mirror/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp synced 2025-01-18 23:03:05 +01:00
Code Activity

Merge branch 'master' into wait-retries

Browse source
This commit is contained in:
Paul Storkman 2025-01-12 01:11:23 +01:00
commit 2b5c77c10a
26 changed files with 573 additions and 184 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
CONTRIBUTORS
View file

@ -707,3 +707,9 @@ Sakura286
SamDecrock
stratus-ss
subrat-lima
gitninja1234
jkruse
xiaomac
wesson09
Crypto90
MutantPiggieGolem1

79
Changelog.md
View file

@ -4,6 +4,85 @@
# To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master
-->
### 2024.12.23
#### Core changes
- [Don't sanitize filename on Unix when `--no-windows-filenames`](https://github.com/yt-dlp/yt-dlp/commit/6fc85f617a5850307fd5b258477070e6ee177796) ([#9591](https://github.com/yt-dlp/yt-dlp/issues/9591)) by [pukkandan](https://github.com/pukkandan)
- **update**
- [Check 64-bitness when upgrading ARM builds](https://github.com/yt-dlp/yt-dlp/commit/b91c3925c2059970daa801cb131c0c2f4f302e72) ([#11819](https://github.com/yt-dlp/yt-dlp/issues/11819)) by [bashonly](https://github.com/bashonly)
- [Fix endless update loop for `linux_exe` builds](https://github.com/yt-dlp/yt-dlp/commit/3d3ee458c1fe49dd5ebd7651a092119d23eb7000) ([#11827](https://github.com/yt-dlp/yt-dlp/issues/11827)) by [bashonly](https://github.com/bashonly)
#### Extractor changes
- **soundcloud**: [Various fixes](https://github.com/yt-dlp/yt-dlp/commit/d298693b1b266d198e8eeecb90ea17c4a031268f) ([#11820](https://github.com/yt-dlp/yt-dlp/issues/11820)) by [bashonly](https://github.com/bashonly)
- **youtube**
- [Add age-gate workaround for some embeddable videos](https://github.com/yt-dlp/yt-dlp/commit/09a6c687126f04e243fcb105a828787efddd1030) ([#11821](https://github.com/yt-dlp/yt-dlp/issues/11821)) by [bashonly](https://github.com/bashonly)
- [Fix `uploader_id` extraction](https://github.com/yt-dlp/yt-dlp/commit/1a8851b689763e5173b96f70f8a71df0e4a44b66) ([#11818](https://github.com/yt-dlp/yt-dlp/issues/11818)) by [bashonly](https://github.com/bashonly)
- [Player client maintenance](https://github.com/yt-dlp/yt-dlp/commit/65cf46cddd873fd229dbb0fc0689bca4c201c6b6) ([#11893](https://github.com/yt-dlp/yt-dlp/issues/11893)) by [bashonly](https://github.com/bashonly)
- [Skip iOS formats that require PO Token](https://github.com/yt-dlp/yt-dlp/commit/9f42e68a74f3f00b0253fe70763abd57cac4237b) ([#11890](https://github.com/yt-dlp/yt-dlp/issues/11890)) by [coletdjnz](https://github.com/coletdjnz)
### 2024.12.13
#### Extractor changes
- **patreon**: campaign: [Support /c/ URLs](https://github.com/yt-dlp/yt-dlp/commit/bc262bcad4d3683ceadf61a7eb87e233e72adef3) ([#11756](https://github.com/yt-dlp/yt-dlp/issues/11756)) by [bashonly](https://github.com/bashonly)
- **soundcloud**: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/f4d3e9e6dc25077b79849a31a2f67f93fdc01e62) ([#11777](https://github.com/yt-dlp/yt-dlp/issues/11777)) by [bashonly](https://github.com/bashonly)
- **youtube**
- [Fix `release_date` extraction](https://github.com/yt-dlp/yt-dlp/commit/d5e2a379f2adcb28bc48c7d9e90716d7278f89d2) ([#11759](https://github.com/yt-dlp/yt-dlp/issues/11759)) by [MutantPiggieGolem1](https://github.com/MutantPiggieGolem1)
- [Fix signature function extraction for `2f1832d2`](https://github.com/yt-dlp/yt-dlp/commit/5460cd91891bf613a2065e2fc278d9903c37a127) ([#11801](https://github.com/yt-dlp/yt-dlp/issues/11801)) by [bashonly](https://github.com/bashonly)
- [Prioritize original language over auto-dubbed audio](https://github.com/yt-dlp/yt-dlp/commit/dc3c4fddcc653989dae71fc563d82a308fc898cc) ([#11803](https://github.com/yt-dlp/yt-dlp/issues/11803)) by [bashonly](https://github.com/bashonly)
- search_url: [Fix playlist searches](https://github.com/yt-dlp/yt-dlp/commit/f6c73aad5f1a67544bea137ebd9d1e22e0e56567) ([#11782](https://github.com/yt-dlp/yt-dlp/issues/11782)) by [Crypto90](https://github.com/Crypto90)
#### Misc. changes
- **cleanup**: [Make more playlist entries lazy](https://github.com/yt-dlp/yt-dlp/commit/54216696261bc07cacd9a837c501d9e0b7fed09e) ([#11763](https://github.com/yt-dlp/yt-dlp/issues/11763)) by [seproDev](https://github.com/seproDev)
### 2024.12.06
#### Core changes
- **cookies**: [Add `--cookies-from-browser` support for MS Store Firefox](https://github.com/yt-dlp/yt-dlp/commit/354cb4026cf2191e1a130ec2a627b95cabfbc60a) ([#11731](https://github.com/yt-dlp/yt-dlp/issues/11731)) by [wesson09](https://github.com/wesson09)
#### Extractor changes
- **bilibili**: [Fix HD formats extraction](https://github.com/yt-dlp/yt-dlp/commit/fca3eb5f8be08d5fab2e18b45b7281a12e566725) ([#11734](https://github.com/yt-dlp/yt-dlp/issues/11734)) by [grqz](https://github.com/grqz)
- **soundcloud**: [Fix formats extraction](https://github.com/yt-dlp/yt-dlp/commit/2feb28028ee48f2185d2d95076e62accb09b9e2e) ([#11742](https://github.com/yt-dlp/yt-dlp/issues/11742)) by [bashonly](https://github.com/bashonly)
- **youtube**
- [Fix `n` sig extraction for player `3bb1f723`](https://github.com/yt-dlp/yt-dlp/commit/a95ee6d8803fca9157adecf63732ab58bf87fd88) ([#11750](https://github.com/yt-dlp/yt-dlp/issues/11750)) by [bashonly](https://github.com/bashonly) (With fixes in [4bd2655](https://github.com/yt-dlp/yt-dlp/commit/4bd2655398aed450456197a6767639114a24eac2))
- [Fix signature function extraction](https://github.com/yt-dlp/yt-dlp/commit/4c85ccd1366c88cf93982f8350f58eed17355981) ([#11751](https://github.com/yt-dlp/yt-dlp/issues/11751)) by [bashonly](https://github.com/bashonly)
- [Player client maintenance](https://github.com/yt-dlp/yt-dlp/commit/2e49c789d3eebc39af8910705d65a98bca0e4c4f) ([#11724](https://github.com/yt-dlp/yt-dlp/issues/11724)) by [bashonly](https://github.com/bashonly)
### 2024.12.03
#### Core changes
- [Add `playlist_webpage_url` field](https://github.com/yt-dlp/yt-dlp/commit/7d6c259a03bc4707a319e5e8c6eff0278707874b) ([#11613](https://github.com/yt-dlp/yt-dlp/issues/11613)) by [seproDev](https://github.com/seproDev)
#### Extractor changes
- [Handle fragmented formats in `_remove_duplicate_formats`](https://github.com/yt-dlp/yt-dlp/commit/e0500cbf796323551bbabe5b8ed8c75a511ba47a) ([#11637](https://github.com/yt-dlp/yt-dlp/issues/11637)) by [Grub4K](https://github.com/Grub4K)
- **bilibili**
- [Always try to extract HD formats](https://github.com/yt-dlp/yt-dlp/commit/dc1687648077c5bf64863b307ecc5ab7e029bd8d) ([#10559](https://github.com/yt-dlp/yt-dlp/issues/10559)) by [grqz](https://github.com/grqz)
- [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/239f5f36fe04603bec59c8b975f6a792f10246db) ([#11667](https://github.com/yt-dlp/yt-dlp/issues/11667)) by [grqz](https://github.com/grqz) (With fixes in [f05a1cd](https://github.com/yt-dlp/yt-dlp/commit/f05a1cd1492fc98dc8d80d2081d632a1879913d2) by [bashonly](https://github.com/bashonly), [grqz](https://github.com/grqz))
- [Fix subtitles and chapters extraction](https://github.com/yt-dlp/yt-dlp/commit/a13a336aa6f906812701abec8101b73b73db8ff7) ([#11708](https://github.com/yt-dlp/yt-dlp/issues/11708)) by [xiaomac](https://github.com/xiaomac)
- **chaturbate**: [Fix support for non-public streams](https://github.com/yt-dlp/yt-dlp/commit/4b5eec0aaa7c02627f27a386591b735b90e681a8) ([#11624](https://github.com/yt-dlp/yt-dlp/issues/11624)) by [jkruse](https://github.com/jkruse)
- **dacast**: [Fix HLS AES formats extraction](https://github.com/yt-dlp/yt-dlp/commit/0a0d80800b9350d1a4c4b18d82cfb77ffbc3c507) ([#11644](https://github.com/yt-dlp/yt-dlp/issues/11644)) by [bashonly](https://github.com/bashonly)
- **dropbox**: [Fix password-protected video extraction](https://github.com/yt-dlp/yt-dlp/commit/00dcde728635633eee969ad4d498b9f233c4a94e) ([#11636](https://github.com/yt-dlp/yt-dlp/issues/11636)) by [bashonly](https://github.com/bashonly)
- **duoplay**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/62cba8a1bedbfc0ddde7267ae57b72bf5f7ea7b1) ([#11588](https://github.com/yt-dlp/yt-dlp/issues/11588)) by [bashonly](https://github.com/bashonly), [glensc](https://github.com/glensc)
- **facebook**: [Support more groups URLs](https://github.com/yt-dlp/yt-dlp/commit/e0f1ae813b36e783e2348ba2a1566e12f5cd8f6e) ([#11576](https://github.com/yt-dlp/yt-dlp/issues/11576)) by [grqz](https://github.com/grqz)
- **instagram**: [Support `share` URLs](https://github.com/yt-dlp/yt-dlp/commit/360aed810ad85db950df586282d256516c98cd2d) ([#11677](https://github.com/yt-dlp/yt-dlp/issues/11677)) by [grqz](https://github.com/grqz)
- **microsoftembed**: [Make format extraction non fatal](https://github.com/yt-dlp/yt-dlp/commit/2bea7936323ca4b6f3b9b1fdd892566223e30efa) ([#11654](https://github.com/yt-dlp/yt-dlp/issues/11654)) by [seproDev](https://github.com/seproDev)
- **mitele**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/cd0f934604587ed793e9177f6a127e5dcf99a7dd) ([#11683](https://github.com/yt-dlp/yt-dlp/issues/11683)) by [DarkZeros](https://github.com/DarkZeros)
- **stripchat**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/16336c51d0848a6868a4fa04e749fa03548b4913) ([#11596](https://github.com/yt-dlp/yt-dlp/issues/11596)) by [gitninja1234](https://github.com/gitninja1234)
- **tiktok**: [Deprioritize animated thumbnails](https://github.com/yt-dlp/yt-dlp/commit/910ecc422930bca14e2abe4986f5f92359e3cea8) ([#11645](https://github.com/yt-dlp/yt-dlp/issues/11645)) by [bashonly](https://github.com/bashonly)
- **vk**: [Fix extractors](https://github.com/yt-dlp/yt-dlp/commit/c038a7b187ba24360f14134842a7a2cf897c33b1) ([#11715](https://github.com/yt-dlp/yt-dlp/issues/11715)) by [bashonly](https://github.com/bashonly)
- **youtube**
- [Adjust player clients for site changes](https://github.com/yt-dlp/yt-dlp/commit/0d146c1e36f467af30e87b7af651bdee67b73500) ([#11663](https://github.com/yt-dlp/yt-dlp/issues/11663)) by [bashonly](https://github.com/bashonly)
- tab: [Fix playlists tab extraction](https://github.com/yt-dlp/yt-dlp/commit/fe70f20aedf528fdee332131bc9b6710e54e6f10) ([#11615](https://github.com/yt-dlp/yt-dlp/issues/11615)) by [seproDev](https://github.com/seproDev)
#### Networking changes
- **Request Handler**: websockets: [Support websockets 14.0+](https://github.com/yt-dlp/yt-dlp/commit/c7316373c0a886f65a07a51e50ee147bb3294c85) ([#11616](https://github.com/yt-dlp/yt-dlp/issues/11616)) by [coletdjnz](https://github.com/coletdjnz)
#### Misc. changes
- **cleanup**
- [Bump ruff to 0.8.x](https://github.com/yt-dlp/yt-dlp/commit/d8fb3490863653182864d2a53522f350d67a9ff8) ([#11608](https://github.com/yt-dlp/yt-dlp/issues/11608)) by [seproDev](https://github.com/seproDev)
- Miscellaneous
- [ccf0a6b](https://github.com/yt-dlp/yt-dlp/commit/ccf0a6b86b7f68a75463804fe485ec240b8635f0) by [bashonly](https://github.com/bashonly), [pzhlkj6612](https://github.com/pzhlkj6612)
- [2b67ac3](https://github.com/yt-dlp/yt-dlp/commit/2b67ac300ac8b44368fb121637d1743cea8c5b6b) by [bashonly](https://github.com/bashonly), [seproDev](https://github.com/seproDev)
### 2024.11.18
#### Important changes

7
README.md
View file

@ -617,8 +617,7 @@ If you fork the project on GitHub, you can run your fork's [build workflow](.git
--no-restrict-filenames Allow Unicode characters, "&" and spaces in
filenames (default)
--windows-filenames Force filenames to be Windows-compatible
--no-windows-filenames Make filenames Windows-compatible only if
using Windows (default)
--no-windows-filenames Sanitize filenames only minimally
--trim-filenames LENGTH Limit the filename length (excluding
extension) to the specified number of
characters
@ -1780,7 +1779,7 @@ The following extractors use this feature:
* `comment_sort`: `top` or `new` (default) - choose comment sorting mode (on YouTube's side)
* `max_comments`: Limit the amount of comments to gather. Comma-separated list of integers representing `max-comments,max-parents,max-replies,max-replies-per-thread`. Default is `all,all,all,all`
* E.g. `all,all,1000,10` will get a maximum of 1000 replies total, with up to 10 replies per thread. `1000,all,100` will get a maximum of 1000 comments, with a maximum of 100 replies total
* `formats`: Change the types of formats to return. `dashy` (convert HTTP to DASH), `duplicate` (identical content but different URLs or protocol; includes `dashy`), `incomplete` (cannot be downloaded completely - live dash and post-live m3u8)
* `formats`: Change the types of formats to return. `dashy` (convert HTTP to DASH), `duplicate` (identical content but different URLs or protocol; includes `dashy`), `incomplete` (cannot be downloaded completely - live dash and post-live m3u8), `missing_pot` (include formats that require a PO Token but are missing one)
* `innertube_host`: Innertube API host to use for all API requests; e.g. `studio.youtube.com`, `youtubei.googleapis.com`. Note that cookies exported from one subdomain will not work on others
* `innertube_key`: Innertube API key to use for all API requests. By default, no API key is used
* `raise_incomplete_data`: `Incomplete Data Received` raises an error instead of reporting a warning
@ -1864,7 +1863,7 @@ The following extractors use this feature:
* `cdn`: One or more CDN IDs to use with the API call for stream URLs, e.g. `gcp_cdn`, `gs_cdn_pc_app`, `gs_cdn_mobile_web`, `gs_cdn_pc_web`
#### soundcloud
* `formats`: Formats to request from the API. Requested values should be in the format of `{protocol}_{extension}` (omitting the bitrate), e.g. `hls_opus,http_aac`. The `*` character functions as a wildcard, e.g. `*_mp3`, and can be passed by itself to request all formats. Known protocols include `http`, `hls` and `hls-aes`; known extensions include `aac`, `opus` and `mp3`. Original `download` formats are always extracted. Default is `http_aac,hls_aac,http_opus,hls_opus,http_mp3,hls_mp3`
* `formats`: Formats to request from the API. Requested values should be in the format of `{protocol}_{codec}`, e.g. `hls_opus,http_aac`. The `*` character functions as a wildcard, e.g. `*_mp3`, and can be passed by itself to request all formats. Known protocols include `http`, `hls` and `hls-aes`; known codecs include `aac`, `opus` and `mp3`. Original `download` formats are always extracted. Default is `http_aac,hls_aac,http_opus,hls_opus,http_mp3,hls_mp3`
#### orfon (orf:on)
* `prefer_segments_playlist`: Prefer a playlist of program segments instead of a single complete video when available. If individual segments are desired, use `--concat-playlist never --extractor-args "orfon:prefer_segments_playlist"`

7
test/test_YoutubeDL.py
View file

@ -761,6 +761,13 @@ class TestYoutubeDL(unittest.TestCase):
test('%(width)06d.%%(ext)s', 'NA.%(ext)s')
test('%%(width)06d.%(ext)s', '%(width)06d.mp4')
# Sanitization options
test('%(title3)s', (None, 'foo⧸bar⧹test'))
test('%(title5)s', (None, 'aei_A'), restrictfilenames=True)
test('%(title3)s', (None, 'foo_bar_test'), windowsfilenames=False, restrictfilenames=True)
if sys.platform != 'win32':
test('%(title3)s', (None, 'foo⧸bar\\test'), windowsfilenames=False)
# ID sanitization
test('%(id)s', '_abcd', info={'id': '_abcd'})
test('%(some_id)s', '_abcd', info={'some_id': '_abcd'})

25
test/test_youtube_signature.py
View file

@ -68,6 +68,16 @@ _SIG_TESTS = [
'2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
'AOq0QJ8wRAIgXmPlOPSBkkUs1bYFYlJCfe29xx8j7v1pDL2QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJoOySqa0',
),
(
'https://www.youtube.com/s/player/3bb1f723/player_ias.vflset/en_US/base.js',
'2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
'MyOSJXtKI3m-uME_jv7-pT12gOFC02RFkGoqWpzE0Cs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
),
(
'https://www.youtube.com/s/player/2f1832d2/player_ias.vflset/en_US/base.js',
'2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
'0QJ8wRAIgXmPlOPSBkkUs1bYFYlJCfe29xxAj7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJ2OySqa0q',
),
]
_NSIG_TESTS = [
@ -183,6 +193,14 @@ _NSIG_TESTS = [
'https://www.youtube.com/s/player/b12cc44b/player_ias.vflset/en_US/base.js',
'keLa5R2U00sR9SQK', 'N1OGyujjEwMnLw',
),
(
'https://www.youtube.com/s/player/3bb1f723/player_ias.vflset/en_US/base.js',
'gK15nzVyaXE9RsMP3z', 'ZFFWFLPWx9DEgQ',
),
(
'https://www.youtube.com/s/player/2f1832d2/player_ias.vflset/en_US/base.js',
'YWt1qdbe8SAfkoPHW5d', 'RrRjWQOJmBiP',
),
]
@ -254,8 +272,11 @@ def signature(jscode, sig_input):
def n_sig(jscode, sig_input):
funcname = YoutubeIE(FakeYDL())._extract_n_function_name(jscode)
return JSInterpreter(jscode).call_function(funcname, sig_input)
ie = YoutubeIE(FakeYDL())
funcname = ie._extract_n_function_name(jscode)
jsi = JSInterpreter(jscode)
func = jsi.extract_function_from_code(*ie._fixup_n_function_code(*jsi.extract_function_code(funcname)))
return func([sig_input])
make_sig_test = t_factory(

26
yt_dlp/YoutubeDL.py
View file

@ -267,7 +267,9 @@ class YoutubeDL:
outtmpl_na_placeholder: Placeholder for unavailable meta fields.
restrictfilenames: Do not allow "&" and spaces in file names
trim_file_name: Limit length of filename (extension excluded)
windowsfilenames: Force the filenames to be windows compatible
windowsfilenames: True: Force filenames to be Windows compatible
False: Sanitize filenames only minimally
This option has no effect when running on Windows
ignoreerrors: Do not stop on download/postprocessing errors.
Can be 'only_download' to ignore only download errors.
Default is 'only_download' for CLI, but False for API
@ -1193,8 +1195,7 @@ class YoutubeDL:
def prepare_outtmpl(self, outtmpl, info_dict, sanitize=False):
""" Make the outtmpl and info_dict suitable for substitution: ydl.escape_outtmpl(outtmpl) % info_dict
@param sanitize Whether to sanitize the output as a filename.
For backward compatibility, a function can also be passed
@param sanitize Whether to sanitize the output as a filename
"""
info_dict.setdefault('epoch', int(time.time())) # keep epoch consistent once set
@ -1310,14 +1311,23 @@ class YoutubeDL:
na = self.params.get('outtmpl_na_placeholder', 'NA')
def filename_sanitizer(key, value, restricted=self.params.get('restrictfilenames')):
def filename_sanitizer(key, value, restricted):
return sanitize_filename(str(value), restricted=restricted, is_id=(
bool(re.search(r'(^|[_.])id(\.|$)', key))
if 'filename-sanitization' in self.params['compat_opts']
else NO_DEFAULT))
sanitizer = sanitize if callable(sanitize) else filename_sanitizer
sanitize = bool(sanitize)
if callable(sanitize):
self.deprecation_warning('Passing a callable "sanitize" to YoutubeDL.prepare_outtmpl is deprecated')
elif not sanitize:
pass
elif (sys.platform != 'win32' and not self.params.get('restrictfilenames')
and self.params.get('windowsfilenames') is False):
def sanitize(key, value):
return str(value).replace('/', '\u29F8').replace('\0', '')
else:
def sanitize(key, value):
return filename_sanitizer(key, value, restricted=self.params.get('restrictfilenames'))
def _dumpjson_default(obj):
if isinstance(obj, (set, LazyList)):
@ -1400,13 +1410,13 @@ class YoutubeDL:
if sanitize:
# If value is an object, sanitize might convert it to a string
# So we convert it to repr first
# So we manually convert it before sanitizing
if fmt[-1] == 'r':
value, fmt = repr(value), str_fmt
elif fmt[-1] == 'a':
value, fmt = ascii(value), str_fmt
if fmt[-1] in 'csra':
value = sanitizer(last_field, value)
value = sanitize(last_field, value)
key = '{}\0{}'.format(key.replace('%', '%\0'), outer_mobj.group('format'))
TMPL_DICT[key] = value

5
yt_dlp/__init__.py
View file

@ -231,9 +231,11 @@ def validate_options(opts):
elif value in ('inf', 'infinite'):
return float('inf')
try:
return int(value)
int_value = int(value)
except (TypeError, ValueError):
validate(False, f'{name} retry count', value)
validate_positive(f'{name} retry count', int_value)
return int_value
def parse_range_with_arg(name, arg_name, value,
parse_limits=parse_duration, parse_arg=parse_retries):
@ -253,7 +255,6 @@ def validate_options(opts):
if opts.wait_for_video is not None:
min_wait, max_wait, wait_retries = parse_range_with_arg(
'time range to wait for video', 'waiting', opts.wait_for_video)
validate_positive('waiting retry count', wait_retries)
opts.wait_for_video = (min_wait, max_wait, wait_retries)
# Format sort

5
yt_dlp/cookies.py
View file

@ -195,7 +195,10 @@ def _extract_firefox_cookies(profile, container, logger):
def _firefox_browser_dirs():
if sys.platform in ('cygwin', 'win32'):
yield os.path.expandvars(R'%APPDATA%\Mozilla\Firefox\Profiles')
yield from map(os.path.expandvars, (
R'%APPDATA%\Mozilla\Firefox\Profiles',
R'%LOCALAPPDATA%\Packages\Mozilla.Firefox_n80bbvh6b1yt2\LocalCache\Roaming\Mozilla\Firefox\Profiles',
))
elif sys.platform == 'darwin':
yield os.path.expanduser('~/Library/Application Support/Firefox/Profiles')

1
yt_dlp/extractor/_extractors.py
View file

@ -1551,6 +1551,7 @@ from .pluralsight import (
PluralsightIE,
)
from .plutotv import PlutoTVIE
from .plvideo import PlVideoIE
from .podbayfm import (
PodbayFMChannelIE,
PodbayFMIE,

2
yt_dlp/extractor/adn.py
View file

@ -232,7 +232,7 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
error = self._parse_json(e.cause.response.read(), video_id)
message = error.get('message')
if e.cause.code == 403 and error.get('code') == 'player-bad-geolocation-country':
if e.cause.status == 403 and error.get('code') == 'player-bad-geolocation-country':
self.raise_geo_restricted(msg=message)
raise ExtractorError(message)
else:

13
yt_dlp/extractor/bilibili.py
View file

@ -681,12 +681,6 @@ class BiliBiliIE(BilibiliBaseIE):
old_video_id = format_field(aid, None, f'%s_part{part_id or 1}')
cid = traverse_obj(video_data, ('pages', part_id - 1, 'cid')) if part_id else video_data.get('cid')
play_info = (
traverse_obj(
self._search_json(r'window\.__playinfo__\s*=', webpage, 'play info', video_id, default=None),
('data', {dict}))
or self._download_playinfo(video_id, cid, headers=headers, query={'try_look': 1}))
festival_info = {}
if is_festival:
festival_info = traverse_obj(initial_state, {
@ -724,6 +718,13 @@ class BiliBiliIE(BilibiliBaseIE):
duration=traverse_obj(initial_state, ('videoData', 'duration', {int_or_none})),
__post_extractor=self.extract_comments(aid))
play_info = None
if self.is_logged_in:
play_info = traverse_obj(
self._search_json(r'window\.__playinfo__\s*=', webpage, 'play info', video_id, default=None),
('data', {dict}))
if not play_info:
play_info = self._download_playinfo(video_id, cid, headers=headers, query={'try_look': 1})
formats = self.extract_formats(play_info)
if video_data.get('is_upower_exclusive'):

5
yt_dlp/extractor/brightcove.py
View file

@ -31,6 +31,7 @@ from ..utils import (
update_url_query,
url_or_none,
)
from ..utils.traversal import traverse_obj
class BrightcoveLegacyIE(InfoExtractor):
@ -935,8 +936,8 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
if content_type == 'playlist':
return self.playlist_result(
[self._parse_brightcove_metadata(vid, vid.get('id'), headers)
for vid in json_data.get('videos', []) if vid.get('id')],
(self._parse_brightcove_metadata(vid, vid['id'], headers)
for vid in traverse_obj(json_data, ('videos', lambda _, v: v['id']))),
json_data.get('id'), json_data.get('name'),
json_data.get('description'))

6
yt_dlp/extractor/cultureunplugged.py
View file

@ -1,7 +1,4 @@
import time
from .common import InfoExtractor
from ..networking import HEADRequest
from ..utils import int_or_none
@ -31,9 +28,6 @@ class CultureUnpluggedIE(InfoExtractor):
video_id = mobj.group('id')
display_id = mobj.group('display_id') or video_id
# request setClientTimezone.php to get PHPSESSID cookie which is need to get valid json data in the next request
self._request_webpage(HEADRequest(
'http://www.cultureunplugged.com/setClientTimezone.php?timeOffset=%d' % -(time.timezone / 3600)), display_id)
movie_data = self._download_json(
f'http://www.cultureunplugged.com/movie-data/cu-{video_id}.json', display_id)

2
yt_dlp/extractor/dvtv.py
View file

@ -162,7 +162,7 @@ class DVTVIE(InfoExtractor):
items = re.findall(r'(?s)playlist\.push\(({.+?})\);', webpage)
if items:
return self.playlist_result(
[self._parse_video_metadata(i, video_id, timestamp) for i in items],
(self._parse_video_metadata(i, video_id, timestamp) for i in items),
video_id, self._html_search_meta('twitter:title', webpage))
item = self._search_regex(

2
yt_dlp/extractor/nytimes.py
View file

@ -343,7 +343,7 @@ class NYTimesCookingIE(NYTimesBaseIE):
if media_ids:
media_ids.append(lead_video_id)
return self.playlist_result(
[self._extract_video(media_id) for media_id in media_ids], page_id, title, description)
map(self._extract_video, media_ids), page_id, title, description)
return {
**self._extract_video(lead_video_id),

22
yt_dlp/extractor/patreon.py
View file

@ -457,7 +457,7 @@ class PatreonCampaignIE(PatreonBaseIE):
_VALID_URL = r'''(?x)
https?://(?:www\.)?patreon\.com/(?:
(?:m|api/campaigns)/(?P<campaign_id>\d+)|
(?P<vanity>(?!creation[?/]|posts/|rss[?/])[\w-]+)
(?:c/)?(?P<vanity>(?!creation[?/]|posts/|rss[?/])[\w-]+)
)(?:/posts)?/?(?:$|[?#])'''
_TESTS = [{
'url': 'https://www.patreon.com/dissonancepod/',
@ -509,6 +509,26 @@ class PatreonCampaignIE(PatreonBaseIE):
'thumbnail': r're:^https?://.*$',
},
'playlist_mincount': 201,
}, {
'url': 'https://www.patreon.com/c/OgSog',
'info_dict': {
'id': '8504388',
'title': 'OGSoG',
'description': r're:(?s)Hello and welcome to our Patreon page. We are Mari, Lasercorn, .+',
'channel': 'OGSoG',
'channel_id': '8504388',
'channel_url': 'https://www.patreon.com/OgSog',
'uploader_url': 'https://www.patreon.com/OgSog',
'uploader_id': '72323575',
'uploader': 'David Moss',
'thumbnail': r're:https?://.+/.+',
'channel_follower_count': int,
'age_limit': 0,
},
'playlist_mincount': 331,
}, {
'url': 'https://www.patreon.com/c/OgSog/posts',
'only_matching': True,
}, {
'url': 'https://www.patreon.com/dissonancepod/posts',
'only_matching': True,

5
yt_dlp/extractor/pixivsketch.py
View file

@ -1,4 +1,5 @@
from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
traverse_obj,
@ -110,8 +111,8 @@ class PixivSketchUserIE(PixivSketchBaseIE):
if not traverse_obj(data, 'is_broadcasting'):
try:
self._call_api(user_id, 'users/current.json', url, 'Investigating reason for request failure')
except ExtractorError as ex:
if ex.cause and ex.cause.code == 401:
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 401:
self.raise_login_required(f'Please log in, or use direct link like https://sketch.pixiv.net/@{user_id}/1234567890', method='cookies')
raise ExtractorError('This user is offline', expected=True)

130
yt_dlp/extractor/plvideo.py Normal file
View file

@ -0,0 +1,130 @@
from .common import InfoExtractor
from ..utils import (
float_or_none,
int_or_none,
parse_iso8601,
parse_resolution,
url_or_none,
)
from ..utils.traversal import traverse_obj
class PlVideoIE(InfoExtractor):
IE_DESC = 'Платформа'
_VALID_URL = r'https?://(?:www\.)?plvideo\.ru/(?:watch\?(?:[^#]+&)?v=|shorts/)(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://plvideo.ru/watch?v=Y5JzUzkcQTMK',
'md5': 'fe8e18aca892b3b31f3bf492169f8a26',
'info_dict': {
'id': 'Y5JzUzkcQTMK',
'ext': 'mp4',
'thumbnail': 'https://img.plvideo.ru/images/fp-2024-images/v/cover/37/dd/37dd00a4c96c77436ab737e85947abd7/original663a4a3bb713e5.33151959.jpg',
'title': 'Presidente de Cuba llega a Moscú en una visita de trabajo',
'channel': 'RT en Español',
'channel_id': 'ZH4EKqunVDvo',
'media_type': 'video',
'comment_count': int,
'tags': ['rusia', 'cuba', 'russia', 'miguel díaz-canel'],
'description': 'md5:a1a395d900d77a86542a91ee0826c115',
'released_timestamp': 1715096124,
'channel_is_verified': True,
'like_count': int,
'timestamp': 1715095911,
'duration': 44320,
'view_count': int,
'dislike_count': int,
'upload_date': '20240507',
'modified_date': '20240701',
'channel_follower_count': int,
'modified_timestamp': 1719824073,
},
}, {
'url': 'https://plvideo.ru/shorts/S3Uo9c-VLwFX',
'md5': '7d8fa2279406c69d2fd2a6fc548a9805',
'info_dict': {
'id': 'S3Uo9c-VLwFX',
'ext': 'mp4',
'channel': 'Romaatom',
'tags': 'count:22',
'dislike_count': int,
'upload_date': '20241130',
'description': 'md5:452e6de219bf2f32bb95806c51c3b364',
'duration': 58433,
'modified_date': '20241130',
'thumbnail': 'https://img.plvideo.ru/images/fp-2024-11-cover/S3Uo9c-VLwFX/f9318999-a941-482b-b700-2102a7049366.jpg',
'media_type': 'shorts',
'like_count': int,
'modified_timestamp': 1732961458,
'channel_is_verified': True,
'channel_id': 'erJyyTIbmUd1',
'timestamp': 1732961355,
'comment_count': int,
'title': 'Белоусов отменил приказы о кадровом резерве на гражданской службе',
'channel_follower_count': int,
'view_count': int,
'released_timestamp': 1732961458,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
video_data = self._download_json(
f'https://api.g1.plvideo.ru/v1/videos/{video_id}?Aud=18', video_id)
is_live = False
formats = []
subtitles = {}
automatic_captions = {}
for quality, data in traverse_obj(video_data, ('item', 'profiles', {dict.items}, lambda _, v: url_or_none(v[1]['hls']))):
formats.append({
'format_id': quality,
'ext': 'mp4',
'protocol': 'm3u8_native',
**traverse_obj(data, {
'url': 'hls',
'fps': ('fps', {float_or_none}),
'aspect_ratio': ('aspectRatio', {float_or_none}),
}),
**parse_resolution(quality),
})
if livestream_url := traverse_obj(video_data, ('item', 'livestream', 'url', {url_or_none})):
is_live = True
formats.extend(self._extract_m3u8_formats(livestream_url, video_id, 'mp4', live=True))
for lang, url in traverse_obj(video_data, ('item', 'subtitles', {dict.items}, lambda _, v: url_or_none(v[1]))):
if lang.endswith('-auto'):
automatic_captions.setdefault(lang[:-5], []).append({
'url': url,
})
else:
subtitles.setdefault(lang, []).append({
'url': url,
})
return {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
'automatic_captions': automatic_captions,
'is_live': is_live,
**traverse_obj(video_data, ('item', {
'id': ('id', {str}),
'title': ('title', {str}),
'description': ('description', {str}),
'thumbnail': ('cover', 'paths', 'original', 'src', {url_or_none}),
'duration': ('uploadFile', 'videoDuration', {int_or_none}),
'channel': ('channel', 'name', {str}),
'channel_id': ('channel', 'id', {str}),
'channel_follower_count': ('channel', 'stats', 'subscribers', {int_or_none}),
'channel_is_verified': ('channel', 'verified', {bool}),
'tags': ('tags', ..., {str}),
'timestamp': ('createdAt', {parse_iso8601}),
'released_timestamp': ('publishedAt', {parse_iso8601}),
'modified_timestamp': ('updatedAt', {parse_iso8601}),
'view_count': ('stats', 'viewTotalCount', {int_or_none}),
'like_count': ('stats', 'likeCount', {int_or_none}),
'dislike_count': ('stats', 'dislikeCount', {int_or_none}),
'comment_count': ('stats', 'commentCount', {int_or_none}),
'media_type': ('type', {str}),
})),
}

108
yt_dlp/extractor/soundcloud.py
View file

@ -7,7 +7,6 @@ from .common import InfoExtractor, SearchInfoExtractor
from ..networking import HEADRequest
from ..networking.exceptions import HTTPError
from ..utils import (
KNOWN_EXTENSIONS,
ExtractorError,
float_or_none,
int_or_none,
@ -211,6 +210,7 @@ class SoundcloudBaseIE(InfoExtractor):
format_urls = set()
formats = []
has_drm = False
query = {'client_id': self._CLIENT_ID}
if secret_token:
query['secret_token'] = secret_token
@ -246,55 +246,24 @@ class SoundcloudBaseIE(InfoExtractor):
'url': format_url,
'quality': 10,
'format_note': 'Original',
'vcodec': 'none',
})
def invalid_url(url):
return not url or url in format_urls
def add_format(f, protocol, is_preview=False):
mobj = re.search(r'\.(?P<abr>\d+)\.(?P<ext>[0-9a-z]{3,4})(?=[/?])', stream_url)
if mobj:
for k, v in mobj.groupdict().items():
if not f.get(k):
f[k] = v
format_id_list = []
if protocol:
format_id_list.append(protocol)
ext = f.get('ext')
if ext == 'aac':
f.update({
'abr': 256,
'quality': 5,
'format_note': 'Premium',
})
for k in ('ext', 'abr'):
v = str_or_none(f.get(k))
if v:
format_id_list.append(v)
preview = is_preview or re.search(r'/(?:preview|playlist)/0/30/', f['url'])
if preview:
format_id_list.append('preview')
abr = f.get('abr')
if abr:
f['abr'] = int(abr)
if protocol in ('hls', 'hls-aes'):
protocol = 'm3u8' if ext == 'aac' else 'm3u8_native'
else:
protocol = 'http'
f.update({
'format_id': '_'.join(format_id_list),
'protocol': protocol,
'preference': -10 if preview else None,
})
formats.append(f)
# New API
for t in traverse_obj(info, ('media', 'transcodings', lambda _, v: url_or_none(v['url']))):
for t in traverse_obj(info, ('media', 'transcodings', lambda _, v: url_or_none(v['url']) and v['preset'])):
if extract_flat:
break
format_url = t['url']
preset = t['preset']
preset_base = preset.partition('_')[0]
protocol = traverse_obj(t, ('format', 'protocol', {str}))
protocol = traverse_obj(t, ('format', 'protocol', {str})) or 'http'
if protocol.startswith(('ctr-', 'cbc-')):
has_drm = True
continue
if protocol == 'progressive':
protocol = 'http'
if protocol != 'hls' and '/hls' in format_url:
@ -302,34 +271,59 @@ class SoundcloudBaseIE(InfoExtractor):
if protocol == 'encrypted-hls' or '/encrypted-hls' in format_url:
protocol = 'hls-aes'
ext = None
if preset := traverse_obj(t, ('preset', {str_or_none})):
ext = preset.split('_')[0]
if ext not in KNOWN_EXTENSIONS:
ext = mimetype2ext(traverse_obj(t, ('format', 'mime_type', {str})))
identifier = join_nonempty(protocol, ext, delim='_')
if not self._is_requested(identifier):
self.write_debug(f'"{identifier}" is not a requested format, skipping')
short_identifier = f'{protocol}_{preset_base}'
if preset_base == 'abr':
self.write_debug(f'Skipping broken "{short_identifier}" format')
continue
if not self._is_requested(short_identifier):
self.write_debug(f'"{short_identifier}" is not a requested format, skipping')
continue
# XXX: if not extract_flat, 429 error must be caught where _extract_info_dict is called
stream_url = traverse_obj(self._call_api(
format_url, track_id, f'Downloading {identifier} format info JSON',
format_url, track_id, f'Downloading {short_identifier} format info JSON',
query=query, headers=self._HEADERS), ('url', {url_or_none}))
if invalid_url(stream_url):
continue
format_urls.add(stream_url)
add_format({
mime_type = traverse_obj(t, ('format', 'mime_type', {str}))
codec = self._search_regex(r'codecs="([^"]+)"', mime_type, 'codec', default=None)
ext = {
'mp4a': 'm4a',
'opus': 'opus',
}.get(codec[:4] if codec else None) or mimetype2ext(mime_type, default=None)
if not ext or ext == 'm3u8':
ext = preset_base
is_premium = t.get('quality') == 'hq'
abr = int_or_none(
self._search_regex(r'(\d+)k$', preset, 'abr', default=None)
or self._search_regex(r'\.(\d+)\.(?:opus|mp3)[/?]', stream_url, 'abr', default=None)
or (256 if (is_premium and 'aac' in preset) else None))
is_preview = (t.get('snipped')
or '/preview/' in format_url
or re.search(r'/(?:preview|playlist)/0/30/', stream_url))
formats.append({
'format_id': join_nonempty(protocol, preset, is_preview and 'preview', delim='_'),
'url': stream_url,
'ext': ext,
}, protocol, t.get('snipped') or '/preview/' in format_url)
'acodec': codec,
'vcodec': 'none',
'abr': abr,
'protocol': 'm3u8_native' if protocol in ('hls', 'hls-aes') else 'http',
'container': 'm4a_dash' if ext == 'm4a' else None,
'quality': 5 if is_premium else 0 if (abr and abr >= 160) else -1,
'format_note': 'Premium' if is_premium else None,
'preference': -10 if is_preview else None,
})
for f in formats:
f['vcodec'] = 'none'
if not formats and info.get('policy') == 'BLOCK':
if not formats:
if has_drm:
self.report_drm(track_id)
if info.get('policy') == 'BLOCK':
self.raise_geo_restricted(metadata_available=True)
user = info.get('user') or {}

2
yt_dlp/extractor/vidyard.py
View file

@ -421,5 +421,5 @@ class VidyardIE(VidyardBaseIE):
return self._process_video_json(video_json['chapters'][0], video_id)
return self.playlist_result(
[self._process_video_json(chapter, video_id) for chapter in video_json['chapters']],
(self._process_video_json(chapter, video_id) for chapter in video_json['chapters']),
str(video_json['playerUuid']), video_json.get('name'))

96
yt_dlp/extractor/vk.py
View file

@ -17,10 +17,10 @@ from ..utils import (
get_element_html_by_id,
int_or_none,
join_nonempty,
parse_qs,
parse_resolution,
str_or_none,
str_to_int,
traverse_obj,
try_call,
unescapeHTML,
unified_timestamp,
@ -29,6 +29,7 @@ from ..utils import (
urlencode_postdata,
urljoin,
)
from ..utils.traversal import require, traverse_obj
class VKBaseIE(InfoExtractor):
@ -91,17 +92,17 @@ class VKBaseIE(InfoExtractor):
class VKIE(VKBaseIE):
IE_NAME = 'vk'
IE_DESC = 'VK'
_EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1']
_EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk(?:(?:video)?\.ru|\.com)/video_ext\.php.+?)\1']
_VALID_URL = r'''(?x)
https?://
(?:
(?:
(?:(?:m|new)\.)?vk\.com/video_|
(?:(?:m|new)\.)?vk(?:(?:video)?\.ru|\.com)/video_|
(?:www\.)?daxab\.com/
)
ext\.php\?(?P<embed_query>.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+).*)|
(?:
(?:(?:m|new)\.)?vk\.com/(?:.+?\?.*?z=)?(?:video|clip)|
(?:(?:m|new)\.)?vk(?:(?:video)?\.ru|\.com)/(?:.+?\?.*?z=)?(?:video|clip)|
(?:www\.)?daxab\.com/embed/
)
(?P<videoid>-?\d+_\d+)(?:.*\blist=(?P<list_id>([\da-f]+)|(ln-[\da-zA-Z]+)))?
@ -110,7 +111,7 @@ class VKIE(VKBaseIE):
_TESTS = [
{
'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
'url': 'https://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
'info_dict': {
'id': '-77521_162222515',
'ext': 'mp4',
@ -127,7 +128,7 @@ class VKIE(VKBaseIE):
'params': {'skip_download': 'm3u8'},
},
{
'url': 'http://vk.com/video205387401_165548505',
'url': 'https://vk.com/video205387401_165548505',
'info_dict': {
'id': '205387401_165548505',
'ext': 'mp4',
@ -182,10 +183,10 @@ class VKIE(VKBaseIE):
'ext': 'mp4',
'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
'description': 'md5:bf9c26cfa4acdfb146362682edd3827a',
'duration': 178,
'duration': 179,
'upload_date': '20130117',
'uploader': "Children's Joy Foundation Inc.",
'uploader_id': 'thecjf',
'uploader_id': '@CJFIofficial',
'view_count': int,
'channel_id': 'UCgzCNQ11TmR9V97ECnhi3gw',
'availability': 'public',
@ -193,7 +194,7 @@ class VKIE(VKBaseIE):
'live_status': 'not_live',
'playable_in_embed': True,
'channel': 'Children\'s Joy Foundation Inc.',
'uploader_url': 'http://www.youtube.com/user/thecjf',
'uploader_url': 'https://www.youtube.com/@CJFIofficial',
'thumbnail': r're:https?://.+\.jpg$',
'tags': 'count:27',
'start_time': 0.0,
@ -201,6 +202,7 @@ class VKIE(VKBaseIE):
'channel_url': 'https://www.youtube.com/channel/UCgzCNQ11TmR9V97ECnhi3gw',
'channel_follower_count': int,
'age_limit': 0,
'timestamp': 1358394935,
},
},
{
@ -222,6 +224,7 @@ class VKIE(VKBaseIE):
'thumbnail': r're:https?://.+x1080$',
'tags': list,
},
'skip': 'This video has been deleted and is no longer available.',
},
{
'url': 'https://vk.com/clips-74006511?z=clip-74006511_456247211',
@ -235,13 +238,13 @@ class VKIE(VKBaseIE):
'timestamp': 1664995597,
'title': 'Clip by @madempress',
'upload_date': '20221005',
'uploader': 'Шальная императрица',
'uploader': 'Шальная Императрица',
'uploader_id': '-74006511',
},
},
{
# video key is extra_data not url\d+
'url': 'http://vk.com/video-110305615_171782105',
'url': 'https://vk.com/video-110305615_171782105',
'md5': 'e13fcda136f99764872e739d13fac1d1',
'info_dict': {
'id': '-110305615_171782105',
@ -273,6 +276,7 @@ class VKIE(VKBaseIE):
'params': {
'skip_download': True,
},
'skip': 'No formats found',
},
{
# live stream, hls and rtmp links, most likely already finished live
@ -312,7 +316,16 @@ class VKIE(VKBaseIE):
{
'url': 'https://vk.com/clip30014565_456240946',
'only_matching': True,
}]
},
{
'url': 'https://vkvideo.ru/video-127553155_456242961',
'only_matching': True,
},
{
'url': 'https://vk.ru/video-220754053_456242564',
'only_matching': True,
},
]
def _real_extract(self, url):
mobj = self._match_valid_url(url)
@ -338,7 +351,7 @@ class VKIE(VKBaseIE):
video_id = '{}_{}'.format(mobj.group('oid'), mobj.group('id'))
info_page = self._download_webpage(
'http://vk.com/video_ext.php?' + mobj.group('embed_query'), video_id)
'https://vk.com/video_ext.php?' + mobj.group('embed_query'), video_id)
error_message = self._html_search_regex(
[r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>',
@ -432,7 +445,7 @@ class VKIE(VKBaseIE):
if m_opts_url:
opts_url = m_opts_url.group(1)
if opts_url.startswith('//'):
opts_url = 'http:' + opts_url
opts_url = 'https:' + opts_url
return self.url_result(opts_url)
data = player['params'][0]
@ -512,8 +525,11 @@ class VKIE(VKBaseIE):
class VKUserVideosIE(VKBaseIE):
IE_NAME = 'vk:uservideos'
IE_DESC = "VK - User's Videos"
_VALID_URL = r'https?://(?:(?:m|new)\.)?vk\.com/video/(?:playlist/)?(?P<id>[^?$#/&]+)(?!\?.*\bz=video)(?:[/?#&](?:.*?\bsection=(?P<section>\w+))?|$)'
_TEMPLATE_URL = 'https://vk.com/videos'
_BASE_URL_RE = r'https?://(?:(?:m|new)\.)?vk(?:video\.ru|\.com/video)'
_VALID_URL = [
rf'{_BASE_URL_RE}/playlist/(?P<id>-?\d+_\d+)',
rf'{_BASE_URL_RE}/(?P<id>@[^/?#]+)(?:/all)?/?(?!\?.*\bz=video)(?:[?#]|$)',
]
_TESTS = [{
'url': 'https://vk.com/video/@mobidevices',
'info_dict': {
@ -527,12 +543,20 @@ class VKUserVideosIE(VKBaseIE):
},
'playlist_mincount': 182,
}, {
'url': 'https://vk.com/video/playlist/-174476437_2',
'url': 'https://vkvideo.ru/playlist/-204353299_426',
'info_dict': {
'id': '-174476437_playlist_2',
'title': 'Анонсы',
'id': '-204353299_playlist_426',
},
'playlist_mincount': 108,
'playlist_mincount': 33,
}, {
'url': 'https://vk.com/video/@gorkyfilmstudio/all',
'only_matching': True,
}, {
'url': 'https://vkvideo.ru/@mobidevices',
'only_matching': True,
}, {
'url': 'https://vk.com/video/playlist/-174476437_2',
'only_matching': True,
}]
_VIDEO = collections.namedtuple('Video', ['owner_id', 'id'])
@ -552,7 +576,7 @@ class VKUserVideosIE(VKBaseIE):
v = self._VIDEO._make(video[:2])
video_id = '%d_%d' % (v.owner_id, v.id)
yield self.url_result(
'http://vk.com/video' + video_id, VKIE.ie_key(), video_id)
'https://vk.com/video' + video_id, VKIE.ie_key(), video_id)
if count >= total:
break
video_list_json = self._download_payload('al_video', page_id, {
@ -561,23 +585,25 @@ class VKUserVideosIE(VKBaseIE):
'oid': page_id,
'section': section,
})[0][section]
count += video_list_json['count']
new_count = video_list_json['count']
if not new_count:
self.to_screen(f'{page_id}: Skipping {total - count} unavailable videos')
break
count += new_count
video_list = video_list_json['list']
def _real_extract(self, url):
u_id, section = self._match_valid_url(url).groups()
u_id = self._match_id(url)
webpage = self._download_webpage(url, u_id)
if u_id.startswith('@'):
page_id = self._search_regex(r'data-owner-id\s?=\s?"([^"]+)"', webpage, 'page_id')
elif '_' in u_id:
page_id, section = u_id.split('_', 1)
section = f'playlist_{section}'
page_id = traverse_obj(
self._search_json(r'\bvar newCur\s*=', webpage, 'cursor data', u_id),
('oid', {int}, {str_or_none}, {require('page id')}))
section = traverse_obj(parse_qs(url), ('section', 0)) or 'all'
else:
raise ExtractorError('Invalid URL', expected=True)
if not section:
section = 'all'
page_id, _, section = u_id.partition('_')
section = f'playlist_{section}'
playlist_title = clean_html(get_element_by_class('VideoInfoPanel__title', webpage))
return self.playlist_result(self._entries(page_id, section), f'{page_id}_{section}', playlist_title)
@ -717,7 +743,7 @@ class VKWallPostIE(VKBaseIE):
class VKPlayBaseIE(InfoExtractor):
_BASE_URL_RE = r'https?://(?:vkplay\.live|live\.vkplay\.ru)/'
_BASE_URL_RE = r'https?://(?:vkplay\.live|live\.vk(?:play|video)\.ru)/'
_RESOLUTIONS = {
'tiny': '256x144',
'lowest': '426x240',
@ -797,6 +823,9 @@ class VKPlayIE(VKPlayBaseIE):
}, {
'url': 'https://live.vkplay.ru/lebwa/record/33a4e4ce-e3ef-49db-bb14-f006cc6fabc9/records',
'only_matching': True,
}, {
'url': 'https://live.vkvideo.ru/lebwa/record/33a4e4ce-e3ef-49db-bb14-f006cc6fabc9/records',
'only_matching': True,
}]
def _real_extract(self, url):
@ -839,6 +868,9 @@ class VKPlayLiveIE(VKPlayBaseIE):
}, {
'url': 'https://live.vkplay.ru/lebwa',
'only_matching': True,
}, {
'url': 'https://live.vkvideo.ru/panterka',
'only_matching': True,
}]
def _real_extract(self, url):

14
yt_dlp/extractor/xiaohongshu.py
View file

@ -10,7 +10,7 @@ from ..utils.traversal import traverse_obj
class XiaoHongShuIE(InfoExtractor):
_VALID_URL = r'https?://www\.xiaohongshu\.com/explore/(?P<id>[\da-f]+)'
_VALID_URL = r'https?://www\.xiaohongshu\.com/(?:explore|discovery/item)/(?P<id>[\da-f]+)'
IE_DESC = '小红书'
_TESTS = [{
'url': 'https://www.xiaohongshu.com/explore/6411cf99000000001300b6d9',
@ -25,6 +25,18 @@ class XiaoHongShuIE(InfoExtractor):
'duration': 101.726,
'thumbnail': r're:https?://sns-webpic-qc\.xhscdn\.com/\d+/[a-z0-9]+/[\w]+',
},
}, {
'url': 'https://www.xiaohongshu.com/discovery/item/674051740000000007027a15?xsec_token=CBgeL8Dxd1ZWBhwqRd568gAZ_iwG-9JIf9tnApNmteU2E=',
'info_dict': {
'id': '674051740000000007027a15',
'ext': 'mp4',
'title': '相互喜欢就可以了',
'uploader_id': '63439913000000001901f49a',
'duration': 28.073,
'description': '#广州[话题]# #深圳[话题]# #香港[话题]# #街头采访[话题]# #是你喜欢的类型[话题]#',
'thumbnail': r're:https?://sns-webpic-qc\.xhscdn\.com/\d+/[\da-f]+/[^/]+',
'tags': ['广州', '深圳', '香港', '街头采访', '是你喜欢的类型'],
},
}]
def _real_extract(self, url):

161
yt_dlp/extractor/youtube.py
View file

@ -78,7 +78,7 @@ INNERTUBE_CLIENTS = {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'WEB',
'clientVersion': '2.20240726.00.00',
'clientVersion': '2.20241126.01.00',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 1,
@ -90,7 +90,7 @@ INNERTUBE_CLIENTS = {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'WEB',
'clientVersion': '2.20240726.00.00',
'clientVersion': '2.20241126.01.00',
'userAgent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/15.5 Safari/605.1.15,gzip(gfe)',
},
},
@ -102,7 +102,7 @@ INNERTUBE_CLIENTS = {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'WEB_EMBEDDED_PLAYER',
'clientVersion': '1.20240723.01.00',
'clientVersion': '1.20241201.00.00',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 56,
@ -113,7 +113,7 @@ INNERTUBE_CLIENTS = {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'WEB_REMIX',
'clientVersion': '1.20240724.00.00',
'clientVersion': '1.20241127.01.00',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
@ -124,7 +124,7 @@ INNERTUBE_CLIENTS = {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'WEB_CREATOR',
'clientVersion': '1.20240723.03.00',
'clientVersion': '1.20241203.01.00',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
@ -162,7 +162,6 @@ INNERTUBE_CLIENTS = {
'REQUIRE_JS_PLAYER': False,
'REQUIRE_PO_TOKEN': True,
'REQUIRE_AUTH': True,
'SUPPORTS_COOKIES': True,
},
# This client now requires sign-in for every video
'android_creator': {
@ -197,7 +196,6 @@ INNERTUBE_CLIENTS = {
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 28,
'REQUIRE_JS_PLAYER': False,
'SUPPORTS_COOKIES': True,
},
# iOS clients have HLS live streams. Setting device model to get 60fps formats.
# See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
@ -214,6 +212,7 @@ INNERTUBE_CLIENTS = {
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
'REQUIRE_PO_TOKEN': True,
'REQUIRE_JS_PLAYER': False,
},
# This client now requires sign-in for every video
@ -232,7 +231,6 @@ INNERTUBE_CLIENTS = {
'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
'REQUIRE_JS_PLAYER': False,
'REQUIRE_AUTH': True,
'SUPPORTS_COOKIES': True,
},
# This client now requires sign-in for every video
'ios_creator': {
@ -257,7 +255,9 @@ INNERTUBE_CLIENTS = {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'MWEB',
'clientVersion': '2.20240726.01.00',
'clientVersion': '2.20241202.07.00',
# mweb does not require PO Token with this UA
'userAgent': 'Mozilla/5.0 (iPad; CPU OS 16_7_10 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.6 Mobile/15E148 Safari/604.1,gzip(gfe)',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 2,
@ -267,7 +267,7 @@ INNERTUBE_CLIENTS = {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'TVHTML5',
'clientVersion': '7.20240724.13.00',
'clientVersion': '7.20241201.18.00',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 7,
@ -517,11 +517,12 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
return self._search_regex(rf'^({self._YT_CHANNEL_UCID_RE})$', ucid, 'UC-id', default=None)
def handle_or_none(self, handle):
return self._search_regex(rf'^({self._YT_HANDLE_RE})$', handle, '@-handle', default=None)
return self._search_regex(rf'^({self._YT_HANDLE_RE})$', urllib.parse.unquote(handle or ''),
'@-handle', default=None)
def handle_from_url(self, url):
return self._search_regex(rf'^(?:https?://(?:www\.)?youtube\.com)?/({self._YT_HANDLE_RE})',
url, 'channel handle', default=None)
urllib.parse.unquote(url or ''), 'channel handle', default=None)
def ucid_from_url(self, url):
return self._search_regex(rf'^(?:https?://(?:www\.)?youtube\.com)?/({self._YT_CHANNEL_UCID_RE})',
@ -1494,7 +1495,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
},
# Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
{
'note': 'Embed allowed age-gate video',
'note': 'Embed allowed age-gate video; works with web_embedded',
'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
'info_dict': {
'id': 'HtVdAasjOgU',
@ -1524,7 +1525,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'heatmap': 'count:100',
'timestamp': 1401991663,
},
'skip': 'Age-restricted; requires authentication',
},
{
'note': 'Age-gate video with embed allowed in public site',
@ -2800,6 +2800,35 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'extractor_args': {'youtube': {'player_client': ['ios'], 'player_skip': ['webpage']}},
},
},
{
# uploader_id has non-ASCII characters that are percent-encoded in YT's JSON
'url': 'https://www.youtube.com/shorts/18NGQq7p3LY',
'info_dict': {
'id': '18NGQq7p3LY',
'ext': 'mp4',
'title': '아이브 이서 장원영 리즈 삐끼삐끼 챌린지',
'description': '',
'uploader': 'ㅇㅇ',
'uploader_id': '@으아-v1k',
'uploader_url': 'https://www.youtube.com/@으아-v1k',
'channel': 'ㅇㅇ',
'channel_id': 'UCC25oTm2J7ZVoi5TngOHg9g',
'channel_url': 'https://www.youtube.com/channel/UCC25oTm2J7ZVoi5TngOHg9g',
'thumbnail': r're:https?://.+/.+\.jpg',
'playable_in_embed': True,
'age_limit': 0,
'duration': 3,
'timestamp': 1724306170,
'upload_date': '20240822',
'availability': 'public',
'live_status': 'not_live',
'view_count': int,
'like_count': int,
'channel_follower_count': int,
'categories': ['People & Blogs'],
'tags': [],
},
},
]
_WEBPAGE_TESTS = [
@ -3118,19 +3147,26 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
self.to_screen('Extracted signature function:\n' + code)
def _parse_sig_js(self, jscode):
# Examples where `sig` is funcname:
# sig=function(a){a=a.split(""); ... ;return a.join("")};
# ;c&&(c=sig(decodeURIComponent(c)),a.set(b,encodeURIComponent(c)));return a};
# {var l=f,m=h.sp,n=sig(decodeURIComponent(h.s));l.set(m,encodeURIComponent(n))}
# sig=function(J){J=J.split(""); ... ;return J.join("")};
# ;N&&(N=sig(decodeURIComponent(N)),J.set(R,encodeURIComponent(N)));return J};
# {var H=u,k=f.sp,v=sig(decodeURIComponent(f.s));H.set(k,encodeURIComponent(v))}
funcname = self._search_regex(
(r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
(r'\b(?P<var>[a-zA-Z0-9_$]+)&&\((?P=var)=(?P<sig>[a-zA-Z0-9_$]{2,})\(decodeURIComponent\((?P=var)\)\)',
r'(?P<sig>[a-zA-Z0-9_$]+)\s*=\s*function\(\s*(?P<arg>[a-zA-Z0-9_$]+)\s*\)\s*{\s*(?P=arg)\s*=\s*(?P=arg)\.split\(\s*""\s*\)\s*;\s*[^}]+;\s*return\s+(?P=arg)\.join\(\s*""\s*\)',
r'(?:\b|[^a-zA-Z0-9_$])(?P<sig>[a-zA-Z0-9_$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)(?:;[a-zA-Z0-9_$]{2}\.[a-zA-Z0-9_$]{2}\(a,\d+\))?',
# Old patterns
r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)(?:;[a-zA-Z0-9$]{2}\.[a-zA-Z0-9$]{2}\(a,\d+\))?',
r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
# Obsolete patterns
r'("|\')signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
jscode, 'Initial JS player signature function name', group='sig')
@ -3204,6 +3240,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
# * a.D&&(b="nn"[+a.D],c=a.get(b))&&(c=narray[idx](c),a.set(b,c),narray.length||nfunc("")
# * a.D&&(PL(a),b=a.j.n||null)&&(b=narray[0](b),a.set("n",b),narray.length||nfunc("")
# * a.D&&(b="nn"[+a.D],vL(a),c=a.j[b]||null)&&(c=narray[idx](c),a.set(b,c),narray.length||nfunc("")
# * J.J="";J.url="";J.Z&&(R="nn"[+J.Z],mW(J),N=J.K[R]||null)&&(N=narray[idx](N),J.set(R,N))}};
funcname, idx = self._search_regex(
r'''(?x)
(?:
@ -3220,7 +3257,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
)\)&&\(c=|
\b(?P<var>[a-zA-Z0-9_$]+)=
)(?P<nfunc>[a-zA-Z0-9_$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z]\)
(?(var),[a-zA-Z0-9_$]+\.set\("n"\,(?P=var)\),(?P=nfunc)\.length)''',
(?(var),[a-zA-Z0-9_$]+\.set\((?:"n+"|[a-zA-Z0-9_$]+)\,(?P=var)\))''',
jscode, 'n function name', group=('nfunc', 'idx'), default=(None, None))
if not funcname:
self.report_warning(join_nonempty(
@ -3229,7 +3266,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
return self._search_regex(
r'''(?xs)
;\s*(?P<name>[a-zA-Z0-9_$]+)\s*=\s*function\([a-zA-Z0-9_$]+\)
\s*\{(?:(?!};).)+?["']enhanced_except_''',
\s*\{(?:(?!};).)+?return\s*(?P<q>["'])[\w-]+_w8_(?P=q)\s*\+\s*[a-zA-Z0-9_$]+''',
jscode, 'Initial JS player n function name', group='name')
elif not idx:
return funcname
@ -3238,6 +3275,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
rf'var {re.escape(funcname)}\s*=\s*(\[.+?\])\s*[,;]', jscode,
f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
def _fixup_n_function_code(self, argnames, code):
return argnames, re.sub(
rf';\s*if\s*\(\s*typeof\s+[a-zA-Z0-9_$]+\s*===?\s*(["\'])undefined\1\s*\)\s*return\s+{argnames[0]};',
';', code)
def _extract_n_function_code(self, video_id, player_url):
player_id = self._extract_player_info(player_url)
func_code = self.cache.load('youtube-nsig', player_id, min_ver='2024.07.09')
@ -3249,7 +3291,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
func_name = self._extract_n_function_name(jscode, player_url=player_url)
func_code = jsi.extract_function_code(func_name)
# XXX: Workaround for the `typeof` gotcha
func_code = self._fixup_n_function_code(*jsi.extract_function_code(func_name))
self.cache.store('youtube-nsig', player_id, func_code)
return jsi, player_id, func_code
@ -3265,7 +3308,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
except Exception as e:
raise JSInterpreter.Exception(traceback.format_exc(), cause=e)
if ret.startswith('enhanced_except_'):
if ret.startswith('enhanced_except_') or ret.endswith(s):
raise JSInterpreter.Exception('Signature function returned an exception')
return ret
@ -3929,13 +3972,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
)
require_po_token = self._get_default_ytcfg(client).get('REQUIRE_PO_TOKEN')
if not po_token and require_po_token:
if not po_token and require_po_token and 'missing_pot' in self._configuration_arg('formats'):
self.report_warning(
f'No PO Token provided for {client} client, '
f'which is required for working {client} formats. '
f'You can manually pass a PO Token for this client with '
f'--extractor-args "youtube:po_token={client}+XXX"',
only_once=True)
f'which may be required for working {client} formats. This client will be deprioritized', only_once=True)
deprioritize_pr = True
pr = initial_pr if client == 'web' else None
@ -3968,15 +4008,24 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
else:
prs.append(pr)
# web_embedded can work around age-gate and age-verification for some embeddable videos
if self._is_agegated(pr) and variant != 'web_embedded':
append_client(f'web_embedded.{base_client}')
# Unauthenticated users will only get web_embedded client formats if age-gated
if self._is_agegated(pr) and not self.is_authenticated:
self.to_screen(
f'{video_id}: This video is age-restricted; some formats may be missing '
f'without authentication. {self._login_hint()}', only_once=True)
''' This code is pointless while web_creator is in _DEFAULT_AUTHED_CLIENTS
# EU countries require age-verification for accounts to access age-restricted videos
# If account is not age-verified, _is_agegated() will be truthy for non-embedded clients
if self.is_authenticated and self._is_agegated(pr):
embedding_is_disabled = variant == 'web_embedded' and self._is_unplayable(pr)
if self.is_authenticated and (self._is_agegated(pr) or embedding_is_disabled):
self.to_screen(
f'{video_id}: This video is age-restricted and YouTube is requiring '
'account age-verification; some formats may be missing', only_once=True)
# web_creator can work around the age-verification requirement
# android_vr may also be able to work around age-verification
# tv_embedded may(?) still work around age-verification if the video is embeddable
append_client('web_creator')
'''
@ -3999,6 +4048,21 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
or (live_status == 'post_live' and (duration or 0) > 2 * 3600)):
return live_status
def _report_pot_format_skipped(self, video_id, client_name, proto):
msg = (
f'{video_id}: {client_name} client {proto} formats require a PO Token which was not provided. '
'They will be skipped as they may yield HTTP Error 403. '
f'You can manually pass a PO Token for this client with --extractor-args "youtube:po_token={client_name}+XXX". '
'For more information, refer to https://github.com/yt-dlp/yt-dlp/wiki/Extractors#po-token-guide . '
'To enable these broken formats anyway, pass --extractor-args "youtube:formats=missing_pot"')
# Only raise a warning for non-default clients, to not confuse users.
# iOS HLS formats still work without PO Token, so we don't need to warn about them.
if client_name in (*self._DEFAULT_CLIENTS, *self._DEFAULT_AUTHED_CLIENTS):
self.write_debug(msg, only_once=True)
else:
self.report_warning(msg, only_once=True)
def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
CHUNK_SIZE = 10 << 20
PREFERRED_LANG_VALUE = 10
@ -4052,10 +4116,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
if height:
res_qualities[height] = quality
display_name = audio_track.get('displayName') or ''
is_original = 'original' in display_name.lower()
is_descriptive = 'descriptive' in display_name.lower()
is_default = audio_track.get('audioIsDefault')
is_descriptive = 'descriptive' in (audio_track.get('displayName') or '').lower()
language_code = audio_track.get('id', '').split('.')[0]
if language_code and is_default:
if language_code and (is_original or (is_default and not original_language)):
original_language = language_code
# FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
@ -4123,11 +4189,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
fmt_url = update_url_query(fmt_url, {'pot': po_token})
# Clients that require PO Token return videoplayback URLs that may return 403
is_broken = (not po_token and self._get_default_ytcfg(client_name).get('REQUIRE_PO_TOKEN'))
if is_broken:
self.report_warning(
f'{video_id}: {client_name} client formats require a PO Token which was not provided. '
'They will be deprioritized as they may yield HTTP Error 403', only_once=True)
require_po_token = (not po_token and self._get_default_ytcfg(client_name).get('REQUIRE_PO_TOKEN'))
if require_po_token and 'missing_pot' not in self._configuration_arg('formats'):
self._report_pot_format_skipped(video_id, client_name, 'https')
continue
name = fmt.get('qualityLabel') or quality.replace('audio_quality_', '') or ''
fps = int_or_none(fmt.get('fps')) or 0
@ -4136,11 +4201,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'filesize': int_or_none(fmt.get('contentLength')),
'format_id': f'{itag}{"-drc" if fmt.get("isDrc") else ""}',
'format_note': join_nonempty(
join_nonempty(audio_track.get('displayName'), is_default and ' (default)', delim=''),
join_nonempty(display_name, is_default and ' (default)', delim=''),
name, fmt.get('isDrc') and 'DRC',
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',
is_damaged and 'DAMAGED', require_po_token and 'MISSING POT',
(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
@ -4155,9 +4220,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'url': fmt_url,
'width': int_or_none(fmt.get('width')),
'language': join_nonempty(language_code, 'desc' if is_descriptive else '') or None,
'language_preference': PREFERRED_LANG_VALUE if is_default else -10 if is_descriptive else -1,
'language_preference': PREFERRED_LANG_VALUE if is_original else 5 if is_default else -10 if is_descriptive else -1,
# Strictly de-prioritize broken, damaged and 3gp formats
'preference': -20 if is_broken else -10 if is_damaged else -2 if itag == '17' else None,
'preference': -20 if require_po_token else -10 if is_damaged else -2 if itag == '17' else None,
}
mime_mobj = re.match(
r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
@ -4207,7 +4272,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
key = (proto, f.get('language'))
if not all_formats and key in itags[itag]:
return False
itags[itag].add(key)
if f.get('source_preference') is None:
f['source_preference'] = -1
@ -4215,12 +4279,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
# Clients that require PO Token return videoplayback URLs that may return 403
# hls does not currently require PO Token
if (not po_token and self._get_default_ytcfg(client_name).get('REQUIRE_PO_TOKEN')) and proto != 'hls':
self.report_warning(
f'{video_id}: {client_name} client {proto} formats require a PO Token which was not provided. '
'They will be deprioritized as they may yield HTTP Error 403', only_once=True)
f['format_note'] = join_nonempty(f.get('format_note'), 'BROKEN', delim=' ')
if 'missing_pot' not in self._configuration_arg('formats'):
self._report_pot_format_skipped(video_id, client_name, proto)
return False
f['format_note'] = join_nonempty(f.get('format_note'), 'MISSING POT', delim=' ')
f['source_preference'] -= 20
itags[itag].add(key)
if itag and all_formats:
f['format_id'] = f'{itag}-{proto}'
elif any(p != proto for p, _ in itags[itag]):
@ -4674,7 +4740,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
(?=(?P<artist>[^\n]+))(?P=artist)\n+
(?=(?P<album>[^\n]+))(?P=album)\n
(?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
(?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
(?:.+?Released\ on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
(.+?\nArtist\s*:\s*
(?=(?P<clean_artist>[^\n]+))(?P=clean_artist)\n
)?.+\nAuto-generated\ by\ YouTube\.\s*$
@ -5267,6 +5333,7 @@ class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)],
'richGridRenderer': lambda x: self._extract_entries(x, continuation_list),
'lockupViewModel': lambda x: [self._extract_lockup_view_model(x)],
}
for key, renderer in isr_content.items():
if key not in known_renderers:

4
yt_dlp/options.py
View file

@ -1372,12 +1372,12 @@ def create_parser():
help='Allow Unicode characters, "&" and spaces in filenames (default)')
filesystem.add_option(
'--windows-filenames',
action='store_true', dest='windowsfilenames', default=False,
action='store_true', dest='windowsfilenames', default=None,
help='Force filenames to be Windows-compatible')
filesystem.add_option(
'--no-windows-filenames',
action='store_false', dest='windowsfilenames',
help='Make filenames Windows-compatible only if using Windows (default)')
help='Sanitize filenames only minimally')
filesystem.add_option(
'--trim-filenames', '--trim-file-names', metavar='LENGTH',
dest='trim_file_name', default=0, type=int,

16
yt_dlp/update.py
View file

@ -65,9 +65,14 @@ def _get_variant_and_executable_path():
machine = '_legacy' if version_tuple(platform.mac_ver()[0]) < (10, 15) else ''
else:
machine = f'_{platform.machine().lower()}'
is_64bits = sys.maxsize > 2**32
# Ref: https://en.wikipedia.org/wiki/Uname#Examples
if machine[1:] in ('x86', 'x86_64', 'amd64', 'i386', 'i686'):
machine = '_x86' if platform.architecture()[0][:2] == '32' else ''
machine = '_x86' if not is_64bits else ''
# platform.machine() on 32-bit raspbian OS may return 'aarch64', so check "64-bitness"
# See: https://github.com/yt-dlp/yt-dlp/issues/11813
elif machine[1:] == 'aarch64' and not is_64bits:
machine = '_armv7l'
# sys.executable returns a /tmp/ path for staticx builds (linux_static)
# Ref: https://staticx.readthedocs.io/en/latest/usage.html#run-time-information
if static_exe_path := os.getenv('STATICX_PROG_PATH'):
@ -525,11 +530,16 @@ class Updater:
@functools.cached_property
def cmd(self):
"""The command-line to run the executable, if known"""
argv = None
# There is no sys.orig_argv in py < 3.10. Also, it can be [] when frozen
if getattr(sys, 'orig_argv', None):
return sys.orig_argv
argv = sys.orig_argv
elif getattr(sys, 'frozen', False):
return sys.argv
argv = sys.argv
# linux_static exe's argv[0] will be /tmp/staticx-NNNN/yt-dlp_linux if we don't fixup here
if argv and os.getenv('STATICX_PROG_PATH'):
argv = [self.filename, *argv[1:]]
return argv
def restart(self):
"""Restart the executable"""

6
yt_dlp/version.py
View file

@ -1,8 +1,8 @@
# Autogenerated by devscripts/update-version.py
__version__ = '2024.11.18'
__version__ = '2024.12.23'
RELEASE_GIT_HEAD = '7ea2787920cccc6b8ea30791993d114fbd564434'
RELEASE_GIT_HEAD = '65cf46cddd873fd229dbb0fc0689bca4c201c6b6'
VARIANT = None
@ -12,4 +12,4 @@ CHANNEL = 'stable'
ORIGIN = 'yt-dlp/yt-dlp'
_pkg_version = '2024.11.18'
_pkg_version = '2024.12.23'