Merge 2eaf303b63 into 2009cb27e1

Authored by: bashonly

README.md

@@ -1869,6 +1869,9 @@ The following extractors use this feature:
 #### digitalconcerthall
 * `prefer_combined_hls`: Prefer extracting combined/pre-merged video and audio HLS formats. This will exclude 4K/HEVC video and lossless/FLAC audio formats, which are only available as split video/audio HLS formats
 
+#### sonylivseries
+* `sort_order`: Episode sort order for series extraction - one of `asc` (ascending, oldest first) or `desc` (descending, newest first). Default is `asc`
+
 **Note**: These options may be changed/removed in the future without concern for backward compatibility
 
 <!-- MANPAGE: MOVE "INSTALLATION" SECTION HERE -->

yt_dlp/extractor/ctvnews.py

@@ -1,14 +1,27 @@
+import json
 import re
+import urllib.parse
 
 from .common import InfoExtractor
-from ..utils import orderedSet
+from .ninecninemedia import NineCNineMediaIE
+from ..utils import extract_attributes, orderedSet
+from ..utils.traversal import find_element, traverse_obj
 
 
 class CTVNewsIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:.+?\.)?ctvnews\.ca/(?:video\?(?:clip|playlist|bin)Id=|.*?)(?P<id>[0-9.]+)'
+    _BASE_REGEX = r'https?://(?:[^.]+\.)?ctvnews\.ca/'
+    _VIDEO_ID_RE = r'(?P<id>\d{5,})'
+    _PLAYLIST_ID_RE = r'(?P<id>\d\.\d{5,})'
+    _VALID_URL = [
+        rf'{_BASE_REGEX}video/c{_VIDEO_ID_RE}',
+        rf'{_BASE_REGEX}video(?:-gallery)?/?\?clipId={_VIDEO_ID_RE}',
+        rf'{_BASE_REGEX}video/?\?(?:playlist|bin)Id={_PLAYLIST_ID_RE}',
+        rf'{_BASE_REGEX}(?!video/)[^?#]*?{_PLAYLIST_ID_RE}/?(?:$|[?#])',
+        rf'{_BASE_REGEX}(?!video/)[^?#]+\?binId={_PLAYLIST_ID_RE}',
+    ]
     _TESTS = [{
         'url': 'http://www.ctvnews.ca/video?clipId=901995',
-        'md5': '9b8624ba66351a23e0b6e1391971f9af',
+        'md5': 'b608f466c7fa24b9666c6439d766ab7e',
         'info_dict': {
             'id': '901995',
             'ext': 'flv',
@@ -16,6 +29,33 @@ class CTVNewsIE(InfoExtractor):
             'description': 'md5:958dd3b4f5bbbf0ed4d045c790d89285',
             'timestamp': 1467286284,
             'upload_date': '20160630',
+            'categories': [],
+            'season_number': 0,
+            'season': 'Season 0',
+            'tags': [],
+            'series': 'CTV News National | Archive | Stories 2',
+            'season_id': '57981',
+            'thumbnail': r're:https?://.*\.jpg$',
+            'duration': 764.631,
+        },
+    }, {
+        'url': 'https://barrie.ctvnews.ca/video/c3030933-here_s-what_s-making-news-for-nov--15?binId=1272429',
+        'md5': '8b8c2b33c5c1803e3c26bc74ff8694d5',
+        'info_dict': {
+            'id': '3030933',
+            'ext': 'flv',
+            'title': 'Here’s what’s making news for Nov. 15',
+            'description': 'Here are the top stories we’re working on for CTV News at 11 for Nov. 15',
+            'thumbnail': 'http://images2.9c9media.com/image_asset/2021_2_22_a602e68e-1514-410e-a67a-e1f7cccbacab_png_2000x1125.jpg',
+            'season_id': '58104',
+            'season_number': 0,
+            'tags': [],
+            'season': 'Season 0',
+            'categories': [],
+            'series': 'CTV News Barrie',
+            'upload_date': '20241116',
+            'duration': 42.943,
+            'timestamp': 1731722452,
         },
     }, {
         'url': 'http://www.ctvnews.ca/video?playlistId=1.2966224',
@@ -31,6 +71,72 @@ class CTVNewsIE(InfoExtractor):
             'id': '1.2876780',
         },
         'playlist_mincount': 100,
+    }, {
+        'url': 'https://www.ctvnews.ca/it-s-been-23-years-since-toronto-called-in-the-army-after-a-major-snowstorm-1.5736957',
+        'info_dict':
+        {
+            'id': '1.5736957',
+        },
+        'playlist_mincount': 6,
+    }, {
+        'url': 'https://www.ctvnews.ca/business/respondents-to-bank-of-canada-questionnaire-largely-oppose-creating-a-digital-loonie-1.6665797',
+        'md5': '24bc4b88cdc17d8c3fc01dfc228ab72c',
+        'info_dict': {
+            'id': '2695026',
+            'ext': 'flv',
+            'season_id': '89852',
+            'series': 'From CTV News Channel',
+            'description': 'md5:796a985a23cacc7e1e2fafefd94afd0a',
+            'season': '2023',
+            'title': 'Bank of Canada asks public about digital currency',
+            'categories': [],
+            'tags': [],
+            'upload_date': '20230526',
+            'season_number': 2023,
+            'thumbnail': 'http://images2.9c9media.com/image_asset/2019_3_28_35f5afc3-10f6-4d92-b194-8b9a86f55c6a_png_1920x1080.jpg',
+            'timestamp': 1685105157,
+            'duration': 253.553,
+        },
+    }, {
+        'url': 'https://stox.ctvnews.ca/video-gallery?clipId=582589',
+        'md5': '135cc592df607d29dddc931f1b756ae2',
+        'info_dict': {
+            'id': '582589',
+            'ext': 'flv',
+            'categories': [],
+            'timestamp': 1427906183,
+            'season_number': 0,
+            'duration': 125.559,
+            'thumbnail': 'http://images2.9c9media.com/image_asset/2019_3_28_35f5afc3-10f6-4d92-b194-8b9a86f55c6a_png_1920x1080.jpg',
+            'series': 'CTV News Stox',
+            'description': 'CTV original footage of the rise and fall of the Berlin Wall.',
+            'title': 'Berlin Wall',
+            'season_id': '63817',
+            'season': 'Season 0',
+            'tags': [],
+            'upload_date': '20150401',
+        },
+    }, {
+        'url': 'https://ottawa.ctvnews.ca/features/regional-contact/regional-contact-archive?binId=1.1164587#3023759',
+        'md5': 'a14c0603557decc6531260791c23cc5e',
+        'info_dict': {
+            'id': '3023759',
+            'ext': 'flv',
+            'season_number': 2024,
+            'timestamp': 1731798000,
+            'season': '2024',
+            'episode': 'Episode 125',
+            'description': 'CTV News Ottawa at Six',
+            'duration': 2712.076,
+            'episode_number': 125,
+            'upload_date': '20241116',
+            'title': 'CTV News Ottawa at Six for Saturday, November 16, 2024',
+            'thumbnail': 'http://images2.9c9media.com/image_asset/2019_3_28_35f5afc3-10f6-4d92-b194-8b9a86f55c6a_png_1920x1080.jpg',
+            'categories': [],
+            'tags': [],
+            'series': 'CTV News Ottawa at Six',
+            'season_id': '92667',
+        },
     }, {
         'url': 'http://www.ctvnews.ca/1.810401',
         'only_matching': True,
@@ -42,29 +148,35 @@ class CTVNewsIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    def _ninecninemedia_url_result(self, clip_id):
+        return self.url_result(f'9c9media:ctvnews_web:{clip_id}', NineCNineMediaIE, clip_id)
+
     def _real_extract(self, url):
         page_id = self._match_id(url)
 
-        def ninecninemedia_url_result(clip_id):
+        if mobj := re.fullmatch(self._VIDEO_ID_RE, urllib.parse.urlparse(url).fragment):
-            return {
+            page_id = mobj.group('id')
-                '_type': 'url_transparent',
-                'id': clip_id,
-                'url': f'9c9media:ctvnews_web:{clip_id}',
-                'ie_key': 'NineCNineMedia',
-            }
 
-        if page_id.isdigit():
+        if re.fullmatch(self._VIDEO_ID_RE, page_id):
-            return ninecninemedia_url_result(page_id)
+            return self._ninecninemedia_url_result(page_id)
-        else:
+
-            webpage = self._download_webpage(f'http://www.ctvnews.ca/{page_id}', page_id, query={
+        webpage = self._download_webpage(f'https://www.ctvnews.ca/{page_id}', page_id, query={
-                'ot': 'example.AjaxPageLayout.ot',
+            'ot': 'example.AjaxPageLayout.ot',
-                'maxItemsPerPage': 1000000,
+            'maxItemsPerPage': 1000000,
-            })
+        })
-            entries = [ninecninemedia_url_result(clip_id) for clip_id in orderedSet(
+        entries = [self._ninecninemedia_url_result(clip_id)
-                re.findall(r'clip\.id\s*=\s*(\d+);', webpage))]
+                   for clip_id in orderedSet(re.findall(r'clip\.id\s*=\s*(\d+);', webpage))]
-            if not entries:
+        if not entries:
-                webpage = self._download_webpage(url, page_id)
+            webpage = self._download_webpage(url, page_id)
-                if 'getAuthStates("' in webpage:
+            if 'getAuthStates("' in webpage:
-                    entries = [ninecninemedia_url_result(clip_id) for clip_id in
+                entries = [self._ninecninemedia_url_result(clip_id) for clip_id in
-                               self._search_regex(r'getAuthStates\("([\d+,]+)"', webpage, 'clip ids').split(',')]
+                           self._search_regex(r'getAuthStates\("([\d+,]+)"', webpage, 'clip ids').split(',')]
-            return self.playlist_result(entries, page_id)
+            else:
+                entries = [
+                    self._ninecninemedia_url_result(clip_id) for clip_id in
+                    traverse_obj(webpage, (
+                        {find_element(tag='jasper-player-container', html=True)},
+                        {extract_attributes}, 'axis-ids', {json.loads}, ..., 'axisId'))
+                ]
+
+        return self.playlist_result(entries, page_id)

yt_dlp/extractor/sonyliv.py

@@ -199,8 +199,9 @@ class SonyLIVSeriesIE(InfoExtractor):
         },
     }]
     _API_BASE = 'https://apiv2.sonyliv.com/AGL'
+    _SORT_ORDERS = ('asc', 'desc')
 
-    def _entries(self, show_id):
+    def _entries(self, show_id, sort_order):
         headers = {
             'Accept': 'application/json, text/plain, */*',
             'Referer': 'https://www.sonyliv.com',
@@ -215,6 +216,9 @@ class SonyLIVSeriesIE(InfoExtractor):
                 'from': '0',
                 'to': '49',
             }), ('resultObj', 'containers', 0, 'containers', lambda _, v: int_or_none(v['id'])))
+
+        if sort_order == 'desc':
+            seasons = reversed(seasons)
         for season in seasons:
             season_id = str(season['id'])
             note = traverse_obj(season, ('metadata', 'title', {str})) or 'season'
@@ -226,7 +230,7 @@ class SonyLIVSeriesIE(InfoExtractor):
                         'from': str(cursor),
                         'to': str(cursor + 99),
                         'orderBy': 'episodeNumber',
-                        'sortOrder': 'asc',
+                        'sortOrder': sort_order,
                     }), ('resultObj', 'containers', 0, 'containers', lambda _, v: int_or_none(v['id'])))
                 if not episodes:
                     break
@@ -237,4 +241,10 @@ class SonyLIVSeriesIE(InfoExtractor):
 
     def _real_extract(self, url):
         show_id = self._match_id(url)
-        return self.playlist_result(self._entries(show_id), playlist_id=show_id)
+
+        sort_order = self._configuration_arg('sort_order', [self._SORT_ORDERS[0]])[0]
+        if sort_order not in self._SORT_ORDERS:
+            raise ValueError(
+                f'Invalid sort order "{sort_order}". Allowed values are: {", ".join(self._SORT_ORDERS)}')
+
+        return self.playlist_result(self._entries(show_id, sort_order), playlist_id=show_id)

yt_dlp/extractor/zoom.py

@@ -7,6 +7,7 @@ from ..utils import (
     parse_resolution,
     str_or_none,
     traverse_obj,
+    update_url,
     url_basename,
     urlencode_postdata,
     urljoin,
@@ -34,6 +35,7 @@ class ZoomIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Prépa AF2023 - Séance 5 du 11 avril - R20/VM/GO',
         },
+        'skip': 'This recording has expired',
     }, {
         # share URL
         'url': 'https://us02web.zoom.us/rec/share/hkUk5Zxcga0nkyNGhVCRfzkA2gX_mzgS3LpTxEEWJz9Y_QpIQ4mZFOUx7KZRZDQA.9LGQBdqmDAYgiZ_8',
@@ -61,41 +63,59 @@ class ZoomIE(InfoExtractor):
         return self._search_json(
             r'window\.__data__\s*=', webpage, 'data', video_id, transform_source=js_to_json)
 
-    def _get_real_webpage(self, url, base_url, video_id, url_type):
+    def _try_login(self, url, base_url, video_id, form):
-        webpage = self._download_webpage(url, video_id, note=f'Downloading {url_type} webpage')
+        # This will most likely only work for password-protected meetings
-        try:
-            form = self._form_hidden_inputs('password_form', webpage)
-        except ExtractorError:
-            return webpage
-
         password = self.get_param('videopassword')
         if not password:
             raise ExtractorError(
                 'This video is protected by a passcode, use the --video-password option', expected=True)
+
         is_meeting = form.get('useWhichPasswd') == 'meeting'
         validation = self._download_json(
-            base_url + 'rec/validate%s_passwd' % ('_meet' if is_meeting else ''),
+            base_url + 'nws/recording/1.0/validate%s-passwd' % ('-meeting' if is_meeting else ''),
             video_id, 'Validating passcode', 'Wrong passcode', data=urlencode_postdata({
-                'id': form[('meet' if is_meeting else 'file') + 'Id'],
+                'id': form[('meeting' if is_meeting else 'file') + '_id'],
                 'passwd': password,
                 'action': form.get('action'),
             }))
+
         if not validation.get('status'):
             raise ExtractorError(validation['errorMessage'], expected=True)
-        return self._download_webpage(url, video_id, note=f'Re-downloading {url_type} webpage')
+
+    def _get_real_webpage(self, url, base_url, video_id, url_type):
+        webpage = self._download_webpage(url, video_id, note=f'Downloading {url_type} webpage')
+
+        data = self._get_page_data(webpage, video_id)
+        if data.get('componentName') != 'need-password':  # not password protected
+            return webpage
+
+        # Password-protected:
+        self._try_login(url, base_url, video_id, form=data)
+        # Return the new HTML document
+        new_url = f"{base_url}rec/share/{data['meeting_id']}"
+        return self._download_webpage(new_url, video_id, note=f'Re-downloading {url_type} webpage')
+
+    def _get_share_redirect_url(self, url, base_url, video_id):
+        """Converts a `/rec/share` url to the corresponding `/rec/play` url, performs login if necessary"""
+        webpage = self._get_real_webpage(url, base_url, video_id, 'share')
+        meeting_id = self._get_page_data(webpage, video_id)['meetingId']
+        redirect_dict = self._download_json(
+            f'{base_url}nws/recording/1.0/play/share-info/{meeting_id}',
+            video_id, note='Downloading share info JSON')['result']
+        redirect_path = redirect_dict.pop('redirectUrl')
+        url = update_url(urljoin(base_url, redirect_path), query_update=redirect_dict)
+
+        if redirect_dict.get('componentName') == 'need-password':
+            # First login, then return redirection URL
+            return self._get_share_redirect_url(url, base_url, video_id)
+
+        return url
 
     def _real_extract(self, url):
         base_url, url_type, video_id = self._match_valid_url(url).group('base_url', 'type', 'id')
-        query = {}
 
         if url_type == 'share':
-            webpage = self._get_real_webpage(url, base_url, video_id, 'share')
+            url = self._get_share_redirect_url(url, base_url, video_id)
-            meeting_id = self._get_page_data(webpage, video_id)['meetingId']
-            redirect_path = self._download_json(
-                f'{base_url}nws/recording/1.0/play/share-info/{meeting_id}',
-                video_id, note='Downloading share info JSON')['result']['redirectUrl']
-            url = urljoin(base_url, redirect_path)
-            query['continueMode'] = 'true'
 
         webpage = self._get_real_webpage(url, base_url, video_id, 'play')
         file_id = self._get_page_data(webpage, video_id)['fileId']
@@ -104,10 +124,12 @@ class ZoomIE(InfoExtractor):
             raise ExtractorError('Unable to extract file ID')
 
         data = self._download_json(
-            f'{base_url}nws/recording/1.0/play/info/{file_id}', video_id, query=query,
+            f'{base_url}nws/recording/1.0/play/info/{file_id}', video_id, query={
+                'continueMode': 'true',  # Makes this return value include interpreter audio information
+            },
             note='Downloading play info JSON')['result']
-
         subtitles = {}
+        # XXX: Would be more appropriate to parse chapters separate from subtitles
         for _type in ('transcript', 'cc', 'chapter'):
             if data.get(f'{_type}Url'):
                 subtitles[_type] = [{
@@ -117,6 +139,19 @@ class ZoomIE(InfoExtractor):
 
         formats = []
 
+        if data.get('interpreterAudioList'):
+            for audio in data.get('interpreterAudioList'):
+                formats.append({
+                    'format_note': f'Intepreter: {audio["languageText"]}',
+                    'url': audio['audioUrl'],
+                    'format_id': f'interpreter-{ audio["icon"].lower()}',
+                    'ext': 'm4a',
+                    # There doesn't seem to be an explicit field for a standardized language code,
+                    # sometimes the `language` field may be more accurate than `icon`
+                    'language': audio['icon'].lower(),
+                    'vcodec': 'none',
+                })
+
         if data.get('viewMp4Url'):
             formats.append({
                 'format_note': 'Camera stream',