Fix 5cc0a8fd2e

Authored by: bashonly

yt_dlp/extractor/_extractors.py

@@ -719,6 +719,10 @@ from .hidive import HiDiveIE
 from .historicfilms import HistoricFilmsIE
 from .hitbox import HitboxIE, HitboxLiveIE
 from .hitrecord import HitRecordIE
+from .hollywoodreporter import (
+    HollywoodReporterIE,
+    HollywoodReporterPlaylistIE,
+)
 from .holodex import HolodexIE
 from .hotnewhiphop import HotNewHipHopIE
 from .hotstar import (
@@ -1393,6 +1397,7 @@ from .periscope import (
     PeriscopeIE,
     PeriscopeUserIE,
 )
+from .pgatour import PGATourIE
 from .philharmoniedeparis import PhilharmonieDeParisIE
 from .phoenix import PhoenixIE
 from .photobucket import PhotobucketIE

yt_dlp/extractor/generic.py

@@ -2188,7 +2188,6 @@ class GenericIE(InfoExtractor):
     def _extra_manifest_info(self, info, manifest_url):
         fragment_query = self._configuration_arg('fragment_query', [None], casesense=True)[0]
         if fragment_query is not None:
-            fragment_query = self._configuration_arg('fragment_query', casesense=True)[0]
             info['extra_param_to_segment_url'] = (
                 urllib.parse.urlparse(fragment_query).query or fragment_query
                 or urllib.parse.urlparse(manifest_url).query or None)

yt_dlp/extractor/hollywoodreporter.py

@@ -0,0 +1,72 @@
+import functools
+import re
+
+from .common import InfoExtractor
+from .jwplatform import JWPlatformIE
+from ..utils import (
+    ExtractorError,
+    OnDemandPagedList,
+    extract_attributes,
+    get_element_by_class,
+    get_element_html_by_class,
+)
+
+
+class HollywoodReporterIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?hollywoodreporter\.com/video/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://www.hollywoodreporter.com/video/chris-pine-michelle-rodriguez-dungeons-dragons-cast-directors-on-what-it-took-to-make-film-sxsw-2023/',
+        'info_dict': {
+            'id': 'zH4jZaR5',
+            'ext': 'mp4',
+            'title': 'md5:a9a1c073770a32f178955997712c4bd9',
+            'description': 'The cast and directors of \'Dungeons & Dragons: Honor Among Thieves\' talk about their new film.',
+            'thumbnail': 'https://cdn.jwplayer.com/v2/media/zH4jZaR5/poster.jpg?width=720',
+            'upload_date': '20230312',
+            'timestamp': 1678586423,
+            'duration': 242.0,
+        },
+        'params': {'skip_download': 'm3u8'},
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        data = extract_attributes(get_element_html_by_class('vlanding-video-card__link', webpage) or '')
+        video_id = data['data-video-showcase-trigger']
+        showcase_type = data['data-video-showcase-type']
+
+        if showcase_type == 'jwplayer':
+            return self.url_result(f'jwplatform:{video_id}', JWPlatformIE)
+        elif showcase_type == 'youtube':
+            return self.url_result(video_id, 'Youtube')
+        else:
+            raise ExtractorError(f'Unsupported showcase type "{showcase_type}"')
+
+
+class HollywoodReporterPlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?hollywoodreporter\.com/vcategory/(?P<slug>[\w-]+)-(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.hollywoodreporter.com/vcategory/heat-vision-breakdown-57822/',
+        'playlist_mincount': 109,
+        'info_dict': {
+            'id': '57822',
+            'title': 'heat-vision-breakdown',
+        }
+    }]
+
+    def _fetch_page(self, slug, pl_id, page):
+        page += 1
+        webpage = self._download_webpage(
+            f'https://www.hollywoodreporter.com/vcategory/{slug}-{pl_id}/page/{page}/',
+            pl_id, note=f'Downloading playlist page {page}')
+        section = get_element_by_class('video-playlist-river', webpage) or ''
+
+        for url in re.findall(r'<a[^>]+href="([^"]+)"[^>]+class="c-title__link', section):
+            yield self.url_result(url, HollywoodReporterIE)
+
+    def _real_extract(self, url):
+        slug, pl_id = self._match_valid_url(url).group('slug', 'id')
+        return self.playlist_result(
+            OnDemandPagedList(functools.partial(self._fetch_page, slug, pl_id), 15), pl_id, slug)

yt_dlp/extractor/pgatour.py

@@ -0,0 +1,47 @@
+from .brightcove import BrightcoveNewIE
+from .common import InfoExtractor
+
+
+class PGATourIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?pgatour\.com/video/[\w-]+/(?P<tc>T)?(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.pgatour.com/video/competition/T6322447785112/adam-hadwin-2023-the-players-round-4-18th-hole-shot-1',
+        'info_dict': {
+            'id': '6322447785112',
+            'ext': 'mp4',
+            'title': 'Adam Hadwin | 2023 THE PLAYERS | Round 4 | 18th hole | Shot 1',
+            'uploader_id': '6116716431001',
+            'upload_date': '20230312',
+            'timestamp': 1678653136,
+            'duration': 20.011,
+            'thumbnail': r're:^https://.+\.jpg',
+            'tags': 'count:7',
+        },
+        'params': {'skip_download': 'm3u8'},
+    }, {
+        'url': 'https://www.pgatour.com/video/features/6322506425112/follow-the-players-trophy-on-championship-sunday',
+        'info_dict': {
+            'id': '6322506425112',
+            'ext': 'mp4',
+            'title': 'Follow THE PLAYERS trophy on Championship Sunday',
+            'description': 'md5:4d29e4bdfa03694a0ebfd08950398568',
+            'uploader_id': '6082840763001',
+            'upload_date': '20230313',
+            'timestamp': 1678739835,
+            'duration': 123.435,
+            'thumbnail': r're:^https://.+\.jpg',
+            'tags': 'count:8',
+        },
+        'params': {'skip_download': 'm3u8'},
+    }]
+
+    def _real_extract(self, url):
+        video_id, is_tourcast = self._match_valid_url(url).group('id', 'tc')
+
+        # From https://www.pgatour.com/_next/static/chunks/pages/_app-8bcf849560daf38d.js
+        account_id = '6116716431001' if is_tourcast else '6082840763001'
+        player_id = 'Vsd5Umu8r' if is_tourcast else 'FWIBYMBPj'
+
+        return self.url_result(
+            f'https://players.brightcove.net/{account_id}/{player_id}_default/index.html?videoId={video_id}',
+            BrightcoveNewIE)

yt_dlp/extractor/tiktok.py

@@ -13,6 +13,7 @@ from ..utils import (
     LazyList,
     UnsupportedError,
     UserNotLive,
+    determine_ext,
     format_field,
     get_element_by_id,
     get_first,
@@ -204,6 +205,16 @@ class TikTokBaseIE(InfoExtractor):
 
         known_resolutions = {}
 
+        def mp3_meta(url):
+            return {
+                'format_note': 'Music track',
+                'ext': 'mp3',
+                'acodec': 'mp3',
+                'vcodec': 'none',
+                'width': None,
+                'height': None,
+            } if determine_ext(url) == 'mp3' else {}
+
         def extract_addr(addr, add_meta={}):
             parsed_meta, res = parse_url_key(addr.get('url_key', ''))
             if res:
@@ -219,7 +230,8 @@ class TikTokBaseIE(InfoExtractor):
                 'source_preference': -2 if 'aweme/v1' in url else -1,  # Downloads from API might get blocked
                 **add_meta, **parsed_meta,
                 'format_note': join_nonempty(
-                    add_meta.get('format_note'), '(API)' if 'aweme/v1' in url else None, delim=' ')
+                    add_meta.get('format_note'), '(API)' if 'aweme/v1' in url else None, delim=' '),
+                **mp3_meta(url),
             } for url in addr.get('url_list') or []]
 
         # Hack: Add direct video links first to prioritize them when removing duplicate formats
@@ -553,6 +565,28 @@ class TikTokIE(TikTokBaseIE):
             'comment_count': int,
         },
         'skip': 'This video is unavailable',
+    }, {
+        # slideshow audio-only mp3 format
+        'url': 'https://www.tiktok.com/@_le_cannibale_/video/7139980461132074283',
+        'info_dict': {
+            'id': '7139980461132074283',
+            'ext': 'mp3',
+            'title': 'TikTok video #7139980461132074283',
+            'description': '',
+            'creator': 'Antaura',
+            'uploader': '_le_cannibale_',
+            'uploader_id': '6604511138619654149',
+            'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAoShJqaw_5gvy48y3azFeFcT4jeyKWbB0VVYasOCt2tTLwjNFIaDcHAM4D-QGXFOP',
+            'artist': 'nathan !',
+            'track': 'grahamscott canon',
+            'upload_date': '20220905',
+            'timestamp': 1662406249,
+            'view_count': int,
+            'like_count': int,
+            'repost_count': int,
+            'comment_count': int,
+            'thumbnail': r're:^https://.+\.webp',
+        },
     }, {
         # Auto-captions available
         'url': 'https://www.tiktok.com/@hankgreen1/video/7047596209028074758',