From 3a3bd00037e9908e87da4fa9f2ad772aa34dc60e Mon Sep 17 00:00:00 2001 From: sepro Date: Fri, 13 Sep 2024 12:51:58 +0200 Subject: [PATCH 001/154] [ie/youtube] Add `po_token`, `visitor_data`, `data_sync_id` extractor args (#10648) Authored by: seproDev, coletdjnz, bashonly --- README.md | 3 + yt_dlp/extractor/youtube.py | 257 +++++++++++++++++++++++++----------- 2 files changed, 182 insertions(+), 78 deletions(-) diff --git a/README.md b/README.md index ca32e09bf..428eb9f47 100644 --- a/README.md +++ b/README.md @@ -1777,6 +1777,9 @@ The following extractors use this feature: * `innertube_host`: Innertube API host to use for all API requests; e.g. `studio.youtube.com`, `youtubei.googleapis.com`. Note that cookies exported from one subdomain will not work on others * `innertube_key`: Innertube API key to use for all API requests. By default, no API key is used * `raise_incomplete_data`: `Incomplete Data Received` raises an error instead of reporting a warning +* `data_sync_id`: Overrides the account Data Sync ID used in Innertube API requests. This may be needed if you are using an account with `youtube:player_skip=webpage,configs` or `youtubetab:skip=webpage` +* `visitor_data`: Overrides the Visitor Data used in Innertube API requests. This should be used with `player_skip=webpage,configs` and without cookies. Note: this may have adverse effects if used improperly. If a session from a browser is wanted, you should pass cookies instead (which contain the Visitor ID) +* `po_token`: Proof of Origin (PO) Token(s) to use for requesting video playback. Comma seperated list of PO Tokens in the format `CLIENT+PO_TOKEN`, e.g. `youtube:po_token=web+XXX,android+YYY` #### youtubetab (YouTube playlists, channels, feeds, etc.) * `skip`: One or more of `webpage` (skip initial webpage download), `authcheck` (allow the download of playlists requiring authentication when no initial webpage is downloaded. This may cause unwanted behavior, see [#1122](https://github.com/yt-dlp/yt-dlp/pull/1122) for more details) diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index 2501398ba..343d103f6 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -69,6 +69,8 @@ from ..utils import ( ) STREAMING_DATA_CLIENT_NAME = '__yt_dlp_client' +STREAMING_DATA_PO_TOKEN = '__yt_dlp_po_token' + # any clients starting with _ cannot be explicitly requested by the user INNERTUBE_CLIENTS = { 'web': { @@ -79,6 +81,7 @@ INNERTUBE_CLIENTS = { }, }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 1, + 'REQUIRE_PO_TOKEN': True, }, # Safari UA returns pre-merged video+audio 144p/240p/360p/720p/1080p HLS formats 'web_safari': { @@ -90,6 +93,7 @@ INNERTUBE_CLIENTS = { }, }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 1, + 'REQUIRE_PO_TOKEN': True, }, 'web_embedded': { 'INNERTUBE_CONTEXT': { @@ -132,6 +136,7 @@ INNERTUBE_CLIENTS = { }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 3, 'REQUIRE_JS_PLAYER': False, + 'REQUIRE_PO_TOKEN': True, }, 'android_music': { 'INNERTUBE_CONTEXT': { @@ -146,6 +151,7 @@ INNERTUBE_CLIENTS = { }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 21, 'REQUIRE_JS_PLAYER': False, + 'REQUIRE_PO_TOKEN': True, }, 'android_creator': { 'INNERTUBE_CONTEXT': { @@ -160,6 +166,7 @@ INNERTUBE_CLIENTS = { }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 14, 'REQUIRE_JS_PLAYER': False, + 'REQUIRE_PO_TOKEN': True, }, # YouTube Kids videos aren't returned on this client for some reason 'android_vr': { @@ -323,6 +330,7 @@ def build_innertube_clients(): for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()): ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com') ytcfg.setdefault('REQUIRE_JS_PLAYER', True) + ytcfg.setdefault('REQUIRE_PO_TOKEN', False) ytcfg.setdefault('PLAYER_PARAMS', None) ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en') @@ -688,31 +696,46 @@ class YoutubeBaseInfoExtractor(InfoExtractor): r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage, 'identity token', default=None, fatal=False) - @staticmethod - def _extract_account_syncid(*args): + def _data_sync_id_to_delegated_session_id(self, data_sync_id): + if not data_sync_id: + return + # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel + # and just "user_syncid||" for primary channel. We only want the channel_syncid + channel_syncid, _, user_syncid = data_sync_id.partition('||') + if user_syncid: + return channel_syncid + + def _extract_account_syncid(self, *args): """ - Extract syncId required to download private playlists of secondary channels + Extract current session ID required to download private playlists of secondary channels @params response and/or ytcfg """ - for data in args: - # ytcfg includes channel_syncid if on secondary channel - delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], str) - if delegated_sid: - return delegated_sid - sync_ids = (try_get( - data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'], - lambda x: x['DATASYNC_ID']), str) or '').split('||') - if len(sync_ids) >= 2 and sync_ids[1]: - # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel - # and just "user_syncid||" for primary channel. We only want the channel_syncid - return sync_ids[0] + # ytcfg includes channel_syncid if on secondary channel + if delegated_sid := traverse_obj(args, (..., 'DELEGATED_SESSION_ID', {str}, any)): + return delegated_sid - @staticmethod - def _extract_visitor_data(*args): + data_sync_id = self._extract_data_sync_id(*args) + return self._data_sync_id_to_delegated_session_id(data_sync_id) + + def _extract_data_sync_id(self, *args): + """ + Extract current account dataSyncId. + In the format DELEGATED_SESSION_ID||USER_SESSION_ID or USER_SESSION_ID|| + @params response and/or ytcfg + """ + if data_sync_id := self._configuration_arg('data_sync_id', [None], ie_key=YoutubeIE, casesense=True)[0]: + return data_sync_id + + return traverse_obj( + args, (..., ('DATASYNC_ID', ('responseContext', 'mainAppWebResponseContext', 'datasyncId')), {str}, any)) + + def _extract_visitor_data(self, *args): """ Extracts visitorData from an API response or ytcfg Appears to be used to track session state """ + if visitor_data := self._configuration_arg('visitor_data', [None], ie_key=YoutubeIE, casesense=True)[0]: + return visitor_data return get_first( args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))], expected_type=str) @@ -1334,11 +1357,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'}, } _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt') - _POTOKEN_EXPERIMENTS = ('51217476', '51217102') - _BROKEN_CLIENTS = { - short_client_name(client): client - for client in ('android', 'android_creator', 'android_music') - } _DEFAULT_CLIENTS = ('ios', 'web_creator') _GEO_BYPASS = False @@ -3701,6 +3719,54 @@ class YoutubeIE(YoutubeBaseInfoExtractor): **cls._get_checkok_params(), } + def _get_config_po_token(self, client): + po_token_strs = self._configuration_arg('po_token', [], ie_key=YoutubeIE, casesense=True) + for token_str in po_token_strs: + po_token_client, sep, po_token = token_str.partition('+') + if not sep: + self.report_warning( + f'Invalid po_token configuration format. Expected "client+po_token", got "{token_str}"', only_once=True) + continue + if po_token_client == client: + return po_token + + def fetch_po_token(self, client='web', visitor_data=None, data_sync_id=None, player_url=None, **kwargs): + # PO Token is bound to visitor_data / Visitor ID when logged out. Must have visitor_data for it to function. + if not visitor_data and not self.is_authenticated and player_url: + self.report_warning( + f'Unable to fetch PO Token for {client} client: Missing required Visitor Data. ' + f'You may need to pass Visitor Data with --extractor-args "youtube:visitor_data=XXX"') + return + + config_po_token = self._get_config_po_token(client) + if config_po_token: + # PO token is bound to data_sync_id / account Session ID when logged in. However, for the config po_token, + # if using first channel in an account then we don't need the data_sync_id anymore... + if not data_sync_id and self.is_authenticated and player_url: + self.report_warning( + f'Got a PO Token for {client} client, but missing Data Sync ID for account. Formats may not work.' + f'You may need to pass a Data Sync ID with --extractor-args "youtube:data_sync_id=XXX"') + + return config_po_token + + # Require PO Token if logged in for external fetching + if not data_sync_id and self.is_authenticated and player_url: + self.report_warning( + f'Unable to fetch PO Token for {client} client: Missing required Data Sync ID for account. ' + f'You may need to pass a Data Sync ID with --extractor-args "youtube:data_sync_id=XXX"') + return + + return self._fetch_po_token( + client=client, + visitor_data=visitor_data, + data_sync_id=data_sync_id, + player_url=player_url, + **kwargs, + ) + + def _fetch_po_token(self, client, visitor_data=None, data_sync_id=None, player_url=None, **kwargs): + """External PO Token fetch stub""" + @staticmethod def _is_agegated(player_response): if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')): @@ -3717,13 +3783,17 @@ class YoutubeIE(YoutubeBaseInfoExtractor): def _is_unplayable(player_response): return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE' - def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data): - - session_index = self._extract_session_index(player_ytcfg, master_ytcfg) - syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr) - sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None + def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, visitor_data, data_sync_id, po_token): headers = self.generate_api_headers( - ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client) + ytcfg=player_ytcfg, + default_client=client, + visitor_data=visitor_data, + session_index=self._extract_session_index(master_ytcfg, player_ytcfg), + account_syncid=( + self._data_sync_id_to_delegated_session_id(data_sync_id) + or self._extract_account_syncid(master_ytcfg, initial_pr, player_ytcfg) + ), + ) yt_query = { 'videoId': video_id, @@ -3734,6 +3804,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): if player_params := self._configuration_arg('player_params', [default_pp], casesense=True)[0]: yt_query['params'] = player_params + if po_token: + yt_query['serviceIntegrityDimensions'] = {'poToken': po_token} + + sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None yt_query.update(self._generate_player_context(sts)) return self._extract_response( item_id=video_id, ep='player', query=yt_query, @@ -3744,7 +3818,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): def _get_requested_clients(self, url, smuggled_data): requested_clients = [] - broken_clients = [] excluded_clients = [] allowed_clients = sorted( (client for client in INNERTUBE_CLIENTS if client[:1] != '_'), @@ -3758,12 +3831,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): excluded_clients.append(client[1:]) elif client not in allowed_clients: self.report_warning(f'Skipping unsupported client "{client}"') - elif client in self._BROKEN_CLIENTS.values(): - broken_clients.append(client) else: requested_clients.append(client) - # Force deprioritization of _BROKEN_CLIENTS for format de-duplication - requested_clients.extend(broken_clients) if not requested_clients: requested_clients.extend(self._DEFAULT_CLIENTS) for excluded_client in excluded_clients: @@ -3788,19 +3857,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor): return pr_id def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data): - initial_pr = ignore_initial_response = None + initial_pr = None if webpage: - if 'web' in clients: - experiments = traverse_obj(master_ytcfg, ( - 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'serializedExperimentIds', {lambda x: x.split(',')}, ...)) - if all(x in experiments for x in self._POTOKEN_EXPERIMENTS): - self.report_warning( - 'Webpage contains broken formats (poToken experiment detected). Ignoring initial player response') - ignore_initial_response = True initial_pr = self._search_json( self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False) prs = [] + deprioritized_prs = [] + if initial_pr and not self._invalid_player_response(initial_pr, video_id): # Android player_response does not have microFormats which are needed for # extraction of some data. So we return the initial_pr with formats @@ -3822,14 +3886,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor): return tried_iframe_fallback = False - player_url = None + player_url = visitor_data = data_sync_id = None skipped_clients = {} while clients: + deprioritize_pr = False client, base_client, variant = _split_innertube_client(clients.pop()) - player_ytcfg = {} - if client == 'web': - player_ytcfg = self._get_default_ytcfg() if ignore_initial_response else master_ytcfg - elif 'configs' not in self._configuration_arg('player_skip'): + player_ytcfg = master_ytcfg if client == 'web' else {} + if 'configs' not in self._configuration_arg('player_skip') and client != 'web': player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage) @@ -3842,34 +3905,53 @@ class YoutubeIE(YoutubeBaseInfoExtractor): player_url = self._download_player_url(video_id) tried_iframe_fallback = True - pr = initial_pr if client == 'web' and not ignore_initial_response else None - for retry in self.RetryManager(fatal=False): - try: - pr = pr or self._extract_player_response( - client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, - player_url if require_js_player else None, initial_pr, smuggled_data) - except ExtractorError as e: - self.report_warning(e) - break - experiments = traverse_obj(pr, ( - 'responseContext', 'serviceTrackingParams', lambda _, v: v['service'] == 'GFEEDBACK', - 'params', lambda _, v: v['key'] == 'e', 'value', {lambda x: x.split(',')}, ...)) - if all(x in experiments for x in self._POTOKEN_EXPERIMENTS): - pr = None - retry.error = ExtractorError('API returned broken formats (poToken experiment detected)', expected=True) - if not pr: + visitor_data = visitor_data or self._extract_visitor_data(master_ytcfg, initial_pr, player_ytcfg) + data_sync_id = data_sync_id or self._extract_data_sync_id(master_ytcfg, initial_pr, player_ytcfg) + po_token = self.fetch_po_token( + client=client, visitor_data=visitor_data, + data_sync_id=data_sync_id if self.is_authenticated else None, + player_url=player_url if require_js_player else None, + ) + + require_po_token = self._get_default_ytcfg(client).get('REQUIRE_PO_TOKEN') + if not po_token and require_po_token: + self.report_warning( + f'No PO Token provided for {client} client, ' + f'which is required for working {client} formats. ' + f'You can manually pass a PO Token for this client with ' + f'--extractor-args "youtube:po_token={client}+XXX"', + only_once=True) + deprioritize_pr = True + + pr = initial_pr if client == 'web' else None + try: + pr = pr or self._extract_player_response( + client, video_id, + master_ytcfg=player_ytcfg or master_ytcfg, + player_ytcfg=player_ytcfg, + player_url=player_url, + initial_pr=initial_pr, + visitor_data=visitor_data, + data_sync_id=data_sync_id, + po_token=po_token) + except ExtractorError as e: + self.report_warning(e) continue if pr_id := self._invalid_player_response(pr, video_id): skipped_clients[client] = pr_id elif pr: # Save client name for introspection later - name = short_client_name(client) sd = traverse_obj(pr, ('streamingData', {dict})) or {} - sd[STREAMING_DATA_CLIENT_NAME] = name + sd[STREAMING_DATA_CLIENT_NAME] = client + sd[STREAMING_DATA_PO_TOKEN] = po_token for f in traverse_obj(sd, (('formats', 'adaptiveFormats'), ..., {dict})): - f[STREAMING_DATA_CLIENT_NAME] = name - prs.append(pr) + f[STREAMING_DATA_CLIENT_NAME] = client + f[STREAMING_DATA_PO_TOKEN] = po_token + if deprioritize_pr: + deprioritized_prs.append(pr) + else: + prs.append(pr) # tv_embedded can work around age-gate and age-verification IF the video is embeddable if self._is_agegated(pr) and variant != 'tv_embedded': @@ -3893,6 +3975,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): # _producer, _testsuite, & _vr variants can also work around age-verification append_client('web_creator', 'mediaconnect') + prs.extend(deprioritized_prs) + if skipped_clients: self.report_warning( f'Skipping player responses from {"/".join(skipped_clients)} clients ' @@ -4027,13 +4111,17 @@ class YoutubeIE(YoutubeBaseInfoExtractor): f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True) client_name = fmt.get(STREAMING_DATA_CLIENT_NAME) - # _BROKEN_CLIENTS return videoplayback URLs that expire after 30 seconds - # Ref: https://github.com/yt-dlp/yt-dlp/issues/9554 - is_broken = client_name in self._BROKEN_CLIENTS + po_token = fmt.get(STREAMING_DATA_PO_TOKEN) + + if po_token: + fmt_url = update_url_query(fmt_url, {'pot': po_token}) + + # Clients that require PO Token return videoplayback URLs that may return 403 + is_broken = (not po_token and self._get_default_ytcfg(client_name).get('REQUIRE_PO_TOKEN')) if is_broken: self.report_warning( - f'{video_id}: {self._BROKEN_CLIENTS[client_name]} client formats are broken ' - 'and may yield HTTP Error 403. They will be deprioritized', only_once=True) + f'{video_id}: {client_name} client formats require a PO Token which was not provided. ' + 'They will be deprioritized as they may yield HTTP Error 403', only_once=True) name = fmt.get('qualityLabel') or quality.replace('audio_quality_', '') or '' fps = int_or_none(fmt.get('fps')) or 0 @@ -4109,12 +4197,24 @@ class YoutubeIE(YoutubeBaseInfoExtractor): elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live': skip_manifests.add('dash') - def process_manifest_format(f, proto, client_name, itag): + def process_manifest_format(f, proto, client_name, itag, po_token): key = (proto, f.get('language')) if not all_formats and key in itags[itag]: return False itags[itag].add(key) + if f.get('source_preference') is None: + f['source_preference'] = -1 + + # Clients that require PO Token return videoplayback URLs that may return 403 + # hls does not currently require PO Token + if (not po_token and self._get_default_ytcfg(client_name).get('REQUIRE_PO_TOKEN')) and proto != 'hls': + self.report_warning( + f'{video_id}: {client_name} client {proto} formats require a PO Token which was not provided. ' + 'They will be deprioritized as they may yield HTTP Error 403', only_once=True) + f['format_note'] = join_nonempty(f.get('format_note'), 'BROKEN', delim=' ') + f['source_preference'] -= 20 + if itag and all_formats: f['format_id'] = f'{itag}-{proto}' elif any(p != proto for p, _ in itags[itag]): @@ -4126,9 +4226,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): f['format_note'] = join_nonempty(f.get('format_note'), '(default)', delim=' ') f['language_preference'] = PREFERRED_LANG_VALUE - if f.get('source_preference') is None: - f['source_preference'] = -1 - if itag in ('616', '235'): f['format_note'] = join_nonempty(f.get('format_note'), 'Premium', delim=' ') f['source_preference'] += 100 @@ -4149,23 +4246,27 @@ class YoutubeIE(YoutubeBaseInfoExtractor): subtitles = {} for sd in streaming_data: client_name = sd.get(STREAMING_DATA_CLIENT_NAME) - + po_token = sd.get(STREAMING_DATA_PO_TOKEN) hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl') if hls_manifest_url: + if po_token: + hls_manifest_url = hls_manifest_url.rstrip('/') + f'/pot/{po_token}' fmts, subs = self._extract_m3u8_formats_and_subtitles( hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live') subtitles = self._merge_subtitles(subs, subtitles) for f in fmts: if process_manifest_format(f, 'hls', client_name, self._search_regex( - r'/itag/(\d+)', f['url'], 'itag', default=None)): + r'/itag/(\d+)', f['url'], 'itag', default=None), po_token): yield f dash_manifest_url = 'dash' not in skip_manifests and sd.get('dashManifestUrl') if dash_manifest_url: + if po_token: + dash_manifest_url = dash_manifest_url.rstrip('/') + f'/pot/{po_token}' formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False) subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH for f in formats: - if process_manifest_format(f, 'dash', client_name, f['format_id']): + if process_manifest_format(f, 'dash', client_name, f['format_id'], po_token): f['filesize'] = int_or_none(self._search_regex( r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None)) if needs_live_processing: From 9431777b4c37129a6093080c77ca59960afbb9d7 Mon Sep 17 00:00:00 2001 From: sepro Date: Sat, 14 Sep 2024 00:46:44 +0200 Subject: [PATCH 002/154] [ie/youtube:tab] Fix shorts tab extraction (#10938) Closes #10936 Authored by: seproDev --- yt_dlp/extractor/youtube.py | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index 343d103f6..3d11c32f6 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -5088,7 +5088,7 @@ class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor): def _rich_entries(self, rich_grid_renderer): renderer = traverse_obj( rich_grid_renderer, - ('content', ('videoRenderer', 'reelItemRenderer', 'playlistRenderer')), get_all=False) or {} + ('content', ('videoRenderer', 'reelItemRenderer', 'playlistRenderer', 'shortsLockupViewModel'), any)) or {} video_id = renderer.get('videoId') if video_id: yield self._extract_video(renderer) @@ -5100,6 +5100,21 @@ class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor): ie=YoutubeTabIE.ie_key(), video_id=playlist_id, video_title=self._get_text(renderer, 'title')) return + # shortsLockupViewModel extraction + entity_id = renderer.get('entityId') + if entity_id: + video_id = traverse_obj(renderer, ('onTap', 'innertubeCommand', 'reelWatchEndpoint', 'videoId', {str})) + if not video_id: + return + yield self.url_result( + f'https://www.youtube.com/shorts/{video_id}', + ie=YoutubeIE, video_id=video_id, + **traverse_obj(renderer, ('overlayMetadata', { + 'title': ('primaryText', 'content', {str}), + 'view_count': ('secondaryText', 'content', {parse_count}), + })), + thumbnails=self._extract_thumbnails(renderer, 'thumbnail', final_key='sources')) + return def _video_entry(self, video_renderer): video_id = video_renderer.get('videoId') From b4760c778d0c92c6e3f2bc8346cd72c8f08595ae Mon Sep 17 00:00:00 2001 From: Deukhoofd <10423862+Deukhoofd@users.noreply.github.com> Date: Sat, 14 Sep 2024 00:50:15 +0200 Subject: [PATCH 003/154] [ie/beacon] Add extractor (#9901) Authored by: Deukhoofd --- yt_dlp/extractor/_extractors.py | 1 + yt_dlp/extractor/beacon.py | 68 +++++++++++++++++++++++++++++++++ 2 files changed, 69 insertions(+) create mode 100644 yt_dlp/extractor/beacon.py diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index e7b162512..4302076f0 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -217,6 +217,7 @@ from .bbc import ( BBCCoUkIPlayerGroupIE, BBCCoUkPlaylistIE, ) +from .beacon import BeaconTvIE from .beatbump import ( BeatBumpPlaylistIE, BeatBumpVideoIE, diff --git a/yt_dlp/extractor/beacon.py b/yt_dlp/extractor/beacon.py new file mode 100644 index 000000000..ae47687cc --- /dev/null +++ b/yt_dlp/extractor/beacon.py @@ -0,0 +1,68 @@ +import json + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + parse_iso8601, + traverse_obj, +) + + +class BeaconTvIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?beacon\.tv/content/(?P[\w-]+)' + + _TESTS = [{ + 'url': 'https://beacon.tv/content/welcome-to-beacon', + 'md5': 'b3f5932d437f288e662f10f3bfc5bd04', + 'info_dict': { + 'id': 'welcome-to-beacon', + 'ext': 'mp4', + 'upload_date': '20240509', + 'description': 'md5:ea2bd32e71acf3f9fca6937412cc3563', + 'thumbnail': 'https://cdn.jwplayer.com/v2/media/I4CkkEvN/poster.jpg?width=720', + 'title': 'Your home for Critical Role!', + 'timestamp': 1715227200, + 'duration': 105.494, + }, + }, { + 'url': 'https://beacon.tv/content/re-slayers-take-trailer', + 'md5': 'd879b091485dbed2245094c8152afd89', + 'info_dict': { + 'id': 're-slayers-take-trailer', + 'ext': 'mp4', + 'title': 'The Re-Slayer’s Take | Official Trailer', + 'timestamp': 1715189040, + 'upload_date': '20240508', + 'duration': 53.249, + 'thumbnail': 'https://cdn.jwplayer.com/v2/media/PW5ApIw3/poster.jpg?width=720', + }, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + content_data = traverse_obj(self._search_nextjs_data(webpage, video_id), ( + 'props', 'pageProps', '__APOLLO_STATE__', + lambda k, v: k.startswith('Content:') and v['slug'] == video_id, any)) + if not content_data: + raise ExtractorError('Failed to extract content data') + + jwplayer_data = traverse_obj(content_data, ( + (('contentVideo', 'video', 'videoData'), + ('contentPodcast', 'podcast', 'audioData')), {json.loads}, {dict}, any)) + if not jwplayer_data: + if content_data.get('contentType') not in ('videoPodcast', 'video', 'podcast'): + raise ExtractorError('Content is not a video/podcast', expected=True) + if traverse_obj(content_data, ('contentTier', '__ref')) != 'MemberTier:65b258d178f89be87b4dc0a4': + self.raise_login_required('This video/podcast is for members only') + raise ExtractorError('Failed to extract content') + + return { + **self._parse_jwplayer_data(jwplayer_data, video_id), + **traverse_obj(content_data, { + 'title': ('title', {str}), + 'description': ('description', {str}), + 'timestamp': ('publishedAt', {parse_iso8601}), + }), + } From 409f8e9e3b4bde81ef76fc563256f876d2ff8099 Mon Sep 17 00:00:00 2001 From: sepro Date: Sat, 14 Sep 2024 00:54:41 +0200 Subject: [PATCH 004/154] [ie] Fix JW Player format parsing (#10956) Authored by: seproDev --- yt_dlp/extractor/common.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/yt_dlp/extractor/common.py b/yt_dlp/extractor/common.py index 187f73e7b..432db9daf 100644 --- a/yt_dlp/extractor/common.py +++ b/yt_dlp/extractor/common.py @@ -3489,7 +3489,7 @@ class InfoExtractor: continue urls.add(source_url) source_type = source.get('type') or '' - ext = mimetype2ext(source_type) or determine_ext(source_url) + ext = determine_ext(source_url, default_ext=mimetype2ext(source_type)) if source_type == 'hls' or ext == 'm3u8' or 'format=m3u8-aapl' in source_url: formats.extend(self._extract_m3u8_formats( source_url, video_id, 'mp4', entry_protocol='m3u8_native', From 5d0176547f16a3642cd71627126e9dfc24981e20 Mon Sep 17 00:00:00 2001 From: Scott Robinson Date: Sat, 14 Sep 2024 09:02:54 +1000 Subject: [PATCH 005/154] [ie/Bandcamp:user] Fix extraction (#10328) Authored by: quad, bashonly Co-authored-by: bashonly <88596187+bashonly@users.noreply.github.com> --- yt_dlp/extractor/bandcamp.py | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) diff --git a/yt_dlp/extractor/bandcamp.py b/yt_dlp/extractor/bandcamp.py index 61cbab5a7..0abe05982 100644 --- a/yt_dlp/extractor/bandcamp.py +++ b/yt_dlp/extractor/bandcamp.py @@ -1,3 +1,5 @@ +import functools +import json import random import re import time @@ -6,7 +8,9 @@ from .common import InfoExtractor from ..utils import ( KNOWN_EXTENSIONS, ExtractorError, + extract_attributes, float_or_none, + get_element_html_by_id, int_or_none, parse_filesize, str_or_none, @@ -17,6 +21,7 @@ from ..utils import ( url_or_none, urljoin, ) +from ..utils.traversal import traverse_obj class BandcampIE(InfoExtractor): @@ -459,7 +464,7 @@ class BandcampUserIE(InfoExtractor): }, }, { 'url': 'https://coldworldofficial.bandcamp.com/music', - 'playlist_mincount': 10, + 'playlist_mincount': 7, 'info_dict': { 'id': 'coldworldofficial', 'title': 'Discography of coldworldofficial', @@ -473,12 +478,19 @@ class BandcampUserIE(InfoExtractor): }, }] + def _yield_items(self, webpage): + yield from ( + re.findall(r'
  • ]+>\s*]+trackTitle["\'][^"\']+["\']([^"\']+)', webpage)) + + yield from traverse_obj(webpage, ( + {functools.partial(get_element_html_by_id, 'music-grid')}, {extract_attributes}, + 'data-client-items', {json.loads}, ..., 'page_url', {str})) + def _real_extract(self, url): uploader = self._match_id(url) webpage = self._download_webpage(url, uploader) - discography_data = (re.findall(r'
  • ]+>\s*]+trackTitle["\'][^"\']+["\']([^"\']+)', webpage)) - return self.playlist_from_matches( - discography_data, uploader, f'Discography of {uploader}', getter=lambda x: urljoin(url, x)) + self._yield_items(webpage), uploader, f'Discography of {uploader}', + getter=functools.partial(urljoin, url)) From d02df303d8e49390599db9f34482697e4d1cf5b2 Mon Sep 17 00:00:00 2001 From: Cosmin Tanislav Date: Sat, 14 Sep 2024 02:09:52 +0300 Subject: [PATCH 006/154] [ie/RTP] Support more subpages (#10787) Authored by: Demon000 --- yt_dlp/extractor/rtp.py | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-) diff --git a/yt_dlp/extractor/rtp.py b/yt_dlp/extractor/rtp.py index 944e8636a..26aec2e4c 100644 --- a/yt_dlp/extractor/rtp.py +++ b/yt_dlp/extractor/rtp.py @@ -8,7 +8,7 @@ from ..utils import js_to_json class RTPIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?rtp\.pt/play/p(?P[0-9]+)/(?P[^/?#]+)/?' + _VALID_URL = r'https?://(?:www\.)?rtp\.pt/play/(?:(?:estudoemcasa|palco|zigzag)/)?p(?P[0-9]+)/(?P[^/?#]+)' _TESTS = [{ 'url': 'http://www.rtp.pt/play/p405/e174042/paixoes-cruzadas', 'md5': 'e736ce0c665e459ddb818546220b4ef8', @@ -19,9 +19,25 @@ class RTPIE(InfoExtractor): 'description': 'As paixões musicais de António Cartaxo e António Macedo', 'thumbnail': r're:^https?://.*\.jpg', }, + }, { + 'url': 'https://www.rtp.pt/play/zigzag/p13166/e757904/25-curiosidades-25-de-abril', + 'md5': '9a81ed53f2b2197cfa7ed455b12f8ade', + 'info_dict': { + 'id': 'e757904', + 'ext': 'mp4', + 'title': '25 Curiosidades, 25 de Abril', + 'description': 'Estudar ou não estudar - Em cada um dos episódios descobrimos uma curiosidade acerca de como era viver em Portugal antes da revolução do 25 de abr', + 'thumbnail': r're:^https?://.*\.jpg', + }, }, { 'url': 'http://www.rtp.pt/play/p831/a-quimica-das-coisas', 'only_matching': True, + }, { + 'url': 'https://www.rtp.pt/play/estudoemcasa/p7776/portugues-1-ano', + 'only_matching': True, + }, { + 'url': 'https://www.rtp.pt/play/palco/p13785/l7nnon', + 'only_matching': True, }] _RX_OBFUSCATION = re.compile(r'''(?xs) @@ -49,17 +65,17 @@ class RTPIE(InfoExtractor): f, config = self._search_regex( r'''(?sx) - var\s+f\s*=\s*(?P".*?"|{[^;]+?});\s* + (?:var\s+f\s*=\s*(?P".*?"|{[^;]+?});\s*)? var\s+player1\s+=\s+new\s+RTPPlayer\s*\((?P{(?:(?!\*/).)+?})\);(?!\s*\*/) ''', webpage, 'player config', group=('f', 'config')) - f = self._parse_json( - f, video_id, - lambda data: self.__unobfuscate(data, video_id=video_id)) config = self._parse_json( config, video_id, lambda data: self.__unobfuscate(data, video_id=video_id)) + f = config['file'] if not f else self._parse_json( + f, video_id, + lambda data: self.__unobfuscate(data, video_id=video_id)) formats = [] if isinstance(f, dict): From 25c1cdaa2650563494d3bf00a38f72d0d9486bff Mon Sep 17 00:00:00 2001 From: hugepower Date: Sat, 14 Sep 2024 07:12:38 +0800 Subject: [PATCH 007/154] [ie/huya:video] Add extractor (#10686) Closes #10679 Authored by: hugepower --- yt_dlp/extractor/_extractors.py | 5 ++- yt_dlp/extractor/huya.py | 80 ++++++++++++++++++++++++++++++++- 2 files changed, 83 insertions(+), 2 deletions(-) diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index 4302076f0..8903bf8fc 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -823,7 +823,10 @@ from .hungama import ( HungamaIE, HungamaSongIE, ) -from .huya import HuyaLiveIE +from .huya import ( + HuyaLiveIE, + HuyaVideoIE, +) from .hypem import HypemIE from .hypergryph import MonsterSirenHypergryphMusicIE from .hytale import HytaleIE diff --git a/yt_dlp/extractor/huya.py b/yt_dlp/extractor/huya.py index 5663a78a3..f79e032e4 100644 --- a/yt_dlp/extractor/huya.py +++ b/yt_dlp/extractor/huya.py @@ -8,15 +8,19 @@ from .common import InfoExtractor from ..utils import ( ExtractorError, int_or_none, + parse_duration, str_or_none, try_get, unescapeHTML, + unified_strdate, update_url_query, + url_or_none, ) +from ..utils.traversal import traverse_obj class HuyaLiveIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.|m\.)?huya\.com/(?P[^/#?&]+)(?:\D|$)' + _VALID_URL = r'https?://(?:www\.|m\.)?huya\.com/(?!(?:video/play/))(?P[^/#?&]+)(?:\D|$)' IE_NAME = 'huya:live' IE_DESC = 'huya.com' TESTS = [{ @@ -24,6 +28,7 @@ class HuyaLiveIE(InfoExtractor): 'info_dict': { 'id': '572329', 'title': str, + 'ext': 'flv', 'description': str, 'is_live': True, 'view_count': int, @@ -131,3 +136,76 @@ class HuyaLiveIE(InfoExtractor): fm = base64.b64decode(params['fm']).decode().split('_', 1)[0] ss = hashlib.md5('|'.join([params['seqid'], params['ctype'], params['t']])) return fm, ss + + +class HuyaVideoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?huya\.com/video/play/(?P\d+)\.html' + IE_NAME = 'huya:video' + IE_DESC = '虎牙视频' + + _TESTS = [{ + 'url': 'https://www.huya.com/video/play/1002412640.html', + 'info_dict': { + 'id': '1002412640', + 'ext': 'mp4', + 'title': '8月3日', + 'thumbnail': r're:https?://.*\.jpg', + 'duration': 14, + 'uploader': '虎牙-ATS欧卡车队青木', + 'uploader_id': '1564376151', + 'upload_date': '20240803', + 'view_count': int, + 'comment_count': int, + 'like_count': int, + }, + }, + { + 'url': 'https://www.huya.com/video/play/556054543.html', + 'info_dict': { + 'id': '556054543', + 'ext': 'mp4', + 'title': '我不挑事 也不怕事', + 'thumbnail': r're:https?://.*\.jpg', + 'duration': 1864, + 'uploader': '卡尔', + 'uploader_id': '367138632', + 'upload_date': '20210811', + 'view_count': int, + 'comment_count': int, + 'like_count': int, + }, + }] + + def _real_extract(self, url: str): + video_id = self._match_id(url) + video_data = self._download_json( + 'https://liveapi.huya.com/moment/getMomentContent', video_id, + query={'videoId': video_id})['data']['moment']['videoInfo'] + + formats = [] + for definition in traverse_obj(video_data, ('definitions', lambda _, v: url_or_none(v['url']))): + formats.append({ + 'url': definition['url'], + **traverse_obj(definition, { + 'format_id': ('defName', {str}), + 'width': ('width', {int_or_none}), + 'height': ('height', {int_or_none}), + 'filesize': ('size', {int_or_none}), + }), + }) + + return { + 'id': video_id, + 'formats': formats, + **traverse_obj(video_data, { + 'title': ('videoTitle', {str}), + 'thumbnail': ('videoCover', {url_or_none}), + 'duration': ('videoDuration', {parse_duration}), + 'uploader': ('nickName', {str}), + 'uploader_id': ('uid', {str_or_none}), + 'upload_date': ('videoUploadTime', {unified_strdate}), + 'view_count': ('videoPlayNum', {int_or_none}), + 'comment_count': ('videoCommentNum', {int_or_none}), + 'like_count': ('favorCount', {int_or_none}), + }), + } From 3dfd720d098b4d49d69cfc77e6376f22bcd90934 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Xingchen=20Song=28=E5=AE=8B=E6=98=9F=E8=BE=B0=29?= Date: Sat, 14 Sep 2024 07:16:34 +0800 Subject: [PATCH 008/154] [ie/ximalaya] Add VIP support (#10832) Closes #6928 Authored by: xingchensong, seproDev Co-authored-by: sepro <4618135+seproDev@users.noreply.github.com> --- yt_dlp/extractor/ximalaya.py | 91 +++++++++++++++++++++++++++++++++--- 1 file changed, 85 insertions(+), 6 deletions(-) diff --git a/yt_dlp/extractor/ximalaya.py b/yt_dlp/extractor/ximalaya.py index e900a4ad9..d63964a00 100644 --- a/yt_dlp/extractor/ximalaya.py +++ b/yt_dlp/extractor/ximalaya.py @@ -1,7 +1,17 @@ +import base64 import math +import time from .common import InfoExtractor -from ..utils import InAdvancePagedList, str_or_none, traverse_obj, try_call +from .videa import VideaIE +from ..utils import ( + InAdvancePagedList, + int_or_none, + str_or_none, + traverse_obj, + try_call, + update_url_query, +) class XimalayaBaseIE(InfoExtractor): @@ -71,23 +81,92 @@ class XimalayaIE(XimalayaBaseIE): 'like_count': int, }, }, + { + # VIP-restricted audio + 'url': 'https://www.ximalaya.com/sound/562111701', + 'only_matching': True, + }, ] + @staticmethod + def _decrypt_filename(file_id, seed): + cgstr = '' + key = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\\:._-1234567890' + for _ in key: + seed = float(int(211 * seed + 30031) % 65536) + r = int(seed / 65536 * len(key)) + cgstr += key[r] + key = key.replace(key[r], '') + parts = file_id.split('*') + filename = ''.join(cgstr[int(part)] for part in parts if part.isdecimal()) + if not filename.startswith('/'): + filename = '/' + filename + return filename + + @staticmethod + def _decrypt_url_params(encrypted_params): + params = VideaIE.rc4( + base64.b64decode(encrypted_params), 'xkt3a41psizxrh9l').split('-') + # sign, token, timestamp + return params[1], params[2], params[3] + def _real_extract(self, url): scheme = 'https' if url.startswith('https') else 'http' audio_id = self._match_id(url) - audio_info_file = f'{scheme}://m.ximalaya.com/tracks/{audio_id}.json' audio_info = self._download_json( - audio_info_file, audio_id, - f'Downloading info json {audio_info_file}', 'Unable to download info file') + f'{scheme}://m.ximalaya.com/tracks/{audio_id}.json', audio_id, + 'Downloading info json', 'Unable to download info file') - formats = [{ + formats = [] + # NOTE: VIP-restricted audio + if audio_info.get('is_paid'): + ts = int(time.time()) + vip_info = self._download_json( + f'{scheme}://mpay.ximalaya.com/mobile/track/pay/{audio_id}/{ts}', + audio_id, 'Downloading VIP info json', 'Unable to download VIP info file', + query={'device': 'pc', 'isBackend': 'true', '_': ts}) + filename = self._decrypt_filename(vip_info['fileId'], vip_info['seed']) + sign, token, timestamp = self._decrypt_url_params(vip_info['ep']) + vip_url = update_url_query( + f'{vip_info["domain"]}/download/{vip_info["apiVersion"]}{filename}', { + 'sign': sign, + 'token': token, + 'timestamp': timestamp, + 'buy_key': vip_info['buyKey'], + 'duration': vip_info['duration'], + }) + fmt = { + 'format_id': 'vip', + 'url': vip_url, + 'vcodec': 'none', + } + if '_preview_' in vip_url: + self.report_warning( + f'This tracks requires a VIP account. Using a sample instead. {self._login_hint()}') + fmt.update({ + 'format_note': 'Sample', + 'preference': -10, + **traverse_obj(vip_info, { + 'filesize': ('sampleLength', {int_or_none}), + 'duration': ('sampleDuration', {int_or_none}), + }), + }) + else: + fmt.update(traverse_obj(vip_info, { + 'filesize': ('totalLength', {int_or_none}), + 'duration': ('duration', {int_or_none}), + })) + + fmt['abr'] = try_call(lambda: fmt['filesize'] * 8 / fmt['duration'] / 1024) + formats.append(fmt) + + formats.extend([{ 'format_id': f'{bps}k', 'url': audio_info[k], 'abr': bps, 'vcodec': 'none', - } for bps, k in ((24, 'play_path_32'), (64, 'play_path_64')) if audio_info.get(k)] + } for bps, k in ((24, 'play_path_32'), (64, 'play_path_64')) if audio_info.get(k)]) thumbnails = [] for k in audio_info: From 0e1b941c6b2caa688b0d3332e723d16dbafa4311 Mon Sep 17 00:00:00 2001 From: Leng Date: Sat, 14 Sep 2024 07:18:13 +0800 Subject: [PATCH 009/154] [ie/facebook:reel] Improve metadata extraction Closes #9057, Closes #10824 Authored by: lengzuo --- yt_dlp/extractor/facebook.py | 42 +++++++++++++++++++++++------------- 1 file changed, 27 insertions(+), 15 deletions(-) diff --git a/yt_dlp/extractor/facebook.py b/yt_dlp/extractor/facebook.py index a43ffe95e..1adb35b5f 100644 --- a/yt_dlp/extractor/facebook.py +++ b/yt_dlp/extractor/facebook.py @@ -84,7 +84,7 @@ class FacebookIE(InfoExtractor): 'timestamp': 1692346159, 'thumbnail': r're:^https?://.*', 'uploader_id': '100063551323670', - 'duration': 3132.184, + 'duration': 3133.583, 'view_count': int, 'concurrent_view_count': 0, }, @@ -112,9 +112,10 @@ class FacebookIE(InfoExtractor): 'upload_date': '20140506', 'timestamp': 1399398998, 'thumbnail': r're:^https?://.*', - 'uploader_id': 'pfbid028wxorhX2ErLFJ578N6P3crHD3PHmXTCqCvfBpsnbSLmbokwSY75p5hWBjHGkG4zxl', + 'uploader_id': 'pfbid05AzrFTXgY37tqwaSgbFTTEpCLBjjEJHkigogwGiRPtKEpAsJYJpzE94H1RxYXWEtl', 'duration': 131.03, 'concurrent_view_count': int, + 'view_count': int, }, }, { 'note': 'Video with DASH manifest', @@ -167,7 +168,7 @@ class FacebookIE(InfoExtractor): # have 1080P, but only up to 720p in swf params # data.video.story.attachments[].media 'url': 'https://www.facebook.com/cnn/videos/10155529876156509/', - 'md5': 'ca63897a90c9452efee5f8c40d080e25', + 'md5': '1659aa21fb3dd1585874f668e81a72c8', 'info_dict': { 'id': '10155529876156509', 'ext': 'mp4', @@ -180,9 +181,10 @@ class FacebookIE(InfoExtractor): 'view_count': int, 'uploader_id': '100059479812265', 'concurrent_view_count': int, - 'duration': 44.478, + 'duration': 44.181, }, }, { + # FIXME: unable to extract uploader, no formats found # bigPipe.onPageletArrive ... onPageletArrive pagelet_group_mall # data.node.comet_sections.content.story.attachments[].style_type_renderer.attachment.media 'url': 'https://www.facebook.com/yaroslav.korpan/videos/1417995061575415/', @@ -241,9 +243,9 @@ class FacebookIE(InfoExtractor): 'timestamp': 1511548260, 'upload_date': '20171124', 'uploader': 'Vickie Gentry', - 'uploader_id': 'pfbid0FuZhHCeWDAxWxEbr3yKPFaRstXvRxgsp9uCPG6GjD4J2AitB35NUAuJ4Q75KcjiDl', + 'uploader_id': 'pfbid0FkkycT95ySNNyfCw4Cho6u5G7WbbZEcxT496Hq8rtx1K3LcTCATpR3wnyYhmyGC5l', 'thumbnail': r're:^https?://.*', - 'duration': 148.435, + 'duration': 148.224, }, }, { # data.node.comet_sections.content.story.attachments[].styles.attachment.media @@ -271,7 +273,7 @@ class FacebookIE(InfoExtractor): 'description': 'Today Makkovik\'s own Pilot Mandy Smith made her inaugural landing on the airstrip in her hometown. What a proud moment as we all cheered and...', 'thumbnail': r're:^https?://.*', 'uploader': 'Lela Evans', - 'uploader_id': 'pfbid0shZJipuigyy5mqrUJn9ub5LJFWNHvan5prtyi3LrDuuuJ4NwrURgnQHYR9fywBepl', + 'uploader_id': 'pfbid0swT2y7t6TAsZVBvcyeYPdhTMefGaS26mzUwML3vd1ma6ndGZKxsyS4Ssu3jitZLXl', 'upload_date': '20231228', 'timestamp': 1703804085, 'duration': 394.347, @@ -322,7 +324,7 @@ class FacebookIE(InfoExtractor): 'upload_date': '20180523', 'uploader': 'ESL One Dota 2', 'uploader_id': '100066514874195', - 'duration': 4524.212, + 'duration': 4524.001, 'view_count': int, 'thumbnail': r're:^https?://.*', 'concurrent_view_count': int, @@ -339,9 +341,9 @@ class FacebookIE(InfoExtractor): 'title': 'Josef', 'thumbnail': r're:^https?://.*', 'concurrent_view_count': int, - 'uploader_id': 'pfbid0cibUN6tV7DYgdbJdsUFN46wc4jKpVSPAvJQhFofGqBGmVn3V3JtAs2tfUwziw2hUl', + 'uploader_id': 'pfbid02gpfwRM2XvdEJfsERupwQiNmBiDArc38RMRYZnap372q6Vs7MtFTVy72mmFWpJBTKl', 'timestamp': 1549275572, - 'duration': 3.413, + 'duration': 3.283, 'uploader': 'Josef Novak', 'description': '', 'upload_date': '20190204', @@ -396,6 +398,7 @@ class FacebookIE(InfoExtractor): 'playlist_count': 1, 'skip': 'Requires logging in', }, { + # FIXME: Cannot parse data error # data.event.cover_media_renderer.cover_video 'url': 'https://m.facebook.com/events/1509582499515440', 'info_dict': { @@ -498,7 +501,8 @@ class FacebookIE(InfoExtractor): or get_first(post, ('video', 'creation_story', 'attachments', ..., 'media', lambda k, v: k == 'owner' and v['name'])) 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 {}) + or get_first(post, ('event', 'event_creator', {dict})) + or get_first(post, ('video', 'creation_story', 'short_form_video_context', 'video_owner', {dict})) or {}) uploader = uploader_data.get('name') or ( clean_html(get_element_by_id('fbPhotoPageAuthorName', webpage)) or self._search_regex( @@ -524,6 +528,11 @@ class FacebookIE(InfoExtractor): webpage, 'view count', default=None)), 'concurrent_view_count': get_first(post, ( ('video', (..., ..., 'attachments', ..., 'media')), 'liveViewerCount', {int_or_none})), + **traverse_obj(post, (lambda _, v: video_id in v['url'], 'feedback', { + 'like_count': ('likers', 'count', {int}), + 'comment_count': ('total_comment_count', {int}), + 'repost_count': ('share_count_reduced', {parse_count}), + }), get_all=False), } info_json_ld = self._search_json_ld(webpage, video_id, default={}) @@ -932,18 +941,21 @@ class FacebookReelIE(InfoExtractor): _TESTS = [{ 'url': 'https://www.facebook.com/reel/1195289147628387', - 'md5': 'f13dd37f2633595982db5ed8765474d3', + 'md5': 'a53256d10fc2105441fe0c4212ed8cea', 'info_dict': { 'id': '1195289147628387', 'ext': 'mp4', - 'title': 'md5:b05800b5b1ad56c0ca78bd3807b6a61e', - 'description': 'md5:22f03309b216ac84720183961441d8db', - 'uploader': 'md5:723e6cb3091241160f20b3c5dc282af1', + 'title': r're:9\.6K views · 355 reactions .+ Let the “Slapathon” commence!! .+ LL COOL J · Mama Said Knock You Out$', + 'description': r're:When your trying to help your partner .+ LL COOL J · Mama Said Knock You Out$', + 'uploader': 'Beast Camp Training', 'uploader_id': '100040874179269', 'duration': 9.579, 'timestamp': 1637502609, 'upload_date': '20211121', 'thumbnail': r're:^https?://.*', + 'like_count': int, + 'comment_count': int, + 'repost_count': int, }, }] From cc85596d5b59f0c14e9381b3675f619c1e12e597 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Fri, 13 Sep 2024 18:19:18 -0500 Subject: [PATCH 010/154] [utils] `mimetype2ext`: Recognize `aacp` as `aac` (#10860) Authored by: bashonly --- yt_dlp/utils/_utils.py | 1 + 1 file changed, 1 insertion(+) diff --git a/yt_dlp/utils/_utils.py b/yt_dlp/utils/_utils.py index 0d3e707c5..04dd0f8d2 100644 --- a/yt_dlp/utils/_utils.py +++ b/yt_dlp/utils/_utils.py @@ -2919,6 +2919,7 @@ def mimetype2ext(mt, default=NO_DEFAULT): 'audio/webm': 'webm', 'audio/x-matroska': 'mka', 'audio/x-mpegurl': 'm3u', + 'aacp': 'aac', 'midi': 'mid', 'ogg': 'ogg', 'wav': 'wav', From 325001317d97f4545d66fac44c4ba772c6f45f22 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Fri, 13 Sep 2024 18:20:17 -0500 Subject: [PATCH 011/154] [ie] Handle decode errors when reading responses (#10868) Authored by: bashonly --- yt_dlp/extractor/common.py | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/yt_dlp/extractor/common.py b/yt_dlp/extractor/common.py index 432db9daf..9501e5ec9 100644 --- a/yt_dlp/extractor/common.py +++ b/yt_dlp/extractor/common.py @@ -35,6 +35,7 @@ from ..networking import HEADRequest, Request from ..networking.exceptions import ( HTTPError, IncompleteRead, + TransportError, network_exceptions, ) from ..networking.impersonate import ImpersonateTarget @@ -965,6 +966,9 @@ class InfoExtractor: return False content = self._webpage_read_content(urlh, url_or_request, video_id, note, errnote, fatal, encoding=encoding, data=data) + if content is False: + assert not fatal + return False return (content, urlh) @staticmethod @@ -1039,7 +1043,15 @@ class InfoExtractor: def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True, prefix=None, encoding=None, data=None): - webpage_bytes = urlh.read() + try: + webpage_bytes = urlh.read() + except TransportError as err: + errmsg = f'{video_id}: Error reading response: {err.msg}' + if fatal: + raise ExtractorError(errmsg, cause=err) + self.report_warning(errmsg) + return False + if prefix is not None: webpage_bytes = prefix + webpage_bytes if self.get_param('dump_intermediate_pages', False): From c8c078fe28b0ffc15ef9646346c00c592fe71a78 Mon Sep 17 00:00:00 2001 From: Sahil Singh Date: Sat, 14 Sep 2024 04:52:14 +0530 Subject: [PATCH 012/154] [ie/pinterest] Extend `_VALID_URL` (#10867) Closes #10850 Authored by: sahilsinghss73, bashonly Co-authored-by: bashonly <88596187+bashonly@users.noreply.github.com> --- yt_dlp/extractor/pinterest.py | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/yt_dlp/extractor/pinterest.py b/yt_dlp/extractor/pinterest.py index 07f249498..f0b38893b 100644 --- a/yt_dlp/extractor/pinterest.py +++ b/yt_dlp/extractor/pinterest.py @@ -109,7 +109,7 @@ class PinterestBaseIE(InfoExtractor): class PinterestIE(PinterestBaseIE): - _VALID_URL = rf'{PinterestBaseIE._VALID_URL_BASE}/pin/(?P\d+)' + _VALID_URL = rf'{PinterestBaseIE._VALID_URL_BASE}/pin/(?:[\w-]+--)?(?P\d+)' _TESTS = [{ # formats found in data['videos'] 'url': 'https://www.pinterest.com/pin/664281013778109217/', @@ -174,6 +174,25 @@ class PinterestIE(PinterestBaseIE): }, { 'url': 'https://co.pinterest.com/pin/824721750502199491/', 'only_matching': True, + }, + { + 'url': 'https://pinterest.com/pin/dive-into-serenity-blue-lagoon-pedi-nails-for-a-tranquil-and-refreshing-spa-experience-video-in-2024--2885187256207927', + 'info_dict': { + 'id': '2885187256207927', + 'ext': 'mp4', + 'title': 'Dive into Serenity: Blue Lagoon Pedi Nails for a Tranquil and Refreshing Spa Experience! 💙💅', + 'description': 'md5:5da41c767d2317e42e49b663b0b2150f', + 'uploader': 'Glamour Artistry |Everyday Outfits, Luxury Fashion & Nail Designs', + 'uploader_id': '1142999717836434688', + 'upload_date': '20240702', + 'timestamp': 1719939156, + 'duration': 7.967, + 'comment_count': int, + 'repost_count': int, + 'categories': 'count:9', + 'tags': ['#BlueLagoonPediNails', '#SpaExperience'], + 'thumbnail': r're:^https?://.*\.(?:jpg|png)$', + }, }] def _real_extract(self, url): From fa83d0b36bc43d30fe9241c1e923f4614864b758 Mon Sep 17 00:00:00 2001 From: naglis <827324+naglis@users.noreply.github.com> Date: Fri, 13 Sep 2024 23:23:19 +0000 Subject: [PATCH 013/154] [ie/LnkGo] Remove extractor (#10904) Authored by: naglis --- yt_dlp/extractor/_extractors.py | 5 +- yt_dlp/extractor/{lnkgo.py => lnk.py} | 75 --------------------------- 2 files changed, 1 insertion(+), 79 deletions(-) rename yt_dlp/extractor/{lnkgo.py => lnk.py} (53%) diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index 8903bf8fc..257d07308 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -1041,10 +1041,7 @@ from .livestream import ( LivestreamShortenerIE, ) from .livestreamfails import LivestreamfailsIE -from .lnkgo import ( - LnkGoIE, - LnkIE, -) +from .lnk import LnkIE from .loom import ( LoomFolderIE, LoomIE, diff --git a/yt_dlp/extractor/lnkgo.py b/yt_dlp/extractor/lnk.py similarity index 53% rename from yt_dlp/extractor/lnkgo.py rename to yt_dlp/extractor/lnk.py index 31a7cefd8..593f73410 100644 --- a/yt_dlp/extractor/lnkgo.py +++ b/yt_dlp/extractor/lnk.py @@ -1,86 +1,11 @@ from .common import InfoExtractor from ..utils import ( - clean_html, format_field, int_or_none, - parse_iso8601, unified_strdate, ) -class LnkGoIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?lnk(?:go)?\.(?:alfa\.)?lt/(?:visi-video/[^/]+|video)/(?P[A-Za-z0-9-]+)(?:/(?P\d+))?' - _TESTS = [{ - 'url': 'http://www.lnkgo.lt/visi-video/aktualai-pratesimas/ziurek-putka-trys-klausimai', - 'info_dict': { - 'id': '10809', - 'ext': 'mp4', - 'title': "Put'ka: Trys Klausimai", - 'upload_date': '20161216', - 'description': 'Seniai matytas Put’ka užduoda tris klausimėlius. Pabandykime surasti atsakymus.', - 'age_limit': 18, - 'duration': 117, - 'thumbnail': r're:^https?://.*\.jpg$', - 'timestamp': 1481904000, - }, - 'params': { - 'skip_download': True, # HLS download - }, - }, { - 'url': 'http://lnkgo.alfa.lt/visi-video/aktualai-pratesimas/ziurek-nerdas-taiso-kompiuteri-2', - 'info_dict': { - 'id': '10467', - 'ext': 'mp4', - 'title': 'Nėrdas: Kompiuterio Valymas', - 'upload_date': '20150113', - 'description': 'md5:7352d113a242a808676ff17e69db6a69', - 'age_limit': 18, - 'duration': 346, - 'thumbnail': r're:^https?://.*\.jpg$', - 'timestamp': 1421164800, - }, - 'params': { - 'skip_download': True, # HLS download - }, - }, { - 'url': 'https://lnk.lt/video/neigalieji-tv-bokste/37413', - 'only_matching': True, - }] - _AGE_LIMITS = { - 'N-7': 7, - 'N-14': 14, - 'S': 18, - } - _M3U8_TEMPL = 'https://vod.lnk.lt/lnk_vod/lnk/lnk/%s:%s/playlist.m3u8%s' - - def _real_extract(self, url): - display_id, video_id = self._match_valid_url(url).groups() - - video_info = self._download_json( - 'https://lnk.lt/api/main/video-page/{}/{}/false'.format(display_id, video_id or '0'), - display_id)['videoConfig']['videoInfo'] - - video_id = str(video_info['id']) - title = video_info['title'] - prefix = 'smil' if video_info.get('isQualityChangeAvailable') else 'mp4' - formats = self._extract_m3u8_formats( - self._M3U8_TEMPL % (prefix, video_info['videoUrl'], video_info.get('secureTokenParams') or ''), - video_id, 'mp4', 'm3u8_native') - - return { - 'id': video_id, - 'display_id': display_id, - 'title': title, - 'formats': formats, - 'thumbnail': format_field(video_info, 'posterImage', 'https://lnk.lt/all-images/%s'), - 'duration': int_or_none(video_info.get('duration')), - 'description': clean_html(video_info.get('htmlDescription')), - 'age_limit': self._AGE_LIMITS.get(video_info.get('pgRating'), 0), - 'timestamp': parse_iso8601(video_info.get('airDate')), - 'view_count': int_or_none(video_info.get('viewsCount')), - } - - class LnkIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?lnk\.lt/[^/]+/(?P\d+)' From 7adff8caf152dcf96d03aff69ed8545c0a63567c Mon Sep 17 00:00:00 2001 From: ischmidt20 Date: Fri, 13 Sep 2024 19:25:12 -0400 Subject: [PATCH 014/154] [ie/WatchESPN] Improve auth support (#10910) Authored by: ischmidt20 --- yt_dlp/extractor/espn.py | 39 +++++++++++++++++++++++---------------- 1 file changed, 23 insertions(+), 16 deletions(-) diff --git a/yt_dlp/extractor/espn.py b/yt_dlp/extractor/espn.py index 4e9b63524..552f9af12 100644 --- a/yt_dlp/extractor/espn.py +++ b/yt_dlp/extractor/espn.py @@ -294,37 +294,37 @@ class ESPNCricInfoIE(InfoExtractor): class WatchESPNIE(AdobePassIE): _VALID_URL = r'https?://(?:www\.)?espn\.com/(?:watch|espnplus)/player/_/id/(?P[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12})' _TESTS = [{ - 'url': 'https://www.espn.com/watch/player/_/id/dbbc6b1d-c084-4b47-9878-5f13c56ce309', + 'url': 'https://www.espn.com/watch/player/_/id/11ce417a-6ac9-42b6-8a15-46aeb9ad5710', 'info_dict': { - 'id': 'dbbc6b1d-c084-4b47-9878-5f13c56ce309', + 'id': '11ce417a-6ac9-42b6-8a15-46aeb9ad5710', 'ext': 'mp4', - 'title': 'Huddersfield vs. Burnley', - 'duration': 7500, - 'thumbnail': 'https://artwork.api.espn.com/artwork/collections/media/dbbc6b1d-c084-4b47-9878-5f13c56ce309/default?width=640&apikey=1ngjw23osgcis1i1vbj96lmfqs', + 'title': 'Abilene Chrstn vs. Texas Tech', + 'duration': 14166, + 'thumbnail': 'https://s.secure.espncdn.com/stitcher/artwork/collections/media/11ce417a-6ac9-42b6-8a15-46aeb9ad5710/16x9.jpg?timestamp=202407252343&showBadge=true&cb=12&package=ESPN_PLUS', }, 'params': { 'skip_download': True, }, }, { - 'url': 'https://www.espn.com/watch/player/_/id/a049a56e-a7ce-477e-aef3-c7e48ef8221c', + 'url': 'https://www.espn.com/watch/player/_/id/90a2c85d-75e0-4b1e-a878-8e428a3cb2f3', 'info_dict': { - 'id': 'a049a56e-a7ce-477e-aef3-c7e48ef8221c', + 'id': '90a2c85d-75e0-4b1e-a878-8e428a3cb2f3', 'ext': 'mp4', - 'title': 'Dynamo Dresden vs. VfB Stuttgart (Round #1) (German Cup)', - 'duration': 8335, - 'thumbnail': 'https://s.secure.espncdn.com/stitcher/artwork/collections/media/bd1f3d12-0654-47d9-852e-71b85ea695c7/16x9.jpg?timestamp=202201112217&showBadge=true&cb=12&package=ESPN_PLUS', + 'title': 'UC Davis vs. California', + 'duration': 9547, + 'thumbnail': 'https://artwork.api.espn.com/artwork/collections/media/90a2c85d-75e0-4b1e-a878-8e428a3cb2f3/default?width=640&apikey=1ngjw23osgcis1i1vbj96lmfqs', }, 'params': { 'skip_download': True, }, }, { - 'url': 'https://www.espn.com/espnplus/player/_/id/317f5fd1-c78a-4ebe-824a-129e0d348421', + 'url': 'https://www.espn.com/watch/player/_/id/c4313bbe-95b5-4bb8-b251-ac143ea0fc54', 'info_dict': { - 'id': '317f5fd1-c78a-4ebe-824a-129e0d348421', + 'id': 'c4313bbe-95b5-4bb8-b251-ac143ea0fc54', 'ext': 'mp4', - 'title': 'The Wheel - Episode 10', - 'duration': 3352, - 'thumbnail': 'https://s.secure.espncdn.com/stitcher/artwork/collections/media/317f5fd1-c78a-4ebe-824a-129e0d348421/16x9.jpg?timestamp=202205031523&showBadge=true&cb=12&package=ESPN_PLUS', + 'title': 'The College Football Show', + 'duration': 3639, + 'thumbnail': 'https://artwork.api.espn.com/artwork/collections/media/c4313bbe-95b5-4bb8-b251-ac143ea0fc54/default?width=640&apikey=1ngjw23osgcis1i1vbj96lmfqs', }, 'params': { 'skip_download': True, @@ -353,6 +353,13 @@ class WatchESPNIE(AdobePassIE): if not cookie: self.raise_login_required(method='cookies') + jwt = self._search_regex(r'=([^|]+)\|', cookie.value, 'cookie jwt') + id_token = self._download_json( + 'https://registerdisney.go.com/jgc/v6/client/ESPN-ONESITE.WEB-PROD/guest/refresh-auth', + None, 'Refreshing token', headers={'Content-Type': 'application/json'}, data=json.dumps({ + 'refreshToken': json.loads(base64.urlsafe_b64decode(f'{jwt}==='))['refresh_token'], + }).encode())['data']['token']['id_token'] + assertion = self._call_bamgrid_api( 'devices', video_id, headers={'Content-Type': 'application/json; charset=UTF-8'}, @@ -371,7 +378,7 @@ class WatchESPNIE(AdobePassIE): })['access_token'] assertion = self._call_bamgrid_api( - 'accounts/grant', video_id, payload={'id_token': cookie.value.split('|')[1]}, + 'accounts/grant', video_id, payload={'id_token': id_token}, headers={ 'Authorization': token, 'Content-Type': 'application/json; charset=UTF-8', From 36f9e602ad55679764bc75a4f67f7562b1d6adcf Mon Sep 17 00:00:00 2001 From: naglis <827324+naglis@users.noreply.github.com> Date: Fri, 13 Sep 2024 23:27:10 +0000 Subject: [PATCH 015/154] [ie/screenrec] Add extractor (#10917) Closes #9780 Authored by: naglis --- yt_dlp/extractor/_extractors.py | 1 + yt_dlp/extractor/screenrec.py | 33 +++++++++++++++++++++++++++++++++ 2 files changed, 34 insertions(+) create mode 100644 yt_dlp/extractor/screenrec.py diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index 257d07308..597876197 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -1812,6 +1812,7 @@ from .screen9 import Screen9IE from .screencast import ScreencastIE from .screencastify import ScreencastifyIE from .screencastomatic import ScreencastOMaticIE +from .screenrec import ScreenRecIE from .scrippsnetworks import ( ScrippsNetworksIE, ScrippsNetworksWatchIE, diff --git a/yt_dlp/extractor/screenrec.py b/yt_dlp/extractor/screenrec.py new file mode 100644 index 000000000..64f8d2494 --- /dev/null +++ b/yt_dlp/extractor/screenrec.py @@ -0,0 +1,33 @@ +from .common import InfoExtractor + + +class ScreenRecIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?screenrec\.com/share/(?P\w{10})' + _TESTS = [{ + 'url': 'https://screenrec.com/share/DasLtbknYo', + 'info_dict': { + 'id': 'DasLtbknYo', + 'ext': 'mp4', + 'title': '02.05.2024_03.01.25_REC', + 'description': 'Recorded with ScreenRec', + 'thumbnail': r're:^https?://.*\.gif$', + }, + 'params': { + 'skip_download': True, + }, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + m3u8_url = self._search_regex( + r'customUrl\s*:\s*(["\'])(?P(?:(?!\1).)+)\1', webpage, 'm3u8 URL', group='url') + + return { + 'id': video_id, + 'title': self._og_search_title(webpage, default=None) or self._html_extract_title(webpage), + 'description': self._og_search_description(webpage), + 'thumbnail': self._og_search_thumbnail(webpage), + 'formats': self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4'), + } From d8d473002b654ab0e7b97ead869f58b4361eeae1 Mon Sep 17 00:00:00 2001 From: aarubui Date: Sat, 14 Sep 2024 10:09:15 +1000 Subject: [PATCH 016/154] [ie/tenplay] Fix extractor (#10928) Closes #10926 Authored by: aarubui --- yt_dlp/extractor/tenplay.py | 104 +++++++++++++++++------------------- 1 file changed, 49 insertions(+), 55 deletions(-) diff --git a/yt_dlp/extractor/tenplay.py b/yt_dlp/extractor/tenplay.py index d8c556ace..07db58347 100644 --- a/yt_dlp/extractor/tenplay.py +++ b/yt_dlp/extractor/tenplay.py @@ -1,33 +1,31 @@ -import base64 -import datetime as dt import functools import itertools from .common import InfoExtractor from ..networking import HEADRequest -from ..utils import int_or_none, traverse_obj, urlencode_postdata, urljoin +from ..utils import int_or_none, traverse_obj, url_or_none, urljoin class TenPlayIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?10play\.com\.au/(?:[^/]+/)+(?Ptpv\d{6}[a-z]{5})' _NETRC_MACHINE = '10play' _TESTS = [{ - 'url': 'https://10play.com.au/neighbours/web-extras/season-39/nathan-borg-is-the-first-aussie-actor-with-a-cochlear-implant-to-join-neighbours/tpv210128qupwd', + 'url': 'https://10play.com.au/neighbours/web-extras/season-41/heres-a-first-look-at-mischa-bartons-neighbours-debut/tpv230911hyxnz', 'info_dict': { - 'id': '6226844312001', + 'id': '6336940246112', 'ext': 'mp4', - 'title': 'Nathan Borg Is The First Aussie Actor With A Cochlear Implant To Join Neighbours', - 'alt_title': 'Nathan Borg Is The First Aussie Actor With A Cochlear Implant To Join Neighbours', - 'description': 'md5:a02d0199c901c2dd4c796f1e7dd0de43', - 'duration': 186, - 'season': 'Season 39', - 'season_number': 39, + 'title': 'Here\'s A First Look At Mischa Barton\'s Neighbours Debut', + 'alt_title': 'Here\'s A First Look At Mischa Barton\'s Neighbours Debut', + 'description': 'Neighbours Premieres Monday, September 18 At 4:30pm On 10 And 10 Play And 6:30pm On 10 Peach', + 'duration': 74, + 'season': 'Season 41', + 'season_number': 41, 'series': 'Neighbours', 'thumbnail': r're:https://.*\.jpg', 'uploader': 'Channel 10', 'age_limit': 15, - 'timestamp': 1611810000, - 'upload_date': '20210128', + 'timestamp': 1694386800, + 'upload_date': '20230910', 'uploader_id': '2199827728001', }, 'params': { @@ -35,21 +33,30 @@ class TenPlayIE(InfoExtractor): }, 'skip': 'Only available in Australia', }, { - 'url': 'https://10play.com.au/todd-sampsons-body-hack/episodes/season-4/episode-7/tpv200921kvngh', + 'url': 'https://10play.com.au/neighbours/episodes/season-42/episode-9107/tpv240902nzqyp', 'info_dict': { - 'id': '6192880312001', + 'id': '9000000000091177', 'ext': 'mp4', - 'title': "Todd Sampson's Body Hack - S4 Ep. 2", - 'description': 'md5:fa278820ad90f08ea187f9458316ac74', + 'title': 'Neighbours - S42 Ep. 9107', + 'alt_title': 'Thu 05 Sep', + 'description': 'md5:37a1f4271be34b9ee2b533426a5fbaef', + 'duration': 1388, + 'episode': 'Episode 9107', + 'episode_number': 9107, + 'season': 'Season 42', + 'season_number': 42, + 'series': 'Neighbours', + 'thumbnail': r're:https://.*\.jpg', 'age_limit': 15, - 'timestamp': 1600770600, - 'upload_date': '20200922', + 'timestamp': 1725517860, + 'upload_date': '20240905', 'uploader': 'Channel 10', 'uploader_id': '2199827728001', }, 'params': { 'skip_download': True, }, + 'skip': 'Only available in Australia', }, { 'url': 'https://10play.com.au/how-to-stay-married/web-extras/season-1/terrys-talks-ep-1-embracing-change/tpv190915ylupc', 'only_matching': True, @@ -66,55 +73,42 @@ class TenPlayIE(InfoExtractor): 'X': 18, } - def _get_bearer_token(self, video_id): - username, password = self._get_login_info() - if username is None or password is None: - self.raise_login_required('Your 10play account\'s details must be provided with --username and --password.') - _timestamp = dt.datetime.now().strftime('%Y%m%d000000') - _auth_header = base64.b64encode(_timestamp.encode('ascii')).decode('ascii') - data = self._download_json('https://10play.com.au/api/user/auth', video_id, 'Getting bearer token', headers={ - 'X-Network-Ten-Auth': _auth_header, - }, data=urlencode_postdata({ - 'email': username, - 'password': password, - })) - return 'Bearer ' + data['jwt']['accessToken'] - def _real_extract(self, url): content_id = self._match_id(url) data = self._download_json( 'https://10play.com.au/api/v1/videos/' + content_id, content_id) - headers = {} - if data.get('memberGated') is True: - _token = self._get_bearer_token(content_id) - headers = {'Authorization': _token} - - _video_url = self._download_json( - data.get('playbackApiEndpoint'), content_id, 'Downloading video JSON', - headers=headers).get('source') - m3u8_url = self._request_webpage(HEADRequest( - _video_url), content_id).url + video_data = self._download_json( + f'https://vod.ten.com.au/api/videos/bcquery?command=find_videos_by_id&video_id={data["altId"]}', + content_id, 'Downloading video JSON') + m3u8_url = self._request_webpage( + HEADRequest(video_data['items'][0]['HLSURL']), + content_id, 'Checking stream URL').url if '10play-not-in-oz' in m3u8_url: self.raise_geo_restricted(countries=['AU']) + # Attempt to get a higher quality stream + m3u8_url = m3u8_url.replace(',150,75,55,0000', ',300,150,75,55,0000') formats = self._extract_m3u8_formats(m3u8_url, content_id, 'mp4') return { + 'id': content_id, 'formats': formats, - 'subtitles': {'en': [{'url': data.get('captionUrl')}]} if data.get('captionUrl') else None, - 'id': data.get('altId') or content_id, - 'duration': data.get('duration'), - 'title': data.get('subtitle'), - 'alt_title': data.get('title'), - 'description': data.get('description'), - 'age_limit': self._AUS_AGES.get(data.get('classification')), - 'series': data.get('tvShow'), - 'season_number': int_or_none(data.get('season')), - 'episode_number': int_or_none(data.get('episode')), - 'timestamp': data.get('published'), - 'thumbnail': data.get('imageUrl'), + 'subtitles': {'en': [{'url': data['captionUrl']}]} if url_or_none(data.get('captionUrl')) else None, 'uploader': 'Channel 10', 'uploader_id': '2199827728001', + **traverse_obj(data, { + 'id': ('altId', {str}), + 'duration': ('duration', {int_or_none}), + 'title': ('subtitle', {str}), + 'alt_title': ('title', {str}), + 'description': ('description', {str}), + 'age_limit': ('classification', {self._AUS_AGES.get}), + 'series': ('tvShow', {str}), + 'season_number': ('season', {int_or_none}), + 'episode_number': ('episode', {int_or_none}), + 'timestamp': ('published', {int_or_none}), + 'thumbnail': ('imageUrl', {url_or_none}), + }), } From 300c91274f7ea5b1b0528fc5ee11cf1a61d4079e Mon Sep 17 00:00:00 2001 From: sepro Date: Sat, 14 Sep 2024 02:14:09 +0200 Subject: [PATCH 017/154] [ie/Servus] Fix extractor (#10944) Closes #10941 Authored by: seproDev --- yt_dlp/extractor/servus.py | 29 ++++++++++++++++++----------- 1 file changed, 18 insertions(+), 11 deletions(-) diff --git a/yt_dlp/extractor/servus.py b/yt_dlp/extractor/servus.py index 117f18081..841c7ebf3 100644 --- a/yt_dlp/extractor/servus.py +++ b/yt_dlp/extractor/servus.py @@ -27,7 +27,7 @@ class ServusIE(InfoExtractor): 'info_dict': { 'id': 'AA-28BYCQNH92111', 'ext': 'mp4', - 'title': 'Klettersteige in den Alpen', + 'title': 'Vie Ferrate - Klettersteige in den Alpen', 'description': 'md5:25e47ddd83a009a0f9789ba18f2850ce', 'thumbnail': r're:^https?://.*\.jpg', 'duration': 2823, @@ -38,6 +38,7 @@ class ServusIE(InfoExtractor): 'season_number': 11, 'episode': 'Episode 8 - Vie Ferrate – Klettersteige in den Alpen', 'episode_number': 8, + 'categories': ['Bergwelten'], }, 'params': {'skip_download': 'm3u8'}, }, { @@ -71,8 +72,11 @@ class ServusIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url).upper() + webpage = self._download_webpage(url, video_id) + next_data = self._search_nextjs_data(webpage, video_id, fatal=False) + video = self._download_json( - 'https://api-player.redbull.com/stv/servus-tv?timeZone=Europe/Berlin', + 'https://api-player.redbull.com/stv/servus-tv-playnet', video_id, 'Downloading video JSON', query={'videoId': video_id}) if not video.get('videoUrl'): self._report_errors(video) @@ -89,7 +93,7 @@ class ServusIE(InfoExtractor): return { 'id': video_id, 'title': video.get('title'), - 'description': self._get_description(video_id) or video.get('description'), + 'description': self._get_description(next_data) or video.get('description'), 'thumbnail': video.get('poster'), 'duration': float_or_none(video.get('duration')), 'timestamp': unified_timestamp(video.get('currentSunrise')), @@ -100,16 +104,19 @@ class ServusIE(InfoExtractor): 'episode_number': episode_number, 'formats': formats, 'subtitles': subtitles, + **traverse_obj(next_data, ('props', 'pageProps', 'data', { + 'title': ('title', 'rendered', {str}), + 'timestamp': ('stv_date', 'raw', {int}), + 'duration': ('stv_duration', {float_or_none}), + 'categories': ('category_names', ..., {str}), + })), } - def _get_description(self, video_id): - info = self._download_json( - f'https://backend.servustv.com/wp-json/rbmh/v2/media_asset/aa_id/{video_id}?fieldset=page', - video_id, fatal=False) - - return join_nonempty(*traverse_obj(info, ( - ('stv_short_description', 'stv_long_description'), - {lambda x: unescapeHTML(x.replace('\n\n', '\n'))})), delim='\n\n') + def _get_description(self, next_data): + return join_nonempty(*traverse_obj(next_data, ( + 'props', 'pageProps', 'data', + ('stv_short_description', 'stv_long_description'), {str}, + {lambda x: x.replace('\n\n', '\n')}, {unescapeHTML})), delim='\n\n') def _report_errors(self, video): playability_errors = traverse_obj(video, ('playabilityErrors', ...)) From 3aa0156e05662923d130ddbc1c82596e38c01a00 Mon Sep 17 00:00:00 2001 From: sepro Date: Sat, 14 Sep 2024 02:15:07 +0200 Subject: [PATCH 018/154] [ie/Xinpianchang] Fix extractor (#10950) Authored by: seproDev --- yt_dlp/extractor/xinpianchang.py | 24 +++++++++++------------- 1 file changed, 11 insertions(+), 13 deletions(-) diff --git a/yt_dlp/extractor/xinpianchang.py b/yt_dlp/extractor/xinpianchang.py index 10849916b..23ed9270d 100644 --- a/yt_dlp/extractor/xinpianchang.py +++ b/yt_dlp/extractor/xinpianchang.py @@ -3,16 +3,13 @@ from ..utils import ( int_or_none, str_or_none, try_get, - update_url_query, url_or_none, ) class XinpianchangIE(InfoExtractor): - _WORKING = False - _VALID_URL = r'https?://www\.xinpianchang\.com/(?P[^/]+?)(?:\D|$)' - IE_NAME = 'xinpianchang' - IE_DESC = 'xinpianchang.com' + _VALID_URL = r'https?://(www\.)?xinpianchang\.com/(?Pa\d+)' + IE_DESC = '新片场' _TESTS = [{ 'url': 'https://www.xinpianchang.com/a11766551', 'info_dict': { @@ -49,11 +46,11 @@ class XinpianchangIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id=video_id) - domain = self.find_value_with_regex(var='requireNewDomain', webpage=webpage) - vid = self.find_value_with_regex(var='vid', webpage=webpage) - app_key = self.find_value_with_regex(var='modeServerAppKey', webpage=webpage) - api = update_url_query(f'{domain}/mod/api/v2/media/{vid}', {'appKey': app_key}) - data = self._download_json(api, video_id=video_id)['data'] + video_data = self._search_nextjs_data(webpage, video_id)['props']['pageProps']['detail']['video'] + + data = self._download_json( + f'https://mod-api.xinpianchang.com/mod/api/v2/media/{video_data["vid"]}', video_id, + query={'appKey': video_data['appKey']})['data'] formats, subtitles = [], {} for k, v in data.get('resource').items(): if k in ('dash', 'hls'): @@ -72,6 +69,10 @@ class XinpianchangIE(InfoExtractor): 'width': int_or_none(prog.get('width')), 'height': int_or_none(prog.get('height')), 'ext': 'mp4', + 'http_headers': { + # NB: Server returns 403 without the Range header + 'Range': 'bytes=0-', + }, } for prog in v if prog.get('url') or []]) return { @@ -87,6 +88,3 @@ class XinpianchangIE(InfoExtractor): 'formats': formats, 'subtitles': subtitles, } - - def find_value_with_regex(self, var, webpage): - return self._search_regex(rf'var\s{var}\s=\s\"(?P[^\"]+)\"', webpage, name=var) From 41a241ca6ffb95b3d9aaf4f42106ca8cba9af1a6 Mon Sep 17 00:00:00 2001 From: sepro Date: Sat, 14 Sep 2024 02:16:34 +0200 Subject: [PATCH 019/154] [ie/Sen] Add extractor (#10952) Closes #10951 Authored by: seproDev --- yt_dlp/extractor/_extractors.py | 1 + yt_dlp/extractor/sen.py | 36 +++++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+) create mode 100644 yt_dlp/extractor/sen.py diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index 597876197..d8abf0b5d 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -1823,6 +1823,7 @@ from .scte import ( SCTECourseIE, ) from .sejmpl import SejmIE +from .sen import SenIE from .senalcolombia import SenalColombiaLiveIE from .senategov import ( SenateGovIE, diff --git a/yt_dlp/extractor/sen.py b/yt_dlp/extractor/sen.py new file mode 100644 index 000000000..d8f14ecdc --- /dev/null +++ b/yt_dlp/extractor/sen.py @@ -0,0 +1,36 @@ +from .common import InfoExtractor +from ..utils import url_or_none +from ..utils.traversal import traverse_obj + + +class SenIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?sen\.com/video/(?P[0-9a-f-]+)' + _TEST = { + 'url': 'https://www.sen.com/video/eef46eb1-4d79-4e28-be9d-bd937767f8c4', + 'md5': 'ff615aca9691053c94f8f10d96cd7884', + 'info_dict': { + 'id': 'eef46eb1-4d79-4e28-be9d-bd937767f8c4', + 'ext': 'mp4', + 'description': 'Florida, 28 Sep 2022', + 'title': 'Hurricane Ian', + 'tags': ['North America', 'Storm', 'Weather'], + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + api_data = self._download_json(f'https://api.sen.com/content/public/video/{video_id}', video_id) + m3u8_url = (traverse_obj(api_data, ( + 'data', 'nodes', lambda _, v: v['id'] == 'player', 'video', 'url', {url_or_none}, any)) + or f'https://vod.sen.com/videos/{video_id}/manifest.m3u8') + + return { + 'id': video_id, + 'formats': self._extract_m3u8_formats(m3u8_url, video_id, 'mp4'), + **traverse_obj(api_data, ('data', 'nodes', lambda _, v: v['id'] == 'details', any, 'content', { + 'title': ('title', 'text', {str}), + 'description': ('descriptions', 0, 'text', {str}), + 'tags': ('badges', ..., 'text', {str}), + })), + } From 4a27b8f092f7f7c10b7a334d3535c97c2af02f0a Mon Sep 17 00:00:00 2001 From: Oto Valek Date: Sat, 14 Sep 2024 02:19:03 +0200 Subject: [PATCH 020/154] [ie/IPrima] Fix zoom URL support (#10959) Closes #6100 Authored by: otovalek --- yt_dlp/extractor/iprima.py | 29 +++++++++++++++++++++++++---- 1 file changed, 25 insertions(+), 4 deletions(-) diff --git a/yt_dlp/extractor/iprima.py b/yt_dlp/extractor/iprima.py index ab26dc5ef..9b91a454b 100644 --- a/yt_dlp/extractor/iprima.py +++ b/yt_dlp/extractor/iprima.py @@ -25,9 +25,29 @@ class IPrimaIE(InfoExtractor): 'id': 'p51388', 'ext': 'mp4', 'title': 'Partička (92)', - 'description': 'md5:859d53beae4609e6dd7796413f1b6cac', - 'upload_date': '20201103', - 'timestamp': 1604437480, + 'description': 'md5:57943f6a50d6188288c3a579d2fd5f01', + 'episode': 'Partička (92)', + 'season': 'Partička', + 'series': 'Prima Partička', + 'episode_number': 92, + 'thumbnail': 'https://d31b9s05ygj54s.cloudfront.net/prima-plus/image/video-ef6cf9de-c980-4443-92e4-17fe8bccd45c-16x9.jpeg', + }, + 'params': { + 'skip_download': True, # m3u8 download + }, + }, { + 'url': 'https://zoom.iprima.cz/porady/krasy-kanarskych-ostrovu/tenerife-v-risi-ohne', + 'info_dict': { + 'id': 'p1412199', + 'ext': 'mp4', + 'episode_number': 3, + 'episode': 'Tenerife: V říši ohně', + 'description': 'md5:4b4a05c574b5eaef130e68d4811c3f2c', + 'duration': 3111.0, + 'thumbnail': 'https://d31b9s05ygj54s.cloudfront.net/prima-plus/image/video-f66dd7fb-c1a0-47d1-b3bc-7db328d566c5-16x9-1711636518.jpg/t_16x9_medium_1366_768', + 'title': 'Tenerife: V říši ohně', + 'timestamp': 1711825800, + 'upload_date': '20240330', }, 'params': { 'skip_download': True, # m3u8 download @@ -131,6 +151,7 @@ class IPrimaIE(InfoExtractor): video_id = self._search_regex(( r'productId\s*=\s*([\'"])(?Pp\d+)\1', r'pproduct_id\s*=\s*([\'"])(?Pp\d+)\1', + r'let\s+videos\s*=\s*([\'"])(?Pp\d+)\1', ), webpage, 'real id', group='id', default=None) if not video_id: @@ -176,7 +197,7 @@ class IPrimaIE(InfoExtractor): final_result = self._search_json_ld(webpage, video_id, default={}) final_result.update({ 'id': video_id, - 'title': title, + 'title': final_result.get('title') or title, 'thumbnail': self._html_search_meta( ['thumbnail', 'og:image', 'twitter:image'], webpage, 'thumbnail', default=None), From 173d54c151b987409e3eb09552d8d89ed8fc50f7 Mon Sep 17 00:00:00 2001 From: N/Ame <173015200+grqz@users.noreply.github.com> Date: Sat, 14 Sep 2024 12:21:07 +1200 Subject: [PATCH 021/154] [ie/kick:vod] Support new URL format (#10988) Closes #10975 Authored by: grqz, bashonly Co-authored-by: bashonly <88596187+bashonly@users.noreply.github.com> --- yt_dlp/extractor/kick.py | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/yt_dlp/extractor/kick.py b/yt_dlp/extractor/kick.py index 1c1b2a177..abea5280b 100644 --- a/yt_dlp/extractor/kick.py +++ b/yt_dlp/extractor/kick.py @@ -67,7 +67,7 @@ class KickIE(KickBaseIE): @classmethod def suitable(cls, url): - return False if KickClipIE.suitable(url) else super().suitable(url) + return False if (KickVODIE.suitable(url) or KickClipIE.suitable(url)) else super().suitable(url) def _real_extract(self, url): channel = self._match_id(url) @@ -98,25 +98,25 @@ class KickIE(KickBaseIE): class KickVODIE(KickBaseIE): IE_NAME = 'kick:vod' - _VALID_URL = r'https?://(?:www\.)?kick\.com/video/(?P[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})' + _VALID_URL = r'https?://(?:www\.)?kick\.com/[\w-]+/videos/(?P[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})' _TESTS = [{ - 'url': 'https://kick.com/video/e74614f4-5270-4319-90ad-32179f19a45c', + 'url': 'https://kick.com/xqc/videos/8dd97a8d-e17f-48fb-8bc3-565f88dbc9ea', 'md5': '3870f94153e40e7121a6e46c068b70cb', 'info_dict': { - 'id': 'e74614f4-5270-4319-90ad-32179f19a45c', + 'id': '8dd97a8d-e17f-48fb-8bc3-565f88dbc9ea', 'ext': 'mp4', - 'title': r're:❎ MEGA DRAMA ❎ LIVE ❎ CLICK ❎ ULTIMATE SKILLS .+', + 'title': '18+ #ad 🛑LIVE🛑CLICK🛑DRAMA🛑NEWS🛑STUFF🛑REACT🛑GET IN HHERE🛑BOP BOP🛑WEEEE WOOOO🛑', 'description': 'THE BEST AT ABSOLUTELY EVERYTHING. THE JUICER. LEADER OF THE JUICERS.', 'channel': 'xqc', 'channel_id': '668', 'uploader': 'xQc', 'uploader_id': '676', - 'upload_date': '20240724', - 'timestamp': 1721796562, - 'duration': 18566.0, + 'upload_date': '20240909', + 'timestamp': 1725919141, + 'duration': 10155.0, 'thumbnail': r're:^https?://.*\.jpg', 'view_count': int, - 'categories': ['VALORANT'], + 'categories': ['Just Chatting'], 'age_limit': 0, }, 'params': {'skip_download': 'm3u8'}, From a555389c9bb32e589e00b4664974423fb7b04dcd Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Fri, 13 Sep 2024 19:23:22 -0500 Subject: [PATCH 022/154] [ie/HGTVDe] Fix extractor (#10992) Closes #10984 Authored by: bashonly, rdamas Co-authored-by: Robert Damas --- yt_dlp/extractor/dplay.py | 65 +++++++++++++++++++++++---------------- 1 file changed, 39 insertions(+), 26 deletions(-) diff --git a/yt_dlp/extractor/dplay.py b/yt_dlp/extractor/dplay.py index 8d7707271..86950b244 100644 --- a/yt_dlp/extractor/dplay.py +++ b/yt_dlp/extractor/dplay.py @@ -319,32 +319,6 @@ class DPlayIE(DPlayBaseIE): url, display_id, host, 'dplay' + country, country, domain) -class HGTVDeIE(DPlayBaseIE): - _VALID_URL = r'https?://de\.hgtv\.com/sendungen' + DPlayBaseIE._PATH_REGEX - _TESTS = [{ - 'url': 'https://de.hgtv.com/sendungen/tiny-house-klein-aber-oho/wer-braucht-schon-eine-toilette/', - 'info_dict': { - 'id': '151205', - 'display_id': 'tiny-house-klein-aber-oho/wer-braucht-schon-eine-toilette', - 'ext': 'mp4', - 'title': 'Wer braucht schon eine Toilette', - 'description': 'md5:05b40a27e7aed2c9172de34d459134e2', - 'duration': 1177.024, - 'timestamp': 1595705400, - 'upload_date': '20200725', - 'creator': 'HGTV', - 'series': 'Tiny House - klein, aber oho', - 'season_number': 3, - 'episode_number': 3, - }, - }] - - def _real_extract(self, url): - display_id = self._match_id(url) - return self._get_disco_api_info( - url, display_id, 'eu1-prod.disco-api.com', 'hgtv', 'de') - - class DiscoveryPlusBaseIE(DPlayBaseIE): """Subclasses must set _PRODUCT, _DISCO_API_PARAMS""" @@ -373,6 +347,45 @@ class DiscoveryPlusBaseIE(DPlayBaseIE): return self._get_disco_api_info(url, self._match_id(url), **self._DISCO_API_PARAMS) +class HGTVDeIE(DiscoveryPlusBaseIE): + _VALID_URL = r'https?://de\.hgtv\.com/sendungen' + DPlayBaseIE._PATH_REGEX + _TESTS = [{ + 'url': 'https://de.hgtv.com/sendungen/mein-kleinstadt-traumhaus/vom-landleben-ins-loft', + 'info_dict': { + 'id': '7332936', + 'ext': 'mp4', + 'display_id': 'mein-kleinstadt-traumhaus/vom-landleben-ins-loft', + 'title': 'Vom Landleben ins Loft', + 'description': 'md5:e5f72c02c853970796dd3818f2e25745', + 'episode': 'Episode 7', + 'episode_number': 7, + 'season': 'Season 7', + 'season_number': 7, + 'series': 'Mein Kleinstadt-Traumhaus', + 'duration': 2645.0, + 'timestamp': 1725998100, + 'upload_date': '20240910', + 'creators': ['HGTV'], + 'tags': [], + 'thumbnail': 'https://eu1-prod-images.disco-api.com/2024/08/09/82a386b9-c688-32c7-b9ff-0b13865f0bae.jpeg', + }, + }] + + _PRODUCT = 'hgtv' + _DISCO_API_PARAMS = { + 'disco_host': 'eu1-prod.disco-api.com', + 'realm': 'hgtv', + 'country': 'de', + } + + def _update_disco_api_headers(self, headers, disco_base, display_id, realm): + headers.update({ + 'x-disco-params': f'realm={realm}', + 'x-disco-client': 'Alps:HyogaPlayer:0.0.0', + 'Authorization': self._get_auth(disco_base, display_id, realm), + }) + + class GoDiscoveryIE(DiscoveryPlusBaseIE): _VALID_URL = r'https?://(?:go\.)?discovery\.com/video' + DPlayBaseIE._PATH_REGEX _TESTS = [{ From a06bb586795ebab87a2356923acfc674d6f0e152 Mon Sep 17 00:00:00 2001 From: Khaoklong51 <159044442+Khaoklong51@users.noreply.github.com> Date: Sat, 14 Sep 2024 23:19:17 +0700 Subject: [PATCH 023/154] [ie/BiliIntl] Fix referer header (#11003) Closes #10996 Authored by: Khaoklong51 --- yt_dlp/extractor/bilibili.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/yt_dlp/extractor/bilibili.py b/yt_dlp/extractor/bilibili.py index 3163df8ab..2fe1103cb 100644 --- a/yt_dlp/extractor/bilibili.py +++ b/yt_dlp/extractor/bilibili.py @@ -1852,7 +1852,7 @@ class BiliBiliPlayerIE(InfoExtractor): class BiliIntlBaseIE(InfoExtractor): _API_URL = 'https://api.bilibili.tv/intl/gateway' _NETRC_MACHINE = 'biliintl' - _HEADERS = {'Referer': 'https://www.bilibili.com/'} + _HEADERS = {'Referer': 'https://www.bilibili.tv/'} def _call_api(self, endpoint, *args, **kwargs): json = self._download_json(self._API_URL + endpoint, *args, **kwargs) From 4a9bc8c3630378bc29f0266126b503f6190c0430 Mon Sep 17 00:00:00 2001 From: 1-Byte <1-Byte@users.noreply.github.com> Date: Tue, 17 Sep 2024 21:17:05 +0200 Subject: [PATCH 024/154] [ie/NZZ] Fix extractor (#10461) Closes #5653 Authored by: 1-Byte --- yt_dlp/extractor/nzz.py | 22 +++++++--------------- 1 file changed, 7 insertions(+), 15 deletions(-) diff --git a/yt_dlp/extractor/nzz.py b/yt_dlp/extractor/nzz.py index ac3b73156..047c4e1ac 100644 --- a/yt_dlp/extractor/nzz.py +++ b/yt_dlp/extractor/nzz.py @@ -1,9 +1,6 @@ import re from .common import InfoExtractor -from ..utils import ( - extract_attributes, -) class NZZIE(InfoExtractor): @@ -22,19 +19,14 @@ class NZZIE(InfoExtractor): 'playlist_count': 1, }] + def _entries(self, webpage, page_id): + for script in re.findall(r'(?s)]* data-hid="jw-video-jw[^>]+>(.+?)', webpage): + settings = self._search_json(r'var\s+settings\s*=[^{]*', script, 'settings', page_id, fatal=False) + if entry := self._parse_jwplayer_data(settings, page_id): + yield entry + def _real_extract(self, url): page_id = self._match_id(url) webpage = self._download_webpage(url, page_id) - entries = [] - for player_element in re.findall( - r'(<[^>]+class="kalturaPlayer[^"]*"[^>]*>)', webpage): - player_params = extract_attributes(player_element) - if player_params.get('data-type') not in ('kaltura_singleArticle',): - self.report_warning('Unsupported player type') - continue - entry_id = player_params['data-id'] - entries.append(self.url_result( - 'kaltura:1750922:' + entry_id, 'Kaltura', entry_id)) - - return self.playlist_result(entries, page_id) + return self.playlist_result(self._entries(webpage, page_id), page_id) From 3ad0b7f422d547204df687b6d0b2d9110fff3990 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Tue, 24 Sep 2024 17:10:42 -0500 Subject: [PATCH 025/154] [ie/tiktok] Fix web formats extraction (#11074) Closes #11034 Authored by: bashonly --- yt_dlp/extractor/tiktok.py | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/yt_dlp/extractor/tiktok.py b/yt_dlp/extractor/tiktok.py index 9d823a315..f7e103fe9 100644 --- a/yt_dlp/extractor/tiktok.py +++ b/yt_dlp/extractor/tiktok.py @@ -542,16 +542,12 @@ class TikTokBaseIE(InfoExtractor): **COMMON_FORMAT_INFO, 'format_id': 'download', 'url': self._proto_relative_url(download_url), + 'format_note': 'watermarked', + 'preference': -2, }) self._remove_duplicate_formats(formats) - for f in traverse_obj(formats, lambda _, v: 'unwatermarked' not in v['url']): - f.update({ - 'format_note': join_nonempty(f.get('format_note'), 'watermarked', delim=', '), - 'preference': f.get('preference') or -2, - }) - # Is it a slideshow with only audio for download? if not formats and traverse_obj(aweme_detail, ('music', 'playUrl', {url_or_none})): audio_url = aweme_detail['music']['playUrl'] @@ -565,7 +561,8 @@ class TikTokBaseIE(InfoExtractor): 'vcodec': 'none', }) - return formats + # Filter out broken formats, see https://github.com/yt-dlp/yt-dlp/issues/11034 + return [f for f in formats if urllib.parse.urlparse(f['url']).hostname != 'www.tiktok.com'] def _parse_aweme_video_web(self, aweme_detail, webpage_url, video_id, extract_flat=False): author_info = traverse_obj(aweme_detail, (('authorInfo', 'author', None), { From fa2be9a7c63babede07480151363e54eee5702bd Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Tue, 24 Sep 2024 17:12:02 -0500 Subject: [PATCH 026/154] [ie/youtube] Fix `format_note` (Bugfix for 3a3bd00037e9908e87da4fa9f2ad772aa34dc60e) (#11028) Authored by: bashonly --- yt_dlp/extractor/youtube.py | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index 3d11c32f6..fc50dbc05 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -4110,7 +4110,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): self.report_warning( f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True) - client_name = fmt.get(STREAMING_DATA_CLIENT_NAME) + client_name = fmt[STREAMING_DATA_CLIENT_NAME] po_token = fmt.get(STREAMING_DATA_PO_TOKEN) if po_token: @@ -4135,7 +4135,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()), try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()), is_damaged and 'DAMAGED', is_broken and 'BROKEN', - (self.get_param('verbose') or all_formats) and client_name, + (self.get_param('verbose') or all_formats) and short_client_name(client_name), delim=', '), # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372 'source_preference': (-5 if itag == '22' else -1) + (100 if 'Premium' in name else 0), @@ -4234,7 +4234,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): if f['quality'] == -1 and f.get('height'): f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))]) if self.get_param('verbose') or all_formats: - f['format_note'] = join_nonempty(f.get('format_note'), client_name, delim=', ') + f['format_note'] = join_nonempty( + f.get('format_note'), short_client_name(client_name), delim=', ') if f.get('fps') and f['fps'] <= 1: del f['fps'] @@ -4245,7 +4246,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): subtitles = {} for sd in streaming_data: - client_name = sd.get(STREAMING_DATA_CLIENT_NAME) + client_name = sd[STREAMING_DATA_CLIENT_NAME] po_token = sd.get(STREAMING_DATA_PO_TOKEN) hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl') if hls_manifest_url: From 5bb1aa04dafce13ba9de707ea53169fab58b5207 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Wed, 25 Sep 2024 15:59:20 -0500 Subject: [PATCH 027/154] [networking] Pin `curl-cffi` version to < 0.7.2 (#11092) Ref: https://github.com/lexiforest/curl_cffi/issues/394 Authored by: bashonly --- pyproject.toml | 2 +- yt_dlp/networking/_curlcffi.py | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/pyproject.toml b/pyproject.toml index fe6894a42..86a8f0f7e 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -56,7 +56,7 @@ dependencies = [ default = [] curl-cffi = [ "curl-cffi==0.5.10; os_name=='nt' and implementation_name=='cpython'", - "curl-cffi>=0.5.10,!=0.6.*,<0.8; os_name!='nt' and implementation_name=='cpython'", + "curl-cffi>=0.5.10,!=0.6.*,<0.7.2; os_name!='nt' and implementation_name=='cpython'", ] secretstorage = [ "cffi", diff --git a/yt_dlp/networking/_curlcffi.py b/yt_dlp/networking/_curlcffi.py index e8a67b734..0643348e7 100644 --- a/yt_dlp/networking/_curlcffi.py +++ b/yt_dlp/networking/_curlcffi.py @@ -31,9 +31,9 @@ if curl_cffi is None: curl_cffi_version = tuple(map(int, re.split(r'[^\d]+', curl_cffi.__version__)[:3])) -if curl_cffi_version != (0, 5, 10) and not ((0, 7, 0) <= curl_cffi_version < (0, 8, 0)): +if curl_cffi_version != (0, 5, 10) and not ((0, 7, 0) <= curl_cffi_version < (0, 7, 2)): curl_cffi._yt_dlp__version = f'{curl_cffi.__version__} (unsupported)' - raise ImportError('Only curl_cffi versions 0.5.10, 0.7.X are supported') + raise ImportError('Only curl_cffi versions 0.5.10, 0.7.0 and 0.7.1 are supported') import curl_cffi.requests from curl_cffi.const import CurlECode, CurlOpt From b397a64691421ace5df09457c2a764821a2dc6f2 Mon Sep 17 00:00:00 2001 From: sepro Date: Wed, 25 Sep 2024 23:13:54 +0200 Subject: [PATCH 028/154] [cookies] Improve error message for Windows `--cookies-from-browser chrome` issue (#11090) Authored by: seproDev --- yt_dlp/cookies.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/yt_dlp/cookies.py b/yt_dlp/cookies.py index 070d2fcb9..cff8d74a7 100644 --- a/yt_dlp/cookies.py +++ b/yt_dlp/cookies.py @@ -1053,8 +1053,9 @@ def _decrypt_windows_dpapi(ciphertext, logger): ctypes.byref(blob_out), # pDataOut ) if not ret: - logger.warning('failed to decrypt with DPAPI', only_once=True) - return None + message = 'Failed to decrypt with DPAPI. See https://github.com/yt-dlp/yt-dlp/issues/10927 for more info' + logger.error(message) + raise DownloadError(message) # force exit result = ctypes.string_at(blob_out.pbData, blob_out.cbData) ctypes.windll.kernel32.LocalFree(blob_out.pbData) From fb8b7f226d251e521a89b23c415e249e5b788e5c Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Wed, 25 Sep 2024 18:07:17 -0500 Subject: [PATCH 029/154] [build] Bump PyInstaller version pin to `>=6.10.0` (#10709) Authored by: bashonly --- .github/workflows/build.yml | 4 ++-- pyproject.toml | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml index 4ff1cbc1d..bd2e42d9a 100644 --- a/.github/workflows/build.yml +++ b/.github/workflows/build.yml @@ -409,7 +409,7 @@ jobs: run: | # Custom pyinstaller built with https://github.com/yt-dlp/pyinstaller-builds python devscripts/install_deps.py -o --include build python devscripts/install_deps.py --include curl-cffi - python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/x86_64/pyinstaller-6.7.0-py3-none-any.whl" + python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/x86_64/pyinstaller-6.10.0-py3-none-any.whl" - name: Prepare run: | @@ -469,7 +469,7 @@ jobs: run: | python devscripts/install_deps.py -o --include build python devscripts/install_deps.py - python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/i686/pyinstaller-6.7.0-py3-none-any.whl" + python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/i686/pyinstaller-6.10.0-py3-none-any.whl" - name: Prepare run: | diff --git a/pyproject.toml b/pyproject.toml index 86a8f0f7e..18d9a0a3a 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -82,7 +82,7 @@ test = [ "pytest~=8.1", ] pyinstaller = [ - "pyinstaller>=6.7.0", # for compat with setuptools>=70 + "pyinstaller>=6.10.0", # Windows temp cleanup fixed in 6.10.0 ] py2exe = [ "py2exe>=0.12", From e2b3634e299be9c16a247ece3b1858d83889c324 Mon Sep 17 00:00:00 2001 From: szantnerb <2652078+szantnerb@users.noreply.github.com> Date: Thu, 26 Sep 2024 18:23:26 +0200 Subject: [PATCH 030/154] [ie/mediaklikk] Fix extractor (#11083) Closes #11061 Authored by: szantnerb --- yt_dlp/extractor/mediaklikk.py | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/yt_dlp/extractor/mediaklikk.py b/yt_dlp/extractor/mediaklikk.py index f51342060..197e91d1d 100644 --- a/yt_dlp/extractor/mediaklikk.py +++ b/yt_dlp/extractor/mediaklikk.py @@ -16,6 +16,15 @@ class MediaKlikkIE(InfoExtractor): (?P[^/#?_]+)''' _TESTS = [{ + 'url': 'https://mediaklikk.hu/filmajanlo/cikk/az-ajto/', + 'info_dict': { + 'id': '668177', + 'title': 'Az ajtó', + 'display_id': 'az-ajto', + 'ext': 'mp4', + 'thumbnail': 'https://cdn.cms.mtv.hu/wp-content/uploads/sites/4/2016/01/vlcsnap-2023-07-31-14h18m52s111.jpg', + }, + }, { # (old) mediaklikk. date in html. 'url': 'https://mediaklikk.hu/video/hazajaro-delnyugat-bacska-a-duna-menten-palankatol-doroszloig/', 'info_dict': { @@ -37,6 +46,7 @@ class MediaKlikkIE(InfoExtractor): 'upload_date': '20230903', 'thumbnail': 'https://mediaklikk.hu/wp-content/uploads/sites/4/2014/02/hazajarouj_JO.jpg', }, + 'skip': 'Webpage redirects to 404 page', }, { # (old) m4sport 'url': 'https://m4sport.hu/video/2021/08/30/gyemant-liga-parizs/', @@ -59,6 +69,7 @@ class MediaKlikkIE(InfoExtractor): 'upload_date': '20230908', 'thumbnail': 'https://m4sport.hu/wp-content/uploads/sites/4/2023/09/vlcsnap-2023-09-08-22h43m18s691.jpg', }, + 'skip': 'Webpage redirects to 404 page', }, { # m4sport with *video/ url and no date 'url': 'https://m4sport.hu/bl-video/real-madrid-chelsea-1-1/', @@ -69,6 +80,7 @@ class MediaKlikkIE(InfoExtractor): 'ext': 'mp4', 'thumbnail': 'https://m4sport.hu/wp-content/uploads/sites/4/2021/04/Sequence-01.Still001-1024x576.png', }, + 'skip': 'Webpage redirects to 404 page', }, { # (old) hirado 'url': 'https://hirado.hu/videok/felteteleket-szabott-a-fovaros/', @@ -90,6 +102,7 @@ class MediaKlikkIE(InfoExtractor): 'upload_date': '20230911', 'thumbnail': 'https://hirado.hu/wp-content/uploads/sites/4/2023/09/vlcsnap-2023-09-11-09h16m09s882.jpg', }, + 'skip': 'Webpage redirects to video list page', }, { # (old) petofilive 'url': 'https://petofilive.hu/video/2021/06/07/tha-shudras-az-akusztikban/', @@ -112,6 +125,7 @@ class MediaKlikkIE(InfoExtractor): 'upload_date': '20230909', 'thumbnail': 'https://petofilive.hu/wp-content/uploads/sites/4/2023/09/Clipboard11-2.jpg', }, + 'skip': 'Webpage redirects to video list page', }] def _real_extract(self, url): @@ -143,14 +157,14 @@ class MediaKlikkIE(InfoExtractor): if not playlist_url: raise ExtractorError('Unable to extract playlist url') - formats = self._extract_wowza_formats( - playlist_url, video_id, skip_protocols=['f4m', 'smil', 'dash']) + formats, subtitles = self._extract_m3u8_formats_and_subtitles(playlist_url, video_id) return { 'id': video_id, 'title': title, 'display_id': display_id, 'formats': formats, + 'subtitles': subtitles, 'upload_date': upload_date, 'thumbnail': player_data.get('bgImage') or self._og_search_thumbnail(webpage), } From 28b0ecba2af5b4919f198474b3d00a76ef322c31 Mon Sep 17 00:00:00 2001 From: Mozi <29089388+pzhlkj6612@users.noreply.github.com> Date: Fri, 27 Sep 2024 00:29:21 +0800 Subject: [PATCH 031/154] [ie/Mojevideo] Add extractor (#11019) Closes #8159 Authored by: 04-pasha-04, pzhlkj6612 Co-authored-by: pasha --- yt_dlp/extractor/_extractors.py | 1 + yt_dlp/extractor/mojevideo.py | 121 ++++++++++++++++++++++++++++++++ 2 files changed, 122 insertions(+) create mode 100644 yt_dlp/extractor/mojevideo.py diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index d8abf0b5d..42607e880 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -1166,6 +1166,7 @@ from .mlb import ( ) from .mlssoccer import MLSSoccerIE from .mocha import MochaVideoIE +from .mojevideo import MojevideoIE from .mojvideo import MojvideoIE from .monstercat import MonstercatIE from .motherless import ( diff --git a/yt_dlp/extractor/mojevideo.py b/yt_dlp/extractor/mojevideo.py new file mode 100644 index 000000000..145e30697 --- /dev/null +++ b/yt_dlp/extractor/mojevideo.py @@ -0,0 +1,121 @@ +from .common import InfoExtractor +from ..utils import js_to_json, remove_end, update_url_query + + +class MojevideoIE(InfoExtractor): + IE_DESC = 'mojevideo.sk' + _VALID_URL = r'https?://(?:www\.)?mojevideo\.sk/video/(?P\w+)/(?P[\w()]+?)\.html' + + _TESTS = [{ + 'url': 'https://www.mojevideo.sk/video/3d17c/chlapci_dobetonovali_sme_mame_hotovo.html', + 'md5': '384a4628bd2bbd261c5206cf77c38c17', + 'info_dict': { + 'id': '3d17c', + 'ext': 'mp4', + 'title': 'Chlapci dobetónovali sme, máme hotovo!', + 'display_id': 'chlapci_dobetonovali_sme_mame_hotovo', + 'description': 'md5:a0822126044050d304a9ef58c92ddb34', + 'thumbnail': 'https://fs5.mojevideo.sk/imgfb/250236.jpg', + 'duration': 21.0, + 'upload_date': '20230919', + 'timestamp': 1695129706, + 'like_count': int, + 'dislike_count': int, + 'view_count': int, + 'comment_count': int, + }, + }, { + # 720p + 'url': 'https://www.mojevideo.sk/video/14677/den_blbec.html', + 'md5': '517c3e111c53a67d10b429c1f344ba2f', + 'info_dict': { + 'id': '14677', + 'ext': 'mp4', + 'title': 'Deň blbec?', + 'display_id': 'den_blbec', + 'description': 'I maličkosť vám môže zmeniť celý deň. Nikdy nezahadzujte žuvačky na zem!', + 'thumbnail': 'https://fs5.mojevideo.sk/imgfb/83575.jpg', + 'duration': 100.0, + 'upload_date': '20120515', + 'timestamp': 1337076481, + 'like_count': int, + 'dislike_count': int, + 'view_count': int, + 'comment_count': int, + }, + }, { + # 1080p + 'url': 'https://www.mojevideo.sk/video/2feb2/band_maid_onset_(instrumental)_live_zepp_tokyo_(full_hd).html', + 'md5': '64599a23d3ac31cf2fe069e4353d8162', + 'info_dict': { + 'id': '2feb2', + 'ext': 'mp4', + 'title': 'BAND-MAID - onset (Instrumental) Live - Zepp Tokyo (Full HD)', + 'display_id': 'band_maid_onset_(instrumental)_live_zepp_tokyo_(full_hd)', + 'description': 'Výborná inštrumentálna skladba od skupiny BAND-MAID.', + 'thumbnail': 'https://fs5.mojevideo.sk/imgfb/196274.jpg', + 'duration': 240.0, + 'upload_date': '20190708', + 'timestamp': 1562576592, + 'like_count': int, + 'dislike_count': int, + 'view_count': int, + 'comment_count': int, + }, + }, { + # 720p + 'url': 'https://www.mojevideo.sk/video/358c8/dva_nissany_skyline_strielaju_v_londyne.html', + 'only_matching': True, + }, { + # 720p + 'url': 'https://www.mojevideo.sk/video/2455d/gopro_hero4_session_nova_sportova_vodotesna_kamera.html', + 'only_matching': True, + }, { + # 1080p + 'url': 'https://www.mojevideo.sk/video/352ee/amd_rx_6800_xt_vs_nvidia_rtx_3080_(test_v_9_hrach).html', + 'only_matching': True, + }, { + # 1080p + 'url': 'https://www.mojevideo.sk/video/2cbeb/trailer_z_avengers_infinity_war.html', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id, display_id = self._match_valid_url(url).groups() + webpage = self._download_webpage(url, video_id) + + video_id_dec = self._search_regex( + r'\bvId\s*=\s*(\d+)', webpage, 'video id', fatal=False) or str(int(video_id, 16)) + video_exp = self._search_regex(r'\bvEx\s*=\s*["\'](\d+)', webpage, 'video expiry') + video_hashes = self._search_json( + r'\bvHash\s*=', webpage, 'video hashes', video_id, + contains_pattern=r'\[(?s:.+)\]', transform_source=js_to_json) + + formats = [] + for video_hash, (suffix, quality, format_note) in zip(video_hashes, [ + ('', 1, 'normálna kvalita'), + ('_lq', 0, 'nízka kvalita'), + ('_hd', 2, 'HD-720p'), + ('_fhd', 3, 'FULL HD-1080p'), + ('_2k', 4, '2K-1440p'), + ]): + formats.append({ + 'format_id': f'mp4-{quality}', + 'quality': quality, + 'format_note': format_note, + 'url': update_url_query( + f'https://cache01.mojevideo.sk/securevideos69/{video_id_dec}{suffix}.mp4', { + 'md5': video_hash, + 'expires': video_exp, + }), + }) + + return { + 'id': video_id, + 'display_id': display_id, + 'formats': formats, + 'title': (self._og_search_title(webpage, default=None) + or remove_end(self._html_extract_title(webpage, 'title'), ' - Mojevideo')), + 'description': self._og_search_description(webpage), + **self._search_json_ld(webpage, video_id, default={}), + } From b37417e4f934fd8909788b493d017777155b0ae5 Mon Sep 17 00:00:00 2001 From: sepro Date: Thu, 26 Sep 2024 18:32:51 +0200 Subject: [PATCH 032/154] [ie/SnapchatSpotlight] Add extractor (#11030) Closes #1797 Authored by: seproDev --- yt_dlp/extractor/_extractors.py | 1 + yt_dlp/extractor/snapchat.py | 76 +++++++++++++++++++++++++++++++++ 2 files changed, 77 insertions(+) create mode 100644 yt_dlp/extractor/snapchat.py diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index 42607e880..fddfba81b 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -1880,6 +1880,7 @@ from .slideshare import SlideshareIE from .slideslive import SlidesLiveIE from .slutload import SlutloadIE from .smotrim import SmotrimIE +from .snapchat import SnapchatSpotlightIE from .snotr import SnotrIE from .sohu import ( SohuIE, diff --git a/yt_dlp/extractor/snapchat.py b/yt_dlp/extractor/snapchat.py new file mode 100644 index 000000000..732677c19 --- /dev/null +++ b/yt_dlp/extractor/snapchat.py @@ -0,0 +1,76 @@ +from .common import InfoExtractor +from ..utils import float_or_none, int_or_none, url_or_none +from ..utils.traversal import traverse_obj + + +class SnapchatSpotlightIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?snapchat\.com/spotlight/(?P\w+)' + + _TESTS = [{ + 'url': 'https://www.snapchat.com/spotlight/W7_EDlXWTBiXAEEniNoMPwAAYYWtidGhudGZpAX1TKn0JAX1TKnXJAAAAAA', + 'md5': '46c580f63592d0cbb76e974d2f9f0fcc', + 'info_dict': { + 'id': 'W7_EDlXWTBiXAEEniNoMPwAAYYWtidGhudGZpAX1TKn0JAX1TKnXJAAAAAA', + 'ext': 'mp4', + 'title': 'Views 💕', + 'description': '', + 'thumbnail': r're:https://cf-st\.sc-cdn\.net/d/kKJHIR1QAznRKK9jgYYDq\.256\.IRZXSOY', + 'duration': 4.665, + 'timestamp': 1637777831.369, + 'upload_date': '20211124', + 'repost_count': int, + 'uploader': 'shreypatel57', + 'uploader_url': 'https://www.snapchat.com/add/shreypatel57', + }, + }, { + 'url': 'https://www.snapchat.com/spotlight/W7_EDlXWTBiXAEEniNoMPwAAYcnVjYWdwcGV1AZEaIYn5AZEaIYnrAAAAAQ', + 'md5': '4cd9626458c1a0e3e6dbe72c544a9ec2', + 'info_dict': { + 'id': 'W7_EDlXWTBiXAEEniNoMPwAAYcnVjYWdwcGV1AZEaIYn5AZEaIYnrAAAAAQ', + 'ext': 'mp4', + 'title': 'Spotlight Snap', + 'description': 'How he flirt her teacher🤭🤭🤩😍 #kdrama#cdrama #dramaclips #dramaspotlight', + 'thumbnail': r're:https://cf-st\.sc-cdn\.net/i/ztfr6xFs0FOcFhwVczWfj\.256\.IRZXSOY', + 'duration': 10.91, + 'timestamp': 1722720291.307, + 'upload_date': '20240803', + 'view_count': int, + 'repost_count': int, + 'uploader': 'ganda0535', + 'uploader_url': 'https://www.snapchat.com/add/ganda0535', + 'tags': ['#dramaspotlight', '#dramaclips', '#cdrama', '#kdrama'], + }, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + page_props = self._search_nextjs_data(webpage, video_id)['props']['pageProps'] + video_data = traverse_obj(page_props, ( + 'spotlightFeed', 'spotlightStories', + lambda _, v: v['story']['storyId']['value'] == video_id, 'metadata', any), None) + + return { + 'id': video_id, + 'ext': 'mp4', + **traverse_obj(video_data, ('videoMetadata', { + 'title': ('name', {str}), + 'description': ('description', {str}), + 'timestamp': ('uploadDateMs', {lambda x: float_or_none(x, 1000)}), + 'view_count': ('viewCount', {int_or_none}, {lambda x: None if x == -1 else x}), + 'repost_count': ('shareCount', {int_or_none}), + 'url': ('contentUrl', {url_or_none}), + 'width': ('width', {int_or_none}), + 'height': ('height', {int_or_none}), + 'duration': ('durationMs', {lambda x: float_or_none(x, 1000)}), + 'thumbnail': ('thumbnailUrl', {url_or_none}), + 'uploader': ('creator', 'personCreator', 'username', {str}), + 'uploader_url': ('creator', 'personCreator', 'url', {url_or_none}), + })), + **traverse_obj(video_data, { + 'description': ('description', {str}), + 'tags': ('hashtags', ..., {str}), + 'view_count': ('engagementStats', 'viewCount', {int_or_none}, {lambda x: None if x == -1 else x}), + 'repost_count': ('engagementStats', 'shareCount', {int_or_none}), + }), + } From 416686ed0cf792ec44ab059f3b229dd776077e14 Mon Sep 17 00:00:00 2001 From: sepro Date: Thu, 26 Sep 2024 18:35:19 +0200 Subject: [PATCH 033/154] [ie/ertgr] Fix video extraction (#11091) Closes #8955 Authored by: seproDev --- yt_dlp/extractor/ertgr.py | 44 +++++++++++++++++++-------------------- 1 file changed, 22 insertions(+), 22 deletions(-) diff --git a/yt_dlp/extractor/ertgr.py b/yt_dlp/extractor/ertgr.py index 864aa6dc5..6f3f60ff4 100644 --- a/yt_dlp/extractor/ertgr.py +++ b/yt_dlp/extractor/ertgr.py @@ -17,6 +17,7 @@ from ..utils import ( url_or_none, variadic, ) +from ..utils.traversal import traverse_obj class ERTFlixBaseIE(InfoExtractor): @@ -74,29 +75,28 @@ class ERTFlixCodenameIE(ERTFlixBaseIE): def _extract_formats_and_subs(self, video_id): media_info = self._call_api(video_id, codename=video_id) - formats, subs = [], {} - for media_file in try_get(media_info, lambda x: x['MediaFiles'], list) or []: - for media in try_get(media_file, lambda x: x['Formats'], list) or []: - fmt_url = url_or_none(try_get(media, lambda x: x['Url'])) - if not fmt_url: - continue - ext = determine_ext(fmt_url) - if ext == 'm3u8': - formats_, subs_ = self._extract_m3u8_formats_and_subtitles( - fmt_url, video_id, m3u8_id='hls', ext='mp4', fatal=False) - elif ext == 'mpd': - formats_, subs_ = self._extract_mpd_formats_and_subtitles( - fmt_url, video_id, mpd_id='dash', fatal=False) - else: - formats.append({ - 'url': fmt_url, - 'format_id': str_or_none(media.get('Id')), - }) - continue - formats.extend(formats_) - self._merge_subtitles(subs_, target=subs) + formats, subtitles = [], {} + for media in traverse_obj(media_info, ( + 'MediaFiles', lambda _, v: v['RoleCodename'] == 'main', + 'Formats', lambda _, v: url_or_none(v['Url']))): + fmt_url = media['Url'] + ext = determine_ext(fmt_url) + if ext == 'm3u8': + fmts, subs = self._extract_m3u8_formats_and_subtitles( + fmt_url, video_id, m3u8_id='hls', ext='mp4', fatal=False) + elif ext == 'mpd': + fmts, subs = self._extract_mpd_formats_and_subtitles( + fmt_url, video_id, mpd_id='dash', fatal=False) + else: + formats.append({ + 'url': fmt_url, + 'format_id': str_or_none(media.get('Id')), + }) + continue + formats.extend(fmts) + self._merge_subtitles(subs, target=subtitles) - return formats, subs + return formats, subtitles def _real_extract(self, url): video_id = self._match_id(url) From 124f058b546d652a359c67025bb479789bfbef0b Mon Sep 17 00:00:00 2001 From: N/Ame <173015200+grqz@users.noreply.github.com> Date: Fri, 27 Sep 2024 04:39:48 +1200 Subject: [PATCH 034/154] [ie/Germanupa] Add extractor (#10538) Closes #10527 Authored by: grqz --- yt_dlp/extractor/_extractors.py | 1 + yt_dlp/extractor/germanupa.py | 91 +++++++++++++++++++++++++++++++++ 2 files changed, 92 insertions(+) create mode 100644 yt_dlp/extractor/germanupa.py diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index fddfba81b..4b1f4c316 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -730,6 +730,7 @@ from .genius import ( GeniusIE, GeniusLyricsIE, ) +from .germanupa import GermanupaIE from .getcourseru import ( GetCourseRuIE, GetCourseRuPlayerIE, diff --git a/yt_dlp/extractor/germanupa.py b/yt_dlp/extractor/germanupa.py new file mode 100644 index 000000000..e40f016b2 --- /dev/null +++ b/yt_dlp/extractor/germanupa.py @@ -0,0 +1,91 @@ +from .common import InfoExtractor +from .vimeo import VimeoIE +from ..utils import ( + parse_qs, + traverse_obj, + url_or_none, +) + + +class GermanupaIE(InfoExtractor): + IE_DESC = 'germanupa.de' + _VALID_URL = r'https?://germanupa\.de/mediathek/(?P[\w-]+)' + _TESTS = [{ + 'url': 'https://germanupa.de/mediathek/4-figma-beratung-deine-sprechstunde-fuer-figma-fragen', + 'info_dict': { + 'id': '909179246', + 'title': 'Tutorial: #4 Figma Beratung - Deine Sprechstunde für Figma-Fragen', + 'ext': 'mp4', + 'uploader': 'German UPA', + 'uploader_id': 'germanupa', + 'thumbnail': 'https://i.vimeocdn.com/video/1792564420-7415283ccef8bf8702dab8c6b7515555ceeb7a1c11371ffcc133b8e887dbf70e-d_1280', + 'uploader_url': 'https://vimeo.com/germanupa', + 'duration': 3987, + }, + 'expected_warnings': ['Failed to parse XML: not well-formed'], + 'params': {'skip_download': 'm3u8'}, + }, { + 'note': 'audio, uses GenericIE', + 'url': 'https://germanupa.de/mediathek/live-vom-ux-festival-neuigkeiten-von-figma-jobmarkt-agenturszene-interview-zu-sustainable', + 'info_dict': { + 'id': '1867346676', + 'title': 'Live vom UX Festival: Neuigkeiten von Figma, Jobmarkt, Agenturszene & Interview zu Sustainable UX', + 'ext': 'opus', + 'timestamp': 1720545088, + 'upload_date': '20240709', + 'duration': 3910.557, + 'like_count': int, + 'description': 'md5:db2aed5ff131e177a7b33901e9a8db05', + 'uploader': 'German UPA', + 'repost_count': int, + 'genres': ['Science'], + 'license': 'all-rights-reserved', + 'uploader_url': 'https://soundcloud.com/user-80097677', + 'uploader_id': '471579486', + 'view_count': int, + 'comment_count': int, + 'thumbnail': 'https://i1.sndcdn.com/artworks-oCti2e9GhaZFWBqY-48ybGw-original.jpg', + }, + }, { + 'note': 'Nur für Mitglieder/Just for members', + 'url': 'https://germanupa.de/mediathek/ux-festival-2024-usability-tests-und-ai', + 'info_dict': { + 'id': '986994430', + 'title': 'UX Festival 2024 "Usability Tests und AI" von Lennart Weber', + 'ext': 'mp4', + 'release_date': '20240719', + 'uploader_url': 'https://vimeo.com/germanupa', + 'timestamp': 1721373980, + 'license': 'by-sa', + 'like_count': int, + 'thumbnail': 'https://i.vimeocdn.com/video/1904187064-2a672630c30f9ad787bd390bff3f51d7506a3e8416763ba6dbf465732b165c5c-d_1280', + 'duration': 2146, + 'release_timestamp': 1721373980, + 'uploader': 'German UPA', + 'uploader_id': 'germanupa', + 'upload_date': '20240719', + 'comment_count': int, + }, + 'expected_warnings': ['Failed to parse XML: not well-formed'], + 'skip': 'login required', + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + param_url = traverse_obj( + self._search_regex( + r']+data-src\s*?=\s*?([\'"])(?Phttps://germanupa\.de/media/oembed\?url=(?:(?!\1).)+)\1', + webpage, 'embedded video', default=None, group='url'), + ({parse_qs}, 'url', 0, {url_or_none})) + + if not param_url: + if self._search_regex( + r']+class\s*?=\s*?([\'"])(?:(?!\1).)*login-wrapper(?:(?!\1).)*\1', + webpage, 'login wrapper', default=None): + self.raise_login_required('This video is only available for members') + return self.url_result(url, 'Generic') # Fall back to generic to extract audio + + real_url = param_url.replace('https://vimeo.com/', 'https://player.vimeo.com/video/') + return self.url_result(VimeoIE._smuggle_referrer(real_url, url), VimeoIE, video_id) From ad0b857f459a6d390fbf124183916218c52f223a Mon Sep 17 00:00:00 2001 From: tony-hn <25278435+tony-hn@users.noreply.github.com> Date: Thu, 26 Sep 2024 17:53:52 +0100 Subject: [PATCH 035/154] [ie/RumbleChannel] Fix extractor (#11049) Closes #10833 Authored by: tony-hn --- yt_dlp/extractor/rumble.py | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/yt_dlp/extractor/rumble.py b/yt_dlp/extractor/rumble.py index db780a2cf..74c7e4f17 100644 --- a/yt_dlp/extractor/rumble.py +++ b/yt_dlp/extractor/rumble.py @@ -8,14 +8,17 @@ from ..utils import ( UnsupportedError, clean_html, determine_ext, + extract_attributes, format_field, get_element_by_class, + get_elements_html_by_class, int_or_none, join_nonempty, parse_count, parse_iso8601, traverse_obj, unescapeHTML, + urljoin, ) @@ -382,8 +385,10 @@ class RumbleChannelIE(InfoExtractor): if isinstance(e.cause, HTTPError) and e.cause.status == 404: break raise - for video_url in re.findall(r'class="[^>"]*videostream__link[^>]+href="([^"]+\.html)"', webpage): - yield self.url_result('https://rumble.com' + video_url) + for video_url in traverse_obj( + get_elements_html_by_class('videostream__link', webpage), (..., {extract_attributes}, 'href'), + ): + yield self.url_result(urljoin('https://rumble.com', video_url)) def _real_extract(self, url): url, playlist_id = self._match_valid_url(url).groups() From 5a8a05aebb49693e78e1123015837ed5e961ff76 Mon Sep 17 00:00:00 2001 From: diman8 Date: Thu, 26 Sep 2024 18:57:00 +0200 Subject: [PATCH 036/154] [ie/SVTPage] Fix extractor (#11010) Authored by: diman8 --- yt_dlp/extractor/svt.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/yt_dlp/extractor/svt.py b/yt_dlp/extractor/svt.py index 38782abac..b5df2e1a1 100644 --- a/yt_dlp/extractor/svt.py +++ b/yt_dlp/extractor/svt.py @@ -472,7 +472,7 @@ class SVTPageIE(SVTBaseIE): title = self._og_search_title(webpage) urql_state = self._search_json( - r'window\.svt\.nyh\.urqlState\s*=', webpage, 'json data', display_id) + r'window\.svt\.(?:nyh\.)?urqlState\s*=', webpage, 'json data', display_id) data = traverse_obj(urql_state, (..., 'data', {str}, {json.loads}), get_all=False) or {} From a2000bc85730c950351d78bb818493dc39dca3cb Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Thu, 26 Sep 2024 18:20:14 -0500 Subject: [PATCH 037/154] [ie/bilibili] Fix chapters and subtitles extraction (#11099) Closes #11089 Authored by: bashonly --- yt_dlp/extractor/bilibili.py | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/yt_dlp/extractor/bilibili.py b/yt_dlp/extractor/bilibili.py index 2fe1103cb..62f68fbc6 100644 --- a/yt_dlp/extractor/bilibili.py +++ b/yt_dlp/extractor/bilibili.py @@ -46,6 +46,7 @@ from ..utils import ( class BilibiliBaseIE(InfoExtractor): + _HEADERS = {'Referer': 'https://www.bilibili.com/'} _FORMAT_ID_RE = re.compile(r'-(\d+)\.m4s\?') _WBI_KEY_CACHE_TIMEOUT = 30 # exact expire timeout is unclear, use 30s for one session _wbi_key_cache = {} @@ -192,7 +193,7 @@ class BilibiliBaseIE(InfoExtractor): video_info = self._download_json( 'https://api.bilibili.com/x/player/v2', video_id, query={'aid': aid, 'cid': cid} if aid else {'bvid': video_id, 'cid': cid}, - note=f'Extracting subtitle info {cid}') + note=f'Extracting subtitle info {cid}', headers=self._HEADERS) if traverse_obj(video_info, ('data', 'need_login_subtitle')): self.report_warning( f'Subtitles are only available when logged in. {self._login_hint()}', only_once=True) @@ -207,7 +208,7 @@ class BilibiliBaseIE(InfoExtractor): def _get_chapters(self, aid, cid): chapters = aid and cid and self._download_json( 'https://api.bilibili.com/x/player/v2', aid, query={'aid': aid, 'cid': cid}, - note='Extracting chapters', fatal=False) + note='Extracting chapters', fatal=False, headers=self._HEADERS) return traverse_obj(chapters, ('data', 'view_points', ..., { 'title': 'content', 'start_time': 'from', @@ -1021,8 +1022,6 @@ class BiliBiliBangumiSeasonIE(BilibiliBaseIE): class BilibiliCheeseBaseIE(BilibiliBaseIE): - _HEADERS = {'Referer': 'https://www.bilibili.com/'} - def _extract_episode(self, season_info, ep_id): episode_info = traverse_obj(season_info, ( 'episodes', lambda _, v: v['id'] == int(ep_id)), get_all=False) From 9f5c9a90898c5a1e672922d9cd799716c73cee34 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Thu, 26 Sep 2024 18:21:03 -0500 Subject: [PATCH 038/154] [ie/wistia] Support password-protected videos (#11100) Closes #10914 Authored by: bashonly --- yt_dlp/extractor/wistia.py | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/yt_dlp/extractor/wistia.py b/yt_dlp/extractor/wistia.py index fb2a8648f..df7ecb3cd 100644 --- a/yt_dlp/extractor/wistia.py +++ b/yt_dlp/extractor/wistia.py @@ -8,6 +8,7 @@ from ..networking.exceptions import HTTPError from ..utils import ( ExtractorError, determine_ext, + filter_dict, float_or_none, int_or_none, parse_qs, @@ -25,16 +26,25 @@ class WistiaBaseIE(InfoExtractor): def _download_embed_config(self, config_type, config_id, referer): base_url = self._EMBED_BASE_URL + f'{config_type}/{config_id}' + video_password = self.get_param('videopassword') embed_config = self._download_json( base_url + '.json', config_id, headers={ 'Referer': referer if referer.startswith('http') else base_url, # Some videos require this. - }) + }, query=filter_dict({'password': video_password})) error = traverse_obj(embed_config, 'error') if error: raise ExtractorError( f'Error while getting the playlist: {error}', expected=True) + if traverse_obj(embed_config, ( + 'media', ('embed_options', 'embedOptions'), 'plugin', + 'passwordProtectedVideo', 'on', any)) == 'true': + if video_password: + raise ExtractorError('Invalid video password', expected=True) + raise ExtractorError( + 'This content is password-protected. Use the --video-password option', expected=True) + return embed_config def _get_real_ext(self, url): From 1d84b780cf33a1d84756825ac23f990a905703df Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Thu, 26 Sep 2024 18:26:10 -0500 Subject: [PATCH 039/154] [ie/youtube:clip] Prioritize `https` formats (#11102) Closes #10856 Authored by: bashonly --- yt_dlp/extractor/youtube.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index fc50dbc05..1382c01b6 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -7655,6 +7655,8 @@ class YoutubeClipIE(YoutubeTabBaseInfoExtractor): 'id': clip_id, 'section_start': int(clip_data['startTimeMs']) / 1000, 'section_end': int(clip_data['endTimeMs']) / 1000, + '_format_sort_fields': ( # https protocol is prioritized for ffmpeg compatibility + 'proto:https', 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang'), } From eabb4680fdb09ba1f48d174a700a2e3b43f82add Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Thu, 26 Sep 2024 18:27:16 -0500 Subject: [PATCH 040/154] [ie/niconico] Fix m3u8 formats extraction (#11103) Closes #10724 Authored by: bashonly --- yt_dlp/extractor/niconico.py | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/yt_dlp/extractor/niconico.py b/yt_dlp/extractor/niconico.py index 179e7a9b1..e06740d62 100644 --- a/yt_dlp/extractor/niconico.py +++ b/yt_dlp/extractor/niconico.py @@ -420,7 +420,7 @@ class NiconicoIE(InfoExtractor): 'x-request-with': 'https://www.nicovideo.jp', })['data']['contentUrl'] # Getting all audio formats results in duplicate video formats which we filter out later - dms_fmts = self._extract_m3u8_formats(dms_m3u8_url, video_id) + dms_fmts = self._extract_m3u8_formats(dms_m3u8_url, video_id, 'mp4') # m3u8 extraction does not provide audio bitrates, so extract from the API data and fix for audio_fmt in traverse_obj(dms_fmts, lambda _, v: v['vcodec'] == 'none'): @@ -432,7 +432,6 @@ class NiconicoIE(InfoExtractor): 'asr': ('samplingRate', {int_or_none}), }), get_all=False), 'acodec': 'aac', - 'ext': 'm4a', } # Sort before removing dupes to keep the format dicts with the lowest tbr From 7f909046f4dc0fba472b4963145aef6e0d42491b Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Fri, 27 Sep 2024 11:37:16 -0500 Subject: [PATCH 041/154] [ie/abc.net.au:iview:showseries] Fix extraction (#11101) Closes #10475 Authored by: bashonly --- yt_dlp/extractor/abc.py | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) diff --git a/yt_dlp/extractor/abc.py b/yt_dlp/extractor/abc.py index 7518ba6f0..7296be73b 100644 --- a/yt_dlp/extractor/abc.py +++ b/yt_dlp/extractor/abc.py @@ -387,17 +387,27 @@ class ABCIViewShowSeriesIE(InfoExtractor): 'thumbnail': r're:^https?://cdn\.iview\.abc\.net\.au/thumbs/.*\.jpg$', }, 'playlist_count': 15, + 'skip': 'This program is not currently available in ABC iview', + }, { + 'url': 'https://iview.abc.net.au/show/inbestigators', + 'info_dict': { + 'id': '175343-1', + 'title': 'Series 1', + 'description': 'md5:b9976935a6450e5b78ce2a940a755685', + 'series': 'The Inbestigators', + 'season': 'Series 1', + 'thumbnail': r're:^https?://cdn\.iview\.abc\.net\.au/thumbs/.+\.jpg', + }, + 'playlist_count': 17, }] def _real_extract(self, url): show_id = self._match_id(url) webpage = self._download_webpage(url, show_id) - webpage_data = self._search_regex( - r'window\.__INITIAL_STATE__\s*=\s*[\'"](.+?)[\'"]\s*;', - webpage, 'initial state') - video_data = self._parse_json( - unescapeHTML(webpage_data).encode().decode('unicode_escape'), show_id) - video_data = video_data['route']['pageData']['_embedded'] + video_data = self._search_json( + r'window\.__INITIAL_STATE__\s*=\s*[\'"]', webpage, 'initial state', show_id, + transform_source=lambda x: x.encode().decode('unicode_escape'), + end_pattern=r'[\'"]\s*;')['route']['pageData']['_embedded'] highlight = try_get(video_data, lambda x: x['highlightVideo']['shareUrl']) if not self._yes_playlist(show_id, bool(highlight), video_label='highlight video'): From 48d629d461e05b1b19f5e53dc959bb9ebe95da42 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Fri, 27 Sep 2024 11:38:08 -0500 Subject: [PATCH 042/154] [ie/YleAreena] Support podcasts (#11104) Closes #10840 Authored by: bashonly --- yt_dlp/extractor/yle_areena.py | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/yt_dlp/extractor/yle_areena.py b/yt_dlp/extractor/yle_areena.py index ef9e96804..c0a218e2f 100644 --- a/yt_dlp/extractor/yle_areena.py +++ b/yt_dlp/extractor/yle_areena.py @@ -10,7 +10,7 @@ from ..utils import ( class YleAreenaIE(InfoExtractor): - _VALID_URL = r'https?://areena\.yle\.fi/(?P[\d-]+)' + _VALID_URL = r'https?://areena\.yle\.fi/(?Ppodcastit/)?(?P[\d-]+)' _GEO_COUNTRIES = ['FI'] _TESTS = [ { @@ -77,7 +77,7 @@ class YleAreenaIE(InfoExtractor): ] def _real_extract(self, url): - video_id = self._match_id(url) + video_id, is_podcast = self._match_valid_url(url).group('id', 'podcast') info = self._search_json_ld(self._download_webpage(url, video_id), video_id, default={}) video_data = self._download_json( f'https://player.api.yle.fi/v1/preview/{video_id}.json?app_id=player_static_prod&app_key=8930d72170e48303cf5f3867780d549b', @@ -103,8 +103,11 @@ class YleAreenaIE(InfoExtractor): 'name': sub.get('kind'), }) - kaltura_id = traverse_obj(video_data, ('data', 'ongoing_ondemand', 'kaltura', 'id'), expected_type=str) - if kaltura_id: + if is_podcast: + info_dict = { + 'url': video_data['data']['ongoing_ondemand']['media_url'], + } + elif kaltura_id := traverse_obj(video_data, ('data', 'ongoing_ondemand', 'kaltura', 'id', {str})): info_dict = { '_type': 'url_transparent', 'url': smuggle_url(f'kaltura:1955031:{kaltura_id}', {'source_url': url}), @@ -114,13 +117,11 @@ class YleAreenaIE(InfoExtractor): formats, subs = self._extract_m3u8_formats_and_subtitles( video_data['data']['ongoing_ondemand']['manifest_url'], video_id, 'mp4', m3u8_id='hls') self._merge_subtitles(subs, target=subtitles) - info_dict = { - 'id': video_id, - 'formats': formats, - } + info_dict = {'formats': formats} return { **info_dict, + 'id': video_id, 'title': (traverse_obj(video_data, ('data', 'ongoing_ondemand', 'title', 'fin'), expected_type=str) or episode or info.get('title')), 'description': description, From 0aa4426e9a35f7f8e184f1f2082b3b313c1448f7 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Fri, 27 Sep 2024 11:38:40 -0500 Subject: [PATCH 043/154] [ie/kick:clips] Support new URL format (#11107) Closes #11105 Authored by: bashonly --- yt_dlp/extractor/kick.py | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/yt_dlp/extractor/kick.py b/yt_dlp/extractor/kick.py index abea5280b..bd21e5950 100644 --- a/yt_dlp/extractor/kick.py +++ b/yt_dlp/extractor/kick.py @@ -148,7 +148,7 @@ class KickVODIE(KickBaseIE): class KickClipIE(KickBaseIE): IE_NAME = 'kick:clips' - _VALID_URL = r'https?://(?:www\.)?kick\.com/[\w-]+/?\?(?:[^#]+&)?clip=(?Pclip_[\w-]+)' + _VALID_URL = r'https?://(?:www\.)?kick\.com/[\w-]+(?:/clips/|/?\?(?:[^#]+&)?clip=)(?Pclip_[\w-]+)' _TESTS = [{ 'url': 'https://kick.com/mxddy?clip=clip_01GYXVB5Y8PWAPWCWMSBCFB05X', 'info_dict': { @@ -189,6 +189,26 @@ class KickClipIE(KickBaseIE): 'age_limit': 0, }, 'params': {'skip_download': 'm3u8'}, + }, { + 'url': 'https://kick.com/spreen/clips/clip_01J8RGZRKHXHXXKJEHGRM932A5', + 'info_dict': { + 'id': 'clip_01J8RGZRKHXHXXKJEHGRM932A5', + 'ext': 'mp4', + 'title': 'KLJASLDJKLJKASDLJKDAS', + 'channel': 'spreen', + 'channel_id': '5312671', + 'uploader': 'AnormalBarraBaja', + 'uploader_id': '26518262', + 'duration': 43.0, + 'upload_date': '20240927', + 'timestamp': 1727399987, + 'thumbnail': 'https://clips.kick.com/clips/f2/clip_01J8RGZRKHXHXXKJEHGRM932A5/thumbnail.webp', + 'view_count': int, + 'like_count': int, + 'categories': ['Minecraft'], + 'age_limit': 0, + }, + 'params': {'skip_download': 'm3u8'}, }] def _real_extract(self, url): From c08e0b20b5edd8957b8318716bc14e896d1b96f4 Mon Sep 17 00:00:00 2001 From: Kieran Date: Fri, 27 Sep 2024 13:52:41 -0700 Subject: [PATCH 044/154] Allow `none` arg to negate `--convert-subs` and `--convert-thumbnails` (#11066) Authored by: kieraneglin --- README.md | 10 +++++++--- yt_dlp/__init__.py | 5 +++++ yt_dlp/options.py | 8 +++++--- 3 files changed, 17 insertions(+), 6 deletions(-) diff --git a/README.md b/README.md index 428eb9f47..1d6a4a86d 100644 --- a/README.md +++ b/README.md @@ -999,12 +999,16 @@ If you fork the project on GitHub, you can run your fork's [build workflow](.git be used multiple times --no-exec Remove any previously defined --exec --convert-subs FORMAT Convert the subtitles to another format - (currently supported: ass, lrc, srt, vtt) - (Alias: --convert-subtitles) + (currently supported: ass, lrc, srt, vtt). + Use "--convert-subs none" to disable + conversion (default) (Alias: --convert- + subtitles) --convert-thumbnails FORMAT Convert the thumbnails to another format (currently supported: jpg, png, webp). You can specify multiple rules using similar - syntax as --remux-video + syntax as "--remux-video". Use "--convert- + thumbnails none" to disable conversion + (default) --split-chapters Split video into multiple files based on internal chapters. The "chapter:" prefix can be used with "--paths" and "--output" to set diff --git a/yt_dlp/__init__.py b/yt_dlp/__init__.py index c0b8e3b50..c2d19f94a 100644 --- a/yt_dlp/__init__.py +++ b/yt_dlp/__init__.py @@ -235,6 +235,11 @@ def validate_options(opts): validate_regex('format sorting', f, FormatSorter.regex) # Postprocessor formats + if opts.convertsubtitles == 'none': + opts.convertsubtitles = None + if opts.convertthumbnails == 'none': + opts.convertthumbnails = None + validate_regex('merge output format', opts.merge_output_format, r'({0})(/({0}))*'.format('|'.join(map(re.escape, FFmpegMergerPP.SUPPORTED_EXTS)))) validate_regex('audio format', opts.audioformat, FFmpegExtractAudioPP.FORMAT_RE) diff --git a/yt_dlp/options.py b/yt_dlp/options.py index ffe2463fe..8077d5d88 100644 --- a/yt_dlp/options.py +++ b/yt_dlp/options.py @@ -1725,15 +1725,17 @@ def create_parser(): '--convert-subs', '--convert-sub', '--convert-subtitles', metavar='FORMAT', dest='convertsubtitles', default=None, help=( - 'Convert the subtitles to another format (currently supported: {}) ' - '(Alias: --convert-subtitles)'.format(', '.join(sorted(FFmpegSubtitlesConvertorPP.SUPPORTED_EXTS))))) + 'Convert the subtitles to another format ' + f'(currently supported: {", ".join(sorted(FFmpegSubtitlesConvertorPP.SUPPORTED_EXTS))}). ' + 'Use "--convert-subs none" to disable conversion (default) (Alias: --convert-subtitles)')) postproc.add_option( '--convert-thumbnails', metavar='FORMAT', dest='convertthumbnails', default=None, help=( 'Convert the thumbnails to another format ' f'(currently supported: {", ".join(sorted(FFmpegThumbnailsConvertorPP.SUPPORTED_EXTS))}). ' - 'You can specify multiple rules using similar syntax as --remux-video')) + 'You can specify multiple rules using similar syntax as "--remux-video". ' + 'Use "--convert-thumbnails none" to disable conversion (default)')) postproc.add_option( '--split-chapters', '--split-tracks', dest='split_chapters', action='store_true', default=False, From a1b4ac2b8ed8e6eaa56044d439f1e0d00c2ba218 Mon Sep 17 00:00:00 2001 From: fireattack Date: Sat, 28 Sep 2024 04:57:57 +0800 Subject: [PATCH 045/154] [ie/vimeo] Fix HLS audio format sorting (#11082) Closes #10854 Authored by: fireattack --- yt_dlp/extractor/vimeo.py | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/yt_dlp/extractor/vimeo.py b/yt_dlp/extractor/vimeo.py index 9a03948cd..367d5e583 100644 --- a/yt_dlp/extractor/vimeo.py +++ b/yt_dlp/extractor/vimeo.py @@ -21,6 +21,7 @@ from ..utils import ( parse_filesize, parse_iso8601, parse_qs, + qualities, smuggle_url, str_or_none, traverse_obj, @@ -146,6 +147,8 @@ class VimeoBaseInfoExtractor(InfoExtractor): }) # TODO: fix handling of 308 status code returned for live archive manifest requests + QUALITIES = ('low', 'medium', 'high') + quality = qualities(QUALITIES) sep_pattern = r'/sep/video/' for files_type in ('hls', 'dash'): for cdn_name, cdn_data in (try_get(config_files, lambda x: x[files_type]['cdns']) or {}).items(): @@ -166,6 +169,11 @@ class VimeoBaseInfoExtractor(InfoExtractor): m_url, video_id, 'mp4', live=is_live, m3u8_id=f_id, note=f'Downloading {cdn_name} m3u8 information', fatal=False) + # m3u8 doesn't give audio bitrates; need to prioritize based on GROUP-ID + # See: https://github.com/yt-dlp/yt-dlp/issues/10854 + for f in fmts: + if mobj := re.search(rf'audio-({"|".join(QUALITIES)})', f['format_id']): + f['quality'] = quality(mobj.group(1)) formats.extend(fmts) self._merge_subtitles(subs, target=subtitles) elif files_type == 'dash': From 8f4ea14680c7865d8ffac10a9174205d1d84ada7 Mon Sep 17 00:00:00 2001 From: rakslice Date: Fri, 27 Sep 2024 14:32:39 -0700 Subject: [PATCH 046/154] Fix format sorting bug with vp9.2 vcodec (#10884) Authored by: rakslice --- test/test_YoutubeDL.py | 29 +++++++++++++++++++++++++++++ test/test_utils.py | 5 +++++ yt_dlp/utils/_utils.py | 2 +- 3 files changed, 35 insertions(+), 1 deletion(-) diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py index 1847c4ffd..a99e62408 100644 --- a/test/test_YoutubeDL.py +++ b/test/test_YoutubeDL.py @@ -236,6 +236,35 @@ class TestFormatSelection(unittest.TestCase): downloaded = ydl.downloaded_info_dicts[0] self.assertEqual(downloaded['format_id'], 'vid-vcodec-dot') + def test_format_selection_by_vcodec_sort(self): + formats = [ + {'format_id': 'av1-format', 'ext': 'mp4', 'vcodec': 'av1', 'acodec': 'none', 'url': TEST_URL}, + {'format_id': 'vp9-hdr-format', 'ext': 'mp4', 'vcodec': 'vp09.02.50.10.01.09.18.09.00', 'acodec': 'none', 'url': TEST_URL}, + {'format_id': 'vp9-sdr-format', 'ext': 'mp4', 'vcodec': 'vp09.00.50.08', 'acodec': 'none', 'url': TEST_URL}, + {'format_id': 'h265-format', 'ext': 'mp4', 'vcodec': 'h265', 'acodec': 'none', 'url': TEST_URL}, + ] + info_dict = _make_result(formats) + + ydl = YDL({'format': 'bestvideo', 'format_sort': ['vcodec:vp9.2']}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'vp9-hdr-format') + + ydl = YDL({'format': 'bestvideo', 'format_sort': ['vcodec:vp9']}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'vp9-sdr-format') + + ydl = YDL({'format': 'bestvideo', 'format_sort': ['+vcodec:vp9.2']}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'vp9-hdr-format') + + ydl = YDL({'format': 'bestvideo', 'format_sort': ['+vcodec:vp9']}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'vp9-sdr-format') + def test_format_selection_string_ops(self): formats = [ {'format_id': 'abc-cba', 'ext': 'mp4', 'url': TEST_URL}, diff --git a/test/test_utils.py b/test/test_utils.py index a2b459352..4f5fa1e10 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -921,6 +921,11 @@ class TestUtil(unittest.TestCase): 'acodec': 'none', 'dynamic_range': 'HDR10', }) + self.assertEqual(parse_codecs('vp09.02.50.10.01.09.18.09.00'), { + 'vcodec': 'vp09.02.50.10.01.09.18.09.00', + 'acodec': 'none', + 'dynamic_range': 'HDR10', + }) self.assertEqual(parse_codecs('av01.0.12M.10.0.110.09.16.09.0'), { 'vcodec': 'av01.0.12M.10.0.110.09.16.09.0', 'acodec': 'none', diff --git a/yt_dlp/utils/_utils.py b/yt_dlp/utils/_utils.py index 04dd0f8d2..184794f95 100644 --- a/yt_dlp/utils/_utils.py +++ b/yt_dlp/utils/_utils.py @@ -5281,7 +5281,7 @@ class FormatSorter: settings = { 'vcodec': {'type': 'ordered', 'regex': True, - 'order': ['av0?1', 'vp0?9.2', 'vp0?9', '[hx]265|he?vc?', '[hx]264|avc', 'vp0?8', 'mp4v|h263', 'theora', '', None, 'none']}, + 'order': ['av0?1', 'vp0?9.0?2', 'vp0?9', '[hx]265|he?vc?', '[hx]264|avc', 'vp0?8', 'mp4v|h263', 'theora', '', None, 'none']}, 'acodec': {'type': 'ordered', 'regex': True, 'order': ['[af]lac', 'wav|aiff', 'opus', 'vorbis|ogg', 'aac', 'mp?4a?', 'mp3', 'ac-?4', 'e-?a?c-?3', 'ac-?3', 'dts', '', None, 'none']}, 'hdr': {'type': 'ordered', 'regex': True, 'field': 'dynamic_range', From 63da31b3b29af90062d8a72a905ffe4b5e499042 Mon Sep 17 00:00:00 2001 From: ndyanx <114776171+ndyanx@users.noreply.github.com> Date: Fri, 27 Sep 2024 17:05:22 -0500 Subject: [PATCH 047/154] [ie/dropbox] Fix password-protected video support (#10735) Also adds thumbnail extraction Closes #9864 Authored by: ndyanx --- yt_dlp/extractor/dropbox.py | 52 +++++++++++++++++++++++++------------ 1 file changed, 35 insertions(+), 17 deletions(-) diff --git a/yt_dlp/extractor/dropbox.py b/yt_dlp/extractor/dropbox.py index 51b40df42..c12209623 100644 --- a/yt_dlp/extractor/dropbox.py +++ b/yt_dlp/extractor/dropbox.py @@ -6,8 +6,10 @@ import urllib.parse from .common import InfoExtractor from ..utils import ( ExtractorError, + update_url, update_url_query, url_basename, + urlencode_postdata, ) @@ -36,43 +38,58 @@ class DropboxIE(InfoExtractor): }, ] + def _yield_decoded_parts(self, webpage): + for encoded in reversed(re.findall(r'registerStreamedPrefetch\s*\(\s*"[\w/+=]+"\s*,\s*"([\w/+=]+)"', webpage)): + yield base64.b64decode(encoded).decode('utf-8', 'ignore') + def _real_extract(self, url): mobj = self._match_valid_url(url) video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) fn = urllib.parse.unquote(url_basename(url)) title = os.path.splitext(fn)[0] - password = self.get_param('videopassword') - if (self._og_search_title(webpage) == 'Dropbox - Password Required' - or 'Enter the password for this link' in webpage): + for part in self._yield_decoded_parts(webpage): + if '/sm/password' in part: + webpage = self._download_webpage( + update_url('https://www.dropbox.com/sm/password', query=part.partition('?')[2]), video_id) + break + + if (self._og_search_title(webpage, default=None) == 'Dropbox - Password Required' + or 'Enter the password for this link' in webpage): if password: - content_id = self._search_regex(r'content_id=(.*?)["\']', webpage, 'content_id') - payload = f'is_xhr=true&t={self._get_cookies("https://www.dropbox.com").get("t").value}&content_id={content_id}&password={password}&url={url}' response = self._download_json( - 'https://www.dropbox.com/sm/auth', video_id, 'POSTing video password', data=payload.encode(), - headers={'content-type': 'application/x-www-form-urlencoded; charset=UTF-8'}) + 'https://www.dropbox.com/sm/auth', video_id, 'POSTing video password', + headers={'content-type': 'application/x-www-form-urlencoded; charset=UTF-8'}, + data=urlencode_postdata({ + 'is_xhr': 'true', + 't': self._get_cookies('https://www.dropbox.com')['t'].value, + 'content_id': self._search_regex(r'content_id=([\w.+=/-]+)["\']', webpage, 'content id'), + 'password': password, + 'url': url, + })) if response.get('status') != 'authed': - raise ExtractorError('Authentication failed!', expected=True) - webpage = self._download_webpage(url, video_id) - elif self._get_cookies('https://dropbox.com').get('sm_auth'): - webpage = self._download_webpage(url, video_id) - else: + raise ExtractorError('Invalid password', expected=True) + elif not self._get_cookies('https://dropbox.com').get('sm_auth'): raise ExtractorError('Password protected video, use --video-password ', expected=True) + webpage = self._download_webpage(url, video_id) - formats, subtitles, has_anonymous_download = [], {}, False - for encoded in reversed(re.findall(r'registerStreamedPrefetch\s*\(\s*"[\w/+=]+"\s*,\s*"([\w/+=]+)"', webpage)): - decoded = base64.b64decode(encoded).decode('utf-8', 'ignore') + formats, subtitles = [], {} + has_anonymous_download = False + thumbnail = None + for part in self._yield_decoded_parts(webpage): if not has_anonymous_download: has_anonymous_download = self._search_regex( - r'(anonymous:\tanonymous)', decoded, 'anonymous', default=False) + r'(anonymous:\tanonymous)', part, 'anonymous', default=False) transcode_url = self._search_regex( - r'\n.(https://[^\x03\x08\x12\n]+\.m3u8)', decoded, 'transcode url', default=None) + r'\n.(https://[^\x03\x08\x12\n]+\.m3u8)', part, 'transcode url', default=None) if not transcode_url: continue formats, subtitles = self._extract_m3u8_formats_and_subtitles(transcode_url, video_id, 'mp4') + thumbnail = self._search_regex( + r'(https://www\.dropbox\.com/temp_thumb_from_token/[\w/?&=]+)', part, 'thumbnail', default=None) break # downloads enabled we can get the original file @@ -89,4 +106,5 @@ class DropboxIE(InfoExtractor): 'title': title, 'formats': formats, 'subtitles': subtitles, + 'thumbnail': thumbnail, } From 7509d692b37a7ec6230ea75bfe1e44a8de5eefce Mon Sep 17 00:00:00 2001 From: kclauhk <78251477+kclauhk@users.noreply.github.com> Date: Sat, 28 Sep 2024 06:28:22 +0800 Subject: [PATCH 048/154] [ie/loom] Fix m3u8 formats extraction (#10760) Closes #10737 Authored by: kclauhk --- yt_dlp/extractor/loom.py | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/yt_dlp/extractor/loom.py b/yt_dlp/extractor/loom.py index 1191aa17e..b0878c33e 100644 --- a/yt_dlp/extractor/loom.py +++ b/yt_dlp/extractor/loom.py @@ -92,9 +92,9 @@ class LoomIE(InfoExtractor): }, 'params': {'videopassword': 'seniorinfants2'}, }, { - # embed, transcoded-url endpoint sends empty JSON response + # embed, transcoded-url endpoint sends empty JSON response, split video and audio HLS formats 'url': 'https://www.loom.com/embed/ddcf1c1ad21f451ea7468b1e33917e4e', - 'md5': '8488817242a0db1cb2ad0ea522553cf6', + 'md5': 'b321d261656848c184a94e3b93eae28d', 'info_dict': { 'id': 'ddcf1c1ad21f451ea7468b1e33917e4e', 'ext': 'mp4', @@ -104,6 +104,7 @@ class LoomIE(InfoExtractor): 'timestamp': 1657216459, 'duration': 181, }, + 'params': {'format': 'bestvideo'}, # Test video-only fixup 'expected_warnings': ['Failed to parse JSON'], }] _WEBPAGE_TESTS = [{ @@ -293,7 +294,11 @@ class LoomIE(InfoExtractor): format_url = format_url.replace('-split.m3u8', '.m3u8') m3u8_formats = self._extract_m3u8_formats( format_url, video_id, 'mp4', m3u8_id=f'hls-{format_id}', fatal=False, quality=quality) + # Sometimes only split video/audio formats are available, need to fixup video-only formats + is_not_premerged = 'none' in traverse_obj(m3u8_formats, (..., 'vcodec')) for fmt in m3u8_formats: + if is_not_premerged and fmt.get('vcodec') != 'none': + fmt['acodec'] = 'none' yield { **fmt, 'url': update_url(fmt['url'], query=query), From cca534cd9e6850c70244f225a4a1895ef4bcdbec Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Fri, 27 Sep 2024 17:30:31 -0500 Subject: [PATCH 049/154] Raise minimum recommended Python version to 3.9 (#11098) Authored by: bashonly --- devscripts/changelog_override.json | 5 ++++ yt_dlp/update.py | 38 +++++++++++++++++++++++------- 2 files changed, 35 insertions(+), 8 deletions(-) diff --git a/devscripts/changelog_override.json b/devscripts/changelog_override.json index 5189de2d7..7be750cfb 100644 --- a/devscripts/changelog_override.json +++ b/devscripts/changelog_override.json @@ -185,5 +185,10 @@ "action": "add", "when": "6075a029dba70a89675ae1250e7cdfd91f0eba41", "short": "[priority] Security: [[ie/douyutv] Do not use dangerous javascript source/URL](https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-3v33-3wmw-3785)\n - A dependency on potentially malicious third-party JavaScript code has been removed from the Douyu extractors" + }, + { + "action": "add", + "when": "fb8b7f226d251e521a89b23c415e249e5b788e5c", + "short": "[priority] **The minimum *recommended* Python version has been raised to 3.9**\nSince Python 3.8 will reach end-of-life in October 2024, support for it will be dropped soon. [Read more](https://github.com/yt-dlp/yt-dlp/issues/10086)" } ] diff --git a/yt_dlp/update.py b/yt_dlp/update.py index 72ae29084..4cf3bdc32 100644 --- a/yt_dlp/update.py +++ b/yt_dlp/update.py @@ -135,20 +135,42 @@ def _get_binary_name(): def _get_system_deprecation(): - MIN_SUPPORTED, MIN_RECOMMENDED = (3, 8), (3, 8) + MIN_SUPPORTED, MIN_RECOMMENDED = (3, 8), (3, 9) if sys.version_info > MIN_RECOMMENDED: return None major, minor = sys.version_info[:2] - if sys.version_info < MIN_SUPPORTED: - msg = f'Python version {major}.{minor} is no longer supported' - else: - msg = (f'Support for Python version {major}.{minor} has been deprecated. ' - '\nYou may stop receiving updates on this version at any time') + PYTHON_MSG = f'Please update to Python {".".join(map(str, MIN_RECOMMENDED))} or above' - major, minor = MIN_RECOMMENDED - return f'{msg}! Please update to Python {major}.{minor} or above' + if sys.version_info < MIN_SUPPORTED: + return f'Python version {major}.{minor} is no longer supported! {PYTHON_MSG}' + + EXE_MSG_TMPL = ('Support for {} has been deprecated. ' + 'See https://github.com/yt-dlp/yt-dlp/{} for details.\n{}') + STOP_MSG = 'You may stop receiving updates on this version at any time!' + variant = detect_variant() + + # Temporary until Windows builds use 3.9, which will drop support for Win7 and 2008ServerR2 + if variant in ('win_exe', 'win_x86_exe', 'py2exe'): + platform_name = platform.platform() + if any(platform_name.startswith(f'Windows-{name}') for name in ('7', '2008ServerR2')): + return EXE_MSG_TMPL.format('Windows 7/Server 2008 R2', 'issues/10086', STOP_MSG) + elif variant == 'py2exe': + return EXE_MSG_TMPL.format( + 'py2exe builds (yt-dlp_min.exe)', 'issues/10087', + 'In a future update you will be migrated to the PyInstaller-bundled executable. ' + 'This will be done automatically; no action is required on your part') + return None + + # Temporary until aarch64/armv7l build flow is bumped to Ubuntu 20.04 and Python 3.9 + elif variant in ('linux_aarch64_exe', 'linux_armv7l_exe'): + libc_ver = version_tuple(os.confstr('CS_GNU_LIBC_VERSION').partition(' ')[2]) + if libc_ver < (2, 31): + return EXE_MSG_TMPL.format('system glibc version < 2.31', 'pull/8638', STOP_MSG) + return None + + return f'Support for Python version {major}.{minor} has been deprecated. {PYTHON_MSG}' def _sha256_file(path): From c6387abc1af9842bb0541288a5610abba9b1ab51 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Fri, 27 Sep 2024 17:46:22 -0500 Subject: [PATCH 050/154] [cleanup] Misc (#10807) Closes #10751, Closes #10769, Closes #10791 Authored by: bashonly, Codenade, pzhlkj6612, seproDev, coletdjnz, grqz, Grub4K Co-authored-by: Codenade Co-authored-by: Mozi <29089388+pzhlkj6612@users.noreply.github.com> Co-authored-by: sepro <4618135+seproDev@users.noreply.github.com> Co-authored-by: coletdjnz Co-authored-by: N/Ame <173015200+grqz@users.noreply.github.com> Co-authored-by: Simon Sawicki --- .github/workflows/quick-test.yml | 2 +- .github/workflows/release.yml | 4 ++-- README.md | 30 ++++++++++++++-------------- pyproject.toml | 2 +- yt_dlp/downloader/external.py | 4 ++-- yt_dlp/extractor/academicearth.py | 2 +- yt_dlp/extractor/ard.py | 4 ++-- yt_dlp/extractor/callin.py | 2 +- yt_dlp/extractor/common.py | 8 ++++---- yt_dlp/extractor/fc2.py | 2 +- yt_dlp/extractor/generic.py | 4 ++-- yt_dlp/extractor/getcourseru.py | 2 +- yt_dlp/extractor/golem.py | 2 +- yt_dlp/extractor/hrfensehen.py | 2 +- yt_dlp/extractor/japandiet.py | 7 +++++-- yt_dlp/extractor/kaltura.py | 2 +- yt_dlp/extractor/mailru.py | 2 +- yt_dlp/extractor/mgtv.py | 2 +- yt_dlp/extractor/mit.py | 2 +- yt_dlp/extractor/nzonscreen.py | 2 +- yt_dlp/extractor/pornhub.py | 3 +-- yt_dlp/extractor/radiofrance.py | 2 +- yt_dlp/extractor/reverbnation.py | 2 +- yt_dlp/extractor/tele13.py | 2 +- yt_dlp/extractor/twitcasting.py | 2 +- yt_dlp/extractor/viu.py | 2 +- yt_dlp/extractor/ximalaya.py | 2 +- yt_dlp/networking/_websockets.py | 4 ++-- yt_dlp/options.py | 10 +++++----- yt_dlp/postprocessor/sponsorblock.py | 2 +- yt_dlp/utils/_utils.py | 6 +++--- 31 files changed, 63 insertions(+), 61 deletions(-) diff --git a/.github/workflows/quick-test.yml b/.github/workflows/quick-test.yml index fe2a7e923..1571d3cab 100644 --- a/.github/workflows/quick-test.yml +++ b/.github/workflows/quick-test.yml @@ -15,7 +15,7 @@ jobs: with: python-version: '3.8' - name: Install test requirements - run: python3 ./devscripts/install_deps.py --include test + run: python3 ./devscripts/install_deps.py -o --include test - name: Run tests timeout-minutes: 15 run: | diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml index fa5ad7e51..8d0bc4026 100644 --- a/.github/workflows/release.yml +++ b/.github/workflows/release.yml @@ -204,7 +204,7 @@ jobs: git config --global user.email "41898282+github-actions[bot]@users.noreply.github.com" git add -u git commit -m "Release ${{ env.version }}" \ - -m "Created by: ${{ github.event.sender.login }}" -m ":ci skip all :ci run dl" + -m "Created by: ${{ github.event.sender.login }}" -m ":ci skip all" git push origin --force ${{ github.event.ref }}:release - name: Get target commitish @@ -325,7 +325,7 @@ jobs: "(https://github.com/yt-dlp/yt-dlp-master-builds/releases/latest \"Master builds\")"' || '' }} > ./RELEASE_NOTES printf '\n\n' >> ./RELEASE_NOTES cat >> ./RELEASE_NOTES << EOF - #### A description of the various files are in the [README](https://github.com/${{ github.repository }}#release-files) + #### A description of the various files is in the [README](https://github.com/${{ github.repository }}#release-files) --- $(python ./devscripts/make_changelog.py -vv --collapsible) EOF diff --git a/README.md b/README.md index 1d6a4a86d..3e76a4efb 100644 --- a/README.md +++ b/README.md @@ -200,7 +200,7 @@ While all the other dependencies are optional, `ffmpeg` and `ffprobe` are highly The following provide support for impersonating browser requests. This may be required for some sites that employ TLS fingerprinting. -* [**curl_cffi**](https://github.com/yifeikong/curl_cffi) (recommended) - Python binding for [curl-impersonate](https://github.com/lwthiker/curl-impersonate). Provides impersonation targets for Chrome, Edge and Safari. Licensed under [MIT](https://github.com/yifeikong/curl_cffi/blob/main/LICENSE) +* [**curl_cffi**](https://github.com/lexiforest/curl_cffi) (recommended) - Python binding for [curl-impersonate](https://github.com/lexiforest/curl-impersonate). Provides impersonation targets for Chrome, Edge and Safari. Licensed under [MIT](https://github.com/lexiforest/curl_cffi/blob/main/LICENSE) * Can be installed with the `curl-cffi` group, e.g. `pip install "yt-dlp[default,curl-cffi]"` * Currently included in `yt-dlp.exe`, `yt-dlp_linux` and `yt-dlp_macos` builds @@ -459,17 +459,17 @@ If you fork the project on GitHub, you can run your fork's [build workflow](.git conditions. Use a "\" to escape "&" or quotes if needed. If used multiple times, the filter matches if at least one of the - conditions is met. E.g. --match-filter - !is_live --match-filter "like_count>?100 & + conditions is met. E.g. --match-filters + !is_live --match-filters "like_count>?100 & description~='(?i)\bcats \& dogs\b'" matches only videos that are not live OR those that have a like count more than 100 (or the like field is not available) and also has a description that contains the phrase "cats & - dogs" (caseless). Use "--match-filter -" to + dogs" (caseless). Use "--match-filters -" to interactively ask whether to download each video - --no-match-filters Do not use any --match-filter (default) + --no-match-filters Do not use any --match-filters (default) --break-match-filters FILTER Same as "--match-filters" but stops the download process when a video is rejected --no-break-match-filters Do not use any --break-match-filters (default) @@ -490,7 +490,7 @@ If you fork the project on GitHub, you can run your fork's [build workflow](.git encountering a file that is in the archive (default) --break-per-input Alters --max-downloads, --break-on-existing, - --break-match-filter, and autonumber to + --break-match-filters, and autonumber to reset per input URL --no-break-per-input --break-on-existing and similar options terminates the entire download queue @@ -1771,7 +1771,7 @@ The following extractors use this feature: #### youtube * `lang`: Prefer translated metadata (`title`, `description` etc) of this language code (case-sensitive). By default, the video primary language metadata is preferred, with a fallback to `en` translated. See [youtube.py](https://github.com/yt-dlp/yt-dlp/blob/c26f9b991a0681fd3ea548d535919cec1fbbd430/yt_dlp/extractor/youtube.py#L381-L390) for list of supported content language codes * `skip`: One or more of `hls`, `dash` or `translated_subs` to skip extraction of the m3u8 manifests, dash manifests and [auto-translated subtitles](https://github.com/yt-dlp/yt-dlp/issues/4090#issuecomment-1158102032) respectively -* `player_client`: Clients to extract video data from. The main clients are `web`, `ios` and `android`, with variants `_music` and `_creator` (e.g. `ios_creator`); and `mediaconnect`, `mweb`, `android_producer`, `android_testsuite`, `android_vr`, `web_safari`, `web_embedded`, `tv` and `tv_embedded` with no variants. By default, `ios,web_creator` is used, and `tv_embedded`, `web_creator` and `mediaconnect` are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. Most `android` clients will be given lowest priority since their formats are broken. You can use `all` to use all the clients, and `default` for the default clients. +* `player_client`: Clients to extract video data from. The main clients are `web`, `ios` and `android`, with variants `_music` and `_creator` (e.g. `ios_creator`); and `mediaconnect`, `mweb`, `android_producer`, `android_testsuite`, `android_vr`, `web_safari`, `web_embedded`, `tv` and `tv_embedded` with no variants. By default, `ios,web_creator` is used, and `tv_embedded`, `web_creator` and `mediaconnect` are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. Most `android` clients will be given lowest priority since their formats are broken. You can use `all` to use all the clients, and `default` for the default clients. You can prefix a client with `-` to exclude it, e.g. `youtube:player_client=all,-web` * `player_skip`: Skip some network requests that are generally needed for robust extraction. One or more of `configs` (skip client configs), `webpage` (skip initial webpage), `js` (skip js player). While these options can help reduce the number of requests needed or avoid some rate-limiting, they could cause some issues. See [#860](https://github.com/yt-dlp/yt-dlp/pull/860) for more details * `player_params`: YouTube player parameters to use for player requests. Will overwrite any default ones set by yt-dlp. * `comment_sort`: `top` or `new` (default) - choose comment sorting mode (on YouTube's side) @@ -2184,9 +2184,9 @@ with yt_dlp.YoutubeDL(ydl_opts) as ydl: * **Output template improvements**: Output templates can now have date-time formatting, numeric offsets, object traversal etc. See [output template](#output-template) for details. Even more advanced operations can also be done with the help of `--parse-metadata` and `--replace-in-metadata` -* **Other new options**: Many new options have been added such as `--alias`, `--print`, `--concat-playlist`, `--wait-for-video`, `--retry-sleep`, `--sleep-requests`, `--convert-thumbnails`, `--force-download-archive`, `--force-overwrites`, `--break-match-filter` etc +* **Other new options**: Many new options have been added such as `--alias`, `--print`, `--concat-playlist`, `--wait-for-video`, `--retry-sleep`, `--sleep-requests`, `--convert-thumbnails`, `--force-download-archive`, `--force-overwrites`, `--break-match-filters` etc -* **Improvements**: Regex and other operators in `--format`/`--match-filter`, multiple `--postprocessor-args` and `--downloader-args`, faster archive checking, more [format selection options](#format-selection), merge multi-video/audio, multiple `--config-locations`, `--exec` at different stages, etc +* **Improvements**: Regex and other operators in `--format`/`--match-filters`, multiple `--postprocessor-args` and `--downloader-args`, faster archive checking, more [format selection options](#format-selection), merge multi-video/audio, multiple `--config-locations`, `--exec` at different stages, etc * **Plugins**: Extractors and PostProcessors can be loaded from an external file. See [plugins](#plugins) for details @@ -2227,7 +2227,7 @@ Some of yt-dlp's default options are different from that of youtube-dl and youtu * `certifi` will be used for SSL root certificates, if installed. If you want to use system certificates (e.g. self-signed), use `--compat-options no-certifi` * yt-dlp's sanitization of invalid characters in filenames is different/smarter than in youtube-dl. You can use `--compat-options filename-sanitization` to revert to youtube-dl's behavior * ~~yt-dlp tries to parse the external downloader outputs into the standard progress output if possible (Currently implemented: [aria2c](https://github.com/yt-dlp/yt-dlp/issues/5931)). You can use `--compat-options no-external-downloader-progress` to get the downloader output as-is~~ -* yt-dlp versions between 2021.09.01 and 2023.01.02 applies `--match-filter` to nested playlists. This was an unintentional side-effect of [8f18ac](https://github.com/yt-dlp/yt-dlp/commit/8f18aca8717bb0dd49054555af8d386e5eda3a88) and is fixed in [d7b460](https://github.com/yt-dlp/yt-dlp/commit/d7b460d0e5fc710950582baed2e3fc616ed98a80). Use `--compat-options playlist-match-filter` to revert this +* yt-dlp versions between 2021.09.01 and 2023.01.02 applies `--match-filters` to nested playlists. This was an unintentional side-effect of [8f18ac](https://github.com/yt-dlp/yt-dlp/commit/8f18aca8717bb0dd49054555af8d386e5eda3a88) and is fixed in [d7b460](https://github.com/yt-dlp/yt-dlp/commit/d7b460d0e5fc710950582baed2e3fc616ed98a80). Use `--compat-options playlist-match-filter` to revert this * yt-dlp versions between 2021.11.10 and 2023.06.21 estimated `filesize_approx` values for fragmented/manifest formats. This was added for convenience in [f2fe69](https://github.com/yt-dlp/yt-dlp/commit/f2fe69c7b0d208bdb1f6292b4ae92bc1e1a7444a), but was reverted in [0dff8e](https://github.com/yt-dlp/yt-dlp/commit/0dff8e4d1e6e9fb938f4256ea9af7d81f42fd54f) due to the potentially extreme inaccuracy of the estimated values. Use `--compat-options manifest-filesize-approx` to keep extracting the estimated values * yt-dlp uses modern http client backends such as `requests`. Use `--compat-options prefer-legacy-http-handler` to prefer the legacy http handler (`urllib`) to be used for standard http requests. * The sub-modules `swfinterp`, `casefold` are removed. @@ -2273,11 +2273,11 @@ While these options are redundant, they are still expected to be used due to the --get-thumbnail --print thumbnail -e, --get-title --print title -g, --get-url --print urls - --match-title REGEX --match-filter "title ~= (?i)REGEX" - --reject-title REGEX --match-filter "title !~= (?i)REGEX" - --min-views COUNT --match-filter "view_count >=? COUNT" - --max-views COUNT --match-filter "view_count <=? COUNT" - --break-on-reject Use --break-match-filter + --match-title REGEX --match-filters "title ~= (?i)REGEX" + --reject-title REGEX --match-filters "title !~= (?i)REGEX" + --min-views COUNT --match-filters "view_count >=? COUNT" + --max-views COUNT --match-filters "view_count <=? COUNT" + --break-on-reject Use --break-match-filters --user-agent UA --add-header "User-Agent:UA" --referer URL --add-header "Referer:URL" --playlist-start NUMBER -I NUMBER: diff --git a/pyproject.toml b/pyproject.toml index 18d9a0a3a..f54980d57 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -76,7 +76,7 @@ dev = [ ] static-analysis = [ "autopep8~=2.0", - "ruff~=0.5.0", + "ruff~=0.6.0", ] test = [ "pytest~=8.1", diff --git a/yt_dlp/downloader/external.py b/yt_dlp/downloader/external.py index ae2372915..6c1ec403c 100644 --- a/yt_dlp/downloader/external.py +++ b/yt_dlp/downloader/external.py @@ -508,7 +508,7 @@ class FFmpegFD(ExternalFD): env = None proxy = self.params.get('proxy') if proxy: - if not re.match(r'^[\da-zA-Z]+://', proxy): + if not re.match(r'[\da-zA-Z]+://', proxy): proxy = f'http://{proxy}' if proxy.startswith('socks'): @@ -559,7 +559,7 @@ class FFmpegFD(ExternalFD): selected_formats = info_dict.get('requested_formats') or [info_dict] for i, fmt in enumerate(selected_formats): - is_http = re.match(r'^https?://', fmt['url']) + is_http = re.match(r'https?://', fmt['url']) cookies = self.ydl.cookiejar.get_cookies_for_url(fmt['url']) if is_http else [] if cookies: args.extend(['-cookies', ''.join( diff --git a/yt_dlp/extractor/academicearth.py b/yt_dlp/extractor/academicearth.py index d9691cb5c..b997a0288 100644 --- a/yt_dlp/extractor/academicearth.py +++ b/yt_dlp/extractor/academicearth.py @@ -4,7 +4,7 @@ from .common import InfoExtractor class AcademicEarthCourseIE(InfoExtractor): - _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/playlists/(?P[^?#/]+)' + _VALID_URL = r'https?://(?:www\.)?academicearth\.org/playlists/(?P[^?#/]+)' IE_NAME = 'AcademicEarth:Course' _TEST = { 'url': 'http://academicearth.org/playlists/laws-of-nature/', diff --git a/yt_dlp/extractor/ard.py b/yt_dlp/extractor/ard.py index 6fd641347..efc79dd14 100644 --- a/yt_dlp/extractor/ard.py +++ b/yt_dlp/extractor/ard.py @@ -231,7 +231,7 @@ class ARDIE(InfoExtractor): class ARDBetaMediathekIE(InfoExtractor): IE_NAME = 'ARDMediathek' - _VALID_URL = r'''(?x)https:// + _VALID_URL = r'''(?x)https?:// (?:(?:beta|www)\.)?ardmediathek\.de/ (?:[^/]+/)? (?:player|live|video)/ @@ -470,7 +470,7 @@ class ARDBetaMediathekIE(InfoExtractor): class ARDMediathekCollectionIE(InfoExtractor): - _VALID_URL = r'''(?x)https:// + _VALID_URL = r'''(?x)https?:// (?:(?:beta|www)\.)?ardmediathek\.de/ (?:[^/?#]+/)? (?Psendung|serie|sammlung)/ diff --git a/yt_dlp/extractor/callin.py b/yt_dlp/extractor/callin.py index b7061a7d1..ee2e56f8e 100644 --- a/yt_dlp/extractor/callin.py +++ b/yt_dlp/extractor/callin.py @@ -3,7 +3,7 @@ from ..utils import float_or_none, int_or_none, make_archive_id, traverse_obj class CallinIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?callin\.com/(episode)/(?P[-a-zA-Z]+)' + _VALID_URL = r'https?://(?:www\.)?callin\.com/episode/(?P[-a-zA-Z]+)' _TESTS = [{ 'url': 'https://www.callin.com/episode/the-title-ix-regime-and-the-long-march-through-EBfXYSrsjc', 'info_dict': { diff --git a/yt_dlp/extractor/common.py b/yt_dlp/extractor/common.py index 9501e5ec9..486a4ea3c 100644 --- a/yt_dlp/extractor/common.py +++ b/yt_dlp/extractor/common.py @@ -2077,7 +2077,7 @@ class InfoExtractor: has_drm = HlsFD._has_drm(m3u8_doc) def format_url(url): - return url if re.match(r'^https?://', url) else urllib.parse.urljoin(m3u8_url, url) + return url if re.match(r'https?://', url) else urllib.parse.urljoin(m3u8_url, url) if self.get_param('hls_split_discontinuity', False): def _extract_m3u8_playlist_indices(manifest_url=None, m3u8_doc=None): @@ -2812,11 +2812,11 @@ class InfoExtractor: base_url_e = element.find(_add_ns('BaseURL')) if try_call(lambda: base_url_e.text) is not None: base_url = base_url_e.text + base_url - if re.match(r'^https?://', base_url): + if re.match(r'https?://', base_url): break if mpd_base_url and base_url.startswith('/'): base_url = urllib.parse.urljoin(mpd_base_url, base_url) - elif mpd_base_url and not re.match(r'^https?://', base_url): + elif mpd_base_url and not re.match(r'https?://', base_url): if not mpd_base_url.endswith('/'): mpd_base_url += '/' base_url = mpd_base_url + base_url @@ -2906,7 +2906,7 @@ class InfoExtractor: } def location_key(location): - return 'url' if re.match(r'^https?://', location) else 'path' + return 'url' if re.match(r'https?://', location) else 'path' if 'segment_urls' not in representation_ms_info and 'media' in representation_ms_info: diff --git a/yt_dlp/extractor/fc2.py b/yt_dlp/extractor/fc2.py index eac70f6a9..f7b883155 100644 --- a/yt_dlp/extractor/fc2.py +++ b/yt_dlp/extractor/fc2.py @@ -14,7 +14,7 @@ from ..utils import ( class FC2IE(InfoExtractor): - _VALID_URL = r'^(?:https?://video\.fc2\.com/(?:[^/]+/)*content/|fc2:)(?P[^/]+)' + _VALID_URL = r'(?:https?://video\.fc2\.com/(?:[^/]+/)*content/|fc2:)(?P[^/]+)' IE_NAME = 'fc2' _NETRC_MACHINE = 'fc2' _TESTS = [{ diff --git a/yt_dlp/extractor/generic.py b/yt_dlp/extractor/generic.py index 04cffaa86..592800287 100644 --- a/yt_dlp/extractor/generic.py +++ b/yt_dlp/extractor/generic.py @@ -2340,7 +2340,7 @@ class GenericIE(InfoExtractor): default_search = 'fixup_error' if default_search in ('auto', 'auto_warning', 'fixup_error'): - if re.match(r'^[^\s/]+\.[^\s/]+/', url): + if re.match(r'[^\s/]+\.[^\s/]+/', url): self.report_warning('The url doesn\'t specify the protocol, trying with http') return self.url_result('http://' + url) elif default_search != 'fixup_error': @@ -2400,7 +2400,7 @@ class GenericIE(InfoExtractor): # Check for direct link to a video content_type = full_response.headers.get('Content-Type', '').lower() - m = re.match(r'^(?Paudio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P[^;\s]+)', content_type) + m = re.match(r'(?Paudio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P[^;\s]+)', content_type) if m: self.report_detected('direct video link') headers = filter_dict({'Referer': smuggled_data.get('referer')}) diff --git a/yt_dlp/extractor/getcourseru.py b/yt_dlp/extractor/getcourseru.py index 53b881011..b7581d77e 100644 --- a/yt_dlp/extractor/getcourseru.py +++ b/yt_dlp/extractor/getcourseru.py @@ -52,7 +52,7 @@ class GetCourseRuIE(InfoExtractor): _BASE_URL_RE = rf'https?://(?:(?!player02\.)[^.]+\.getcourse\.(?:ru|io)|{"|".join(map(re.escape, _DOMAINS))})' _VALID_URL = [ rf'{_BASE_URL_RE}/(?!pl/|teach/)(?P[^?#]+)', - rf'{_BASE_URL_RE}/(:?pl/)?teach/control/lesson/view\?(?:[^#]+&)?id=(?P\d+)', + rf'{_BASE_URL_RE}/(?:pl/)?teach/control/lesson/view\?(?:[^#]+&)?id=(?P\d+)', ] _TESTS = [{ 'url': 'http://academymel.online/3video_1', diff --git a/yt_dlp/extractor/golem.py b/yt_dlp/extractor/golem.py index 90d2fe6c2..964bf6519 100644 --- a/yt_dlp/extractor/golem.py +++ b/yt_dlp/extractor/golem.py @@ -7,7 +7,7 @@ from ..utils import ( class GolemIE(InfoExtractor): - _VALID_URL = r'^https?://video\.golem\.de/.+?/(?P.+?)/' + _VALID_URL = r'https?://video\.golem\.de/.+?/(?P.+?)/' _TEST = { 'url': 'http://video.golem.de/handy/14095/iphone-6-und-6-plus-test.html', 'md5': 'c1a2c0a3c863319651c7c992c5ee29bf', diff --git a/yt_dlp/extractor/hrfensehen.py b/yt_dlp/extractor/hrfensehen.py index 17673d5b8..b5a7b14a5 100644 --- a/yt_dlp/extractor/hrfensehen.py +++ b/yt_dlp/extractor/hrfensehen.py @@ -13,7 +13,7 @@ from ..utils import ( class HRFernsehenIE(InfoExtractor): IE_NAME = 'hrfernsehen' - _VALID_URL = r'^https?://www\.(?:hr-fernsehen|hessenschau)\.de/.*,video-(?P[0-9]{6})\.html' + _VALID_URL = r'https?://www\.(?:hr-fernsehen|hessenschau)\.de/.*,video-(?P[0-9]{6})\.html' _TESTS = [{ 'url': 'https://www.hessenschau.de/tv-sendung/hessenschau-vom-26082020,video-130546.html', 'md5': '5c4e0ba94677c516a2f65a84110fc536', diff --git a/yt_dlp/extractor/japandiet.py b/yt_dlp/extractor/japandiet.py index 2ef091aff..994da22ae 100644 --- a/yt_dlp/extractor/japandiet.py +++ b/yt_dlp/extractor/japandiet.py @@ -194,11 +194,14 @@ class ShugiinItvVodIE(ShugiinItvBaseIE): class SangiinInstructionIE(InfoExtractor): - _VALID_URL = r'^https?://www\.webtv\.sangiin\.go\.jp/webtv/index\.php' + _VALID_URL = r'https?://www\.webtv\.sangiin\.go\.jp/webtv/index\.php' IE_DESC = False # this shouldn't be listed as a supported site def _real_extract(self, url): - raise ExtractorError('Copy the link from the botton below the video description or player, and use the link to download. If there are no button in the frame, get the URL of the frame showing the video.', expected=True) + raise ExtractorError( + 'Copy the link from the button below the video description/player ' + 'and use that link to download. If there is no button in the frame, ' + 'get the URL of the frame showing the video.', expected=True) class SangiinIE(InfoExtractor): diff --git a/yt_dlp/extractor/kaltura.py b/yt_dlp/extractor/kaltura.py index e5737b1e9..6d51e32f6 100644 --- a/yt_dlp/extractor/kaltura.py +++ b/yt_dlp/extractor/kaltura.py @@ -22,7 +22,7 @@ class KalturaIE(InfoExtractor): (?: kaltura:(?P\w+):(?P\w+)(?::(?P\w+))?| https?:// - (:?(?:www|cdnapi(?:sec)?)\.)?kaltura\.com(?::\d+)?/ + (?:(?:www|cdnapi(?:sec)?)\.)?kaltura\.com(?::\d+)?/ (?: (?: # flash player diff --git a/yt_dlp/extractor/mailru.py b/yt_dlp/extractor/mailru.py index cca678f14..0496a87f0 100644 --- a/yt_dlp/extractor/mailru.py +++ b/yt_dlp/extractor/mailru.py @@ -126,7 +126,7 @@ class MailRuIE(InfoExtractor): video_data = None # fix meta_url if missing the host address - if re.match(r'^\/\+\/', meta_url): + if re.match(r'\/\+\/', meta_url): meta_url = urljoin('https://my.mail.ru', meta_url) if meta_url: diff --git a/yt_dlp/extractor/mgtv.py b/yt_dlp/extractor/mgtv.py index d5dda06f9..c793626fd 100644 --- a/yt_dlp/extractor/mgtv.py +++ b/yt_dlp/extractor/mgtv.py @@ -16,7 +16,7 @@ from ..utils import ( class MGTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:w(?:ww)?\.)?mgtv\.com/(v|b)/(?:[^/]+/)*(?P\d+)\.html' + _VALID_URL = r'https?://(?:w(?:ww)?\.)?mgtv\.com/[bv]/(?:[^/]+/)*(?P\d+)\.html' IE_DESC = '芒果TV' IE_NAME = 'MangoTV' diff --git a/yt_dlp/extractor/mit.py b/yt_dlp/extractor/mit.py index e75c540a2..66c3b0793 100644 --- a/yt_dlp/extractor/mit.py +++ b/yt_dlp/extractor/mit.py @@ -65,7 +65,7 @@ class TechTVMITIE(InfoExtractor): class OCWMITIE(InfoExtractor): IE_NAME = 'ocw.mit.edu' - _VALID_URL = r'^https?://ocw\.mit\.edu/courses/(?P[a-z0-9\-]+)' + _VALID_URL = r'https?://ocw\.mit\.edu/courses/(?P[a-z0-9\-]+)' _BASE_URL = 'http://ocw.mit.edu/' _TESTS = [ diff --git a/yt_dlp/extractor/nzonscreen.py b/yt_dlp/extractor/nzonscreen.py index 5fc516daf..755039804 100644 --- a/yt_dlp/extractor/nzonscreen.py +++ b/yt_dlp/extractor/nzonscreen.py @@ -10,7 +10,7 @@ from ..utils import ( class NZOnScreenIE(InfoExtractor): - _VALID_URL = r'^https?://www\.nzonscreen\.com/title/(?P[^/?#]+)' + _VALID_URL = r'https?://www\.nzonscreen\.com/title/(?P[^/?#]+)' _TESTS = [{ 'url': 'https://www.nzonscreen.com/title/shoop-shoop-diddy-wop-cumma-cumma-wang-dang-1982', 'info_dict': { diff --git a/yt_dlp/extractor/pornhub.py b/yt_dlp/extractor/pornhub.py index 679dc6323..e1e9777e8 100644 --- a/yt_dlp/extractor/pornhub.py +++ b/yt_dlp/extractor/pornhub.py @@ -628,8 +628,7 @@ class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE): page_entries = self._extract_entries(webpage, host) if not page_entries: break - for e in page_entries: - yield e + yield from page_entries if not self._has_more(webpage): break diff --git a/yt_dlp/extractor/radiofrance.py b/yt_dlp/extractor/radiofrance.py index ff2196354..9d9043984 100644 --- a/yt_dlp/extractor/radiofrance.py +++ b/yt_dlp/extractor/radiofrance.py @@ -16,7 +16,7 @@ from ..utils import ( class RadioFranceIE(InfoExtractor): - _VALID_URL = r'^https?://maison\.radiofrance\.fr/radiovisions/(?P[^?#]+)' + _VALID_URL = r'https?://maison\.radiofrance\.fr/radiovisions/(?P[^?#]+)' IE_NAME = 'radiofrance' _TEST = { diff --git a/yt_dlp/extractor/reverbnation.py b/yt_dlp/extractor/reverbnation.py index ddf8c3753..f3bcc2c32 100644 --- a/yt_dlp/extractor/reverbnation.py +++ b/yt_dlp/extractor/reverbnation.py @@ -6,7 +6,7 @@ from ..utils import ( class ReverbNationIE(InfoExtractor): - _VALID_URL = r'^https?://(?:www\.)?reverbnation\.com/.*?/song/(?P\d+).*?$' + _VALID_URL = r'https?://(?:www\.)?reverbnation\.com/.*?/song/(?P\d+).*?$' _TESTS = [{ 'url': 'http://www.reverbnation.com/alkilados/song/16965047-mona-lisa', 'md5': 'c0aaf339bcee189495fdf5a8c8ba8645', diff --git a/yt_dlp/extractor/tele13.py b/yt_dlp/extractor/tele13.py index c5ca208fb..0d721773e 100644 --- a/yt_dlp/extractor/tele13.py +++ b/yt_dlp/extractor/tele13.py @@ -8,7 +8,7 @@ from ..utils import ( class Tele13IE(InfoExtractor): - _VALID_URL = r'^https?://(?:www\.)?t13\.cl/videos(?:/[^/]+)+/(?P[\w-]+)' + _VALID_URL = r'https?://(?:www\.)?t13\.cl/videos(?:/[^/]+)+/(?P[\w-]+)' _TESTS = [ { 'url': 'http://www.t13.cl/videos/actualidad/el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda', diff --git a/yt_dlp/extractor/twitcasting.py b/yt_dlp/extractor/twitcasting.py index 53b408469..bf9c6348c 100644 --- a/yt_dlp/extractor/twitcasting.py +++ b/yt_dlp/extractor/twitcasting.py @@ -270,7 +270,7 @@ class TwitCastingLiveIE(InfoExtractor): class TwitCastingUserIE(InfoExtractor): - _VALID_URL = r'https?://(?:[^/?#]+\.)?twitcasting\.tv/(?P[^/?#]+)/(:?show|archive)/?(?:[#?]|$)' + _VALID_URL = r'https?://(?:[^/?#]+\.)?twitcasting\.tv/(?P[^/?#]+)/(?:show|archive)/?(?:[#?]|$)' _TESTS = [{ 'url': 'https://twitcasting.tv/natsuiromatsuri/archive/', 'info_dict': { diff --git a/yt_dlp/extractor/viu.py b/yt_dlp/extractor/viu.py index 01e59352b..f4ed96bf6 100644 --- a/yt_dlp/extractor/viu.py +++ b/yt_dlp/extractor/viu.py @@ -90,7 +90,7 @@ class ViuIE(ViuBaseIE): formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, 'mp4') for key, value in video_data.items(): - mobj = re.match(r'^subtitle_(?P[^_]+)_(?P(vtt|srt))', key) + mobj = re.match(r'subtitle_(?P[^_]+)_(?P(vtt|srt))', key) if not mobj: continue subtitles.setdefault(mobj.group('lang'), []).append({ diff --git a/yt_dlp/extractor/ximalaya.py b/yt_dlp/extractor/ximalaya.py index d63964a00..02bf6a7be 100644 --- a/yt_dlp/extractor/ximalaya.py +++ b/yt_dlp/extractor/ximalaya.py @@ -21,7 +21,7 @@ class XimalayaBaseIE(InfoExtractor): class XimalayaIE(XimalayaBaseIE): IE_NAME = 'ximalaya' IE_DESC = '喜马拉雅FM' - _VALID_URL = r'https?://(?:www\.|m\.)?ximalaya\.com/(:?(?P\d+)/)?sound/(?P[0-9]+)' + _VALID_URL = r'https?://(?:www\.|m\.)?ximalaya\.com/(?:(?P\d+)/)?sound/(?P[0-9]+)' _TESTS = [ { 'url': 'http://www.ximalaya.com/sound/47740352/', diff --git a/yt_dlp/networking/_websockets.py b/yt_dlp/networking/_websockets.py index 21b765b91..ec55567da 100644 --- a/yt_dlp/networking/_websockets.py +++ b/yt_dlp/networking/_websockets.py @@ -33,8 +33,8 @@ if not websockets: import websockets.version websockets_version = tuple(map(int_or_none, websockets.version.version.split('.'))) -if websockets_version < (12, 0): - raise ImportError('Only websockets>=12.0 is supported') +if websockets_version < (13, 0): + raise ImportError('Only websockets>=13.0 is supported') import websockets.sync.client from websockets.uri import parse_uri diff --git a/yt_dlp/options.py b/yt_dlp/options.py index 8077d5d88..9980b7fc3 100644 --- a/yt_dlp/options.py +++ b/yt_dlp/options.py @@ -647,16 +647,16 @@ def create_parser(): 'You can also simply specify a field to match if the field is present, ' 'use "!field" to check if the field is not present, and "&" to check multiple conditions. ' 'Use a "\\" to escape "&" or quotes if needed. If used multiple times, ' - 'the filter matches if at least one of the conditions is met. E.g. --match-filter ' - '!is_live --match-filter "like_count>?100 & description~=\'(?i)\\bcats \\& dogs\\b\'" ' + 'the filter matches if at least one of the conditions is met. E.g. --match-filters ' + '!is_live --match-filters "like_count>?100 & description~=\'(?i)\\bcats \\& dogs\\b\'" ' 'matches only videos that are not live OR those that have a like count more than 100 ' '(or the like field is not available) and also has a description ' 'that contains the phrase "cats & dogs" (caseless). ' - 'Use "--match-filter -" to interactively ask whether to download each video')) + 'Use "--match-filters -" to interactively ask whether to download each video')) selection.add_option( '--no-match-filters', dest='match_filter', action='store_const', const=None, - help='Do not use any --match-filter (default)') + help='Do not use any --match-filters (default)') selection.add_option( '--break-match-filters', metavar='FILTER', dest='breaking_match_filter', action='append', @@ -704,7 +704,7 @@ def create_parser(): selection.add_option( '--break-per-input', action='store_true', dest='break_per_url', default=False, - help='Alters --max-downloads, --break-on-existing, --break-match-filter, and autonumber to reset per input URL') + help='Alters --max-downloads, --break-on-existing, --break-match-filters, and autonumber to reset per input URL') selection.add_option( '--no-break-per-input', action='store_false', dest='break_per_url', diff --git a/yt_dlp/postprocessor/sponsorblock.py b/yt_dlp/postprocessor/sponsorblock.py index 6cf9ab62e..b3fc8b54a 100644 --- a/yt_dlp/postprocessor/sponsorblock.py +++ b/yt_dlp/postprocessor/sponsorblock.py @@ -33,7 +33,7 @@ class SponsorBlockPP(FFmpegPostProcessor): def __init__(self, downloader, categories=None, api='https://sponsor.ajay.app'): FFmpegPostProcessor.__init__(self, downloader) self._categories = tuple(categories or self.CATEGORIES.keys()) - self._API_URL = api if re.match('^https?://', api) else 'https://' + api + self._API_URL = api if re.match('https?://', api) else 'https://' + api def run(self, info): extractor = info['extractor_key'] diff --git a/yt_dlp/utils/_utils.py b/yt_dlp/utils/_utils.py index 184794f95..e1b3c48d6 100644 --- a/yt_dlp/utils/_utils.py +++ b/yt_dlp/utils/_utils.py @@ -1954,7 +1954,7 @@ def urljoin(base, path): path = path.decode() if not isinstance(path, str) or not path: return None - if re.match(r'^(?:[a-zA-Z][a-zA-Z0-9+-.]*:)?//', path): + if re.match(r'(?:[a-zA-Z][a-zA-Z0-9+-.]*:)?//', path): return path if isinstance(base, bytes): base = base.decode() @@ -2007,7 +2007,7 @@ def url_or_none(url): if not url or not isinstance(url, str): return None url = url.strip() - return url if re.match(r'^(?:(?:https?|rt(?:m(?:pt?[es]?|fp)|sp[su]?)|mms|ftps?):)?//', url) else None + return url if re.match(r'(?:(?:https?|rt(?:m(?:pt?[es]?|fp)|sp[su]?)|mms|ftps?):)?//', url) else None def strftime_or_none(timestamp, date_format='%Y%m%d', default=None): @@ -3113,7 +3113,7 @@ def is_html(first_bytes): while first_bytes.startswith(bom): encoding, first_bytes = enc, first_bytes[len(bom):] - return re.match(r'^\s*<', first_bytes.decode(encoding, 'replace')) + return re.match(r'\s*<', first_bytes.decode(encoding, 'replace')) def determine_protocol(info_dict): From 5945fc1945a4001537072e39f03725f944437834 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" <41898282+github-actions[bot]@users.noreply.github.com> Date: Fri, 27 Sep 2024 23:01:13 +0000 Subject: [PATCH 051/154] Release 2024.09.27 Created by: bashonly :ci skip all --- CONTRIBUTORS | 16 +++++++++ Changelog.md | 90 +++++++++++++++++++++++++++++++++++++++++++++++ supportedsites.md | 14 ++++++-- yt_dlp/version.py | 6 ++-- 4 files changed, 120 insertions(+), 6 deletions(-) diff --git a/CONTRIBUTORS b/CONTRIBUTORS index 489ab7da8..c80f71405 100644 --- a/CONTRIBUTORS +++ b/CONTRIBUTORS @@ -657,3 +657,19 @@ luvyana szantnerb hugepower scribblemaniac +Codenade +Demon000 +Deukhoofd +grqz +hibes +Khaoklong51 +kieraneglin +lengzuo +naglis +ndyanx +otovalek +quad +rakslice +sahilsinghss73 +tony-hn +xingchensong diff --git a/Changelog.md b/Changelog.md index 0b96ab29c..2ef28fa07 100644 --- a/Changelog.md +++ b/Changelog.md @@ -4,6 +4,96 @@ # To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master --> +### 2024.09.27 + +#### Important changes +- **The minimum *recommended* Python version has been raised to 3.9** +Since Python 3.8 will reach end-of-life in October 2024, support for it will be dropped soon. [Read more](https://github.com/yt-dlp/yt-dlp/issues/10086) + +#### Core changes +- [Allow `none` arg to negate `--convert-subs` and `--convert-thumbnails`](https://github.com/yt-dlp/yt-dlp/commit/c08e0b20b5edd8957b8318716bc14e896d1b96f4) ([#11066](https://github.com/yt-dlp/yt-dlp/issues/11066)) by [kieraneglin](https://github.com/kieraneglin) +- [Fix format sorting bug with vp9.2 vcodec](https://github.com/yt-dlp/yt-dlp/commit/8f4ea14680c7865d8ffac10a9174205d1d84ada7) ([#10884](https://github.com/yt-dlp/yt-dlp/issues/10884)) by [rakslice](https://github.com/rakslice) +- [Raise minimum recommended Python version to 3.9](https://github.com/yt-dlp/yt-dlp/commit/cca534cd9e6850c70244f225a4a1895ef4bcdbec) ([#11098](https://github.com/yt-dlp/yt-dlp/issues/11098)) by [bashonly](https://github.com/bashonly) +- **cookies**: [Improve error message for Windows `--cookies-from-browser chrome` issue](https://github.com/yt-dlp/yt-dlp/commit/b397a64691421ace5df09457c2a764821a2dc6f2) ([#11090](https://github.com/yt-dlp/yt-dlp/issues/11090)) by [seproDev](https://github.com/seproDev) +- **utils**: `mimetype2ext`: [Recognize `aacp` as `aac`](https://github.com/yt-dlp/yt-dlp/commit/cc85596d5b59f0c14e9381b3675f619c1e12e597) ([#10860](https://github.com/yt-dlp/yt-dlp/issues/10860)) by [bashonly](https://github.com/bashonly) + +#### Extractor changes +- [Fix JW Player format parsing](https://github.com/yt-dlp/yt-dlp/commit/409f8e9e3b4bde81ef76fc563256f876d2ff8099) ([#10956](https://github.com/yt-dlp/yt-dlp/issues/10956)) by [seproDev](https://github.com/seproDev) +- [Handle decode errors when reading responses](https://github.com/yt-dlp/yt-dlp/commit/325001317d97f4545d66fac44c4ba772c6f45f22) ([#10868](https://github.com/yt-dlp/yt-dlp/issues/10868)) by [bashonly](https://github.com/bashonly) +- **abc.net.au**: iview, showseries: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/7f909046f4dc0fba472b4963145aef6e0d42491b) ([#11101](https://github.com/yt-dlp/yt-dlp/issues/11101)) by [bashonly](https://github.com/bashonly) +- **adn**: [Fix extractors](https://github.com/yt-dlp/yt-dlp/commit/cc88a54bb1ef285154775f8a6a413335ce4c71ce) ([#10749](https://github.com/yt-dlp/yt-dlp/issues/10749)) by [infanf](https://github.com/infanf) +- **asobistage**: [Support redirected URLs](https://github.com/yt-dlp/yt-dlp/commit/a7d3235c84dac57a127cbe0ff38f7f7c2fdd8fa0) ([#10768](https://github.com/yt-dlp/yt-dlp/issues/10768)) by [pzhlkj6612](https://github.com/pzhlkj6612) +- **bandcamp**: user: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/5d0176547f16a3642cd71627126e9dfc24981e20) ([#10328](https://github.com/yt-dlp/yt-dlp/issues/10328)) by [bashonly](https://github.com/bashonly), [quad](https://github.com/quad) +- **beacon**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/b4760c778d0c92c6e3f2bc8346cd72c8f08595ae) ([#9901](https://github.com/yt-dlp/yt-dlp/issues/9901)) by [Deukhoofd](https://github.com/Deukhoofd) +- **bilibili** + - [Fix chapters and subtitles extraction](https://github.com/yt-dlp/yt-dlp/commit/a2000bc85730c950351d78bb818493dc39dca3cb) ([#11099](https://github.com/yt-dlp/yt-dlp/issues/11099)) by [bashonly](https://github.com/bashonly) + - [Fix festival URL support](https://github.com/yt-dlp/yt-dlp/commit/b43bd864851f2862e26caa85461c5d825d49d463) ([#10740](https://github.com/yt-dlp/yt-dlp/issues/10740)) by [bashonly](https://github.com/bashonly), [grqz](https://github.com/grqz) +- **biliintl**: [Fix referer header](https://github.com/yt-dlp/yt-dlp/commit/a06bb586795ebab87a2356923acfc674d6f0e152) ([#11003](https://github.com/yt-dlp/yt-dlp/issues/11003)) by [Khaoklong51](https://github.com/Khaoklong51) +- **dropbox**: [Fix password-protected video support](https://github.com/yt-dlp/yt-dlp/commit/63da31b3b29af90062d8a72a905ffe4b5e499042) ([#10735](https://github.com/yt-dlp/yt-dlp/issues/10735)) by [ndyanx](https://github.com/ndyanx) +- **ertgr**: [Fix video extraction](https://github.com/yt-dlp/yt-dlp/commit/416686ed0cf792ec44ab059f3b229dd776077e14) ([#11091](https://github.com/yt-dlp/yt-dlp/issues/11091)) by [seproDev](https://github.com/seproDev) +- **eurosport**: [Support local URL variants](https://github.com/yt-dlp/yt-dlp/commit/f0bb28504c8c2b75ee3e5796aed50de2a7f90a1b) ([#10785](https://github.com/yt-dlp/yt-dlp/issues/10785)) by [seproDev](https://github.com/seproDev) +- **facebook** + - ads: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/d62fef7e07d454c0d2ba2d69fb96d691dba1ded0) ([#10704](https://github.com/yt-dlp/yt-dlp/issues/10704)) by [kclauhk](https://github.com/kclauhk) + - reel: [Improve metadata extraction](https://github.com/yt-dlp/yt-dlp/commit/0e1b941c6b2caa688b0d3332e723d16dbafa4311) by [lengzuo](https://github.com/lengzuo) +- **germanupa**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/124f058b546d652a359c67025bb479789bfbef0b) ([#10538](https://github.com/yt-dlp/yt-dlp/issues/10538)) by [grqz](https://github.com/grqz) +- **hgtvde**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/a555389c9bb32e589e00b4664974423fb7b04dcd) ([#10992](https://github.com/yt-dlp/yt-dlp/issues/10992)) by [bashonly](https://github.com/bashonly), [rdamas](https://github.com/rdamas) +- **huya**: video: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/25c1cdaa2650563494d3bf00a38f72d0d9486bff) ([#10686](https://github.com/yt-dlp/yt-dlp/issues/10686)) by [hugepower](https://github.com/hugepower) +- **iprima**: [Fix zoom URL support](https://github.com/yt-dlp/yt-dlp/commit/4a27b8f092f7f7c10b7a334d3535c97c2af02f0a) ([#10959](https://github.com/yt-dlp/yt-dlp/issues/10959)) by [otovalek](https://github.com/otovalek) +- **khanacademy**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/0fba08485b6445b72b5b63ae23ca2a73fa5d967f) ([#10913](https://github.com/yt-dlp/yt-dlp/issues/10913)) by [seproDev](https://github.com/seproDev) +- **kick** + - clips: [Support new URL format](https://github.com/yt-dlp/yt-dlp/commit/0aa4426e9a35f7f8e184f1f2082b3b313c1448f7) ([#11107](https://github.com/yt-dlp/yt-dlp/issues/11107)) by [bashonly](https://github.com/bashonly) + - vod: [Support new URL format](https://github.com/yt-dlp/yt-dlp/commit/173d54c151b987409e3eb09552d8d89ed8fc50f7) ([#10988](https://github.com/yt-dlp/yt-dlp/issues/10988)) by [bashonly](https://github.com/bashonly), [grqz](https://github.com/grqz) +- **kika**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/e6f48ca80821939c1fd11ec2a0cdbf2fba9b258a) ([#5788](https://github.com/yt-dlp/yt-dlp/issues/5788)) by [1100101](https://github.com/1100101) +- **lnkgo**: [Remove extractor](https://github.com/yt-dlp/yt-dlp/commit/fa83d0b36bc43d30fe9241c1e923f4614864b758) ([#10904](https://github.com/yt-dlp/yt-dlp/issues/10904)) by [naglis](https://github.com/naglis) +- **loom**: [Fix m3u8 formats extraction](https://github.com/yt-dlp/yt-dlp/commit/7509d692b37a7ec6230ea75bfe1e44a8de5eefce) ([#10760](https://github.com/yt-dlp/yt-dlp/issues/10760)) by [kclauhk](https://github.com/kclauhk) +- **mediaklikk**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/e2b3634e299be9c16a247ece3b1858d83889c324) ([#11083](https://github.com/yt-dlp/yt-dlp/issues/11083)) by [szantnerb](https://github.com/szantnerb) +- **mojevideo**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/28b0ecba2af5b4919f198474b3d00a76ef322c31) ([#11019](https://github.com/yt-dlp/yt-dlp/issues/11019)) by [04-pasha-04](https://github.com/04-pasha-04), [pzhlkj6612](https://github.com/pzhlkj6612) +- **niconico**: [Fix m3u8 formats extraction](https://github.com/yt-dlp/yt-dlp/commit/eabb4680fdb09ba1f48d174a700a2e3b43f82add) ([#11103](https://github.com/yt-dlp/yt-dlp/issues/11103)) by [bashonly](https://github.com/bashonly) +- **nzz**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/4a9bc8c3630378bc29f0266126b503f6190c0430) ([#10461](https://github.com/yt-dlp/yt-dlp/issues/10461)) by [1-Byte](https://github.com/1-Byte) +- **patreoncampaign**: [Support API URLs](https://github.com/yt-dlp/yt-dlp/commit/232e6db30c474d1b387e405342f34173ceeaf832) ([#10734](https://github.com/yt-dlp/yt-dlp/issues/10734)) by [bashonly](https://github.com/bashonly), [hibes](https://github.com/hibes) +- **pinterest**: [Extend `_VALID_URL`](https://github.com/yt-dlp/yt-dlp/commit/c8c078fe28b0ffc15ef9646346c00c592fe71a78) ([#10867](https://github.com/yt-dlp/yt-dlp/issues/10867)) by [bashonly](https://github.com/bashonly), [sahilsinghss73](https://github.com/sahilsinghss73) +- **radiko**: [Extract unique `id` values](https://github.com/yt-dlp/yt-dlp/commit/c8d096c5ce111411fbdbe2abb8fed54f317a6182) ([#10726](https://github.com/yt-dlp/yt-dlp/issues/10726)) by [garret1317](https://github.com/garret1317) +- **rtp**: [Support more subpages](https://github.com/yt-dlp/yt-dlp/commit/d02df303d8e49390599db9f34482697e4d1cf5b2) ([#10787](https://github.com/yt-dlp/yt-dlp/issues/10787)) by [Demon000](https://github.com/Demon000) +- **rumblechannel**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/ad0b857f459a6d390fbf124183916218c52f223a) ([#11049](https://github.com/yt-dlp/yt-dlp/issues/11049)) by [tony-hn](https://github.com/tony-hn) +- **rutube**: [Support livestreams](https://github.com/yt-dlp/yt-dlp/commit/41be32e78c3845000dbac188ffb90ea3ea7c4dfa) ([#10844](https://github.com/yt-dlp/yt-dlp/issues/10844)) by [pzhlkj6612](https://github.com/pzhlkj6612) +- **samplefocus**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/46f4c80bc363ee8116c33d37f65202e6c3470954) ([#10947](https://github.com/yt-dlp/yt-dlp/issues/10947)) by [seproDev](https://github.com/seproDev) +- **screenrec**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/36f9e602ad55679764bc75a4f67f7562b1d6adcf) ([#10917](https://github.com/yt-dlp/yt-dlp/issues/10917)) by [naglis](https://github.com/naglis) +- **sen**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/41a241ca6ffb95b3d9aaf4f42106ca8cba9af1a6) ([#10952](https://github.com/yt-dlp/yt-dlp/issues/10952)) by [seproDev](https://github.com/seproDev) +- **servus**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/300c91274f7ea5b1b0528fc5ee11cf1a61d4079e) ([#10944](https://github.com/yt-dlp/yt-dlp/issues/10944)) by [seproDev](https://github.com/seproDev) +- **snapchatspotlight**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/b37417e4f934fd8909788b493d017777155b0ae5) ([#11030](https://github.com/yt-dlp/yt-dlp/issues/11030)) by [seproDev](https://github.com/seproDev) +- **svtpage**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/5a8a05aebb49693e78e1123015837ed5e961ff76) ([#11010](https://github.com/yt-dlp/yt-dlp/issues/11010)) by [diman8](https://github.com/diman8) +- **tenplay**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/d8d473002b654ab0e7b97ead869f58b4361eeae1) ([#10928](https://github.com/yt-dlp/yt-dlp/issues/10928)) by [aarubui](https://github.com/aarubui) +- **tiktok**: [Fix web formats extraction](https://github.com/yt-dlp/yt-dlp/commit/3ad0b7f422d547204df687b6d0b2d9110fff3990) ([#11074](https://github.com/yt-dlp/yt-dlp/issues/11074)) by [bashonly](https://github.com/bashonly) +- **twitter**: spaces: [Support video spaces](https://github.com/yt-dlp/yt-dlp/commit/bef1d4d6fc9493fda7f75e2289c07c507d10092f) ([#10789](https://github.com/yt-dlp/yt-dlp/issues/10789)) by [bashonly](https://github.com/bashonly) +- **vidflex**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/e978c312d6550a6ae4c9df18001afb1b420cb72f) ([#10002](https://github.com/yt-dlp/yt-dlp/issues/10002)) by [pzhlkj6612](https://github.com/pzhlkj6612) +- **vimeo** + - [Always try to extract original format](https://github.com/yt-dlp/yt-dlp/commit/4115c24d157c5b5f63089d75c4e0f51d1f8b4489) ([#10721](https://github.com/yt-dlp/yt-dlp/issues/10721)) by [bashonly](https://github.com/bashonly) (With fixes in [e8e6a98](https://github.com/yt-dlp/yt-dlp/commit/e8e6a982a1b659eed434d225d7922f632bac6568) by [seproDev](https://github.com/seproDev)) + - [Fix HLS audio format sorting](https://github.com/yt-dlp/yt-dlp/commit/a1b4ac2b8ed8e6eaa56044d439f1e0d00c2ba218) ([#11082](https://github.com/yt-dlp/yt-dlp/issues/11082)) by [fireattack](https://github.com/fireattack) +- **watchespn**: [Improve auth support](https://github.com/yt-dlp/yt-dlp/commit/7adff8caf152dcf96d03aff69ed8545c0a63567c) ([#10910](https://github.com/yt-dlp/yt-dlp/issues/10910)) by [ischmidt20](https://github.com/ischmidt20) +- **wistia**: [Support password-protected videos](https://github.com/yt-dlp/yt-dlp/commit/9f5c9a90898c5a1e672922d9cd799716c73cee34) ([#11100](https://github.com/yt-dlp/yt-dlp/issues/11100)) by [bashonly](https://github.com/bashonly) +- **ximalaya**: [Add VIP support](https://github.com/yt-dlp/yt-dlp/commit/3dfd720d098b4d49d69cfc77e6376f22bcd90934) ([#10832](https://github.com/yt-dlp/yt-dlp/issues/10832)) by [seproDev](https://github.com/seproDev), [xingchensong](https://github.com/xingchensong) +- **xinpianchang**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/3aa0156e05662923d130ddbc1c82596e38c01a00) ([#10950](https://github.com/yt-dlp/yt-dlp/issues/10950)) by [seproDev](https://github.com/seproDev) +- **yleareena**: [Support podcasts](https://github.com/yt-dlp/yt-dlp/commit/48d629d461e05b1b19f5e53dc959bb9ebe95da42) ([#11104](https://github.com/yt-dlp/yt-dlp/issues/11104)) by [bashonly](https://github.com/bashonly) +- **youtube** + - [Add `po_token`, `visitor_data`, `data_sync_id` extractor args](https://github.com/yt-dlp/yt-dlp/commit/3a3bd00037e9908e87da4fa9f2ad772aa34dc60e) ([#10648](https://github.com/yt-dlp/yt-dlp/issues/10648)) by [bashonly](https://github.com/bashonly), [coletdjnz](https://github.com/coletdjnz), [seproDev](https://github.com/seproDev) (With fixes in [fa2be9a](https://github.com/yt-dlp/yt-dlp/commit/fa2be9a7c63babede07480151363e54eee5702bd) by [bashonly](https://github.com/bashonly)) + - [Support excluding `player_client`s in extractor-arg](https://github.com/yt-dlp/yt-dlp/commit/49f3741a820ed142f6866317c2e7d247b130960e) ([#10710](https://github.com/yt-dlp/yt-dlp/issues/10710)) by [bashonly](https://github.com/bashonly) + - clip: [Prioritize `https` formats](https://github.com/yt-dlp/yt-dlp/commit/1d84b780cf33a1d84756825ac23f990a905703df) ([#11102](https://github.com/yt-dlp/yt-dlp/issues/11102)) by [bashonly](https://github.com/bashonly) + - tab: [Fix shorts tab extraction](https://github.com/yt-dlp/yt-dlp/commit/9431777b4c37129a6093080c77ca59960afbb9d7) ([#10938](https://github.com/yt-dlp/yt-dlp/issues/10938)) by [seproDev](https://github.com/seproDev) + +#### Networking changes +- [Fix handler not being added to RequestError](https://github.com/yt-dlp/yt-dlp/commit/d1c4d88b2d912e8da5e76db455562ca63b1af690) ([#10955](https://github.com/yt-dlp/yt-dlp/issues/10955)) by [coletdjnz](https://github.com/coletdjnz) +- [Pin `curl-cffi` version to < 0.7.2](https://github.com/yt-dlp/yt-dlp/commit/5bb1aa04dafce13ba9de707ea53169fab58b5207) ([#11092](https://github.com/yt-dlp/yt-dlp/issues/11092)) by [bashonly](https://github.com/bashonly) +- **Request Handler**: websockets: [Upgrade websockets to 13.0](https://github.com/yt-dlp/yt-dlp/commit/6f9e6537434562d513d0c9b68ced8a61ade94a64) ([#10815](https://github.com/yt-dlp/yt-dlp/issues/10815)) by [coletdjnz](https://github.com/coletdjnz) + +#### Misc. changes +- **build** + - [Bump PyInstaller version pin to `>=6.10.0`](https://github.com/yt-dlp/yt-dlp/commit/fb8b7f226d251e521a89b23c415e249e5b788e5c) ([#10709](https://github.com/yt-dlp/yt-dlp/issues/10709)) by [bashonly](https://github.com/bashonly) + - [Pin `delocate` version for `macos`](https://github.com/yt-dlp/yt-dlp/commit/7e41628ff523b3fe373b0981a5db441358980dab) ([#10901](https://github.com/yt-dlp/yt-dlp/issues/10901)) by [bashonly](https://github.com/bashonly) +- **ci** + - [Add comment sanitization workflow](https://github.com/yt-dlp/yt-dlp/commit/b6200bdcf3a9415ae36859188f9a57e3e461c696) ([#10915](https://github.com/yt-dlp/yt-dlp/issues/10915)) by [bashonly](https://github.com/bashonly), [Grub4K](https://github.com/Grub4K) + - [Add issue tracker anti-spam protection](https://github.com/yt-dlp/yt-dlp/commit/ad9a8115aa29a1a95c961b16fcf129a228d98f50) ([#10861](https://github.com/yt-dlp/yt-dlp/issues/10861)) by [bashonly](https://github.com/bashonly) +- **cleanup**: Miscellaneous: [c6387ab](https://github.com/yt-dlp/yt-dlp/commit/c6387abc1af9842bb0541288a5610abba9b1ab51) by [bashonly](https://github.com/bashonly), [Codenade](https://github.com/Codenade), [coletdjnz](https://github.com/coletdjnz), [grqz](https://github.com/grqz), [Grub4K](https://github.com/Grub4K), [pzhlkj6612](https://github.com/pzhlkj6612), [seproDev](https://github.com/seproDev) + ### 2024.08.06 #### Core changes diff --git a/supportedsites.md b/supportedsites.md index e3bbe03ec..e23d395fd 100644 --- a/supportedsites.md +++ b/supportedsites.md @@ -143,6 +143,7 @@ - **BBVTV**: [*bbvtv*](## "netrc machine") - **BBVTVLive**: [*bbvtv*](## "netrc machine") - **BBVTVRecordings**: [*bbvtv*](## "netrc machine") + - **BeaconTv** - **BeatBumpPlaylist** - **BeatBumpVideo** - **Beatport** @@ -505,6 +506,7 @@ - **gem.cbc.ca:playlist** - **Genius** - **GeniusLyrics** + - **Germanupa**: germanupa.de - **GetCourseRu**: [*getcourseru*](## "netrc machine") - **GetCourseRuPlayer** - **Gettr** @@ -580,6 +582,7 @@ - **HungamaAlbumPlaylist** - **HungamaSong** - **huya:live**: huya.com + - **huya:video**: 虎牙视频 - **Hypem** - **Hytale** - **Icareus** @@ -660,6 +663,7 @@ - **kick:vod** - **Kicker** - **KickStarter** + - **Kika**: KiKA.de - **kinja:embed** - **KinoPoisk** - **Kommunetv** @@ -722,7 +726,6 @@ - **livestream:original** - **Livestreamfails** - **Lnk** - - **LnkGo** - **loc**: Library of Congress - **loom** - **loom:folder** @@ -756,7 +759,7 @@ - **Masters** - **MatchTV** - **MBN**: mbn.co.kr (매일방송) - - **MDR**: MDR.DE and KiKA + - **MDR**: MDR.DE - **MedalTV** - **media.ccc.de** - **media.ccc.de:lists** @@ -811,6 +814,7 @@ - **MNetTVLive**: [*mnettv*](## "netrc machine") - **MNetTVRecordings**: [*mnettv*](## "netrc machine") - **MochaVideo** + - **Mojevideo**: mojevideo.sk - **Mojvideo** - **Monstercat** - **MonsterSirenHypergryphMusic** @@ -1285,12 +1289,14 @@ - **Screencast** - **Screencastify** - **ScreencastOMatic** + - **ScreenRec** - **ScrippsNetworks** - **scrippsnetworks:watch** - **Scrolller** - **SCTE**: [*scte*](## "netrc machine") (**Currently broken**) - **SCTECourse**: [*scte*](## "netrc machine") (**Currently broken**) - **sejm** + - **Sen** - **SenalColombiaLive**: (**Currently broken**) - **SenateGov** - **SenateISVP** @@ -1327,6 +1333,7 @@ - **SlidesLive** - **Slutload** - **Smotrim** + - **SnapchatSpotlight** - **Snotr** - **Sohu** - **SohuV** @@ -1608,6 +1615,7 @@ - **videomore:season** - **videomore:video** - **VideoPress** + - **Vidflex** - **Vidio**: [*vidio*](## "netrc machine") - **VidioLive**: [*vidio*](## "netrc machine") - **VidioPremier**: [*vidio*](## "netrc machine") @@ -1736,7 +1744,7 @@ - **XiaoHongShu**: 小红书 - **ximalaya**: 喜马拉雅FM - **ximalaya:album**: 喜马拉雅FM 专辑 - - **xinpianchang**: xinpianchang.com (**Currently broken**) + - **Xinpianchang**: 新片场 - **XMinus**: (**Currently broken**) - **XNXX** - **Xstream** diff --git a/yt_dlp/version.py b/yt_dlp/version.py index 6633a11b9..76b8bf0ee 100644 --- a/yt_dlp/version.py +++ b/yt_dlp/version.py @@ -1,8 +1,8 @@ # Autogenerated by devscripts/update-version.py -__version__ = '2024.08.06' +__version__ = '2024.09.27' -RELEASE_GIT_HEAD = '4d9231208332d4c32364b8cd814bff8b20232cae' +RELEASE_GIT_HEAD = 'c6387abc1af9842bb0541288a5610abba9b1ab51' VARIANT = None @@ -12,4 +12,4 @@ CHANNEL = 'stable' ORIGIN = 'yt-dlp/yt-dlp' -_pkg_version = '2024.08.06' +_pkg_version = '2024.09.27' From 6328e2e67a4e126e08af382e6a387073082d5c5f Mon Sep 17 00:00:00 2001 From: Corey Wright Date: Sun, 29 Sep 2024 16:03:39 -0500 Subject: [PATCH 052/154] [ie/ApplePodcasts] Fix extractor (#10903) Closes #10809 Authored by: coreywright --- yt_dlp/extractor/applepodcasts.py | 78 ++++++++++++++----------------- yt_dlp/extractor/common.py | 2 +- 2 files changed, 36 insertions(+), 44 deletions(-) diff --git a/yt_dlp/extractor/applepodcasts.py b/yt_dlp/extractor/applepodcasts.py index bd301e904..b99d24e0e 100644 --- a/yt_dlp/extractor/applepodcasts.py +++ b/yt_dlp/extractor/applepodcasts.py @@ -1,27 +1,42 @@ from .common import InfoExtractor from ..utils import ( - clean_html, clean_podcast_url, - get_element_by_class, int_or_none, parse_iso8601, - try_get, ) +from ..utils.traversal import traverse_obj class ApplePodcastsIE(InfoExtractor): _VALID_URL = r'https?://podcasts\.apple\.com/(?:[^/]+/)?podcast(?:/[^/]+){1,2}.*?\bi=(?P\d+)' _TESTS = [{ + 'url': 'https://podcasts.apple.com/us/podcast/ferreck-dawn-to-the-break-of-dawn-117/id1625658232?i=1000665010654', + 'md5': '82cc219b8cc1dcf8bfc5a5e99b23b172', + 'info_dict': { + 'id': '1000665010654', + 'ext': 'mp3', + 'title': 'Ferreck Dawn - To The Break of Dawn 117', + 'episode': 'Ferreck Dawn - To The Break of Dawn 117', + 'description': 'md5:1fc571102f79dbd0a77bfd71ffda23bc', + 'upload_date': '20240812', + 'timestamp': 1723449600, + 'duration': 3596, + 'series': 'Ferreck Dawn - To The Break of Dawn', + 'thumbnail': 're:.+[.](png|jpe?g|webp)', + }, + }, { 'url': 'https://podcasts.apple.com/us/podcast/207-whitney-webb-returns/id1135137367?i=1000482637777', - 'md5': '41dc31cd650143e530d9423b6b5a344f', + 'md5': 'baf8a6b8b8aa6062dbb4639ed73d0052', 'info_dict': { 'id': '1000482637777', 'ext': 'mp3', 'title': '207 - Whitney Webb Returns', + 'episode': '207 - Whitney Webb Returns', + 'episode_number': 207, 'description': 'md5:75ef4316031df7b41ced4e7b987f79c6', 'upload_date': '20200705', 'timestamp': 1593932400, - 'duration': 6454, + 'duration': 5369, 'series': 'The Tim Dillon Show', 'thumbnail': 're:.+[.](png|jpe?g|webp)', }, @@ -39,47 +54,24 @@ class ApplePodcastsIE(InfoExtractor): def _real_extract(self, url): episode_id = self._match_id(url) webpage = self._download_webpage(url, episode_id) - episode_data = {} - ember_data = {} - # new page type 2021-11 - amp_data = self._parse_json(self._search_regex( - r'(?s)id="shoebox-media-api-cache-amp-podcasts"[^>]*>\s*({.+?})\s*<', - webpage, 'AMP data', default='{}'), episode_id, fatal=False) or {} - amp_data = try_get(amp_data, - lambda a: self._parse_json( - next(a[x] for x in iter(a) if episode_id in x), - episode_id), - dict) or {} - amp_data = amp_data.get('d') or [] - episode_data = try_get( - amp_data, - lambda a: next(x for x in a - if x['type'] == 'podcast-episodes' and x['id'] == episode_id), - dict) - if not episode_data: - # try pre 2021-11 page type: TODO: consider deleting if no longer used - ember_data = self._parse_json(self._search_regex( - r'(?s)id="shoebox-ember-data-store"[^>]*>\s*({.+?})\s*<', - webpage, 'ember data'), episode_id) or {} - ember_data = ember_data.get(episode_id) or ember_data - episode_data = try_get(ember_data, lambda x: x['data'], dict) - episode = episode_data['attributes'] - description = episode.get('description') or {} - - series = None - for inc in (amp_data or ember_data.get('included') or []): - if inc.get('type') == 'media/podcast': - series = try_get(inc, lambda x: x['attributes']['name']) - series = series or clean_html(get_element_by_class('podcast-header__identity', webpage)) + server_data = self._search_json( + r'', webpage), + (..., {js_to_json}, {json.loads}, ..., {self._find_json}, ...)) + meta = traverse_obj(nextjs_data, ( + ..., lambda _, v: v['meta']['path'] == urllib.parse.urlparse(url).path, 'meta', any)) + + video_id = meta['uuid'] + info_dict = traverse_obj(meta, { + 'title': ('title', {str}), + 'description': ('description', {str.strip}), + }) + + if traverse_obj(meta, ('program', 'subtype')) != 'movie': + for season_data in traverse_obj(nextjs_data, (..., 'children', ..., 'playlists', ...)): + episode_data = traverse_obj( + season_data, ('videos', lambda _, v: v['videoId'] == video_id, any)) + if not episode_data: + continue + + episode_title = traverse_obj( + episode_data, 'contextualTitle', 'episodeTitle', expected_type=str) + info_dict.update({ + 'title': episode_title or info_dict.get('title'), + 'series': remove_end(info_dict.get('title'), f' - {episode_title}'), + 'season_number': traverse_obj(season_data, ('season', {int_or_none})), + 'episode_number': traverse_obj(episode_data, ('episodeNumber', {int_or_none})), + }) + break api = self._download_json( f'https://api.goplay.be/web/v1/videos/long-form/{video_id}', From a9f85670d03ab993dc589f21a9ffffcad61392d5 Mon Sep 17 00:00:00 2001 From: manav_chaudhary <100396248+manavchaudhary1@users.noreply.github.com> Date: Tue, 12 Nov 2024 04:11:56 +0530 Subject: [PATCH 148/154] [ie/Chaturbate] Support alternate domains (#10595) Closes #10594 Authored by: manavchaudhary1 --- yt_dlp/extractor/chaturbate.py | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/yt_dlp/extractor/chaturbate.py b/yt_dlp/extractor/chaturbate.py index b49f741ef..864d61f9c 100644 --- a/yt_dlp/extractor/chaturbate.py +++ b/yt_dlp/extractor/chaturbate.py @@ -9,7 +9,7 @@ from ..utils import ( class ChaturbateIE(InfoExtractor): - _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?:fullvideo/?\?.*?\bb=)?(?P[^/?&#]+)' + _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.(?Pcom|eu|global)/(?:fullvideo/?\?.*?\bb=)?(?P[^/?&#]+)' _TESTS = [{ 'url': 'https://www.chaturbate.com/siswet19/', 'info_dict': { @@ -29,15 +29,24 @@ class ChaturbateIE(InfoExtractor): }, { 'url': 'https://en.chaturbate.com/siswet19/', 'only_matching': True, + }, { + 'url': 'https://chaturbate.eu/siswet19/', + 'only_matching': True, + }, { + 'url': 'https://chaturbate.eu/fullvideo/?b=caylin', + 'only_matching': True, + }, { + 'url': 'https://chaturbate.global/siswet19/', + 'only_matching': True, }] _ROOM_OFFLINE = 'Room is currently offline' def _real_extract(self, url): - video_id = self._match_id(url) + video_id, tld = self._match_valid_url(url).group('id', 'tld') webpage = self._download_webpage( - f'https://chaturbate.com/{video_id}/', video_id, + f'https://chaturbate.{tld}/{video_id}/', video_id, headers=self.geo_verification_headers()) found_m3u8_urls = [] From bacc31b05a04181b63100c481565256b14813a5e Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Tue, 12 Nov 2024 23:23:10 +0000 Subject: [PATCH 149/154] [ie/facebook] Fix formats extraction (#11513) Closes #11497 Authored by: bashonly --- yt_dlp/extractor/facebook.py | 35 ++++++++++++++++++++++++++++++----- 1 file changed, 30 insertions(+), 5 deletions(-) diff --git a/yt_dlp/extractor/facebook.py b/yt_dlp/extractor/facebook.py index 2bcb5a841..91e2f3489 100644 --- a/yt_dlp/extractor/facebook.py +++ b/yt_dlp/extractor/facebook.py @@ -563,13 +563,13 @@ class FacebookIE(InfoExtractor): return extract_video_data(try_get( js_data, lambda x: x['jsmods']['instances'], list) or []) - def extract_dash_manifest(video, formats): + def extract_dash_manifest(vid_data, formats, mpd_url=None): dash_manifest = traverse_obj( - video, 'dash_manifest', 'playlist', 'dash_manifest_xml_string', expected_type=str) + vid_data, 'dash_manifest', 'playlist', 'dash_manifest_xml_string', 'manifest_xml', expected_type=str) if dash_manifest: formats.extend(self._parse_mpd_formats( compat_etree_fromstring(urllib.parse.unquote_plus(dash_manifest)), - mpd_url=url_or_none(video.get('dash_manifest_url')))) + mpd_url=url_or_none(video.get('dash_manifest_url')) or mpd_url)) def process_formats(info): # Downloads with browser's User-Agent are rate limited. Working around @@ -619,9 +619,12 @@ class FacebookIE(InfoExtractor): video = video['creation_story'] video['owner'] = traverse_obj(video, ('short_form_video_context', 'video_owner')) video.update(reel_info) - fmt_data = traverse_obj(video, ('videoDeliveryLegacyFields', {dict})) or video + formats = [] q = qualities(['sd', 'hd']) + + # Legacy formats extraction + fmt_data = traverse_obj(video, ('videoDeliveryLegacyFields', {dict})) or video for key, format_id in (('playable_url', 'sd'), ('playable_url_quality_hd', 'hd'), ('playable_url_dash', ''), ('browser_native_hd_url', 'hd'), ('browser_native_sd_url', 'sd')): @@ -629,7 +632,7 @@ class FacebookIE(InfoExtractor): if not playable_url: continue if determine_ext(playable_url) == 'mpd': - formats.extend(self._extract_mpd_formats(playable_url, video_id)) + formats.extend(self._extract_mpd_formats(playable_url, video_id, fatal=False)) else: formats.append({ 'format_id': format_id, @@ -638,6 +641,28 @@ class FacebookIE(InfoExtractor): 'url': playable_url, }) extract_dash_manifest(fmt_data, formats) + + # New videoDeliveryResponse formats extraction + fmt_data = traverse_obj(video, ('videoDeliveryResponseFragment', 'videoDeliveryResponseResult')) + mpd_urls = traverse_obj(fmt_data, ('dash_manifest_urls', ..., 'manifest_url', {url_or_none})) + dash_manifests = traverse_obj(fmt_data, ('dash_manifests', lambda _, v: v['manifest_xml'])) + for idx, dash_manifest in enumerate(dash_manifests): + extract_dash_manifest(dash_manifest, formats, mpd_url=traverse_obj(mpd_urls, idx)) + if not dash_manifests: + # Only extract from MPD URLs if the manifests are not already provided + for mpd_url in mpd_urls: + formats.extend(self._extract_mpd_formats(mpd_url, video_id, fatal=False)) + for prog_fmt in traverse_obj(fmt_data, ('progressive_urls', lambda _, v: v['progressive_url'])): + format_id = traverse_obj(prog_fmt, ('metadata', 'quality', {str.lower})) + formats.append({ + 'format_id': format_id, + # sd, hd formats w/o resolution info should be deprioritized below DASH + 'quality': q(format_id) - 3, + 'url': prog_fmt['progressive_url'], + }) + for m3u8_url in traverse_obj(fmt_data, ('hls_playlist_urls', ..., 'hls_playlist_url', {url_or_none})): + formats.extend(self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', fatal=False, m3u8_id='hls')) + if not formats: # Do not append false positive entry w/o any formats return From f2a4983df7a64c4e93b56f79dbd16a781bd90206 Mon Sep 17 00:00:00 2001 From: Jackson Humphrey Date: Tue, 12 Nov 2024 17:26:18 -0600 Subject: [PATCH 150/154] [ie/archive.org] Fix comments extraction (#11527) Closes #11526 Authored by: jshumphrey --- yt_dlp/extractor/archiveorg.py | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/yt_dlp/extractor/archiveorg.py b/yt_dlp/extractor/archiveorg.py index f5a55efc4..2849d9fd5 100644 --- a/yt_dlp/extractor/archiveorg.py +++ b/yt_dlp/extractor/archiveorg.py @@ -205,6 +205,26 @@ class ArchiveOrgIE(InfoExtractor): }, }, ], + }, { + # The reviewbody is None for one of the reviews; just need to extract data without crashing + 'url': 'https://archive.org/details/gd95-04-02.sbd.11622.sbeok.shnf/gd95-04-02d1t04.shn', + 'info_dict': { + 'id': 'gd95-04-02.sbd.11622.sbeok.shnf/gd95-04-02d1t04.shn', + 'ext': 'mp3', + 'title': 'Stuck Inside of Mobile with the Memphis Blues Again', + 'creators': ['Grateful Dead'], + 'duration': 338.31, + 'track': 'Stuck Inside of Mobile with the Memphis Blues Again', + 'description': 'md5:764348a470b986f1217ffd38d6ac7b72', + 'display_id': 'gd95-04-02d1t04.shn', + 'location': 'Pyramid Arena', + 'uploader': 'jon@archive.org', + 'album': '1995-04-02 - Pyramid Arena', + 'upload_date': '20040519', + 'track_number': 4, + 'release_date': '19950402', + 'timestamp': 1084927901, + }, }] @staticmethod @@ -335,7 +355,7 @@ class ArchiveOrgIE(InfoExtractor): info['comments'].append({ 'id': review.get('review_id'), 'author': review.get('reviewer'), - 'text': str_or_none(review.get('reviewtitle'), '') + '\n\n' + review.get('reviewbody'), + 'text': join_nonempty('reviewtitle', 'reviewbody', from_dict=review, delim='\n\n'), 'timestamp': unified_timestamp(review.get('createdate')), 'parent': 'root'}) From 39d79c9b9cf23411d935910685c40aa1a2fdb409 Mon Sep 17 00:00:00 2001 From: Simon Sawicki Date: Fri, 15 Nov 2024 22:06:15 +0100 Subject: [PATCH 151/154] [utils] Fix `join_nonempty`, add `**kwargs` to `unpack` (#11559) Authored by: Grub4K --- test/test_traversal.py | 2 +- test/test_utils.py | 5 ----- yt_dlp/utils/_utils.py | 3 +-- yt_dlp/utils/traversal.py | 4 ++-- 4 files changed, 4 insertions(+), 10 deletions(-) diff --git a/test/test_traversal.py b/test/test_traversal.py index d48606e99..52ea19fab 100644 --- a/test/test_traversal.py +++ b/test/test_traversal.py @@ -525,7 +525,7 @@ class TestTraversalHelpers: def test_unpack(self): assert unpack(lambda *x: ''.join(map(str, x)))([1, 2, 3]) == '123' assert unpack(join_nonempty)([1, 2, 3]) == '1-2-3' - assert unpack(join_nonempty(delim=' '))([1, 2, 3]) == '1 2 3' + assert unpack(join_nonempty, delim=' ')([1, 2, 3]) == '1 2 3' with pytest.raises(TypeError): unpack(join_nonempty)() with pytest.raises(TypeError): diff --git a/test/test_utils.py b/test/test_utils.py index b5f35736b..835774a91 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -72,7 +72,6 @@ from yt_dlp.utils import ( intlist_to_bytes, iri_to_uri, is_html, - join_nonempty, js_to_json, limit_length, locked_file, @@ -2158,10 +2157,6 @@ Line 1 assert int_or_none(v=10) == 10, 'keyword passed positional should call function' assert int_or_none(scale=0.1)(10) == 100, 'call after partial application should call the function' - assert callable(join_nonempty(delim=', ')), 'varargs positional should apply partially' - assert callable(join_nonempty()), 'varargs positional should apply partially' - assert join_nonempty(None, delim=', ') == '', 'passed varargs should call the function' - if __name__ == '__main__': unittest.main() diff --git a/yt_dlp/utils/_utils.py b/yt_dlp/utils/_utils.py index b28bb555e..89c53c39e 100644 --- a/yt_dlp/utils/_utils.py +++ b/yt_dlp/utils/_utils.py @@ -216,7 +216,7 @@ def partial_application(func): sig = inspect.signature(func) required_args = [ param.name for param in sig.parameters.values() - if param.kind in (inspect.Parameter.POSITIONAL_ONLY, inspect.Parameter.POSITIONAL_OR_KEYWORD, inspect.Parameter.VAR_POSITIONAL) + if param.kind in (inspect.Parameter.POSITIONAL_ONLY, inspect.Parameter.POSITIONAL_OR_KEYWORD) if param.default is inspect.Parameter.empty ] @@ -4837,7 +4837,6 @@ def number_of_digits(number): return len('%d' % number) -@partial_application def join_nonempty(*values, delim='-', from_dict=None): if from_dict is not None: values = (traversal.traverse_obj(from_dict, variadic(v)) for v in values) diff --git a/yt_dlp/utils/traversal.py b/yt_dlp/utils/traversal.py index 361f239ba..6bb52050f 100644 --- a/yt_dlp/utils/traversal.py +++ b/yt_dlp/utils/traversal.py @@ -452,9 +452,9 @@ def trim_str(*, start=None, end=None): return trim -def unpack(func): +def unpack(func, **kwargs): @functools.wraps(func) - def inner(items, **kwargs): + def inner(items): return func(*items, **kwargs) return inner From c014fbcddcb4c8f79d914ac5bb526758b540ea33 Mon Sep 17 00:00:00 2001 From: Simon Sawicki Date: Fri, 15 Nov 2024 23:25:52 +0100 Subject: [PATCH 152/154] [utils] `subs_list_to_dict`: Add `lang` default parameter (#11508) Authored by: Grub4K --- test/test_traversal.py | 50 ++++++++++++++++++++++++++++++++++++++- yt_dlp/utils/traversal.py | 22 ++++++++++------- 2 files changed, 63 insertions(+), 9 deletions(-) diff --git a/test/test_traversal.py b/test/test_traversal.py index 52ea19fab..bc433029d 100644 --- a/test/test_traversal.py +++ b/test/test_traversal.py @@ -481,7 +481,7 @@ class TestTraversalHelpers: 'id': 'name', 'data': 'content', 'url': 'url', - }, all, {subs_list_to_dict}]) == { + }, all, {subs_list_to_dict(lang=None)}]) == { 'de': [{'url': 'https://example.com/subs/de.ass'}], 'en': [{'data': 'content'}], }, 'subs with mandatory items missing should be filtered' @@ -507,6 +507,54 @@ class TestTraversalHelpers: {'url': 'https://example.com/subs/en1', 'ext': 'ext'}, {'url': 'https://example.com/subs/en2', 'ext': 'ext'}, ]}, '`quality` key should sort subtitle list accordingly' + assert traverse_obj([ + {'name': 'de', 'url': 'https://example.com/subs/de.ass'}, + {'name': 'de'}, + {'name': 'en', 'content': 'content'}, + {'url': 'https://example.com/subs/en'}, + ], [..., { + 'id': 'name', + 'url': 'url', + 'data': 'content', + }, all, {subs_list_to_dict(lang='en')}]) == { + 'de': [{'url': 'https://example.com/subs/de.ass'}], + 'en': [ + {'data': 'content'}, + {'url': 'https://example.com/subs/en'}, + ], + }, 'optionally provided lang should be used if no id available' + assert traverse_obj([ + {'name': 1, 'url': 'https://example.com/subs/de1'}, + {'name': {}, 'url': 'https://example.com/subs/de2'}, + {'name': 'de', 'ext': 1, 'url': 'https://example.com/subs/de3'}, + {'name': 'de', 'ext': {}, 'url': 'https://example.com/subs/de4'}, + ], [..., { + 'id': 'name', + 'url': 'url', + 'ext': 'ext', + }, all, {subs_list_to_dict(lang=None)}]) == { + 'de': [ + {'url': 'https://example.com/subs/de3'}, + {'url': 'https://example.com/subs/de4'}, + ], + }, 'non str types should be ignored for id and ext' + assert traverse_obj([ + {'name': 1, 'url': 'https://example.com/subs/de1'}, + {'name': {}, 'url': 'https://example.com/subs/de2'}, + {'name': 'de', 'ext': 1, 'url': 'https://example.com/subs/de3'}, + {'name': 'de', 'ext': {}, 'url': 'https://example.com/subs/de4'}, + ], [..., { + 'id': 'name', + 'url': 'url', + 'ext': 'ext', + }, all, {subs_list_to_dict(lang='de')}]) == { + 'de': [ + {'url': 'https://example.com/subs/de1'}, + {'url': 'https://example.com/subs/de2'}, + {'url': 'https://example.com/subs/de3'}, + {'url': 'https://example.com/subs/de4'}, + ], + }, 'non str types should be replaced by default id' def test_trim_str(self): with pytest.raises(TypeError): diff --git a/yt_dlp/utils/traversal.py b/yt_dlp/utils/traversal.py index 6bb52050f..76b51f53d 100644 --- a/yt_dlp/utils/traversal.py +++ b/yt_dlp/utils/traversal.py @@ -332,14 +332,14 @@ class _RequiredError(ExtractorError): @typing.overload -def subs_list_to_dict(*, ext: str | None = None) -> collections.abc.Callable[[list[dict]], dict[str, list[dict]]]: ... +def subs_list_to_dict(*, lang: str | None = 'und', ext: str | None = None) -> collections.abc.Callable[[list[dict]], dict[str, list[dict]]]: ... @typing.overload -def subs_list_to_dict(subs: list[dict] | None, /, *, ext: str | None = None) -> dict[str, list[dict]]: ... +def subs_list_to_dict(subs: list[dict] | None, /, *, lang: str | None = 'und', ext: str | None = None) -> dict[str, list[dict]]: ... -def subs_list_to_dict(subs: list[dict] | None = None, /, *, ext=None): +def subs_list_to_dict(subs: list[dict] | None = None, /, *, lang='und', ext=None): """ Convert subtitles from a traversal into a subtitle dict. The path should have an `all` immediately before this function. @@ -352,7 +352,7 @@ def subs_list_to_dict(subs: list[dict] | None = None, /, *, ext=None): `quality` The sort order for each subtitle """ if subs is None: - return functools.partial(subs_list_to_dict, ext=ext) + return functools.partial(subs_list_to_dict, lang=lang, ext=ext) result = collections.defaultdict(list) @@ -360,10 +360,16 @@ def subs_list_to_dict(subs: list[dict] | None = None, /, *, ext=None): if not url_or_none(sub.get('url')) and not sub.get('data'): continue sub_id = sub.pop('id', None) - if sub_id is None: - continue - if ext is not None and not sub.get('ext'): - sub['ext'] = ext + if not isinstance(sub_id, str): + if not lang: + continue + sub_id = lang + sub_ext = sub.get('ext') + if not isinstance(sub_ext, str): + if not ext: + sub.pop('ext', None) + else: + sub['ext'] = ext result[sub_id].append(sub) result = dict(result) From eb64ae7d5def6df2aba74fb703e7f168fb299865 Mon Sep 17 00:00:00 2001 From: bashonly Date: Thu, 14 Nov 2024 16:08:50 -0600 Subject: [PATCH 153/154] [ie] Allow `ext` override for thumbnails (#11545) Authored by: bashonly --- yt_dlp/YoutubeDL.py | 4 +++- yt_dlp/extractor/common.py | 1 + 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/yt_dlp/YoutubeDL.py b/yt_dlp/YoutubeDL.py index 3186a999d..3130deda3 100644 --- a/yt_dlp/YoutubeDL.py +++ b/yt_dlp/YoutubeDL.py @@ -4381,7 +4381,9 @@ class YoutubeDL: return None for idx, t in list(enumerate(thumbnails))[::-1]: - thumb_ext = (f'{t["id"]}.' if multiple else '') + determine_ext(t['url'], 'jpg') + thumb_ext = t.get('ext') or determine_ext(t['url'], 'jpg') + if multiple: + thumb_ext = f'{t["id"]}.{thumb_ext}' thumb_display_id = f'{label} thumbnail {t["id"]}' thumb_filename = replace_extension(filename, thumb_ext, info_dict.get('ext')) thumb_filename_final = replace_extension(thumb_filename_base, thumb_ext, info_dict.get('ext')) diff --git a/yt_dlp/extractor/common.py b/yt_dlp/extractor/common.py index 01915acf2..23f6fc6c4 100644 --- a/yt_dlp/extractor/common.py +++ b/yt_dlp/extractor/common.py @@ -279,6 +279,7 @@ class InfoExtractor: thumbnails: A list of dictionaries, with the following entries: * "id" (optional, string) - Thumbnail format ID * "url" + * "ext" (optional, string) - actual image extension if not given in URL * "preference" (optional, int) - quality of the image * "width" (optional, int) * "height" (optional, int) From c699bafc5038b59c9afe8c2e69175fb66424c832 Mon Sep 17 00:00:00 2001 From: bashonly Date: Thu, 14 Nov 2024 16:09:11 -0600 Subject: [PATCH 154/154] [ie/soop] Fix thumbnail extraction (#11545) Closes #11537 Authored by: bashonly --- yt_dlp/extractor/afreecatv.py | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/yt_dlp/extractor/afreecatv.py b/yt_dlp/extractor/afreecatv.py index 6682a8981..572d1a389 100644 --- a/yt_dlp/extractor/afreecatv.py +++ b/yt_dlp/extractor/afreecatv.py @@ -66,6 +66,14 @@ class AfreecaTVBaseIE(InfoExtractor): extensions={'legacy_ssl': True}), display_id, 'Downloading API JSON', 'Unable to download API JSON') + @staticmethod + def _fixup_thumb(thumb_url): + if not url_or_none(thumb_url): + return None + # Core would determine_ext as 'php' from the url, so we need to provide the real ext + # See: https://github.com/yt-dlp/yt-dlp/issues/11537 + return [{'url': thumb_url, 'ext': 'jpg'}] + class AfreecaTVIE(AfreecaTVBaseIE): IE_NAME = 'soop' @@ -155,7 +163,7 @@ class AfreecaTVIE(AfreecaTVBaseIE): 'uploader': ('writer_nick', {str}), 'uploader_id': ('bj_id', {str}), 'duration': ('total_file_duration', {int_or_none(scale=1000)}), - 'thumbnail': ('thumb', {url_or_none}), + 'thumbnails': ('thumb', {self._fixup_thumb}), }) entries = [] @@ -226,8 +234,7 @@ class AfreecaTVCatchStoryIE(AfreecaTVBaseIE): return self.playlist_result(self._entries(data), video_id) - @staticmethod - def _entries(data): + def _entries(self, data): # 'files' is always a list with 1 element yield from traverse_obj(data, ( 'data', lambda _, v: v['story_type'] == 'catch', @@ -238,7 +245,7 @@ class AfreecaTVCatchStoryIE(AfreecaTVBaseIE): 'title': ('title', {str}), 'uploader': ('writer_nick', {str}), 'uploader_id': ('writer_id', {str}), - 'thumbnail': ('thumb', {url_or_none}), + 'thumbnails': ('thumb', {self._fixup_thumb}), 'timestamp': ('write_timestamp', {int_or_none}), }))