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 001/131] [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 002/131] [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 003/131] [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 004/131] [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 005/131] [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 006/131] [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 007/131] [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 008/131] [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 009/131] [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 010/131] [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 011/131] [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 012/131] [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 013/131] [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 014/131] [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 015/131] [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 016/131] [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 017/131] [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 018/131] [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 019/131] [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 020/131] [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 021/131] 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 022/131] [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 023/131] 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 024/131] [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 025/131] [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 026/131] 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 027/131] [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 028/131] 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 029/131] [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 125/131] [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 126/131] [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 127/131] [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 128/131] [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 129/131] [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 130/131] [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 131/131] [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}), }))