[ie/Parlview] Rework extractor (#13788)

Closes #13787
Authored by: barryvan

yt_dlp/extractor/parlview.py

@@ -1,63 +1,63 @@
+import re
+
 from .common import InfoExtractor
-from ..utils import (
+from ..utils import parse_duration, parse_iso8601, url_or_none
-    int_or_none,
+from ..utils.traversal import traverse_obj
-    try_get,
-    unified_timestamp,
-)
 
 
 class ParlviewIE(InfoExtractor):
-    _WORKING = False
+    _VALID_URL = r'https?://(?:www\.)?aph\.gov\.au/News_and_Events/Watch_Read_Listen/ParlView/video/(?P<id>[^/?#]+)'
-    _VALID_URL = r'https?://(?:www\.)?parlview\.aph\.gov\.au/(?:[^/]+)?\bvideoID=(?P<id>\d{6})'
     _TESTS = [{
-        'url': 'https://parlview.aph.gov.au/mediaPlayer.php?videoID=542661',
+        'url': 'https://www.aph.gov.au/News_and_Events/Watch_Read_Listen/ParlView/video/3406614',
         'info_dict': {
-            'id': '542661',
+            'id': '3406614',
             'ext': 'mp4',
-            'title': "Australia's Family Law System [Part 2]",
+            'title': 'Senate Chamber',
-            'duration': 5799,
+            'description': 'Official Recording of Senate Proceedings from the Australian Parliament',
-            'description': 'md5:7099883b391619dbae435891ca871a62',
+            'thumbnail': 'https://aphbroadcasting-prod.z01.azurefd.net/vod-storage/vod-logos/SenateParlview06.jpg',
-            'timestamp': 1621430700,
+            'upload_date': '20250325',
-            'upload_date': '20210519',
+            'duration': 17999,
-            'uploader': 'Joint Committee',
+            'timestamp': 1742939400,
         },
         'params': {
             'skip_download': True,
         },
     }, {
-        'url': 'https://parlview.aph.gov.au/mediaPlayer.php?videoID=539936',
+        'url': 'https://www.aph.gov.au/News_and_Events/Watch_Read_Listen/ParlView/video/SV1394.dv',
-        'only_matching': True,
+        'info_dict': {
+            'id': 'SV1394.dv',
+            'ext': 'mp4',
+            'title': 'Senate Select Committee on Uranium Mining and Milling [Part 1]',
+            'description': 'Official Recording of Senate Committee Proceedings from the Australian Parliament',
+            'thumbnail': 'https://aphbroadcasting-prod.z01.azurefd.net/vod-storage/vod-logos/CommitteeThumbnail06.jpg',
+            'upload_date': '19960822',
+            'duration': 14765,
+            'timestamp': 840754200,
+        },
+        'params': {
+            'skip_download': True,
+        },
     }]
-    _API_URL = 'https://parlview.aph.gov.au/api_v3/1/playback/getUniversalPlayerConfig?videoID=%s&format=json'
-    _MEDIA_INFO_URL = 'https://parlview.aph.gov.au/ajaxPlayer.php?videoID=%s&tabNum=4&action=loadTab'
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        video_details = self._download_json(
-        media = self._download_json(self._API_URL % video_id, video_id).get('media')
+            f'https://vodapi.aph.gov.au/api/search/parlview/{video_id}', video_id)['videoDetails']
-        timestamp = try_get(media, lambda x: x['timeMap']['source']['timecode_offsets'][0], str) or '/'
 
-        stream = try_get(media, lambda x: x['renditions'][0], dict)
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
-        if not stream:
+            video_details['files']['file']['url'], video_id, 'mp4')
-            self.raise_no_formats('No streams were detected')
-        elif stream.get('streamType') != 'VOD':
-            self.raise_no_formats('Unknown type of stream was detected: "{}"'.format(str(stream.get('streamType'))))
-        formats = self._extract_m3u8_formats(stream['url'], video_id, 'mp4', 'm3u8_native')
 
-        media_info = self._download_webpage(
+        DURATION_RE = re.compile(r'(?P<duration>\d+:\d+:\d+):\d+')
-            self._MEDIA_INFO_URL % video_id, video_id, note='Downloading media info', fatal=False)
 
         return {
             'id': video_id,
-            'url': url,
-            'title': self._html_search_regex(r'<h2>([^<]+)<', webpage, 'title', fatal=False),
             'formats': formats,
-            'duration': int_or_none(media.get('duration')),
+            'subtitles': subtitles,
-            'timestamp': unified_timestamp(timestamp.split('/', 1)[1].replace('_', ' ')),
+            **traverse_obj(video_details, {
-            'description': self._html_search_regex(
+                'title': (('parlViewTitle', 'title'), {str}, any),
-                r'<div[^>]+class="descripti?on"[^>]*>[^>]+<strong>[^>]+>[^>]+>([^<]+)',
+                'description': ('parlViewDescription', {str}),
-                webpage, 'description', fatal=False),
+                'duration': ('files', 'file', 'duration', {DURATION_RE.fullmatch}, 'duration', {parse_duration}),
-            'uploader': self._html_search_regex(
+                'timestamp': ('recordingFrom', {parse_iso8601}),
-                r'<td>[^>]+>Channel:[^>]+>([^<]+)', media_info, 'channel', fatal=False),
+                'thumbnail': ('thumbUrl', {url_or_none}),
-            'thumbnail': media.get('staticImage'),
+            }),
         }