mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-12-27 01:51:24 +00:00
Code Issues Projects Releases Wiki Activity

Merge branch 'master' into ke/refactor-move-files-pp

Browse Source
This commit is contained in:
bashonly
2024-07-08 00:13:14 -05:00
committed by GitHub
parent b3f1ef087a 39bc699d2e
commit 81d8716a40
102 changed files with 3221 additions and 1268 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
yt_dlp/YoutubeDL.py
View File

@@ -4,6 +4,7 @@ import copy
import datetime as dt
import errno
import fileinput
import functools
import http.cookiejar
import io
import itertools
@@ -24,7 +25,7 @@ import traceback
import unicodedata
from .cache import Cache
from .compat import functools, urllib # isort: split
from .compat import urllib # isort: split
from .compat import compat_os_name, urllib_req_to_req
from .cookies import LenientSimpleCookie, load_cookies
from .downloader import FFmpegFD, get_suitable_downloader, shorten_protocol_name
@@ -158,7 +159,7 @@ from .utils import (
write_json_file,
write_string,
)
from .utils._utils import _YDLLogger
from .utils._utils import _UnsafeExtensionError, _YDLLogger
from .utils.networking import (
HTTPHeaderDict,
clean_headers,
@@ -171,6 +172,20 @@ if compat_os_name == 'nt':
import ctypes
def _catch_unsafe_extension_error(func):
@functools.wraps(func)
def wrapper(self, *args, **kwargs):
try:
return func(self, *args, **kwargs)
except _UnsafeExtensionError as error:
self.report_error(
f'The extracted extension ({error.extension!r}) is unusual '
'and will be skipped for safety reasons. '
f'If you believe this is an error{bug_reports_message(",")}')
return wrapper
class YoutubeDL:
"""YoutubeDL class.
@@ -453,8 +468,9 @@ class YoutubeDL:
Set the value to 'native' to use the native downloader
compat_opts: Compatibility options. See "Differences in default behavior".
The following options do not work when used through the API:
filename, abort-on-error, multistreams, no-live-chat, format-sort
no-clean-infojson, no-playlist-metafiles, no-keep-subs, no-attach-info-json.
filename, abort-on-error, multistreams, no-live-chat,
format-sort, no-clean-infojson, no-playlist-metafiles,
no-keep-subs, no-attach-info-json, allow-unsafe-ext.
Refer __init__.py for their implementation
progress_template: Dictionary of templates for progress outputs.
Allowed keys are 'download', 'postprocess',
@@ -581,8 +597,9 @@ class YoutubeDL:
'vbr', 'fps', 'vcodec', 'container', 'filesize', 'filesize_approx', 'rows', 'columns',
'player_url', 'protocol', 'fragment_base_url', 'fragments', 'is_from_start', 'is_dash_periods', 'request_data',
'preference', 'language', 'language_preference', 'quality', 'source_preference', 'cookies',
'http_headers', 'stretched_ratio', 'no_resume', 'has_drm', 'extra_param_to_segment_url', 'hls_aes', 'downloader_options',
'page_url', 'app', 'play_path', 'tc_url', 'flash_version', 'rtmp_live', 'rtmp_conn', 'rtmp_protocol', 'rtmp_real_time',
'http_headers', 'stretched_ratio', 'no_resume', 'has_drm', 'extra_param_to_segment_url', 'extra_param_to_key_url',
'hls_aes', 'downloader_options', 'page_url', 'app', 'play_path', 'tc_url', 'flash_version',
'rtmp_live', 'rtmp_conn', 'rtmp_protocol', 'rtmp_real_time',
}
_deprecated_multivalue_fields = {
'album_artist': 'album_artists',
@@ -1398,6 +1415,7 @@ class YoutubeDL:
outtmpl, info_dict = self.prepare_outtmpl(outtmpl, info_dict, *args, **kwargs)
return self.escape_outtmpl(outtmpl) % info_dict
@_catch_unsafe_extension_error
def _prepare_filename(self, info_dict, *, outtmpl=None, tmpl_type=None):
assert None in (outtmpl, tmpl_type), 'outtmpl and tmpl_type are mutually exclusive'
if outtmpl is None:
@@ -1925,6 +1943,8 @@ class YoutubeDL:
'playlist_title': ie_result.get('title'),
'playlist_uploader': ie_result.get('uploader'),
'playlist_uploader_id': ie_result.get('uploader_id'),
'playlist_channel': ie_result.get('channel'),
'playlist_channel_id': ie_result.get('channel_id'),
**kwargs,
}
if strict:
@@ -3188,6 +3208,7 @@ class YoutubeDL:
os.remove(file)
return None
@_catch_unsafe_extension_error
def process_info(self, info_dict):
"""Process a single resolved IE result. (Modifies it in-place)"""

8
yt_dlp/__init__.py
View File

@@ -64,6 +64,7 @@ from .utils import (
write_string,
)
from .utils.networking import std_headers
from .utils._utils import _UnsafeExtensionError
from .YoutubeDL import YoutubeDL
_IN_CLI = False
@@ -593,6 +594,13 @@ def validate_options(opts):
if opts.ap_username is not None and opts.ap_password is None:
opts.ap_password = getpass.getpass('Type TV provider account password and press [Return]: ')
# compat option changes global state destructively; only allow from cli
if 'allow-unsafe-ext' in opts.compat_opts:
warnings.append(
'Using allow-unsafe-ext opens you up to potential attacks. '
'Use with great care!')
_UnsafeExtensionError.sanitize_extension = lambda x, prepend=False: x
return warnings, deprecation_warnings

26
yt_dlp/compat/imghdr.py
View File

@@ -1,16 +1,22 @@
tests = {
'webp': lambda h: h[0:4] == b'RIFF' and h[8:] == b'WEBP',
'png': lambda h: h[:8] == b'\211PNG\r\n\032\n',
'jpeg': lambda h: h[6:10] in (b'JFIF', b'Exif'),
'gif': lambda h: h[:6] in (b'GIF87a', b'GIF89a'),
}
def what(file=None, h=None):
"""Detect format of image (Currently supports jpeg, png, webp, gif only)
Ref: https://github.com/python/cpython/blob/3.10/Lib/imghdr.py
Ref: https://github.com/python/cpython/blob/3.11/Lib/imghdr.py
Ref: https://www.w3.org/Graphics/JPEG/itu-t81.pdf
"""
if h is None:
with open(file, 'rb') as f:
h = f.read(12)
return next((type_ for type_, test in tests.items() if test(h)), None)
if h.startswith(b'RIFF') and h.startswith(b'WEBP', 8):
return 'webp'
if h.startswith(b'\x89PNG'):
return 'png'
if h.startswith(b'\xFF\xD8\xFF'):
return 'jpeg'
if h.startswith(b'GIF'):
return 'gif'
return None

70
yt_dlp/cookies.py
View File

@@ -2,7 +2,9 @@ import base64
import collections
import contextlib
import datetime as dt
import functools
import glob
import hashlib
import http.cookiejar
import http.cookies
import io
@@ -17,14 +19,12 @@ import tempfile
import time
import urllib.request
from enum import Enum, auto
from hashlib import pbkdf2_hmac
from .aes import (
aes_cbc_decrypt_bytes,
aes_gcm_decrypt_and_verify_bytes,
unpad_pkcs7,
)
from .compat import functools # isort: split
from .compat import compat_os_name
from .dependencies import (
_SECRETSTORAGE_UNAVAILABLE_REASON,
@@ -740,40 +740,38 @@ def _get_linux_desktop_environment(env, logger):
xdg_current_desktop = env.get('XDG_CURRENT_DESKTOP', None)
desktop_session = env.get('DESKTOP_SESSION', None)
if xdg_current_desktop is not None:
xdg_current_desktop = xdg_current_desktop.split(':')[0].strip()
if xdg_current_desktop == 'Unity':
if desktop_session is not None and 'gnome-fallback' in desktop_session:
for part in map(str.strip, xdg_current_desktop.split(':')):
if part == 'Unity':
if desktop_session is not None and 'gnome-fallback' in desktop_session:
return _LinuxDesktopEnvironment.GNOME
else:
return _LinuxDesktopEnvironment.UNITY
elif part == 'Deepin':
return _LinuxDesktopEnvironment.DEEPIN
elif part == 'GNOME':
return _LinuxDesktopEnvironment.GNOME
else:
return _LinuxDesktopEnvironment.UNITY
elif xdg_current_desktop == 'Deepin':
return _LinuxDesktopEnvironment.DEEPIN
elif xdg_current_desktop == 'GNOME':
return _LinuxDesktopEnvironment.GNOME
elif xdg_current_desktop == 'X-Cinnamon':
return _LinuxDesktopEnvironment.CINNAMON
elif xdg_current_desktop == 'KDE':
kde_version = env.get('KDE_SESSION_VERSION', None)
if kde_version == '5':
return _LinuxDesktopEnvironment.KDE5
elif kde_version == '6':
return _LinuxDesktopEnvironment.KDE6
elif kde_version == '4':
return _LinuxDesktopEnvironment.KDE4
else:
logger.info(f'unknown KDE version: "{kde_version}". Assuming KDE4')
return _LinuxDesktopEnvironment.KDE4
elif xdg_current_desktop == 'Pantheon':
return _LinuxDesktopEnvironment.PANTHEON
elif xdg_current_desktop == 'XFCE':
return _LinuxDesktopEnvironment.XFCE
elif xdg_current_desktop == 'UKUI':
return _LinuxDesktopEnvironment.UKUI
elif xdg_current_desktop == 'LXQt':
return _LinuxDesktopEnvironment.LXQT
else:
logger.info(f'XDG_CURRENT_DESKTOP is set to an unknown value: "{xdg_current_desktop}"')
elif part == 'X-Cinnamon':
return _LinuxDesktopEnvironment.CINNAMON
elif part == 'KDE':
kde_version = env.get('KDE_SESSION_VERSION', None)
if kde_version == '5':
return _LinuxDesktopEnvironment.KDE5
elif kde_version == '6':
return _LinuxDesktopEnvironment.KDE6
elif kde_version == '4':
return _LinuxDesktopEnvironment.KDE4
else:
logger.info(f'unknown KDE version: "{kde_version}". Assuming KDE4')
return _LinuxDesktopEnvironment.KDE4
elif part == 'Pantheon':
return _LinuxDesktopEnvironment.PANTHEON
elif part == 'XFCE':
return _LinuxDesktopEnvironment.XFCE
elif part == 'UKUI':
return _LinuxDesktopEnvironment.UKUI
elif part == 'LXQt':
return _LinuxDesktopEnvironment.LXQT
logger.info(f'XDG_CURRENT_DESKTOP is set to an unknown value: "{xdg_current_desktop}"')
elif desktop_session is not None:
if desktop_session == 'deepin':
@@ -1001,7 +999,7 @@ def _get_windows_v10_key(browser_root, logger):
def pbkdf2_sha1(password, salt, iterations, key_length):
return pbkdf2_hmac('sha1', password, salt, iterations, key_length)
return hashlib.pbkdf2_hmac('sha1', password, salt, iterations, key_length)
def _decrypt_aes_cbc_multi(ciphertext, keys, logger, initialization_vector=b' ' * 16):

4
yt_dlp/downloader/external.py
View File

@@ -1,4 +1,5 @@
import enum
import functools
import json
import os
import re
@@ -9,7 +10,6 @@ import time
import uuid
from .fragment import FragmentFD
from ..compat import functools
from ..networking import Request
from ..postprocessor.ffmpeg import EXT_TO_OUT_FORMATS, FFmpegPostProcessor
from ..utils import (
@@ -108,7 +108,7 @@ class ExternalFD(FragmentFD):
return all((
not info_dict.get('to_stdout') or Features.TO_STDOUT in cls.SUPPORTED_FEATURES,
'+' not in info_dict['protocol'] or Features.MULTIPLE_FORMATS in cls.SUPPORTED_FEATURES,
not traverse_obj(info_dict, ('hls_aes', ...), 'extra_param_to_segment_url'),
not traverse_obj(info_dict, ('hls_aes', ...), 'extra_param_to_segment_url', 'extra_param_to_key_url'),
all(proto in cls.SUPPORTED_PROTOCOLS for proto in info_dict['protocol'].split('+')),
))

24
yt_dlp/downloader/hls.py
View File

@@ -160,10 +160,12 @@ class HlsFD(FragmentFD):
extra_state = ctx.setdefault('extra_state', {})
format_index = info_dict.get('format_index')
extra_query = None
extra_param_to_segment_url = info_dict.get('extra_param_to_segment_url')
if extra_param_to_segment_url:
extra_query = urllib.parse.parse_qs(extra_param_to_segment_url)
extra_segment_query = None
if extra_param_to_segment_url := info_dict.get('extra_param_to_segment_url'):
extra_segment_query = urllib.parse.parse_qs(extra_param_to_segment_url)
extra_key_query = None
if extra_param_to_key_url := info_dict.get('extra_param_to_key_url'):
extra_key_query = urllib.parse.parse_qs(extra_param_to_key_url)
i = 0
media_sequence = 0
decrypt_info = {'METHOD': 'NONE'}
@@ -190,8 +192,8 @@ class HlsFD(FragmentFD):
if frag_index <= ctx['fragment_index']:
continue
frag_url = urljoin(man_url, line)
if extra_query:
frag_url = update_url_query(frag_url, extra_query)
if extra_segment_query:
frag_url = update_url_query(frag_url, extra_segment_query)
fragments.append({
'frag_index': frag_index,
@@ -212,8 +214,8 @@ class HlsFD(FragmentFD):
frag_index += 1
map_info = parse_m3u8_attributes(line[11:])
frag_url = urljoin(man_url, map_info.get('URI'))
if extra_query:
frag_url = update_url_query(frag_url, extra_query)
if extra_segment_query:
frag_url = update_url_query(frag_url, extra_segment_query)
if map_info.get('BYTERANGE'):
splitted_byte_range = map_info.get('BYTERANGE').split('@')
@@ -244,8 +246,10 @@ class HlsFD(FragmentFD):
decrypt_info['KEY'] = external_aes_key
else:
decrypt_info['URI'] = urljoin(man_url, decrypt_info['URI'])
if extra_query:
decrypt_info['URI'] = update_url_query(decrypt_info['URI'], extra_query)
if extra_key_query or extra_segment_query:
# Fall back to extra_segment_query to key for backwards compat
decrypt_info['URI'] = update_url_query(
decrypt_info['URI'], extra_key_query or extra_segment_query)
if decrypt_url != decrypt_info['URI']:
decrypt_info['KEY'] = None

29
yt_dlp/extractor/_extractors.py
View File

@@ -76,6 +76,7 @@ from .aenetworks import (
)
from .aeonco import AeonCoIE
from .afreecatv import (
AfreecaTVCatchStoryIE,
AfreecaTVIE,
AfreecaTVLiveIE,
AfreecaTVUserIE,
@@ -779,6 +780,7 @@ from .gopro import GoProIE
from .goshgay import GoshgayIE
from .gotostage import GoToStageIE
from .gputechconf import GPUTechConfIE
from .graspop import GraspopIE
from .gronkh import (
GronkhFeedIE,
GronkhIE,
@@ -969,6 +971,10 @@ from .la7 import (
LA7PodcastEpisodeIE,
LA7PodcastIE,
)
from .laracasts import (
LaracastsIE,
LaracastsPlaylistIE,
)
from .lastfm import (
LastFMIE,
LastFMPlaylistIE,
@@ -1113,12 +1119,15 @@ from .meipai import MeipaiIE
from .melonvod import MelonVODIE
from .metacritic import MetacriticIE
from .mgtv import MGTVIE
from .microsoftembed import MicrosoftEmbedIE
from .microsoftstream import MicrosoftStreamIE
from .microsoftvirtualacademy import (
MicrosoftVirtualAcademyCourseIE,
MicrosoftVirtualAcademyIE,
from .microsoftembed import (
MicrosoftBuildIE,
MicrosoftEmbedIE,
MicrosoftLearnEpisodeIE,
MicrosoftLearnPlaylistIE,
MicrosoftLearnSessionIE,
MicrosoftMediusIE,
)
from .microsoftstream import MicrosoftStreamIE
from .mildom import (
MildomClipIE,
MildomIE,
@@ -1603,6 +1612,7 @@ from .qqmusic import (
QQMusicPlaylistIE,
QQMusicSingerIE,
QQMusicToplistIE,
QQMusicVideoIE,
)
from .r7 import (
R7IE,
@@ -1928,6 +1938,10 @@ from .spreaker import (
)
from .springboardplatform import SpringboardPlatformIE
from .sprout import SproutIE
from .sproutvideo import (
SproutVideoIE,
VidsIoIE,
)
from .srgssr import (
SRGSSRIE,
SRGSSRPlayIE,
@@ -2310,6 +2324,7 @@ from .vidio import (
)
from .vidlii import VidLiiIE
from .vidly import VidlyIE
from .vidyard import VidyardIE
from .viewlift import (
ViewLiftEmbedIE,
ViewLiftIE,
@@ -2375,6 +2390,10 @@ from .vrt import (
VrtNUIE,
)
from .vtm import VTMIE
from .vtv import (
VTVIE,
VTVGoIE,
)
from .vuclip import VuClipIE
from .vvvvid import (
VVVVIDIE,

4
yt_dlp/extractor/abematv.py
View File

@@ -368,6 +368,7 @@ class AbemaTVIE(AbemaTVBaseIE):
info['episode_number'] = epis if epis < 2000 else None
is_live, m3u8_url = False, None
availability = 'public'
if video_type == 'now-on-air':
is_live = True
channel_url = 'https://api.abema.io/v1/channels'
@@ -389,6 +390,7 @@ class AbemaTVIE(AbemaTVBaseIE):
if 3 not in ondemand_types:
# cannot acquire decryption key for these streams
self.report_warning('This is a premium-only stream')
availability = 'premium_only'
info.update(traverse_obj(api_response, {
'series': ('series', 'title'),
'season': ('season', 'name'),
@@ -408,6 +410,7 @@ class AbemaTVIE(AbemaTVBaseIE):
headers=headers)
if not traverse_obj(api_response, ('slot', 'flags', 'timeshiftFree'), default=False):
self.report_warning('This is a premium-only stream')
availability = 'premium_only'
m3u8_url = f'https://vod-abematv.akamaized.net/slot/{video_id}/playlist.m3u8'
else:
@@ -425,6 +428,7 @@ class AbemaTVIE(AbemaTVBaseIE):
'description': description,
'formats': formats,
'is_live': is_live,
'availability': availability,
})
return info

41
yt_dlp/extractor/afreecatv.py
View File

@@ -72,7 +72,7 @@ class AfreecaTVIE(AfreecaTVBaseIE):
)\?.*?\bnTitleNo=|
vod\.afreecatv\.com/(PLAYER/STATION|player)/
)
(?P<id>\d+)
(?P<id>\d+)/?(?:$|[?#&])
'''
_TESTS = [{
'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=',
@@ -189,7 +189,7 @@ class AfreecaTVIE(AfreecaTVBaseIE):
headers={'Referer': url}, data=urlencode_postdata({
'nTitleNo': video_id,
'nApiLevel': 10,
}))['data']
}), impersonate=True)['data']
error_code = traverse_obj(data, ('code', {int}))
if error_code == -6221:
@@ -253,6 +253,43 @@ class AfreecaTVIE(AfreecaTVBaseIE):
return self.playlist_result(entries, video_id, multi_video=True, **common_info)
class AfreecaTVCatchStoryIE(AfreecaTVBaseIE):
IE_NAME = 'afreecatv:catchstory'
IE_DESC = 'afreecatv.com catch story'
_VALID_URL = r'https?://vod\.afreecatv\.com/player/(?P<id>\d+)/catchstory'
_TESTS = [{
'url': 'https://vod.afreecatv.com/player/103247/catchstory',
'info_dict': {
'id': '103247',
},
'playlist_count': 2,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._download_json(
'https://api.m.afreecatv.com/catchstory/a/view', video_id, headers={'Referer': url},
query={'aStoryListIdx': '', 'nStoryIdx': video_id}, impersonate=True)
return self.playlist_result(self._entries(data), video_id)
@staticmethod
def _entries(data):
# 'files' is always a list with 1 element
yield from traverse_obj(data, (
'data', lambda _, v: v['story_type'] == 'catch',
'catch_list', lambda _, v: v['files'][0]['file'], {
'id': ('files', 0, 'file_info_key', {str}),
'url': ('files', 0, 'file', {url_or_none}),
'duration': ('files', 0, 'duration', {functools.partial(int_or_none, scale=1000)}),
'title': ('title', {str}),
'uploader': ('writer_nick', {str}),
'uploader_id': ('writer_id', {str}),
'thumbnail': ('thumb', {url_or_none}),
'timestamp': ('write_timestamp', {int_or_none}),
}))
class AfreecaTVLiveIE(AfreecaTVBaseIE):
IE_NAME = 'afreecatv:live'
IE_DESC = 'afreecatv.com livestreams'

3
yt_dlp/extractor/arcpublishing.py
View File

@@ -4,6 +4,7 @@ from .common import InfoExtractor
from ..utils import (
extract_attributes,
int_or_none,
join_nonempty,
parse_iso8601,
try_get,
)
@@ -136,7 +137,7 @@ class ArcPublishingIE(InfoExtractor):
else:
vbr = int_or_none(s.get('bitrate'))
formats.append({
'format_id': f'{stream_type}-{vbr}' if vbr else stream_type,
'format_id': join_nonempty(stream_type, vbr),
'vbr': vbr,
'width': int_or_none(s.get('width')),
'height': int_or_none(s.get('height')),

4
yt_dlp/extractor/arkena.py
View File

@@ -131,8 +131,8 @@ class ArkenaIE(InfoExtractor):
formats.extend(self._extract_f4m_formats(
href, video_id, f4m_id='hds', fatal=False))
elif mime_type == 'application/dash+xml':
formats.extend(self._extract_f4m_formats(
href, video_id, f4m_id='hds', fatal=False))
formats.extend(self._extract_mpd_formats(
href, video_id, mpd_id='dash', fatal=False))
elif mime_type == 'application/vnd.ms-sstr+xml':
formats.extend(self._extract_ism_formats(
href, video_id, ism_id='mss', fatal=False))

19
yt_dlp/extractor/atresplayer.py
View File

@@ -33,14 +33,6 @@ class AtresPlayerIE(InfoExtractor):
]
_API_BASE = 'https://api.atresplayer.com/'
def _handle_error(self, e, code):
if isinstance(e.cause, HTTPError) and e.cause.status == code:
error = self._parse_json(e.cause.response.read(), None)
if error.get('error') == 'required_registered':
self.raise_login_required()
raise ExtractorError(error['error_description'], expected=True)
raise
def _perform_login(self, username, password):
self._request_webpage(
self._API_BASE + 'login', None, 'Downloading login page')
@@ -55,7 +47,9 @@ class AtresPlayerIE(InfoExtractor):
'password': password,
}))['targetUrl']
except ExtractorError as e:
self._handle_error(e, 400)
if isinstance(e.cause, HTTPError) and e.cause.status == 400:
raise ExtractorError('Invalid username and/or password', expected=True)
raise
self._request_webpage(target_url, None, 'Following Target URL')
@@ -66,7 +60,12 @@ class AtresPlayerIE(InfoExtractor):
episode = self._download_json(
self._API_BASE + 'client/v1/player/episode/' + video_id, video_id)
except ExtractorError as e:
self._handle_error(e, 403)
if isinstance(e.cause, HTTPError) and e.cause.status == 403:
error = self._parse_json(e.cause.response.read(), None)
if error.get('error') == 'required_registered':
self.raise_login_required()
raise ExtractorError(error['error_description'], expected=True)
raise
title = episode['titulo']

71
yt_dlp/extractor/banbye.py
View File

@@ -4,9 +4,13 @@ import urllib.parse
from .common import InfoExtractor
from ..utils import (
InAdvancePagedList,
determine_ext,
format_field,
int_or_none,
join_nonempty,
traverse_obj,
unified_timestamp,
url_or_none,
)
@@ -30,6 +34,7 @@ class BanByeBaseIE(InfoExtractor):
class BanByeIE(BanByeBaseIE):
_VALID_URL = r'https?://(?:www\.)?banbye\.com/(?:en/)?watch/(?P<id>[\w-]+)'
_TESTS = [{
# ['src']['mp4']['levels'] direct mp4 urls only
'url': 'https://banbye.com/watch/v_ytfmvkVYLE8T',
'md5': '2f4ea15c5ca259a73d909b2cfd558eb5',
'info_dict': {
@@ -58,6 +63,7 @@ class BanByeIE(BanByeBaseIE):
},
'playlist_mincount': 9,
}, {
# ['src']['mp4']['levels'] direct mp4 urls only
'url': 'https://banbye.com/watch/v_kb6_o1Kyq-CD',
'info_dict': {
'id': 'v_kb6_o1Kyq-CD',
@@ -77,6 +83,48 @@ class BanByeIE(BanByeBaseIE):
'view_count': int,
'comment_count': int,
},
}, {
# ['src']['hls']['levels'] variant m3u8 urls only; master m3u8 is 404
'url': 'https://banbye.com/watch/v_a_gPFuC9LoW5',
'info_dict': {
'id': 'v_a_gPFuC9LoW5',
'ext': 'mp4',
'title': 'md5:183524056bebdfa245fd6d214f63c0fe',
'description': 'md5:943ac87287ca98d28d8b8797719827c6',
'uploader': 'wRealu24',
'channel_id': 'ch_wrealu24',
'channel_url': 'https://banbye.com/channel/ch_wrealu24',
'upload_date': '20231113',
'timestamp': 1699874062,
'view_count': int,
'like_count': int,
'dislike_count': int,
'comment_count': int,
'thumbnail': 'https://cdn.banbye.com/video/v_a_gPFuC9LoW5/96.webp',
'tags': ['jaszczur', 'sejm', 'lewica', 'polska', 'ukrainizacja', 'pierwszeposiedzeniesejmu'],
},
'expected_warnings': ['Failed to download m3u8'],
}, {
# ['src']['hls']['masterPlaylist'] m3u8 only
'url': 'https://banbye.com/watch/v_B0rsKWsr-aaa',
'info_dict': {
'id': 'v_B0rsKWsr-aaa',
'ext': 'mp4',
'title': 'md5:00b254164b82101b3f9e5326037447ed',
'description': 'md5:3fd8b48aa81954ba024bc60f5de6e167',
'uploader': 'PSTV Piotr Szlachtowicz ',
'channel_id': 'ch_KV9EVObkB9wB',
'channel_url': 'https://banbye.com/channel/ch_KV9EVObkB9wB',
'upload_date': '20240629',
'timestamp': 1719646816,
'duration': 2377,
'view_count': int,
'like_count': int,
'dislike_count': int,
'comment_count': int,
'thumbnail': 'https://cdn.banbye.com/video/v_B0rsKWsr-aaa/96.webp',
'tags': ['Biden', 'Trump', 'Wybory', 'USA'],
},
}]
def _real_extract(self, url):
@@ -91,11 +139,24 @@ class BanByeIE(BanByeBaseIE):
'id': f'{quality}p',
'url': f'{self._CDN_BASE}/video/{video_id}/{quality}.webp',
} for quality in [48, 96, 144, 240, 512, 1080]]
formats = [{
'format_id': f'http-{quality}p',
'quality': quality,
'url': f'{self._CDN_BASE}/video/{video_id}/{quality}.mp4',
} for quality in data['quality']]
formats = []
url_data = self._download_json(f'{self._API_BASE}/videos/{video_id}/url', video_id, data=b'')
if master_url := traverse_obj(url_data, ('src', 'hls', 'masterPlaylist', {url_or_none})):
formats = self._extract_m3u8_formats(master_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
for format_id, format_url in traverse_obj(url_data, (
'src', ('mp4', 'hls'), 'levels', {dict.items}, lambda _, v: url_or_none(v[1]))):
ext = determine_ext(format_url)
is_hls = ext == 'm3u8'
formats.append({
'url': format_url,
'ext': 'mp4' if is_hls else ext,
'format_id': join_nonempty(is_hls and 'hls', format_id),
'protocol': 'm3u8_native' if is_hls else 'https',
'height': int_or_none(format_id),
})
self._remove_duplicate_formats(formats)
return {
'id': video_id,

2
yt_dlp/extractor/bandcamp.py
View File

@@ -41,7 +41,7 @@ class BandcampIE(InfoExtractor):
'uploader_id': 'youtube-dl',
'thumbnail': 'https://f4.bcbits.com/img/a3216802731_5.jpg',
},
'_skip': 'There is a limit of 200 free downloads / month for the test song',
'skip': 'There is a limit of 200 free downloads / month for the test song',
}, {
# free download
'url': 'http://benprunty.bandcamp.com/track/lanius-battle',

364
yt_dlp/extractor/bilibili.py
View File

@@ -31,12 +31,12 @@ from ..utils import (
mimetype2ext,
parse_count,
parse_qs,
parse_resolution,
qualities,
smuggle_url,
srt_subtitles_timecode,
str_or_none,
traverse_obj,
try_call,
unified_timestamp,
unsmuggle_url,
url_or_none,
@@ -47,6 +47,23 @@ from ..utils import (
class BilibiliBaseIE(InfoExtractor):
_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 = {}
@property
def is_logged_in(self):
return bool(self._get_cookies('https://api.bilibili.com').get('SESSDATA'))
def _check_missing_formats(self, play_info, formats):
parsed_qualities = set(traverse_obj(formats, (..., 'quality')))
missing_formats = join_nonempty(*[
traverse_obj(fmt, 'new_description', 'display_desc', 'quality')
for fmt in traverse_obj(play_info, (
'support_formats', lambda _, v: v['quality'] not in parsed_qualities))], delim=', ')
if missing_formats:
self.to_screen(
f'Format(s) {missing_formats} are missing; you have to login or '
f'become a premium member to download them. {self._login_hint()}')
def extract_formats(self, play_info):
format_names = {
@@ -86,18 +103,75 @@ class BilibiliBaseIE(InfoExtractor):
'format': format_names.get(video.get('id')),
} for video in traverse_obj(play_info, ('dash', 'video', ...)))
missing_formats = format_names.keys() - set(traverse_obj(formats, (..., 'quality')))
if missing_formats:
self.to_screen(f'Format(s) {", ".join(format_names[i] for i in missing_formats)} are missing; '
f'you have to login or become premium member to download them. {self._login_hint()}')
if formats:
self._check_missing_formats(play_info, formats)
fragments = traverse_obj(play_info, ('durl', lambda _, v: url_or_none(v['url']), {
'url': ('url', {url_or_none}),
'duration': ('length', {functools.partial(float_or_none, scale=1000)}),
'filesize': ('size', {int_or_none}),
}))
if fragments:
formats.append({
'url': fragments[0]['url'],
'filesize': sum(traverse_obj(fragments, (..., 'filesize'))),
**({
'fragments': fragments,
'protocol': 'http_dash_segments',
} if len(fragments) > 1 else {}),
**traverse_obj(play_info, {
'quality': ('quality', {int_or_none}),
'format_id': ('quality', {str_or_none}),
'format_note': ('quality', {lambda x: format_names.get(x)}),
'duration': ('timelength', {functools.partial(float_or_none, scale=1000)}),
}),
**parse_resolution(format_names.get(play_info.get('quality'))),
})
return formats
def _download_playinfo(self, video_id, cid, headers=None):
def _get_wbi_key(self, video_id):
if time.time() < self._wbi_key_cache.get('ts', 0) + self._WBI_KEY_CACHE_TIMEOUT:
return self._wbi_key_cache['key']
session_data = self._download_json(
'https://api.bilibili.com/x/web-interface/nav', video_id, note='Downloading wbi sign')
lookup = ''.join(traverse_obj(session_data, (
'data', 'wbi_img', ('img_url', 'sub_url'),
{lambda x: x.rpartition('/')[2].partition('.')[0]})))
# from getMixinKey() in the vendor js
mixin_key_enc_tab = [
46, 47, 18, 2, 53, 8, 23, 32, 15, 50, 10, 31, 58, 3, 45, 35, 27, 43, 5, 49,
33, 9, 42, 19, 29, 28, 14, 39, 12, 38, 41, 13, 37, 48, 7, 16, 24, 55, 40,
61, 26, 17, 0, 1, 60, 51, 30, 4, 22, 25, 54, 21, 56, 59, 6, 63, 57, 62, 11,
36, 20, 34, 44, 52,
]
self._wbi_key_cache.update({
'key': ''.join(lookup[i] for i in mixin_key_enc_tab)[:32],
'ts': time.time(),
})
return self._wbi_key_cache['key']
def _sign_wbi(self, params, video_id):
params['wts'] = round(time.time())
params = {
k: ''.join(filter(lambda char: char not in "!'()*", str(v)))
for k, v in sorted(params.items())
}
query = urllib.parse.urlencode(params)
params['w_rid'] = hashlib.md5(f'{query}{self._get_wbi_key(video_id)}'.encode()).hexdigest()
return params
def _download_playinfo(self, bvid, cid, headers=None, qn=None):
params = {'bvid': bvid, 'cid': cid, 'fnval': 4048}
if qn:
params['qn'] = qn
return self._download_json(
'https://api.bilibili.com/x/player/playurl', video_id,
query={'bvid': video_id, 'cid': cid, 'fnval': 4048},
note=f'Downloading video formats for cid {cid}', headers=headers)['data']
'https://api.bilibili.com/x/player/wbi/playurl', bvid,
query=self._sign_wbi(params, bvid), headers=headers,
note=f'Downloading video formats for cid {cid} {qn or ""}')['data']
def json2srt(self, json_data):
srt_data = ''
@@ -115,15 +189,15 @@ class BilibiliBaseIE(InfoExtractor):
}],
}
subtitle_info = traverse_obj(self._download_json(
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}'), ('data', 'subtitle'))
subs_list = traverse_obj(subtitle_info, ('subtitles', lambda _, v: v['subtitle_url'] and v['lan']))
if not subs_list and traverse_obj(subtitle_info, 'allow_submit'):
if not self._get_cookies('https://api.bilibili.com').get('SESSDATA'): # no login session cookie
self.report_warning(f'CC subtitles (if any) are only visible when logged in. {self._login_hint()}', only_once=True)
for s in subs_list:
note=f'Extracting subtitle info {cid}')
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)
for s in traverse_obj(video_info, (
'data', 'subtitle', 'subtitles', lambda _, v: v['subtitle_url'] and v['lan'])):
subtitles.setdefault(s['lan'], []).append({
'ext': 'srt',
'data': self.json2srt(self._download_json(s['subtitle_url'], video_id)),
@@ -203,15 +277,15 @@ class BilibiliBaseIE(InfoExtractor):
self._get_divisions(video_id, graph_version, edges, choice['edge_id'], cid_edges=cid_edges)
return cid_edges
def _get_interactive_entries(self, video_id, cid, metainfo):
def _get_interactive_entries(self, video_id, cid, metainfo, headers=None):
graph_version = traverse_obj(
self._download_json(
'https://api.bilibili.com/x/player/wbi/v2', video_id,
'Extracting graph version', query={'bvid': video_id, 'cid': cid}),
'Extracting graph version', query={'bvid': video_id, 'cid': cid}, headers=headers),
('data', 'interaction', 'graph_version', {int_or_none}))
cid_edges = self._get_divisions(video_id, graph_version, {1: {'cid': cid}}, 1)
for cid, edges in cid_edges.items():
play_info = self._download_playinfo(video_id, cid)
play_info = self._download_playinfo(video_id, cid, headers=headers)
yield {
**metainfo,
'id': f'{video_id}_{cid}',
@@ -243,17 +317,17 @@ class BiliBiliIE(BilibiliBaseIE):
'timestamp': 1488353834,
'like_count': int,
'view_count': int,
'_old_archive_ids': ['bilibili 8903802_part1'],
},
}, {
'note': 'old av URL version',
'url': 'http://www.bilibili.com/video/av1074402/',
'info_dict': {
'thumbnail': r're:^https?://.*\.(jpg|jpeg)$',
'id': 'BV11x411K7CN',
'ext': 'mp4',
'title': '【金坷垃】金泡沫',
'uploader': '菊子桑',
'uploader_id': '156160',
'id': 'BV11x411K7CN',
'title': '【金坷垃】金泡沫',
'duration': 308.36,
'upload_date': '20140420',
'timestamp': 1397983878,
@@ -262,6 +336,8 @@ class BiliBiliIE(BilibiliBaseIE):
'comment_count': int,
'view_count': int,
'tags': list,
'thumbnail': r're:^https?://.*\.(jpg|jpeg)$',
'_old_archive_ids': ['bilibili 1074402_part1'],
},
'params': {'skip_download': True},
}, {
@@ -288,6 +364,7 @@ class BiliBiliIE(BilibiliBaseIE):
'view_count': int,
'description': 'md5:e3c401cf7bc363118d1783dd74068a68',
'duration': 90.314,
'_old_archive_ids': ['bilibili 498159642_part1'],
},
}],
}, {
@@ -308,28 +385,8 @@ class BiliBiliIE(BilibiliBaseIE):
'view_count': int,
'description': 'md5:e3c401cf7bc363118d1783dd74068a68',
'duration': 90.314,
'_old_archive_ids': ['bilibili 498159642_part1'],
},
}, {
'note': 'video has subtitles',
'url': 'https://www.bilibili.com/video/BV12N4y1M7rh',
'info_dict': {
'id': 'BV12N4y1M7rh',
'ext': 'mp4',
'title': 'md5:96e8bb42c2b432c0d4ce3434a61479c1',
'tags': list,
'description': 'md5:afde2b7ba9025c01d9e3dde10de221e4',
'duration': 313.557,
'upload_date': '20220709',
'uploader': '小夫太渴',
'timestamp': 1657347907,
'uploader_id': '1326814124',
'comment_count': int,
'view_count': int,
'like_count': int,
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'subtitles': 'count:2',
},
'params': {'listsubtitles': True},
}, {
'url': 'https://www.bilibili.com/video/av8903802/',
'info_dict': {
@@ -347,6 +404,7 @@ class BiliBiliIE(BilibiliBaseIE):
'comment_count': int,
'view_count': int,
'like_count': int,
'_old_archive_ids': ['bilibili 8903802_part1'],
},
'params': {
'skip_download': True,
@@ -370,6 +428,7 @@ class BiliBiliIE(BilibiliBaseIE):
'view_count': int,
'like_count': int,
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'_old_archive_ids': ['bilibili 463665680_part1'],
},
'params': {'skip_download': True},
}, {
@@ -388,8 +447,8 @@ class BiliBiliIE(BilibiliBaseIE):
'view_count': int,
'like_count': int,
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'_old_archive_ids': ['bilibili 893839363_part1'],
},
'params': {'skip_download': True},
}, {
'note': 'newer festival video',
'url': 'https://www.bilibili.com/festival/2023honkaiimpact3gala?bvid=BV1ay4y1d77f',
@@ -406,8 +465,57 @@ class BiliBiliIE(BilibiliBaseIE):
'view_count': int,
'like_count': int,
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'_old_archive_ids': ['bilibili 778246196_part1'],
},
}, {
'note': 'legacy flv/mp4 video',
'url': 'https://www.bilibili.com/video/BV1ms411Q7vw/?p=4',
'info_dict': {
'id': 'BV1ms411Q7vw_p4',
'title': '[搞笑]【动画】云南方言快乐生产线出品 p04 新烧包谷之漫游桃花岛',
'timestamp': 1458222815,
'upload_date': '20160317',
'description': '云南方言快乐生产线出品',
'duration': float,
'uploader': '一笑颠天',
'uploader_id': '3916081',
'view_count': int,
'comment_count': int,
'like_count': int,
'tags': list,
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'_old_archive_ids': ['bilibili 4120229_part4'],
},
'params': {'extractor_args': {'bilibili': {'prefer_multi_flv': ['32']}}},
'playlist_count': 19,
'playlist': [{
'info_dict': {
'id': 'BV1ms411Q7vw_p4_0',
'ext': 'flv',
'title': '[搞笑]【动画】云南方言快乐生产线出品 p04 新烧包谷之漫游桃花岛',
'duration': 399.102,
},
}],
}, {
'note': 'legacy mp4-only video',
'url': 'https://www.bilibili.com/video/BV1nx411u79K',
'info_dict': {
'id': 'BV1nx411u79K',
'ext': 'mp4',
'title': '【练习室】201603声乐练习《No Air》with VigoVan',
'timestamp': 1508893551,
'upload_date': '20171025',
'description': '@ZERO-G伯远\n声乐练习 《No Air》with Vigo Van',
'duration': 80.384,
'uploader': '伯远',
'uploader_id': '10584494',
'comment_count': int,
'view_count': int,
'like_count': int,
'tags': list,
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'_old_archive_ids': ['bilibili 15700301_part1'],
},
'params': {'skip_download': True},
}, {
'note': 'interactive/split-path video',
'url': 'https://www.bilibili.com/video/BV1af4y1H7ga/',
@@ -425,6 +533,7 @@ class BiliBiliIE(BilibiliBaseIE):
'view_count': int,
'like_count': int,
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'_old_archive_ids': ['bilibili 292734508_part1'],
},
'playlist_count': 33,
'playlist': [{
@@ -443,6 +552,7 @@ class BiliBiliIE(BilibiliBaseIE):
'view_count': int,
'like_count': int,
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'_old_archive_ids': ['bilibili 292734508_part1'],
},
}],
}, {
@@ -465,6 +575,29 @@ class BiliBiliIE(BilibiliBaseIE):
'upload_date': '20191021',
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
},
}, {
'note': 'video has subtitles, which requires login',
'url': 'https://www.bilibili.com/video/BV12N4y1M7rh',
'info_dict': {
'id': 'BV12N4y1M7rh',
'ext': 'mp4',
'title': 'md5:96e8bb42c2b432c0d4ce3434a61479c1',
'tags': list,
'description': 'md5:afde2b7ba9025c01d9e3dde10de221e4',
'duration': 313.557,
'upload_date': '20220709',
'uploader': '小夫太渴',
'timestamp': 1657347907,
'uploader_id': '1326814124',
'comment_count': int,
'view_count': int,
'like_count': int,
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
'subtitles': 'count:2', # login required for CC subtitle
'_old_archive_ids': ['bilibili 898179753_part1'],
},
'params': {'listsubtitles': True},
'skip': 'login required for subtitle',
}, {
'url': 'https://www.bilibili.com/video/BV1jL41167ZG/',
'info_dict': {
@@ -498,8 +631,9 @@ class BiliBiliIE(BilibiliBaseIE):
if not self._match_valid_url(urlh.url):
return self.url_result(urlh.url)
initial_state = self._search_json(r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', video_id)
headers['Referer'] = url
initial_state = self._search_json(r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', video_id)
is_festival = 'videoData' not in initial_state
if is_festival:
video_data = initial_state['videoInfo']
@@ -548,7 +682,6 @@ class BiliBiliIE(BilibiliBaseIE):
aid = video_data.get('aid')
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')
festival_info = {}
@@ -586,18 +719,65 @@ class BiliBiliIE(BilibiliBaseIE):
is_interactive = traverse_obj(video_data, ('rights', 'is_stein_gate'))
if is_interactive:
return self.playlist_result(
self._get_interactive_entries(video_id, cid, metainfo), **metainfo,
self._get_interactive_entries(video_id, cid, metainfo, headers=headers), **metainfo,
duration=traverse_obj(initial_state, ('videoData', 'duration', {int_or_none})),
__post_extractor=self.extract_comments(aid))
else:
return {
**metainfo,
'duration': float_or_none(play_info.get('timelength'), scale=1000),
'chapters': self._get_chapters(aid, cid),
'subtitles': self.extract_subtitles(video_id, cid),
'formats': self.extract_formats(play_info),
'__post_extractor': self.extract_comments(aid),
}
formats = self.extract_formats(play_info)
if not traverse_obj(play_info, ('dash')):
# we only have legacy formats and need additional work
has_qn = lambda x: x in traverse_obj(formats, (..., 'quality'))
for qn in traverse_obj(play_info, ('accept_quality', lambda _, v: not has_qn(v), {int})):
formats.extend(traverse_obj(
self.extract_formats(self._download_playinfo(video_id, cid, headers=headers, qn=qn)),
lambda _, v: not has_qn(v['quality'])))
self._check_missing_formats(play_info, formats)
flv_formats = traverse_obj(formats, lambda _, v: v['fragments'])
if flv_formats and len(flv_formats) < len(formats):
# Flv and mp4 are incompatible due to `multi_video` workaround, so drop one
if not self._configuration_arg('prefer_multi_flv'):
dropped_fmts = ', '.join(
f'{f.get("format_note")} ({f.get("format_id")})' for f in flv_formats)
formats = traverse_obj(formats, lambda _, v: not v.get('fragments'))
if dropped_fmts:
self.to_screen(
f'Dropping incompatible flv format(s) {dropped_fmts} since mp4 is available. '
'To extract flv, pass --extractor-args "bilibili:prefer_multi_flv"')
else:
formats = traverse_obj(
# XXX: Filtering by extractor-arg is for testing purposes
formats, lambda _, v: v['quality'] == int(self._configuration_arg('prefer_multi_flv')[0]),
) or [max(flv_formats, key=lambda x: x['quality'])]
if traverse_obj(formats, (0, 'fragments')):
# We have flv formats, which are individual short videos with their own timestamps and metainfo
# Binary concatenation corrupts their timestamps, so we need a `multi_video` workaround
return {
**metainfo,
'_type': 'multi_video',
'entries': [{
'id': f'{metainfo["id"]}_{idx}',
'title': metainfo['title'],
'http_headers': metainfo['http_headers'],
'formats': [{
**fragment,
'format_id': formats[0].get('format_id'),
}],
'subtitles': self.extract_subtitles(video_id, cid) if idx == 0 else None,
'__post_extractor': self.extract_comments(aid) if idx == 0 else None,
} for idx, fragment in enumerate(formats[0]['fragments'])],
'duration': float_or_none(play_info.get('timelength'), scale=1000),
}
else:
return {
**metainfo,
'formats': formats,
'duration': float_or_none(play_info.get('timelength'), scale=1000),
'chapters': self._get_chapters(aid, cid),
'subtitles': self.extract_subtitles(video_id, cid),
'__post_extractor': self.extract_comments(aid),
}
class BiliBiliBangumiIE(BilibiliBaseIE):
@@ -968,7 +1148,7 @@ class BilibiliCheeseSeasonIE(BilibiliCheeseBaseIE):
}))
class BilibiliSpaceBaseIE(InfoExtractor):
class BilibiliSpaceBaseIE(BilibiliBaseIE):
def _extract_playlist(self, fetch_page, get_metadata, get_entries):
first_page = fetch_page(0)
metadata = get_metadata(first_page)
@@ -988,73 +1168,53 @@ class BilibiliSpaceVideoIE(BilibiliSpaceBaseIE):
'id': '3985676',
},
'playlist_mincount': 178,
'skip': 'login required',
}, {
'url': 'https://space.bilibili.com/313580179/video',
'info_dict': {
'id': '313580179',
},
'playlist_mincount': 92,
'skip': 'login required',
}]
def _extract_signature(self, playlist_id):
session_data = self._download_json('https://api.bilibili.com/x/web-interface/nav', playlist_id, fatal=False)
key_from_url = lambda x: x[x.rfind('/') + 1:].split('.')[0]
img_key = traverse_obj(
session_data, ('data', 'wbi_img', 'img_url', {key_from_url})) or '34478ba821254d9d93542680e3b86100'
sub_key = traverse_obj(
session_data, ('data', 'wbi_img', 'sub_url', {key_from_url})) or '7e16a90d190a4355a78fd00b32a38de6'
session_key = img_key + sub_key
signature_values = []
for position in (
46, 47, 18, 2, 53, 8, 23, 32, 15, 50, 10, 31, 58, 3, 45, 35, 27, 43, 5, 49, 33, 9, 42, 19, 29, 28, 14, 39,
12, 38, 41, 13, 37, 48, 7, 16, 24, 55, 40, 61, 26, 17, 0, 1, 60, 51, 30, 4, 22, 25, 54, 21, 56, 59, 6, 63,
57, 62, 11, 36, 20, 34, 44, 52,
):
char_at_position = try_call(lambda: session_key[position])
if char_at_position:
signature_values.append(char_at_position)
return ''.join(signature_values)[:32]
def _real_extract(self, url):
playlist_id, is_video_url = self._match_valid_url(url).group('id', 'video')
if not is_video_url:
self.to_screen('A channel URL was given. Only the channel\'s videos will be downloaded. '
'To download audios, add a "/audio" to the URL')
signature = self._extract_signature(playlist_id)
def fetch_page(page_idx):
query = {
'keyword': '',
'mid': playlist_id,
'order': 'pubdate',
'order': traverse_obj(parse_qs(url), ('order', 0)) or 'pubdate',
'order_avoided': 'true',
'platform': 'web',
'pn': page_idx + 1,
'ps': 30,
'tid': 0,
'web_location': 1550101,
'wts': int(time.time()),
}
query['w_rid'] = hashlib.md5(f'{urllib.parse.urlencode(query)}{signature}'.encode()).hexdigest()
try:
response = self._download_json('https://api.bilibili.com/x/space/wbi/arc/search',
playlist_id, note=f'Downloading page {page_idx}', query=query,
headers={'referer': url})
response = self._download_json(
'https://api.bilibili.com/x/space/wbi/arc/search', playlist_id,
query=self._sign_wbi(query, playlist_id),
note=f'Downloading space page {page_idx}', headers={'Referer': url})
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 412:
raise ExtractorError(
'Request is blocked by server (412), please add cookies, wait and try later.', expected=True)
raise
if response['code'] in (-352, -401):
status_code = response['code']
if status_code == -401:
raise ExtractorError(
f'Request is blocked by server ({-response["code"]}), '
'please add cookies, wait and try later.', expected=True)
'Request is blocked by server (401), please add cookies, wait and try later.', expected=True)
elif status_code == -352 and not self.is_logged_in:
self.raise_login_required('Request is rejected, you need to login to access playlist')
elif status_code != 0:
raise ExtractorError(f'Request failed ({status_code}): {response.get("message") or "Unknown error"}')
return response['data']
def get_metadata(page_data):
@@ -1280,7 +1440,10 @@ class BilibiliWatchlaterIE(BilibiliSpaceListBaseIE):
_VALID_URL = r'https?://(?:www\.)?bilibili\.com/watchlater/?(?:[?#]|$)'
_TESTS = [{
'url': 'https://www.bilibili.com/watchlater/#/list',
'info_dict': {'id': 'watchlater'},
'info_dict': {
'id': r're:\d+',
'title': '稍后再看',
},
'playlist_mincount': 0,
'skip': 'login required',
}]
@@ -1356,14 +1519,19 @@ class BilibiliPlaylistIE(BilibiliSpaceListBaseIE):
'skip': 'redirect url',
}, {
'url': 'https://www.bilibili.com/list/watchlater',
'info_dict': {'id': 'watchlater'},
'info_dict': {
'id': r're:2_\d+',
'title': '稍后再看',
'uploader': str,
'uploader_id': str,
},
'playlist_mincount': 0,
'skip': 'login required',
}, {
'url': 'https://www.bilibili.com/medialist/play/watchlater',
'info_dict': {'id': 'watchlater'},
'playlist_mincount': 0,
'skip': 'login required',
'skip': 'redirect url & login required',
}]
def _extract_medialist(self, query, list_id):
@@ -1414,7 +1582,7 @@ class BilibiliPlaylistIE(BilibiliSpaceListBaseIE):
'title': ('title', {str}),
'uploader': ('upper', 'name', {str}),
'uploader_id': ('upper', 'mid', {str_or_none}),
'timestamp': ('ctime', {int_or_none}),
'timestamp': ('ctime', {int_or_none}, {lambda x: x or None}),
'thumbnail': ('cover', {url_or_none}),
})),
}
@@ -1808,7 +1976,8 @@ class BiliIntlBaseIE(InfoExtractor):
public_key = Cryptodome.RSA.importKey(key_data['key'])
password_hash = Cryptodome.PKCS1_v1_5.new(public_key).encrypt((key_data['hash'] + password).encode())
login_post = self._download_json(
'https://passport.bilibili.tv/x/intl/passport-login/web/login/password?lang=en-US', None, data=urlencode_postdata({
'https://passport.bilibili.tv/x/intl/passport-login/web/login/password?lang=en-US', None,
data=urlencode_postdata({
'username': username,
'password': base64.b64encode(password_hash).decode('ascii'),
'keep_me': 'true',
@@ -2140,7 +2309,8 @@ class BiliIntlSeriesIE(BiliIntlBaseIE):
def _real_extract(self, url):
series_id = self._match_id(url)
series_info = self._call_api(f'/web/v2/ogv/play/season_info?season_id={series_id}&platform=web', series_id).get('season') or {}
series_info = self._call_api(
f'/web/v2/ogv/play/season_info?season_id={series_id}&platform=web', series_id).get('season') or {}
return self.playlist_result(
self._entries(series_id), series_id, series_info.get('title'), series_info.get('description'),
categories=traverse_obj(series_info, ('styles', ..., 'title'), expected_type=str_or_none),

16
yt_dlp/extractor/bitchute.py
View File

@@ -24,7 +24,7 @@ from ..utils import (
class BitChuteIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?bitchute\.com/(?:video|embed|torrent/[^/]+)/(?P<id>[^/?#&]+)'
_VALID_URL = r'https?://(?:(?:www|old)\.)?bitchute\.com/(?:video|embed|torrent/[^/]+)/(?P<id>[^/?#&]+)'
_EMBED_REGEX = [rf'<(?:script|iframe)[^>]+\bsrc=(["\'])(?P<url>{_VALID_URL})']
_TESTS = [{
'url': 'https://www.bitchute.com/video/UGlrF9o9b-Q/',
@@ -91,6 +91,9 @@ class BitChuteIE(InfoExtractor):
}, {
'url': 'https://www.bitchute.com/torrent/Zee5BE49045h/szoMrox2JEI.webtorrent',
'only_matching': True,
}, {
'url': 'https://old.bitchute.com/video/UGlrF9o9b-Q/',
'only_matching': True,
}]
_GEO_BYPASS = False
@@ -132,7 +135,7 @@ class BitChuteIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
f'https://www.bitchute.com/video/{video_id}', video_id, headers=self._HEADERS)
f'https://old.bitchute.com/video/{video_id}', video_id, headers=self._HEADERS)
self._raise_if_restricted(webpage)
publish_date = clean_html(get_element_by_class('video-publish-date', webpage))
@@ -171,13 +174,13 @@ class BitChuteIE(InfoExtractor):
class BitChuteChannelIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?bitchute\.com/(?P<type>channel|playlist)/(?P<id>[^/?#&]+)'
_VALID_URL = r'https?://(?:(?:www|old)\.)?bitchute\.com/(?P<type>channel|playlist)/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://www.bitchute.com/channel/bitchute/',
'info_dict': {
'id': 'bitchute',
'title': 'BitChute',
'description': 'md5:5329fb3866125afa9446835594a9b138',
'description': 'md5:2134c37d64fc3a4846787c402956adac',
},
'playlist': [
{
@@ -210,6 +213,9 @@ class BitChuteChannelIE(InfoExtractor):
'title': 'Bruce MacDonald and "The Light of Darkness"',
'description': 'md5:747724ef404eebdfc04277714f81863e',
},
}, {
'url': 'https://old.bitchute.com/playlist/wV9Imujxasw9/',
'only_matching': True,
}]
_TOKEN = 'zyG6tQcGPE5swyAEFLqKUwMuMMuF6IO2DZ6ZDQjGfsL0e4dcTLwqkTTul05Jdve7'
@@ -230,7 +236,7 @@ class BitChuteChannelIE(InfoExtractor):
@staticmethod
def _make_url(playlist_id, playlist_type):
return f'https://www.bitchute.com/{playlist_type}/{playlist_id}/'
return f'https://old.bitchute.com/{playlist_type}/{playlist_id}/'
def _fetch_page(self, playlist_id, playlist_type, page_num):
playlist_url = self._make_url(playlist_id, playlist_type)

20
yt_dlp/extractor/brightcove.py
View File

@@ -18,6 +18,7 @@ from ..utils import (
fix_xml_ampersands,
float_or_none,
int_or_none,
join_nonempty,
js_to_json,
mimetype2ext,
parse_iso8601,
@@ -386,7 +387,7 @@ class BrightcoveLegacyIE(InfoExtractor):
@classmethod
def _make_brightcove_url(cls, params):
return update_url_query(
'http://c.brightcove.com/services/viewer/htmlFederated', params)
'https://c.brightcove.com/services/viewer/htmlFederated', params)
@classmethod
def _extract_brightcove_url(cls, webpage):
@@ -470,7 +471,7 @@ class BrightcoveLegacyIE(InfoExtractor):
if referer:
headers['Referer'] = referer
player_page = self._download_webpage(
'http://link.brightcove.com/services/player/bcpid' + player_id[0],
'https://link.brightcove.com/services/player/bcpid' + player_id[0],
video_id, headers=headers, fatal=False)
if player_page:
player_key = self._search_regex(
@@ -480,7 +481,7 @@ class BrightcoveLegacyIE(InfoExtractor):
enc_pub_id = player_key.split(',')[1].replace('~', '=')
publisher_id = struct.unpack('>Q', base64.urlsafe_b64decode(enc_pub_id))[0]
if publisher_id:
brightcove_new_url = f'http://players.brightcove.net/{publisher_id}/default_default/index.html?videoId={video_id}'
brightcove_new_url = f'https://players.brightcove.net/{publisher_id}/default_default/index.html?videoId={video_id}'
if referer:
brightcove_new_url = smuggle_url(brightcove_new_url, {'referrer': referer})
return self.url_result(brightcove_new_url, BrightcoveNewIE.ie_key(), video_id)
@@ -538,12 +539,7 @@ class BrightcoveNewBaseIE(AdobePassIE):
})
def build_format_id(kind):
format_id = kind
if tbr:
format_id += f'-{int(tbr)}k'
if height:
format_id += f'-{height}p'
return format_id
return join_nonempty(kind, tbr and f'{int(tbr)}k', height and f'{height}p')
if src or streaming_src:
f.update({
@@ -801,7 +797,7 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
# Look for iframe embeds [1]
for _, url in re.findall(
r'<iframe[^>]+src=(["\'])((?:https?:)?//players\.brightcove\.net/\d+/[^/]+/index\.html.+?)\1', webpage):
entries.append(url if url.startswith('http') else 'http:' + url)
entries.append(url if url.startswith(('http:', 'https:')) else 'https:' + url)
# Look for <video> tags [2] and embed_in_page embeds [3]
# [2] looks like:
@@ -830,7 +826,7 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
player_id = player_id or attrs.get('data-player') or 'default'
embed = embed or attrs.get('data-embed') or 'default'
bc_url = f'http://players.brightcove.net/{account_id}/{player_id}_{embed}/index.html?videoId={video_id}'
bc_url = f'https://players.brightcove.net/{account_id}/{player_id}_{embed}/index.html?videoId={video_id}'
# Some brightcove videos may be embedded with video tag only and
# without script tag or any mentioning of brightcove at all. Such
@@ -867,7 +863,7 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
store_pk = lambda x: self.cache.store('brightcove', policy_key_id, x)
def extract_policy_key():
base_url = f'http://players.brightcove.net/{account_id}/{player_id}_{embed}/'
base_url = f'https://players.brightcove.net/{account_id}/{player_id}_{embed}/'
config = self._download_json(
base_url + 'config.json', video_id, fatal=False) or {}
policy_key = try_get(

6
yt_dlp/extractor/cbc.py
View File

@@ -455,10 +455,8 @@ class CBCGemIE(InfoExtractor):
def claims_token_expired(self):
exp = self._get_claims_token_expiry()
if exp - time.time() < 10:
# It will expire in less than 10 seconds, or has already expired
return True
return False
# It will expire in less than 10 seconds, or has already expired
return exp - time.time() < 10
def claims_token_valid(self):
return self._claims_token is not None and not self.claims_token_expired()

1
yt_dlp/extractor/cbsnews.py
View File

@@ -1,6 +1,5 @@
import base64
import re
import urllib.error
import urllib.parse
import zlib

69
yt_dlp/extractor/cellebrite.py
View File

@@ -1,63 +1,50 @@
from .common import InfoExtractor
from ..utils import traverse_obj
from .vidyard import VidyardBaseIE, VidyardIE
from ..utils import ExtractorError, make_archive_id, url_basename
class CellebriteIE(InfoExtractor):
class CellebriteIE(VidyardBaseIE):
_VALID_URL = r'https?://cellebrite\.com/(?:\w+)?/(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://cellebrite.com/en/collect-data-from-android-devices-with-cellebrite-ufed/',
'info_dict': {
'id': '16025876',
'id': 'ZqmUss3dQfEMGpauambPuH',
'display_id': '16025876',
'ext': 'mp4',
'description': 'md5:174571cb97083fd1d457d75c684f4e2b',
'thumbnail': 'https://cellebrite.com/wp-content/uploads/2021/05/Chat-Capture-1024x559.png',
'title': 'Ask the Expert: Chat Capture - Collect Data from Android Devices in Cellebrite UFED',
'duration': 455,
'tags': [],
'description': 'md5:dee48fe12bbae5c01fe6a053f7676da4',
'thumbnail': 'https://cellebrite.com/wp-content/uploads/2021/05/Chat-Capture-1024x559.png',
'duration': 455.979,
'_old_archive_ids': ['cellebrite 16025876'],
},
}, {
'url': 'https://cellebrite.com/en/how-to-lawfully-collect-the-maximum-amount-of-data-from-android-devices/',
'info_dict': {
'id': '29018255',
'id': 'QV1U8a2yzcxigw7VFnqKyg',
'display_id': '29018255',
'ext': 'mp4',
'duration': 134,
'tags': [],
'description': 'md5:e9a3d124c7287b0b07bad2547061cacf',
'title': 'How to Lawfully Collect the Maximum Amount of Data From Android Devices',
'description': 'md5:0e943a9ac14c374d5d74faed634d773c',
'thumbnail': 'https://cellebrite.com/wp-content/uploads/2022/07/How-to-Lawfully-Collect-the-Maximum-Amount-of-Data-From-Android-Devices.png',
'title': 'Android Extractions Explained',
'duration': 134.315,
'_old_archive_ids': ['cellebrite 29018255'],
},
}]
def _get_formats_and_subtitles(self, json_data, display_id):
formats = [{'url': url} for url in traverse_obj(json_data, ('mp4', ..., 'url')) or []]
subtitles = {}
for url in traverse_obj(json_data, ('hls', ..., 'url')) or []:
fmt, sub = self._extract_m3u8_formats_and_subtitles(
url, display_id, ext='mp4', headers={'Referer': 'https://play.vidyard.com/'})
formats.extend(fmt)
self._merge_subtitles(sub, target=subtitles)
return formats, subtitles
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
slug = self._match_id(url)
webpage = self._download_webpage(url, slug)
vidyard_url = next(VidyardIE._extract_embed_urls(url, webpage), None)
if not vidyard_url:
raise ExtractorError('No Vidyard video embeds found on page')
player_uuid = self._search_regex(
r'<img\s[^>]*\bdata-uuid\s*=\s*"([^"\?]+)', webpage, 'player UUID')
json_data = self._download_json(
f'https://play.vidyard.com/player/{player_uuid}.json', display_id)['payload']['chapters'][0]
video_id = url_basename(vidyard_url)
info = self._process_video_json(self._fetch_video_json(video_id)['chapters'][0], video_id)
if info.get('display_id'):
info['_old_archive_ids'] = [make_archive_id(self, info['display_id'])]
if thumbnail := self._og_search_thumbnail(webpage, default=None):
info.setdefault('thumbnails', []).append({'url': thumbnail})
formats, subtitles = self._get_formats_and_subtitles(json_data['sources'], display_id)
return {
'id': str(json_data['videoId']),
'title': json_data.get('name') or self._og_search_title(webpage),
'formats': formats,
'subtitles': subtitles,
'description': json_data.get('description') or self._og_search_description(webpage),
'duration': json_data.get('seconds'),
'tags': json_data.get('tags'),
'thumbnail': self._og_search_thumbnail(webpage),
'http_headers': {'Referer': 'https://play.vidyard.com/'},
'description': self._og_search_description(webpage, default=None),
**info,
}

37
yt_dlp/extractor/chzzk.py
View File

@@ -36,7 +36,7 @@ class CHZZKLiveIE(InfoExtractor):
def _real_extract(self, url):
channel_id = self._match_id(url)
live_detail = self._download_json(
f'https://api.chzzk.naver.com/service/v2/channels/{channel_id}/live-detail', channel_id,
f'https://api.chzzk.naver.com/service/v3/channels/{channel_id}/live-detail', channel_id,
note='Downloading channel info', errnote='Unable to download channel info')['content']
if live_detail.get('status') == 'CLOSE':
@@ -106,12 +106,45 @@ class CHZZKVideoIE(InfoExtractor):
'upload_date': '20231219',
'view_count': int,
},
'skip': 'Replay video is expired',
}, {
# Manually uploaded video
'url': 'https://chzzk.naver.com/video/1980',
'info_dict': {
'id': '1980',
'ext': 'mp4',
'title': '※시청주의※한번보면 잊기 힘든 영상',
'channel': '라디유radiyu',
'channel_id': '68f895c59a1043bc5019b5e08c83a5c5',
'channel_is_verified': False,
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 95,
'timestamp': 1703102631.722,
'upload_date': '20231220',
'view_count': int,
},
}, {
# Partner channel replay video
'url': 'https://chzzk.naver.com/video/2458',
'info_dict': {
'id': '2458',
'ext': 'mp4',
'title': '첫 방송',
'channel': '강지',
'channel_id': 'b5ed5db484d04faf4d150aedd362f34b',
'channel_is_verified': True,
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 4433,
'timestamp': 1703307460.214,
'upload_date': '20231223',
'view_count': int,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
video_meta = self._download_json(
f'https://api.chzzk.naver.com/service/v2/videos/{video_id}', video_id,
f'https://api.chzzk.naver.com/service/v3/videos/{video_id}', video_id,
note='Downloading video info', errnote='Unable to download video info')['content']
formats, subtitles = self._extract_mpd_formats_and_subtitles(
f'https://apis.naver.com/neonplayer/vodplay/v1/playback/{video_meta["videoId"]}', video_id,

17
yt_dlp/extractor/cloudflarestream.py
View File

@@ -6,11 +6,11 @@ from .common import InfoExtractor
class CloudflareStreamIE(InfoExtractor):
_SUBDOMAIN_RE = r'(?:(?:watch|iframe|customer-\w+)\.)?'
_DOMAIN_RE = r'(?:cloudflarestream\.com|(?:videodelivery|bytehighway)\.net)'
_EMBED_RE = rf'embed\.{_DOMAIN_RE}/embed/[^/]+\.js\?.*?\bvideo='
_ID_RE = r'[\da-f]{32}|[\w-]+\.[\w-]+\.[\w-]+'
_EMBED_RE = rf'(?:embed\.|{_SUBDOMAIN_RE}){_DOMAIN_RE}/embed/[^/?#]+\.js\?(?:[^#]+&)?video='
_ID_RE = r'[\da-f]{32}|eyJ[\w-]+\.[\w-]+\.[\w-]+'
_VALID_URL = rf'https?://(?:{_SUBDOMAIN_RE}{_DOMAIN_RE}/|{_EMBED_RE})(?P<id>{_ID_RE})'
_EMBED_REGEX = [
rf'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//{_EMBED_RE}(?:{_ID_RE}).*?)\1',
rf'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//{_EMBED_RE}(?:{_ID_RE})(?:(?!\1).)*)\1',
rf'<iframe[^>]+\bsrc=["\'](?P<url>https?://{_SUBDOMAIN_RE}{_DOMAIN_RE}/[\da-f]{{32}})',
]
_TESTS = [{
@@ -24,6 +24,14 @@ class CloudflareStreamIE(InfoExtractor):
'params': {
'skip_download': 'm3u8',
},
}, {
'url': 'https://watch.cloudflarestream.com/embed/sdk-iframe-integration.fla9.latest.js?video=0e8e040aec776862e1d632a699edf59e',
'info_dict': {
'id': '0e8e040aec776862e1d632a699edf59e',
'ext': 'mp4',
'title': '0e8e040aec776862e1d632a699edf59e',
'thumbnail': 'https://videodelivery.net/0e8e040aec776862e1d632a699edf59e/thumbnails/thumbnail.jpg',
},
}, {
'url': 'https://watch.cloudflarestream.com/9df17203414fd1db3e3ed74abbe936c1',
'only_matching': True,
@@ -36,6 +44,9 @@ class CloudflareStreamIE(InfoExtractor):
}, {
'url': 'https://customer-aw5py76sw8wyqzmh.cloudflarestream.com/2463f6d3e06fa29710a337f5f5389fd8/iframe',
'only_matching': True,
}, {
'url': 'https://watch.cloudflarestream.com/eyJhbGciOiJSUzI1NiIsInR5cCI6IkpXVCJ9.eyJraWQiOiJmYTA0YjViMzQ2NDkwYTM5NWJiNzQ1NWFhZTA2YzYwZSIsInN1YiI6Ijg4ZDQxMDhhMzY0MjA3M2VhYmFhZjg3ZGExODJkMjYzIiwiZXhwIjoxNjAwNjA5MzE5fQ.xkRJwLGkt0nZ%5F0BlPiwU7iW4pqb4lKkznbKfAhGg0tGcxSS6ZBA3lcTUwu7W%2DyCFbnAl%2Dhqk3Fn%5FqeQS%5FQydP27qTHpB9iIFFsMtk1tqzGZV5v4yrYDnwLSKzEKvVd6QwJnfABtxH2JdpSNuWlMUiVXFxGWgjOw6QeTNDDklTQYXV%5FNLV7sErSn5CeOPeRRkdXb%2D8ip%5FVOcfk1nDsFoOo4fctFtGP0wYMyY5ae8nhhatydHwevuvJCcEvEfh%2D4qjq9mCZOodevmtSQ4YWmggf4BxtWnDWYrGW8Otp6oqezrR8oY4%2DbKdV6PaqBj49aJdcls6xK7PmM8%5Fvjy3xfm0Mg',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
'url': 'https://upride.cc/incident/shoulder-pass-at-light/',

19
yt_dlp/extractor/cloudycdn.py
View File

@@ -1,3 +1,5 @@
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
@@ -35,6 +37,20 @@ class CloudyCDNIE(InfoExtractor):
'duration': 1205,
'upload_date': '20221130',
},
}, {
# Video-only m3u8 formats need manual fixup
'url': 'https://embed.cloudycdn.services/ltv/media/08j_d24-6000-074',
'md5': 'fc472e40f6e6238446509be411c920e2',
'info_dict': {
'id': '08j_d24-6000-074',
'ext': 'mp4',
'upload_date': '20240620',
'duration': 1673,
'title': 'D24-6000-074-cetstud',
'timestamp': 1718902233,
'thumbnail': 'https://store.cloudycdn.services/tmsp00060/assets/media/788392/placeholder1718903938.jpg',
},
'params': {'format': 'bv'},
}]
_WEBPAGE_TESTS = [{
'url': 'https://www.tavaklase.lv/video/es-esmu-mina-um-2/',
@@ -63,6 +79,9 @@ class CloudyCDNIE(InfoExtractor):
formats, subtitles = [], {}
for m3u8_url in traverse_obj(data, ('source', 'sources', ..., 'src', {url_or_none})):
fmts, subs = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, fatal=False)
for fmt in fmts:
if re.search(r'chunklist_b\d+_vo_', fmt['url']):
fmt['acodec'] = 'none'
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)

14
yt_dlp/extractor/common.py
View File

@@ -234,7 +234,14 @@ class InfoExtractor:
'maybe' if the format may have DRM and has to be tested before download.
* extra_param_to_segment_url A query string to append to each
fragment's URL, or to update each existing query string
with. Only applied by the native HLS/DASH downloaders.
with. If it is an HLS stream with an AES-128 decryption key,
the query paramaters will be passed to the key URI as well,
unless there is an `extra_param_to_key_url` given,
or unless an external key URI is provided via `hls_aes`.
Only applied by the native HLS/DASH downloaders.
* extra_param_to_key_url A query string to append to the URL
of the format's HLS AES-128 decryption key.
Only applied by the native HLS downloader.
* hls_aes A dictionary of HLS AES-128 decryption information
used by the native HLS downloader to override the
values in the media playlist when an '#EXT-X-KEY' tag
@@ -2215,6 +2222,11 @@ class InfoExtractor:
'quality': quality,
'has_drm': has_drm,
}
# YouTube-specific
if yt_audio_content_id := last_stream_inf.get('YT-EXT-AUDIO-CONTENT-ID'):
f['language'] = yt_audio_content_id.split('.')[0]
resolution = last_stream_inf.get('RESOLUTION')
if resolution:
mobj = re.search(r'(?P<width>\d+)[xX](?P<height>\d+)', resolution)

3
yt_dlp/extractor/dailymail.py
View File

@@ -2,6 +2,7 @@ from .common import InfoExtractor
from ..utils import (
determine_protocol,
int_or_none,
join_nonempty,
try_get,
unescapeHTML,
)
@@ -52,7 +53,7 @@ class DailyMailIE(InfoExtractor):
is_hls = container == 'M2TS'
protocol = 'm3u8_native' if is_hls else determine_protocol({'url': rendition_url})
formats.append({
'format_id': ('hls' if is_hls else protocol) + (f'-{tbr}' if tbr else ''),
'format_id': join_nonempty('hls' if is_hls else protocol, tbr),
'url': rendition_url,
'width': int_or_none(rendition.get('frameWidth')),
'height': int_or_none(rendition.get('frameHeight')),

61
yt_dlp/extractor/digitalconcerthall.py
View File

@@ -1,16 +1,16 @@
from .common import InfoExtractor
from ..utils import (
ExtractorError,
parse_resolution,
traverse_obj,
try_get,
url_or_none,
urlencode_postdata,
)
from ..utils.traversal import traverse_obj
class DigitalConcertHallIE(InfoExtractor):
IE_DESC = 'DigitalConcertHall extractor'
_VALID_URL = r'https?://(?:www\.)?digitalconcerthall\.com/(?P<language>[a-z]+)/(?P<type>film|concert)/(?P<id>[0-9]+)'
_VALID_URL = r'https?://(?:www\.)?digitalconcerthall\.com/(?P<language>[a-z]+)/(?P<type>film|concert|work)/(?P<id>[0-9]+)-?(?P<part>[0-9]+)?'
_OAUTH_URL = 'https://api.digitalconcerthall.com/v2/oauth2/token'
_ACCESS_TOKEN = None
_NETRC_MACHINE = 'digitalconcerthall'
@@ -26,7 +26,8 @@ class DigitalConcertHallIE(InfoExtractor):
'upload_date': '20210624',
'timestamp': 1624548600,
'duration': 2798,
'album_artist': 'Members of the Berliner Philharmoniker / Simon Rössler',
'album_artists': ['Members of the Berliner Philharmoniker', 'Simon Rössler'],
'composers': ['Kurt Weill'],
},
'params': {'skip_download': 'm3u8'},
}, {
@@ -34,8 +35,9 @@ class DigitalConcertHallIE(InfoExtractor):
'url': 'https://www.digitalconcerthall.com/en/concert/53785',
'info_dict': {
'id': '53785',
'album_artist': 'Berliner Philharmoniker / Kirill Petrenko',
'album_artists': ['Berliner Philharmoniker', 'Kirill Petrenko'],
'title': 'Kirill Petrenko conducts Mendelssohn and Shostakovich',
'thumbnail': r're:^https?://images.digitalconcerthall.com/cms/thumbnails.*\.jpg$',
},
'params': {'skip_download': 'm3u8'},
'playlist_count': 3,
@@ -49,9 +51,20 @@ class DigitalConcertHallIE(InfoExtractor):
'thumbnail': r're:^https?://images.digitalconcerthall.com/cms/thumbnails.*\.jpg$',
'upload_date': '20220714',
'timestamp': 1657785600,
'album_artist': 'Frank Peter Zimmermann / Benedikt von Bernstorff / Jakob von Bernstorff',
'album_artists': ['Frank Peter Zimmermann', 'Benedikt von Bernstorff', 'Jakob von Bernstorff'],
},
'params': {'skip_download': 'm3u8'},
}, {
'note': 'Concert with several works and an interview',
'url': 'https://www.digitalconcerthall.com/en/work/53785-1',
'info_dict': {
'id': '53785',
'album_artists': ['Berliner Philharmoniker', 'Kirill Petrenko'],
'title': 'Kirill Petrenko conducts Mendelssohn and Shostakovich',
'thumbnail': r're:^https?://images.digitalconcerthall.com/cms/thumbnails.*\.jpg$',
},
'params': {'skip_download': 'm3u8'},
'playlist_count': 1,
}]
def _perform_login(self, username, password):
@@ -97,15 +110,14 @@ class DigitalConcertHallIE(InfoExtractor):
'Accept-Language': language,
})
m3u8_url = traverse_obj(
stream_info, ('channel', lambda k, _: k.startswith('vod_mixed'), 'stream', 0, 'url'), get_all=False)
formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', 'm3u8_native', fatal=False)
formats = []
for m3u8_url in traverse_obj(stream_info, ('channel', ..., 'stream', ..., 'url', {url_or_none})):
formats.extend(self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', fatal=False))
yield {
'id': video_id,
'title': item.get('title'),
'composer': item.get('name_composer'),
'url': m3u8_url,
'formats': formats,
'duration': item.get('duration_total'),
'timestamp': traverse_obj(item, ('date', 'published')),
@@ -119,31 +131,32 @@ class DigitalConcertHallIE(InfoExtractor):
}
def _real_extract(self, url):
language, type_, video_id = self._match_valid_url(url).group('language', 'type', 'id')
language, type_, video_id, part = self._match_valid_url(url).group('language', 'type', 'id', 'part')
if not language:
language = 'en'
thumbnail_url = self._html_search_regex(
r'(https?://images\.digitalconcerthall\.com/cms/thumbnails/.*\.jpg)',
self._download_webpage(url, video_id), 'thumbnail')
thumbnails = [{
'url': thumbnail_url,
**parse_resolution(thumbnail_url),
}]
api_type = 'concert' if type_ == 'work' else type_
vid_info = self._download_json(
f'https://api.digitalconcerthall.com/v2/{type_}/{video_id}', video_id, headers={
f'https://api.digitalconcerthall.com/v2/{api_type}/{video_id}', video_id, headers={
'Accept': 'application/json',
'Accept-Language': language,
})
album_artist = ' / '.join(traverse_obj(vid_info, ('_links', 'artist', ..., 'name')) or '')
album_artists = traverse_obj(vid_info, ('_links', 'artist', ..., 'name'))
videos = [vid_info] if type_ == 'film' else traverse_obj(vid_info, ('_embedded', ..., ...))
if type_ == 'work':
videos = [videos[int(part) - 1]]
thumbnail = traverse_obj(vid_info, (
'image', ..., {self._proto_relative_url}, {url_or_none},
{lambda x: x.format(width=0, height=0)}, any)) # NB: 0x0 is the original size
return {
'_type': 'playlist',
'id': video_id,
'title': vid_info.get('title'),
'entries': self._entries(videos, language, thumbnails=thumbnails, album_artist=album_artist, type_=type_),
'thumbnails': thumbnails,
'album_artist': album_artist,
'entries': self._entries(
videos, language, type_, thumbnail=thumbnail, album_artists=album_artists),
'thumbnail': thumbnail,
'album_artists': album_artists,
}

6
yt_dlp/extractor/douyutv.py
View File

@@ -24,8 +24,9 @@ from ..utils import (
class DouyuBaseIE(InfoExtractor):
def _download_cryptojs_md5(self, video_id):
for url in [
# XXX: Do NOT use cdn.bootcdn.net; ref: https://sansec.io/research/polyfill-supply-chain-attack
'https://cdnjs.cloudflare.com/ajax/libs/crypto-js/3.1.2/rollups/md5.js',
'https://cdn.bootcdn.net/ajax/libs/crypto-js/3.1.2/rollups/md5.js',
'https://unpkg.com/cryptojslib@3.1.2/rollups/md5.js',
]:
js_code = self._download_webpage(
url, video_id, note='Downloading signing dependency', fatal=False)
@@ -35,7 +36,8 @@ class DouyuBaseIE(InfoExtractor):
raise ExtractorError('Unable to download JS dependency (crypto-js/md5)')
def _get_cryptojs_md5(self, video_id):
return self.cache.load('douyu', 'crypto-js-md5') or self._download_cryptojs_md5(video_id)
return self.cache.load(
'douyu', 'crypto-js-md5', min_ver='2024.07.04') or self._download_cryptojs_md5(video_id)
def _calc_sign(self, sign_func, video_id, a):
b = uuid.uuid4().hex

12
yt_dlp/extractor/eitb.py
View File

@@ -1,6 +1,11 @@
from .common import InfoExtractor
from ..networking import Request
from ..utils import float_or_none, int_or_none, parse_iso8601
from ..utils import (
float_or_none,
int_or_none,
join_nonempty,
parse_iso8601,
)
class EitbIE(InfoExtractor):
@@ -37,12 +42,9 @@ class EitbIE(InfoExtractor):
if not video_url:
continue
tbr = float_or_none(rendition.get('ENCODING_RATE'), 1000)
format_id = 'http'
if tbr:
format_id += f'-{int(tbr)}'
formats.append({
'url': rendition['PMD_URL'],
'format_id': format_id,
'format_id': join_nonempty('http', int_or_none(tbr)),
'width': int_or_none(rendition.get('FRAME_WIDTH')),
'height': int_or_none(rendition.get('FRAME_HEIGHT')),
'tbr': tbr,

3
yt_dlp/extractor/eporner.py
View File

@@ -29,9 +29,6 @@ class EpornerIE(InfoExtractor):
'view_count': int,
'age_limit': 18,
},
'params': {
'proxy': '127.0.0.1:8118',
},
}, {
# New (May 2016) URL layout
'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0/Star-Wars-XXX-Parody/',

3
yt_dlp/extractor/facebook.py
View File

@@ -621,6 +621,9 @@ class FacebookIE(InfoExtractor):
'url': playable_url,
})
extract_dash_manifest(video, formats)
if not formats:
# Do not append false positive entry w/o any formats
return
automatic_captions, subtitles = {}, {}
is_broadcast = traverse_obj(video, ('is_video_broadcast', {bool}))

10
yt_dlp/extractor/generic.py
View File

@@ -2167,7 +2167,15 @@ class GenericIE(InfoExtractor):
urllib.parse.urlparse(fragment_query).query or fragment_query
or urllib.parse.urlparse(manifest_url).query or None)
hex_or_none = lambda x: x if re.fullmatch(r'(0x)?[\da-f]+', x, re.IGNORECASE) else None
key_query = self._configuration_arg('key_query', [None], casesense=True)[0]
if key_query is not None:
info['extra_param_to_key_url'] = (
urllib.parse.urlparse(key_query).query or key_query
or urllib.parse.urlparse(manifest_url).query or None)
def hex_or_none(value):
return value if re.fullmatch(r'(0x)?[\da-f]+', value, re.IGNORECASE) else None
info['hls_aes'] = traverse_obj(self._configuration_arg('hls_key', casesense=True), {
'uri': (0, {url_or_none}), 'key': (0, {hex_or_none}), 'iv': (1, {hex_or_none}),
}) or None

3
yt_dlp/extractor/go.py
View File

@@ -5,6 +5,7 @@ from ..utils import (
ExtractorError,
determine_ext,
int_or_none,
join_nonempty,
parse_age_limit,
remove_end,
remove_start,
@@ -287,7 +288,7 @@ class GoIE(AdobePassIE):
if mobj:
height = int(mobj.group(2))
f.update({
'format_id': (f'{format_id}-' if format_id else '') + f'{height}P',
'format_id': join_nonempty(format_id, f'{height}P'),
'width': int(mobj.group(1)),
'height': height,
})

32
yt_dlp/extractor/graspop.py Normal file
View File

@@ -0,0 +1,32 @@
from .common import InfoExtractor
from ..utils import update_url, url_or_none
from ..utils.traversal import traverse_obj
class GraspopIE(InfoExtractor):
_VALID_URL = r'https?://vod\.graspop\.be/[a-z]{2}/(?P<id>\d+)/'
_TESTS = [{
'url': 'https://vod.graspop.be/fr/101556/thy-art-is-murder-concert/',
'info_dict': {
'id': '101556',
'ext': 'mp4',
'title': 'Thy Art Is Murder',
'thumbnail': r're:https://cdn-mds\.pickx\.be/festivals/v3/global/original/.+\.jpg',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
metadata = self._download_json(
f'https://tv.proximus.be/MWC/videocenter/festivals/{video_id}/stream', video_id)
return {
'id': video_id,
'formats': self._extract_m3u8_formats(
# Downgrade manifest request to avoid incomplete certificate chain error
update_url(metadata['source']['assetUri'], scheme='http'), video_id, 'mp4'),
**traverse_obj(metadata, {
'title': ('name', {str}),
'thumbnail': ('source', 'poster', {url_or_none}),
}),
}

3
yt_dlp/extractor/hbo.py
View File

@@ -3,6 +3,7 @@ import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
join_nonempty,
parse_duration,
urljoin,
xpath_element,
@@ -69,7 +70,7 @@ class HBOBaseIE(InfoExtractor):
height = format_info.get('height')
fmt = {
'url': path,
'format_id': 'http{}'.format(f'-{height}p' if height else ''),
'format_id': join_nonempty('http'. height and f'{height}p'),
'width': format_info.get('width'),
'height': height,
}

3
yt_dlp/extractor/hketv.py
View File

@@ -44,9 +44,6 @@ class HKETVIE(InfoExtractor):
'duration': 907,
'subtitles': {},
},
'params': {
'geo_verification_proxy': '<HK proxy here>',
},
'skip': 'Geo restricted to HK',
}]

2
yt_dlp/extractor/instagram.py
View File

@@ -453,7 +453,7 @@ class InstagramIE(InstagramBaseIE):
else:
self.report_warning('Main webpage is locked behind the login page. Retrying with embed webpage (some metadata might be missing).')
webpage = self._download_webpage(
f'{url}/embed/', video_id, note='Downloading embed webpage', fatal=False)
f'{url}/embed/', video_id, note='Downloading embed webpage', fatal=False) or ''
additional_data = self._search_json(
r'window\.__additionalDataLoaded\s*\(\s*[^,]+,', webpage, 'additional data', video_id, fatal=False)
if not additional_data and not media:

1
yt_dlp/extractor/iwara.py
View File

@@ -2,7 +2,6 @@ import functools
import hashlib
import json
import time
import urllib.error
import urllib.parse
from .common import InfoExtractor

23
yt_dlp/extractor/jiocinema.py
View File

@@ -364,20 +364,25 @@ class JioCinemaSeriesIE(JioCinemaBaseIE):
'title': 'naagin',
},
'playlist_mincount': 120,
}, {
'url': 'https://www.jiocinema.com/tv-shows/mtv-splitsvilla-x5/3499820',
'info_dict': {
'id': '3499820',
'title': 'mtv-splitsvilla-x5',
},
'playlist_mincount': 310,
}]
def _entries(self, series_id):
seasons = self._download_json(
f'{self._METADATA_API_BASE}/voot/v1/voot-web/content/generic/season-by-show', series_id,
'Downloading series metadata JSON', query={
'sort': 'season:asc',
'id': series_id,
'responseType': 'common',
})
seasons = traverse_obj(self._download_json(
f'{self._METADATA_API_BASE}/voot/v1/voot-web/view/show/{series_id}', series_id,
'Downloading series metadata JSON', query={'responseType': 'common'}), (
'trays', lambda _, v: v['trayId'] == 'season-by-show-multifilter',
'trayTabs', lambda _, v: v['id']))
for season_num, season in enumerate(traverse_obj(seasons, ('result', lambda _, v: v['id'])), 1):
for season_num, season in enumerate(seasons, start=1):
season_id = season['id']
label = season.get('season') or season_num
label = season.get('label') or season_num
for page_num in itertools.count(1):
episodes = traverse_obj(self._download_json(
f'{self._METADATA_API_BASE}/voot/v1/voot-web/content/generic/series-wise-episode',

9
yt_dlp/extractor/jiosaavn.py
View File

@@ -158,7 +158,7 @@ class JioSaavnAlbumIE(JioSaavnBaseIE):
class JioSaavnPlaylistIE(JioSaavnBaseIE):
IE_NAME = 'jiosaavn:playlist'
_VALID_URL = r'https?://(?:www\.)?(?:jio)?saavn\.com/s/playlist/(?:[^/?#]+/){2}(?P<id>[^/?#]+)'
_VALID_URL = r'https?://(?:www\.)?(?:jio)?saavn\.com/(?:s/playlist/(?:[^/?#]+/){2}|featured/[^/?#]+/)(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.jiosaavn.com/s/playlist/2279fbe391defa793ad7076929a2f5c9/mood-english/LlJ8ZWT1ibN5084vKHRj2Q__',
'info_dict': {
@@ -173,6 +173,13 @@ class JioSaavnPlaylistIE(JioSaavnBaseIE):
'title': 'Mood Hindi',
},
'playlist_mincount': 801,
}, {
'url': 'https://www.jiosaavn.com/featured/taaza-tunes/Me5RridRfDk_',
'info_dict': {
'id': 'Me5RridRfDk_',
'title': 'Taaza Tunes',
},
'playlist_mincount': 301,
}]
_PAGE_SIZE = 50

141
yt_dlp/extractor/khanacademy.py
View File

@@ -3,43 +3,52 @@ import json
from .common import InfoExtractor
from ..utils import (
int_or_none,
make_archive_id,
parse_iso8601,
try_get,
str_or_none,
traverse_obj,
url_or_none,
urljoin,
)
class KhanAcademyBaseIE(InfoExtractor):
_VALID_URL_TEMPL = r'https?://(?:www\.)?khanacademy\.org/(?P<id>(?:[^/]+/){%s}%s[^?#/&]+)'
_PUBLISHED_CONTENT_VERSION = '171419ab20465d931b356f22d20527f13969bb70'
def _parse_video(self, video):
return {
'_type': 'url_transparent',
'url': video['youtubeId'],
'id': video.get('slug'),
'title': video.get('title'),
'thumbnail': video.get('imageUrl') or video.get('thumbnailUrl'),
'duration': int_or_none(video.get('duration')),
'description': video.get('description'),
'id': video['youtubeId'],
'ie_key': 'Youtube',
**traverse_obj(video, {
'display_id': ('id', {str_or_none}),
'title': ('translatedTitle', {str}),
'thumbnail': ('thumbnailUrls', ..., 'url', {url_or_none}),
'duration': ('duration', {int_or_none}),
'description': ('description', {str}),
}, get_all=False),
}
def _real_extract(self, url):
display_id = self._match_id(url)
content = self._download_json(
'https://www.khanacademy.org/api/internal/graphql/FetchContentData',
display_id, query={
'https://www.khanacademy.org/api/internal/graphql/ContentForPath', display_id,
query={
'fastly_cacheable': 'persist_until_publish',
'hash': '4134764944',
'lang': 'en',
'pcv': self._PUBLISHED_CONTENT_VERSION,
'hash': '1242644265',
'variables': json.dumps({
'path': display_id,
'queryParams': 'lang=en',
'isModal': False,
'followRedirects': True,
'countryCode': 'US',
'kaLocale': 'en',
'clientPublishedContentVersion': self._PUBLISHED_CONTENT_VERSION,
}),
})['data']['contentJson']
return self._parse_component_props(self._parse_json(content, display_id)['componentProps'])
'lang': 'en',
})['data']['contentRoute']['listedPathData']
return self._parse_component_props(content, display_id)
class KhanAcademyIE(KhanAcademyBaseIE):
@@ -47,64 +56,98 @@ class KhanAcademyIE(KhanAcademyBaseIE):
_VALID_URL = KhanAcademyBaseIE._VALID_URL_TEMPL % ('4', 'v/')
_TEST = {
'url': 'https://www.khanacademy.org/computing/computer-science/cryptography/crypt/v/one-time-pad',
'md5': '9c84b7b06f9ebb80d22a5c8dedefb9a0',
'md5': '1d5c2e70fa6aa29c38eca419f12515ce',
'info_dict': {
'id': 'FlIG3TvQCBQ',
'ext': 'mp4',
'title': 'The one-time pad',
'description': 'The perfect cipher',
'display_id': '716378217',
'duration': 176,
'uploader': 'Brit Cruise',
'uploader_id': 'khanacademy',
'uploader': 'Khan Academy',
'uploader_id': '@khanacademy',
'uploader_url': 'https://www.youtube.com/@khanacademy',
'upload_date': '20120411',
'timestamp': 1334170113,
'license': 'cc-by-nc-sa',
'live_status': 'not_live',
'channel': 'Khan Academy',
'channel_id': 'UC4a-Gbdw7vOaccHmFo40b9g',
'channel_url': 'https://www.youtube.com/channel/UC4a-Gbdw7vOaccHmFo40b9g',
'channel_is_verified': True,
'playable_in_embed': True,
'categories': ['Education'],
'creators': ['Brit Cruise'],
'tags': [],
'age_limit': 0,
'availability': 'public',
'comment_count': int,
'channel_follower_count': int,
'thumbnail': str,
'view_count': int,
'like_count': int,
'heatmap': list,
},
'add_ie': ['Youtube'],
}
def _parse_component_props(self, component_props):
video = component_props['tutorialPageData']['contentModel']
info = self._parse_video(video)
author_names = video.get('authorNames')
info.update({
'uploader': ', '.join(author_names) if author_names else None,
'timestamp': parse_iso8601(video.get('dateAdded')),
'license': video.get('kaUserLicense'),
})
return info
def _parse_component_props(self, component_props, display_id):
video = component_props['content']
return {
**self._parse_video(video),
**traverse_obj(video, {
'creators': ('authorNames', ..., {str}),
'timestamp': ('dateAdded', {parse_iso8601}),
'license': ('kaUserLicense', {str}),
}),
}
class KhanAcademyUnitIE(KhanAcademyBaseIE):
IE_NAME = 'khanacademy:unit'
_VALID_URL = (KhanAcademyBaseIE._VALID_URL_TEMPL % ('2', '')) + '/?(?:[?#&]|$)'
_TEST = {
_VALID_URL = (KhanAcademyBaseIE._VALID_URL_TEMPL % ('1,2', '')) + '/?(?:[?#&]|$)'
_TESTS = [{
'url': 'https://www.khanacademy.org/computing/computer-science/cryptography',
'info_dict': {
'id': 'cryptography',
'id': 'x48c910b6',
'title': 'Cryptography',
'description': 'How have humans protected their secret messages through history? What has changed today?',
'display_id': 'computing/computer-science/cryptography',
'_old_archive_ids': ['khanacademyunit cryptography'],
},
'playlist_mincount': 31,
}
}, {
'url': 'https://www.khanacademy.org/computing/computer-science',
'info_dict': {
'id': 'x301707a0',
'title': 'Computer science theory',
'description': 'md5:4b472a4646e6cf6ec4ccb52c4062f8ba',
'display_id': 'computing/computer-science',
'_old_archive_ids': ['khanacademyunit computer-science'],
},
'playlist_mincount': 50,
}]
def _parse_component_props(self, component_props):
curation = component_props['curation']
def _parse_component_props(self, component_props, display_id):
course = component_props['course']
selected_unit = traverse_obj(course, (
'unitChildren', lambda _, v: v['relativeUrl'] == f'/{display_id}', any)) or course
entries = []
tutorials = try_get(curation, lambda x: x['tabs'][0]['modules'][0]['tutorials'], list) or []
for tutorial_number, tutorial in enumerate(tutorials, 1):
chapter_info = {
'chapter': tutorial.get('title'),
'chapter_number': tutorial_number,
'chapter_id': tutorial.get('id'),
}
for content_item in (tutorial.get('contentItems') or []):
if content_item.get('kind') == 'Video':
info = self._parse_video(content_item)
info.update(chapter_info)
entries.append(info)
def build_entry(entry):
return self.url_result(urljoin(
'https://www.khanacademy.org', entry['canonicalUrl']),
KhanAcademyIE, title=entry.get('translatedTitle'))
entries = traverse_obj(selected_unit, (
(('unitChildren', ...), None), 'allOrderedChildren', ..., 'curatedChildren',
lambda _, v: v['contentKind'] == 'Video' and v['canonicalUrl'], {build_entry}))
return self.playlist_result(
entries, curation.get('unit'), curation.get('title'),
curation.get('description'))
entries,
display_id=display_id,
**traverse_obj(selected_unit, {
'id': ('id', {str}),
'title': ('translatedTitle', {str}),
'description': ('translatedDescription', {str}),
'_old_archive_ids': ('slug', {str}, {lambda x: [make_archive_id(self, x)] if x else None}),
}))

114
yt_dlp/extractor/laracasts.py Normal file
View File

@@ -0,0 +1,114 @@
import json
from .common import InfoExtractor
from .vimeo import VimeoIE
from ..utils import (
clean_html,
extract_attributes,
get_element_html_by_id,
int_or_none,
parse_duration,
str_or_none,
unified_strdate,
url_or_none,
urljoin,
)
from ..utils.traversal import traverse_obj
class LaracastsBaseIE(InfoExtractor):
def _get_prop_data(self, url, display_id):
webpage = self._download_webpage(url, display_id)
return traverse_obj(
get_element_html_by_id('app', webpage),
({extract_attributes}, 'data-page', {json.loads}, 'props'))
def _parse_episode(self, episode):
if not traverse_obj(episode, 'vimeoId'):
self.raise_login_required('This video is only available for subscribers.')
return self.url_result(
VimeoIE._smuggle_referrer(
f'https://player.vimeo.com/video/{episode["vimeoId"]}', 'https://laracasts.com/'),
VimeoIE, url_transparent=True,
**traverse_obj(episode, {
'id': ('id', {int}, {str_or_none}),
'webpage_url': ('path', {lambda x: urljoin('https://laracasts.com', x)}),
'title': ('title', {clean_html}),
'season_number': ('chapter', {int_or_none}),
'episode_number': ('position', {int_or_none}),
'description': ('body', {clean_html}),
'thumbnail': ('largeThumbnail', {url_or_none}),
'duration': ('length', {int_or_none}),
'date': ('dateSegments', 'published', {unified_strdate}),
}))
class LaracastsIE(LaracastsBaseIE):
IE_NAME = 'laracasts'
_VALID_URL = r'https?://(?:www\.)?laracasts\.com/series/(?P<id>[\w-]+/episodes/\d+)/?(?:[?#]|$)'
_TESTS = [{
'url': 'https://laracasts.com/series/30-days-to-learn-laravel-11/episodes/1',
'md5': 'c8f5e7b02ad0e438ef9280a08c8493dc',
'info_dict': {
'id': '922040563',
'title': 'Hello, Laravel',
'ext': 'mp4',
'duration': 519,
'date': '20240312',
'thumbnail': 'https://laracasts.s3.amazonaws.com/videos/thumbnails/youtube/30-days-to-learn-laravel-11-1.png',
'description': 'md5:ddd658bb241975871d236555657e1dd1',
'season_number': 1,
'season': 'Season 1',
'episode_number': 1,
'episode': 'Episode 1',
'uploader': 'Laracasts',
'uploader_id': 'user20182673',
'uploader_url': 'https://vimeo.com/user20182673',
},
'expected_warnings': ['Failed to parse XML'], # TODO: Remove when vimeo extractor is fixed
}]
def _real_extract(self, url):
display_id = self._match_id(url)
return self._parse_episode(self._get_prop_data(url, display_id)['lesson'])
class LaracastsPlaylistIE(LaracastsBaseIE):
IE_NAME = 'laracasts:series'
_VALID_URL = r'https?://(?:www\.)?laracasts\.com/series/(?P<id>[\w-]+)/?(?:[?#]|$)'
_TESTS = [{
'url': 'https://laracasts.com/series/30-days-to-learn-laravel-11',
'info_dict': {
'title': '30 Days to Learn Laravel',
'id': '210',
'thumbnail': 'https://laracasts.s3.amazonaws.com/series/thumbnails/social-cards/30-days-to-learn-laravel-11.png?v=2',
'duration': 30600.0,
'modified_date': '20240511',
'description': 'md5:27c260a1668a450984e8f901579912dd',
'categories': ['Frameworks'],
'tags': ['Laravel'],
'display_id': '30-days-to-learn-laravel-11',
},
'playlist_count': 30,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
series = self._get_prop_data(url, display_id)['series']
metadata = {
'display_id': display_id,
**traverse_obj(series, {
'title': ('title', {str}),
'id': ('id', {int}, {str_or_none}),
'description': ('body', {clean_html}),
'thumbnail': (('large_thumbnail', 'thumbnail'), {url_or_none}, any),
'duration': ('runTime', {parse_duration}),
'categories': ('taxonomy', 'name', {str}, {lambda x: x and [x]}),
'tags': ('topics', ..., 'name', {str}),
'modified_date': ('lastUpdated', {unified_strdate}),
}),
}
return self.playlist_result(traverse_obj(
series, ('chapters', ..., 'episodes', lambda _, v: v['vimeoId'], {self._parse_episode})), **metadata)

40
yt_dlp/extractor/matchtv.py
View File

@@ -1,51 +1,35 @@
import random
from .common import InfoExtractor
from ..utils import xpath_text
class MatchTVIE(InfoExtractor):
_VALID_URL = r'https?://matchtv\.ru(?:/on-air|/?#live-player)'
_VALID_URL = [
r'https?://matchtv\.ru/on-air/?(?:$|[?#])',
r'https?://video\.matchtv\.ru/iframe/channel/106/?(?:$|[?#])',
]
_TESTS = [{
'url': 'http://matchtv.ru/#live-player',
'url': 'http://matchtv.ru/on-air/',
'info_dict': {
'id': 'matchtv-live',
'ext': 'flv',
'ext': 'mp4',
'title': r're:^Матч ТВ - Прямой эфир \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
'is_live': True,
'live_status': 'is_live',
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://matchtv.ru/on-air/',
'url': 'https://video.matchtv.ru/iframe/channel/106',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = 'matchtv-live'
video_url = self._download_json(
'http://player.matchtv.ntvplus.tv/player/smil', video_id,
query={
'ts': '',
'quality': 'SD',
'contentId': '561d2c0df7159b37178b4567',
'sign': '',
'includeHighlights': '0',
'userId': '',
'sessionId': random.randint(1, 1000000000),
'contentType': 'channel',
'timeShift': '0',
'platform': 'portal',
},
headers={
'Referer': 'http://player.matchtv.ntvplus.tv/embed-player/NTVEmbedPlayer.swf',
})['data']['videoUrl']
f4m_url = xpath_text(self._download_xml(video_url, video_id), './to')
formats = self._extract_f4m_formats(f4m_url, video_id)
webpage = self._download_webpage('https://video.matchtv.ru/iframe/channel/106', video_id)
video_url = self._html_search_regex(
r'data-config="config=(https?://[^?"]+)[?"]', webpage, 'video URL').replace('/feed/', '/media/') + '.m3u8'
return {
'id': video_id,
'title': 'Матч ТВ - Прямой эфир',
'is_live': True,
'formats': formats,
'formats': self._extract_m3u8_formats(video_url, video_id, 'mp4', live=True),
}

19
yt_dlp/extractor/mediasite.py
View File

@@ -15,6 +15,7 @@ from ..utils import (
url_or_none,
urljoin,
)
from ..utils.traversal import traverse_obj
_ID_RE = r'(?:[0-9a-f]{32,34}|[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12,14})'
@@ -212,13 +213,14 @@ class MediasiteIE(InfoExtractor):
stream_type, 'type%u' % stream_type)
stream_formats = []
for unum, video_url in enumerate(video_urls):
video_url = url_or_none(video_url.get('Location'))
for unum, video in enumerate(video_urls):
video_url = url_or_none(video.get('Location'))
if not video_url:
continue
# XXX: if Stream.get('CanChangeScheme', False), switch scheme to HTTP/HTTPS
media_type = video_url.get('MediaType')
media_type = video.get('MediaType')
ext = mimetype2ext(video.get('MimeType'))
if media_type == 'SS':
stream_formats.extend(self._extract_ism_formats(
video_url, resource_id,
@@ -229,15 +231,20 @@ class MediasiteIE(InfoExtractor):
video_url, resource_id,
mpd_id=f'{stream_id}-{snum}.{unum}',
fatal=False))
elif ext in ('m3u', 'm3u8'):
stream_formats.extend(self._extract_m3u8_formats(
video_url, resource_id,
m3u8_id=f'{stream_id}-{snum}.{unum}',
fatal=False))
else:
stream_formats.append({
'format_id': f'{stream_id}-{snum}.{unum}',
'url': video_url,
'ext': mimetype2ext(video_url.get('MimeType')),
'ext': ext,
})
if stream.get('HasSlideContent', False):
images = player_options['PlayerLayoutOptions']['Images']
images = traverse_obj(player_options, ('PlayerLayoutOptions', 'Images', {dict}))
if stream.get('HasSlideContent') and images:
stream_formats.append(self.__extract_slides(
stream_id=stream_id,
snum=snum,

258
yt_dlp/extractor/microsoftembed.py
View File

@@ -1,5 +1,14 @@
import re
from .common import InfoExtractor
from ..utils import int_or_none, traverse_obj, unified_timestamp
from ..utils import (
int_or_none,
parse_iso8601,
traverse_obj,
unified_timestamp,
url_basename,
url_or_none,
)
class MicrosoftEmbedIE(InfoExtractor):
@@ -63,3 +72,250 @@ class MicrosoftEmbedIE(InfoExtractor):
'subtitles': subtitles,
'thumbnails': thumbnails,
}
class MicrosoftMediusBaseIE(InfoExtractor):
@staticmethod
def _sub_to_dict(subtitle_list):
subtitles = {}
for sub in subtitle_list:
subtitles.setdefault(sub.pop('tag', 'und'), []).append(sub)
return subtitles
def _extract_ism(self, ism_url, video_id):
formats = self._extract_ism_formats(ism_url, video_id)
for fmt in formats:
if fmt['language'] != 'eng' and 'English' not in fmt['format_id']:
fmt['language_preference'] = -10
return formats
class MicrosoftMediusIE(MicrosoftMediusBaseIE):
_VALID_URL = r'https?://medius\.microsoft\.com/Embed/(?:Video\?id=|video-nc/|VideoDetails/)(?P<id>[\da-f-]+)'
_TESTS = [{
'url': 'https://medius.microsoft.com/Embed/video-nc/9640d86c-f513-4889-959e-5dace86e7d2b',
'info_dict': {
'id': '9640d86c-f513-4889-959e-5dace86e7d2b',
'ext': 'ismv',
'title': 'Rapidly code, test and ship from secure cloud developer environments',
'description': 'md5:33c8e4facadc438613476eea24165f71',
'thumbnail': r're:https://mediusimg\.event\.microsoft\.com/video-\d+/thumbnail\.jpg.*',
'subtitles': 'count:30',
},
}, {
'url': 'https://medius.microsoft.com/Embed/video-nc/81215af5-c813-4dcd-aede-94f4e1a7daa3',
'info_dict': {
'id': '81215af5-c813-4dcd-aede-94f4e1a7daa3',
'ext': 'ismv',
'title': 'Microsoft Build opening',
'description': 'md5:43455096141077a1f23144cab8cec1cb',
'thumbnail': r're:https://mediusimg\.event\.microsoft\.com/video-\d+/thumbnail\.jpg.*',
'subtitles': 'count:31',
},
}, {
'url': 'https://medius.microsoft.com/Embed/VideoDetails/78493569-9b3b-4a85-a409-ee76e789e25c',
'info_dict': {
'id': '78493569-9b3b-4a85-a409-ee76e789e25c',
'ext': 'ismv',
'title': ' Anomaly Detection & Root cause at Edge',
'description': 'md5:f8f1ad93d7918649bfb97fa081b03b83',
'thumbnail': r're:https://mediusdownload.event.microsoft.com/asset.*\.jpg.*',
'subtitles': 'count:17',
},
}, {
'url': 'https://medius.microsoft.com/Embed/Video?id=0dc69bda-079b-4070-a7db-a8da1a06a9c7',
'only_matching': True,
}, {
'url': 'https://medius.microsoft.com/Embed/video-nc/fe823a91-959c-465b-96d4-8f4db624f72c',
'only_matching': True,
}]
def _extract_subtitle(self, webpage, video_id):
captions = traverse_obj(
self._search_json(r'const\s+captionsConfiguration\s*=', webpage, 'captions', video_id, default=None),
('languageList', lambda _, v: url_or_none(v['src']), {
'url': 'src',
'tag': ('srclang', {str}),
'name': ('kind', {str}),
})) or [{'url': url, 'tag': url_basename(url).split('.vtt')[0].split('_')[-1]}
for url in re.findall(r'var\s+file\s+=\s+\{[^}]+\'(https://[^\']+\.vtt\?[^\']+)', webpage)]
return self._sub_to_dict(captions)
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(f'https://medius.microsoft.com/Embed/video-nc/{video_id}', video_id)
return {
'id': video_id,
'title': self._og_search_title(webpage),
'description': self._og_search_description(webpage),
'formats': self._extract_ism(
self._search_regex(r'StreamUrl\s*=\s*"([^"]+manifest)"', webpage, 'ism url'), video_id),
'thumbnail': self._og_search_thumbnail(webpage),
'subtitles': self._extract_subtitle(webpage, video_id),
}
class MicrosoftLearnPlaylistIE(InfoExtractor):
_VALID_URL = r'https?://learn\.microsoft\.com/(?:[\w-]+/)?(?P<type>shows|events)/(?P<id>[\w-]+)/?(?:[?#]|$)'
_TESTS = [{
'url': 'https://learn.microsoft.com/en-us/shows/bash-for-beginners',
'info_dict': {
'id': 'bash-for-beginners',
'title': 'Bash for Beginners',
'description': 'md5:16a91c07222117d1e00912f0dbc02c2c',
},
'playlist_count': 20,
}, {
'url': 'https://learn.microsoft.com/en-us/events/build-2022',
'info_dict': {
'id': 'build-2022',
'title': 'Microsoft Build 2022 - Events',
'description': 'md5:c16b43848027df837b22c6fbac7648d3',
},
'playlist_count': 201,
}]
def _entries(self, url_base, video_id):
skip = 0
while True:
playlist_info = self._download_json(url_base, video_id, f'Downloading entries {skip}', query={
'locale': 'en-us',
'$skip': skip,
})
url_paths = traverse_obj(playlist_info, ('results', ..., 'url', {str}))
for url_path in url_paths:
yield self.url_result(f'https://learn.microsoft.com/en-us{url_path}')
skip += len(url_paths)
if skip >= playlist_info.get('count', 0) or not url_paths:
break
def _real_extract(self, url):
playlist_id, playlist_type = self._match_valid_url(url).group('id', 'type')
webpage = self._download_webpage(url, playlist_id)
metainfo = {
'title': self._og_search_title(webpage),
'description': self._og_search_description(webpage),
}
sub_type = 'episodes' if playlist_type == 'shows' else 'sessions'
url_base = f'https://learn.microsoft.com/api/contentbrowser/search/{playlist_type}/{playlist_id}/{sub_type}'
return self.playlist_result(self._entries(url_base, playlist_id), playlist_id, **metainfo)
class MicrosoftLearnEpisodeIE(MicrosoftMediusBaseIE):
_VALID_URL = r'https?://learn\.microsoft\.com/(?:[\w-]+/)?shows/[\w-]+/(?P<id>[^?#/]+)'
_TESTS = [{
'url': 'https://learn.microsoft.com/en-us/shows/bash-for-beginners/what-is-the-difference-between-a-terminal-and-a-shell-2-of-20-bash-for-beginners/',
'info_dict': {
'id': 'd44e1a03-a0e5-45c2-9496-5c9fa08dc94c',
'ext': 'ismv',
'title': 'What is the Difference Between a Terminal and a Shell? (Part 2 of 20)',
'description': 'md5:7bbbfb593d21c2cf2babc3715ade6b88',
'timestamp': 1676339547,
'upload_date': '20230214',
'thumbnail': r're:https://learn\.microsoft\.com/video/media/.*\.png',
'subtitles': 'count:14',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
entry_id = self._html_search_meta('entryId', webpage, 'entryId', fatal=True)
video_info = self._download_json(
f'https://learn.microsoft.com/api/video/public/v1/entries/{entry_id}', video_id)
return {
'id': entry_id,
'formats': self._extract_ism(video_info['publicVideo']['adaptiveVideoUrl'], video_id),
'subtitles': self._sub_to_dict(traverse_obj(video_info, (
'publicVideo', 'captions', lambda _, v: url_or_none(v['url']), {
'tag': ('language', {str}),
'url': 'url',
}))),
'title': self._og_search_title(webpage),
'description': self._og_search_description(webpage),
**traverse_obj(video_info, {
'timestamp': ('createTime', {parse_iso8601}),
'thumbnails': ('publicVideo', 'thumbnailOtherSizes', ..., {'url': {url_or_none}}),
}),
}
class MicrosoftLearnSessionIE(InfoExtractor):
_VALID_URL = r'https?://learn\.microsoft\.com/(?:[\w-]+/)?events/[\w-]+/(?P<id>[^?#/]+)'
_TESTS = [{
'url': 'https://learn.microsoft.com/en-us/events/build-2022/ts01-rapidly-code-test-ship-from-secure-cloud-developer-environments',
'info_dict': {
'id': '9640d86c-f513-4889-959e-5dace86e7d2b',
'ext': 'ismv',
'title': 'Rapidly code, test and ship from secure cloud developer environments - Events',
'description': 'md5:f26c1a85d41c1cffd27a0279254a25c3',
'timestamp': 1653408600,
'upload_date': '20220524',
'thumbnail': r're:https://mediusimg\.event\.microsoft\.com/video-\d+/thumbnail\.jpg.*',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
metainfo = {
'title': self._og_search_title(webpage),
'description': self._og_search_description(webpage),
'timestamp': parse_iso8601(self._html_search_meta('startDate', webpage, 'startDate')),
}
return self.url_result(
self._html_search_meta('externalVideoUrl', webpage, 'videoUrl', fatal=True),
url_transparent=True, ie=MicrosoftMediusIE, **metainfo)
class MicrosoftBuildIE(InfoExtractor):
_VALID_URL = [
r'https?://build\.microsoft\.com/[\w-]+/sessions/(?P<id>[\da-f-]+)',
r'https?://build\.microsoft\.com/[\w-]+/(?P<id>sessions)/?(?:[?#]|$)',
]
_TESTS = [{
'url': 'https://build.microsoft.com/en-US/sessions/b49feb31-afcd-4217-a538-d3ca1d171198?source=sessions',
'info_dict': {
'id': 'aee55fb5-fcf9-4b38-b764-a3527cb57554',
'ext': 'ismv',
'title': 'Microsoft Build opening keynote',
'description': 'md5:d38338f336ef4b6ef9ad2a7466a76655',
'timestamp': 1716307200,
'upload_date': '20240521',
'thumbnail': r're:https://mediusimg\.event\.microsoft\.com/video-\d+/thumbnail\.jpg.*',
},
}, {
'url': 'https://build.microsoft.com/en-US/sessions',
'info_dict': {
'id': 'sessions',
},
'playlist_mincount': 418,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
entries = [
self.url_result(
video_info['onDemand'], ie=MicrosoftMediusIE, url_transparent=True, **traverse_obj(video_info, {
'id': ('sessionId', {str}),
'title': ('title', {str}),
'description': ('description', {str}),
'timestamp': ('startDateTime', {parse_iso8601}),
}))
for video_info in self._download_json(
'https://api-v2.build.microsoft.com/api/session/all/en-US', video_id, 'Downloading video info')
]
if video_id == 'sessions':
return self.playlist_result(entries, video_id)
else:
return traverse_obj(entries, (lambda _, v: v['id'] == video_id), get_all=False)

188
yt_dlp/extractor/microsoftvirtualacademy.py
View File

@@ -1,188 +0,0 @@
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_duration,
smuggle_url,
unsmuggle_url,
xpath_text,
)
class MicrosoftVirtualAcademyBaseIE(InfoExtractor):
def _extract_base_url(self, course_id, display_id):
return self._download_json(
f'https://api-mlxprod.microsoft.com/services/products/anonymous/{course_id}',
display_id, 'Downloading course base URL')
def _extract_chapter_and_title(self, title):
if not title:
return None, None
m = re.search(r'(?P<chapter>\d+)\s*\|\s*(?P<title>.+)', title)
return (int(m.group('chapter')), m.group('title')) if m else (None, title)
class MicrosoftVirtualAcademyIE(MicrosoftVirtualAcademyBaseIE):
IE_NAME = 'mva'
IE_DESC = 'Microsoft Virtual Academy videos'
_VALID_URL = rf'(?:{IE_NAME}:|https?://(?:mva\.microsoft|(?:www\.)?microsoftvirtualacademy)\.com/[^/]+/training-courses/[^/?#&]+-)(?P<course_id>\d+)(?::|\?l=)(?P<id>[\da-zA-Z]+_\d+)'
_TESTS = [{
'url': 'https://mva.microsoft.com/en-US/training-courses/microsoft-azure-fundamentals-virtual-machines-11788?l=gfVXISmEB_6804984382',
'md5': '7826c44fc31678b12ad8db11f6b5abb9',
'info_dict': {
'id': 'gfVXISmEB_6804984382',
'ext': 'mp4',
'title': 'Course Introduction',
'formats': 'mincount:3',
'subtitles': {
'en': [{
'ext': 'ttml',
}],
},
},
}, {
'url': 'mva:11788:gfVXISmEB_6804984382',
'only_matching': True,
}]
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
mobj = self._match_valid_url(url)
course_id = mobj.group('course_id')
video_id = mobj.group('id')
base_url = smuggled_data.get('base_url') or self._extract_base_url(course_id, video_id)
settings = self._download_xml(
f'{base_url}/content/content_{video_id}/videosettings.xml?v=1',
video_id, 'Downloading video settings XML')
_, title = self._extract_chapter_and_title(xpath_text(
settings, './/Title', 'title', fatal=True))
formats = []
for sources in settings.findall('.//MediaSources'):
sources_type = sources.get('videoType')
for source in sources.findall('./MediaSource'):
video_url = source.text
if not video_url or not video_url.startswith('http'):
continue
if sources_type == 'smoothstreaming':
formats.extend(self._extract_ism_formats(
video_url, video_id, 'mss', fatal=False))
continue
video_mode = source.get('videoMode')
height = int_or_none(self._search_regex(
r'^(\d+)[pP]$', video_mode or '', 'height', default=None))
codec = source.get('codec')
acodec, vcodec = [None] * 2
if codec:
codecs = codec.split(',')
if len(codecs) == 2:
acodec, vcodec = codecs
elif len(codecs) == 1:
vcodec = codecs[0]
formats.append({
'url': video_url,
'format_id': video_mode,
'height': height,
'acodec': acodec,
'vcodec': vcodec,
})
subtitles = {}
for source in settings.findall('.//MarkerResourceSource'):
subtitle_url = source.text
if not subtitle_url:
continue
subtitles.setdefault('en', []).append({
'url': f'{base_url}/{subtitle_url}',
'ext': source.get('type'),
})
return {
'id': video_id,
'title': title,
'subtitles': subtitles,
'formats': formats,
}
class MicrosoftVirtualAcademyCourseIE(MicrosoftVirtualAcademyBaseIE):
IE_NAME = 'mva:course'
IE_DESC = 'Microsoft Virtual Academy courses'
_VALID_URL = rf'(?:{IE_NAME}:|https?://(?:mva\.microsoft|(?:www\.)?microsoftvirtualacademy)\.com/[^/]+/training-courses/(?P<display_id>[^/?#&]+)-)(?P<id>\d+)'
_TESTS = [{
'url': 'https://mva.microsoft.com/en-US/training-courses/microsoft-azure-fundamentals-virtual-machines-11788',
'info_dict': {
'id': '11788',
'title': 'Microsoft Azure Fundamentals: Virtual Machines',
},
'playlist_count': 36,
}, {
# with emphasized chapters
'url': 'https://mva.microsoft.com/en-US/training-courses/developing-windows-10-games-with-construct-2-16335',
'info_dict': {
'id': '16335',
'title': 'Developing Windows 10 Games with Construct 2',
},
'playlist_count': 10,
}, {
'url': 'https://www.microsoftvirtualacademy.com/en-US/training-courses/microsoft-azure-fundamentals-virtual-machines-11788',
'only_matching': True,
}, {
'url': 'mva:course:11788',
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
return False if MicrosoftVirtualAcademyIE.suitable(url) else super().suitable(url)
def _real_extract(self, url):
mobj = self._match_valid_url(url)
course_id = mobj.group('id')
display_id = mobj.group('display_id')
base_url = self._extract_base_url(course_id, display_id)
manifest = self._download_json(
f'{base_url}/imsmanifestlite.json',
display_id, 'Downloading course manifest JSON')['manifest']
organization = manifest['organizations']['organization'][0]
entries = []
for chapter in organization['item']:
chapter_number, chapter_title = self._extract_chapter_and_title(chapter.get('title'))
chapter_id = chapter.get('@identifier')
for item in chapter.get('item', []):
item_id = item.get('@identifier')
if not item_id:
continue
metadata = item.get('resource', {}).get('metadata') or {}
if metadata.get('learningresourcetype') != 'Video':
continue
_, title = self._extract_chapter_and_title(item.get('title'))
duration = parse_duration(metadata.get('duration'))
description = metadata.get('description')
entries.append({
'_type': 'url_transparent',
'url': smuggle_url(
f'mva:{course_id}:{item_id}', {'base_url': base_url}),
'title': title,
'description': description,
'duration': duration,
'chapter': chapter_title,
'chapter_number': chapter_number,
'chapter_id': chapter_id,
})
title = organization.get('title') or manifest.get('metadata', {}).get('title')
return self.playlist_result(entries, course_id, title)

18
yt_dlp/extractor/mlb.py
View File

@@ -9,9 +9,10 @@ from ..utils import (
join_nonempty,
parse_duration,
parse_iso8601,
traverse_obj,
try_get,
url_or_none,
)
from ..utils.traversal import traverse_obj
class MLBBaseIE(InfoExtractor):
@@ -326,15 +327,20 @@ class MLBTVIE(InfoExtractor):
video_id)['data']['Airings']
formats, subtitles = [], {}
for airing in airings:
m3u8_url = self._download_json(
for airing in traverse_obj(airings, lambda _, v: v['playbackUrls'][0]['href']):
format_id = join_nonempty('feedType', 'feedLanguage', from_dict=airing)
m3u8_url = traverse_obj(self._download_json(
airing['playbackUrls'][0]['href'].format(scenario='browser~csai'), video_id,
headers={
note=f'Downloading {format_id} stream info JSON',
errnote=f'Failed to download {format_id} stream info, skipping',
fatal=False, headers={
'Authorization': self._access_token,
'Accept': 'application/vnd.media-service+json; version=2',
})['stream']['complete']
}), ('stream', 'complete', {url_or_none}))
if not m3u8_url:
continue
f, s = self._extract_m3u8_formats_and_subtitles(
m3u8_url, video_id, 'mp4', m3u8_id=join_nonempty(airing.get('feedType'), airing.get('feedLanguage')))
m3u8_url, video_id, 'mp4', m3u8_id=format_id, fatal=False)
formats.extend(f)
self._merge_subtitles(s, target=subtitles)

157
yt_dlp/extractor/murrtube.py
View File

@@ -5,39 +5,103 @@ from .common import InfoExtractor
from ..utils import (
ExtractorError,
OnDemandPagedList,
determine_ext,
int_or_none,
try_get,
clean_html,
extract_attributes,
get_element_by_class,
get_element_html_by_id,
parse_count,
remove_end,
update_url,
urlencode_postdata,
)
class MurrtubeIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'''(?x)
(?:
murrtube:|
https?://murrtube\.net/videos/(?P<slug>[a-z0-9\-]+)\-
https?://murrtube\.net/(?:v/|videos/(?P<slug>[a-z0-9-]+?)-)
)
(?P<id>[a-f0-9]{8}\-[a-f0-9]{4}\-[a-f0-9]{4}\-[a-f0-9]{4}\-[a-f0-9]{12})
(?P<id>[A-Z0-9]{4}|[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12})
'''
_TEST = {
_TESTS = [{
'url': 'https://murrtube.net/videos/inferno-x-skyler-148b6f2a-fdcc-4902-affe-9c0f41aaaca0',
'md5': '169f494812d9a90914b42978e73aa690',
'md5': '70380878a77e8565d4aea7f68b8bbb35',
'info_dict': {
'id': '148b6f2a-fdcc-4902-affe-9c0f41aaaca0',
'id': 'ca885d8456b95de529b6723b158032e11115d',
'ext': 'mp4',
'title': 'Inferno X Skyler',
'description': 'Humping a very good slutty sheppy (roomate)',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 284,
'uploader': 'Inferno Wolf',
'age_limit': 18,
'thumbnail': 'https://storage.murrtube.net/murrtube-production/ekbs3zcfvuynnqfx72nn2tkokvsd',
'comment_count': int,
'view_count': int,
'like_count': int,
'tags': ['hump', 'breed', 'Fursuit', 'murrsuit', 'bareback'],
},
}
}, {
'url': 'https://murrtube.net/v/0J2Q',
'md5': '31262f6ac56f0ca75e5a54a0f3fefcb6',
'info_dict': {
'id': '8442998c52134968d9caa36e473e1a6bac6ca',
'ext': 'mp4',
'uploader': 'Hayel',
'title': 'Who\'s in charge now?',
'description': 'md5:795791e97e5b0f1805ea84573f02a997',
'age_limit': 18,
'thumbnail': 'https://storage.murrtube.net/murrtube-production/fb1ojjwiucufp34ya6hxu5vfqi5s',
'comment_count': int,
'view_count': int,
'like_count': int,
},
}]
def _extract_count(self, name, html):
return parse_count(self._search_regex(
rf'([\d,]+)\s+<span[^>]*>{name}</span>', html, name, default=None))
def _real_initialize(self):
homepage = self._download_webpage(
'https://murrtube.net', None, note='Getting session token')
self._request_webpage(
'https://murrtube.net/accept_age_check', None, 'Setting age cookie',
data=urlencode_postdata(self._hidden_inputs(homepage)))
def _real_extract(self, url):
video_id = self._match_id(url)
if video_id.startswith('murrtube:'):
raise ExtractorError('Support for murrtube: prefix URLs is broken')
video_page = self._download_webpage(url, video_id)
video_attrs = extract_attributes(get_element_html_by_id('video', video_page))
playlist = update_url(video_attrs['data-url'], query=None)
video_id = self._search_regex(r'/([\da-f]+)/index.m3u8', playlist, 'video id')
return {
'id': video_id,
'title': remove_end(self._og_search_title(video_page), ' - Murrtube'),
'age_limit': 18,
'formats': self._extract_m3u8_formats(playlist, video_id, 'mp4'),
'description': self._og_search_description(video_page),
'thumbnail': update_url(self._og_search_thumbnail(video_page, default=''), query=None) or None,
'uploader': clean_html(get_element_by_class('pl-1 is-size-6 has-text-lighter', video_page)),
'view_count': self._extract_count('Views', video_page),
'like_count': self._extract_count('Likes', video_page),
'comment_count': self._extract_count('Comments', video_page),
}
class MurrtubeUserIE(InfoExtractor):
_WORKING = False
IE_DESC = 'Murrtube user profile'
_VALID_URL = r'https?://murrtube\.net/(?P<id>[^/]+)$'
_TESTS = [{
'url': 'https://murrtube.net/stormy',
'info_dict': {
'id': 'stormy',
},
'playlist_mincount': 27,
}]
_PAGE_SIZE = 10
def _download_gql(self, video_id, op, note=None, fatal=True):
result = self._download_json(
@@ -46,73 +110,6 @@ class MurrtubeIE(InfoExtractor):
headers={'Content-Type': 'application/json'})
return result['data']
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._download_gql(video_id, {
'operationName': 'Medium',
'variables': {
'id': video_id,
},
'query': '''\
query Medium($id: ID!) {
medium(id: $id) {
title
description
key
duration
commentsCount
likesCount
viewsCount
thumbnailKey
tagList
user {
name
__typename
}
__typename
}
}'''})
meta = data['medium']
storage_url = 'https://storage.murrtube.net/murrtube/'
format_url = storage_url + meta.get('key', '')
thumbnail = storage_url + meta.get('thumbnailKey', '')
if determine_ext(format_url) == 'm3u8':
formats = self._extract_m3u8_formats(
format_url, video_id, 'mp4', entry_protocol='m3u8_native', fatal=False)
else:
formats = [{'url': format_url}]
return {
'id': video_id,
'title': meta.get('title'),
'description': meta.get('description'),
'formats': formats,
'thumbnail': thumbnail,
'duration': int_or_none(meta.get('duration')),
'uploader': try_get(meta, lambda x: x['user']['name']),
'view_count': meta.get('viewsCount'),
'like_count': meta.get('likesCount'),
'comment_count': meta.get('commentsCount'),
'tags': meta.get('tagList'),
'age_limit': 18,
}
class MurrtubeUserIE(MurrtubeIE): # XXX: Do not subclass from concrete IE
_WORKING = False
IE_DESC = 'Murrtube user profile'
_VALID_URL = r'https?://murrtube\.net/(?P<id>[^/]+)$'
_TEST = {
'url': 'https://murrtube.net/stormy',
'info_dict': {
'id': 'stormy',
},
'playlist_mincount': 27,
}
_PAGE_SIZE = 10
def _fetch_page(self, username, user_id, page):
data = self._download_gql(username, {
'operationName': 'Media',

5
yt_dlp/extractor/nbc.py
View File

@@ -16,6 +16,7 @@ from ..utils import (
determine_ext,
float_or_none,
int_or_none,
join_nonempty,
mimetype2ext,
parse_age_limit,
parse_duration,
@@ -498,10 +499,8 @@ class NBCNewsIE(ThePlatformIE): # XXX: Do not subclass from concrete IE
m3u8_id=format_id, fatal=False))
continue
tbr = int_or_none(va.get('bitrate'), 1000)
if tbr:
format_id += f'-{tbr}'
formats.append({
'format_id': format_id,
'format_id': join_nonempty(format_id, tbr),
'url': public_url,
'width': int_or_none(va.get('width')),
'height': int_or_none(va.get('height')),

188
yt_dlp/extractor/neteasemusic.py
View File

@@ -22,12 +22,22 @@ from ..utils import (
class NetEaseMusicBaseIE(InfoExtractor):
_FORMATS = ['bMusic', 'mMusic', 'hMusic']
# XXX: _extract_formats logic depends on the order of the levels in each tier
_LEVELS = (
'standard', # free tier; 标准; 128kbps mp3 or aac
'higher', # free tier; 192kbps mp3 or aac
'exhigh', # free tier; 极高 (HQ); 320kbps mp3 or aac
'lossless', # VIP tier; 无损 (SQ); 48kHz/16bit flac
'hires', # VIP tier; 高解析度无损 (Hi-Res); 192kHz/24bit flac
'jyeffect', # VIP tier; 高清臻音 (Spatial Audio); 96kHz/24bit flac
'jymaster', # SVIP tier; 超清母带 (Master); 192kHz/24bit flac
'sky', # SVIP tier; 沉浸环绕声 (Surround Audio); flac
)
_API_BASE = 'http://music.163.com/api/'
_GEO_BYPASS = False
@staticmethod
def kilo_or_none(value):
def _kilo_or_none(value):
return int_or_none(value, scale=1000)
def _create_eapi_cipher(self, api_path, query_body, cookies):
@@ -66,45 +76,43 @@ class NetEaseMusicBaseIE(InfoExtractor):
**headers,
}, **kwargs)
def _call_player_api(self, song_id, bitrate):
def _call_player_api(self, song_id, level):
return self._download_eapi_json(
'/song/enhance/player/url', song_id, {'ids': f'[{song_id}]', 'br': bitrate},
note=f'Downloading song URL info: bitrate {bitrate}')
'/song/enhance/player/url/v1', song_id,
{'ids': f'[{song_id}]', 'level': level, 'encodeType': 'flac'},
note=f'Downloading song URL info: level {level}')
def extract_formats(self, info):
err = 0
def _extract_formats(self, info):
formats = []
song_id = info['id']
for song_format in self._FORMATS:
details = info.get(song_format)
if not details:
for level in self._LEVELS:
song = traverse_obj(
self._call_player_api(song_id, level), ('data', lambda _, v: url_or_none(v['url']), any))
if not song:
break # Media is not available due to removal or geo-restriction
actual_level = song.get('level')
if actual_level and actual_level != level:
if level in ('lossless', 'jymaster'):
break # We've already extracted the highest level of the user's account tier
continue
bitrate = int_or_none(details.get('bitrate')) or 999000
for song in traverse_obj(self._call_player_api(song_id, bitrate), ('data', lambda _, v: url_or_none(v['url']))):
song_url = song['url']
if self._is_valid_url(song_url, info['id'], 'song'):
formats.append({
'url': song_url,
'format_id': song_format,
'asr': traverse_obj(details, ('sr', {int_or_none})),
**traverse_obj(song, {
'ext': ('type', {str}),
'abr': ('br', {self.kilo_or_none}),
'filesize': ('size', {int_or_none}),
}),
})
elif err == 0:
err = traverse_obj(song, ('code', {int})) or 0
formats.append({
'url': song['url'],
'format_id': level,
'vcodec': 'none',
**traverse_obj(song, {
'ext': ('type', {str}),
'abr': ('br', {self._kilo_or_none}),
'filesize': ('size', {int_or_none}),
}),
})
if not actual_level:
break # Only 1 level is available if API does not return a value (netease:program)
if not formats:
if err != 0 and (err < 200 or err >= 400):
raise ExtractorError(f'No media links found (site code {err})', expected=True)
else:
self.raise_geo_restricted(
'No media links found: probably due to geo restriction.', countries=['CN'])
self.raise_geo_restricted(
'No media links found; possibly due to geo restriction', countries=['CN'])
return formats
def query_api(self, endpoint, video_id, note):
def _query_api(self, endpoint, video_id, note):
result = self._download_json(
f'{self._API_BASE}{endpoint}', video_id, note, headers={'Referer': self._API_BASE})
code = traverse_obj(result, ('code', {int}))
@@ -128,32 +136,29 @@ class NetEaseMusicBaseIE(InfoExtractor):
class NetEaseMusicIE(NetEaseMusicBaseIE):
IE_NAME = 'netease:song'
IE_DESC = '网易云音乐'
_VALID_URL = r'https?://(y\.)?music\.163\.com/(?:[#m]/)?song\?.*?\bid=(?P<id>[0-9]+)'
_VALID_URL = r'https?://(?:y\.)?music\.163\.com/(?:[#m]/)?song\?.*?\bid=(?P<id>[0-9]+)'
_TESTS = [{
'url': 'https://music.163.com/#/song?id=548648087',
'url': 'https://music.163.com/#/song?id=550136151',
'info_dict': {
'id': '548648087',
'id': '550136151',
'ext': 'mp3',
'title': '戒烟 (Live)',
'creator': '李荣浩 / 朱正廷 / 陈立农 / 尤长靖 / ONER灵超 / ONER木子洋 / 杨非同 / 陆定昊',
'title': 'It\'s Ok (Live)',
'creators': 'count:10',
'timestamp': 1522944000,
'upload_date': '20180405',
'description': 'md5:3650af9ee22c87e8637cb2dde22a765c',
'subtitles': {'lyrics': [{'ext': 'lrc'}]},
'duration': 256,
'description': 'md5:9fd07059c2ccee3950dc8363429a3135',
'duration': 197,
'thumbnail': r're:^http.*\.jpg',
'album': '偶像练习生 表演曲目合集',
'average_rating': int,
'album_artist': '偶像练习生',
'album_artists': ['偶像练习生'],
},
}, {
'note': 'No lyrics.',
'url': 'http://music.163.com/song?id=17241424',
'info_dict': {
'id': '17241424',
'ext': 'mp3',
'title': 'Opus 28',
'creator': 'Dustin O\'Halloran',
'upload_date': '20080211',
'timestamp': 1202745600,
'duration': 263,
@@ -161,15 +166,18 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
'album': 'Piano Solos Vol. 2',
'album_artist': 'Dustin O\'Halloran',
'average_rating': int,
'description': '[00:05.00]纯音乐，请欣赏\n',
'album_artists': ['Dustin O\'Halloran'],
'creators': ['Dustin O\'Halloran'],
'subtitles': {'lyrics': [{'ext': 'lrc'}]},
},
}, {
'url': 'https://y.music.163.com/m/song?app_version=8.8.45&id=95670&uct2=sKnvS4+0YStsWkqsPhFijw%3D%3D&dlt=0846',
'md5': '95826c73ea50b1c288b22180ec9e754d',
'md5': 'b896be78d8d34bd7bb665b26710913ff',
'info_dict': {
'id': '95670',
'ext': 'mp3',
'title': '国际歌',
'creator': '马备',
'upload_date': '19911130',
'timestamp': 691516800,
'description': 'md5:1ba2f911a2b0aa398479f595224f2141',
@@ -180,6 +188,8 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
'average_rating': int,
'album': '红色摇滚',
'album_artist': '侯牧人',
'creators': ['马备'],
'album_artists': ['侯牧人'],
},
}, {
'url': 'http://music.163.com/#/song?id=32102397',
@@ -188,7 +198,7 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
'id': '32102397',
'ext': 'mp3',
'title': 'Bad Blood',
'creator': 'Taylor Swift / Kendrick Lamar',
'creators': ['Taylor Swift', 'Kendrick Lamar'],
'upload_date': '20150516',
'timestamp': 1431792000,
'description': 'md5:21535156efb73d6d1c355f95616e285a',
@@ -207,7 +217,7 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
'id': '22735043',
'ext': 'mp3',
'title': '소원을 말해봐 (Genie)',
'creator': '少女时代',
'creators': ['少女时代'],
'upload_date': '20100127',
'timestamp': 1264608000,
'description': 'md5:03d1ffebec3139aa4bafe302369269c5',
@@ -251,12 +261,12 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
def _real_extract(self, url):
song_id = self._match_id(url)
info = self.query_api(
info = self._query_api(
f'song/detail?id={song_id}&ids=%5B{song_id}%5D', song_id, 'Downloading song info')['songs'][0]
formats = self.extract_formats(info)
formats = self._extract_formats(info)
lyrics = self._process_lyrics(self.query_api(
lyrics = self._process_lyrics(self._query_api(
f'song/lyric?id={song_id}&lv=-1&tv=-1', song_id, 'Downloading lyrics data'))
lyric_data = {
'description': traverse_obj(lyrics, (('lyrics_merged', 'lyrics'), 0, 'data'), get_all=False),
@@ -267,14 +277,14 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
'id': song_id,
'formats': formats,
'alt_title': '/'.join(traverse_obj(info, (('transNames', 'alias'), ...))) or None,
'creator': ' / '.join(traverse_obj(info, ('artists', ..., 'name'))) or None,
'album_artist': ' / '.join(traverse_obj(info, ('album', 'artists', ..., 'name'))) or None,
'creators': traverse_obj(info, ('artists', ..., 'name')) or None,
'album_artists': traverse_obj(info, ('album', 'artists', ..., 'name')) or None,
**lyric_data,
**traverse_obj(info, {
'title': ('name', {str}),
'timestamp': ('album', 'publishTime', {self.kilo_or_none}),
'timestamp': ('album', 'publishTime', {self._kilo_or_none}),
'thumbnail': ('album', 'picUrl', {url_or_none}),
'duration': ('duration', {self.kilo_or_none}),
'duration': ('duration', {self._kilo_or_none}),
'album': ('album', 'name', {str}),
'average_rating': ('score', {int_or_none}),
}),
@@ -284,7 +294,7 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
class NetEaseMusicAlbumIE(NetEaseMusicBaseIE):
IE_NAME = 'netease:album'
IE_DESC = '网易云音乐 - 专辑'
_VALID_URL = r'https?://music\.163\.com/(#/)?album\?id=(?P<id>[0-9]+)'
_VALID_URL = r'https?://music\.163\.com/(?:#/)?album\?id=(?P<id>[0-9]+)'
_TESTS = [{
'url': 'https://music.163.com/#/album?id=133153666',
'info_dict': {
@@ -294,7 +304,7 @@ class NetEaseMusicAlbumIE(NetEaseMusicBaseIE):
'description': '桃几2021年翻唱合集',
'thumbnail': r're:^http.*\.jpg',
},
'playlist_mincount': 13,
'playlist_mincount': 12,
}, {
'url': 'http://music.163.com/#/album?id=220780',
'info_dict': {
@@ -328,7 +338,7 @@ class NetEaseMusicAlbumIE(NetEaseMusicBaseIE):
class NetEaseMusicSingerIE(NetEaseMusicBaseIE):
IE_NAME = 'netease:singer'
IE_DESC = '网易云音乐 - 歌手'
_VALID_URL = r'https?://music\.163\.com/(#/)?artist\?id=(?P<id>[0-9]+)'
_VALID_URL = r'https?://music\.163\.com/(?:#/)?artist\?id=(?P<id>[0-9]+)'
_TESTS = [{
'note': 'Singer has aliases.',
'url': 'http://music.163.com/#/artist?id=10559',
@@ -358,7 +368,7 @@ class NetEaseMusicSingerIE(NetEaseMusicBaseIE):
def _real_extract(self, url):
singer_id = self._match_id(url)
info = self.query_api(
info = self._query_api(
f'artist/{singer_id}?id={singer_id}', singer_id, note='Downloading singer data')
name = join_nonempty(
@@ -372,7 +382,7 @@ class NetEaseMusicSingerIE(NetEaseMusicBaseIE):
class NetEaseMusicListIE(NetEaseMusicBaseIE):
IE_NAME = 'netease:playlist'
IE_DESC = '网易云音乐 - 歌单'
_VALID_URL = r'https?://music\.163\.com/(#/)?(playlist|discover/toplist)\?id=(?P<id>[0-9]+)'
_VALID_URL = r'https?://music\.163\.com/(?:#/)?(?:playlist|discover/toplist)\?id=(?P<id>[0-9]+)'
_TESTS = [{
'url': 'http://music.163.com/#/playlist?id=79177352',
'info_dict': {
@@ -405,11 +415,15 @@ class NetEaseMusicListIE(NetEaseMusicBaseIE):
'url': 'http://music.163.com/#/discover/toplist?id=3733003',
'info_dict': {
'id': '3733003',
'title': 're:韩国Melon排行榜周榜 [0-9]{4}-[0-9]{2}-[0-9]{2}',
'title': 're:韩国Melon排行榜周榜(?: [0-9]{4}-[0-9]{2}-[0-9]{2})?',
'description': 'md5:73ec782a612711cadc7872d9c1e134fc',
'upload_date': '20200109',
'uploader_id': '2937386',
'tags': ['韩语', '榜单'],
'uploader': 'Melon榜单',
'timestamp': 1578569373,
},
'playlist_count': 50,
'skip': 'Blocked outside Mainland China',
}]
def _real_extract(self, url):
@@ -426,7 +440,7 @@ class NetEaseMusicListIE(NetEaseMusicBaseIE):
'tags': ('tags', ..., {str}),
'uploader': ('creator', 'nickname', {str}),
'uploader_id': ('creator', 'userId', {str_or_none}),
'timestamp': ('updateTime', {self.kilo_or_none}),
'timestamp': ('updateTime', {self._kilo_or_none}),
}))
if traverse_obj(info, ('playlist', 'specialType')) == 10:
metainfo['title'] = f'{metainfo.get("title")} {strftime_or_none(metainfo.get("timestamp"), "%Y-%m-%d")}'
@@ -437,7 +451,7 @@ class NetEaseMusicListIE(NetEaseMusicBaseIE):
class NetEaseMusicMvIE(NetEaseMusicBaseIE):
IE_NAME = 'netease:mv'
IE_DESC = '网易云音乐 - MV'
_VALID_URL = r'https?://music\.163\.com/(#/)?mv\?id=(?P<id>[0-9]+)'
_VALID_URL = r'https?://music\.163\.com/(?:#/)?mv\?id=(?P<id>[0-9]+)'
_TESTS = [{
'url': 'https://music.163.com/#/mv?id=10958064',
'info_dict': {
@@ -445,7 +459,7 @@ class NetEaseMusicMvIE(NetEaseMusicBaseIE):
'ext': 'mp4',
'title': '交换余生',
'description': 'md5:e845872cff28820642a2b02eda428fea',
'creator': '林俊杰',
'creators': ['林俊杰'],
'upload_date': '20200916',
'thumbnail': r're:http.*\.jpg',
'duration': 364,
@@ -460,7 +474,7 @@ class NetEaseMusicMvIE(NetEaseMusicBaseIE):
'ext': 'mp4',
'title': '이럴거면 그러지말지',
'description': '白雅言自作曲唱甜蜜爱情',
'creator': '白娥娟',
'creators': ['白娥娟'],
'upload_date': '20150520',
'thumbnail': r're:http.*\.jpg',
'duration': 216,
@@ -468,12 +482,28 @@ class NetEaseMusicMvIE(NetEaseMusicBaseIE):
'like_count': int,
'comment_count': int,
},
'skip': 'Blocked outside Mainland China',
}, {
'note': 'This MV has multiple creators.',
'url': 'https://music.163.com/#/mv?id=22593543',
'info_dict': {
'id': '22593543',
'ext': 'mp4',
'title': '老北京杀器',
'creators': ['秃子2z', '辉子', 'Saber梁维嘉'],
'duration': 206,
'upload_date': '20240618',
'like_count': int,
'comment_count': int,
'thumbnail': r're:http.*\.jpg',
'view_count': int,
},
}]
def _real_extract(self, url):
mv_id = self._match_id(url)
info = self.query_api(
info = self._query_api(
f'mv/detail?id={mv_id}&type=mp4', mv_id, 'Downloading mv info')['data']
formats = [
@@ -484,13 +514,13 @@ class NetEaseMusicMvIE(NetEaseMusicBaseIE):
return {
'id': mv_id,
'formats': formats,
'creators': traverse_obj(info, ('artists', ..., 'name')) or [info.get('artistName')],
**traverse_obj(info, {
'title': ('name', {str}),
'description': (('desc', 'briefDesc'), {str}, {lambda x: x or None}),
'creator': ('artistName', {str}),
'upload_date': ('publishTime', {unified_strdate}),
'thumbnail': ('cover', {url_or_none}),
'duration': ('duration', {self.kilo_or_none}),
'duration': ('duration', {self._kilo_or_none}),
'view_count': ('playCount', {int_or_none}),
'like_count': ('likeCount', {int_or_none}),
'comment_count': ('commentCount', {int_or_none}),
@@ -501,7 +531,7 @@ class NetEaseMusicMvIE(NetEaseMusicBaseIE):
class NetEaseMusicProgramIE(NetEaseMusicBaseIE):
IE_NAME = 'netease:program'
IE_DESC = '网易云音乐 - 电台节目'
_VALID_URL = r'https?://music\.163\.com/(#/?)program\?id=(?P<id>[0-9]+)'
_VALID_URL = r'https?://music\.163\.com/(?:#/)?program\?id=(?P<id>[0-9]+)'
_TESTS = [{
'url': 'http://music.163.com/#/program?id=10109055',
'info_dict': {
@@ -509,7 +539,7 @@ class NetEaseMusicProgramIE(NetEaseMusicBaseIE):
'ext': 'mp3',
'title': '不丹足球背后的故事',
'description': '喜马拉雅人的足球梦 ...',
'creator': '大话西藏',
'creators': ['大话西藏'],
'timestamp': 1434179287,
'upload_date': '20150613',
'thumbnail': r're:http.*\.jpg',
@@ -522,7 +552,7 @@ class NetEaseMusicProgramIE(NetEaseMusicBaseIE):
'id': '10141022',
'title': '滚滚电台的有声节目',
'description': 'md5:8d594db46cc3e6509107ede70a4aaa3b',
'creator': '滚滚电台ORZ',
'creators': ['滚滚电台ORZ'],
'timestamp': 1434450733,
'upload_date': '20150616',
'thumbnail': r're:http.*\.jpg',
@@ -536,7 +566,7 @@ class NetEaseMusicProgramIE(NetEaseMusicBaseIE):
'ext': 'mp3',
'title': '滚滚电台的有声节目',
'description': 'md5:8d594db46cc3e6509107ede70a4aaa3b',
'creator': '滚滚电台ORZ',
'creators': ['滚滚电台ORZ'],
'timestamp': 1434450733,
'upload_date': '20150616',
'thumbnail': r're:http.*\.jpg',
@@ -550,7 +580,7 @@ class NetEaseMusicProgramIE(NetEaseMusicBaseIE):
def _real_extract(self, url):
program_id = self._match_id(url)
info = self.query_api(
info = self._query_api(
f'dj/program/detail?id={program_id}', program_id, note='Downloading program info')['program']
metainfo = traverse_obj(info, {
@@ -558,17 +588,17 @@ class NetEaseMusicProgramIE(NetEaseMusicBaseIE):
'description': ('description', {str}),
'creator': ('dj', 'brand', {str}),
'thumbnail': ('coverUrl', {url_or_none}),
'timestamp': ('createTime', {self.kilo_or_none}),
'timestamp': ('createTime', {self._kilo_or_none}),
})
if not self._yes_playlist(
info['songs'] and program_id, info['mainSong']['id'], playlist_label='program', video_label='song'):
formats = self.extract_formats(info['mainSong'])
formats = self._extract_formats(info['mainSong'])
return {
'id': str(info['mainSong']['id']),
'formats': formats,
'duration': traverse_obj(info, ('mainSong', 'duration', {self.kilo_or_none})),
'duration': traverse_obj(info, ('mainSong', 'duration', {self._kilo_or_none})),
**metainfo,
}
@@ -579,7 +609,7 @@ class NetEaseMusicProgramIE(NetEaseMusicBaseIE):
class NetEaseMusicDjRadioIE(NetEaseMusicBaseIE):
IE_NAME = 'netease:djradio'
IE_DESC = '网易云音乐 - 电台'
_VALID_URL = r'https?://music\.163\.com/(#/)?djradio\?id=(?P<id>[0-9]+)'
_VALID_URL = r'https?://music\.163\.com/(?:#/)?djradio\?id=(?P<id>[0-9]+)'
_TEST = {
'url': 'http://music.163.com/#/djradio?id=42',
'info_dict': {
@@ -597,7 +627,7 @@ class NetEaseMusicDjRadioIE(NetEaseMusicBaseIE):
metainfo = {}
entries = []
for offset in itertools.count(start=0, step=self._PAGE_SIZE):
info = self.query_api(
info = self._query_api(
f'dj/program/byradio?asc=false&limit={self._PAGE_SIZE}&radioId={dj_id}&offset={offset}',
dj_id, note=f'Downloading dj programs - {offset}')

3
yt_dlp/extractor/nhl.py
View File

@@ -2,6 +2,7 @@ from .common import InfoExtractor
from ..utils import (
determine_ext,
int_or_none,
join_nonempty,
parse_duration,
parse_iso8601,
)
@@ -41,7 +42,7 @@ class NHLBaseIE(InfoExtractor):
else:
height = int_or_none(playback.get('height'))
formats.append({
'format_id': playback.get('name', 'http' + (f'-{height}p' if height else '')),
'format_id': playback.get('name') or join_nonempty('http', height and f'{height}p'),
'url': playback_url,
'width': int_or_none(playback.get('width')),
'height': height,

6
yt_dlp/extractor/nuum.py
View File

@@ -43,15 +43,17 @@ class NuumBaseIE(InfoExtractor):
is_live = media.get('media_status') == 'RUNNING'
formats, subtitles = None, None
headers = {'Referer': 'https://nuum.ru/'}
if extract_formats:
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
media_url, video_id, 'mp4', live=is_live)
media_url, video_id, 'mp4', live=is_live, headers=headers)
return filter_dict({
'id': video_id,
'is_live': is_live,
'formats': formats,
'subtitles': subtitles,
'http_headers': headers,
**traverse_obj(container, {
'title': ('media_container_name', {str}),
'description': ('media_container_description', {str}),
@@ -78,7 +80,7 @@ class NuumMediaIE(NuumBaseIE):
'only_matching': True,
}, {
'url': 'https://nuum.ru/videos/1567547-toxi-hurtz',
'md5': 'f1d9118a30403e32b702a204eb03aca3',
'md5': 'ce28837a5bbffe6952d7bfd3d39811b0',
'info_dict': {
'id': '1567547',
'ext': 'mp4',

3
yt_dlp/extractor/orf.py
View File

@@ -550,7 +550,8 @@ class ORFONIE(InfoExtractor):
return self._extract_video_info(segment_id, selected_segment)
# Even some segmented videos have an unsegmented version available in API response root
if not traverse_obj(api_json, ('sources', ..., ..., 'src', {url_or_none})):
if (self._configuration_arg('prefer_segments_playlist')
or not traverse_obj(api_json, ('sources', ..., ..., 'src', {url_or_none}))):
return self.playlist_result(
(self._extract_video_info(str(segment['id']), segment) for segment in segments),
video_id, **self._parse_metadata(api_json), multi_video=True)

18
yt_dlp/extractor/patreon.py
View File

@@ -2,6 +2,7 @@ import itertools
import urllib.parse
from .common import InfoExtractor
from .sproutvideo import VidsIoIE
from .vimeo import VimeoIE
from ..networking.exceptions import HTTPError
from ..utils import (
@@ -12,6 +13,7 @@ from ..utils import (
int_or_none,
mimetype2ext,
parse_iso8601,
smuggle_url,
str_or_none,
traverse_obj,
url_or_none,
@@ -305,22 +307,28 @@ class PatreonIE(PatreonBaseIE):
'channel_follower_count': ('attributes', 'patron_count', {int_or_none}),
}))
# all-lowercase 'referer' so we can smuggle it to Generic, SproutVideo, Vimeo
headers = {'referer': 'https://patreon.com/'}
# handle Vimeo embeds
if traverse_obj(attributes, ('embed', 'provider')) == 'Vimeo':
v_url = urllib.parse.unquote(self._html_search_regex(
r'(https(?:%3A%2F%2F|://)player\.vimeo\.com.+app_id(?:=|%3D)+\d+)',
traverse_obj(attributes, ('embed', 'html', {str})), 'vimeo url', fatal=False) or '')
if url_or_none(v_url) and self._request_webpage(
v_url, video_id, 'Checking Vimeo embed URL',
headers={'Referer': 'https://patreon.com/'},
fatal=False, errnote=False):
v_url, video_id, 'Checking Vimeo embed URL', headers=headers,
fatal=False, errnote=False, expected_status=429): # 429 is TLS fingerprint rejection
entries.append(self.url_result(
VimeoIE._smuggle_referrer(v_url, 'https://patreon.com/'),
VimeoIE, url_transparent=True))
embed_url = traverse_obj(attributes, ('embed', 'url', {url_or_none}))
if embed_url and self._request_webpage(embed_url, video_id, 'Checking embed URL', fatal=False, errnote=False):
entries.append(self.url_result(embed_url))
if embed_url and (urlh := self._request_webpage(
embed_url, video_id, 'Checking embed URL', headers=headers,
fatal=False, errnote=False, expected_status=403)):
# Password-protected vids.io embeds return 403 errors w/o --video-password or session cookie
if urlh.status != 403 or VidsIoIE.suitable(embed_url):
entries.append(self.url_result(smuggle_url(embed_url, headers)))
post_file = traverse_obj(attributes, ('post_file', {dict}))
if post_file:

6
yt_dlp/extractor/peloton.py
View File

@@ -41,7 +41,7 @@ class PelotonIE(InfoExtractor):
}, 'params': {
'skip_download': 'm3u8',
},
'_skip': 'Account needed',
'skip': 'Account needed',
}, {
'url': 'https://members.onepeloton.com/classes/player/26603d53d6bb4de1b340514864a6a6a8',
'info_dict': {
@@ -61,7 +61,7 @@ class PelotonIE(InfoExtractor):
}, 'params': {
'skip_download': 'm3u8',
},
'_skip': 'Account needed',
'skip': 'Account needed',
}]
_MANIFEST_URL_TEMPLATE = '%s?hdnea=%s'
@@ -199,7 +199,7 @@ class PelotonLiveIE(InfoExtractor):
'params': {
'skip_download': 'm3u8',
},
'_skip': 'Account needed',
'skip': 'Account needed',
}
def _real_extract(self, url):

7
yt_dlp/extractor/performgroup.py
View File

@@ -1,5 +1,5 @@
from .common import InfoExtractor
from ..utils import int_or_none
from ..utils import int_or_none, join_nonempty
class PerformGroupIE(InfoExtractor):
@@ -50,11 +50,8 @@ class PerformGroupIE(InfoExtractor):
if not c_url:
continue
tbr = int_or_none(c.get('bitrate'), 1000)
format_id = 'http'
if tbr:
format_id += f'-{tbr}'
formats.append({
'format_id': format_id,
'format_id': join_nonempty('http', tbr),
'url': c_url,
'tbr': tbr,
'width': int_or_none(c.get('width')),

41
yt_dlp/extractor/podbayfm.py
View File

@@ -1,28 +1,40 @@
from .common import InfoExtractor
from ..utils import OnDemandPagedList, int_or_none, jwt_decode_hs256, try_call
from ..utils import (
OnDemandPagedList,
clean_html,
int_or_none,
jwt_decode_hs256,
url_or_none,
)
from ..utils.traversal import traverse_obj
def result_from_props(props, episode_id=None):
def result_from_props(props):
return {
'id': props.get('podcast_id') or episode_id,
'title': props.get('title'),
'url': props['mediaURL'],
**traverse_obj(props, {
'id': ('_id', {str}),
'title': ('title', {str}),
'url': ('mediaURL', {url_or_none}),
'description': ('description', {clean_html}),
'thumbnail': ('image', {jwt_decode_hs256}, 'url', {url_or_none}),
'timestamp': ('timestamp', {int_or_none}),
'duration': ('duration', {int_or_none}),
}),
'ext': 'mp3',
'thumbnail': try_call(lambda: jwt_decode_hs256(props['image'])['url']),
'timestamp': props.get('timestamp'),
'duration': int_or_none(props.get('duration')),
'vcodec': 'none',
}
class PodbayFMIE(InfoExtractor):
_VALID_URL = r'https?://podbay\.fm/p/[^/]*/e/(?P<id>[^/]*)/?(?:[\?#].*)?$'
_VALID_URL = r'https?://podbay\.fm/p/[^/?#]+/e/(?P<id>\d+)'
_TESTS = [{
'url': 'https://podbay.fm/p/behind-the-bastards/e/1647338400',
'md5': '98b41285dcf7989d105a4ed0404054cf',
'md5': '895ac8505de349515f5ee8a4a3195c93',
'info_dict': {
'id': '1647338400',
'id': '62306451f4a48e58d0c4d6a8',
'title': 'Part One: Kissinger',
'ext': 'mp3',
'description': r're:^We begin our epic six part series on Henry Kissinger.+',
'thumbnail': r're:^https?://.*\.jpg',
'timestamp': 1647338400,
'duration': 5001,
@@ -34,24 +46,25 @@ class PodbayFMIE(InfoExtractor):
episode_id = self._match_id(url)
webpage = self._download_webpage(url, episode_id)
data = self._search_nextjs_data(webpage, episode_id)
return result_from_props(data['props']['pageProps']['episode'], episode_id)
return result_from_props(data['props']['pageProps']['episode'])
class PodbayFMChannelIE(InfoExtractor):
_VALID_URL = r'https?://podbay\.fm/p/(?P<id>[^/]*)/?(?:[\?#].*)?$'
_VALID_URL = r'https?://podbay\.fm/p/(?P<id>[^/?#]+)/?(?:$|[?#])'
_TESTS = [{
'url': 'https://podbay.fm/p/behind-the-bastards',
'info_dict': {
'id': 'behind-the-bastards',
'title': 'Behind the Bastards',
},
'playlist_mincount': 21,
}]
_PAGE_SIZE = 10
def _fetch_page(self, channel_id, pagenum):
return self._download_json(
f'https://podbay.fm/api/podcast?reverse=true&page={pagenum}&slug={channel_id}',
channel_id)['podcast']
f'Downloading channel JSON page {pagenum + 1}', channel_id)['podcast']
@staticmethod
def _results_from_page(channel_id, page):

3
yt_dlp/extractor/pokergo.py
View File

@@ -5,6 +5,7 @@ from ..utils import (
ExtractorError,
try_get,
)
from ..utils.traversal import traverse_obj
class PokerGoBaseIE(InfoExtractor):
@@ -65,7 +66,7 @@ class PokerGoIE(PokerGoBaseIE):
'width': image.get('width'),
'height': image.get('height'),
} for image in data_json.get('images') or [] if image.get('url')]
series_json = next(dct for dct in data_json.get('show_tags') or [] if dct.get('video_id') == video_id) or {}
series_json = traverse_obj(data_json, ('show_tags', lambda _, v: v['video_id'] == video_id, any)) or {}
return {
'_type': 'url_transparent',

2
yt_dlp/extractor/pr0gramm.py
View File

@@ -1,9 +1,9 @@
import datetime as dt
import functools
import json
import urllib.parse
from .common import InfoExtractor
from ..compat import functools
from ..utils import (
ExtractorError,
float_or_none,

5
yt_dlp/extractor/prosiebensat1.py
View File

@@ -7,6 +7,7 @@ from ..utils import (
determine_ext,
float_or_none,
int_or_none,
join_nonempty,
merge_dicts,
unified_strdate,
)
@@ -147,13 +148,13 @@ class ProSiebenSat1BaseIE(InfoExtractor):
'page_url': 'http://www.prosieben.de',
'tbr': tbr,
'ext': 'flv',
'format_id': 'rtmp{}'.format(f'-{tbr}' if tbr else ''),
'format_id': join_nonempty('rtmp', tbr),
})
else:
formats.append({
'url': source_url,
'tbr': tbr,
'format_id': 'http{}'.format(f'-{tbr}' if tbr else ''),
'format_id': join_nonempty('http', tbr),
})
return {

544
yt_dlp/extractor/qqmusic.py
View File

@@ -1,48 +1,125 @@
import base64
import functools
import json
import random
import re
import time
from .common import InfoExtractor
from ..utils import (
ExtractorError,
OnDemandPagedList,
clean_html,
int_or_none,
join_nonempty,
js_to_json,
str_or_none,
strip_jsonp,
traverse_obj,
unescapeHTML,
url_or_none,
urljoin,
)
class QQMusicIE(InfoExtractor):
class QQMusicBaseIE(InfoExtractor):
def _get_cookie(self, key, default=None):
return getattr(self._get_cookies('https://y.qq.com').get(key), 'value', default)
def _get_g_tk(self):
n = 5381
for c in self._get_cookie('qqmusic_key', ''):
n += (n << 5) + ord(c)
return n & 2147483647
def _get_uin(self):
return int_or_none(self._get_cookie('uin')) or 0
@property
def is_logged_in(self):
return bool(self._get_uin() and self._get_cookie('fqm_pvqid'))
# Reference: m_r_GetRUin() in top_player.js
# http://imgcache.gtimg.cn/music/portal_v3/y/top_player.js
@staticmethod
def _m_r_get_ruin():
cur_ms = int(time.time() * 1000) % 1000
return int(round(random.random() * 2147483647) * cur_ms % 1E10)
def _download_init_data(self, url, mid, fatal=True):
webpage = self._download_webpage(url, mid, fatal=fatal)
return self._search_json(r'window\.__INITIAL_DATA__\s*=', webpage,
'init data', mid, transform_source=js_to_json, fatal=fatal)
def _make_fcu_req(self, req_dict, mid, headers={}, **kwargs):
return self._download_json(
'https://u.y.qq.com/cgi-bin/musicu.fcg', mid, data=json.dumps({
'comm': {
'cv': 0,
'ct': 24,
'format': 'json',
'uin': self._get_uin(),
},
**req_dict,
}, separators=(',', ':')).encode(), headers=headers, **kwargs)
class QQMusicIE(QQMusicBaseIE):
IE_NAME = 'qqmusic'
IE_DESC = 'QQ音乐'
_VALID_URL = r'https?://y\.qq\.com/n/yqq/song/(?P<id>[0-9A-Za-z]+)\.html'
_VALID_URL = r'https?://y\.qq\.com/n/ryqq/songDetail/(?P<id>[0-9A-Za-z]+)'
_TESTS = [{
'url': 'https://y.qq.com/n/yqq/song/004295Et37taLD.html',
'url': 'https://y.qq.com/n/ryqq/songDetail/004Ti8rT003TaZ',
'md5': 'd7adc5c438d12e2cb648cca81593fd47',
'info_dict': {
'id': '004Ti8rT003TaZ',
'ext': 'mp3',
'title': '永夜のパレード (永夜的游行)',
'album': '幻想遊園郷 -Fantastic Park-',
'release_date': '20111230',
'duration': 281,
'creators': ['ケーキ姫', 'JUMA'],
'genres': ['Pop'],
'description': 'md5:b5261f3d595657ae561e9e6aee7eb7d9',
'size': 4501244,
'thumbnail': r're:^https?://.*\.jpg(?:$|[#?])',
'subtitles': 'count:1',
},
}, {
'url': 'https://y.qq.com/n/ryqq/songDetail/004295Et37taLD',
'md5': '5f1e6cea39e182857da7ffc5ef5e6bb8',
'info_dict': {
'id': '004295Et37taLD',
'ext': 'mp3',
'title': '可惜没如果',
'release_date': '20141227',
'creator': '林俊杰',
'description': 'md5:d85afb3051952ecc50a1ee8a286d1eac',
'thumbnail': r're:^https?://.*\.jpg$',
'album': '新地球 - 人 (Special Edition)',
'release_date': '20150129',
'duration': 298,
'creators': ['林俊杰'],
'genres': ['Pop'],
'description': 'md5:f568421ff618d2066e74b65a04149c4e',
'thumbnail': r're:^https?://.*\.jpg(?:$|[#?])',
},
'skip': 'premium member only',
}, {
'note': 'There is no mp3-320 version of this song.',
'url': 'https://y.qq.com/n/yqq/song/004MsGEo3DdNxV.html',
'md5': 'fa3926f0c585cda0af8fa4f796482e3e',
'url': 'https://y.qq.com/n/ryqq/songDetail/004MsGEo3DdNxV',
'md5': '028aaef1ae13d8a9f4861a92614887f9',
'info_dict': {
'id': '004MsGEo3DdNxV',
'ext': 'mp3',
'title': '如果',
'album': '新传媒电视连续剧金曲系列II',
'release_date': '20050626',
'creator': '李季美',
'description': 'md5:46857d5ed62bc4ba84607a805dccf437',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 220,
'creators': ['李季美'],
'genres': [],
'description': 'md5:fc711212aa623b28534954dc4bd67385',
'size': 3535730,
'thumbnail': r're:^https?://.*\.jpg(?:$|[#?])',
},
}, {
'note': 'lyrics not in .lrc format',
'url': 'https://y.qq.com/n/yqq/song/001JyApY11tIp6.html',
'url': 'https://y.qq.com/n/ryqq/songDetail/001JyApY11tIp6',
'info_dict': {
'id': '001JyApY11tIp6',
'ext': 'mp3',
@@ -50,185 +127,193 @@ class QQMusicIE(InfoExtractor):
'release_date': '19970225',
'creator': 'Dark Funeral',
'description': 'md5:c9b20210587cbcd6836a1c597bab4525',
'thumbnail': r're:^https?://.*\.jpg$',
},
'params': {
'skip_download': True,
'thumbnail': r're:^https?://.*\.jpg(?:$|[#?])',
},
'params': {'skip_download': True},
'skip': 'no longer available',
}]
_FORMATS = {
'mp3-320': {'prefix': 'M800', 'ext': 'mp3', 'preference': 40, 'abr': 320},
'mp3-128': {'prefix': 'M500', 'ext': 'mp3', 'preference': 30, 'abr': 128},
'm4a': {'prefix': 'C200', 'ext': 'm4a', 'preference': 10},
'F000': {'name': 'flac', 'prefix': 'F000', 'ext': 'flac', 'preference': 60},
'A000': {'name': 'ape', 'prefix': 'A000', 'ext': 'ape', 'preference': 50},
'M800': {'name': '320mp3', 'prefix': 'M800', 'ext': 'mp3', 'preference': 40, 'abr': 320},
'M500': {'name': '128mp3', 'prefix': 'M500', 'ext': 'mp3', 'preference': 30, 'abr': 128},
'C400': {'name': '96aac', 'prefix': 'C400', 'ext': 'm4a', 'preference': 20, 'abr': 96},
'C200': {'name': '48aac', 'prefix': 'C200', 'ext': 'm4a', 'preference': 20, 'abr': 48},
}
# Reference: m_r_GetRUin() in top_player.js
# http://imgcache.gtimg.cn/music/portal_v3/y/top_player.js
@staticmethod
def m_r_get_ruin():
cur_ms = int(time.time() * 1000) % 1000
return int(round(random.random() * 2147483647) * cur_ms % 1E10)
def _real_extract(self, url):
mid = self._match_id(url)
detail_info_page = self._download_webpage(
f'http://s.plcloud.music.qq.com/fcgi-bin/fcg_yqq_song_detail_info.fcg?songmid={mid}&play=0',
mid, note='Download song detail info',
errnote='Unable to get song detail info', encoding='gbk')
init_data = self._download_init_data(url, mid, fatal=False)
info_data = self._make_fcu_req({'info': {
'module': 'music.pf_song_detail_svr',
'method': 'get_song_detail_yqq',
'param': {
'song_mid': mid,
'song_type': 0,
},
}}, mid, note='Downloading song info')['info']['data']['track_info']
song_name = self._html_search_regex(
r"songname:\s*'([^']+)'", detail_info_page, 'song name')
media_mid = info_data['file']['media_mid']
publish_time = self._html_search_regex(
r'发行时间：(\d{4}-\d{2}-\d{2})', detail_info_page,
'publish time', default=None)
if publish_time:
publish_time = publish_time.replace('-', '')
singer = self._html_search_regex(
r"singer:\s*'([^']+)", detail_info_page, 'singer', default=None)
lrc_content = self._html_search_regex(
r'<div class="content" id="lrc_content"[^<>]*>([^<>]+)</div>',
detail_info_page, 'LRC lyrics', default=None)
if lrc_content:
lrc_content = lrc_content.replace('\\n', '\n')
thumbnail_url = None
albummid = self._search_regex(
[r'albummid:\'([0-9a-zA-Z]+)\'', r'"albummid":"([0-9a-zA-Z]+)"'],
detail_info_page, 'album mid', default=None)
if albummid:
thumbnail_url = f'http://i.gtimg.cn/music/photo/mid_album_500/{albummid[-2:-1]}/{albummid[-1]}/{albummid}.jpg'
guid = self.m_r_get_ruin()
vkey = self._download_json(
f'http://base.music.qq.com/fcgi-bin/fcg_musicexpress.fcg?json=3&guid={guid}',
mid, note='Retrieve vkey', errnote='Unable to get vkey',
transform_source=strip_jsonp)['key']
data = self._make_fcu_req({
'req_1': {
'module': 'vkey.GetVkeyServer',
'method': 'CgiGetVkey',
'param': {
'guid': str(self._m_r_get_ruin()),
'songmid': [mid] * len(self._FORMATS),
'songtype': [0] * len(self._FORMATS),
'uin': str(self._get_uin()),
'loginflag': 1,
'platform': '20',
'filename': [f'{f["prefix"]}{media_mid}.{f["ext"]}' for f in self._FORMATS.values()],
},
},
'req_2': {
'module': 'music.musichallSong.PlayLyricInfo',
'method': 'GetPlayLyricInfo',
'param': {'songMID': mid},
},
}, mid, note='Downloading formats and lyric', headers=self.geo_verification_headers())
code = traverse_obj(data, ('req_1', 'code', {int}))
if code != 0:
raise ExtractorError(f'Failed to download format info, error code {code or "unknown"}')
formats = []
for format_id, details in self._FORMATS.items():
for media_info in traverse_obj(data, (
'req_1', 'data', 'midurlinfo', lambda _, v: v['songmid'] == mid and v['purl']),
):
format_key = traverse_obj(media_info, ('filename', {str}, {lambda x: x[:4]}))
format_info = self._FORMATS.get(format_key) or {}
format_id = format_info.get('name')
formats.append({
'url': 'http://cc.stream.qqmusic.qq.com/{}{}.{}?vkey={}&guid={}&fromtag=0'.format(
details['prefix'], mid, details['ext'], vkey, guid),
'url': urljoin('https://dl.stream.qqmusic.qq.com', media_info['purl']),
'format': format_id,
'format_id': format_id,
'quality': details['preference'],
'abr': details.get('abr'),
'size': traverse_obj(info_data, ('file', f'size_{format_id}', {int_or_none})),
'quality': format_info.get('preference'),
'abr': format_info.get('abr'),
'ext': format_info.get('ext'),
'vcodec': 'none',
})
self._check_formats(formats, mid)
actual_lrc_lyrics = ''.join(
line + '\n' for line in re.findall(
r'(?m)^(\[[0-9]{2}:[0-9]{2}(?:\.[0-9]{2,})?\][^\n]*|\[[^\]]*\])', lrc_content))
if not formats and not self.is_logged_in:
self.raise_login_required()
if traverse_obj(data, ('req_2', 'code')):
self.report_warning(f'Failed to download lyric, error {data["req_2"]["code"]!r}')
lrc_content = traverse_obj(data, ('req_2', 'data', 'lyric', {lambda x: base64.b64decode(x).decode('utf-8')}))
info_dict = {
'id': mid,
'formats': formats,
'title': song_name,
'release_date': publish_time,
'creator': singer,
'description': lrc_content,
'thumbnail': thumbnail_url,
**traverse_obj(info_data, {
'title': ('title', {str}),
'album': ('album', 'title', {str}, {lambda x: x or None}),
'release_date': ('time_public', {lambda x: x.replace('-', '') or None}),
'creators': ('singer', ..., 'name', {str}),
'alt_title': ('subtitle', {str}, {lambda x: x or None}),
'duration': ('interval', {int_or_none}),
}),
**traverse_obj(init_data, ('detail', {
'thumbnail': ('picurl', {url_or_none}),
'description': ('info', 'intro', 'content', ..., 'value', {str}),
'genres': ('info', 'genre', 'content', ..., 'value', {str}, all),
}), get_all=False),
}
if actual_lrc_lyrics:
info_dict['subtitles'] = {
'origin': [{
'ext': 'lrc',
'data': actual_lrc_lyrics,
}],
}
if lrc_content:
info_dict['subtitles'] = {'origin': [{'ext': 'lrc', 'data': lrc_content}]}
info_dict['description'] = join_nonempty(info_dict.get('description'), lrc_content, delim='\n')
return info_dict
class QQPlaylistBaseIE(InfoExtractor):
@staticmethod
def qq_static_url(category, mid):
return f'http://y.qq.com/y/static/{category}/{mid[-2]}/{mid[-1]}/{mid}.html'
def get_singer_all_songs(self, singmid, num):
return self._download_webpage(
r'https://c.y.qq.com/v8/fcg-bin/fcg_v8_singer_track_cp.fcg', singmid,
query={
'format': 'json',
'inCharset': 'utf8',
'outCharset': 'utf-8',
'platform': 'yqq',
'needNewCode': 0,
'singermid': singmid,
'order': 'listen',
'begin': 0,
'num': num,
'songstatus': 1,
})
def get_entries_from_page(self, singmid):
entries = []
default_num = 1
json_text = self.get_singer_all_songs(singmid, default_num)
json_obj_all_songs = self._parse_json(json_text, singmid)
if json_obj_all_songs['code'] == 0:
total = json_obj_all_songs['data']['total']
json_text = self.get_singer_all_songs(singmid, total)
json_obj_all_songs = self._parse_json(json_text, singmid)
for item in json_obj_all_songs['data']['list']:
if item['musicData'].get('songmid') is not None:
songmid = item['musicData']['songmid']
entries.append(self.url_result(
rf'https://y.qq.com/n/yqq/song/{songmid}.html', 'QQMusic', songmid))
return entries
class QQMusicSingerIE(QQPlaylistBaseIE):
class QQMusicSingerIE(QQMusicBaseIE):
IE_NAME = 'qqmusic:singer'
IE_DESC = 'QQ音乐 - 歌手'
_VALID_URL = r'https?://y\.qq\.com/n/yqq/singer/(?P<id>[0-9A-Za-z]+)\.html'
_TEST = {
'url': 'https://y.qq.com/n/yqq/singer/001BLpXF2DyJe2.html',
_VALID_URL = r'https?://y\.qq\.com/n/ryqq/singer/(?P<id>[0-9A-Za-z]+)'
_TESTS = [{
'url': 'https://y.qq.com/n/ryqq/singer/001BLpXF2DyJe2',
'info_dict': {
'id': '001BLpXF2DyJe2',
'title': '林俊杰',
'description': 'md5:870ec08f7d8547c29c93010899103751',
'description': 'md5:10624ce73b06fa400bc846f59b0305fa',
'thumbnail': r're:^https?://.*\.jpg(?:$|[#?])',
},
'playlist_mincount': 12,
}
'playlist_mincount': 100,
}, {
'url': 'https://y.qq.com/n/ryqq/singer/000Q00f213YzNV',
'info_dict': {
'id': '000Q00f213YzNV',
'title': '桃几OvO',
'description': '小破站小唱见~希望大家喜欢听我唱歌~！',
'thumbnail': r're:^https?://.*\.jpg(?:$|[#?])',
},
'playlist_count': 12,
'playlist': [{
'info_dict': {
'id': '0016cvsy02mmCl',
'ext': 'mp3',
'title': '群青',
'album': '桃几2021年翻唱集',
'release_date': '20210913',
'duration': 248,
'creators': ['桃几OvO'],
'genres': ['Pop'],
'description': 'md5:4296005a04edcb5cdbe0889d5055a7ae',
'size': 3970822,
'thumbnail': r're:^https?://.*\.jpg(?:$|[#?])',
},
}],
}]
_PAGE_SIZE = 50
def _fetch_page(self, mid, page_size, page_num):
data = self._make_fcu_req({'req_1': {
'module': 'music.web_singer_info_svr',
'method': 'get_singer_detail_info',
'param': {
'sort': 5,
'singermid': mid,
'sin': page_num * page_size,
'num': page_size,
}}}, mid, note=f'Downloading page {page_num}')
yield from traverse_obj(data, ('req_1', 'data', 'songlist', ..., {lambda x: self.url_result(
f'https://y.qq.com/n/ryqq/songDetail/{x["mid"]}', QQMusicIE, x['mid'], x.get('title'))}))
def _real_extract(self, url):
mid = self._match_id(url)
init_data = self._download_init_data(url, mid, fatal=False)
entries = self.get_entries_from_page(mid)
singer_page = self._download_webpage(url, mid, 'Download singer page')
singer_name = self._html_search_regex(
r"singername\s*:\s*'(.*?)'", singer_page, 'singer name', default=None)
singer_desc = None
return self.playlist_result(
OnDemandPagedList(functools.partial(self._fetch_page, mid, self._PAGE_SIZE), self._PAGE_SIZE),
mid, **traverse_obj(init_data, ('singerDetail', {
'title': ('basic_info', 'name', {str}),
'description': ('ex_info', 'desc', {str}),
'thumbnail': ('pic', 'pic', {url_or_none}),
})))
if mid:
singer_desc_page = self._download_xml(
'http://s.plcloud.music.qq.com/fcgi-bin/fcg_get_singer_desc.fcg', mid,
'Donwload singer description XML',
query={'utf8': 1, 'outCharset': 'utf-8', 'format': 'xml', 'singermid': mid},
headers={'Referer': 'https://y.qq.com/n/yqq/singer/'})
singer_desc = singer_desc_page.find('./data/info/desc').text
return self.playlist_result(entries, mid, singer_name, singer_desc)
class QQPlaylistBaseIE(InfoExtractor):
def _extract_entries(self, info_json, path):
for song in traverse_obj(info_json, path):
song_mid = song.get('songmid')
if not song_mid:
continue
yield self.url_result(
f'https://y.qq.com/n/ryqq/songDetail/{song_mid}',
QQMusicIE, song_mid, song.get('songname'))
class QQMusicAlbumIE(QQPlaylistBaseIE):
IE_NAME = 'qqmusic:album'
IE_DESC = 'QQ音乐 - 专辑'
_VALID_URL = r'https?://y\.qq\.com/n/yqq/album/(?P<id>[0-9A-Za-z]+)\.html'
_VALID_URL = r'https?://y\.qq\.com/n/ryqq/albumDetail/(?P<id>[0-9A-Za-z]+)'
_TESTS = [{
'url': 'https://y.qq.com/n/yqq/album/000gXCTb2AhRR1.html',
'url': 'https://y.qq.com/n/ryqq/albumDetail/000gXCTb2AhRR1',
'info_dict': {
'id': '000gXCTb2AhRR1',
'title': '我们都是这样长大的',
@@ -236,10 +321,10 @@ class QQMusicAlbumIE(QQPlaylistBaseIE):
},
'playlist_count': 4,
}, {
'url': 'https://y.qq.com/n/yqq/album/002Y5a3b3AlCu3.html',
'url': 'https://y.qq.com/n/ryqq/albumDetail/002Y5a3b3AlCu3',
'info_dict': {
'id': '002Y5a3b3AlCu3',
'title': '그리고...',
'title': '그리고…',
'description': 'md5:a48823755615508a95080e81b51ba729',
},
'playlist_count': 8,
@@ -248,49 +333,45 @@ class QQMusicAlbumIE(QQPlaylistBaseIE):
def _real_extract(self, url):
mid = self._match_id(url)
album = self._download_json(
f'http://i.y.qq.com/v8/fcg-bin/fcg_v8_album_info_cp.fcg?albummid={mid}&format=json',
mid, 'Download album page')['data']
album_json = self._download_json(
'http://i.y.qq.com/v8/fcg-bin/fcg_v8_album_info_cp.fcg',
mid, 'Download album page',
query={'albummid': mid, 'format': 'json'})['data']
entries = [
self.url_result(
'https://y.qq.com/n/yqq/song/' + song['songmid'] + '.html', 'QQMusic', song['songmid'],
) for song in album['list']
]
album_name = album.get('name')
album_detail = album.get('desc')
if album_detail is not None:
album_detail = album_detail.strip()
entries = self._extract_entries(album_json, ('list', ...))
return self.playlist_result(entries, mid, album_name, album_detail)
return self.playlist_result(entries, mid, **traverse_obj(album_json, {
'title': ('name', {str}),
'description': ('desc', {str.strip}),
}))
class QQMusicToplistIE(QQPlaylistBaseIE):
IE_NAME = 'qqmusic:toplist'
IE_DESC = 'QQ音乐 - 排行榜'
_VALID_URL = r'https?://y\.qq\.com/n/yqq/toplist/(?P<id>[0-9]+)\.html'
_VALID_URL = r'https?://y\.qq\.com/n/ryqq/toplist/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'https://y.qq.com/n/yqq/toplist/123.html',
'url': 'https://y.qq.com/n/ryqq/toplist/123',
'info_dict': {
'id': '123',
'title': '美国iTunes榜',
'description': 'md5:89db2335fdbb10678dee2d43fe9aba08',
'title': r're:美国热门音乐榜 \d{4}-\d{2}-\d{2}',
'description': '美国热门音乐榜，每周一更新。',
},
'playlist_count': 100,
'playlist_count': 95,
}, {
'url': 'https://y.qq.com/n/yqq/toplist/3.html',
'url': 'https://y.qq.com/n/ryqq/toplist/3',
'info_dict': {
'id': '3',
'title': '巅峰榜·欧美',
'description': 'md5:5a600d42c01696b26b71f8c4d43407da',
'title': r're:巅峰榜·欧美 \d{4}-\d{2}-\d{2}',
'description': 'md5:4def03b60d3644be4c9a36f21fd33857',
},
'playlist_count': 100,
}, {
'url': 'https://y.qq.com/n/yqq/toplist/106.html',
'url': 'https://y.qq.com/n/ryqq/toplist/106',
'info_dict': {
'id': '106',
'title': '韩国Mnet榜',
'title': r're:韩国Mnet榜 \d{4}-\d{2}-\d{2}',
'description': 'md5:cb84b325215e1d21708c615cac82a6e7',
},
'playlist_count': 50,
@@ -304,33 +385,20 @@ class QQMusicToplistIE(QQPlaylistBaseIE):
note='Download toplist page',
query={'type': 'toplist', 'topid': list_id, 'format': 'json'})
entries = [self.url_result(
'https://y.qq.com/n/yqq/song/' + song['data']['songmid'] + '.html', 'QQMusic',
song['data']['songmid'])
for song in toplist_json['songlist']]
topinfo = toplist_json.get('topinfo', {})
list_name = topinfo.get('ListName')
list_description = topinfo.get('info')
return self.playlist_result(entries, list_id, list_name, list_description)
return self.playlist_result(
self._extract_entries(toplist_json, ('songlist', ..., 'data')), list_id,
playlist_title=join_nonempty(*traverse_obj(
toplist_json, ((('topinfo', 'ListName'), 'update_time'), None)), delim=' '),
playlist_description=traverse_obj(toplist_json, ('topinfo', 'info')))
class QQMusicPlaylistIE(QQPlaylistBaseIE):
IE_NAME = 'qqmusic:playlist'
IE_DESC = 'QQ音乐 - 歌单'
_VALID_URL = r'https?://y\.qq\.com/n/yqq/playlist/(?P<id>[0-9]+)\.html'
_VALID_URL = r'https?://y\.qq\.com/n/ryqq/playlist/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'http://y.qq.com/n/yqq/playlist/3462654915.html',
'info_dict': {
'id': '3462654915',
'title': '韩国5月新歌精选下旬',
'description': 'md5:d2c9d758a96b9888cf4fe82f603121d4',
},
'playlist_count': 40,
'skip': 'playlist gone',
}, {
'url': 'https://y.qq.com/n/yqq/playlist/1374105607.html',
'url': 'https://y.qq.com/n/ryqq/playlist/1374105607',
'info_dict': {
'id': '1374105607',
'title': '易入人心的华语民谣',
@@ -346,19 +414,83 @@ class QQMusicPlaylistIE(QQPlaylistBaseIE):
'http://i.y.qq.com/qzone-music/fcg-bin/fcg_ucc_getcdinfo_byids_cp.fcg',
list_id, 'Download list page',
query={'type': 1, 'json': 1, 'utf8': 1, 'onlysong': 0, 'disstid': list_id},
transform_source=strip_jsonp)
transform_source=strip_jsonp, headers={'Referer': url})
if not len(list_json.get('cdlist', [])):
if list_json.get('code'):
raise ExtractorError(
'QQ Music said: error %d in fetching playlist info' % list_json['code'],
expected=True)
raise ExtractorError('Unable to get playlist info')
raise ExtractorError(join_nonempty(
'Unable to get playlist info',
join_nonempty('code', 'subcode', from_dict=list_json),
list_json.get('msg'), delim=': '))
cdlist = list_json['cdlist'][0]
entries = [self.url_result(
'https://y.qq.com/n/yqq/song/' + song['songmid'] + '.html', 'QQMusic', song['songmid'])
for song in cdlist['songlist']]
entries = self._extract_entries(list_json, ('cdlist', 0, 'songlist', ...))
list_name = cdlist.get('dissname')
list_description = clean_html(unescapeHTML(cdlist.get('desc')))
return self.playlist_result(entries, list_id, list_name, list_description)
return self.playlist_result(entries, list_id, **traverse_obj(list_json, ('cdlist', 0, {
'title': ('dissname', {str}),
'description': ('desc', {unescapeHTML}, {clean_html}),
})))
class QQMusicVideoIE(QQMusicBaseIE):
IE_NAME = 'qqmusic:mv'
IE_DESC = 'QQ音乐 - MV'
_VALID_URL = r'https?://y\.qq\.com/n/ryqq/mv/(?P<id>[0-9A-Za-z]+)'
_TESTS = [{
'url': 'https://y.qq.com/n/ryqq/mv/002Vsarh3SVU8K',
'info_dict': {
'id': '002Vsarh3SVU8K',
'ext': 'mp4',
'title': 'The Chant (Extended Mix / Audio)',
'description': '',
'thumbnail': r're:^https?://.*\.jpg(?:$|[#?])',
'release_timestamp': 1688918400,
'release_date': '20230709',
'duration': 313,
'creators': ['Duke Dumont'],
'view_count': int,
},
}]
def _parse_url_formats(self, url_data):
return traverse_obj(url_data, ('mp4', lambda _, v: v['freeflow_url'], {
'url': ('freeflow_url', 0, {url_or_none}),
'filesize': ('fileSize', {int_or_none}),
'format_id': ('newFileType', {str_or_none}),
}))
def _real_extract(self, url):
video_id = self._match_id(url)
video_info = self._make_fcu_req({
'mvInfo': {
'module': 'music.video.VideoData',
'method': 'get_video_info_batch',
'param': {
'vidlist': [video_id],
'required': [
'vid', 'type', 'sid', 'cover_pic', 'duration', 'singers',
'video_pay', 'hint', 'code', 'msg', 'name', 'desc',
'playcnt', 'pubdate', 'play_forbid_reason'],
},
},
'mvUrl': {
'module': 'music.stream.MvUrlProxy',
'method': 'GetMvUrls',
'param': {'vids': [video_id]},
},
}, video_id, headers=self.geo_verification_headers())
if traverse_obj(video_info, ('mvInfo', 'data', video_id, 'play_forbid_reason')) == 3:
self.raise_geo_restricted()
return {
'id': video_id,
'formats': self._parse_url_formats(traverse_obj(video_info, ('mvUrl', 'data', video_id))),
**traverse_obj(video_info, ('mvInfo', 'data', video_id, {
'title': ('name', {str}),
'description': ('desc', {str}),
'thumbnail': ('cover_pic', {url_or_none}),
'release_timestamp': ('pubdate', {int_or_none}),
'duration': ('duration', {int_or_none}),
'creators': ('singers', ..., 'name', {str}),
'view_count': ('playcnt', {int_or_none}),
})),
}

198
yt_dlp/extractor/sproutvideo.py Normal file
View File

@@ -0,0 +1,198 @@
import base64
import urllib.parse
from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
int_or_none,
qualities,
remove_start,
smuggle_url,
unsmuggle_url,
update_url_query,
url_or_none,
urlencode_postdata,
)
from ..utils.traversal import traverse_obj
class SproutVideoIE(InfoExtractor):
_NO_SCHEME_RE = r'//videos\.sproutvideo\.com/embed/(?P<id>[\da-f]+)/[\da-f]+'
_VALID_URL = rf'https?:{_NO_SCHEME_RE}'
_EMBED_REGEX = [rf'<iframe [^>]*\bsrc=["\'](?P<url>(?:https?:)?{_NO_SCHEME_RE}[^"\']*)["\']']
_TESTS = [{
'url': 'https://videos.sproutvideo.com/embed/4c9dddb01910e3c9c4/0fc24387c4f24ee3',
'md5': '1343ce1a6cb39d67889bfa07c7b02b0e',
'info_dict': {
'id': '4c9dddb01910e3c9c4',
'ext': 'mp4',
'title': 'Adrien Labaeye : Berlin, des communautés aux communs',
'duration': 576,
'thumbnail': r're:https?://images\.sproutvideo\.com/.+\.jpg',
},
}, {
'url': 'https://videos.sproutvideo.com/embed/a79fdcb21f1be2c62e/93bf31e41e39ca27',
'md5': 'cebae5cf558cca83271917cf4ec03f26',
'info_dict': {
'id': 'a79fdcb21f1be2c62e',
'ext': 'mp4',
'title': 'HS_01_Live Stream 2023-01-14 10:00',
'duration': 703,
'thumbnail': r're:https?://images\.sproutvideo\.com/.+\.jpg',
},
}, {
# http formats 'sd' and 'hd' are available
'url': 'https://videos.sproutvideo.com/embed/119cd6bc1a18e6cd98/30751a1761ae5b90',
'md5': 'f368c78df07e78a749508b221528672c',
'info_dict': {
'id': '119cd6bc1a18e6cd98',
'ext': 'mp4',
'title': '3. Updating your Partner details',
'thumbnail': r're:https?://images\.sproutvideo\.com/.+\.jpg',
'duration': 60,
},
'params': {'format': 'hd'},
}, {
# subtitles
'url': 'https://videos.sproutvideo.com/embed/119dd8ba121ee0cc98/4ee50c88a343215d?type=hd',
'md5': '7f6798f037d7a3e3e07e67959de68fc6',
'info_dict': {
'id': '119dd8ba121ee0cc98',
'ext': 'mp4',
'title': 'Recipients Setup - Domestic Wire Only',
'thumbnail': r're:https?://images\.sproutvideo\.com/.+\.jpg',
'duration': 77,
'subtitles': {'en': 'count:1'},
},
}]
_WEBPAGE_TESTS = [{
'url': 'https://www.solidarum.org/vivre-ensemble/adrien-labaeye-berlin-des-communautes-aux-communs',
'info_dict': {
'id': '4c9dddb01910e3c9c4',
'ext': 'mp4',
'title': 'Adrien Labaeye : Berlin, des communautés aux communs',
'duration': 576,
'thumbnail': r're:https?://images\.sproutvideo\.com/.+\.jpg',
},
}]
_M3U8_URL_TMPL = 'https://{base}.videos.sproutvideo.com/{s3_user_hash}/{s3_video_hash}/video/index.m3u8'
_QUALITIES = ('hd', 'uhd', 'source') # Exclude 'sd' to prioritize hls formats above it
@staticmethod
def _policy_to_qs(policy, signature_key, as_string=False):
query = {}
for key, value in policy['signatures'][signature_key].items():
query[remove_start(key, 'CloudFront-')] = value
query['sessionID'] = policy['sessionID']
return urllib.parse.urlencode(query, doseq=True) if as_string else query
@classmethod
def _extract_embed_urls(cls, url, webpage):
for embed_url in super()._extract_embed_urls(url, webpage):
if embed_url.startswith('//'):
embed_url = f'https:{embed_url}'
yield smuggle_url(embed_url, {'referer': url})
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
video_id = self._match_id(url)
webpage = self._download_webpage(
url, video_id, headers=traverse_obj(smuggled_data, {'Referer': 'referer'}))
data = self._search_json(
r'var\s+dat\s*=\s*["\']', webpage, 'data', video_id, contains_pattern=r'[A-Za-z0-9+/=]+',
end_pattern=r'["\'];', transform_source=lambda x: base64.b64decode(x).decode())
formats, subtitles = [], {}
headers = {
'Accept': '*/*',
'Origin': 'https://videos.sproutvideo.com',
'Referer': url,
}
# HLS extraction is fatal; only attempt it if the JSON data says it's available
if traverse_obj(data, 'hls'):
manifest_query = self._policy_to_qs(data, 'm')
fragment_query = self._policy_to_qs(data, 't', as_string=True)
key_query = self._policy_to_qs(data, 'k', as_string=True)
formats.extend(self._extract_m3u8_formats(
self._M3U8_URL_TMPL.format(**data), video_id, 'mp4',
m3u8_id='hls', headers=headers, query=manifest_query))
for fmt in formats:
fmt.update({
'url': update_url_query(fmt['url'], manifest_query),
'extra_param_to_segment_url': fragment_query,
'extra_param_to_key_url': key_query,
})
if downloads := traverse_obj(data, ('downloads', {dict.items}, lambda _, v: url_or_none(v[1]))):
quality = qualities(self._QUALITIES)
acodec = 'none' if data.get('has_audio') is False else None
formats.extend([{
'format_id': str(format_id),
'url': format_url,
'ext': 'mp4',
'quality': quality(format_id),
'acodec': acodec,
} for format_id, format_url in downloads])
for sub_data in traverse_obj(data, ('subtitleData', lambda _, v: url_or_none(v['src']))):
subtitles.setdefault(sub_data.get('srclang', 'en'), []).append({
'url': sub_data['src'],
})
return {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
'http_headers': headers,
**traverse_obj(data, {
'title': ('title', {str}),
'duration': ('duration', {int_or_none}),
'thumbnail': ('posterframe_url', {url_or_none}),
}),
}
class VidsIoIE(InfoExtractor):
IE_NAME = 'vids.io'
_VALID_URL = r'https?://[\w-]+\.vids\.io/videos/(?P<id>[\da-f]+)/(?P<display_id>[\w-]+)'
_TESTS = [{
'url': 'https://how-to-video.vids.io/videos/799cd8b11c10efc1f0/how-to-video-live-streaming',
'md5': '9bbbb2c0c0739eb163b80f87b8d77c9e',
'info_dict': {
'id': '799cd8b11c10efc1f0',
'ext': 'mp4',
'title': 'How to Video: Live Streaming',
'duration': 2787,
'thumbnail': r're:https?://images\.sproutvideo\.com/.+\.jpg',
},
}]
def _real_extract(self, url):
video_id, display_id = self._match_valid_url(url).group('id', 'display_id')
webpage, urlh = self._download_webpage_handle(url, display_id, expected_status=403)
if urlh.status == 403:
password = self.get_param('videopassword')
if not password:
raise ExtractorError(
'This video is password-protected; use the --video-password option', expected=True)
try:
webpage = self._download_webpage(
url, display_id, 'Submitting video password',
data=urlencode_postdata({
'password': password,
**self._hidden_inputs(webpage),
}))
# Requests with user's session cookie `_sproutvideo_session` are now authorized
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 403:
raise ExtractorError('Incorrect password', expected=True)
raise
if embed_url := next(SproutVideoIE._extract_embed_urls(url, webpage), None):
return self.url_result(embed_url, SproutVideoIE, video_id)
raise ExtractorError('Unable to extract any SproutVideo embed url')

64
yt_dlp/extractor/swearnet.py
View File

@@ -1,55 +1,31 @@
from .common import InfoExtractor
from ..utils import ExtractorError, int_or_none, traverse_obj
from .vidyard import VidyardBaseIE
from ..utils import ExtractorError, int_or_none, make_archive_id
class SwearnetEpisodeIE(InfoExtractor):
class SwearnetEpisodeIE(VidyardBaseIE):
_VALID_URL = r'https?://www\.swearnet\.com/shows/(?P<id>[\w-]+)/seasons/(?P<season_num>\d+)/episodes/(?P<episode_num>\d+)'
_TESTS = [{
'url': 'https://www.swearnet.com/shows/gettin-learnt-with-ricky/seasons/1/episodes/1',
'info_dict': {
'id': '232819',
'id': 'wicK2EOzjOdxkUXGDIgcPw',
'display_id': '232819',
'ext': 'mp4',
'episode_number': 1,
'episode': 'Episode 1',
'duration': 719,
'description': 'md5:c48ef71440ce466284c07085cd7bd761',
'description': r're:Are you drunk and high and craving a grilled cheese sandwich.+',
'season': 'Season 1',
'title': 'Episode 1 - Grilled Cheese Sammich',
'season_number': 1,
'thumbnail': 'https://cdn.vidyard.com/thumbnails/232819/_RX04IKIq60a2V6rIRqq_Q_small.jpg',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/custom/0dd74f9b-388a-452e-b570-b407fb64435b_small.jpg',
'tags': ['Getting Learnt with Ricky', 'drunk', 'grilled cheese', 'high'],
'_old_archive_ids': ['swearnetepisode 232819'],
},
}]
def _get_formats_and_subtitle(self, video_source, video_id):
video_source = video_source or {}
formats, subtitles = [], {}
for key, value in video_source.items():
if key == 'hls':
for video_hls in value:
fmts, subs = self._extract_m3u8_formats_and_subtitles(video_hls.get('url'), video_id)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
else:
formats.extend({
'url': video_mp4.get('url'),
'ext': 'mp4',
} for video_mp4 in value)
return formats, subtitles
def _get_direct_subtitle(self, caption_json):
subs = {}
for caption in caption_json:
subs.setdefault(caption.get('language') or 'und', []).append({
'url': caption.get('vttUrl'),
'name': caption.get('name'),
})
return subs
def _real_extract(self, url):
display_id, season_number, episode_number = self._match_valid_url(url).group('id', 'season_num', 'episode_num')
webpage = self._download_webpage(url, display_id)
slug, season_number, episode_number = self._match_valid_url(url).group('id', 'season_num', 'episode_num')
webpage = self._download_webpage(url, slug)
try:
external_id = self._search_regex(r'externalid\s*=\s*"([^"]+)', webpage, 'externalid')
@@ -58,22 +34,12 @@ class SwearnetEpisodeIE(InfoExtractor):
self.raise_login_required()
raise
json_data = self._download_json(
f'https://play.vidyard.com/player/{external_id}.json', display_id)['payload']['chapters'][0]
formats, subtitles = self._get_formats_and_subtitle(json_data['sources'], display_id)
self._merge_subtitles(self._get_direct_subtitle(json_data.get('captions')), target=subtitles)
info = self._process_video_json(self._fetch_video_json(external_id)['chapters'][0], external_id)
if info.get('display_id'):
info['_old_archive_ids'] = [make_archive_id(self, info['display_id'])]
return {
'id': str(json_data['videoId']),
'title': json_data.get('name') or self._html_search_meta(['og:title', 'twitter:title'], webpage),
'description': (json_data.get('description')
or self._html_search_meta(['og:description', 'twitter:description'], webpage)),
'duration': int_or_none(json_data.get('seconds')),
'formats': formats,
'subtitles': subtitles,
**info,
'season_number': int_or_none(season_number),
'episode_number': int_or_none(episode_number),
'thumbnails': [{'url': thumbnail_url}
for thumbnail_url in traverse_obj(json_data, ('thumbnailUrls', ...))],
}

32
yt_dlp/extractor/tiktok.py
View File

@@ -30,6 +30,7 @@ from ..utils import (
try_call,
try_get,
url_or_none,
urlencode_postdata,
)
@@ -43,8 +44,8 @@ class TikTokBaseIE(InfoExtractor):
'iid': None,
# TikTok (KR/PH/TW/TH/VN) = trill, TikTok (rest of world) = musical_ly, Douyin = aweme
'app_name': 'musical_ly',
'app_version': '34.1.2',
'manifest_app_version': '2023401020',
'app_version': '35.1.3',
'manifest_app_version': '2023501030',
# "app id": aweme = 1128, trill = 1180, musical_ly = 1233, universal = 0
'aid': '0',
}
@@ -114,7 +115,7 @@ class TikTokBaseIE(InfoExtractor):
'universal data', display_id, end_pattern=r'</script>', default={}),
('__DEFAULT_SCOPE__', {dict})) or {}
def _call_api_impl(self, ep, query, video_id, fatal=True,
def _call_api_impl(self, ep, video_id, query=None, data=None, headers=None, fatal=True,
note='Downloading API JSON', errnote='Unable to download API page'):
self._set_cookie(self._API_HOSTNAME, 'odin_tt', ''.join(random.choices('0123456789abcdef', k=160)))
webpage_cookies = self._get_cookies(self._WEBPAGE_HOST)
@@ -125,7 +126,8 @@ class TikTokBaseIE(InfoExtractor):
fatal=fatal, note=note, errnote=errnote, headers={
'User-Agent': self._APP_USER_AGENT,
'Accept': 'application/json',
}, query=query)
**(headers or {}),
}, query=query, data=data)
def _build_api_query(self, query):
return filter_dict({
@@ -174,7 +176,7 @@ class TikTokBaseIE(InfoExtractor):
'openudid': ''.join(random.choices('0123456789abcdef', k=16)),
})
def _call_api(self, ep, query, video_id, fatal=True,
def _call_api(self, ep, video_id, query=None, data=None, headers=None, fatal=True,
note='Downloading API JSON', errnote='Unable to download API page'):
if not self._APP_INFO and not self._get_next_app_info():
message = 'No working app info is available'
@@ -187,9 +189,11 @@ class TikTokBaseIE(InfoExtractor):
max_tries = len(self._APP_INFO_POOL) + 1 # _APP_INFO_POOL + _APP_INFO
for count in itertools.count(1):
self.write_debug(str(self._APP_INFO))
real_query = self._build_api_query(query)
real_query = self._build_api_query(query or {})
try:
return self._call_api_impl(ep, real_query, video_id, fatal, note, errnote)
return self._call_api_impl(
ep, video_id, query=real_query, data=data, headers=headers,
fatal=fatal, note=note, errnote=errnote)
except ExtractorError as e:
if isinstance(e.cause, json.JSONDecodeError) and e.cause.pos == 0:
message = str(e.cause or e.msg)
@@ -204,12 +208,13 @@ class TikTokBaseIE(InfoExtractor):
raise
def _extract_aweme_app(self, aweme_id):
feed_list = self._call_api(
'feed', {'aweme_id': aweme_id}, aweme_id, note='Downloading video feed',
errnote='Unable to download video feed').get('aweme_list') or []
aweme_detail = next((aweme for aweme in feed_list if str(aweme.get('aweme_id')) == aweme_id), None)
aweme_detail = traverse_obj(
self._call_api('multi/aweme/detail', aweme_id, data=urlencode_postdata({
'aweme_ids': f'[{aweme_id}]',
'request_source': '0',
}), headers={'X-Argus': ''}), ('aweme_details', 0, {dict}))
if not aweme_detail:
raise ExtractorError('Unable to find video in feed', video_id=aweme_id)
raise ExtractorError('Unable to extract aweme detail info', video_id=aweme_id)
return self._parse_aweme_video_app(aweme_detail)
def _extract_web_data_and_status(self, url, video_id, fatal=True):
@@ -1037,7 +1042,8 @@ class TikTokBaseListIE(TikTokBaseIE): # XXX: Conventionally, base classes shoul
for retry in self.RetryManager():
try:
post_list = self._call_api(
self._API_ENDPOINT, query, display_id, note=f'Downloading video list page {page}',
self._API_ENDPOINT, display_id, query=query,
note=f'Downloading video list page {page}',
errnote='Unable to download video list')
except ExtractorError as e:
if isinstance(e.cause, json.JSONDecodeError) and e.cause.pos == 0:

28
yt_dlp/extractor/toggle.py
View File

@@ -28,35 +28,11 @@ class ToggleIE(InfoExtractor):
'skip_download': 'm3u8 download',
},
}, {
'note': 'DRM-protected video',
'url': 'http://www.mewatch.sg/en/movies/dug-s-special-mission/341413',
'info_dict': {
'id': '341413',
'ext': 'wvm',
'title': 'Dug\'s Special Mission',
'description': 'md5:e86c6f4458214905c1772398fabc93e0',
'upload_date': '20150827',
'timestamp': 1440644006,
},
'params': {
'skip_download': 'DRM-protected wvm download',
},
'only_matching': True,
}, {
# this also tests correct video id extraction
'note': 'm3u8 links are geo-restricted, but Android/mp4 is okay',
'url': 'http://www.mewatch.sg/en/series/28th-sea-games-5-show/28th-sea-games-5-show-ep11/332861',
'info_dict': {
'id': '332861',
'ext': 'mp4',
'title': '28th SEA Games (5 Show) - Episode 11',
'description': 'md5:3cd4f5f56c7c3b1340c50a863f896faa',
'upload_date': '20150605',
'timestamp': 1433480166,
},
'params': {
'skip_download': 'DRM-protected wvm download',
},
'skip': 'm3u8 links are geo-restricted',
'only_matching': True,
}, {
'url': 'http://video.toggle.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331',
'only_matching': True,

10
yt_dlp/extractor/tubetugraz.py
View File

@@ -21,7 +21,7 @@ class TubeTuGrazBaseIE(InfoExtractor):
if not urlh:
return
content, urlh = self._download_webpage_handle(
response = self._download_webpage_handle(
urlh.url, None, fatal=False, headers={'referer': urlh.url},
note='logging in', errnote='unable to log in',
data=urlencode_postdata({
@@ -30,7 +30,11 @@ class TubeTuGrazBaseIE(InfoExtractor):
'j_username': username,
'j_password': password,
}))
if not urlh or urlh.url == 'https://tube.tugraz.at/paella/ui/index.html':
if not response:
return
content, urlh = response
if urlh.url == 'https://tube.tugraz.at/paella/ui/index.html':
return
if not self._html_search_regex(
@@ -39,7 +43,7 @@ class TubeTuGrazBaseIE(InfoExtractor):
self.report_warning('unable to login: incorrect password')
return
content, urlh = self._download_webpage_handle(
urlh = self._request_webpage(
urlh.url, None, fatal=False, headers={'referer': urlh.url},
note='logging in with TFA', errnote='unable to log in with TFA',
data=urlencode_postdata({

3
yt_dlp/extractor/twitter.py
View File

@@ -14,6 +14,7 @@ from ..utils import (
float_or_none,
format_field,
int_or_none,
join_nonempty,
make_archive_id,
remove_end,
str_or_none,
@@ -107,7 +108,7 @@ class TwitterBaseIE(InfoExtractor):
tbr = int_or_none(dict_get(variant, ('bitrate', 'bit_rate')), 1000) or None
f = {
'url': variant_url,
'format_id': 'http' + (f'-{tbr}' if tbr else ''),
'format_id': join_nonempty('http', tbr),
'tbr': tbr,
}
self._search_dimensions_in_video_url(f, variant_url)

426
yt_dlp/extractor/vidyard.py Normal file
View File

@@ -0,0 +1,426 @@
import functools
import re
from .common import InfoExtractor
from ..utils import (
extract_attributes,
float_or_none,
int_or_none,
join_nonempty,
mimetype2ext,
parse_resolution,
str_or_none,
unescapeHTML,
url_or_none,
)
from ..utils.traversal import traverse_obj
class VidyardBaseIE(InfoExtractor):
_HEADERS = {'Referer': 'https://play.vidyard.com/'}
def _get_formats_and_subtitles(self, sources, video_id):
formats, subtitles = [], {}
def add_hls_fmts_and_subs(m3u8_url):
fmts, subs = self._extract_m3u8_formats_and_subtitles(
m3u8_url, video_id, 'mp4', m3u8_id='hls', headers=self._HEADERS, fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
hls_list = isinstance(sources, dict) and sources.pop('hls', None)
if master_m3u8_url := traverse_obj(
hls_list, (lambda _, v: v['profile'] == 'auto', 'url', {url_or_none}, any)):
add_hls_fmts_and_subs(master_m3u8_url)
if not formats: # These are duplicate and unnecesary requests if we got 'auto' hls fmts
for variant_m3u8_url in traverse_obj(hls_list, (..., 'url', {url_or_none})):
add_hls_fmts_and_subs(variant_m3u8_url)
for source_type, source_list in traverse_obj(sources, ({dict.items}, ...)):
for source in traverse_obj(source_list, lambda _, v: url_or_none(v['url'])):
profile = source.get('profile')
formats.append({
'url': source['url'],
'ext': mimetype2ext(source.get('mimeType'), default=None),
'format_id': join_nonempty('http', source_type, profile),
**parse_resolution(profile),
})
self._remove_duplicate_formats(formats)
return formats, subtitles
def _get_direct_subtitles(self, caption_json):
subs = {}
for caption in traverse_obj(caption_json, lambda _, v: url_or_none(v['vttUrl'])):
subs.setdefault(caption.get('language') or 'und', []).append({
'url': caption['vttUrl'],
'name': caption.get('name'),
})
return subs
def _fetch_video_json(self, video_id):
return self._download_json(
f'https://play.vidyard.com/player/{video_id}.json', video_id)['payload']
def _process_video_json(self, json_data, video_id):
formats, subtitles = self._get_formats_and_subtitles(json_data['sources'], video_id)
self._merge_subtitles(self._get_direct_subtitles(json_data.get('captions')), target=subtitles)
return {
**traverse_obj(json_data, {
'id': ('facadeUuid', {str}),
'display_id': ('videoId', {int}, {str_or_none}),
'title': ('name', {str}),
'description': ('description', {str}, {unescapeHTML}, {lambda x: x or None}),
'duration': ((
('milliseconds', {functools.partial(float_or_none, scale=1000)}),
('seconds', {int_or_none})), any),
'thumbnails': ('thumbnailUrls', ('small', 'normal'), {'url': {url_or_none}}),
'tags': ('tags', ..., 'name', {str}),
}),
'formats': formats,
'subtitles': subtitles,
'http_headers': self._HEADERS,
}
class VidyardIE(VidyardBaseIE):
_VALID_URL = [
r'https?://[\w-]+(?:\.hubs)?\.vidyard\.com/watch/(?P<id>[\w-]+)',
r'https?://(?:embed|share)\.vidyard\.com/share/(?P<id>[\w-]+)',
r'https?://play\.vidyard\.com/(?:player/)?(?P<id>[\w-]+)',
]
_EMBED_REGEX = [r'<iframe[^>]* src=["\'](?P<url>(?:https?:)?//play\.vidyard\.com/[\w-]+)']
_TESTS = [{
'url': 'https://vyexample03.hubs.vidyard.com/watch/oTDMPlUv--51Th455G5u7Q',
'info_dict': {
'id': 'oTDMPlUv--51Th455G5u7Q',
'display_id': '50347',
'ext': 'mp4',
'title': 'Homepage Video',
'description': 'Look I changed the description.',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/50347/OUPa5LTKV46849sLYngMqQ_small.jpg',
'duration': 99,
'tags': ['these', 'are', 'all', 'tags'],
},
}, {
'url': 'https://share.vidyard.com/watch/PaQzDAT1h8JqB8ivEu2j6Y?',
'info_dict': {
'id': 'PaQzDAT1h8JqB8ivEu2j6Y',
'display_id': '9281024',
'ext': 'mp4',
'title': 'Inline Embed',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/spacer.gif',
'duration': 41.186,
},
}, {
'url': 'https://embed.vidyard.com/share/oTDMPlUv--51Th455G5u7Q',
'info_dict': {
'id': 'oTDMPlUv--51Th455G5u7Q',
'display_id': '50347',
'ext': 'mp4',
'title': 'Homepage Video',
'description': 'Look I changed the description.',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/50347/OUPa5LTKV46849sLYngMqQ_small.jpg',
'duration': 99,
'tags': ['these', 'are', 'all', 'tags'],
},
}, {
# First video from playlist below
'url': 'https://embed.vidyard.com/share/SyStyHtYujcBHe5PkZc5DL',
'info_dict': {
'id': 'SyStyHtYujcBHe5PkZc5DL',
'display_id': '41974005',
'ext': 'mp4',
'title': 'Prepare the Frame and Track for Palm Beach Polysatin Shutters With BiFold Track',
'description': r're:In this video, you will learn how to prepare the frame.+',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/41974005/IJw7oCaJcF1h7WWu3OVZ8A_small.png',
'duration': 258.666,
},
}, {
# Playlist
'url': 'https://thelink.hubs.vidyard.com/watch/pwu7pCYWSwAnPxs8nDoFrE',
'info_dict': {
'id': 'pwu7pCYWSwAnPxs8nDoFrE',
'title': 'PLAYLIST - Palm Beach Shutters- Bi-Fold Track System Installation',
'entries': [{
'id': 'SyStyHtYujcBHe5PkZc5DL',
'display_id': '41974005',
'ext': 'mp4',
'title': 'Prepare the Frame and Track for Palm Beach Polysatin Shutters With BiFold Track',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/41974005/IJw7oCaJcF1h7WWu3OVZ8A_small.png',
'duration': 258.666,
}, {
'id': '1Fw4B84jZTXLXWqkE71RiM',
'display_id': '5861113',
'ext': 'mp4',
'title': 'Palm Beach - Bi-Fold Track System "Frame Installation"',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/5861113/29CJ54s5g1_aP38zkKLHew_small.jpg',
'duration': 167.858,
}, {
'id': 'DqP3wBvLXSpxrcqpT5kEeo',
'display_id': '41976334',
'ext': 'mp4',
'title': 'Install the Track for Palm Beach Polysatin Shutters With BiFold Track',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/5861090/RwG2VaTylUa6KhSTED1r1Q_small.png',
'duration': 94.229,
}, {
'id': 'opfybfxpzQArxqtQYB6oBU',
'display_id': '41976364',
'ext': 'mp4',
'title': 'Install the Panel for Palm Beach Polysatin Shutters With BiFold Track',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/5860926/JIOaJR08dM4QgXi_iQ2zGA_small.png',
'duration': 191.467,
}, {
'id': 'rWrXvkbTNNaNqD6189HJya',
'display_id': '41976382',
'ext': 'mp4',
'title': 'Adjust the Panels for Palm Beach Polysatin Shutters With BiFold Track',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/5860687/CwHxBv4UudAhOh43FVB4tw_small.png',
'duration': 138.155,
}, {
'id': 'eYPTB521MZ9TPEArSethQ5',
'display_id': '41976409',
'ext': 'mp4',
'title': 'Assemble and Install the Valance for Palm Beach Polysatin Shutters With BiFold Track',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/5861425/0y68qlMU4O5VKU7bJ8i_AA_small.png',
'duration': 148.224,
}],
},
'playlist_count': 6,
}, {
# Non hubs.vidyard.com playlist
'url': 'https://salesforce.vidyard.com/watch/d4vqPjs7Q5EzVEis5QT3jd',
'info_dict': {
'id': 'd4vqPjs7Q5EzVEis5QT3jd',
'title': 'How To: Service Cloud: Import External Content in Lightning Knowledge',
'entries': [{
'id': 'mcjDpSZir2iSttbvFkx6Rv',
'display_id': '29479036',
'ext': 'mp4',
'title': 'Welcome to this Expert Coaching Series',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/ouyQi9WuwyiOupChUWNmjQ/7170d3485ba602e012df05_small.jpg',
'duration': 38.205,
}, {
'id': '84bPYwpg243G6xYEfJdYw9',
'display_id': '21820704',
'ext': 'mp4',
'title': 'Chapter 1 - Title + Agenda',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/HFPN0ZgQq4Ow8BghGcQSow/bfaa30123c8f6601e7d7f2_small.jpg',
'duration': 98.016,
}, {
'id': 'nP17fMuvA66buVHUrzqjTi',
'display_id': '21820707',
'ext': 'mp4',
'title': 'Chapter 2 - Import Options',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/rGRIF5nFjPI9OOA2qJ_Dbg/86a8d02bfec9a566845dd4_small.jpg',
'duration': 199.136,
}, {
'id': 'm54EcwXdpA5gDBH5rgCYoV',
'display_id': '21820710',
'ext': 'mp4',
'title': 'Chapter 3 - Importing Article Translations',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/IVX4XR8zpSsiNIHx45kz-A/1ccbf8a29a33856d06b3ed_small.jpg',
'duration': 184.352,
}, {
'id': 'j4nzS42oq4hE9oRV73w3eQ',
'display_id': '21820716',
'ext': 'mp4',
'title': 'Chapter 4 - Best Practices',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/BtrRrQpRDLbA4AT95YQyog/1f1e6b8e7fdc3fa95ec8d3_small.jpg',
'duration': 296.960,
}, {
'id': 'y28PYfW5pftvers9PXzisC',
'display_id': '21820727',
'ext': 'mp4',
'title': 'Chapter 5 - Migration Steps',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/K2CdQOXDfLcrVTF60r0bdw/a09239ada28b6ffce12b1f_small.jpg',
'duration': 620.640,
}, {
'id': 'YWU1eQxYvhj29SjYoPw5jH',
'display_id': '21820733',
'ext': 'mp4',
'title': 'Chapter 6 - Demo',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/rsmhP-cO8dAa8ilvFGCX0g/7911ef415167cd14032068_small.jpg',
'duration': 631.456,
}, {
'id': 'nmEvVqpwdJUgb74zKsLGxn',
'display_id': '29479037',
'ext': 'mp4',
'title': 'Schedule Your Follow-Up',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/Rtwc7X4PEkF4Ae5kHi-Jvw/174ebed3f34227b1ffa1d0_small.jpg',
'duration': 33.608,
}],
},
'playlist_count': 8,
}, {
# URL of iframe embed src
'url': 'https://play.vidyard.com/iDqTwWGrd36vaLuaCY3nTs.html',
'info_dict': {
'id': 'iDqTwWGrd36vaLuaCY3nTs',
'display_id': '9281009',
'ext': 'mp4',
'title': 'Lightbox Embed',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/spacer.gif',
'duration': 39.035,
},
}, {
# Player JSON URL
'url': 'https://play.vidyard.com/player/7GAApnNNbcZZ46k6JqJQSh.json?disable_analytics=0',
'info_dict': {
'id': '7GAApnNNbcZZ46k6JqJQSh',
'display_id': '820026',
'ext': 'mp4',
'title': 'The Art of Storytelling: How to Deliver Your Brand Story with Content & Social',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/MhbE-5sEFQu4x3fI6FkNlA/41eb5717c557cd19456910_small.jpg',
'duration': 2153.013,
'tags': ['Summit2017'],
},
}, {
'url': 'http://share.vidyard.com/share/diYeo6YR2yiGgL8odvS8Ri',
'only_matching': True,
}, {
'url': 'https://play.vidyard.com/FFlz3ZpxhIfKQ1fd9DAryA',
'only_matching': True,
}, {
'url': 'https://play.vidyard.com/qhMAu5A76GZVrFzOPgSf9A/type/standalone',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
# URL containing inline/lightbox embedded video
'url': 'https://resources.altium.com/p/2-the-extreme-importance-of-pc-board-stack-up',
'info_dict': {
'id': 'GDx1oXrFWj4XHbipfoXaMn',
'display_id': '3225198',
'ext': 'mp4',
'title': 'The Extreme Importance of PC Board Stack Up',
'thumbnail': 'https://cdn.vidyard.com/thumbnails/73_Q3_hBexWX7Og1sae6cg/9998fa4faec921439e2c04_small.jpg',
'duration': 3422.742,
},
}, {
# <script ... id="vidyard_embed_code_DXx2sW4WaLA6hTdGFz7ja8" src="//play.vidyard.com/DXx2sW4WaLA6hTdGFz7ja8.js?
'url': 'http://videos.vivint.com/watch/DXx2sW4WaLA6hTdGFz7ja8',
'info_dict': {
'id': 'DXx2sW4WaLA6hTdGFz7ja8',
'display_id': '2746529',
'ext': 'mp4',
'title': 'How To Powercycle the Smart Hub Panel',
'duration': 30.613,
'thumbnail': 'https://cdn.vidyard.com/thumbnails/_-6cw8xQUJ3qiCs_JENc_A/b21d7a5e47967f49399d30_small.jpg',
},
}, {
# <script id="vidyard_embed_code_MIBHhiLVTxga7wqLsuoDjQ" src="//embed.vidyard.com/embed/MIBHhiLVTxga7wqLsuoDjQ/inline?v=2.1">
'url': 'https://www.babypips.com/learn/forex/introduction-to-metatrader4',
'info_dict': {
'id': 'MIBHhiLVTxga7wqLsuoDjQ',
'display_id': '20291',
'ext': 'mp4',
'title': 'Lesson 1 - Opening an MT4 Account',
'description': 'Never heard of MetaTrader4? Here\'s the 411 on the popular trading platform!',
'duration': 168,
'thumbnail': 'https://cdn.vidyard.com/thumbnails/20291/IM-G2WXQR9VBLl2Cmzvftg_small.jpg',
},
}, {
# <iframe ... src="//play.vidyard.com/d61w8EQoZv1LDuPxDkQP2Q/type/background?preview=1"
'url': 'https://www.avaya.com/en/',
'info_dict': {
# These values come from the generic extractor and don't matter
'id': str,
'title': str,
'age_limit': 0,
'upload_date': str,
'description': str,
'thumbnail': str,
'timestamp': float,
},
'playlist': [{
'info_dict': {
'id': 'd61w8EQoZv1LDuPxDkQP2Q',
'display_id': '42456529',
'ext': 'mp4',
'title': 'GettyImages-1027',
'duration': 6.0,
'thumbnail': 'https://cdn.vidyard.com/thumbnails/42061563/p6bY08d2N4e4IDz-7J4_wkgsPq3-qgcx_small.jpg',
},
}, {
'info_dict': {
'id': 'VAsYDi7eiqZRbHodUA2meC',
'display_id': '42456569',
'ext': 'mp4',
'title': 'GettyImages-1325598833',
'duration': 6.083,
'thumbnail': 'https://cdn.vidyard.com/thumbnails/42052358/y3qrbDpn_2quWr_5XBi7yzS3UvEI__ZM_small.jpg',
},
}],
'playlist_count': 2,
}, {
# <div class="vidyard-player-embed" data-uuid="vpCWTVHw3qrciLtVY94YkS"
'url': 'https://www.gogoair.com/',
'info_dict': {
# These values come from the generic extractor and don't matter
'id': str,
'title': str,
'description': str,
'age_limit': 0,
},
'playlist': [{
'info_dict': {
'id': 'vpCWTVHw3qrciLtVY94YkS',
'display_id': '40780699',
'ext': 'mp4',
'title': 'Upgrade to AVANCE 100% worth it - Jason Talley, Owner and Pilot, Testimonial',
'description': 'md5:f609824839439a51990cef55ffc472aa',
'duration': 70.737,
'thumbnail': 'https://cdn.vidyard.com/thumbnails/40780699/KzjfYZz5MZl2gHF_e-4i2c6ib1cLDweQ_small.jpg',
},
}, {
'info_dict': {
'id': 'xAmV9AsLbnitCw35paLBD8',
'display_id': '31130867',
'ext': 'mp4',
'title': 'Brad Keselowski goes faster with Gogo AVANCE inflight Wi-Fi',
'duration': 132.565,
'thumbnail': 'https://cdn.vidyard.com/thumbnails/31130867/HknyDtLdm2Eih9JZ4A5XLjhfBX_6HRw5_small.jpg',
},
}, {
'info_dict': {
'id': 'RkkrFRNxfP79nwCQavecpF',
'display_id': '39009815',
'ext': 'mp4',
'title': 'Live Demo of Gogo Galileo',
'description': 'md5:e2df497236f4e12c3fef8b392b5f23e0',
'duration': 112.128,
'thumbnail': 'https://cdn.vidyard.com/thumbnails/38144873/CWLlxfUbJ4Gh0ThbUum89IsEM4yupzMb_small.jpg',
},
}],
'playlist_count': 3,
}]
@classmethod
def _extract_embed_urls(cls, url, webpage):
# Handle protocol-less embed URLs
for embed_url in super()._extract_embed_urls(url, webpage):
if embed_url.startswith('//'):
embed_url = f'https:{embed_url}'
yield embed_url
# Extract inline/lightbox embeds
for embed_element in re.findall(
r'(<(?:img|div)[^>]* class=(["\'])(?:[^>"\']* )?vidyard-player-embed(?: [^>"\']*)?\2[^>]+>)', webpage):
if video_id := extract_attributes(embed_element[0]).get('data-uuid'):
yield f'https://play.vidyard.com/{video_id}'
for embed_id in re.findall(r'<script[^>]* id=["\']vidyard_embed_code_([\w-]+)["\']', webpage):
yield f'https://play.vidyard.com/{embed_id}'
def _real_extract(self, url):
video_id = self._match_id(url)
video_json = self._fetch_video_json(video_id)
if len(video_json['chapters']) == 1:
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']],
str(video_json['playerUuid']), video_json.get('name'))

3
yt_dlp/extractor/viewlift.py
View File

@@ -5,6 +5,7 @@ from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
int_or_none,
join_nonempty,
parse_age_limit,
traverse_obj,
)
@@ -120,7 +121,7 @@ class ViewLiftEmbedIE(ViewLiftBaseIE):
'height', default=None))
formats.append({
'url': video_asset_url,
'format_id': 'http{}'.format(f'-{bitrate}' if bitrate else ''),
'format_id': join_nonempty('http', bitrate),
'tbr': bitrate,
'height': height,
'vcodec': video_asset.get('codec'),

121
yt_dlp/extractor/vimeo.py
View File

@@ -1,6 +1,7 @@
import base64
import functools
import itertools
import json
import re
import urllib.parse
@@ -14,6 +15,7 @@ from ..utils import (
determine_ext,
get_element_by_class,
int_or_none,
join_nonempty,
js_to_json,
merge_dicts,
parse_filesize,
@@ -84,29 +86,23 @@ class VimeoBaseInfoExtractor(InfoExtractor):
expected=True)
return password
def _verify_video_password(self, url, video_id, password, token, vuid):
if url.startswith('http://'):
# vimeo only supports https now, but the user can give an http url
url = url.replace('http://', 'https://')
self._set_vimeo_cookie('vuid', vuid)
return self._download_webpage(
url + '/password', video_id, 'Verifying the password',
'Wrong password', data=urlencode_postdata({
'password': password,
'token': token,
}), headers={
'Content-Type': 'application/x-www-form-urlencoded',
'Referer': url,
})
def _extract_xsrft_and_vuid(self, webpage):
xsrft = self._search_regex(
r'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|xsrft\s*[=:])\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
webpage, 'login token', group='xsrft')
vuid = self._search_regex(
r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
webpage, 'vuid', group='vuid')
return xsrft, vuid
def _verify_video_password(self, video_id, password, token):
url = f'https://vimeo.com/{video_id}'
try:
return self._download_webpage(
f'{url}/password', video_id,
'Submitting video password', data=json.dumps({
'password': password,
'token': token,
}, separators=(',', ':')).encode(), headers={
'Accept': '*/*',
'Content-Type': 'application/json',
'Referer': url,
}, impersonate=True)
except ExtractorError as error:
if isinstance(error.cause, HTTPError) and error.cause.status == 418:
raise ExtractorError('Wrong password', expected=True)
raise
def _extract_vimeo_config(self, webpage, video_id, *args, **kwargs):
vimeo_config = self._search_regex(
@@ -745,21 +741,34 @@ class VimeoIE(VimeoBaseInfoExtractor):
raise ExtractorError('Wrong video password', expected=True)
return checked
def _extract_from_api(self, video_id, unlisted_hash=None):
token = self._download_json(
'https://vimeo.com/_rv/jwt', video_id, headers={
'X-Requested-With': 'XMLHttpRequest',
})['token']
api_url = 'https://api.vimeo.com/videos/' + video_id
if unlisted_hash:
api_url += ':' + unlisted_hash
video = self._download_json(
api_url, video_id, headers={
'Authorization': 'jwt ' + token,
def _call_videos_api(self, video_id, jwt_token, unlisted_hash=None):
return self._download_json(
join_nonempty(f'https://api.vimeo.com/videos/{video_id}', unlisted_hash, delim=':'),
video_id, 'Downloading API JSON', headers={
'Authorization': f'jwt {jwt_token}',
'Accept': 'application/json',
}, query={
'fields': 'config_url,created_time,description,license,metadata.connections.comments.total,metadata.connections.likes.total,release_time,stats.plays',
})
def _extract_from_api(self, video_id, unlisted_hash=None):
viewer = self._download_json(
'https://vimeo.com/_next/viewer', video_id, 'Downloading viewer info')
for retry in (False, True):
try:
video = self._call_videos_api(video_id, viewer['jwt'], unlisted_hash)
except ExtractorError as e:
if (not retry and isinstance(e.cause, HTTPError) and e.cause.status == 400
and 'password' in traverse_obj(
e.cause.response.read(),
({bytes.decode}, {json.loads}, 'invalid_parameters', ..., 'field'),
)):
self._verify_video_password(
video_id, self._get_video_password(), viewer['xsrft'])
continue
raise
info = self._parse_config(self._download_json(
video['config_url'], video_id), video_id)
get_timestamp = lambda x: parse_iso8601(video.get(x + '_time'))
@@ -829,21 +838,33 @@ class VimeoIE(VimeoBaseInfoExtractor):
url = 'https://vimeo.com/' + video_id
self._try_album_password(url)
is_secure = urllib.parse.urlparse(url).scheme == 'https'
try:
# Retrieve video webpage to extract further information
webpage, urlh = self._download_webpage_handle(
url, video_id, headers=headers)
url, video_id, headers=headers, impersonate=is_secure)
redirect_url = urlh.url
except ExtractorError as ee:
if isinstance(ee.cause, HTTPError) and ee.cause.status == 403:
errmsg = ee.cause.response.read()
if b'Because of its privacy settings, this video cannot be played here' in errmsg:
raise ExtractorError(
'Cannot download embed-only video without embedding '
'URL. Please call yt-dlp with the URL of the page '
'that embeds this video.',
expected=True)
raise
except ExtractorError as error:
if not isinstance(error.cause, HTTPError) or error.cause.status not in (403, 429):
raise
errmsg = error.cause.response.read()
if b'Because of its privacy settings, this video cannot be played here' in errmsg:
raise ExtractorError(
'Cannot download embed-only video without embedding URL. Please call yt-dlp '
'with the URL of the page that embeds this video.', expected=True)
# 403 == vimeo.com TLS fingerprint or DC IP block; 429 == player.vimeo.com TLS FP block
status = error.cause.status
dcip_msg = 'If you are using a data center IP or VPN/proxy, your IP may be blocked'
if target := error.cause.response.extensions.get('impersonate'):
raise ExtractorError(
f'Got HTTP Error {status} when using impersonate target "{target}". {dcip_msg}')
elif not is_secure:
raise ExtractorError(f'Got HTTP Error {status}. {dcip_msg}', expected=True)
raise ExtractorError(
'This request has been blocked due to its TLS fingerprint. Install a '
'required impersonation dependency if possible, or else if you are okay with '
f'{self._downloader._format_err("compromising your security/cookies", "light red")}, '
f'try replacing "https:" with "http:" in the input URL. {dcip_msg}.', expected=True)
if '://player.vimeo.com/video/' in url:
config = self._search_json(
@@ -853,12 +874,6 @@ class VimeoIE(VimeoBaseInfoExtractor):
redirect_url, video_id, headers)
return self._parse_config(config, video_id)
if re.search(r'<form[^>]+?id="pw_form"', webpage):
video_password = self._get_video_password()
token, vuid = self._extract_xsrft_and_vuid(webpage)
webpage = self._verify_video_password(
redirect_url, video_id, video_password, token, vuid)
vimeo_config = self._extract_vimeo_config(webpage, video_id, default=None)
if vimeo_config:
seed_status = vimeo_config.get('seed_status') or {}
@@ -1278,9 +1293,7 @@ class VimeoReviewIE(VimeoBaseInfoExtractor):
video_password = self._get_video_password()
viewer = self._download_json(
'https://vimeo.com/_rv/viewer', video_id)
webpage = self._verify_video_password(
'https://vimeo.com/' + video_id, video_id,
video_password, viewer['xsrft'], viewer['vuid'])
webpage = self._verify_video_password(video_id, video_password, viewer['xsrft'])
clip_page_config = self._parse_json(self._search_regex(
r'window\.vimeo\.clip_page_config\s*=\s*({.+?});',
webpage, 'clip page config'), video_id)

108
yt_dlp/extractor/vtv.py Normal file
View File

@@ -0,0 +1,108 @@
from .common import InfoExtractor
from ..utils import extract_attributes, get_element_html_by_class, remove_start
class VTVGoIE(InfoExtractor):
_VALID_URL = [
r'https?://(?:www\.)?vtvgo\.vn/(kho-video|tin-tuc)/[\w.-]*?(?P<id>\d+)(?:\.[a-z]+|/)?(?:$|[?#])',
r'https?://(?:www\.)?vtvgo\.vn/digital/detail\.php\?(?:[^#]+&)?content_id=(?P<id>\d+)',
]
_TESTS = [{
'url': 'https://vtvgo.vn/kho-video/bep-vtv-vit-chao-rieng-so-24-888456.html',
'info_dict': {
'id': '888456',
'ext': 'mp4',
'title': 'Bếp VTV | Vịt chao riềng | Số 24',
'description': 'md5:2b4e93ec2b954304170d32be288ce2c8',
'thumbnail': 'https://vtvgo-images.vtvdigital.vn/images/20230201/VIT-CHAO-RIENG_VTV_638108894672812459.jpg',
},
}, {
'url': 'https://vtvgo.vn/tin-tuc/hot-search-1-zlife-khong-ngo-toi-phai-khong-862074',
'info_dict': {
'id': '862074',
'ext': 'mp4',
'title': 'Hot Search #1 | Zlife | Không ngờ tới phải không? ',
'description': 'md5:e967d0e2efbbebbee8814a55799b4d0f',
'thumbnail': 'https://vtvgo-images.vtvdigital.vn/images/20220504/6b9a8552-e71c-46ce-bc9d-50c9bb506f9c.jpeg',
},
}, {
'url': 'https://vtvgo.vn/kho-video/918311.html',
'info_dict': {
'id': '918311',
'title': 'Cà phê sáng | 05/02/2024 | Tái hiện hình ảnh Hà Nội xưa tại ngôi nhà di sản',
'ext': 'mp4',
'thumbnail': 'https://vtvgo-images.vtvdigital.vn/images/20240205/0506_ca_phe_sang_638427226021318322.jpg',
'description': 'md5:b121c67948f1ce58e6a036042fc14c1b',
},
}, {
'url': 'https://vtvgo.vn/digital/detail.php?digital_id=168&content_id=918634',
'info_dict': {
'id': '918634',
'ext': 'mp4',
'title': 'Gặp nhau cuối năm | Táo quân 2024',
'description': 'md5:a1c221e78e5954d29d49b2a11c20513c',
'thumbnail': 'https://vtvgo-images.vtvdigital.vn/images/20240210/d0f73369-8f03-4108-9edd-83d4bc3997b2.png',
},
}, {
'url': 'https://vtvgo.vn/digital/detail.php?content_id=919358',
'info_dict': {
'id': '919358',
'ext': 'mp4',
'title': 'Chúng ta của 8 năm sau | Tập 45 | Dương có bằng chứng, nhân chứng vạch mặt ông Khiêm',
'description': 'md5:16ff5208cac6585137f554472a4677f3',
'thumbnail': 'https://vtvgo-images.vtvdigital.vn/images/20240221/550deff9-7736-4a0e-8b5d-33274d97cd7d.jpg',
},
}, {
'url': 'https://vtvgo.vn/kho-video/888456',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
m3u8_url = self._search_regex(
r'(?:var\s+link\s*=\s*|addPlayer\()["\'](https://[^"\']+/index\.m3u8)["\']', webpage, 'm3u8 url')
return {
'id': video_id,
'title': self._og_search_title(webpage, default=None),
'description': self._og_search_description(webpage, default=None),
'thumbnail': self._og_search_thumbnail(webpage, default=None),
'formats': self._extract_m3u8_formats(m3u8_url, video_id, 'mp4'),
}
class VTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?vtv\.vn/video/[\w-]*?(?P<id>\d+)\.htm'
_TESTS = [{
'url': 'https://vtv.vn/video/thoi-su-20h-vtv1-12-6-2024-680411.htm',
'info_dict': {
'id': '680411',
'ext': 'mp4',
'title': 'Thời sự 20h VTV1 - 12/6/2024 - Video đã phát trên VTV1 | VTV.VN',
'thumbnail': 'https://cdn-images.vtv.vn/zoom/600_315/66349b6076cb4dee98746cf1/2024/06/12/thumb/1206-ts-20h-02929741475480320806760.mp4/thumb0.jpg',
},
}, {
'url': 'https://vtv.vn/video/zlife-1-khong-ngo-toi-phai-khong-vtv24-560248.htm',
'info_dict': {
'id': '560248',
'ext': 'mp4',
'title': 'ZLife #1: Không ngờ tới phải không? | VTV24 - Video đã phát trên VTV-NEWS | VTV.VN',
'description': 'Ai đứng sau vụ việc thay đổi ảnh đại diện trên các trang mạng xã hội của VTV Digital tối 2/5?',
'thumbnail': 'https://video-thumbs.mediacdn.vn/zoom/600_315/vtv/2022/5/13/t67s6btf3ji-16524555726231894427334.jpg',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
data_vid = extract_attributes(get_element_html_by_class(
'VCSortableInPreviewMode', get_element_html_by_class(
'video-highlight-box', webpage)))['data-vid']
m3u8_url = f'https://cdn-videos.vtv.vn/{remove_start(data_vid, "vtv.mediacdn.vn/")}/master.m3u8'
return {
'id': video_id,
'title': self._og_search_title(webpage, default=None),
'description': self._og_search_description(webpage, default=None),
'thumbnail': self._og_search_thumbnail(webpage, default=None),
'formats': self._extract_m3u8_formats(m3u8_url, video_id, 'mp4'),
}

1
yt_dlp/extractor/weibo.py
View File

@@ -52,6 +52,7 @@ class WeiboBaseIE(InfoExtractor):
})
def _weibo_download_json(self, url, video_id, *args, fatal=True, note='Downloading JSON metadata', **kwargs):
# XXX: Always fatal; _download_webpage_handle only returns False (not a tuple) on error
webpage, urlh = self._download_webpage_handle(url, video_id, *args, fatal=fatal, note=note, **kwargs)
if urllib.parse.urlparse(urlh.url).netloc == 'passport.weibo.com':
self._update_visitor_cookies(urlh.url, video_id)

3
yt_dlp/extractor/wsj.py
View File

@@ -2,6 +2,7 @@ from .common import InfoExtractor
from ..utils import (
float_or_none,
int_or_none,
join_nonempty,
unified_strdate,
)
@@ -76,7 +77,7 @@ class WSJIE(InfoExtractor):
tbr = int_or_none(v.get('bitrate'))
formats.append({
'url': mp4_url,
'format_id': 'http' + (f'-{tbr}' if tbr else ''),
'format_id': join_nonempty('http', tbr),
'tbr': tbr,
'width': int_or_none(v.get('width')),
'height': int_or_none(v.get('height')),

8
yt_dlp/extractor/yahoo.py
View File

@@ -8,6 +8,7 @@ from ..utils import (
ExtractorError,
clean_html,
int_or_none,
join_nonempty,
mimetype2ext,
parse_iso8601,
traverse_obj,
@@ -213,7 +214,7 @@ class YahooIE(InfoExtractor):
tbr = int_or_none(s.get('bitrate'))
formats.append({
'url': s_url,
'format_id': fmt + (f'-{tbr}' if tbr else ''),
'format_id': join_nonempty(fmt, tbr),
'width': int_or_none(s.get('width')),
'height': int_or_none(s.get('height')),
'tbr': tbr,
@@ -371,12 +372,13 @@ class YahooJapanNewsIE(InfoExtractor):
url, content_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
else:
bitrate = int_or_none(vid.get('bitrate'))
formats.append({
'url': url,
'format_id': f'http-{vid.get("bitrate")}',
'format_id': join_nonempty('http', bitrate),
'height': int_or_none(vid.get('height')),
'width': int_or_none(vid.get('width')),
'tbr': int_or_none(vid.get('bitrate')),
'tbr': bitrate,
})
self._remove_duplicate_formats(formats)

6
yt_dlp/extractor/yandexdisk.py
View File

@@ -5,6 +5,7 @@ from ..utils import (
determine_ext,
float_or_none,
int_or_none,
join_nonempty,
mimetype2ext,
try_get,
urljoin,
@@ -116,12 +117,9 @@ class YandexDiskIE(InfoExtractor):
else:
size = video.get('size') or {}
height = int_or_none(size.get('height'))
format_id = 'hls'
if height:
format_id += f'-{height}p'
formats.append({
'ext': 'mp4',
'format_id': format_id,
'format_id': join_nonempty('hls', height and f'{height}p'),
'height': height,
'protocol': 'm3u8_native',
'url': format_url,

15
yt_dlp/extractor/yle_areena.py
View File

@@ -11,6 +11,7 @@ from ..utils import (
class YleAreenaIE(InfoExtractor):
_VALID_URL = r'https?://areena\.yle\.fi/(?P<id>[\d-]+)'
_GEO_COUNTRIES = ['FI']
_TESTS = [
{
'url': 'https://areena.yle.fi/1-4371942',
@@ -19,7 +20,7 @@ class YleAreenaIE(InfoExtractor):
'id': '0_a3tjk92c',
'ext': 'mp4',
'title': 'Pouchit',
'description': 'md5:d487309c3abbe5650265bbd1742d2f82',
'description': 'md5:01071d7056ceec375f63960f90c35366',
'series': 'Modernit miehet',
'season': 'Season 1',
'season_number': 1,
@@ -87,8 +88,8 @@ class YleAreenaIE(InfoExtractor):
})
# Example title: 'K1, J2: Pouchit | Modernit miehet'
series, season_number, episode_number, episode = self._search_regex(
r'K(?P<season_no>[\d]+),\s*J(?P<episode_no>[\d]+):?\s*\b(?P<episode>[^|]+)\s*|\s*(?P<series>.+)',
season_number, episode_number, episode, series = self._search_regex(
r'K(?P<season_no>\d+),\s*J(?P<episode_no>\d+):?\s*\b(?P<episode>[^|]+)\s*|\s*(?P<series>.+)',
info.get('title') or '', 'episode metadata', group=('season_no', 'episode_no', 'episode', 'series'),
default=(None, None, None, None))
description = traverse_obj(video_data, ('data', 'ongoing_ondemand', 'description', 'fin'), expected_type=str)
@@ -110,10 +111,12 @@ class YleAreenaIE(InfoExtractor):
'ie_key': KalturaIE.ie_key(),
}
else:
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': self._extract_m3u8_formats(
video_data['data']['ongoing_ondemand']['manifest_url'], video_id, 'mp4', m3u8_id='hls'),
'formats': formats,
}
return {
@@ -129,6 +132,6 @@ class YleAreenaIE(InfoExtractor):
or int_or_none(episode_number)),
'thumbnails': traverse_obj(info, ('thumbnails', ..., {'url': 'url'})),
'age_limit': traverse_obj(video_data, ('data', 'ongoing_ondemand', 'content_rating', 'age_restriction'), expected_type=int_or_none),
'subtitles': subtitles,
'subtitles': subtitles or None,
'release_date': unified_strdate(traverse_obj(video_data, ('data', 'ongoing_ondemand', 'start_time'), expected_type=str)),
}

46
yt_dlp/extractor/youtube.py
View File

@@ -4,6 +4,7 @@ import collections
import copy
import datetime as dt
import enum
import functools
import hashlib
import itertools
import json
@@ -20,7 +21,6 @@ import urllib.parse
from .common import InfoExtractor, SearchInfoExtractor
from .openload import PhantomJSwrapper
from ..compat import functools
from ..jsinterp import JSInterpreter
from ..networking.exceptions import HTTPError, network_exceptions
from ..utils import (
@@ -468,7 +468,10 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
'si', 'th', 'lo', 'my', 'ka', 'am', 'km', 'zh-CN', 'zh-TW', 'zh-HK', 'ja', 'ko',
]
_IGNORED_WARNINGS = {'Unavailable videos will be hidden during playback'}
_IGNORED_WARNINGS = {
'Unavailable videos will be hidden during playback',
'Unavailable videos are hidden',
}
_YT_HANDLE_RE = r'@[\w.-]{3,30}' # https://support.google.com/youtube/answer/11585688?hl=en
_YT_CHANNEL_UCID_RE = r'UC[\w-]{22}'
@@ -3797,6 +3800,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
CHUNK_SIZE = 10 << 20
PREFERRED_LANG_VALUE = 10
original_language = None
itags, stream_ids = collections.defaultdict(set), []
itag_qualities, res_qualities = {}, {0: None}
q = qualities([
@@ -3845,6 +3850,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
itag_qualities[itag] = quality
if height:
res_qualities[height] = quality
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:
original_language = language_code
# FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
# (adding `&sq=0` to the URL) and parsing emsg box to determine the
# number of fragment that would subsequently requested with (`&sq=N`)
@@ -3870,7 +3882,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
continue
query = parse_qs(fmt_url)
throttled = False
if query.get('n'):
try:
decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
@@ -3884,20 +3895,16 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
if player_url:
self.report_warning(
f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
f'nsig extraction failed: Some formats may be missing\n{phantomjs_hint}'
f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
self.write_debug(e, only_once=True)
else:
self.report_warning(
'Cannot decrypt nsig without player_url: You may experience throttling for some formats',
'Cannot decrypt nsig without player_url: Some formats may be missing',
video_id=video_id, only_once=True)
throttled = True
continue
tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
language_preference = (
10 if audio_track.get('audioIsDefault') and 10
else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
else -1)
format_duration = traverse_obj(fmt, ('approxDurationMs', {lambda x: float_or_none(x, 1000)}))
# Some formats may have much smaller duration than others (possibly damaged during encoding)
# E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
@@ -3924,17 +3931,15 @@ 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'),
language_preference > 0 and ' (default)', delim=''),
join_nonempty(audio_track.get('displayName'), 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()),
throttled and 'THROTTLED', is_damaged and 'DAMAGED', is_broken and 'BROKEN',
is_damaged and 'DAMAGED', is_broken and 'BROKEN',
(self.get_param('verbose') or all_formats) and client_name,
delim=', '),
# Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
'source_preference': ((-10 if throttled else -5 if itag == '22' else -1)
+ (100 if 'Premium' in name else 0)),
'source_preference': (-5 if itag == '22' else -1) + (100 if 'Premium' in name else 0),
'fps': fps if fps > 1 else None, # For some formats, fps is wrongly returned as 1
'audio_channels': fmt.get('audioChannels'),
'height': height,
@@ -3944,9 +3949,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'filesize_approx': filesize_from_tbr(tbr, format_duration),
'url': fmt_url,
'width': int_or_none(fmt.get('width')),
'language': join_nonempty(audio_track.get('id', '').split('.')[0],
'desc' if language_preference < -1 else '') or None,
'language_preference': language_preference,
'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,
# 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,
}
@@ -4007,6 +4011,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
elif itag:
f['format_id'] = itag
if original_language and f.get('language') == original_language:
f['format_note'] = join_nonempty(f.get('format_note'), '(default)', delim=' ')
f['language_preference'] = PREFERRED_LANG_VALUE
if f.get('source_preference') is None:
f['source_preference'] = -1
@@ -4351,7 +4359,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
'live_status': live_status,
'release_timestamp': live_start_time,
'_format_sort_fields': ( # source_preference is lower for throttled/potentially damaged formats
'_format_sort_fields': ( # source_preference is lower for potentially damaged formats
'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto'),
}

18
yt_dlp/extractor/zaiko.py
View File

@@ -66,7 +66,9 @@ class ZaikoIE(ZaikoBaseIE):
stream_meta['stream-access']['video_source'], video_id,
'Downloading player page', headers={'referer': 'https://zaiko.io/'})
player_meta = self._parse_vue_element_attr('player', player_page, video_id)
status = traverse_obj(player_meta, ('initial_event_info', 'status', {str}))
initial_event_info = traverse_obj(player_meta, ('initial_event_info', {dict})) or {}
status = traverse_obj(initial_event_info, ('status', {str}))
live_status, msg, expected = {
'vod': ('was_live', 'No VOD stream URL was found', False),
'archiving': ('post_live', 'Event VOD is still being processed', True),
@@ -80,14 +82,20 @@ class ZaikoIE(ZaikoBaseIE):
'cancelled': ('not_live', 'Event has been cancelled', True),
}.get(status) or ('not_live', f'Unknown event status "{status}"', False)
stream_url = traverse_obj(player_meta, ('initial_event_info', 'endpoint', {url_or_none}))
if traverse_obj(initial_event_info, ('is_jwt_protected', {bool})):
stream_url = self._download_json(
initial_event_info['jwt_token_url'], video_id, 'Downloading JWT-protected stream URL',
'Failed to download JWT-protected stream URL')['playback_url']
else:
stream_url = traverse_obj(initial_event_info, ('endpoint', {url_or_none}))
formats = self._extract_m3u8_formats(
stream_url, video_id, live=True, fatal=False) if stream_url else []
if not formats:
self.raise_no_formats(msg, expected=expected)
thumbnail_urls = [
traverse_obj(player_meta, ('initial_event_info', 'poster_url')),
traverse_obj(initial_event_info, ('poster_url', {url_or_none})),
self._og_search_thumbnail(self._download_webpage(
f'https://zaiko.io/event/{video_id}', video_id, 'Downloading event page', fatal=False) or ''),
]
@@ -103,9 +111,7 @@ class ZaikoIE(ZaikoBaseIE):
'release_timestamp': ('stream', 'start', 'timestamp', {int_or_none}),
'categories': ('event', 'genres', ..., {lambda x: x or None}),
}),
**traverse_obj(player_meta, ('initial_event_info', {
'alt_title': ('title', {str}),
})),
'alt_title': traverse_obj(initial_event_info, ('title', {str})),
'thumbnails': [{'url': url, 'id': url_basename(url)} for url in thumbnail_urls if url_or_none(url)],
}

4
yt_dlp/jsinterp.py
View File

@@ -667,12 +667,12 @@ class JSInterpreter:
self.interpret_expression(v, local_vars, allow_recursion)
for v in self._separate(arg_str)]
if obj == str:
if obj is str:
if member == 'fromCharCode':
assertion(argvals, 'takes one or more arguments')
return ''.join(map(chr, argvals))
raise self.Exception(f'Unsupported String method {member}', expr)
elif obj == float:
elif obj is float:
if member == 'pow':
assertion(len(argvals) == 2, 'takes two arguments')
return argvals[0] ** argvals[1]

4
yt_dlp/networking/_requests.py
View File

@@ -230,9 +230,7 @@ class Urllib3LoggingFilter(logging.Filter):
def filter(self, record):
# Ignore HTTP request messages since HTTPConnection prints those
if record.msg == '%s://%s:%s "%s %s %s" %s %s':
return False
return True
return record.msg != '%s://%s:%s "%s %s %s" %s %s'
class Urllib3LoggingHandler(logging.Handler):

2
yt_dlp/networking/_websockets.py
View File

@@ -1,6 +1,7 @@
from __future__ import annotations
import contextlib
import functools
import io
import logging
import ssl
@@ -22,7 +23,6 @@ from .exceptions import (
TransportError,
)
from .websocket import WebSocketRequestHandler, WebSocketResponse
from ..compat import functools
from ..dependencies import websockets
from ..socks import ProxyError as SocksProxyError
from ..utils import int_or_none

12
yt_dlp/options.py
View File

@@ -474,10 +474,10 @@ def create_parser():
'no-attach-info-json', 'embed-thumbnail-atomicparsley', 'no-external-downloader-progress',
'embed-metadata', 'seperate-video-versions', 'no-clean-infojson', 'no-keep-subs', 'no-certifi',
'no-youtube-channel-redirect', 'no-youtube-unavailable-videos', 'no-youtube-prefer-utc-upload-date',
'prefer-legacy-http-handler', 'manifest-filesize-approx',
'prefer-legacy-http-handler', 'manifest-filesize-approx', 'allow-unsafe-ext',
}, 'aliases': {
'youtube-dl': ['all', '-multistreams', '-playlist-match-filter', '-manifest-filesize-approx'],
'youtube-dlc': ['all', '-no-youtube-channel-redirect', '-no-live-chat', '-playlist-match-filter', '-manifest-filesize-approx'],
'youtube-dl': ['all', '-multistreams', '-playlist-match-filter', '-manifest-filesize-approx', '-allow-unsafe-ext'],
'youtube-dlc': ['all', '-no-youtube-channel-redirect', '-no-live-chat', '-playlist-match-filter', '-manifest-filesize-approx', '-allow-unsafe-ext'],
'2021': ['2022', 'no-certifi', 'filename-sanitization'],
'2022': ['2023', 'no-external-downloader-progress', 'playlist-match-filter', 'prefer-legacy-http-handler', 'manifest-filesize-approx'],
'2023': [],
@@ -646,7 +646,7 @@ 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 atleast one of the conditions are met. E.g. --match-filter '
'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\'" '
'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 '
@@ -1479,7 +1479,7 @@ def create_parser():
'Optionally, the KEYRING used for decrypting Chromium cookies on Linux, '
'the name/path of the PROFILE to load cookies from, '
'and the CONTAINER name (if Firefox) ("none" for no container) '
'can be given with their respective seperators. '
'can be given with their respective separators. '
'By default, all containers of the most recently accessed profile are used. '
f'Currently supported keyrings are: {", ".join(map(str.lower, sorted(SUPPORTED_KEYRINGS)))}'))
filesystem.add_option(
@@ -1781,7 +1781,7 @@ def create_parser():
'It can be one of "pre_process" (after video extraction), "after_filter" (after video passes filter), '
'"video" (after --format; before --print/--output), "before_dl" (before each video download), '
'"post_process" (after each video download; default), '
'"after_move" (after moving video file to it\'s final locations), '
'"after_move" (after moving video file to its final locations), '
'"after_video" (after downloading and processing all formats of a video), '
'or "playlist" (at end of playlist). '
'This option can be used multiple times to add different postprocessors'))

20
yt_dlp/postprocessor/embedthumbnail.py
View File

@@ -119,15 +119,22 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
if not mutagen or prefer_atomicparsley:
success = False
else:
self._report_run('mutagen', filename)
f = {'jpeg': MP4Cover.FORMAT_JPEG, 'png': MP4Cover.FORMAT_PNG}
try:
self._report_run('mutagen', filename)
with open(thumbnail_filename, 'rb') as thumbfile:
thumb_data = thumbfile.read()
type_ = imghdr.what(h=thumb_data)
if not type_:
raise ValueError('could not determine image type')
elif type_ not in f:
raise ValueError(f'incompatible image type: {type_}')
meta = MP4(filename)
# NOTE: the 'covr' atom is a non-standard MPEG-4 atom,
# Apple iTunes 'M4A' files include the 'moov.udta.meta.ilst' atom.
f = {'jpeg': MP4Cover.FORMAT_JPEG, 'png': MP4Cover.FORMAT_PNG}[imghdr.what(thumbnail_filename)]
with open(thumbnail_filename, 'rb') as thumbfile:
thumb_data = thumbfile.read()
meta.tags['covr'] = [MP4Cover(data=thumb_data, imageformat=f)]
meta.tags['covr'] = [MP4Cover(data=thumb_data, imageformat=f[type_])]
meta.save()
temp_filename = filename
except Exception as err:
@@ -160,9 +167,10 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
stdout, stderr, returncode = Popen.run(cmd, text=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
if returncode:
self.report_warning(f'Unable to embed thumbnails using AtomicParsley; {stderr.strip()}')
success = False
# for formats that don't support thumbnails (like 3gp) AtomicParsley
# won't create to the temporary file
if 'No changes' in stdout:
elif 'No changes' in stdout:
self.report_warning('The file format doesn\'t support embedding a thumbnail')
success = False

3
yt_dlp/postprocessor/ffmpeg.py
View File

@@ -1,5 +1,6 @@
import collections
import contextvars
import functools
import itertools
import json
import os
@@ -8,7 +9,7 @@ import subprocess
import time
from .common import PostProcessor
from ..compat import functools, imghdr
from ..compat import imghdr
from ..utils import (
MEDIA_EXTENSIONS,
ISO639Utils,

152
yt_dlp/utils/_utils.py
View File

@@ -2085,19 +2085,20 @@ def parse_duration(s):
(days, 86400), (hours, 3600), (mins, 60), (secs, 1), (ms, 1)))
def prepend_extension(filename, ext, expected_real_ext=None):
def _change_extension(prepend, filename, ext, expected_real_ext=None):
name, real_ext = os.path.splitext(filename)
return (
f'{name}.{ext}{real_ext}'
if not expected_real_ext or real_ext[1:] == expected_real_ext
else f'{filename}.{ext}')
if not expected_real_ext or real_ext[1:] == expected_real_ext:
filename = name
if prepend and real_ext:
_UnsafeExtensionError.sanitize_extension(ext, prepend=True)
return f'{filename}.{ext}{real_ext}'
return f'{filename}.{_UnsafeExtensionError.sanitize_extension(ext)}'
def replace_extension(filename, ext, expected_real_ext=None):
name, real_ext = os.path.splitext(filename)
ext = ext if ext.startswith('.') else '.' + ext
return f'{name if not expected_real_ext or real_ext[1:] == expected_real_ext else filename}{ext}'
prepend_extension = functools.partial(_change_extension, True)
replace_extension = functools.partial(_change_extension, False)
def check_executable(exe, args=[]):
@@ -5025,7 +5026,7 @@ MEDIA_EXTENSIONS = Namespace(
common_video=('avi', 'flv', 'mkv', 'mov', 'mp4', 'webm'),
video=('3g2', '3gp', 'f4v', 'mk3d', 'divx', 'mpg', 'ogv', 'm4v', 'wmv'),
common_audio=('aiff', 'alac', 'flac', 'm4a', 'mka', 'mp3', 'ogg', 'opus', 'wav'),
audio=('aac', 'ape', 'asf', 'f4a', 'f4b', 'm4b', 'm4p', 'm4r', 'oga', 'ogx', 'spx', 'vorbis', 'wma', 'weba'),
audio=('aac', 'ape', 'asf', 'f4a', 'f4b', 'm4b', 'm4r', 'oga', 'ogx', 'spx', 'vorbis', 'wma', 'weba'),
thumbnails=('jpg', 'png', 'webp'),
storyboards=('mhtml', ),
subtitles=('srt', 'vtt', 'ass', 'lrc'),
@@ -5037,6 +5038,135 @@ MEDIA_EXTENSIONS.audio += MEDIA_EXTENSIONS.common_audio
KNOWN_EXTENSIONS = (*MEDIA_EXTENSIONS.video, *MEDIA_EXTENSIONS.audio, *MEDIA_EXTENSIONS.manifests)
class _UnsafeExtensionError(Exception):
"""
Mitigation exception for uncommon/malicious file extensions
This should be caught in YoutubeDL.py alongside a warning
Ref: https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-79w7-vh3h-8g4j
"""
ALLOWED_EXTENSIONS = frozenset([
# internal
'description',
'json',
'meta',
'orig',
'part',
'temp',
'uncut',
'unknown_video',
'ytdl',
# video
*MEDIA_EXTENSIONS.video,
'asx',
'ismv',
'm2t',
'm2ts',
'm2v',
'm4s',
'mng',
'mp2v',
'mp4v',
'mpe',
'mpeg',
'mpeg1',
'mpeg2',
'mpeg4',
'mxf',
'ogm',
'qt',
'rm',
'swf',
'ts',
'vob',
'vp9',
# audio
*MEDIA_EXTENSIONS.audio,
'3ga',
'ac3',
'adts',
'aif',
'au',
'dts',
'isma',
'it',
'mid',
'mod',
'mpga',
'mp1',
'mp2',
'mp4a',
'mpa',
'ra',
'shn',
'xm',
# image
*MEDIA_EXTENSIONS.thumbnails,
'avif',
'bmp',
'gif',
'heic',
'ico',
'jng',
'jpeg',
'jxl',
'svg',
'tif',
'tiff',
'wbmp',
# subtitle
*MEDIA_EXTENSIONS.subtitles,
'dfxp',
'fs',
'ismt',
'json3',
'sami',
'scc',
'srv1',
'srv2',
'srv3',
'ssa',
'tt',
'ttml',
'xml',
# others
*MEDIA_EXTENSIONS.manifests,
*MEDIA_EXTENSIONS.storyboards,
'desktop',
'ism',
'm3u',
'sbv',
'url',
'webloc',
])
def __init__(self, extension, /):
super().__init__(f'unsafe file extension: {extension!r}')
self.extension = extension
@classmethod
def sanitize_extension(cls, extension, /, *, prepend=False):
if extension is None:
return None
if '/' in extension or '\\' in extension:
raise cls(extension)
if not prepend:
_, _, last = extension.rpartition('.')
if last == 'bin':
extension = last = 'unknown_video'
if last.lower() not in cls.ALLOWED_EXTENSIONS:
raise cls(extension)
return extension
class RetryManager:
"""Usage:
for retry in RetryManager(...):

6
yt_dlp/version.py
View File

@@ -1,8 +1,8 @@
# Autogenerated by devscripts/update-version.py
__version__ = '2024.05.27'
__version__ = '2024.07.07'
RELEASE_GIT_HEAD = '12b248ce60be1aa1362edd839d915bba70dbee4b'
RELEASE_GIT_HEAD = 'b337d2989ce0614651d363383f6f743d977248ef'
VARIANT = None
@@ -12,4 +12,4 @@ CHANNEL = 'stable'
ORIGIN = 'yt-dlp/yt-dlp'
_pkg_version = '2024.05.27'
_pkg_version = '2024.07.07'