@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/nuvid.py

@@ -0,0 +1,99 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    int_or_none,
+    strip_or_none,
+    traverse_obj,
+    url_or_none,
+)
+
+
+class NuvidIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www|m)\.nuvid\.com/video/(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'https://www.nuvid.com/video/6513023/italian-babe',
+        'md5': '772d2f8288f3d3c5c45f7a41761c7844',
+        'info_dict': {
+            'id': '6513023',
+            'ext': 'mp4',
+            'title': 'italian babe',
+            'duration': 321.0,
+            'age_limit': 18,
+            'thumbnail': r're:https?://.+\.jpg',
+        }
+    }, {
+        'url': 'https://m.nuvid.com/video/6523263',
+        'md5': 'ebd22ce8e47e1d9a4d0756a15c67da52',
+        'info_dict': {
+            'id': '6523263',
+            'ext': 'mp4',
+            'title': 'Slut brunette college student anal dorm',
+            'duration': 421.0,
+            'age_limit': 18,
+            'thumbnail': r're:https?://.+\.jpg',
+            'thumbnails': list,
+        }
+    }, {
+        'url': 'http://m.nuvid.com/video/6415801/',
+        'md5': '638d5ececb138d5753593f751ae3f697',
+        'info_dict': {
+            'id': '6415801',
+            'ext': 'mp4',
+            'title': 'My best friend wanted to fuck my wife for a long time',
+            'duration': 1882,
+            'age_limit': 18,
+            'thumbnail': r're:https?://.+\.jpg',
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        qualities = {
+            'lq': '360p',
+            'hq': '720p',
+        }
+
+        json_url = f'https://www.nuvid.com/player_config_json/?vid={video_id}&aid=0&domain_id=0&embed=0&check_speed=0'
+        video_data = self._download_json(
+            json_url, video_id, headers={
+                'Accept': 'application/json, text/javascript, */*; q = 0.01',
+                'Content-Type': 'application/x-www-form-urlencoded; charset=utf-8',
+            })
+
+        webpage = self._download_webpage(
+            'http://m.nuvid.com/video/%s' % (video_id, ),
+            video_id, 'Downloading video page', fatal=False) or ''
+
+        title = strip_or_none(video_data.get('title') or self._html_search_regex(
+            (r'''<span\s[^>]*?\btitle\s*=\s*(?P<q>"|'|\b)(?P<title>[^"]+)(?P=q)\s*>''',
+                r'''<div\s[^>]*?\bclass\s*=\s*(?P<q>"|'|\b)thumb-holder video(?P=q)>\s*<h5\b[^>]*>(?P<title>[^<]+)</h5''',
+                r'''<span\s[^>]*?\bclass\s*=\s*(?P<q>"|'|\b)title_thumb(?P=q)>(?P<title>[^<]+)</span'''),
+            webpage, 'title', group='title'))
+
+        formats = [{
+            'url': source,
+            'format_id': qualities.get(quality),
+            'height': int_or_none(qualities.get(quality)[:-1]),
+        } for quality, source in video_data.get('files').items() if source]
+
+        self._check_formats(formats, video_id)
+
+        duration = parse_duration(traverse_obj(video_data, 'duration', 'duration_format'))
+        thumbnails = [
+            {'url': thumb_url} for thumb_url in re.findall(
+                r'<div\s+class\s*=\s*"video-tmb-wrap"\s*>\s*<img\s+src\s*=\s*"([^"]+)"\s*/>', webpage)
+            if url_or_none(thumb_url)]
+        if url_or_none(video_data.get('poster')):
+            thumbnails.append({'url': video_data['poster'], 'preference': 1})
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': title,
+            'thumbnails': thumbnails,
+            'duration': duration,
+            'age_limit': 18,
+        }

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

@@ -0,0 +1,420 @@
+import json
+import uuid
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    clean_html,
+    determine_ext,
+    extract_attributes,
+    float_or_none,
+    get_elements_html_by_class,
+    int_or_none,
+    merge_dicts,
+    mimetype2ext,
+    parse_iso8601,
+    remove_end,
+    remove_start,
+    str_or_none,
+    traverse_obj,
+    url_or_none,
+)
+
+
+class NYTimesBaseIE(InfoExtractor):
+    _DNS_NAMESPACE = uuid.UUID('36dd619a-56dc-595b-9e09-37f4152c7b5d')
+    _TOKEN = 'MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAuNIzKBOFB77aT/jN/FQ+/QVKWq5V1ka1AYmCR9hstz1pGNPH5ajOU9gAqta0T89iPnhjwla+3oec/Z3kGjxbpv6miQXufHFq3u2RC6HyU458cLat5kVPSOQCe3VVB5NRpOlRuwKHqn0txfxnwSSj8mqzstR997d3gKB//RO9zE16y3PoWlDQXkASngNJEWvL19iob/xwAkfEWCjyRILWFY0JYX3AvLMSbq7wsqOCE5srJpo7rRU32zsByhsp1D5W9OYqqwDmflsgCEQy2vqTsJjrJohuNg+urMXNNZ7Y3naMoqttsGDrWVxtPBafKMI8pM2ReNZBbGQsQXRzQNo7+QIDAQAB'
+    _GRAPHQL_API = 'https://samizdat-graphql.nytimes.com/graphql/v2'
+    _GRAPHQL_QUERY = '''query VideoQuery($id: String!) {
+  video(id: $id) {
+    ... on Video {
+      bylines {
+        renderedRepresentation
+      }
+      duration
+      firstPublished
+      promotionalHeadline
+      promotionalMedia {
+        ... on Image {
+          crops {
+            name
+            renditions {
+              name
+              width
+              height
+              url
+            }
+          }
+        }
+      }
+      renditions {
+        type
+        width
+        height
+        url
+        bitrate
+      }
+      summary
+    }
+  }
+}'''
+
+    def _call_api(self, media_id):
+        # reference: `id-to-uri.js`
+        video_uuid = uuid.uuid5(self._DNS_NAMESPACE, 'video')
+        media_uuid = uuid.uuid5(video_uuid, media_id)
+
+        return traverse_obj(self._download_json(
+            self._GRAPHQL_API, media_id, 'Downloading JSON from GraphQL API', data=json.dumps({
+                'query': self._GRAPHQL_QUERY,
+                'variables': {'id': f'nyt://video/{media_uuid}'},
+            }, separators=(',', ':')).encode(), headers={
+                'Content-Type': 'application/json',
+                'Nyt-App-Type': 'vhs',
+                'Nyt-App-Version': 'v3.52.21',
+                'Nyt-Token': self._TOKEN,
+                'Origin': 'https://nytimes.com',
+            }, fatal=False), ('data', 'video', {dict})) or {}
+
+    def _extract_thumbnails(self, thumbs):
+        return traverse_obj(thumbs, (lambda _, v: url_or_none(v['url']), {
+            'url': 'url',
+            'width': ('width', {int_or_none}),
+            'height': ('height', {int_or_none}),
+        }), default=None)
+
+    def _extract_formats_and_subtitles(self, video_id, content_media_json):
+        urls = []
+        formats = []
+        subtitles = {}
+        for video in traverse_obj(content_media_json, ('renditions', ..., {dict})):
+            video_url = video.get('url')
+            format_id = video.get('type')
+            if not video_url or format_id == 'thumbs' or video_url in urls:
+                continue
+            urls.append(video_url)
+            ext = mimetype2ext(video.get('mimetype')) or determine_ext(video_url)
+            if ext == 'm3u8':
+                m3u8_fmts, m3u8_subs = self._extract_m3u8_formats_and_subtitles(
+                    video_url, video_id, 'mp4', 'm3u8_native',
+                    m3u8_id=format_id or 'hls', fatal=False)
+                formats.extend(m3u8_fmts)
+                self._merge_subtitles(m3u8_subs, target=subtitles)
+            elif ext == 'mpd':
+                continue  # all mpd urls give 404 errors
+            else:
+                formats.append({
+                    'url': video_url,
+                    'format_id': format_id,
+                    'vcodec': video.get('videoencoding') or video.get('video_codec'),
+                    'width': int_or_none(video.get('width')),
+                    'height': int_or_none(video.get('height')),
+                    'filesize': traverse_obj(video, (
+                        ('file_size', 'fileSize'), (None, ('value')), {int_or_none}), get_all=False),
+                    'tbr': int_or_none(video.get('bitrate'), 1000) or None,
+                    'ext': ext,
+                })
+
+        return formats, subtitles
+
+    def _extract_video(self, media_id):
+        data = self._call_api(media_id)
+        formats, subtitles = self._extract_formats_and_subtitles(media_id, data)
+
+        return {
+            'id': media_id,
+            'title': data.get('promotionalHeadline'),
+            'description': data.get('summary'),
+            'timestamp': parse_iso8601(data.get('firstPublished')),
+            'duration': float_or_none(data.get('duration'), scale=1000),
+            'creator': ', '.join(traverse_obj(data, (  # TODO: change to 'creators'
+                'bylines', ..., 'renderedRepresentation', {lambda x: remove_start(x, 'By ')}))),
+            'formats': formats,
+            'subtitles': subtitles,
+            'thumbnails': self._extract_thumbnails(
+                traverse_obj(data, ('promotionalMedia', 'crops', ..., 'renditions', ...))),
+        }
+
+
+class NYTimesIE(NYTimesBaseIE):
+    _VALID_URL = r'https?://(?:(?:www\.)?nytimes\.com/video/(?:[^/]+/)+?|graphics8\.nytimes\.com/bcvideo/\d+(?:\.\d+)?/iframe/embed\.html\?videoId=)(?P<id>\d+)'
+    _EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>']
+    _TESTS = [{
+        'url': 'http://www.nytimes.com/video/opinion/100000002847155/verbatim-what-is-a-photocopier.html?playlistId=100000001150263',
+        'md5': 'a553aa344014e3723d33893d89d4defc',
+        'info_dict': {
+            'id': '100000002847155',
+            'ext': 'mp4',
+            'title': 'Verbatim: What Is a Photocopier?',
+            'description': 'md5:93603dada88ddbda9395632fdc5da260',
+            'timestamp': 1398646132,
+            'upload_date': '20140428',
+            'creator': 'Brett Weiner',
+            'thumbnail': r're:https?://\w+\.nyt.com/images/.+\.jpg',
+            'duration': 419,
+        },
+    }, {
+        'url': 'http://www.nytimes.com/video/travel/100000003550828/36-hours-in-dubai.html',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        return self._extract_video(video_id)
+
+
+class NYTimesArticleIE(NYTimesBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?nytimes\.com/\d{4}/\d{2}/\d{2}/(?!books|podcasts)[^/?#]+/(?:\w+/)?(?P<id>[^./?#]+)(?:\.html)?'
+    _TESTS = [{
+        'url': 'http://www.nytimes.com/2015/04/14/business/owner-of-gravity-payments-a-credit-card-processor-is-setting-a-new-minimum-wage-70000-a-year.html?_r=0',
+        'md5': '3eb5ddb1d6f86254fe4f233826778737',
+        'info_dict': {
+            'id': '100000003628438',
+            'ext': 'mp4',
+            'title': 'One Company’s New Minimum Wage: $70,000 a Year',
+            'description': 'md5:89ba9ab67ca767bb92bf823d1f138433',
+            'timestamp': 1429047468,
+            'upload_date': '20150414',
+            'uploader': 'Matthew Williams',
+            'creator': 'Patricia Cohen',
+            'thumbnail': r're:https?://\w+\.nyt.com/images/.*\.jpg',
+            'duration': 119.0,
+        },
+    }, {
+        # article with audio and no video
+        'url': 'https://www.nytimes.com/2023/09/29/health/mosquitoes-genetic-engineering.html',
+        'md5': '2365b3555c8aa7f4dd34ca735ad02e6a',
+        'info_dict': {
+            'id': '100000009110381',
+            'ext': 'mp3',
+            'title': 'The Gamble: Can Genetically Modified Mosquitoes End Disease?',
+            'description': 'md5:9ff8b47acbaf7f3ca8c732f5c815be2e',
+            'timestamp': 1695960700,
+            'upload_date': '20230929',
+            'creator': 'Stephanie Nolen, Natalija Gormalova',
+            'thumbnail': r're:https?://\w+\.nyt.com/images/.*\.jpg',
+            'duration': 1322,
+        },
+    }, {
+        'url': 'https://www.nytimes.com/2023/11/29/business/dealbook/kamala-harris-biden-voters.html',
+        'md5': '3eb5ddb1d6f86254fe4f233826778737',
+        'info_dict': {
+            'id': '100000009202270',
+            'ext': 'mp4',
+            'title': 'Kamala Harris Defends Biden Policies, but Says ‘More Work’ Needed to Reach Voters',
+            'description': 'md5:de4212a7e19bb89e4fb14210ca915f1f',
+            'timestamp': 1701290997,
+            'upload_date': '20231129',
+            'uploader': 'By The New York Times',
+            'creator': 'Katie Rogers',
+            'thumbnail': r're:https?://\w+\.nyt.com/images/.*\.jpg',
+            'duration': 97.631,
+        },
+        'params': {
+            'skip_download': 'm3u8',
+        },
+    }, {
+        # multiple videos in the same article
+        'url': 'https://www.nytimes.com/2023/12/02/business/air-traffic-controllers-safety.html',
+        'info_dict': {
+            'id': 'air-traffic-controllers-safety',
+            'title': 'Drunk and Asleep on the Job: Air Traffic Controllers Pushed to the Brink',
+            'description': 'md5:549e5a5e935bf7d048be53ba3d2c863d',
+            'upload_date': '20231202',
+            'creator': 'Emily Steel, Sydney Ember',
+            'timestamp': 1701511264,
+        },
+        'playlist_count': 3,
+    }, {
+        'url': 'https://www.nytimes.com/2023/12/02/business/media/netflix-squid-game-challenge.html',
+        'only_matching': True,
+    }]
+
+    def _extract_content_from_block(self, block):
+        details = traverse_obj(block, {
+            'id': ('sourceId', {str}),
+            'uploader': ('bylines', ..., 'renderedRepresentation', {str}),
+            'duration': (None, (('duration', {lambda x: float_or_none(x, scale=1000)}), ('length', {int_or_none}))),
+            'timestamp': ('firstPublished', {parse_iso8601}),
+            'series': ('podcastSeries', {str}),
+        }, get_all=False)
+
+        formats, subtitles = self._extract_formats_and_subtitles(details.get('id'), block)
+        # audio articles will have an url and no formats
+        url = traverse_obj(block, ('fileUrl', {url_or_none}))
+        if not formats and url:
+            formats.append({'url': url, 'vcodec': 'none'})
+
+        return {
+            **details,
+            'thumbnails': self._extract_thumbnails(traverse_obj(
+                block, ('promotionalMedia', 'crops', ..., 'renditions', ...))),
+            'formats': formats,
+            'subtitles': subtitles
+        }
+
+    def _real_extract(self, url):
+        page_id = self._match_id(url)
+        webpage = self._download_webpage(url, page_id)
+        art_json = self._search_json(
+            r'window\.__preloadedData\s*=', webpage, 'media details', page_id,
+            transform_source=lambda x: x.replace('undefined', 'null'))['initialData']['data']['article']
+
+        blocks = traverse_obj(art_json, (
+            'sprinkledBody', 'content', ..., ('ledeMedia', None),
+            lambda _, v: v['__typename'] in ('Video', 'Audio')))
+        if not blocks:
+            raise ExtractorError('Unable to extract any media blocks from webpage')
+
+        common_info = {
+            'title': remove_end(self._html_extract_title(webpage), ' - The New York Times'),
+            'description': traverse_obj(art_json, (
+                'sprinkledBody', 'content', ..., 'summary', 'content', ..., 'text', {str}),
+                get_all=False) or self._html_search_meta(['og:description', 'twitter:description'], webpage),
+            'timestamp': traverse_obj(art_json, ('firstPublished', {parse_iso8601})),
+            'creator': ', '.join(
+                traverse_obj(art_json, ('bylines', ..., 'creators', ..., 'displayName'))),  # TODO: change to 'creators' (list)
+            'thumbnails': self._extract_thumbnails(traverse_obj(
+                art_json, ('promotionalMedia', 'assetCrops', ..., 'renditions', ...))),
+        }
+
+        entries = []
+        for block in blocks:
+            entries.append(merge_dicts(self._extract_content_from_block(block), common_info))
+
+        if len(entries) > 1:
+            return self.playlist_result(entries, page_id, **common_info)
+
+        return {
+            'id': page_id,
+            **entries[0],
+        }
+
+
+class NYTimesCookingIE(NYTimesBaseIE):
+    IE_NAME = 'NYTimesCookingGuide'
+    _VALID_URL = r'https?://cooking\.nytimes\.com/guides/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://cooking.nytimes.com/guides/13-how-to-cook-a-turkey',
+        'info_dict': {
+            'id': '13-how-to-cook-a-turkey',
+            'title': 'How to Cook a Turkey',
+            'description': 'md5:726cfd3f9b161bdf5c279879e8050ca0',
+        },
+        'playlist_count': 2,
+    }, {
+        # single video example
+        'url': 'https://cooking.nytimes.com/guides/50-how-to-make-mac-and-cheese',
+        'md5': '64415805fe0b8640fce6b0b9def5989a',
+        'info_dict': {
+            'id': '100000005835845',
+            'ext': 'mp4',
+            'title': 'How to Make Mac and Cheese',
+            'description': 'md5:b8f2f33ec1fb7523b21367147c9594f1',
+            'timestamp': 1522950315,
+            'upload_date': '20180405',
+            'duration': 9.51,
+            'creator': 'Alison Roman',
+            'thumbnail': r're:https?://\w+\.nyt.com/images/.*\.jpg',
+        },
+    }, {
+        'url': 'https://cooking.nytimes.com/guides/20-how-to-frost-a-cake',
+        'md5': '64415805fe0b8640fce6b0b9def5989a',
+        'info_dict': {
+            'id': '20-how-to-frost-a-cake',
+            'title': 'How to Frost a Cake',
+            'description': 'md5:a31fe3b98a8ce7b98aae097730c269cd',
+        },
+        'playlist_count': 8,
+    }]
+
+    def _real_extract(self, url):
+        page_id = self._match_id(url)
+        webpage = self._download_webpage(url, page_id)
+        title = self._html_search_meta(['og:title', 'twitter:title'], webpage)
+        description = self._html_search_meta(['og:description', 'twitter:description'], webpage)
+
+        lead_video_id = self._search_regex(
+            r'data-video-player-id="(\d+)"></div>', webpage, 'lead video')
+        media_ids = traverse_obj(
+            get_elements_html_by_class('video-item', webpage), (..., {extract_attributes}, 'data-video-id'))
+
+        if media_ids:
+            media_ids.append(lead_video_id)
+            return self.playlist_result(
+                [self._extract_video(media_id) for media_id in media_ids], page_id, title, description)
+
+        return {
+            **self._extract_video(lead_video_id),
+            'title': title,
+            'description': description,
+            'creator': self._search_regex(  # TODO: change to 'creators'
+                r'<span itemprop="author">([^<]+)</span></p>', webpage, 'author', default=None),
+        }
+
+
+class NYTimesCookingRecipeIE(InfoExtractor):
+    _VALID_URL = r'https?://cooking\.nytimes\.com/recipes/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://cooking.nytimes.com/recipes/1017817-cranberry-curd-tart',
+        'md5': '579e83bbe8e61e9de67f80edba8a78a8',
+        'info_dict': {
+            'id': '1017817',
+            'ext': 'mp4',
+            'title': 'Cranberry Curd Tart',
+            'description': 'md5:ad77a3fc321db636256d4343c5742152',
+            'timestamp': 1447804800,
+            'upload_date': '20151118',
+            'creator': 'David Tanis',
+            'thumbnail': r're:https?://\w+\.nyt.com/images/.*\.jpg',
+        },
+    }, {
+        'url': 'https://cooking.nytimes.com/recipes/1024781-neapolitan-checkerboard-cookies',
+        'md5': '58df35998241dcf0620e99e646331b42',
+        'info_dict': {
+            'id': '1024781',
+            'ext': 'mp4',
+            'title': 'Neapolitan Checkerboard Cookies',
+            'description': 'md5:ba12394c585ababea951cb6d2fcc6631',
+            'timestamp': 1701302400,
+            'upload_date': '20231130',
+            'creator': 'Sue Li',
+            'thumbnail': r're:https?://\w+\.nyt.com/images/.*\.jpg',
+        },
+    }, {
+        'url': 'https://cooking.nytimes.com/recipes/1019516-overnight-oats',
+        'md5': '2fe7965a3adc899913b8e25ada360823',
+        'info_dict': {
+            'id': '1019516',
+            'ext': 'mp4',
+            'timestamp': 1546387200,
+            'description': 'md5:8856ce10239161bd2596ac335b9f9bfb',
+            'upload_date': '20190102',
+            'title': 'Overnight Oats',
+            'creator': 'Genevieve Ko',
+            'thumbnail': r're:https?://\w+\.nyt.com/images/.*\.jpg',
+        },
+    }]
+
+    def _real_extract(self, url):
+        page_id = self._match_id(url)
+        webpage = self._download_webpage(url, page_id)
+        recipe_data = self._search_nextjs_data(webpage, page_id)['props']['pageProps']['recipe']
+
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+            recipe_data['videoSrc'], page_id, 'mp4', m3u8_id='hls')
+
+        return {
+            **traverse_obj(recipe_data, {
+                'id': ('id', {str_or_none}),
+                'title': ('title', {str}),
+                'description': ('topnote', {clean_html}),
+                'timestamp': ('publishedAt', {int_or_none}),
+                'creator': ('contentAttribution', 'cardByline', {str}),
+            }),
+            'formats': formats,
+            'subtitles': subtitles,
+            'thumbnails': [{'url': thumb_url} for thumb_url in traverse_obj(
+                recipe_data, ('image', 'crops', 'recipe', ..., {url_or_none}))],
+        }

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

@@ -0,0 +1,123 @@
+import json
+
+from .brightcove import BrightcoveNewIE
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    ExtractorError,
+    traverse_obj
+)
+
+
+class NZHeraldIE(InfoExtractor):
+    IE_NAME = 'nzherald'
+    _VALID_URL = r'https?://(?:www\.)?nzherald\.co\.nz/[\w\/-]+\/(?P<id>[A-Z0-9]+)'
+    _TESTS = [
+        {
+            # Video accessible under 'video' key
+            'url': 'https://www.nzherald.co.nz/nz/queen-elizabeth-death-nz-public-holiday-announced-for-september-26/CEOPBSXO2JDCLNK3H7E3BIE2FA/',
+            'info_dict': {
+                'id': '6312191736112',
+                'ext': 'mp4',
+                'title': 'Focus: PM holds post-Cabinet press conference',
+                'duration': 238.08,
+                'upload_date': '20220912',
+                'uploader_id': '1308227299001',
+                'timestamp': 1662957159,
+                'tags': [],
+                'thumbnail': r're:https?://.*\.jpg$',
+                'description': 'md5:2f17713fcbfcfbe38bb9e7dfccbb0f2e',
+            }
+        }, {
+            # Webpage has brightcove embed player url
+            'url': 'https://www.nzherald.co.nz/travel/pencarrow-coastal-trail/HDVTPJEPP46HJ2UEMK4EGD2DFI/',
+            'info_dict': {
+                'id': '6261791733001',
+                'ext': 'mp4',
+                'title': 'Pencarrow Coastal Trail',
+                'timestamp': 1625102897,
+                'upload_date': '20210701',
+                'uploader_id': '1308227299001',
+                'description': 'md5:d361aaa0c6498f7ac1bc4fc0a0aec1e4',
+                'thumbnail': r're:https?://.*\.jpg$',
+                'tags': ['travel', 'video'],
+                'duration': 43.627,
+            }
+        }, {
+            # two video embeds of the same video
+            'url': 'https://www.nzherald.co.nz/nz/truck-driver-captured-cutting-off-motorist-on-state-highway-1-in-canterbury/FIHNJB7PLLPHWQPK4S7ZBDUC4I/',
+            'info_dict': {
+                'id': '6251114530001',
+                'ext': 'mp4',
+                'title': 'Truck travelling north from Rakaia runs car off road',
+                'timestamp': 1619730509,
+                'upload_date': '20210429',
+                'uploader_id': '1308227299001',
+                'description': 'md5:4cae7dfb7613ac4c73b9e73a75c6b5d7'
+            },
+            'skip': 'video removed',
+        }, {
+            # customVideo embed requiring additional API call
+            'url': 'https://www.nzherald.co.nz/nz/politics/reserve-bank-rejects-political-criticisms-stands-by-review/2JO5Q4WLZRCBBNWTLACZMOP4RA/',
+            'info_dict': {
+                'id': '6315123873112',
+                'ext': 'mp4',
+                'timestamp': 1667862725,
+                'title': 'Focus: Luxon on re-appointment of Reserve Bank governor Adrian Orr',
+                'upload_date': '20221107',
+                'description': 'md5:df2f1f7033a8160c66e28e4743f5d934',
+                'uploader_id': '1308227299001',
+                'tags': ['video', 'nz herald focus', 'politics', 'politics videos'],
+                'thumbnail': r're:https?://.*\.jpg$',
+                'duration': 99.584,
+            }
+        }, {
+            'url': 'https://www.nzherald.co.nz/kahu/kaupapa-companies-my-taiao-supporting-maori-in-study-and-business/PQBO2J25WCG77VGRX7W7BVYEAI/',
+            'only_matching': True
+        }, {
+            'url': 'https://nzherald.co.nz/the-country/video/focus-nzs-first-mass-covid-19-vaccination-event/N5I7IL3BRFLZSD33TLDLYJDGK4/',
+            'only_matching': True
+        }, {
+            'url': 'https://www.nzherald.co.nz/the-vision-is-clear/news/tvic-damian-roper-planting-trees-an-addiction/AN2AAEPNRK5VLISDWQAJZB6ATQ',
+            'only_matching': True
+        }
+    ]
+
+    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1308227299001/S1BXZn8t_default/index.html?videoId=%s'
+
+    def _extract_bc_embed_url(self, webpage):
+        """The initial webpage may include the brightcove player embed url"""
+        bc_url = BrightcoveNewIE._extract_url(self, webpage)
+        return bc_url or self._search_regex(
+            r'(?:embedUrl)\"\s*:\s*\"(?P<embed_url>%s)' % BrightcoveNewIE._VALID_URL,
+            webpage, 'embed url', default=None, group='embed_url')
+
+    def _real_extract(self, url):
+        article_id = self._match_id(url)
+        webpage = self._download_webpage(url, article_id)
+        bc_url = self._extract_bc_embed_url(webpage)
+
+        if not bc_url:
+            fusion_metadata = self._parse_json(
+                self._search_regex(r'Fusion\.globalContent\s*=\s*({.+?})\s*;', webpage, 'fusion metadata'), article_id)
+
+            video_metadata = fusion_metadata.get('video')
+            if not video_metadata:
+                custom_video_id = traverse_obj(fusion_metadata, ('customVideo', 'embed', 'id'), expected_type=str)
+                if custom_video_id:
+                    video_metadata = self._download_json(
+                        'https://www.nzherald.co.nz/pf/api/v3/content/fetch/full-content-by-id', article_id,
+                        query={'query': json.dumps({'id': custom_video_id, 'site': 'nzh'}), '_website': 'nzh'})
+            bc_video_id = traverse_obj(
+                video_metadata or fusion_metadata,  # fusion metadata is the video metadata for video-only pages
+                'brightcoveId', ('content_elements', ..., 'referent', 'id'),
+                get_all=False, expected_type=compat_str)
+
+            if not bc_video_id:
+                if isinstance(video_metadata, dict) and len(video_metadata) == 0:
+                    raise ExtractorError('This article does not have a video.', expected=True)
+                else:
+                    raise ExtractorError('Failed to extract brightcove video id')
+            bc_url = self.BRIGHTCOVE_URL_TEMPLATE % bc_video_id
+
+        return self.url_result(bc_url, 'BrightcoveNew')