timestamp': int,
+            'modified_date': str,
+            'tags': 'count:7',
+        },
+        'playlist_mincount': 425,
+    }, {
+        'url': 'https://rss.art19.com/scamfluencers',
+        'info_dict': {
+            '_type': 'playlist',
+            'id': 'd3c9b8ca-26b3-42f4-9bd8-21d1a9031e75',
+            'display_id': 'scamfluencers',
+            'title': 'Scamfluencers',
+            'description': 'md5:7d239d670c0ced6dadbf71c4caf764b7',
+            'timestamp': 1647368573,
+            'upload_date': '20220315',
+            'modified_timestamp': int,
+            'modified_date': str,
+            'tags': [],
+        },
+        'playlist_mincount': 90,
+    }, {
+        'url': 'https://art19.com/shows/enthuellt/embed',
+        'info_dict': {
+            '_type': 'playlist',
+            'id': 'e2cacf57-bb8a-4263-aa81-719bcdd4f80c',
+            'display_id': 'enthuellt',
+            'title': 'Enthüllt',
+            'description': 'md5:17752246643414a2fd51744fc9a1c08e',
+            'timestamp': 1601645860,
+            'upload_date': '20201002',
+            'modified_timestamp': int,
+            'modified_date': str,
+            'tags': 'count:10',
+        },
+        'playlist_mincount': 10,
+    }]
+    _WEBPAGE_TESTS = [{
+        'url': 'https://deconstructingyourself.com/deconstructing-yourself-podcast',
+        'info_dict': {
+            '_type': 'playlist',
+            'id': 'cfbb9b01-c295-4adb-8726-adde7c03cf21',
+            'display_id': 'deconstructing-yourself',
+            'title': 'Deconstructing Yourself',
+            'description': 'md5:dab5082b28b248a35476abf64768854d',
+            'timestamp': 1570581181,
+            'upload_date': '20191009',
+            'modified_timestamp': int,
+            'modified_date': str,
+            'tags': 'count:5',
+        },
+        'playlist_mincount': 80,
+    }, {
+        'url': 'https://chicagoreader.com/columns-opinion/podcasts/ben-joravsky-show-podcast-episodes/',
+        'info_dict': {
+            '_type': 'playlist',
+            'id': '9dfa2c37-ab87-4c13-8388-4897914313ec',
+            'display_id': 'the-ben-joravsky-show',
+            'title': 'The Ben Joravsky Show',
+            'description': 'md5:c0f3ec0ee0dbea764390e521adc8780a',
+            'timestamp': 1550875095,
+            'upload_date': '20190222',
+            'modified_timestamp': int,
+            'modified_date': str,
+            'tags': ['Chicago Politics', 'chicago', 'Ben Joravsky'],
+        },
+        'playlist_mincount': 1900,
+    }]
+
+    @classmethod
+    def _extract_embed_urls(cls, url, webpage):
+        yield from super()._extract_embed_urls(url, webpage)
+        for series_id in re.findall(
+                r'<div[^>]+\bclass=[\'"][^\'"]*art19-web-player[^\'"]*[\'"][^>]+\bdata-series-id=[\'"]([\w-]+)[\'"]', webpage):
+            yield f'https://art19.com/shows/{series_id}'
+
+    def _real_extract(self, url):
+        series_id = self._match_id(url)
+        series_metadata = self._download_json(
+            f'https://art19.com/series/{series_id}', series_id, note='Downloading series metadata',
+            headers={'Accept': 'application/vnd.art19.v0+json'})
+
+        return {
+            '_type': 'playlist',
+            'entries': [
+                self.url_result(f'https://rss.art19.com/episodes/{episode_id}.mp3', Art19IE)
+                for episode_id in traverse_obj(series_metadata, ('series', 'episode_ids', ..., {str}))
+            ],
+            **traverse_obj(series_metadata, ('series', {
+                'id': ('id', {str}),
+                'display_id': ('slug', {str}),
+                'title': ('title', {str}),
+                'description': ('description_plain', {str}),
+                'timestamp': ('created_at', {parse_iso8601}),
+                'modified_timestamp': ('updated_at', {parse_iso8601}),
+            })),
+            'tags': traverse_obj(series_metadata, ('tags', ..., 'name', {str})),
+        }

yt_dlp/extractor/facebook.py

@@ -54,6 +54,7 @@ class FacebookIE(InfoExtractor):
                             )\?(?:.*?)(?:v|video_id|story_fbid)=|
                             [^/]+/videos/(?:[^/]+/)?|
                             [^/]+/posts/|
+                            events/(?:[^/]+/)?|
                             groups/[^/]+/(?:permalink|posts)/|
                             watchparty/
                         )|
@@ -399,6 +400,18 @@ class FacebookIE(InfoExtractor):
         },
         'playlist_count': 1,
         'skip': 'Requires logging in',
+    }, {
+        # data.event.cover_media_renderer.cover_video
+        'url': 'https://m.facebook.com/events/1509582499515440',
+        'info_dict': {
+            'id': '637246984455045',
+            'ext': 'mp4',
+            'title': 'ANALISI IN CAMPO OSCURO " Coaguli nel sangue dei vaccinati"',
+            'description': 'Other event by Comitato Liberi Pensatori on Tuesday, October 18 2022',
+            'thumbnail': r're:^https?://.*',
+            'uploader': 'Comitato Liberi Pensatori',
+            'uploader_id': '100065709540881',
+        },
     }]
     _SUPPORTED_PAGLETS_REGEX = r'(?:pagelet_group_mall|permalink_video_pagelet|hyperfeed_story_id_[0-9a-f]+)'
     _api_config = {
@@ -473,38 +486,10 @@ class FacebookIE(InfoExtractor):
                 r'data-sjs>({.*?ScheduledServerJS.*?})</script>', webpage)]
             post = traverse_obj(post_data, (
                 ..., 'require', ..., ..., ..., '__bbox', 'require', ..., ..., ..., '__bbox', 'result', 'data'), expected_type=dict) or []
-
-            automatic_captions, subtitles = {}, {}
-            subs_data = traverse_obj(post, (..., 'video', ..., 'attachments', ..., lambda k, v: (
-                k == 'media' and str(v['id']) == video_id and v['__typename'] == 'Video')))
-            is_video_broadcast = get_first(subs_data, 'is_video_broadcast', expected_type=bool)
-            captions = get_first(subs_data, 'video_available_captions_locales', 'captions_url')
-            if url_or_none(captions):  # if subs_data only had a 'captions_url'
-                locale = self._html_search_meta(['og:locale', 'twitter:locale'], webpage, 'locale', default='en_US')
-                subtitles[locale] = [{'url': captions}]
-            # or else subs_data had 'video_available_captions_locales', a list of dicts
-            for caption in traverse_obj(captions, (
-                {lambda x: sorted(x, key=lambda c: c['locale'])}, lambda _, v: v['captions_url'])
-            ):
-                lang = caption.get('localized_language') or ''
-                subs = {
-                    'url': caption['captions_url'],
-                    'name': format_field(caption, 'localized_country', f'{lang} (%s)', default=lang),
-                }
-                if caption.get('localized_creation_method') or is_video_broadcast:
-                    automatic_captions.setdefault(caption['locale'], []).append(subs)
-                else:
-                    subtitles.setdefault(caption['locale'], []).append(subs)
-
             media = traverse_obj(post, (..., 'attachments', ..., lambda k, v: (
                 k == 'media' and str(v['id']) == video_id and v['__typename'] == 'Video')), expected_type=dict)
             title = get_first(media, ('title', 'text'))
             description = get_first(media, ('creation_story', 'comet_sections', 'message', 'story', 'message', 'text'))
-            uploader_data = (
-                get_first(media, ('owner', {dict}))
-                or get_first(post, (..., 'video', lambda k, v: k == 'owner' and v['name']))
-                or get_first(post, ('node', 'actors', ..., {dict})) or {})
-
             page_title = title or self._html_search_regex((
                 r'<h2\s+[^>]*class="uiHeaderTitle"[^>]*>(?P<content>[^<]*)</h2>',
                 r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(?P<content>.*?)</span>',
@@ -513,11 +498,15 @@ class FacebookIE(InfoExtractor):
             description = description or self._html_search_meta(
                 ['description', 'og:description', 'twitter:description'],
                 webpage, 'description', default=None)
+            uploader_data = (
+                get_first(media, ('owner', {dict}))
+                or get_first(post, (..., 'video', lambda k, v: k == 'owner' and v['name']))
+                or get_first(post, ('node', 'actors', ..., {dict}))
+                or get_first(post, ('event', 'event_creator', {dict})) or {})
             uploader = uploader_data.get('name') or (
                 clean_html(get_element_by_id('fbPhotoPageAuthorName', webpage))
                 or self._search_regex(
                     (r'ownerName\s*:\s*"([^"]+)"', *self._og_regexes('title')), webpage, 'uploader', fatal=False))
-
             timestamp = int_or_none(self._search_regex(
                 r'<abbr[^>]+data-utime=["\'](\d+)', webpage,
                 'timestamp', default=None))
@@ -539,8 +528,6 @@ class FacebookIE(InfoExtractor):
                     webpage, 'view count', default=None)),
                 'concurrent_view_count': get_first(post, (
                     ('video', (..., ..., 'attachments', ..., 'media')), 'liveViewerCount', {int_or_none})),
-                'automatic_captions': automatic_captions,
-                'subtitles': subtitles,
             }
 
             info_json_ld = self._search_json_ld(webpage, video_id, default={})
@@ -638,6 +625,29 @@ class FacebookIE(InfoExtractor):
                                 'url': playable_url,
                             })
                     extract_dash_manifest(video, formats)
+
+                    automatic_captions, subtitles = {}, {}
+                    is_broadcast = traverse_obj(video, ('is_video_broadcast', {bool}))
+                    for caption in traverse_obj(video, (
+                        'video_available_captions_locales',
+                        {lambda x: sorted(x, key=lambda c: c['locale'])},
+                        lambda _, v: url_or_none(v['captions_url'])
+                    )):
+                        lang = caption.get('localized_language') or 'und'
+                        subs = {
+                            'url': caption['captions_url'],
+                            'name': format_field(caption, 'localized_country', f'{lang} (%s)', default=lang),
+                        }
+                        if caption.get('localized_creation_method') or is_broadcast:
+                            automatic_captions.setdefault(caption['locale'], []).append(subs)
+                        else:
+                            subtitles.setdefault(caption['locale'], []).append(subs)
+                    captions_url = traverse_obj(video, ('captions_url', {url_or_none}))
+                    if captions_url and not automatic_captions and not subtitles:
+                        locale = self._html_search_meta(
+                            ['og:locale', 'twitter:locale'], webpage, 'locale', default='en_US')
+                        (automatic_captions if is_broadcast else subtitles)[locale] = [{'url': captions_url}]
+
                     info = {
                         'id': v_id,
                         'formats': formats,
@@ -647,6 +657,8 @@ class FacebookIE(InfoExtractor):
                         'timestamp': traverse_obj(video, 'publish_time', 'creation_time', expected_type=int_or_none),
                         'duration': (float_or_none(video.get('playable_duration_in_ms'), 1000)
                                      or float_or_none(video.get('length_in_second'))),
+                        'automatic_captions': automatic_captions,
+                        'subtitles': subtitles,
                     }
                     process_formats(info)
                     description = try_get(video, lambda x: x['savable_description']['text'])
@@ -681,7 +693,8 @@ class FacebookIE(InfoExtractor):
                 for edge in edges:
                     parse_attachment(edge, key='node')
 
-                video = data.get('video') or {}
+                video = traverse_obj(data, (
+                    'event', 'cover_media_renderer', 'cover_video'), 'video', expected_type=dict) or {}
                 if video:
                     attachments = try_get(video, [
                         lambda x: x['story']['attachments'],

yt_dlp/extractor/vbox7.py

@@ -1,5 +1,6 @@
 from .common import InfoExtractor
-from ..utils import ExtractorError
+from ..utils import ExtractorError, base_url, int_or_none, url_basename
+from ..utils.traversal import traverse_obj
 
 
 class Vbox7IE(InfoExtractor):
@@ -19,7 +20,7 @@ class Vbox7IE(InfoExtractor):
     _GEO_COUNTRIES = ['BG']
     _TESTS = [{
         'url': 'http://vbox7.com/play:0946fff23c',
-        'md5': 'a60f9ab3a3a2f013ef9a967d5f7be5bf',
+        'md5': '50ca1f78345a9c15391af47d8062d074',
         'info_dict': {
             'id': '0946fff23c',
             'ext': 'mp4',
@@ -29,19 +30,25 @@ class Vbox7IE(InfoExtractor):
             'timestamp': 1470982814,
             'upload_date': '20160812',
             'uploader': 'zdraveibulgaria',
-        },
-        'params': {
-            'proxy': '127.0.0.1:8118',
+            'view_count': int,
+            'duration': 2640,
         },
     }, {
         'url': 'http://vbox7.com/play:249bb972c2',
-        'md5': '99f65c0c9ef9b682b97313e052734c3f',
+        'md5': 'da1dd2eb245200cb86e6d09d43232116',
         'info_dict': {
             'id': '249bb972c2',
             'ext': 'mp4',
             'title': 'Смях! Чудо - чист за секунди - Скрита камера',
+            'uploader': 'svideteliat_ot_varshava',
+            'view_count': int,
+            'timestamp': 1360215023,
+            'thumbnail': 'https://i49.vbox7.com/design/iconci/png/noimg6.png',
+            'description': 'Смях! Чудо - чист за секунди - Скрита камера',
+            'upload_date': '20130207',
+            'duration': 83,
         },
-        'skip': 'georestricted',
+        'expected_warnings': ['Failed to download m3u8 information'],
     }, {
         'url': 'http://vbox7.com/emb/external.php?vid=a240d20f9c&autoplay=1',
         'only_matching': True,
@@ -53,41 +60,38 @@ class Vbox7IE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        response = self._download_json(
-            'https://www.vbox7.com/ajax/video/nextvideo.php?vid=%s' % video_id,
-            video_id)
+        data = self._download_json(
+            'https://www.vbox7.com/aj/player/item/options', video_id,
+            query={'vid': video_id})['options']
 
-        if 'error' in response:
-            raise ExtractorError(
-                '%s said: %s' % (self.IE_NAME, response['error']), expected=True)
+        src_url = data.get('src')
+        if src_url in (None, '', 'blank'):
+            raise ExtractorError('Video is unavailable', expected=True)
 
-        video = response['options']
+        fmt_base = url_basename(src_url).rsplit('.', 1)[0].rsplit('_', 1)[0]
+        if fmt_base == 'vn':
+            self.raise_geo_restricted()
 
-        title = video['title']
-        video_url = video['src']
+        fmt_base = base_url(src_url) + fmt_base
 
-        if '/na.mp4' in video_url:
-            self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
-
-        uploader = video.get('uploader')
-
-        webpage = self._download_webpage(
-            'http://vbox7.com/play:%s' % video_id, video_id, fatal=None)
-
-        info = {}
-
-        if webpage:
-            info = self._search_json_ld(
-                webpage.replace('"/*@context"', '"@context"'), video_id,
-                fatal=False)
-
-        info.update({
-            'id': video_id,
-            'title': title,
-            'url': video_url,
-            'uploader': uploader,
-            'thumbnail': self._proto_relative_url(
-                info.get('thumbnail') or self._og_search_thumbnail(webpage),
-                'http:'),
+        formats = self._extract_m3u8_formats(
+            f'{fmt_base}.m3u8', video_id, m3u8_id='hls', fatal=False)
+        # TODO: Add MPD formats, when dash range support is added
+        for res in traverse_obj(data, ('resolutions', lambda _, v: v != 0, {int})):
+            formats.append({
+                'url': f'{fmt_base}_{res}.mp4',
+                'format_id': f'http-{res}',
+                'height': res,
             })
-        return info
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            **self._search_json_ld(self._download_webpage(
+                f'https://www.vbox7.com/play:{video_id}', video_id, fatal=False) or '', video_id, fatal=False),
+            **traverse_obj(data, {
+                'title': ('title', {str}),
+                'uploader': ('uploader', {str}),
+                'duration': ('duration', {int_or_none}),
+            }),
+        }