mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-12-29 19:11:30 +00:00
Code Issues Projects Releases Wiki Activity

Merge branch 'yt-dlp:master' into ie/shouttv

Browse Source
This commit is contained in:
bashonly
2024-11-17 11:22:20 -06:00
parent 134cb81bc9 10fc719bc7
commit 2c7a1dc392
153 changed files with 3415 additions and 2162 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
yt_dlp/extractor/_extractors.py
View File

@@ -208,6 +208,10 @@ from .bandcamp import (
BandcampUserIE,
BandcampWeeklyIE,
)
from .bandlab import (
BandlabIE,
BandlabPlaylistIE,
)
from .bannedvideo import BannedVideoIE
from .bbc import (
BBCIE,
@@ -278,6 +282,7 @@ from .bleacherreport import (
from .blerp import BlerpIE
from .blogger import BloggerIE
from .bloomberg import BloombergIE
from .bluesky import BlueskyIE
from .bokecc import BokeCCIE
from .bongacams import BongaCamsIE
from .boosty import BoostyIE
@@ -707,6 +712,7 @@ from .gab import (
GabTVIE,
)
from .gaia import GaiaIE
from .gamedevtv import GameDevTVDashboardIE
from .gamejolt import (
GameJoltCommunityIE,
GameJoltGameIE,
@@ -940,6 +946,10 @@ from .kaltura import KalturaIE
from .kankanews import KankaNewsIE
from .karaoketv import KaraoketvIE
from .kelbyone import KelbyOneIE
from .kenh14 import (
Kenh14PlaylistIE,
Kenh14VideoIE,
)
from .khanacademy import (
KhanAcademyIE,
KhanAcademyUnitIE,
@@ -1129,12 +1139,6 @@ from .microsoftembed import (
MicrosoftMediusIE,
)
from .microsoftstream import MicrosoftStreamIE
from .mildom import (
MildomClipIE,
MildomIE,
MildomUserVodIE,
MildomVodIE,
)
from .minds import (
MindsChannelIE,
MindsGroupIE,
@@ -1154,6 +1158,7 @@ from .mitele import MiTeleIE
from .mixch import (
MixchArchiveIE,
MixchIE,
MixchMovieIE,
)
from .mixcloud import (
MixcloudIE,
@@ -1552,10 +1557,6 @@ from .podbayfm import (
)
from .podchaser import PodchaserIE
from .podomatic import PodomaticIE
from .pokemon import (
PokemonIE,
PokemonWatchIE,
)
from .pokergo import (
PokerGoCollectionIE,
PokerGoIE,
@@ -1646,6 +1647,7 @@ from .radiokapital import (
RadioKapitalIE,
RadioKapitalShowIE,
)
from .radioradicale import RadioRadicaleIE
from .radiozet import RadioZetPodcastIE
from .radlive import (
RadLiveChannelIE,
@@ -1942,9 +1944,7 @@ from .spotify import (
)
from .spreaker import (
SpreakerIE,
SpreakerPageIE,
SpreakerShowIE,
SpreakerShowPageIE,
)
from .springboardplatform import SpringboardPlatformIE
from .sprout import SproutIE
@@ -2283,10 +2283,6 @@ from .utreon import UtreonIE
from .varzesh3 import Varzesh3IE
from .vbox7 import Vbox7IE
from .veo import VeoIE
from .veoh import (
VeohIE,
VeohUserIE,
)
from .vesti import VestiIE
from .vevo import (
VevoIE,

9
yt_dlp/extractor/abematv.py
View File

@@ -6,7 +6,6 @@ import hmac
import io
import json
import re
import struct
import time
import urllib.parse
import uuid
@@ -18,10 +17,8 @@ from ..networking.exceptions import TransportError
from ..utils import (
ExtractorError,
OnDemandPagedList,
bytes_to_intlist,
decode_base_n,
int_or_none,
intlist_to_bytes,
time_seconds,
traverse_obj,
update_url_query,
@@ -72,15 +69,15 @@ class AbemaLicenseRH(RequestHandler):
})
res = decode_base_n(license_response['k'], table=self._STRTABLE)
encvideokey = bytes_to_intlist(struct.pack('>QQ', res >> 64, res & 0xffffffffffffffff))
encvideokey = list(res.to_bytes(16, 'big'))
h = hmac.new(
binascii.unhexlify(self._HKEY),
(license_response['cid'] + self.ie._DEVICE_ID).encode(),
digestmod=hashlib.sha256)
enckey = bytes_to_intlist(h.digest())
enckey = list(h.digest())
return intlist_to_bytes(aes_ecb_decrypt(encvideokey, enckey))
return bytes(aes_ecb_decrypt(encvideokey, enckey))
class AbemaTVBaseIE(InfoExtractor):

8
yt_dlp/extractor/adn.py
View File

@@ -11,11 +11,9 @@ from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
ass_subtitles_timecode,
bytes_to_intlist,
bytes_to_long,
float_or_none,
int_or_none,
intlist_to_bytes,
join_nonempty,
long_to_bytes,
parse_iso8601,
@@ -198,16 +196,16 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
links_url = try_get(options, lambda x: x['video']['url']) or (video_base_url + 'link')
self._K = ''.join(random.choices('0123456789abcdef', k=16))
message = bytes_to_intlist(json.dumps({
message = list(json.dumps({
'k': self._K,
't': token,
}))
}).encode())
# Sometimes authentication fails for no good reason, retry with
# a different random padding
links_data = None
for _ in range(3):
padded_message = intlist_to_bytes(pkcs1pad(message, 128))
padded_message = bytes(pkcs1pad(message, 128))
n, e = self._RSA_KEY
encrypted_message = long_to_bytes(pow(bytes_to_long(padded_message), e, n))
authorization = base64.b64encode(encrypted_message).decode()

2
yt_dlp/extractor/adobepass.py
View File

@@ -1362,7 +1362,7 @@ class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should en
def _download_webpage_handle(self, *args, **kwargs):
headers = self.geo_verification_headers()
headers.update(kwargs.get('headers', {}))
headers.update(kwargs.get('headers') or {})
kwargs['headers'] = headers
return super()._download_webpage_handle(
*args, **kwargs)

21
yt_dlp/extractor/afreecatv.py
View File

@@ -66,6 +66,14 @@ class AfreecaTVBaseIE(InfoExtractor):
extensions={'legacy_ssl': True}), display_id,
'Downloading API JSON', 'Unable to download API JSON')
@staticmethod
def _fixup_thumb(thumb_url):
if not url_or_none(thumb_url):
return None
# Core would determine_ext as 'php' from the url, so we need to provide the real ext
# See: https://github.com/yt-dlp/yt-dlp/issues/11537
return [{'url': thumb_url, 'ext': 'jpg'}]
class AfreecaTVIE(AfreecaTVBaseIE):
IE_NAME = 'soop'
@@ -154,8 +162,8 @@ class AfreecaTVIE(AfreecaTVBaseIE):
'title': ('title', {str}),
'uploader': ('writer_nick', {str}),
'uploader_id': ('bj_id', {str}),
'duration': ('total_file_duration', {functools.partial(int_or_none, scale=1000)}),
'thumbnail': ('thumb', {url_or_none}),
'duration': ('total_file_duration', {int_or_none(scale=1000)}),
'thumbnails': ('thumb', {self._fixup_thumb}),
})
entries = []
@@ -178,7 +186,7 @@ class AfreecaTVIE(AfreecaTVBaseIE):
'title': f'{common_info.get("title") or "Untitled"} (part {file_num})',
'formats': formats,
**traverse_obj(file_element, {
'duration': ('duration', {functools.partial(int_or_none, scale=1000)}),
'duration': ('duration', {int_or_none(scale=1000)}),
'timestamp': ('file_start', {unified_timestamp}),
}),
})
@@ -226,19 +234,18 @@ class AfreecaTVCatchStoryIE(AfreecaTVBaseIE):
return self.playlist_result(self._entries(data), video_id)
@staticmethod
def _entries(data):
def _entries(self, data):
# 'files' is always a list with 1 element
yield from traverse_obj(data, (
'data', lambda _, v: v['story_type'] == 'catch',
'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)}),
'duration': ('files', 0, 'duration', {int_or_none(scale=1000)}),
'title': ('title', {str}),
'uploader': ('writer_nick', {str}),
'uploader_id': ('writer_id', {str}),
'thumbnail': ('thumb', {url_or_none}),
'thumbnails': ('thumb', {self._fixup_thumb}),
'timestamp': ('write_timestamp', {int_or_none}),
}))

2
yt_dlp/extractor/allstar.py
View File

@@ -71,7 +71,7 @@ class AllstarBaseIE(InfoExtractor):
'thumbnails': (('clipImageThumb', 'clipImageSource'), {'url': {media_url_or_none}}),
'duration': ('clipLength', {int_or_none}),
'filesize': ('clipSizeBytes', {int_or_none}),
'timestamp': ('createdDate', {functools.partial(int_or_none, scale=1000)}),
'timestamp': ('createdDate', {int_or_none(scale=1000)}),
'uploader': ('username', {str}),
'uploader_id': ('user', '_id', {str}),
'view_count': ('views', {int_or_none}),

51
yt_dlp/extractor/anvato.py
View File

@@ -8,10 +8,8 @@ import time
from .common import InfoExtractor
from ..aes import aes_encrypt
from ..utils import (
bytes_to_intlist,
determine_ext,
int_or_none,
intlist_to_bytes,
join_nonempty,
smuggle_url,
strip_jsonp,
@@ -33,24 +31,6 @@ class AnvatoIE(InfoExtractor):
_AUTH_KEY = b'\x31\xc2\x42\x84\x9e\x73\xa0\xce' # from anvplayer.min.js
_TESTS = [{
# from https://www.nfl.com/videos/baker-mayfield-s-game-changing-plays-from-3-td-game-week-14
'url': 'anvato:GXvEgwyJeWem8KCYXfeoHWknwP48Mboj:899441',
'md5': '921919dab3cd0b849ff3d624831ae3e2',
'info_dict': {
'id': '899441',
'ext': 'mp4',
'title': 'Baker Mayfield\'s game-changing plays from 3-TD game Week 14',
'description': 'md5:85e05a3cc163f8c344340f220521136d',
'upload_date': '20201215',
'timestamp': 1608009755,
'thumbnail': r're:^https?://.*\.jpg',
'uploader': 'NFL',
'tags': ['Baltimore Ravens at Cleveland Browns (2020-REG-14)', 'Baker Mayfield', 'Game Highlights',
'Player Highlights', 'Cleveland Browns', 'league'],
'duration': 157,
'categories': ['Entertainment', 'Game', 'Highlights'],
},
}, {
# from https://ktla.com/news/99-year-old-woman-learns-to-fly-in-torrance-checks-off-bucket-list-dream/
'url': 'anvato:X8POa4zpGZMmeiq0wqiO8IP5rMqQM9VN:8032455',
'md5': '837718bcfb3a7778d022f857f7a9b19e',
@@ -241,31 +221,6 @@ class AnvatoIE(InfoExtractor):
'telemundo': 'anvato_mcp_telemundo_web_prod_c5278d51ad46fda4b6ca3d0ea44a7846a054f582',
}
def _generate_nfl_token(self, anvack, mcp_id):
reroute = self._download_json(
'https://api.nfl.com/v1/reroute', mcp_id, data=b'grant_type=client_credentials',
headers={'X-Domain-Id': 100}, note='Fetching token info')
token_type = reroute.get('token_type') or 'Bearer'
auth_token = f'{token_type} {reroute["access_token"]}'
response = self._download_json(
'https://api.nfl.com/v3/shield/', mcp_id, data=json.dumps({
'query': '''{
viewer {
mediaToken(anvack: "%s", id: %s) {
token
}
}
}''' % (anvack, mcp_id), # noqa: UP031
}).encode(), headers={
'Authorization': auth_token,
'Content-Type': 'application/json',
}, note='Fetching NFL API token')
return traverse_obj(response, ('data', 'viewer', 'mediaToken', 'token'))
_TOKEN_GENERATORS = {
'GXvEgwyJeWem8KCYXfeoHWknwP48Mboj': _generate_nfl_token,
}
def _server_time(self, access_key, video_id):
return int_or_none(traverse_obj(self._download_json(
f'{self._API_BASE_URL}/server_time', video_id, query={'anvack': access_key},
@@ -277,8 +232,8 @@ class AnvatoIE(InfoExtractor):
server_time = self._server_time(access_key, video_id)
input_data = f'{server_time}~{md5_text(video_data_url)}~{md5_text(server_time)}'
auth_secret = intlist_to_bytes(aes_encrypt(
bytes_to_intlist(input_data[:64]), bytes_to_intlist(self._AUTH_KEY)))
auth_secret = bytes(aes_encrypt(
list(input_data[:64].encode()), list(self._AUTH_KEY)))
query = {
'X-Anvato-Adst-Auth': base64.b64encode(auth_secret).decode('ascii'),
'rtyp': 'fp',
@@ -290,8 +245,6 @@ class AnvatoIE(InfoExtractor):
}
if extracted_token is not None:
api['anvstk2'] = extracted_token
elif self._TOKEN_GENERATORS.get(access_key) is not None:
api['anvstk2'] = self._TOKEN_GENERATORS[access_key](self, access_key, video_id)
elif self._ANVACK_TABLE.get(access_key) is not None:
api['anvstk'] = md5_text(f'{access_key}|{anvrid}|{server_time}|{self._ANVACK_TABLE[access_key]}')
else:

22
yt_dlp/extractor/archiveorg.py
View File

@@ -205,6 +205,26 @@ class ArchiveOrgIE(InfoExtractor):
},
},
],
}, {
# The reviewbody is None for one of the reviews; just need to extract data without crashing
'url': 'https://archive.org/details/gd95-04-02.sbd.11622.sbeok.shnf/gd95-04-02d1t04.shn',
'info_dict': {
'id': 'gd95-04-02.sbd.11622.sbeok.shnf/gd95-04-02d1t04.shn',
'ext': 'mp3',
'title': 'Stuck Inside of Mobile with the Memphis Blues Again',
'creators': ['Grateful Dead'],
'duration': 338.31,
'track': 'Stuck Inside of Mobile with the Memphis Blues Again',
'description': 'md5:764348a470b986f1217ffd38d6ac7b72',
'display_id': 'gd95-04-02d1t04.shn',
'location': 'Pyramid Arena',
'uploader': 'jon@archive.org',
'album': '1995-04-02 - Pyramid Arena',
'upload_date': '20040519',
'track_number': 4,
'release_date': '19950402',
'timestamp': 1084927901,
},
}]
@staticmethod
@@ -335,7 +355,7 @@ class ArchiveOrgIE(InfoExtractor):
info['comments'].append({
'id': review.get('review_id'),
'author': review.get('reviewer'),
'text': str_or_none(review.get('reviewtitle'), '') + '\n\n' + review.get('reviewbody'),
'text': join_nonempty('reviewtitle', 'reviewbody', from_dict=review, delim='\n\n'),
'timestamp': unified_timestamp(review.get('createdate')),
'parent': 'root'})

28
yt_dlp/extractor/ard.py
View File

@@ -299,7 +299,7 @@ class ARDBetaMediathekIE(InfoExtractor):
'info_dict': {
'id': '94834686',
'ext': 'mp4',
'duration': 2700,
'duration': 2670,
'episode': '7 Tage ... unter harten Jungs',
'description': 'md5:0f215470dcd2b02f59f4bd10c963f072',
'upload_date': '20231005',
@@ -307,10 +307,28 @@ class ARDBetaMediathekIE(InfoExtractor):
'display_id': 'N2I2YmM5MzgtNWFlOS00ZGFlLTg2NzMtYzNjM2JlNjk4MDg3',
'series': '7 Tage ...',
'channel': 'HR',
'thumbnail': 'https://api.ardmediathek.de/image-service/images/urn:ard:image:f6e6d5ffac41925c?w=960&ch=fa32ba69bc87989a',
'thumbnail': 'https://api.ardmediathek.de/image-service/images/urn:ard:image:430c86d233afa42d?w=960&ch=fa32ba69bc87989a',
'title': '7 Tage ... unter harten Jungs',
'_old_archive_ids': ['ardbetamediathek N2I2YmM5MzgtNWFlOS00ZGFlLTg2NzMtYzNjM2JlNjk4MDg3'],
},
}, {
'url': 'https://www.ardmediathek.de/video/lokalzeit-aus-duesseldorf/lokalzeit-aus-duesseldorf-oder-31-10-2024/wdr-duesseldorf/Y3JpZDovL3dkci5kZS9CZWl0cmFnLXNvcGhvcmEtOWFkMTc0ZWMtMDA5ZS00ZDEwLWFjYjctMGNmNTdhNzVmNzUz',
'info_dict': {
'id': '13847165',
'chapters': 'count:8',
'ext': 'mp4',
'channel': 'WDR',
'display_id': 'Y3JpZDovL3dkci5kZS9CZWl0cmFnLXNvcGhvcmEtOWFkMTc0ZWMtMDA5ZS00ZDEwLWFjYjctMGNmNTdhNzVmNzUz',
'episode': 'Lokalzeit aus Düsseldorf | 31.10.2024',
'series': 'Lokalzeit aus Düsseldorf',
'thumbnail': 'https://api.ardmediathek.de/image-service/images/urn:ard:image:f02ec9bd9b7bd5f6?w=960&ch=612491dcd5e09b0c',
'title': 'Lokalzeit aus Düsseldorf | 31.10.2024',
'upload_date': '20241031',
'timestamp': 1730399400,
'description': 'md5:12db30b3b706314efe3778b8df1a7058',
'duration': 1759,
'_old_archive_ids': ['ardbetamediathek Y3JpZDovL3dkci5kZS9CZWl0cmFnLXNvcGhvcmEtOWFkMTc0ZWMtMDA5ZS00ZDEwLWFjYjctMGNmNTdhNzVmNzUz'],
},
}, {
'url': 'https://beta.ardmediathek.de/ard/video/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE',
'only_matching': True,
@@ -455,6 +473,12 @@ class ARDBetaMediathekIE(InfoExtractor):
'subtitles': subtitles,
'is_live': is_live,
'age_limit': age_limit,
**traverse_obj(media_data, {
'chapters': ('pluginData', 'jumpmarks@all', 'chapterArray', lambda _, v: int_or_none(v['chapterTime']), {
'start_time': ('chapterTime', {int_or_none}),
'title': ('chapterTitle', {str}),
}),
}),
**traverse_obj(media_data, ('meta', {
'title': 'title',
'description': 'synopsis',

41
yt_dlp/extractor/bandcamp.py
View File

@@ -1,4 +1,3 @@
import functools
import json
import random
import re
@@ -10,7 +9,6 @@ from ..utils import (
ExtractorError,
extract_attributes,
float_or_none,
get_element_html_by_id,
int_or_none,
parse_filesize,
str_or_none,
@@ -21,7 +19,7 @@ from ..utils import (
url_or_none,
urljoin,
)
from ..utils.traversal import traverse_obj
from ..utils.traversal import find_element, traverse_obj
class BandcampIE(InfoExtractor):
@@ -45,6 +43,8 @@ class BandcampIE(InfoExtractor):
'uploader_url': 'https://youtube-dl.bandcamp.com',
'uploader_id': 'youtube-dl',
'thumbnail': 'https://f4.bcbits.com/img/a3216802731_5.jpg',
'artists': ['youtube-dl "\'/\\ä↭'],
'album_artists': ['youtube-dl "\'/\\ä↭'],
},
'skip': 'There is a limit of 200 free downloads / month for the test song',
}, {
@@ -271,6 +271,18 @@ class BandcampAlbumIE(BandcampIE): # XXX: Do not subclass from concrete IE
'timestamp': 1311756226,
'upload_date': '20110727',
'uploader': 'Blazo',
'thumbnail': 'https://f4.bcbits.com/img/a1721150828_5.jpg',
'album_artists': ['Blazo'],
'uploader_url': 'https://blazo.bandcamp.com',
'release_date': '20110727',
'release_timestamp': 1311724800.0,
'track': 'Intro',
'uploader_id': 'blazo',
'track_number': 1,
'album': 'Jazz Format Mixtape vol.1',
'artists': ['Blazo'],
'duration': 19.335,
'track_id': '1353101989',
},
},
{
@@ -282,6 +294,18 @@ class BandcampAlbumIE(BandcampIE): # XXX: Do not subclass from concrete IE
'timestamp': 1311757238,
'upload_date': '20110727',
'uploader': 'Blazo',
'track': 'Kero One - Keep It Alive (Blazo remix)',
'release_date': '20110727',
'track_id': '38097443',
'track_number': 2,
'duration': 181.467,
'uploader_url': 'https://blazo.bandcamp.com',
'album': 'Jazz Format Mixtape vol.1',
'uploader_id': 'blazo',
'album_artists': ['Blazo'],
'artists': ['Blazo'],
'thumbnail': 'https://f4.bcbits.com/img/a1721150828_5.jpg',
'release_timestamp': 1311724800.0,
},
},
],
@@ -289,6 +313,7 @@ class BandcampAlbumIE(BandcampIE): # XXX: Do not subclass from concrete IE
'title': 'Jazz Format Mixtape vol.1',
'id': 'jazz-format-mixtape-vol-1',
'uploader_id': 'blazo',
'description': 'md5:38052a93217f3ffdc033cd5dbbce2989',
},
'params': {
'playlistend': 2,
@@ -363,10 +388,10 @@ class BandcampWeeklyIE(BandcampIE): # XXX: Do not subclass from concrete IE
_VALID_URL = r'https?://(?:www\.)?bandcamp\.com/?\?(?:.*?&)?show=(?P<id>\d+)'
_TESTS = [{
'url': 'https://bandcamp.com/?show=224',
'md5': 'b00df799c733cf7e0c567ed187dea0fd',
'md5': '61acc9a002bed93986b91168aa3ab433',
'info_dict': {
'id': '224',
'ext': 'opus',
'ext': 'mp3',
'title': 'BC Weekly April 4th 2017 - Magic Moments',
'description': 'md5:5d48150916e8e02d030623a48512c874',
'duration': 5829.77,
@@ -376,7 +401,7 @@ class BandcampWeeklyIE(BandcampIE): # XXX: Do not subclass from concrete IE
'episode_id': '224',
},
'params': {
'format': 'opus-lo',
'format': 'mp3-128',
},
}, {
'url': 'https://bandcamp.com/?blah/blah@&show=228',
@@ -484,7 +509,7 @@ class BandcampUserIE(InfoExtractor):
or re.findall(r'<div[^>]+trackTitle["\'][^"\']+["\']([^"\']+)', webpage))
yield from traverse_obj(webpage, (
{functools.partial(get_element_html_by_id, 'music-grid')}, {extract_attributes},
{find_element(id='music-grid', html=True)}, {extract_attributes},
'data-client-items', {json.loads}, ..., 'page_url', {str}))
def _real_extract(self, url):
@@ -493,4 +518,4 @@ class BandcampUserIE(InfoExtractor):
return self.playlist_from_matches(
self._yield_items(webpage), uploader, f'Discography of {uploader}',
getter=functools.partial(urljoin, url))
getter=urljoin(url))

438
yt_dlp/extractor/bandlab.py Normal file
View File

@@ -0,0 +1,438 @@
from .common import InfoExtractor
from ..utils import (
ExtractorError,
float_or_none,
format_field,
int_or_none,
parse_iso8601,
parse_qs,
truncate_string,
url_or_none,
)
from ..utils.traversal import traverse_obj, value
class BandlabBaseIE(InfoExtractor):
def _call_api(self, endpoint, asset_id, **kwargs):
headers = kwargs.pop('headers', None) or {}
return self._download_json(
f'https://www.bandlab.com/api/v1.3/{endpoint}/{asset_id}',
asset_id, headers={
'accept': 'application/json',
'referer': 'https://www.bandlab.com/',
'x-client-id': 'BandLab-Web',
'x-client-version': '10.1.124',
**headers,
}, **kwargs)
def _parse_revision(self, revision_data, url=None):
return {
'vcodec': 'none',
'media_type': 'revision',
'extractor_key': BandlabIE.ie_key(),
'extractor': BandlabIE.IE_NAME,
**traverse_obj(revision_data, {
'webpage_url': (
'id', ({value(url)}, {format_field(template='https://www.bandlab.com/revision/%s')}), filter, any),
'id': (('revisionId', 'id'), {str}, any),
'title': ('song', 'name', {str}),
'track': ('song', 'name', {str}),
'url': ('mixdown', 'file', {url_or_none}),
'thumbnail': ('song', 'picture', 'url', {url_or_none}),
'description': ('description', {str}),
'uploader': ('creator', 'name', {str}),
'uploader_id': ('creator', 'username', {str}),
'timestamp': ('createdOn', {parse_iso8601}),
'duration': ('mixdown', 'duration', {float_or_none}),
'view_count': ('counters', 'plays', {int_or_none}),
'like_count': ('counters', 'likes', {int_or_none}),
'comment_count': ('counters', 'comments', {int_or_none}),
'genres': ('genres', ..., 'name', {str}),
}),
}
def _parse_track(self, track_data, url=None):
return {
'vcodec': 'none',
'media_type': 'track',
'extractor_key': BandlabIE.ie_key(),
'extractor': BandlabIE.IE_NAME,
**traverse_obj(track_data, {
'webpage_url': (
'id', ({value(url)}, {format_field(template='https://www.bandlab.com/post/%s')}), filter, any),
'id': (('revisionId', 'id'), {str}, any),
'url': ('track', 'sample', 'audioUrl', {url_or_none}),
'title': ('track', 'name', {str}),
'track': ('track', 'name', {str}),
'description': ('caption', {str}),
'thumbnail': ('track', 'picture', ('original', 'url'), {url_or_none}, any),
'view_count': ('counters', 'plays', {int_or_none}),
'like_count': ('counters', 'likes', {int_or_none}),
'comment_count': ('counters', 'comments', {int_or_none}),
'duration': ('track', 'sample', 'duration', {float_or_none}),
'uploader': ('creator', 'name', {str}),
'uploader_id': ('creator', 'username', {str}),
'timestamp': ('createdOn', {parse_iso8601}),
}),
}
def _parse_video(self, video_data, url=None):
return {
'media_type': 'video',
'extractor_key': BandlabIE.ie_key(),
'extractor': BandlabIE.IE_NAME,
**traverse_obj(video_data, {
'id': ('id', {str}),
'webpage_url': (
'id', ({value(url)}, {format_field(template='https://www.bandlab.com/post/%s')}), filter, any),
'url': ('video', 'url', {url_or_none}),
'title': ('caption', {lambda x: x.replace('\n', ' ')}, {truncate_string(left=50)}),
'description': ('caption', {str}),
'thumbnail': ('video', 'picture', 'url', {url_or_none}),
'view_count': ('video', 'counters', 'plays', {int_or_none}),
'like_count': ('video', 'counters', 'likes', {int_or_none}),
'comment_count': ('counters', 'comments', {int_or_none}),
'duration': ('video', 'duration', {float_or_none}),
'uploader': ('creator', 'name', {str}),
'uploader_id': ('creator', 'username', {str}),
}),
}
class BandlabIE(BandlabBaseIE):
_VALID_URL = [
r'https?://(?:www\.)?bandlab.com/(?P<url_type>track|post|revision)/(?P<id>[\da-f_-]+)',
r'https?://(?:www\.)?bandlab.com/(?P<url_type>embed)/\?(?:[^#]*&)?id=(?P<id>[\da-f-]+)',
]
_EMBED_REGEX = [rf'<iframe[^>]+src=[\'"](?P<url>{_VALID_URL[1]})[\'"]']
_TESTS = [{
'url': 'https://www.bandlab.com/track/04b37e88dba24967b9dac8eb8567ff39_07d7f906fc96ee11b75e000d3a428fff',
'md5': '46f7b43367dd268bbcf0bbe466753b2c',
'info_dict': {
'id': '02d7f906-fc96-ee11-b75e-000d3a428fff',
'ext': 'm4a',
'uploader_id': 'ender_milze',
'track': 'sweet black',
'description': 'composed by juanjn3737',
'timestamp': 1702171963,
'view_count': int,
'like_count': int,
'duration': 54.629999999999995,
'title': 'sweet black',
'upload_date': '20231210',
'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/songs/fa082beb-b856-4730-9170-a57e4e32cc2c/',
'genres': ['Lofi'],
'uploader': 'ender milze',
'comment_count': int,
'media_type': 'revision',
},
}, {
# Same track as above but post URL
'url': 'https://www.bandlab.com/post/07d7f906-fc96-ee11-b75e-000d3a428fff',
'md5': '46f7b43367dd268bbcf0bbe466753b2c',
'info_dict': {
'id': '02d7f906-fc96-ee11-b75e-000d3a428fff',
'ext': 'm4a',
'uploader_id': 'ender_milze',
'track': 'sweet black',
'description': 'composed by juanjn3737',
'timestamp': 1702171973,
'view_count': int,
'like_count': int,
'duration': 54.629999999999995,
'title': 'sweet black',
'upload_date': '20231210',
'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/songs/fa082beb-b856-4730-9170-a57e4e32cc2c/',
'genres': ['Lofi'],
'uploader': 'ender milze',
'comment_count': int,
'media_type': 'revision',
},
}, {
# SharedKey Example
'url': 'https://www.bandlab.com/track/048916c2-c6da-ee11-85f9-6045bd2e11f9?sharedKey=0NNWX8qYAEmI38lWAzCNDA',
'md5': '15174b57c44440e2a2008be9cae00250',
'info_dict': {
'id': '038916c2-c6da-ee11-85f9-6045bd2e11f9',
'ext': 'm4a',
'comment_count': int,
'genres': ['Other'],
'uploader_id': 'user8353034818103753',
'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/songs/51b18363-da23-4b9b-a29c-2933a3e561ca/',
'timestamp': 1709625771,
'track': 'PodcastMaerchen4b',
'duration': 468.14,
'view_count': int,
'description': 'Podcast: Neues aus der Märchenwelt',
'like_count': int,
'upload_date': '20240305',
'uploader': 'Erna Wageneder',
'title': 'PodcastMaerchen4b',
'media_type': 'revision',
},
}, {
# Different Revision selected
'url': 'https://www.bandlab.com/track/130343fc-148b-ea11-96d2-0003ffd1fc09?revId=110343fc-148b-ea11-96d2-0003ffd1fc09',
'md5': '74e055ef9325d63f37088772fbfe4454',
'info_dict': {
'id': '110343fc-148b-ea11-96d2-0003ffd1fc09',
'ext': 'm4a',
'timestamp': 1588273294,
'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/users/b612e533-e4f7-4542-9f50-3fcfd8dd822c/',
'description': 'Final Revision.',
'title': 'Replay ( Instrumental)',
'uploader': 'David R Sparks',
'uploader_id': 'davesnothome69',
'view_count': int,
'comment_count': int,
'track': 'Replay ( Instrumental)',
'genres': ['Rock'],
'upload_date': '20200430',
'like_count': int,
'duration': 279.43,
'media_type': 'revision',
},
}, {
# Video
'url': 'https://www.bandlab.com/post/5cdf9036-3857-ef11-991a-6045bd36e0d9',
'md5': '8caa2ef28e86c1dacf167293cfdbeba9',
'info_dict': {
'id': '5cdf9036-3857-ef11-991a-6045bd36e0d9',
'ext': 'mp4',
'duration': 44.705,
'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/videos/67c6cef1-cef6-40d3-831e-a55bc1dcb972/',
'comment_count': int,
'title': 'backing vocals',
'uploader_id': 'marliashya',
'uploader': 'auraa',
'like_count': int,
'description': 'backing vocals',
'media_type': 'video',
},
}, {
# Embed Example
'url': 'https://www.bandlab.com/embed/?blur=false&id=014de0a4-7d82-ea11-a94c-0003ffd19c0f',
'md5': 'a4ad05cb68c54faaed9b0a8453a8cf4a',
'info_dict': {
'id': '014de0a4-7d82-ea11-a94c-0003ffd19c0f',
'ext': 'm4a',
'comment_count': int,
'genres': ['Electronic'],
'uploader': 'Charlie Henson',
'timestamp': 1587328674,
'upload_date': '20200419',
'view_count': int,
'track': 'Positronic Meltdown',
'duration': 318.55,
'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/songs/87165bc3-5439-496e-b1f7-a9f13b541ff2/',
'description': 'Checkout my tracks at AOMX http://aomxsounds.com/',
'uploader_id': 'microfreaks',
'title': 'Positronic Meltdown',
'like_count': int,
'media_type': 'revision',
},
}, {
# Track without revisions available
'url': 'https://www.bandlab.com/track/55767ac51789ea11a94c0003ffd1fc09_2f007b0a37b94ec7a69bc25ae15108a5',
'md5': 'f05d68a3769952c2d9257c473e14c15f',
'info_dict': {
'id': '55767ac51789ea11a94c0003ffd1fc09_2f007b0a37b94ec7a69bc25ae15108a5',
'ext': 'm4a',
'track': 'insame',
'like_count': int,
'duration': 84.03,
'title': 'insame',
'view_count': int,
'comment_count': int,
'uploader': 'Sorakime',
'uploader_id': 'sorakime',
'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/users/572a351a-0f3a-4c6a-ac39-1a5defdeeb1c/',
'timestamp': 1691162128,
'upload_date': '20230804',
'media_type': 'track',
},
}, {
'url': 'https://www.bandlab.com/revision/014de0a4-7d82-ea11-a94c-0003ffd19c0f',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
'url': 'https://phantomluigi.github.io/',
'info_dict': {
'id': 'e14223c3-7871-ef11-bdfd-000d3a980db3',
'ext': 'm4a',
'view_count': int,
'upload_date': '20240913',
'uploader_id': 'phantommusicofficial',
'timestamp': 1726194897,
'uploader': 'Phantom',
'comment_count': int,
'genres': ['Progresive Rock'],
'description': 'md5:a38cd668f7a2843295ef284114f18429',
'duration': 225.23,
'like_count': int,
'title': 'Vermilion Pt. 2 (Cover)',
'track': 'Vermilion Pt. 2 (Cover)',
'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/songs/62b10750-7aef-4f42-ad08-1af52f577e97/',
'media_type': 'revision',
},
}]
def _real_extract(self, url):
display_id, url_type = self._match_valid_url(url).group('id', 'url_type')
qs = parse_qs(url)
revision_id = traverse_obj(qs, (('revId', 'id'), 0, any))
if url_type == 'revision':
revision_id = display_id
revision_data = None
if not revision_id:
post_data = self._call_api(
'posts', display_id, note='Downloading post data',
query=traverse_obj(qs, {'sharedKey': ('sharedKey', 0)}))
revision_id = traverse_obj(post_data, (('revisionId', ('revision', 'id')), {str}, any))
revision_data = traverse_obj(post_data, ('revision', {dict}))
if not revision_data and not revision_id:
post_type = post_data.get('type')
if post_type == 'Video':
return self._parse_video(post_data, url=url)
if post_type == 'Track':
return self._parse_track(post_data, url=url)
raise ExtractorError(f'Could not extract data for post type {post_type!r}')
if not revision_data:
revision_data = self._call_api(
'revisions', revision_id, note='Downloading revision data', query={'edit': 'false'})
return self._parse_revision(revision_data, url=url)
class BandlabPlaylistIE(BandlabBaseIE):
_VALID_URL = [
r'https?://(?:www\.)?bandlab.com/(?:[\w]+/)?(?P<type>albums|collections)/(?P<id>[\da-f-]+)',
r'https?://(?:www\.)?bandlab.com/(?P<type>embed)/collection/\?(?:[^#]*&)?id=(?P<id>[\da-f-]+)',
]
_EMBED_REGEX = [rf'<iframe[^>]+src=[\'"](?P<url>{_VALID_URL[1]})[\'"]']
_TESTS = [{
'url': 'https://www.bandlab.com/davesnothome69/albums/89b79ea6-de42-ed11-b495-00224845aac7',
'info_dict': {
'thumbnail': 'https://bl-prod-images.azureedge.net/v1.3/albums/69507ff3-579a-45be-afca-9e87eddec944/',
'release_date': '20221003',
'title': 'Remnants',
'album': 'Remnants',
'like_count': int,
'album_type': 'LP',
'description': 'A collection of some feel good, rock hits.',
'comment_count': int,
'view_count': int,
'id': '89b79ea6-de42-ed11-b495-00224845aac7',
'uploader': 'David R Sparks',
'uploader_id': 'davesnothome69',
},
'playlist_count': 10,
}, {
'url': 'https://www.bandlab.com/slytheband/collections/955102d4-1040-ef11-86c3-000d3a42581b',
'info_dict': {
'id': '955102d4-1040-ef11-86c3-000d3a42581b',
'timestamp': 1720762659,
'view_count': int,
'title': 'My Shit 🖤',
'uploader_id': 'slytheband',
'uploader': '𝓢𝓛𝓨',
'upload_date': '20240712',
'like_count': int,
'thumbnail': 'https://bandlabimages.azureedge.net/v1.0/collections/2c64ca12-b180-4b76-8587-7a8da76bddc8/',
},
'playlist_count': 15,
}, {
# Embeds can contain both albums and collections with the same URL pattern. This is an album
'url': 'https://www.bandlab.com/embed/collection/?id=12cc6f7f-951b-ee11-907c-00224844f303',
'info_dict': {
'id': '12cc6f7f-951b-ee11-907c-00224844f303',
'release_date': '20230706',
'description': 'This is a collection of songs I created when I had an Amiga computer.',
'view_count': int,
'title': 'Mark Salud The Amiga Collection',
'uploader_id': 'mssirmooth1962',
'comment_count': int,
'thumbnail': 'https://bl-prod-images.azureedge.net/v1.3/albums/d618bd7b-0537-40d5-bdd8-61b066e77d59/',
'like_count': int,
'uploader': 'Mark Salud',
'album': 'Mark Salud The Amiga Collection',
'album_type': 'LP',
},
'playlist_count': 24,
}, {
# Tracks without revision id
'url': 'https://www.bandlab.com/embed/collection/?id=e98aafb5-d932-ee11-b8f0-00224844c719',
'info_dict': {
'like_count': int,
'uploader_id': 'sorakime',
'comment_count': int,
'uploader': 'Sorakime',
'view_count': int,
'description': 'md5:4ec31c568a5f5a5a2b17572ea64c3825',
'release_date': '20230812',
'title': 'Art',
'album': 'Art',
'album_type': 'Album',
'id': 'e98aafb5-d932-ee11-b8f0-00224844c719',
'thumbnail': 'https://bl-prod-images.azureedge.net/v1.3/albums/20c890de-e94a-4422-828a-2da6377a13c8/',
},
'playlist_count': 13,
}, {
'url': 'https://www.bandlab.com/albums/89b79ea6-de42-ed11-b495-00224845aac7',
'only_matching': True,
}]
def _entries(self, album_data):
for post in traverse_obj(album_data, ('posts', lambda _, v: v['type'])):
post_type = post['type']
if post_type == 'Revision':
yield self._parse_revision(post.get('revision'))
elif post_type == 'Track':
yield self._parse_track(post)
elif post_type == 'Video':
yield self._parse_video(post)
else:
self.report_warning(f'Skipping unknown post type: "{post_type}"')
def _real_extract(self, url):
playlist_id, playlist_type = self._match_valid_url(url).group('id', 'type')
endpoints = {
'albums': ['albums'],
'collections': ['collections'],
'embed': ['collections', 'albums'],
}.get(playlist_type)
for endpoint in endpoints:
playlist_data = self._call_api(
endpoint, playlist_id, note=f'Downloading {endpoint[:-1]} data',
fatal=False, expected_status=404)
if not playlist_data.get('errorCode'):
playlist_type = endpoint
break
if error_code := playlist_data.get('errorCode'):
raise ExtractorError(f'Could not find playlist data. Error code: "{error_code}"')
return self.playlist_result(
self._entries(playlist_data), playlist_id,
**traverse_obj(playlist_data, {
'title': ('name', {str}),
'description': ('description', {str}),
'uploader': ('creator', 'name', {str}),
'uploader_id': ('creator', 'username', {str}),
'timestamp': ('createdOn', {parse_iso8601}),
'release_date': ('releaseDate', {lambda x: x.replace('-', '')}, filter),
'thumbnail': ('picture', ('original', 'url'), {url_or_none}, any),
'like_count': ('counters', 'likes', {int_or_none}),
'comment_count': ('counters', 'comments', {int_or_none}),
'view_count': ('counters', 'plays', {int_or_none}),
}),
**(traverse_obj(playlist_data, {
'album': ('name', {str}),
'album_type': ('type', {str}),
}) if playlist_type == 'albums' else {}))

10
yt_dlp/extractor/bbc.py
View File

@@ -1284,9 +1284,9 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
**traverse_obj(model, {
'title': ('title', {str}),
'thumbnail': ('imageUrl', {lambda u: urljoin(url, u.replace('$recipe', 'raw'))}),
'description': ('synopses', ('long', 'medium', 'short'), {str}, {lambda x: x or None}, any),
'description': ('synopses', ('long', 'medium', 'short'), {str}, filter, any),
'duration': ('versions', 0, 'duration', {int}),
'timestamp': ('versions', 0, 'availableFrom', {functools.partial(int_or_none, scale=1000)}),
'timestamp': ('versions', 0, 'availableFrom', {int_or_none(scale=1000)}),
}),
}
@@ -1386,7 +1386,7 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
formats = traverse_obj(media_data, ('playlist', lambda _, v: url_or_none(v['url']), {
'url': ('url', {url_or_none}),
'ext': ('format', {str}),
'tbr': ('bitrate', {functools.partial(int_or_none, scale=1000)}),
'tbr': ('bitrate', {int_or_none(scale=1000)}),
}))
if formats:
entry = {
@@ -1398,7 +1398,7 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
'title': ('title', {str}),
'thumbnail': ('imageUrl', {lambda u: urljoin(url, u.replace('$recipe', 'raw'))}),
'description': ('synopses', ('long', 'medium', 'short'), {str}, any),
'timestamp': ('firstPublished', {functools.partial(int_or_none, scale=1000)}),
'timestamp': ('firstPublished', {int_or_none(scale=1000)}),
}),
}
done = True
@@ -1428,7 +1428,7 @@ class BBCIE(BBCCoUkIE): # XXX: Do not subclass from concrete IE
if not entry.get('timestamp'):
entry['timestamp'] = traverse_obj(next_data, (
..., 'contents', is_type('timestamp'), 'model',
'timestamp', {functools.partial(int_or_none, scale=1000)}, any))
'timestamp', {int_or_none(scale=1000)}, any))
entries.append(entry)
return self.playlist_result(
entries, playlist_id, playlist_title, playlist_description)

66
yt_dlp/extractor/bfmtv.py
View File

@@ -1,18 +1,33 @@
import re
from .common import InfoExtractor
from ..utils import extract_attributes
from ..utils import ExtractorError, extract_attributes
class BFMTVBaseIE(InfoExtractor):
_VALID_URL_BASE = r'https?://(?:www\.|rmc\.)?bfmtv\.com/'
_VALID_URL_TMPL = _VALID_URL_BASE + r'(?:[^/]+/)*[^/?&#]+_%s[A-Z]-(?P<id>\d{12})\.html'
_VIDEO_BLOCK_REGEX = r'(<div[^>]+class="video_block[^"]*"[^>]*>)'
_VIDEO_BLOCK_REGEX = r'(<div[^>]+class="video_block[^"]*"[^>]*>.*?</div>)'
_VIDEO_ELEMENT_REGEX = r'(<video-js[^>]+>)'
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s'
def _brightcove_url_result(self, video_id, video_block):
account_id = video_block.get('accountid') or '876450612001'
player_id = video_block.get('playerid') or 'I2qBTln4u'
def _extract_video(self, video_block):
video_element = self._search_regex(
self._VIDEO_ELEMENT_REGEX, video_block, 'video element', default=None)
if video_element:
video_element_attrs = extract_attributes(video_element)
video_id = video_element_attrs.get('data-video-id')
if not video_id:
return
account_id = video_element_attrs.get('data-account') or '876450610001'
player_id = video_element_attrs.get('adjustplayer') or '19dszYXgm'
else:
video_block_attrs = extract_attributes(video_block)
video_id = video_block_attrs.get('videoid')
if not video_id:
return
account_id = video_block_attrs.get('accountid') or '876630703001'
player_id = video_block_attrs.get('playerid') or 'KbPwEbuHx'
return self.url_result(
self.BRIGHTCOVE_URL_TEMPLATE % (account_id, player_id, video_id),
'BrightcoveNew', video_id)
@@ -40,23 +55,25 @@ class BFMTVIE(BFMTVBaseIE):
def _real_extract(self, url):
bfmtv_id = self._match_id(url)
webpage = self._download_webpage(url, bfmtv_id)
video_block = extract_attributes(self._search_regex(
video = self._extract_video(self._search_regex(
self._VIDEO_BLOCK_REGEX, webpage, 'video block'))
return self._brightcove_url_result(video_block['videoid'], video_block)
if not video:
raise ExtractorError('Failed to extract video')
return video
class BFMTVLiveIE(BFMTVIE): # XXX: Do not subclass from concrete IE
class BFMTVLiveIE(BFMTVBaseIE):
IE_NAME = 'bfmtv:live'
_VALID_URL = BFMTVBaseIE._VALID_URL_BASE + '(?P<id>(?:[^/]+/)?en-direct)'
_TESTS = [{
'url': 'https://www.bfmtv.com/en-direct/',
'info_dict': {
'id': '5615950982001',
'id': '6346069778112',
'ext': 'mp4',
'title': r're:^le direct BFMTV WEB \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
'title': r're:^Le Live BFM TV \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
'uploader_id': '876450610001',
'upload_date': '20220926',
'timestamp': 1664207191,
'upload_date': '20240202',
'timestamp': 1706887572,
'live_status': 'is_live',
'thumbnail': r're:https://.+/image\.jpg',
'tags': [],
@@ -69,6 +86,15 @@ class BFMTVLiveIE(BFMTVIE): # XXX: Do not subclass from concrete IE
'only_matching': True,
}]
def _real_extract(self, url):
bfmtv_id = self._match_id(url)
webpage = self._download_webpage(url, bfmtv_id)
video = self._extract_video(self._search_regex(
self._VIDEO_BLOCK_REGEX, webpage, 'video block'))
if not video:
raise ExtractorError('Failed to extract video')
return video
class BFMTVArticleIE(BFMTVBaseIE):
IE_NAME = 'bfmtv:article'
@@ -102,18 +128,16 @@ class BFMTVArticleIE(BFMTVBaseIE):
},
}]
def _entries(self, webpage):
for video_block_el in re.findall(self._VIDEO_BLOCK_REGEX, webpage):
video = self._extract_video(video_block_el)
if video:
yield video
def _real_extract(self, url):
bfmtv_id = self._match_id(url)
webpage = self._download_webpage(url, bfmtv_id)
entries = []
for video_block_el in re.findall(self._VIDEO_BLOCK_REGEX, webpage):
video_block = extract_attributes(video_block_el)
video_id = video_block.get('videoid')
if not video_id:
continue
entries.append(self._brightcove_url_result(video_id, video_block))
return self.playlist_result(
entries, bfmtv_id, self._og_search_title(webpage, fatal=False),
self._entries(webpage), bfmtv_id, self._og_search_title(webpage, fatal=False),
self._html_search_meta(['og:description', 'description'], webpage))

3
yt_dlp/extractor/bibeltv.py
View File

@@ -1,4 +1,3 @@
import functools
from .common import InfoExtractor
from ..utils import (
@@ -50,7 +49,7 @@ class BibelTVBaseIE(InfoExtractor):
**traverse_obj(data, {
'title': 'title',
'description': 'description',
'duration': ('duration', {functools.partial(int_or_none, scale=1000)}),
'duration': ('duration', {int_or_none(scale=1000)}),
'timestamp': ('schedulingStart', {parse_iso8601}),
'season_number': 'seasonNumber',
'episode_number': 'episodeNumber',

6
yt_dlp/extractor/bilibili.py
View File

@@ -109,7 +109,7 @@ class BilibiliBaseIE(InfoExtractor):
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)}),
'duration': ('length', {float_or_none(scale=1000)}),
'filesize': ('size', {int_or_none}),
}))
if fragments:
@@ -124,7 +124,7 @@ class BilibiliBaseIE(InfoExtractor):
'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)}),
'duration': ('timelength', {float_or_none(scale=1000)}),
}),
**parse_resolution(format_names.get(play_info.get('quality'))),
})
@@ -1585,7 +1585,7 @@ class BilibiliPlaylistIE(BilibiliSpaceListBaseIE):
'title': ('title', {str}),
'uploader': ('upper', 'name', {str}),
'uploader_id': ('upper', 'mid', {str_or_none}),
'timestamp': ('ctime', {int_or_none}, {lambda x: x or None}),
'timestamp': ('ctime', {int_or_none}, filter),
'thumbnail': ('cover', {url_or_none}),
})),
}

388
yt_dlp/extractor/bluesky.py Normal file
View File

@@ -0,0 +1,388 @@
from .common import InfoExtractor
from ..utils import (
ExtractorError,
format_field,
int_or_none,
mimetype2ext,
orderedSet,
parse_iso8601,
truncate_string,
update_url_query,
url_basename,
url_or_none,
variadic,
)
from ..utils.traversal import traverse_obj
class BlueskyIE(InfoExtractor):
_VALID_URL = [
r'https?://(?:www\.)?(?:bsky\.app|main\.bsky\.dev)/profile/(?P<handle>[\w.:%-]+)/post/(?P<id>\w+)',
r'at://(?P<handle>[\w.:%-]+)/app\.bsky\.feed\.post/(?P<id>\w+)',
]
_TESTS = [{
'url': 'https://bsky.app/profile/blu3blue.bsky.social/post/3l4omssdl632g',
'md5': '375539c1930ab05d15585ed772ab54fd',
'info_dict': {
'id': '3l4omssdl632g',
'ext': 'mp4',
'uploader': 'Blu3Blu3Lilith',
'uploader_id': 'blu3blue.bsky.social',
'uploader_url': 'https://bsky.app/profile/blu3blue.bsky.social',
'channel_id': 'did:plc:pzdr5ylumf7vmvwasrpr5bf2',
'channel_url': 'https://bsky.app/profile/did:plc:pzdr5ylumf7vmvwasrpr5bf2',
'thumbnail': r're:https://video.bsky.app/watch/.*\.jpg$',
'title': 'OMG WE HAVE VIDEOS NOW',
'description': 'OMG WE HAVE VIDEOS NOW',
'upload_date': '20240921',
'timestamp': 1726940605,
'like_count': int,
'repost_count': int,
'comment_count': int,
'tags': [],
},
}, {
'url': 'https://bsky.app/profile/bsky.app/post/3l3vgf77uco2g',
'md5': 'b9e344fdbce9f2852c668a97efefb105',
'info_dict': {
'id': '3l3vgf77uco2g',
'ext': 'mp4',
'uploader': 'Bluesky',
'uploader_id': 'bsky.app',
'uploader_url': 'https://bsky.app/profile/bsky.app',
'channel_id': 'did:plc:z72i7hdynmk6r22z27h6tvur',
'channel_url': 'https://bsky.app/profile/did:plc:z72i7hdynmk6r22z27h6tvur',
'thumbnail': r're:https://video.bsky.app/watch/.*\.jpg$',
'title': 'Bluesky now has video! Update your app to versi...',
'alt_title': 'Bluesky video feature announcement',
'description': r're:(?s)Bluesky now has video! .{239}',
'upload_date': '20240911',
'timestamp': 1726074716,
'like_count': int,
'repost_count': int,
'comment_count': int,
'tags': [],
'subtitles': {
'en': 'mincount:1',
},
},
}, {
'url': 'https://main.bsky.dev/profile/souris.moe/post/3l4qhp7bcs52c',
'md5': '5f2df8c200b5633eb7fb2c984d29772f',
'info_dict': {
'id': '3l4qhp7bcs52c',
'ext': 'mp4',
'uploader': 'souris',
'uploader_id': 'souris.moe',
'uploader_url': 'https://bsky.app/profile/souris.moe',
'channel_id': 'did:plc:tj7g244gl5v6ai6cm4f4wlqp',
'channel_url': 'https://bsky.app/profile/did:plc:tj7g244gl5v6ai6cm4f4wlqp',
'thumbnail': r're:https://video.bsky.app/watch/.*\.jpg$',
'title': 'Bluesky video #3l4qhp7bcs52c',
'upload_date': '20240922',
'timestamp': 1727003838,
'like_count': int,
'repost_count': int,
'comment_count': int,
'tags': [],
},
}, {
'url': 'https://bsky.app/profile/de1.pds.tentacle.expert/post/3l3w4tnezek2e',
'md5': '1af9c7fda061cf7593bbffca89e43d1c',
'info_dict': {
'id': '3l3w4tnezek2e',
'ext': 'mp4',
'uploader': 'clean',
'uploader_id': 'de1.pds.tentacle.expert',
'uploader_url': 'https://bsky.app/profile/de1.pds.tentacle.expert',
'channel_id': 'did:web:de1.tentacle.expert',
'channel_url': 'https://bsky.app/profile/did:web:de1.tentacle.expert',
'thumbnail': r're:https://video.bsky.app/watch/.*\.jpg$',
'title': 'Bluesky video #3l3w4tnezek2e',
'upload_date': '20240911',
'timestamp': 1726098823,
'like_count': int,
'repost_count': int,
'comment_count': int,
'tags': [],
},
}, {
'url': 'https://bsky.app/profile/yunayuispink.bsky.social/post/3l7gqcfes742o',
'info_dict': {
'id': 'XxK3t_5V3ao',
'ext': 'mp4',
'uploader': 'yunayu',
'uploader_id': '@yunayuispink',
'uploader_url': 'https://www.youtube.com/@yunayuispink',
'channel': 'yunayu',
'channel_id': 'UCPLvXnHa7lTyNoR_dGsU14w',
'channel_url': 'https://www.youtube.com/channel/UCPLvXnHa7lTyNoR_dGsU14w',
'thumbnail': 'https://i.ytimg.com/vi_webp/XxK3t_5V3ao/maxresdefault.webp',
'description': r're:Have a good goodx10000day',
'title': '5min vs 5hours drawing',
'availability': 'public',
'live_status': 'not_live',
'playable_in_embed': True,
'upload_date': '20241026',
'timestamp': 1729967784,
'duration': 321,
'age_limit': 0,
'like_count': int,
'view_count': int,
'comment_count': int,
'channel_follower_count': int,
'categories': ['Entertainment'],
'tags': [],
},
'add_ie': ['Youtube'],
}, {
'url': 'https://bsky.app/profile/endshark.bsky.social/post/3jzxjkcemae2m',
'info_dict': {
'id': '222792849',
'ext': 'mp3',
'uploader': 'LASERBAT',
'uploader_id': 'laserbatx',
'uploader_url': 'https://laserbatx.bandcamp.com',
'artists': ['LASERBAT'],
'album_artists': ['LASERBAT'],
'album': 'Hari Nezumi [EP]',
'track': 'Forward to the End',
'title': 'LASERBAT - Forward to the End',
'thumbnail': 'https://f4.bcbits.com/img/a2507705510_5.jpg',
'duration': 228.571,
'track_id': '222792849',
'release_date': '20230423',
'upload_date': '20230423',
'timestamp': 1682276040.0,
'release_timestamp': 1682276040.0,
'track_number': 1,
},
'add_ie': ['Bandcamp'],
}, {
'url': 'https://bsky.app/profile/dannybhoix.bsky.social/post/3l6oe5mtr2c2j',
'md5': 'b9e344fdbce9f2852c668a97efefb105',
'info_dict': {
'id': '3l3vgf77uco2g',
'ext': 'mp4',
'uploader': 'Bluesky',
'uploader_id': 'bsky.app',
'uploader_url': 'https://bsky.app/profile/bsky.app',
'channel_id': 'did:plc:z72i7hdynmk6r22z27h6tvur',
'channel_url': 'https://bsky.app/profile/did:plc:z72i7hdynmk6r22z27h6tvur',
'thumbnail': r're:https://video.bsky.app/watch/.*\.jpg$',
'title': 'Bluesky now has video! Update your app to versi...',
'alt_title': 'Bluesky video feature announcement',
'description': r're:(?s)Bluesky now has video! .{239}',
'upload_date': '20240911',
'timestamp': 1726074716,
'like_count': int,
'repost_count': int,
'comment_count': int,
'tags': [],
'subtitles': {
'en': 'mincount:1',
},
},
}, {
'url': 'https://bsky.app/profile/alt.bun.how/post/3l7rdfxhyds2f',
'md5': '8775118b235cf9fa6b5ad30f95cda75c',
'info_dict': {
'id': '3l7rdfxhyds2f',
'ext': 'mp4',
'uploader': 'cinnamon',
'uploader_id': 'alt.bun.how',
'uploader_url': 'https://bsky.app/profile/alt.bun.how',
'channel_id': 'did:plc:7x6rtuenkuvxq3zsvffp2ide',
'channel_url': 'https://bsky.app/profile/did:plc:7x6rtuenkuvxq3zsvffp2ide',
'thumbnail': r're:https://video.bsky.app/watch/.*\.jpg$',
'title': 'crazy that i look like this tbh',
'description': 'crazy that i look like this tbh',
'upload_date': '20241030',
'timestamp': 1730332128,
'like_count': int,
'repost_count': int,
'comment_count': int,
'tags': ['sexual'],
'age_limit': 18,
},
}, {
'url': 'at://did:plc:ia76kvnndjutgedggx2ibrem/app.bsky.feed.post/3l6zrz6zyl2dr',
'md5': '71b0eb6d85d03145e6af6642c7fc6d78',
'info_dict': {
'id': '3l6zrz6zyl2dr',
'ext': 'mp4',
'uploader': 'mary🐇',
'uploader_id': 'mary.my.id',
'uploader_url': 'https://bsky.app/profile/mary.my.id',
'channel_id': 'did:plc:ia76kvnndjutgedggx2ibrem',
'channel_url': 'https://bsky.app/profile/did:plc:ia76kvnndjutgedggx2ibrem',
'thumbnail': r're:https://video.bsky.app/watch/.*\.jpg$',
'title': 'Bluesky video #3l6zrz6zyl2dr',
'upload_date': '20241021',
'timestamp': 1729523172,
'like_count': int,
'repost_count': int,
'comment_count': int,
'tags': [],
},
}, {
'url': 'https://bsky.app/profile/purpleicetea.bsky.social/post/3l7gv55dc2o2w',
'info_dict': {
'id': '3l7gv55dc2o2w',
},
'playlist': [{
'info_dict': {
'id': '3l7gv55dc2o2w',
'ext': 'mp4',
'upload_date': '20241026',
'description': 'One of my favorite videos',
'comment_count': int,
'uploader_url': 'https://bsky.app/profile/purpleicetea.bsky.social',
'uploader': 'Purple.Ice.Tea',
'thumbnail': r're:https://video.bsky.app/watch/.*\.jpg$',
'channel_url': 'https://bsky.app/profile/did:plc:bjh5ffwya5f53dfy47dezuwx',
'like_count': int,
'channel_id': 'did:plc:bjh5ffwya5f53dfy47dezuwx',
'repost_count': int,
'timestamp': 1729973202,
'tags': [],
'uploader_id': 'purpleicetea.bsky.social',
'title': 'One of my favorite videos',
},
}, {
'info_dict': {
'id': '3l77u64l7le2e',
'ext': 'mp4',
'title': 'hearing people on twitter say that bluesky isn\'...',
'like_count': int,
'uploader_id': 'thafnine.net',
'uploader_url': 'https://bsky.app/profile/thafnine.net',
'upload_date': '20241024',
'channel_url': 'https://bsky.app/profile/did:plc:6ttyq36rhiyed7wu3ws7dmqj',
'description': r're:(?s)hearing people on twitter say that bluesky .{93}',
'tags': [],
'alt_title': 'md5:9b1ee1937fb3d1a81e932f9ec14d560e',
'uploader': 'T9',
'channel_id': 'did:plc:6ttyq36rhiyed7wu3ws7dmqj',
'thumbnail': r're:https://video.bsky.app/watch/.*\.jpg$',
'timestamp': 1729731642,
'comment_count': int,
'repost_count': int,
},
}],
}]
_BLOB_URL_TMPL = '{}/xrpc/com.atproto.sync.getBlob'
def _get_service_endpoint(self, did, video_id):
if did.startswith('did:web:'):
url = f'https://{did[8:]}/.well-known/did.json'
else:
url = f'https://plc.directory/{did}'
services = self._download_json(
url, video_id, 'Fetching service endpoint', 'Falling back to bsky.social', fatal=False)
return traverse_obj(
services, ('service', lambda _, x: x['type'] == 'AtprotoPersonalDataServer',
'serviceEndpoint', {url_or_none}, any)) or 'https://bsky.social'
def _real_extract(self, url):
handle, video_id = self._match_valid_url(url).group('handle', 'id')
post = self._download_json(
'https://public.api.bsky.app/xrpc/app.bsky.feed.getPostThread',
video_id, query={
'uri': f'at://{handle}/app.bsky.feed.post/{video_id}',
'depth': 0,
'parentHeight': 0,
})['thread']['post']
entries = []
# app.bsky.embed.video.view/app.bsky.embed.external.view
entries.extend(self._extract_videos(post, video_id))
# app.bsky.embed.recordWithMedia.view
entries.extend(self._extract_videos(
post, video_id, embed_path=('embed', 'media'), record_subpath=('embed', 'media')))
# app.bsky.embed.record.view
if nested_post := traverse_obj(post, ('embed', 'record', ('record', None), {dict}, any)):
entries.extend(self._extract_videos(
nested_post, video_id, embed_path=('embeds', 0), record_path='value'))
if not entries:
raise ExtractorError('No video could be found in this post', expected=True)
if len(entries) == 1:
return entries[0]
return self.playlist_result(entries, video_id)
@staticmethod
def _build_profile_url(path):
return format_field(path, None, 'https://bsky.app/profile/%s', default=None)
def _extract_videos(self, root, video_id, embed_path='embed', record_path='record', record_subpath='embed'):
embed_path = variadic(embed_path, (str, bytes, dict, set))
record_path = variadic(record_path, (str, bytes, dict, set))
record_subpath = variadic(record_subpath, (str, bytes, dict, set))
entries = []
if external_uri := traverse_obj(root, (
((*record_path, *record_subpath), embed_path), 'external', 'uri', {url_or_none}, any)):
entries.append(self.url_result(external_uri))
if playlist := traverse_obj(root, (*embed_path, 'playlist', {url_or_none})):
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
playlist, video_id, 'mp4', m3u8_id='hls', fatal=False)
else:
return entries
video_cid = traverse_obj(
root, (*embed_path, 'cid', {str}),
(*record_path, *record_subpath, 'video', 'ref', '$link', {str}))
did = traverse_obj(root, ('author', 'did', {str}))
if did and video_cid:
endpoint = self._get_service_endpoint(did, video_id)
formats.append({
'format_id': 'blob',
'url': update_url_query(
self._BLOB_URL_TMPL.format(endpoint), {'did': did, 'cid': video_cid}),
**traverse_obj(root, (*embed_path, 'aspectRatio', {
'width': ('width', {int_or_none}),
'height': ('height', {int_or_none}),
})),
**traverse_obj(root, (*record_path, *record_subpath, 'video', {
'filesize': ('size', {int_or_none}),
'ext': ('mimeType', {mimetype2ext}),
})),
})
for sub_data in traverse_obj(root, (
*record_path, *record_subpath, 'captions', lambda _, v: v['file']['ref']['$link'])):
subtitles.setdefault(sub_data.get('lang') or 'und', []).append({
'url': update_url_query(
self._BLOB_URL_TMPL.format(endpoint), {'did': did, 'cid': sub_data['file']['ref']['$link']}),
'ext': traverse_obj(sub_data, ('file', 'mimeType', {mimetype2ext})),
})
entries.append({
'id': video_id,
'formats': formats,
'subtitles': subtitles,
**traverse_obj(root, {
'id': ('uri', {url_basename}),
'thumbnail': (*embed_path, 'thumbnail', {url_or_none}),
'alt_title': (*embed_path, 'alt', {str}, filter),
'uploader': ('author', 'displayName', {str}),
'uploader_id': ('author', 'handle', {str}),
'uploader_url': ('author', 'handle', {self._build_profile_url}),
'channel_id': ('author', 'did', {str}),
'channel_url': ('author', 'did', {self._build_profile_url}),
'like_count': ('likeCount', {int_or_none}),
'repost_count': ('repostCount', {int_or_none}),
'comment_count': ('replyCount', {int_or_none}),
'timestamp': ('indexedAt', {parse_iso8601}),
'tags': ('labels', ..., 'val', {str}, all, {orderedSet}),
'age_limit': (
'labels', ..., 'val', {lambda x: 18 if x in ('sexual', 'porn', 'graphic-media') else None}, any),
'description': (*record_path, 'text', {str}, filter),
'title': (*record_path, 'text', {lambda x: x.replace('\n', ' ')}, {truncate_string(left=50)}),
}),
})
return entries

65
yt_dlp/extractor/bpb.py
View File

@@ -1,35 +1,20 @@
import functools
import re
from .common import InfoExtractor
from ..utils import (
clean_html,
extract_attributes,
get_element_text_and_html_by_tag,
get_elements_by_class,
join_nonempty,
js_to_json,
mimetype2ext,
unified_strdate,
url_or_none,
urljoin,
variadic,
)
from ..utils.traversal import traverse_obj
def html_get_element(tag=None, cls=None):
assert tag or cls, 'One of tag or class is required'
if cls:
func = functools.partial(get_elements_by_class, cls, tag=tag)
else:
func = functools.partial(get_element_text_and_html_by_tag, tag)
def html_get_element_wrapper(html):
return variadic(func(html))[0]
return html_get_element_wrapper
from ..utils.traversal import (
find_element,
traverse_obj,
)
class BpbIE(InfoExtractor):
@@ -41,12 +26,12 @@ class BpbIE(InfoExtractor):
'info_dict': {
'id': '297',
'ext': 'mp4',
'creator': 'Kooperative Berlin',
'description': 'md5:f4f75885ba009d3e2b156247a8941ce6',
'release_date': '20160115',
'creators': ['Kooperative Berlin'],
'description': r're:Joachim Gauck, .*\n\nKamera: .*',
'release_date': '20150716',
'series': 'Interview auf dem Geschichtsforum 1989 | 2009',
'tags': ['Friedliche Revolution', 'Erinnerungskultur', 'Vergangenheitspolitik', 'DDR 1949 - 1990', 'Freiheitsrecht', 'BStU', 'Deutschland'],
'thumbnail': 'https://www.bpb.de/cache/images/7/297_teaser_16x9_1240.jpg?8839D',
'tags': [],
'thumbnail': r're:https?://www\.bpb\.de/cache/images/7/297_teaser_16x9_1240\.jpg.*',
'title': 'Joachim Gauck zu 1989 und die Erinnerung an die DDR',
'uploader': 'Bundeszentrale für politische Bildung',
},
@@ -55,11 +40,12 @@ class BpbIE(InfoExtractor):
'info_dict': {
'id': '522184',
'ext': 'mp4',
'creator': 'Institute for Strategic Dialogue Germany gGmbH (ISD)',
'creators': ['Institute for Strategic Dialogue Germany gGmbH (ISD)'],
'description': 'md5:f83c795ff8f825a69456a9e51fc15903',
'release_date': '20230621',
'tags': ['Desinformation', 'Ukraine', 'Russland', 'Geflüchtete'],
'thumbnail': 'https://www.bpb.de/cache/images/4/522184_teaser_16x9_1240.png?EABFB',
'series': 'Narrative über den Krieg Russlands gegen die Ukraine (NUK)',
'tags': [],
'thumbnail': r're:https://www\.bpb\.de/cache/images/4/522184_teaser_16x9_1240\.png.*',
'title': 'md5:9b01ccdbf58dbf9e5c9f6e771a803b1c',
'uploader': 'Bundeszentrale für politische Bildung',
},
@@ -68,11 +54,12 @@ class BpbIE(InfoExtractor):
'info_dict': {
'id': '518789',
'ext': 'mp4',
'creator': 'Institute for Strategic Dialogue Germany gGmbH (ISD)',
'creators': ['Institute for Strategic Dialogue Germany gGmbH (ISD)'],
'description': 'md5:85228aed433e84ff0ff9bc582abd4ea8',
'release_date': '20230302',
'tags': ['Desinformation', 'Ukraine', 'Russland', 'Geflüchtete'],
'thumbnail': 'https://www.bpb.de/cache/images/9/518789_teaser_16x9_1240.jpeg?56D0D',
'series': 'Narrative über den Krieg Russlands gegen die Ukraine (NUK)',
'tags': [],
'thumbnail': r're:https://www\.bpb\.de/cache/images/9/518789_teaser_16x9_1240\.jpeg.*',
'title': 'md5:3e956f264bb501f6383f10495a401da4',
'uploader': 'Bundeszentrale für politische Bildung',
},
@@ -84,12 +71,12 @@ class BpbIE(InfoExtractor):
'info_dict': {
'id': '315813',
'ext': 'mp3',
'creator': 'Axel Schröder',
'creators': ['Axel Schröder'],
'description': 'md5:eda9d1af34e5912efef5baf54fba4427',
'release_date': '20200921',
'series': 'Auf Endlagersuche. Der deutsche Weg zu einem sicheren Atommülllager',
'tags': ['Atomenergie', 'Endlager', 'hoch-radioaktiver Abfall', 'Endlagersuche', 'Atommüll', 'Atomendlager', 'Gorleben', 'Deutschland'],
'thumbnail': 'https://www.bpb.de/cache/images/3/315813_teaser_16x9_1240.png?92A94',
'thumbnail': r're:https://www\.bpb\.de/cache/images/3/315813_teaser_16x9_1240\.png.*',
'title': 'Folge 1: Eine Einführung',
'uploader': 'Bundeszentrale für politische Bildung',
},
@@ -98,12 +85,12 @@ class BpbIE(InfoExtractor):
'info_dict': {
'id': '517806',
'ext': 'mp3',
'creator': 'Bundeszentrale für politische Bildung',
'creators': ['Bundeszentrale für politische Bildung'],
'description': 'md5:594689600e919912aade0b2871cc3fed',
'release_date': '20230127',
'series': 'Vorträge des Fachtags "Modernisierer. Grenzgänger. Anstifter. Sechs Jahrzehnte \'Neue Rechte\'"',
'tags': ['Rechtsextremismus', 'Konservatismus', 'Konservativismus', 'neue Rechte', 'Rechtspopulismus', 'Schnellroda', 'Deutschland'],
'thumbnail': 'https://www.bpb.de/cache/images/6/517806_teaser_16x9_1240.png?7A7A0',
'thumbnail': r're:https://www\.bpb\.de/cache/images/6/517806_teaser_16x9_1240\.png.*',
'title': 'Die Weltanschauung der "Neuen Rechten"',
'uploader': 'Bundeszentrale für politische Bildung',
},
@@ -147,7 +134,7 @@ class BpbIE(InfoExtractor):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title_result = traverse_obj(webpage, ({html_get_element(cls='opening-header__title')}, {self._TITLE_RE.match}))
title_result = traverse_obj(webpage, ({find_element(cls='opening-header__title')}, {self._TITLE_RE.match}))
json_lds = list(self._yield_json_ld(webpage, video_id, fatal=False))
return {
@@ -156,15 +143,15 @@ class BpbIE(InfoExtractor):
# This metadata could be interpreted otherwise, but it fits "series" the most
'series': traverse_obj(title_result, ('series', {str.strip})) or None,
'description': join_nonempty(*traverse_obj(webpage, [(
{html_get_element(cls='opening-intro')},
[{html_get_element(tag='bpb-accordion-item')}, {html_get_element(cls='text-content')}],
{find_element(cls='opening-intro')},
[{find_element(tag='bpb-accordion-item')}, {find_element(cls='text-content')}],
), {clean_html}]), delim='\n\n') or None,
'creator': self._html_search_meta('author', webpage),
'creators': traverse_obj(self._html_search_meta('author', webpage), all),
'uploader': self._html_search_meta('publisher', webpage),
'release_date': unified_strdate(self._html_search_meta('date', webpage)),
'tags': traverse_obj(json_lds, (..., 'keywords', {lambda x: x.split(',')}, ...)),
**traverse_obj(self._parse_vue_attributes('bpb-player', webpage, video_id), {
'formats': (':sources', ..., {self._process_source}),
'thumbnail': ('poster', {lambda x: urljoin(url, x)}),
'thumbnail': ('poster', {urljoin(url)}),
}),
}

9
yt_dlp/extractor/bravotv.py
View File

@@ -145,10 +145,9 @@ class BravoTVIE(AdobePassIE):
tp_metadata = self._download_json(
update_url_query(tp_url, {'format': 'preview'}), video_id, fatal=False)
seconds_or_none = lambda x: float_or_none(x, 1000)
chapters = traverse_obj(tp_metadata, ('chapters', ..., {
'start_time': ('startTime', {seconds_or_none}),
'end_time': ('endTime', {seconds_or_none}),
'start_time': ('startTime', {float_or_none(scale=1000)}),
'end_time': ('endTime', {float_or_none(scale=1000)}),
}))
# prune pointless single chapters that span the entire duration from short videos
if len(chapters) == 1 and not traverse_obj(chapters, (0, 'end_time')):
@@ -168,8 +167,8 @@ class BravoTVIE(AdobePassIE):
**merge_dicts(traverse_obj(tp_metadata, {
'title': 'title',
'description': 'description',
'duration': ('duration', {seconds_or_none}),
'timestamp': ('pubDate', {seconds_or_none}),
'duration': ('duration', {float_or_none(scale=1000)}),
'timestamp': ('pubDate', {float_or_none(scale=1000)}),
'season_number': (('pl1$seasonNumber', 'nbcu$seasonNumber'), {int_or_none}),
'episode_number': (('pl1$episodeNumber', 'nbcu$episodeNumber'), {int_or_none}),
'series': (('pl1$show', 'nbcu$show'), (None, ...), {str}),

11
yt_dlp/extractor/bundestag.py
View File

@@ -8,11 +8,13 @@ from ..utils import (
bug_reports_message,
clean_html,
format_field,
get_element_text_and_html_by_tag,
int_or_none,
url_or_none,
)
from ..utils.traversal import traverse_obj
from ..utils.traversal import (
find_element,
traverse_obj,
)
class BundestagIE(InfoExtractor):
@@ -115,9 +117,8 @@ class BundestagIE(InfoExtractor):
note='Downloading metadata overlay', fatal=False,
), {
'title': (
{functools.partial(get_element_text_and_html_by_tag, 'h3')}, 0,
{functools.partial(re.sub, r'<span[^>]*>[^<]+</span>', '')}, {clean_html}),
'description': ({functools.partial(get_element_text_and_html_by_tag, 'p')}, 0, {clean_html}),
{find_element(tag='h3')}, {functools.partial(re.sub, r'<span[^>]*>[^<]+</span>', '')}, {clean_html}),
'description': ({find_element(tag='p')}, {clean_html}),
}))
return result

4
yt_dlp/extractor/caffeinetv.py
View File

@@ -53,7 +53,7 @@ class CaffeineTVIE(InfoExtractor):
'like_count': ('like_count', {int_or_none}),
'view_count': ('view_count', {int_or_none}),
'comment_count': ('comment_count', {int_or_none}),
'tags': ('tags', ..., {str}, {lambda x: x or None}),
'tags': ('tags', ..., {str}, filter),
'uploader': ('user', 'name', {str}),
'uploader_id': (((None, 'user'), 'username'), {str}, any),
'is_live': ('is_live', {bool}),
@@ -62,7 +62,7 @@ class CaffeineTVIE(InfoExtractor):
'title': ('broadcast_title', {str}),
'duration': ('content_duration', {int_or_none}),
'timestamp': ('broadcast_start_time', {parse_iso8601}),
'thumbnail': ('preview_image_path', {lambda x: urljoin(url, x)}),
'thumbnail': ('preview_image_path', {urljoin(url)}),
}),
'age_limit': {
# assume Apple Store ratings: https://en.wikipedia.org/wiki/Mobile_software_content_rating_system

8
yt_dlp/extractor/cbc.py
View File

@@ -453,8 +453,8 @@ class CBCPlayerIE(InfoExtractor):
chapters = traverse_obj(data, (
'media', 'chapters', lambda _, v: float(v['startTime']) is not None, {
'start_time': ('startTime', {functools.partial(float_or_none, scale=1000)}),
'end_time': ('endTime', {functools.partial(float_or_none, scale=1000)}),
'start_time': ('startTime', {float_or_none(scale=1000)}),
'end_time': ('endTime', {float_or_none(scale=1000)}),
'title': ('name', {str}),
}))
# Filter out pointless single chapters with start_time==0 and no end_time
@@ -465,8 +465,8 @@ class CBCPlayerIE(InfoExtractor):
**traverse_obj(data, {
'title': ('title', {str}),
'description': ('description', {str.strip}),
'thumbnail': ('image', 'url', {url_or_none}, {functools.partial(update_url, query=None)}),
'timestamp': ('publishedAt', {functools.partial(float_or_none, scale=1000)}),
'thumbnail': ('image', 'url', {url_or_none}, {update_url(query=None)}),
'timestamp': ('publishedAt', {float_or_none(scale=1000)}),
'media_type': ('media', 'clipType', {str}),
'series': ('showName', {str}),
'season_number': ('media', 'season', {int_or_none}),

2
yt_dlp/extractor/cbsnews.py
View File

@@ -96,7 +96,7 @@ class CBSNewsBaseIE(InfoExtractor):
**traverse_obj(item, {
'title': (None, ('fulltitle', 'title')),
'description': 'dek',
'timestamp': ('timestamp', {lambda x: float_or_none(x, 1000)}),
'timestamp': ('timestamp', {float_or_none(scale=1000)}),
'duration': ('duration', {float_or_none}),
'subtitles': ('captions', {get_subtitles}),
'thumbnail': ('images', ('hd', 'sd'), {url_or_none}),

64
yt_dlp/extractor/chaturbate.py
View File

@@ -5,11 +5,12 @@ from ..utils import (
ExtractorError,
lowercase_escape,
url_or_none,
urlencode_postdata,
)
class ChaturbateIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?:fullvideo/?\?.*?\bb=)?(?P<id>[^/?&#]+)'
_VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.(?P<tld>com|eu|global)/(?:fullvideo/?\?.*?\bb=)?(?P<id>[^/?&#]+)'
_TESTS = [{
'url': 'https://www.chaturbate.com/siswet19/',
'info_dict': {
@@ -29,16 +30,59 @@ class ChaturbateIE(InfoExtractor):
}, {
'url': 'https://en.chaturbate.com/siswet19/',
'only_matching': True,
}, {
'url': 'https://chaturbate.eu/siswet19/',
'only_matching': True,
}, {
'url': 'https://chaturbate.eu/fullvideo/?b=caylin',
'only_matching': True,
}, {
'url': 'https://chaturbate.global/siswet19/',
'only_matching': True,
}]
_ROOM_OFFLINE = 'Room is currently offline'
_ERROR_MAP = {
'offline': 'Room is currently offline',
'private': 'Room is currently in a private show',
'away': 'Performer is currently away',
'password protected': 'Room is password protected',
'hidden': 'Hidden session in progress',
}
def _real_extract(self, url):
video_id = self._match_id(url)
def _extract_from_api(self, video_id, tld):
response = self._download_json(
f'https://chaturbate.{tld}/get_edge_hls_url_ajax/', video_id,
data=urlencode_postdata({'room_slug': video_id}),
headers={
**self.geo_verification_headers(),
'X-Requested-With': 'XMLHttpRequest',
'Accept': 'application/json',
}, fatal=False, impersonate=True) or {}
status = response.get('room_status')
if status != 'public':
if error := self._ERROR_MAP.get(status):
raise ExtractorError(error, expected=True)
self.report_warning('Falling back to webpage extraction')
return None
m3u8_url = response.get('url')
if not m3u8_url:
self.raise_geo_restricted()
return {
'id': video_id,
'title': video_id,
'thumbnail': f'https://roomimg.stream.highwebmedia.com/ri/{video_id}.jpg',
'is_live': True,
'age_limit': 18,
'formats': self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', live=True),
}
def _extract_from_html(self, video_id, tld):
webpage = self._download_webpage(
f'https://chaturbate.com/{video_id}/', video_id,
headers=self.geo_verification_headers())
f'https://chaturbate.{tld}/{video_id}/', video_id,
headers=self.geo_verification_headers(), impersonate=True)
found_m3u8_urls = []
@@ -76,8 +120,8 @@ class ChaturbateIE(InfoExtractor):
webpage, 'error', group='error', default=None)
if not error:
if any(p in webpage for p in (
self._ROOM_OFFLINE, 'offline_tipping', 'tip_offline')):
error = self._ROOM_OFFLINE
self._ERROR_MAP['offline'], 'offline_tipping', 'tip_offline')):
error = self._ERROR_MAP['offline']
if error:
raise ExtractorError(error, expected=True)
raise ExtractorError('Unable to find stream URL')
@@ -104,3 +148,7 @@ class ChaturbateIE(InfoExtractor):
'is_live': True,
'formats': formats,
}
def _real_extract(self, url):
video_id, tld = self._match_valid_url(url).group('id', 'tld')
return self._extract_from_api(video_id, tld) or self._extract_from_html(video_id, tld)

36
yt_dlp/extractor/chzzk.py
View File

@@ -1,5 +1,3 @@
import functools
from .common import InfoExtractor
from ..utils import (
UserNotLive,
@@ -77,7 +75,7 @@ class CHZZKLiveIE(InfoExtractor):
'thumbnails': thumbnails,
**traverse_obj(live_detail, {
'title': ('liveTitle', {str}),
'timestamp': ('openDate', {functools.partial(parse_iso8601, delimiter=' ')}),
'timestamp': ('openDate', {parse_iso8601(delimiter=' ')}),
'concurrent_view_count': ('concurrentUserCount', {int_or_none}),
'view_count': ('accumulateCount', {int_or_none}),
'channel': ('channel', 'channelName', {str}),
@@ -146,23 +144,37 @@ class CHZZKVideoIE(InfoExtractor):
video_meta = self._download_json(
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,
query={
'key': video_meta['inKey'],
'env': 'real',
'lc': 'en_US',
'cpl': 'en_US',
}, note='Downloading video playback', errnote='Unable to download video playback')
live_status = 'was_live' if video_meta.get('liveOpenDate') else 'not_live'
video_status = video_meta.get('vodStatus')
if video_status == 'UPLOAD':
playback = self._parse_json(video_meta['liveRewindPlaybackJson'], video_id)
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
playback['media'][0]['path'], video_id, 'mp4', m3u8_id='hls')
elif video_status == 'ABR_HLS':
formats, subtitles = self._extract_mpd_formats_and_subtitles(
f'https://apis.naver.com/neonplayer/vodplay/v1/playback/{video_meta["videoId"]}',
video_id, query={
'key': video_meta['inKey'],
'env': 'real',
'lc': 'en_US',
'cpl': 'en_US',
})
else:
self.raise_no_formats(
f'Unknown video status detected: "{video_status}"', expected=True, video_id=video_id)
formats, subtitles = [], {}
live_status = 'post_live' if live_status == 'was_live' else None
return {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
'live_status': live_status,
**traverse_obj(video_meta, {
'title': ('videoTitle', {str}),
'thumbnail': ('thumbnailImageUrl', {url_or_none}),
'timestamp': ('publishDateAt', {functools.partial(float_or_none, scale=1000)}),
'timestamp': ('publishDateAt', {float_or_none(scale=1000)}),
'view_count': ('readCount', {int_or_none}),
'duration': ('duration', {int_or_none}),
'channel': ('channel', 'channelName', {str}),

3
yt_dlp/extractor/cineverse.py
View File

@@ -3,6 +3,7 @@ import re
from .common import InfoExtractor
from ..utils import (
filter_dict,
float_or_none,
int_or_none,
parse_age_limit,
smuggle_url,
@@ -85,7 +86,7 @@ class CineverseIE(CineverseBaseIE):
'title': 'title',
'id': ('details', 'item_id'),
'description': ('details', 'description'),
'duration': ('duration', {lambda x: x / 1000}),
'duration': ('duration', {float_or_none(scale=1000)}),
'cast': ('details', 'cast', {lambda x: x.split(', ')}),
'modified_timestamp': ('details', 'updated_by', 0, 'update_time', 'time', {int_or_none}),
'season_number': ('details', 'season', {int_or_none}),

13
yt_dlp/extractor/cloudflarestream.py
View File

@@ -8,7 +8,7 @@ class CloudflareStreamIE(InfoExtractor):
_DOMAIN_RE = r'(?:cloudflarestream\.com|(?:videodelivery|bytehighway)\.net)'
_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})'
_VALID_URL = rf'https?://(?:{_SUBDOMAIN_RE}(?P<domain>{_DOMAIN_RE})/|{_EMBED_RE})(?P<id>{_ID_RE})'
_EMBED_REGEX = [
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}})',
@@ -19,7 +19,7 @@ class CloudflareStreamIE(InfoExtractor):
'id': '31c9291ab41fac05471db4e73aa11717',
'ext': 'mp4',
'title': '31c9291ab41fac05471db4e73aa11717',
'thumbnail': 'https://videodelivery.net/31c9291ab41fac05471db4e73aa11717/thumbnails/thumbnail.jpg',
'thumbnail': 'https://cloudflarestream.com/31c9291ab41fac05471db4e73aa11717/thumbnails/thumbnail.jpg',
},
'params': {
'skip_download': 'm3u8',
@@ -30,7 +30,7 @@ class CloudflareStreamIE(InfoExtractor):
'id': '0e8e040aec776862e1d632a699edf59e',
'ext': 'mp4',
'title': '0e8e040aec776862e1d632a699edf59e',
'thumbnail': 'https://videodelivery.net/0e8e040aec776862e1d632a699edf59e/thumbnails/thumbnail.jpg',
'thumbnail': 'https://cloudflarestream.com/0e8e040aec776862e1d632a699edf59e/thumbnails/thumbnail.jpg',
},
}, {
'url': 'https://watch.cloudflarestream.com/9df17203414fd1db3e3ed74abbe936c1',
@@ -54,7 +54,7 @@ class CloudflareStreamIE(InfoExtractor):
'id': 'eaef9dea5159cf968be84241b5cedfe7',
'ext': 'mp4',
'title': 'eaef9dea5159cf968be84241b5cedfe7',
'thumbnail': 'https://videodelivery.net/eaef9dea5159cf968be84241b5cedfe7/thumbnails/thumbnail.jpg',
'thumbnail': 'https://cloudflarestream.com/eaef9dea5159cf968be84241b5cedfe7/thumbnails/thumbnail.jpg',
},
'params': {
'skip_download': 'm3u8',
@@ -62,8 +62,9 @@ class CloudflareStreamIE(InfoExtractor):
}]
def _real_extract(self, url):
video_id = self._match_id(url)
domain = 'bytehighway.net' if 'bytehighway.net/' in url else 'videodelivery.net'
video_id, domain = self._match_valid_url(url).group('id', 'domain')
if domain != 'bytehighway.net':
domain = 'cloudflarestream.com'
base_url = f'https://{domain}/{video_id}/'
if '.' in video_id:
video_id = self._parse_json(base64.urlsafe_b64decode(

3
yt_dlp/extractor/cnn.py
View File

@@ -1,4 +1,3 @@
import functools
import json
import re
@@ -199,7 +198,7 @@ class CNNIE(InfoExtractor):
'timestamp': ('data-publish-date', {parse_iso8601}),
'thumbnail': (
'data-poster-image-override', {json.loads}, 'big', 'uri', {url_or_none},
{functools.partial(update_url, query='c=original')}),
{update_url(query='c=original')}),
'display_id': 'data-video-slug',
}),
**traverse_obj(video_data, {

15
yt_dlp/extractor/common.py
View File

@@ -25,7 +25,6 @@ import xml.etree.ElementTree
from ..compat import (
compat_etree_fromstring,
compat_expanduser,
compat_os_name,
urllib_req_to_req,
)
from ..cookies import LenientSimpleCookie
@@ -279,6 +278,7 @@ class InfoExtractor:
thumbnails: A list of dictionaries, with the following entries:
* "id" (optional, string) - Thumbnail format ID
* "url"
* "ext" (optional, string) - actual image extension if not given in URL
* "preference" (optional, int) - quality of the image
* "width" (optional, int)
* "height" (optional, int)
@@ -1028,7 +1028,7 @@ class InfoExtractor:
filename = sanitize_filename(f'{basen}.dump', restricted=True)
# Working around MAX_PATH limitation on Windows (see
# http://msdn.microsoft.com/en-us/library/windows/desktop/aa365247(v=vs.85).aspx)
if compat_os_name == 'nt':
if os.name == 'nt':
absfilepath = os.path.abspath(filename)
if len(absfilepath) > 259:
filename = fR'\\?\{absfilepath}'
@@ -1409,6 +1409,13 @@ class InfoExtractor:
return None, None
self.write_debug(f'Using netrc for {netrc_machine} authentication')
# compat: <=py3.10: netrc cannot parse tokens as empty strings, will return `""` instead
# Ref: https://github.com/yt-dlp/yt-dlp/issues/11413
# https://github.com/python/cpython/commit/15409c720be0503131713e3d3abc1acd0da07378
if sys.version_info < (3, 11):
return tuple(x if x != '""' else '' for x in info[::2])
return info[0], info[2]
def _get_login_info(self, username_option='username', password_option='password', netrc_machine=None):
@@ -1571,7 +1578,9 @@ class InfoExtractor:
if default is not NO_DEFAULT:
fatal = False
for mobj in re.finditer(JSON_LD_RE, html):
json_ld_item = self._parse_json(mobj.group('json_ld'), video_id, fatal=fatal)
json_ld_item = self._parse_json(
mobj.group('json_ld'), video_id, fatal=fatal,
errnote=False if default is not NO_DEFAULT else None)
for json_ld in variadic(json_ld_item):
if isinstance(json_ld, dict):
yield json_ld

4
yt_dlp/extractor/condenast.py
View File

@@ -12,6 +12,7 @@ from ..utils import (
parse_iso8601,
strip_or_none,
try_get,
urljoin,
)
@@ -112,8 +113,7 @@ class CondeNastIE(InfoExtractor):
m_paths = re.finditer(
r'(?s)<p class="cne-thumb-title">.*?<a href="(/watch/.+?)["\?]', webpage)
paths = orderedSet(m.group(1) for m in m_paths)
build_url = lambda path: urllib.parse.urljoin(base_url, path)
entries = [self.url_result(build_url(path), 'CondeNast') for path in paths]
entries = [self.url_result(urljoin(base_url, path), 'CondeNast') for path in paths]
return self.playlist_result(entries, playlist_title=title)
def _extract_video_params(self, webpage, display_id):

4
yt_dlp/extractor/crunchyroll.py
View File

@@ -456,7 +456,7 @@ class CrunchyrollBetaIE(CrunchyrollCmsBaseIE):
}),
}),
**traverse_obj(metadata, {
'duration': ('duration_ms', {lambda x: float_or_none(x, 1000)}),
'duration': ('duration_ms', {float_or_none(scale=1000)}),
'timestamp': ('upload_date', {parse_iso8601}),
'series': ('series_title', {str}),
'series_id': ('series_id', {str}),
@@ -484,7 +484,7 @@ class CrunchyrollBetaIE(CrunchyrollCmsBaseIE):
}),
}),
**traverse_obj(metadata, {
'duration': ('duration_ms', {lambda x: float_or_none(x, 1000)}),
'duration': ('duration_ms', {float_or_none(scale=1000)}),
'age_limit': ('maturity_ratings', -1, {parse_age_limit}),
}),
}

138
yt_dlp/extractor/dailymotion.py
View File

@@ -10,11 +10,14 @@ from ..utils import (
OnDemandPagedList,
age_restricted,
clean_html,
extract_attributes,
int_or_none,
traverse_obj,
try_get,
unescapeHTML,
unsmuggle_url,
update_url,
url_or_none,
urlencode_postdata,
)
@@ -98,12 +101,20 @@ class DailymotionBaseInfoExtractor(InfoExtractor):
class DailymotionIE(DailymotionBaseInfoExtractor):
_VALID_URL = r'''(?ix)
https?://
(?:
dai\.ly/|
(?:
(?:(?:www|touch|geo)\.)?dailymotion\.[a-z]{2,3}/(?:(?:(?:(?:embed|swf|\#)/)|player(?:/\w+)?\.html\?)?video|swf)|
(?:www\.)?lequipe\.fr/video
(?:(?:www|touch|geo)\.)?dailymotion\.[a-z]{2,3}|
(?:www\.)?lequipe\.fr
)/
(?:
swf/(?!video)|
(?:(?:crawler|embed|swf)/)?video/|
player(?:/[\da-z]+)?\.html\?(?:video|(?P<is_playlist>playlist))=
)
[/=](?P<id>[^/?_&]+)(?:.+?\bplaylist=(?P<playlist_id>x[0-9a-z]+))?
'''
)
(?P<id>[^/?_&#]+)(?:[\w-]*\?playlist=(?P<playlist_id>x[0-9a-z]+))?
'''
IE_NAME = 'dailymotion'
_EMBED_REGEX = [r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1']
_TESTS = [{
@@ -123,7 +134,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'view_count': int,
'like_count': int,
'tags': ['hollywood', 'celeb', 'celebrity', 'movies', 'red carpet'],
'thumbnail': r're:https://(?:s[12]\.)dmcdn\.net/v/K456B1aXqIx58LKWQ/x1080',
'thumbnail': r're:https://(?:s[12]\.)dmcdn\.net/v/K456B1cmt4ZcZ9KiM/x1080',
},
}, {
'url': 'https://geo.dailymotion.com/player.html?video=x89eyek&mute=true',
@@ -142,7 +153,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'view_count': int,
'like_count': int,
'tags': ['en_quete_d_esprit'],
'thumbnail': r're:https://(?:s[12]\.)dmcdn\.net/v/Tncwi1YNg_RUl7ueu/x1080',
'thumbnail': r're:https://(?:s[12]\.)dmcdn\.net/v/Tncwi1clTH6StrxMP/x1080',
},
}, {
'url': 'https://www.dailymotion.com/video/x2iuewm_steam-machine-models-pricing-listed-on-steam-store-ign-news_videogames',
@@ -217,6 +228,66 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
}, {
'url': 'https://geo.dailymotion.com/player/xakln.html?video=x8mjju4&customConfig%5BcustomParams%5D=%2Ffr-fr%2Ftennis%2Fwimbledon-mens-singles%2Farticles-video',
'only_matching': True,
}, { # playlist-only
'url': 'https://geo.dailymotion.com/player/xf7zn.html?playlist=x7wdsj',
'only_matching': True,
}, {
'url': 'https://geo.dailymotion.com/player/xmyye.html?video=x93blhi',
'only_matching': True,
}, {
'url': 'https://www.dailymotion.com/crawler/video/x8u4owg',
'only_matching': True,
}, {
'url': 'https://www.dailymotion.com/embed/video/x8u4owg',
'only_matching': True,
}, {
'url': 'https://dai.ly/x94cnnk',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
# https://geo.dailymotion.com/player/xmyye.html?video=x93blhi
'url': 'https://www.financialounge.com/video/2024/08/01/borse-europee-in-rosso-dopo-la-fed-a-milano-volano-mediobanca-e-tim-edizione-del-1-agosto/',
'info_dict': {
'id': 'x93blhi',
'ext': 'mp4',
'title': 'OnAir - 01/08/24',
'description': '',
'duration': 217,
'timestamp': 1722505658,
'upload_date': '20240801',
'uploader': 'Financialounge',
'uploader_id': 'x2vtgmm',
'age_limit': 0,
'tags': [],
'view_count': int,
'like_count': int,
},
}, {
# https://geo.dailymotion.com/player/xf7zn.html?playlist=x7wdsj
'url': 'https://www.cycleworld.com/blogs/ask-kevin/ducati-continues-to-evolve-with-v4/',
'info_dict': {
'id': 'x7wdsj',
},
'playlist_mincount': 50,
}, {
# https://www.dailymotion.com/crawler/video/x8u4owg
'url': 'https://www.leparisien.fr/environnement/video-le-veloto-la-voiture-a-pedales-qui-aimerait-se-faire-une-place-sur-les-routes-09-03-2024-KCYMCPM4WFHJXMSKBUI66UNFPU.php',
'info_dict': {
'id': 'x8u4owg',
'ext': 'mp4',
'like_count': int,
'uploader': 'Le Parisien',
'thumbnail': 'https://www.leparisien.fr/resizer/ho_GwveeYftNkLwg_cEta--5Bv4=/1200x675/cloudfront-eu-central-1.images.arcpublishing.com/leparisien/BFXJNEBN75EUNHGYJLORUC3TX4.jpg',
'upload_date': '20240309',
'view_count': int,
'timestamp': 1709997866,
'age_limit': 0,
'uploader_id': 'x32f7b',
'title': 'VIDÉO. Le «\xa0véloto\xa0», la voiture à pédales qui aimerait se faire une place sur les routes',
'duration': 428.0,
'description': 'À bord du « véloto », l’alternative à la voiture pour la campagne',
'tags': ['biclou', 'vélo', 'véloto', 'campagne', 'voiture', 'environnement', 'véhicules intermédiaires'],
},
}]
_GEO_BYPASS = False
_COMMON_MEDIA_FIELDS = '''description
@@ -232,16 +303,35 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
for mobj in re.finditer(
r'(?s)DM\.player\([^,]+,\s*{.*?video[\'"]?\s*:\s*["\']?(?P<id>[0-9a-zA-Z]+).+?}\s*\);', webpage):
yield from 'https://www.dailymotion.com/embed/video/' + mobj.group('id')
for mobj in re.finditer(
r'(?s)<script [^>]*\bsrc=(["\'])(?:https?:)?//[\w-]+\.dailymotion\.com/player/(?:(?!\1).)+\1[^>]*>', webpage):
attrs = extract_attributes(mobj.group(0))
player_url = url_or_none(attrs.get('src'))
if not player_url:
continue
player_url = player_url.replace('.js', '.html')
if player_url.startswith('//'):
player_url = f'https:{player_url}'
if video_id := attrs.get('data-video'):
query_string = f'video={video_id}'
elif playlist_id := attrs.get('data-playlist'):
query_string = f'playlist={playlist_id}'
else:
continue
yield update_url(player_url, query=query_string)
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url)
video_id, playlist_id = self._match_valid_url(url).groups()
video_id, is_playlist, playlist_id = self._match_valid_url(url).group('id', 'is_playlist', 'playlist_id')
if playlist_id:
if self._yes_playlist(playlist_id, video_id):
return self.url_result(
'http://www.dailymotion.com/playlist/' + playlist_id,
'DailymotionPlaylist', playlist_id)
if is_playlist: # We matched the playlist query param as video_id
playlist_id = video_id
video_id = None
if self._yes_playlist(playlist_id, video_id):
return self.url_result(
f'http://www.dailymotion.com/playlist/{playlist_id}',
'DailymotionPlaylist', playlist_id)
password = self.get_param('videopassword')
media = self._call_api(
@@ -282,6 +372,8 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
title = metadata['title']
is_live = media.get('isOnAir')
formats = []
subtitles = {}
for quality, media_list in metadata['qualities'].items():
for m in media_list:
media_url = m.get('url')
@@ -289,8 +381,10 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
if not media_url or media_type == 'application/vnd.lumberjack.manifest':
continue
if media_type == 'application/x-mpegURL':
formats.extend(self._extract_m3u8_formats(
media_url, video_id, 'mp4', live=is_live, m3u8_id='hls', fatal=False))
fmt, subs = self._extract_m3u8_formats_and_subtitles(
media_url, video_id, 'mp4', live=is_live, m3u8_id='hls', fatal=False)
formats.extend(fmt)
self._merge_subtitles(subs, target=subtitles)
else:
f = {
'url': media_url,
@@ -310,20 +404,18 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
if not f.get('fps') and f['format_id'].endswith('@60'):
f['fps'] = 60
subtitles = {}
subtitles_data = try_get(metadata, lambda x: x['subtitles']['data'], dict) or {}
for subtitle_lang, subtitle in subtitles_data.items():
subtitles[subtitle_lang] = [{
'url': subtitle_url,
} for subtitle_url in subtitle.get('urls', [])]
thumbnails = []
for height, poster_url in metadata.get('posters', {}).items():
thumbnails.append({
'height': int_or_none(height),
'id': height,
'url': poster_url,
})
thumbnails = traverse_obj(metadata, (
('posters', 'thumbnails'), {dict.items}, lambda _, v: url_or_none(v[1]), {
'height': (0, {int_or_none}),
'id': (0, {str}),
'url': 1,
}))
owner = metadata.get('owner') or {}
stats = media.get('stats') or {}
@@ -447,7 +539,7 @@ class DailymotionSearchIE(DailymotionPlaylistBaseIE):
class DailymotionUserIE(DailymotionPlaylistBaseIE):
IE_NAME = 'dailymotion:user'
_VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|swf|#|video|playlist|search)/)(?:(?:old/)?user/)?(?P<id>[^/?#]+)'
_VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|swf|#|video|playlist|search|crawler)/)(?:(?:old/)?user/)?(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.dailymotion.com/user/nqtv',
'info_dict': {

2
yt_dlp/extractor/dangalplay.py
View File

@@ -40,7 +40,7 @@ class DangalPlayBaseIE(InfoExtractor):
'id': ('content_id', {str}),
'title': ('display_title', {str}),
'episode': ('title', {str}),
'series': ('show_name', {str}, {lambda x: x or None}),
'series': ('show_name', {str}, filter),
'series_id': ('catalog_id', {str}),
'duration': ('duration', {int_or_none}),
'release_timestamp': ('release_date_uts', {int_or_none}),

2
yt_dlp/extractor/err.py
View File

@@ -207,7 +207,7 @@ class ERRJupiterIE(InfoExtractor):
**traverse_obj(data, {
'title': ('heading', {str}),
'alt_title': ('subHeading', {str}),
'description': (('lead', 'body'), {clean_html}, {lambda x: x or None}),
'description': (('lead', 'body'), {clean_html}, filter),
'timestamp': ('created', {int_or_none}),
'modified_timestamp': ('updated', {int_or_none}),
'release_timestamp': (('scheduleStart', 'publicStart'), {int_or_none}),

35
yt_dlp/extractor/facebook.py
View File

@@ -563,13 +563,13 @@ class FacebookIE(InfoExtractor):
return extract_video_data(try_get(
js_data, lambda x: x['jsmods']['instances'], list) or [])
def extract_dash_manifest(video, formats):
def extract_dash_manifest(vid_data, formats, mpd_url=None):
dash_manifest = traverse_obj(
video, 'dash_manifest', 'playlist', 'dash_manifest_xml_string', expected_type=str)
vid_data, 'dash_manifest', 'playlist', 'dash_manifest_xml_string', 'manifest_xml', expected_type=str)
if dash_manifest:
formats.extend(self._parse_mpd_formats(
compat_etree_fromstring(urllib.parse.unquote_plus(dash_manifest)),
mpd_url=url_or_none(video.get('dash_manifest_url'))))
mpd_url=url_or_none(video.get('dash_manifest_url')) or mpd_url))
def process_formats(info):
# Downloads with browser's User-Agent are rate limited. Working around
@@ -619,9 +619,12 @@ class FacebookIE(InfoExtractor):
video = video['creation_story']
video['owner'] = traverse_obj(video, ('short_form_video_context', 'video_owner'))
video.update(reel_info)
fmt_data = traverse_obj(video, ('videoDeliveryLegacyFields', {dict})) or video
formats = []
q = qualities(['sd', 'hd'])
# Legacy formats extraction
fmt_data = traverse_obj(video, ('videoDeliveryLegacyFields', {dict})) or video
for key, format_id in (('playable_url', 'sd'), ('playable_url_quality_hd', 'hd'),
('playable_url_dash', ''), ('browser_native_hd_url', 'hd'),
('browser_native_sd_url', 'sd')):
@@ -629,7 +632,7 @@ class FacebookIE(InfoExtractor):
if not playable_url:
continue
if determine_ext(playable_url) == 'mpd':
formats.extend(self._extract_mpd_formats(playable_url, video_id))
formats.extend(self._extract_mpd_formats(playable_url, video_id, fatal=False))
else:
formats.append({
'format_id': format_id,
@@ -638,6 +641,28 @@ class FacebookIE(InfoExtractor):
'url': playable_url,
})
extract_dash_manifest(fmt_data, formats)
# New videoDeliveryResponse formats extraction
fmt_data = traverse_obj(video, ('videoDeliveryResponseFragment', 'videoDeliveryResponseResult'))
mpd_urls = traverse_obj(fmt_data, ('dash_manifest_urls', ..., 'manifest_url', {url_or_none}))
dash_manifests = traverse_obj(fmt_data, ('dash_manifests', lambda _, v: v['manifest_xml']))
for idx, dash_manifest in enumerate(dash_manifests):
extract_dash_manifest(dash_manifest, formats, mpd_url=traverse_obj(mpd_urls, idx))
if not dash_manifests:
# Only extract from MPD URLs if the manifests are not already provided
for mpd_url in mpd_urls:
formats.extend(self._extract_mpd_formats(mpd_url, video_id, fatal=False))
for prog_fmt in traverse_obj(fmt_data, ('progressive_urls', lambda _, v: v['progressive_url'])):
format_id = traverse_obj(prog_fmt, ('metadata', 'quality', {str.lower}))
formats.append({
'format_id': format_id,
# sd, hd formats w/o resolution info should be deprioritized below DASH
'quality': q(format_id) - 3,
'url': prog_fmt['progressive_url'],
})
for m3u8_url in traverse_obj(fmt_data, ('hls_playlist_urls', ..., 'hls_playlist_url', {url_or_none})):
formats.extend(self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', fatal=False, m3u8_id='hls'))
if not formats:
# Do not append false positive entry w/o any formats
return

141
yt_dlp/extractor/gamedevtv.py Normal file
View File

@@ -0,0 +1,141 @@
import json
from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
clean_html,
int_or_none,
join_nonempty,
parse_iso8601,
str_or_none,
url_or_none,
)
from ..utils.traversal import traverse_obj
class GameDevTVDashboardIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?gamedev\.tv/dashboard/courses/(?P<course_id>\d+)(?:/(?P<lecture_id>\d+))?'
_NETRC_MACHINE = 'gamedevtv'
_TESTS = [{
'url': 'https://www.gamedev.tv/dashboard/courses/25',
'info_dict': {
'id': '25',
'title': 'Complete Blender Creator 3: Learn 3D Modelling for Beginners',
'tags': ['blender', 'course', 'all', 'box modelling', 'sculpting'],
'categories': ['Blender', '3D Art'],
'thumbnail': 'https://gamedev-files.b-cdn.net/courses/qisc9pmu1jdc.jpg',
'upload_date': '20220516',
'timestamp': 1652694420,
'modified_date': '20241027',
'modified_timestamp': 1730049658,
},
'playlist_count': 100,
}, {
'url': 'https://www.gamedev.tv/dashboard/courses/63/2279',
'info_dict': {
'id': 'df04f4d8-68a4-4756-a71b-9ca9446c3a01',
'ext': 'mp4',
'modified_timestamp': 1701695752,
'upload_date': '20230504',
'episode': 'MagicaVoxel Community Course Introduction',
'series_id': '63',
'title': 'MagicaVoxel Community Course Introduction',
'timestamp': 1683195397,
'modified_date': '20231204',
'categories': ['3D Art', 'MagicaVoxel'],
'season': 'MagicaVoxel Community Course',
'tags': ['MagicaVoxel', 'all', 'course'],
'series': 'MagicaVoxel 3D Art Mini Course',
'duration': 1405,
'episode_number': 1,
'season_number': 1,
'season_id': '219',
'description': 'md5:a378738c5bbec1c785d76c067652d650',
'display_id': '63-219-2279',
'alt_title': '1_CC_MVX MagicaVoxel Community Course Introduction.mp4',
'thumbnail': 'https://vz-23691c65-6fa.b-cdn.net/df04f4d8-68a4-4756-a71b-9ca9446c3a01/thumbnail.jpg',
},
}]
_API_HEADERS = {}
def _perform_login(self, username, password):
try:
response = self._download_json(
'https://api.gamedev.tv/api/students/login', None, 'Logging in',
headers={'Content-Type': 'application/json'},
data=json.dumps({
'email': username,
'password': password,
'cart_items': [],
}).encode())
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 401:
raise ExtractorError('Invalid username/password', expected=True)
raise
self._API_HEADERS['Authorization'] = f'{response["token_type"]} {response["access_token"]}'
def _real_initialize(self):
if not self._API_HEADERS.get('Authorization'):
self.raise_login_required(
'This content is only available with purchase', method='password')
def _entries(self, data, course_id, course_info, selected_lecture):
for section in traverse_obj(data, ('sections', ..., {dict})):
section_info = traverse_obj(section, {
'season_id': ('id', {str_or_none}),
'season': ('title', {str}),
'season_number': ('order', {int_or_none}),
})
for lecture in traverse_obj(section, ('lectures', lambda _, v: url_or_none(v['video']['playListUrl']))):
if selected_lecture and str(lecture.get('id')) != selected_lecture:
continue
display_id = join_nonempty(course_id, section_info.get('season_id'), lecture.get('id'))
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
lecture['video']['playListUrl'], display_id, 'mp4', m3u8_id='hls')
yield {
**course_info,
**section_info,
'id': display_id, # fallback
'display_id': display_id,
'formats': formats,
'subtitles': subtitles,
'series': course_info.get('title'),
'series_id': course_id,
**traverse_obj(lecture, {
'id': ('video', 'guid', {str}),
'title': ('title', {str}),
'alt_title': ('video', 'title', {str}),
'description': ('description', {clean_html}),
'episode': ('title', {str}),
'episode_number': ('order', {int_or_none}),
'duration': ('video', 'duration_in_sec', {int_or_none}),
'timestamp': ('video', 'created_at', {parse_iso8601}),
'modified_timestamp': ('video', 'updated_at', {parse_iso8601}),
'thumbnail': ('video', 'thumbnailUrl', {url_or_none}),
}),
}
def _real_extract(self, url):
course_id, lecture_id = self._match_valid_url(url).group('course_id', 'lecture_id')
data = self._download_json(
f'https://api.gamedev.tv/api/courses/my/{course_id}', course_id,
headers=self._API_HEADERS)['data']
course_info = traverse_obj(data, {
'title': ('title', {str}),
'tags': ('tags', ..., 'name', {str}),
'categories': ('categories', ..., 'title', {str}),
'timestamp': ('created_at', {parse_iso8601}),
'modified_timestamp': ('updated_at', {parse_iso8601}),
'thumbnail': ('image', {url_or_none}),
})
entries = self._entries(data, course_id, course_info, lecture_id)
if lecture_id:
lecture = next(entries, None)
if not lecture:
raise ExtractorError('Lecture not found')
return lecture
return self.playlist_result(entries, course_id, **course_info)

96
yt_dlp/extractor/goplay.py
View File

@@ -5,56 +5,63 @@ import hashlib
import hmac
import json
import os
import re
import urllib.parse
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
js_to_json,
remove_end,
traverse_obj,
unescapeHTML,
)
class GoPlayIE(InfoExtractor):
_VALID_URL = r'https?://(www\.)?goplay\.be/video/([^/]+/[^/]+/|)(?P<display_id>[^/#]+)'
_VALID_URL = r'https?://(www\.)?goplay\.be/video/([^/?#]+/[^/?#]+/|)(?P<id>[^/#]+)'
_NETRC_MACHINE = 'goplay'
_TESTS = [{
'url': 'https://www.goplay.be/video/de-container-cup/de-container-cup-s3/de-container-cup-s3-aflevering-2#autoplay',
'url': 'https://www.goplay.be/video/de-slimste-mens-ter-wereld/de-slimste-mens-ter-wereld-s22/de-slimste-mens-ter-wereld-s22-aflevering-1',
'info_dict': {
'id': '9c4214b8-e55d-4e4b-a446-f015f6c6f811',
'id': '2baa4560-87a0-421b-bffc-359914e3c387',
'ext': 'mp4',
'title': 'S3 - Aflevering 2',
'series': 'De Container Cup',
'season': 'Season 3',
'season_number': 3,
'episode': 'Episode 2',
'episode_number': 2,
'title': 'S22 - Aflevering 1',
'description': r're:In aflevering 1 nemen Daan Alferink, Tess Elst en Xander De Rycke .{66}',
'series': 'De Slimste Mens ter Wereld',
'episode': 'Episode 1',
'season_number': 22,
'episode_number': 1,
'season': 'Season 22',
},
'params': {'skip_download': True},
'skip': 'This video is only available for registered users',
}, {
'url': 'https://www.goplay.be/video/a-family-for-thr-holidays-s1-aflevering-1#autoplay',
'url': 'https://www.goplay.be/video/1917',
'info_dict': {
'id': '74e3ed07-748c-49e4-85a0-393a93337dbf',
'id': '40cac41d-8d29-4ef5-aa11-75047b9f0907',
'ext': 'mp4',
'title': 'A Family for the Holidays',
'title': '1917',
'description': r're:Op het hoogtepunt van de Eerste Wereldoorlog krijgen twee jonge .{94}',
},
'params': {'skip_download': True},
'skip': 'This video is only available for registered users',
}, {
'url': 'https://www.goplay.be/video/de-mol/de-mol-s11/de-mol-s11-aflevering-1#autoplay',
'info_dict': {
'id': '03eb8f2f-153e-41cb-9805-0d3a29dab656',
'id': 'ecb79672-92b9-4cd9-a0d7-e2f0250681ee',
'ext': 'mp4',
'title': 'S11 - Aflevering 1',
'description': r're:Tien kandidaten beginnen aan hun verovering van Amerika en ontmoeten .{102}',
'episode': 'Episode 1',
'series': 'De Mol',
'season_number': 11,
'episode_number': 1,
'season': 'Season 11',
},
'params': {
'skip_download': True,
},
'params': {'skip_download': True},
'skip': 'This video is only available for registered users',
}]
@@ -69,27 +76,42 @@ class GoPlayIE(InfoExtractor):
if not self._id_token:
raise self.raise_login_required(method='password')
def _real_extract(self, url):
url, display_id = self._match_valid_url(url).group(0, 'display_id')
webpage = self._download_webpage(url, display_id)
video_data_json = self._html_search_regex(r'<div\s+data-hero="([^"]+)"', webpage, 'video_data')
video_data = self._parse_json(unescapeHTML(video_data_json), display_id).get('data')
def _find_json(self, s):
return self._search_json(
r'\w+\s*:\s*', s, 'next js data', None, contains_pattern=r'\[(?s:.+)\]', default=None)
movie = video_data.get('movie')
if movie:
video_id = movie['videoUuid']
info_dict = {
'title': movie.get('title'),
}
else:
episode = traverse_obj(video_data, ('playlists', ..., 'episodes', lambda _, v: v['pageInfo']['url'] == url), get_all=False)
video_id = episode['videoUuid']
info_dict = {
'title': episode.get('episodeTitle'),
'series': traverse_obj(episode, ('program', 'title')),
'season_number': episode.get('seasonNumber'),
'episode_number': episode.get('episodeNumber'),
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
nextjs_data = traverse_obj(
re.findall(r'<script[^>]*>\s*self\.__next_f\.push\(\s*(\[.+?\])\s*\);?\s*</script>', webpage),
(..., {js_to_json}, {json.loads}, ..., {self._find_json}, ...))
meta = traverse_obj(nextjs_data, (
..., lambda _, v: v['meta']['path'] == urllib.parse.urlparse(url).path, 'meta', any))
video_id = meta['uuid']
info_dict = traverse_obj(meta, {
'title': ('title', {str}),
'description': ('description', {str.strip}),
})
if traverse_obj(meta, ('program', 'subtype')) != 'movie':
for season_data in traverse_obj(nextjs_data, (..., 'children', ..., 'playlists', ...)):
episode_data = traverse_obj(
season_data, ('videos', lambda _, v: v['videoId'] == video_id, any))
if not episode_data:
continue
episode_title = traverse_obj(
episode_data, 'contextualTitle', 'episodeTitle', expected_type=str)
info_dict.update({
'title': episode_title or info_dict.get('title'),
'series': remove_end(info_dict.get('title'), f' - {episode_title}'),
'season_number': traverse_obj(season_data, ('season', {int_or_none})),
'episode_number': traverse_obj(episode_data, ('episodeNumber', {int_or_none})),
})
break
api = self._download_json(
f'https://api.goplay.be/web/v1/videos/long-form/{video_id}',

3
yt_dlp/extractor/ilpost.py
View File

@@ -1,4 +1,3 @@
import functools
from .common import InfoExtractor
from ..utils import (
@@ -63,7 +62,7 @@ class IlPostIE(InfoExtractor):
'url': ('podcast_raw_url', {url_or_none}),
'thumbnail': ('image', {url_or_none}),
'timestamp': ('timestamp', {int_or_none}),
'duration': ('milliseconds', {functools.partial(float_or_none, scale=1000)}),
'duration': ('milliseconds', {float_or_none(scale=1000)}),
'availability': ('free', {lambda v: 'public' if v else 'subscriber_only'}),
}),
}

12
yt_dlp/extractor/jiocinema.py
View File

@@ -326,11 +326,11 @@ class JioCinemaIE(JioCinemaBaseIE):
# fallback metadata
'title': ('name', {str}),
'description': ('fullSynopsis', {str}),
'series': ('show', 'name', {str}, {lambda x: x or None}),
'series': ('show', 'name', {str}, filter),
'season': ('tournamentName', {str}, {lambda x: x if x != 'Season 0' else None}),
'season_number': ('episode', 'season', {int_or_none}, {lambda x: x or None}),
'season_number': ('episode', 'season', {int_or_none}, filter),
'episode': ('fullTitle', {str}),
'episode_number': ('episode', 'episodeNo', {int_or_none}, {lambda x: x or None}),
'episode_number': ('episode', 'episodeNo', {int_or_none}, filter),
'age_limit': ('ageNemonic', {parse_age_limit}),
'duration': ('totalDuration', {float_or_none}),
'thumbnail': ('images', {url_or_none}),
@@ -338,10 +338,10 @@ class JioCinemaIE(JioCinemaBaseIE):
**traverse_obj(metadata, ('result', 0, {
'title': ('fullTitle', {str}),
'description': ('fullSynopsis', {str}),
'series': ('showName', {str}, {lambda x: x or None}),
'season': ('seasonName', {str}, {lambda x: x or None}),
'series': ('showName', {str}, filter),
'season': ('seasonName', {str}, filter),
'season_number': ('season', {int_or_none}),
'season_id': ('seasonId', {str}, {lambda x: x or None}),
'season_id': ('seasonId', {str}, filter),
'episode': ('fullTitle', {str}),
'episode_number': ('episode', {int_or_none}),
'timestamp': ('uploadTime', {int_or_none}),

160
yt_dlp/extractor/kenh14.py Normal file
View File

@@ -0,0 +1,160 @@
from .common import InfoExtractor
from ..utils import (
clean_html,
extract_attributes,
get_element_by_class,
get_element_html_by_attribute,
get_elements_html_by_class,
int_or_none,
parse_duration,
parse_iso8601,
remove_start,
strip_or_none,
unescapeHTML,
update_url,
url_or_none,
)
from ..utils.traversal import traverse_obj
class Kenh14VideoIE(InfoExtractor):
_VALID_URL = r'https?://video\.kenh14\.vn/(?:video/)?[\w-]+-(?P<id>[0-9]+)\.chn'
_TESTS = [{
'url': 'https://video.kenh14.vn/video/mo-hop-iphone-14-pro-max-nguon-unbox-therapy-316173.chn',
'md5': '1ed67f9c3a1e74acf15db69590cf6210',
'info_dict': {
'id': '316173',
'ext': 'mp4',
'title': 'Video mở hộp iPhone 14 Pro Max (Nguồn: Unbox Therapy)',
'description': 'Video mở hộp iPhone 14 Pro MaxVideo mở hộp iPhone 14 Pro Max (Nguồn: Unbox Therapy)',
'thumbnail': r're:^https?://videothumbs\.mediacdn\.vn/.*\.jpg$',
'tags': [],
'uploader': 'Unbox Therapy',
'upload_date': '20220517',
'view_count': int,
'duration': 722.86,
'timestamp': 1652764468,
},
}, {
'url': 'https://video.kenh14.vn/video-316174.chn',
'md5': '2b41877d2afaf4a3f487ceda8e5c7cbd',
'info_dict': {
'id': '316174',
'ext': 'mp4',
'title': 'Khoảnh khắc VĐV nằm gục khóc sau chiến thắng: 7 năm trời Việt Nam mới có HCV kiếm chém nữ, chỉ có 8 tháng để khổ luyện trước khi lên sàn đấu',
'description': 'md5:de86aa22e143e2b277bce8ec9c6f17dc',
'thumbnail': r're:^https?://videothumbs\.mediacdn\.vn/.*\.jpg$',
'tags': [],
'upload_date': '20220517',
'view_count': int,
'duration': 70.04,
'timestamp': 1652766021,
},
}, {
'url': 'https://video.kenh14.vn/0-344740.chn',
'md5': 'b843495d5e728142c8870c09b46df2a9',
'info_dict': {
'id': '344740',
'ext': 'mov',
'title': 'Kỳ Duyên đầy căng thẳng trong buổi ra quân đi Miss Universe, nghi thức tuyên thuệ lần đầu xuất hiện gây nhiều tranh cãi',
'description': 'md5:2a2dbb4a7397169fb21ee68f09160497',
'thumbnail': r're:^https?://kenh14cdn\.com/.*\.jpg$',
'tags': ['kỳ duyên', 'Kỳ Duyên tuyên thuệ', 'miss universe'],
'uploader': 'Quang Vũ',
'upload_date': '20241024',
'view_count': int,
'duration': 198.88,
'timestamp': 1729741590,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
attrs = extract_attributes(get_element_html_by_attribute('type', 'VideoStream', webpage) or '')
direct_url = attrs['data-vid']
metadata = self._download_json(
'https://api.kinghub.vn/video/api/v1/detailVideoByGet?FileName={}'.format(
remove_start(direct_url, 'kenh14cdn.com/')), video_id, fatal=False)
formats = [{'url': f'https://{direct_url}', 'format_id': 'http', 'quality': 1}]
subtitles = {}
video_data = self._download_json(
f'https://{direct_url}.json', video_id, note='Downloading video data', fatal=False)
if hls_url := traverse_obj(video_data, ('hls', {url_or_none})):
fmts, subs = self._extract_m3u8_formats_and_subtitles(
hls_url, video_id, m3u8_id='hls', fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
if dash_url := traverse_obj(video_data, ('mpd', {url_or_none})):
fmts, subs = self._extract_mpd_formats_and_subtitles(
dash_url, video_id, mpd_id='dash', fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
return {
**traverse_obj(metadata, {
'duration': ('duration', {parse_duration}),
'uploader': ('author', {strip_or_none}),
'timestamp': ('uploadtime', {parse_iso8601(delimiter=' ')}),
'view_count': ('views', {int_or_none}),
}),
'id': video_id,
'title': (
traverse_obj(metadata, ('title', {strip_or_none}))
or clean_html(self._og_search_title(webpage))
or clean_html(get_element_by_class('vdbw-title', webpage))),
'formats': formats,
'subtitles': subtitles,
'description': (
clean_html(self._og_search_description(webpage))
or clean_html(get_element_by_class('vdbw-sapo', webpage))),
'thumbnail': (self._og_search_thumbnail(webpage) or attrs.get('data-thumb')),
'tags': traverse_obj(self._html_search_meta('keywords', webpage), (
{lambda x: x.split(';')}, ..., filter)),
}
class Kenh14PlaylistIE(InfoExtractor):
_VALID_URL = r'https?://video\.kenh14\.vn/playlist/[\w-]+-(?P<id>[0-9]+)\.chn'
_TESTS = [{
'url': 'https://video.kenh14.vn/playlist/tran-tinh-naked-love-mua-2-71.chn',
'info_dict': {
'id': '71',
'title': 'Trần Tình (Naked love) mùa 2',
'description': 'md5:e9522339304956dea931722dd72eddb2',
'thumbnail': r're:^https?://kenh14cdn\.com/.*\.png$',
},
'playlist_count': 9,
}, {
'url': 'https://video.kenh14.vn/playlist/0-72.chn',
'info_dict': {
'id': '72',
'title': 'Lau Lại Đầu Từ',
'description': 'Cùng xem xưa và nay có gì khác biệt nhé!',
'thumbnail': r're:^https?://kenh14cdn\.com/.*\.png$',
},
'playlist_count': 6,
}]
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
category_detail = get_element_by_class('category-detail', webpage) or ''
embed_info = traverse_obj(
self._yield_json_ld(webpage, playlist_id),
(lambda _, v: v['name'] and v['alternateName'], any)) or {}
return self.playlist_from_matches(
get_elements_html_by_class('video-item', webpage), playlist_id,
(clean_html(get_element_by_class('name', category_detail)) or unescapeHTML(embed_info.get('name'))),
getter=lambda x: 'https://video.kenh14.vn/video/video-{}.chn'.format(extract_attributes(x)['data-id']),
ie=Kenh14VideoIE, playlist_description=(
clean_html(get_element_by_class('description', category_detail))
or unescapeHTML(embed_info.get('alternateName'))),
thumbnail=traverse_obj(
self._og_search_thumbnail(webpage),
({url_or_none}, {update_url(query=None)})))

3
yt_dlp/extractor/kick.py
View File

@@ -1,4 +1,3 @@
import functools
from .common import InfoExtractor
from ..networking import HEADRequest
@@ -137,7 +136,7 @@ class KickVODIE(KickBaseIE):
'uploader': ('livestream', 'channel', 'user', 'username', {str}),
'uploader_id': ('livestream', 'channel', 'user_id', {int}, {str_or_none}),
'timestamp': ('created_at', {parse_iso8601}),
'duration': ('livestream', 'duration', {functools.partial(float_or_none, scale=1000)}),
'duration': ('livestream', 'duration', {float_or_none(scale=1000)}),
'thumbnail': ('livestream', 'thumbnail', {url_or_none}),
'categories': ('livestream', 'categories', ..., 'name', {str}),
'view_count': ('views', {int_or_none}),

2
yt_dlp/extractor/kika.py
View File

@@ -119,7 +119,7 @@ class KikaIE(InfoExtractor):
'width': ('frameWidth', {int_or_none}),
'height': ('frameHeight', {int_or_none}),
# NB: filesize is 0 if unknown, bitrate is -1 if unknown
'filesize': ('fileSize', {int_or_none}, {lambda x: x or None}),
'filesize': ('fileSize', {int_or_none}, filter),
'abr': ('bitrateAudio', {int_or_none}, {lambda x: None if x == -1 else x}),
'vbr': ('bitrateVideo', {int_or_none}, {lambda x: None if x == -1 else x}),
}),

4
yt_dlp/extractor/laracasts.py
View File

@@ -32,7 +32,7 @@ class LaracastsBaseIE(InfoExtractor):
VimeoIE, url_transparent=True,
**traverse_obj(episode, {
'id': ('id', {int}, {str_or_none}),
'webpage_url': ('path', {lambda x: urljoin('https://laracasts.com', x)}),
'webpage_url': ('path', {urljoin('https://laracasts.com')}),
'title': ('title', {clean_html}),
'season_number': ('chapter', {int_or_none}),
'episode_number': ('position', {int_or_none}),
@@ -104,7 +104,7 @@ class LaracastsPlaylistIE(LaracastsBaseIE):
'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]}),
'categories': ('taxonomy', 'name', {str}, all, filter),
'tags': ('topics', ..., 'name', {str}),
'modified_date': ('lastUpdated', {unified_strdate}),
}),

2
yt_dlp/extractor/lbry.py
View File

@@ -66,7 +66,7 @@ class LBRYBaseIE(InfoExtractor):
'license': ('value', 'license', {str}),
'timestamp': ('timestamp', {int_or_none}),
'release_timestamp': ('value', 'release_time', {int_or_none}),
'tags': ('value', 'tags', ..., {lambda x: x or None}),
'tags': ('value', 'tags', ..., filter),
'duration': ('value', stream_type, 'duration', {int_or_none}),
'channel': ('signing_channel', 'value', 'title', {str}),
'channel_id': ('signing_channel', 'claim_id', {str}),

20
yt_dlp/extractor/learningonscreen.py
View File

@@ -6,13 +6,11 @@ from ..utils import (
ExtractorError,
clean_html,
extract_attributes,
get_element_by_class,
get_element_html_by_id,
join_nonempty,
parse_duration,
unified_timestamp,
)
from ..utils.traversal import traverse_obj
from ..utils.traversal import find_element, traverse_obj
class LearningOnScreenIE(InfoExtractor):
@@ -32,28 +30,24 @@ class LearningOnScreenIE(InfoExtractor):
def _real_initialize(self):
if not self._get_cookies('https://learningonscreen.ac.uk/').get('PHPSESSID-BOB-LIVE'):
self.raise_login_required(
'Use --cookies for authentication. See '
' https://github.com/yt-dlp/yt-dlp/wiki/FAQ#how-do-i-pass-cookies-to-yt-dlp '
'for how to manually pass cookies', method=None)
self.raise_login_required(method='session_cookies')
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
details = traverse_obj(webpage, (
{functools.partial(get_element_html_by_id, 'programme-details')}, {
'title': ({functools.partial(re.search, r'<h2>([^<]+)</h2>')}, 1, {clean_html}),
{find_element(id='programme-details', html=True)}, {
'title': ({find_element(tag='h2')}, {clean_html}),
'timestamp': (
{functools.partial(get_element_by_class, 'broadcast-date')},
{find_element(cls='broadcast-date')},
{functools.partial(re.match, r'([^<]+)')}, 1, {unified_timestamp}),
'duration': (
{functools.partial(get_element_by_class, 'prog-running-time')},
{clean_html}, {parse_duration}),
{find_element(cls='prog-running-time')}, {clean_html}, {parse_duration}),
}))
title = details.pop('title', None) or traverse_obj(webpage, (
{functools.partial(get_element_html_by_id, 'add-to-existing-playlist')},
{find_element(id='add-to-existing-playlist', html=True)},
{extract_attributes}, 'data-record-title', {clean_html}))
entries = self._parse_html5_media_entries(

22
yt_dlp/extractor/listennotes.py
View File

@@ -6,12 +6,10 @@ from ..utils import (
extract_attributes,
get_element_by_class,
get_element_html_by_id,
get_element_text_and_html_by_tag,
parse_duration,
strip_or_none,
traverse_obj,
try_call,
)
from ..utils.traversal import find_element, traverse_obj
class ListenNotesIE(InfoExtractor):
@@ -22,14 +20,14 @@ class ListenNotesIE(InfoExtractor):
'info_dict': {
'id': 'KrDgvNb_u1n',
'ext': 'mp3',
'title': 'md5:32236591a921adf17bbdbf0441b6c0e9',
'description': 'md5:c581ed197eeddcee55a67cdb547c8cbd',
'duration': 2148.0,
'channel': 'Thriving on Overload',
'title': r're:Tim O’Reilly on noticing things other people .{113}',
'description': r're:(?s)‘’We shape reality by what we notice and .{27459}',
'duration': 2215.0,
'channel': 'Amplifying Cognition',
'channel_id': 'ed84wITivxF',
'episode_id': 'e1312583fa7b4e24acfbb5131050be00',
'thumbnail': 'https://production.listennotes.com/podcasts/thriving-on-overload-ross-dawson-1wb_KospA3P-ed84wITivxF.300x300.jpg',
'channel_url': 'https://www.listennotes.com/podcasts/thriving-on-overload-ross-dawson-ed84wITivxF/',
'thumbnail': 'https://cdn-images-3.listennotes.com/podcasts/amplifying-cognition-ross-dawson-Iemft4Gdr0k-ed84wITivxF.300x300.jpg',
'channel_url': 'https://www.listennotes.com/podcasts/amplifying-cognition-ross-dawson-ed84wITivxF/',
'cast': ['Tim O’Reilly', 'Cookie Monster', 'Lao Tzu', 'Wallace Steven', 'Eric Raymond', 'Christine Peterson', 'John Maynard Keyne', 'Ross Dawson'],
},
}, {
@@ -39,13 +37,13 @@ class ListenNotesIE(InfoExtractor):
'id': 'lwEA3154JzG',
'ext': 'mp3',
'title': 'Episode 177: WireGuard with Jason Donenfeld',
'description': 'md5:24744f36456a3e95f83c1193a3458594',
'description': r're:(?s)Jason Donenfeld lead developer joins us this hour to discuss WireGuard, .{3169}',
'duration': 3861.0,
'channel': 'Ask Noah Show',
'channel_id': '4DQTzdS5-j7',
'episode_id': '8c8954b95e0b4859ad1eecec8bf6d3a4',
'channel_url': 'https://www.listennotes.com/podcasts/ask-noah-show-noah-j-chelliah-4DQTzdS5-j7/',
'thumbnail': 'https://production.listennotes.com/podcasts/ask-noah-show-noah-j-chelliah-cfbRUw9Gs3F-4DQTzdS5-j7.300x300.jpg',
'thumbnail': 'https://cdn-images-3.listennotes.com/podcasts/ask-noah-show-noah-j-chelliah-gD7vG150cxf-4DQTzdS5-j7.300x300.jpg',
'cast': ['noah showlink', 'noah show', 'noah dashboard', 'jason donenfeld'],
},
}]
@@ -70,7 +68,7 @@ class ListenNotesIE(InfoExtractor):
'id': audio_id,
'url': data['audio'],
'title': (data.get('data-title')
or try_call(lambda: get_element_text_and_html_by_tag('h1', webpage)[0])
or traverse_obj(webpage, ({find_element(tag='h1')}, {clean_html}))
or self._html_search_meta(('og:title', 'title', 'twitter:title'), webpage, 'title')),
'description': (self._clean_description(get_element_by_class('ln-text-p', webpage))
or strip_or_none(description)),

2
yt_dlp/extractor/lsm.py
View File

@@ -114,7 +114,7 @@ class LSMLREmbedIE(InfoExtractor):
def _real_extract(self, url):
query = parse_qs(url)
video_id = traverse_obj(query, (
('show', 'id'), 0, {int_or_none}, {lambda x: x or None}, {str_or_none}), get_all=False)
('show', 'id'), 0, {int_or_none}, filter, {str_or_none}), get_all=False)
webpage = self._download_webpage(url, video_id)
player_data, media_data = self._search_regex(

2
yt_dlp/extractor/magentamusik.py
View File

@@ -57,6 +57,6 @@ class MagentaMusikIE(InfoExtractor):
'duration': ('runtimeInSeconds', {int_or_none}),
'location': ('countriesOfProduction', {list}, {lambda x: join_nonempty(*x, delim=', ')}),
'release_year': ('yearOfProduction', {int_or_none}),
'categories': ('mainGenre', {str}, {lambda x: x and [x]}),
'categories': ('mainGenre', {str}, all, filter),
})),
}

2
yt_dlp/extractor/mediastream.py
View File

@@ -17,7 +17,7 @@ class MediaStreamBaseIE(InfoExtractor):
_BASE_URL_RE = r'https?://mdstrm\.com/(?:embed|live-stream)'
def _extract_mediastream_urls(self, webpage):
yield from traverse_obj(list(self._yield_json_ld(webpage, None, fatal=False)), (
yield from traverse_obj(list(self._yield_json_ld(webpage, None, default={})), (
lambda _, v: v['@type'] == 'VideoObject', ('embedUrl', 'contentUrl'),
{lambda x: x if re.match(rf'{self._BASE_URL_RE}/\w+', x) else None}))

291
yt_dlp/extractor/mildom.py
View File

@@ -1,291 +0,0 @@
import functools
import json
import uuid
from .common import InfoExtractor
from ..utils import (
ExtractorError,
OnDemandPagedList,
determine_ext,
dict_get,
float_or_none,
traverse_obj,
)
class MildomBaseIE(InfoExtractor):
_GUEST_ID = None
def _call_api(self, url, video_id, query=None, note='Downloading JSON metadata', body=None):
if not self._GUEST_ID:
self._GUEST_ID = f'pc-gp-{uuid.uuid4()}'
content = self._download_json(
url, video_id, note=note, data=json.dumps(body).encode() if body else None,
headers={'Content-Type': 'application/json'} if body else {},
query={
'__guest_id': self._GUEST_ID,
'__platform': 'web',
**(query or {}),
})
if content['code'] != 0:
raise ExtractorError(
f'Mildom says: {content["message"]} (code {content["code"]})',
expected=True)
return content['body']
class MildomIE(MildomBaseIE):
IE_NAME = 'mildom'
IE_DESC = 'Record ongoing live by specific user in Mildom'
_VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/(?P<id>\d+)'
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(f'https://www.mildom.com/{video_id}', video_id)
enterstudio = self._call_api(
'https://cloudac.mildom.com/nonolive/gappserv/live/enterstudio', video_id,
note='Downloading live metadata', query={'user_id': video_id})
result_video_id = enterstudio.get('log_id', video_id)
servers = self._call_api(
'https://cloudac.mildom.com/nonolive/gappserv/live/liveserver', result_video_id,
note='Downloading live server list', query={
'user_id': video_id,
'live_server_type': 'hls',
})
playback_token = self._call_api(
'https://cloudac.mildom.com/nonolive/gappserv/live/token', result_video_id,
note='Obtaining live playback token', body={'host_id': video_id, 'type': 'hls'})
playback_token = traverse_obj(playback_token, ('data', ..., 'token'), get_all=False)
if not playback_token:
raise ExtractorError('Failed to obtain live playback token')
formats = self._extract_m3u8_formats(
f'{servers["stream_server"]}/{video_id}_master.m3u8?{playback_token}',
result_video_id, 'mp4', headers={
'Referer': 'https://www.mildom.com/',
'Origin': 'https://www.mildom.com',
})
for fmt in formats:
fmt.setdefault('http_headers', {})['Referer'] = 'https://www.mildom.com/'
return {
'id': result_video_id,
'title': self._html_search_meta('twitter:description', webpage, default=None) or traverse_obj(enterstudio, 'anchor_intro'),
'description': traverse_obj(enterstudio, 'intro', 'live_intro', expected_type=str),
'timestamp': float_or_none(enterstudio.get('live_start_ms'), scale=1000),
'uploader': self._html_search_meta('twitter:title', webpage, default=None) or traverse_obj(enterstudio, 'loginname'),
'uploader_id': video_id,
'formats': formats,
'is_live': True,
}
class MildomVodIE(MildomBaseIE):
IE_NAME = 'mildom:vod'
IE_DESC = 'VOD in Mildom'
_VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/playback/(?P<user_id>\d+)/(?P<id>(?P=user_id)-[a-zA-Z0-9]+-?[0-9]*)'
_TESTS = [{
'url': 'https://www.mildom.com/playback/10882672/10882672-1597662269',
'info_dict': {
'id': '10882672-1597662269',
'ext': 'mp4',
'title': '始めてのミルダム配信じゃぃ！',
'thumbnail': r're:^https?://.*\.(png|jpg)$',
'upload_date': '20200817',
'duration': 4138.37,
'description': 'ゲームをしたくて！',
'timestamp': 1597662269.0,
'uploader_id': '10882672',
'uploader': 'kson組長(けいそん)',
},
}, {
'url': 'https://www.mildom.com/playback/10882672/10882672-1597758589870-477',
'info_dict': {
'id': '10882672-1597758589870-477',
'ext': 'mp4',
'title': '【kson】感染メイズ！麻酔銃で無双する',
'thumbnail': r're:^https?://.*\.(png|jpg)$',
'timestamp': 1597759093.0,
'uploader': 'kson組長(けいそん)',
'duration': 4302.58,
'uploader_id': '10882672',
'description': 'このステージ絶対乗り越えたい',
'upload_date': '20200818',
},
}, {
'url': 'https://www.mildom.com/playback/10882672/10882672-buha9td2lrn97fk2jme0',
'info_dict': {
'id': '10882672-buha9td2lrn97fk2jme0',
'ext': 'mp4',
'title': '【kson組長】CART RACER!!!',
'thumbnail': r're:^https?://.*\.(png|jpg)$',
'uploader_id': '10882672',
'uploader': 'kson組長(けいそん)',
'upload_date': '20201104',
'timestamp': 1604494797.0,
'duration': 4657.25,
'description': 'WTF',
},
}]
def _real_extract(self, url):
user_id, video_id = self._match_valid_url(url).group('user_id', 'id')
webpage = self._download_webpage(f'https://www.mildom.com/playback/{user_id}/{video_id}', video_id)
autoplay = self._call_api(
'https://cloudac.mildom.com/nonolive/videocontent/playback/getPlaybackDetail', video_id,
note='Downloading playback metadata', query={
'v_id': video_id,
})['playback']
formats = [{
'url': autoplay['audio_url'],
'format_id': 'audio',
'protocol': 'm3u8_native',
'vcodec': 'none',
'acodec': 'aac',
'ext': 'm4a',
}]
for fmt in autoplay['video_link']:
formats.append({
'format_id': 'video-{}'.format(fmt['name']),
'url': fmt['url'],
'protocol': 'm3u8_native',
'width': fmt['level'] * autoplay['video_width'] // autoplay['video_height'],
'height': fmt['level'],
'vcodec': 'h264',
'acodec': 'aac',
'ext': 'mp4',
})
return {
'id': video_id,
'title': self._html_search_meta(('og:description', 'description'), webpage, default=None) or autoplay.get('title'),
'description': traverse_obj(autoplay, 'video_intro'),
'timestamp': float_or_none(autoplay.get('publish_time'), scale=1000),
'duration': float_or_none(autoplay.get('video_length'), scale=1000),
'thumbnail': dict_get(autoplay, ('upload_pic', 'video_pic')),
'uploader': traverse_obj(autoplay, ('author_info', 'login_name')),
'uploader_id': user_id,
'formats': formats,
}
class MildomClipIE(MildomBaseIE):
IE_NAME = 'mildom:clip'
IE_DESC = 'Clip in Mildom'
_VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/clip/(?P<id>(?P<user_id>\d+)-[a-zA-Z0-9]+)'
_TESTS = [{
'url': 'https://www.mildom.com/clip/10042245-63921673e7b147ebb0806d42b5ba5ce9',
'info_dict': {
'id': '10042245-63921673e7b147ebb0806d42b5ba5ce9',
'title': '全然違ったよ',
'timestamp': 1619181890,
'duration': 59,
'thumbnail': r're:https?://.+',
'uploader': 'ざきんぽ',
'uploader_id': '10042245',
},
}, {
'url': 'https://www.mildom.com/clip/10111524-ebf4036e5aa8411c99fb3a1ae0902864',
'info_dict': {
'id': '10111524-ebf4036e5aa8411c99fb3a1ae0902864',
'title': 'かっこいい',
'timestamp': 1621094003,
'duration': 59,
'thumbnail': r're:https?://.+',
'uploader': '(ルーキー',
'uploader_id': '10111524',
},
}, {
'url': 'https://www.mildom.com/clip/10660174-2c539e6e277c4aaeb4b1fbe8d22cb902',
'info_dict': {
'id': '10660174-2c539e6e277c4aaeb4b1fbe8d22cb902',
'title': 'あ',
'timestamp': 1614769431,
'duration': 31,
'thumbnail': r're:https?://.+',
'uploader': 'ドルゴルスレンギーン＝ダグワドルジ',
'uploader_id': '10660174',
},
}]
def _real_extract(self, url):
user_id, video_id = self._match_valid_url(url).group('user_id', 'id')
webpage = self._download_webpage(f'https://www.mildom.com/clip/{video_id}', video_id)
clip_detail = self._call_api(
'https://cloudac-cf-jp.mildom.com/nonolive/videocontent/clip/detail', video_id,
note='Downloading playback metadata', query={
'clip_id': video_id,
})
return {
'id': video_id,
'title': self._html_search_meta(
('og:description', 'description'), webpage, default=None) or clip_detail.get('title'),
'timestamp': float_or_none(clip_detail.get('create_time')),
'duration': float_or_none(clip_detail.get('length')),
'thumbnail': clip_detail.get('cover'),
'uploader': traverse_obj(clip_detail, ('user_info', 'loginname')),
'uploader_id': user_id,
'url': clip_detail['url'],
'ext': determine_ext(clip_detail.get('url'), 'mp4'),
}
class MildomUserVodIE(MildomBaseIE):
IE_NAME = 'mildom:user:vod'
IE_DESC = 'Download all VODs from specific user in Mildom'
_VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/profile/(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.mildom.com/profile/10093333',
'info_dict': {
'id': '10093333',
'title': 'Uploads from ねこばたけ',
},
'playlist_mincount': 732,
}, {
'url': 'https://www.mildom.com/profile/10882672',
'info_dict': {
'id': '10882672',
'title': 'Uploads from kson組長(けいそん)',
},
'playlist_mincount': 201,
}]
def _fetch_page(self, user_id, page):
page += 1
reply = self._call_api(
'https://cloudac.mildom.com/nonolive/videocontent/profile/playbackList',
user_id, note=f'Downloading page {page}', query={
'user_id': user_id,
'page': page,
'limit': '30',
})
if not reply:
return
for x in reply:
v_id = x.get('v_id')
if not v_id:
continue
yield self.url_result(f'https://www.mildom.com/playback/{user_id}/{v_id}')
def _real_extract(self, url):
user_id = self._match_id(url)
self.to_screen(f'This will download all VODs belonging to user. To download ongoing live video, use "https://www.mildom.com/{user_id}" instead')
profile = self._call_api(
'https://cloudac.mildom.com/nonolive/gappserv/user/profileV2', user_id,
query={'user_id': user_id}, note='Downloading user profile')['user_info']
return self.playlist_result(
OnDemandPagedList(functools.partial(self._fetch_page, user_id), 30),
user_id, f'Uploads from {profile["loginname"]}')

59
yt_dlp/extractor/mixch.py
View File

@@ -12,7 +12,7 @@ from ..utils.traversal import traverse_obj
class MixchIE(InfoExtractor):
IE_NAME = 'mixch'
_VALID_URL = r'https?://(?:www\.)?mixch\.tv/u/(?P<id>\d+)'
_VALID_URL = r'https?://mixch\.tv/u/(?P<id>\d+)'
_TESTS = [{
'url': 'https://mixch.tv/u/16943797/live',
@@ -66,7 +66,7 @@ class MixchIE(InfoExtractor):
note='Downloading comments', errnote='Failed to download comments'), (..., {
'author': ('name', {str}),
'author_id': ('user_id', {str_or_none}),
'id': ('message_id', {str}, {lambda x: x or None}),
'id': ('message_id', {str}, filter),
'text': ('body', {str}),
'timestamp': ('created', {int}),
}))
@@ -74,7 +74,7 @@ class MixchIE(InfoExtractor):
class MixchArchiveIE(InfoExtractor):
IE_NAME = 'mixch:archive'
_VALID_URL = r'https?://(?:www\.)?mixch\.tv/archive/(?P<id>\d+)'
_VALID_URL = r'https?://mixch\.tv/archive/(?P<id>\d+)'
_TESTS = [{
'url': 'https://mixch.tv/archive/421',
@@ -116,3 +116,56 @@ class MixchArchiveIE(InfoExtractor):
'formats': self._extract_m3u8_formats(info_json['archiveURL'], video_id),
'thumbnail': traverse_obj(info_json, ('thumbnailURL', {url_or_none})),
}
class MixchMovieIE(InfoExtractor):
IE_NAME = 'mixch:movie'
_VALID_URL = r'https?://mixch\.tv/m/(?P<id>\w+)'
_TESTS = [{
'url': 'https://mixch.tv/m/Ve8KNkJ5',
'info_dict': {
'id': 'Ve8KNkJ5',
'title': '夏☀️\nムービーへのポイントは本イベントに加算されないので配信にてお願い致します🙇🏻\u200d♀️\n#TGCCAMPUS #ミス東大 #ミス東大2024 ',
'ext': 'mp4',
'uploader': 'ミス東大No.5 松藤百香🍑💫',
'uploader_id': '12299174',
'channel_follower_count': int,
'view_count': int,
'like_count': int,
'comment_count': int,
'timestamp': 1724070828,
'uploader_url': 'https://mixch.tv/u/12299174',
'live_status': 'not_live',
'upload_date': '20240819',
},
}, {
'url': 'https://mixch.tv/m/61DzpIKE',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._download_json(
f'https://mixch.tv/api-web/movies/{video_id}', video_id)
return {
'id': video_id,
'formats': [{
'format_id': 'mp4',
'url': data['movie']['file'],
'ext': 'mp4',
}],
**traverse_obj(data, {
'title': ('movie', 'title', {str}),
'thumbnail': ('movie', 'thumbnailURL', {url_or_none}),
'uploader': ('ownerInfo', 'name', {str}),
'uploader_id': ('ownerInfo', 'id', {int}, {str_or_none}),
'channel_follower_count': ('ownerInfo', 'fan', {int_or_none}),
'view_count': ('ownerInfo', 'view', {int_or_none}),
'like_count': ('movie', 'favCount', {int_or_none}),
'comment_count': ('movie', 'commentCount', {int_or_none}),
'timestamp': ('movie', 'published', {int_or_none}),
'uploader_url': ('ownerInfo', 'id', {lambda x: x and f'https://mixch.tv/u/{x}'}, filter),
}),
'live_status': 'not_live',
}

37
yt_dlp/extractor/monstercat.py
View File

@@ -4,15 +4,11 @@ from .common import InfoExtractor
from ..utils import (
clean_html,
extract_attributes,
get_element_by_class,
get_element_html_by_class,
get_element_text_and_html_by_tag,
int_or_none,
strip_or_none,
traverse_obj,
try_call,
unified_strdate,
)
from ..utils.traversal import find_element, traverse_obj
class MonstercatIE(InfoExtractor):
@@ -26,19 +22,21 @@ class MonstercatIE(InfoExtractor):
'thumbnail': 'https://www.monstercat.com/release/742779548009/cover',
'release_date': '20230711',
'album': 'The Secret Language of Trees',
'album_artist': 'BT',
'album_artists': ['BT'],
},
}]
def _extract_tracks(self, table, album_meta):
for td in re.findall(r'<tr[^<]*>((?:(?!</tr>)[\w\W])+)', table): # regex by chatgpt due to lack of get_elements_by_tag
title = clean_html(try_call(
lambda: get_element_by_class('d-inline-flex flex-column', td).partition(' <span')[0]))
ids = extract_attributes(try_call(lambda: get_element_html_by_class('btn-play cursor-pointer mr-small', td)) or '')
title = traverse_obj(td, (
{find_element(cls='d-inline-flex flex-column')},
{lambda x: x.partition(' <span')}, 0, {clean_html}))
ids = traverse_obj(td, (
{find_element(cls='btn-play cursor-pointer mr-small', html=True)}, {extract_attributes})) or {}
track_id = ids.get('data-track-id')
release_id = ids.get('data-release-id')
track_number = int_or_none(try_call(lambda: get_element_by_class('py-xsmall', td)))
track_number = traverse_obj(td, ({find_element(cls='py-xsmall')}, {int_or_none}))
if not track_id or not release_id:
self.report_warning(f'Skipping track {track_number}, ID(s) not found')
self.write_debug(f'release_id={release_id!r} track_id={track_id!r}')
@@ -48,7 +46,7 @@ class MonstercatIE(InfoExtractor):
'title': title,
'track': title,
'track_number': track_number,
'artist': clean_html(try_call(lambda: get_element_by_class('d-block fs-xxsmall', td))),
'artists': traverse_obj(td, ({find_element(cls='d-block fs-xxsmall')}, {clean_html}, all)),
'url': f'https://www.monstercat.com/api/release/{release_id}/track-stream/{track_id}',
'id': track_id,
'ext': 'mp3',
@@ -57,20 +55,19 @@ class MonstercatIE(InfoExtractor):
def _real_extract(self, url):
url_id = self._match_id(url)
html = self._download_webpage(url, url_id)
# wrap all `get_elements` in `try_call`, HTMLParser has problems with site's html
tracklist_table = try_call(lambda: get_element_by_class('table table-small', html)) or ''
title = try_call(lambda: get_element_text_and_html_by_tag('h1', html)[0])
date = traverse_obj(html, ({lambda html: get_element_by_class('font-italic mb-medium d-tablet-none d-phone-block',
html).partition('Released ')}, 2, {strip_or_none}, {unified_strdate}))
# NB: HTMLParser may choke on this html; use {find_element} or try_call(lambda: get_element...)
tracklist_table = traverse_obj(html, {find_element(cls='table table-small')}) or ''
title = traverse_obj(html, ({find_element(tag='h1')}, {clean_html}))
album_meta = {
'title': title,
'album': title,
'thumbnail': f'https://www.monstercat.com/release/{url_id}/cover',
'album_artist': try_call(
lambda: get_element_by_class('h-normal text-uppercase mb-desktop-medium mb-smallish', html)),
'release_date': date,
'album_artists': traverse_obj(html, (
{find_element(cls='h-normal text-uppercase mb-desktop-medium mb-smallish')}, {clean_html}, all)),
'release_date': traverse_obj(html, (
{find_element(cls='font-italic mb-medium d-tablet-none d-phone-block')},
{lambda x: x.partition('Released ')}, 2, {strip_or_none}, {unified_strdate})),
}
return self.playlist_result(

2
yt_dlp/extractor/nebula.py
View File

@@ -86,7 +86,7 @@ class NebulaBaseIE(InfoExtractor):
def _extract_video_metadata(self, episode):
channel_url = traverse_obj(
episode, (('channel_slug', 'class_slug'), {lambda x: urljoin('https://nebula.tv/', x)}), get_all=False)
episode, (('channel_slug', 'class_slug'), {urljoin('https://nebula.tv/')}), get_all=False)
return {
'id': episode['id'].partition(':')[2],
**traverse_obj(episode, {

31
yt_dlp/extractor/nekohacker.py
View File

@@ -6,12 +6,10 @@ from ..utils import (
determine_ext,
extract_attributes,
get_element_by_class,
get_element_text_and_html_by_tag,
parse_duration,
traverse_obj,
try_call,
url_or_none,
)
from ..utils.traversal import find_element, traverse_obj
class NekoHackerIE(InfoExtractor):
@@ -35,7 +33,7 @@ class NekoHackerIE(InfoExtractor):
'acodec': 'mp3',
'release_date': '20221101',
'album': 'Nekoverse',
'artist': 'Neko Hacker',
'artists': ['Neko Hacker'],
'track': 'Spaceship',
'track_number': 1,
'duration': 195.0,
@@ -53,7 +51,7 @@ class NekoHackerIE(InfoExtractor):
'acodec': 'mp3',
'release_date': '20221101',
'album': 'Nekoverse',
'artist': 'Neko Hacker',
'artists': ['Neko Hacker'],
'track': 'City Runner',
'track_number': 2,
'duration': 148.0,
@@ -71,7 +69,7 @@ class NekoHackerIE(InfoExtractor):
'acodec': 'mp3',
'release_date': '20221101',
'album': 'Nekoverse',
'artist': 'Neko Hacker',
'artists': ['Neko Hacker'],
'track': 'Nature Talk',
'track_number': 3,
'duration': 174.0,
@@ -89,7 +87,7 @@ class NekoHackerIE(InfoExtractor):
'acodec': 'mp3',
'release_date': '20221101',
'album': 'Nekoverse',
'artist': 'Neko Hacker',
'artists': ['Neko Hacker'],
'track': 'Crystal World',
'track_number': 4,
'duration': 199.0,
@@ -115,7 +113,7 @@ class NekoHackerIE(InfoExtractor):
'acodec': 'mp3',
'release_date': '20210115',
'album': '進め！むじなカンパニー',
'artist': 'Neko Hacker',
'artists': ['Neko Hacker'],
'track': 'md5:1a5fcbc96ca3c3265b1c6f9f79f30fd0',
'track_number': 1,
},
@@ -132,7 +130,7 @@ class NekoHackerIE(InfoExtractor):
'acodec': 'mp3',
'release_date': '20210115',
'album': '進め！むじなカンパニー',
'artist': 'Neko Hacker',
'artists': ['Neko Hacker'],
'track': 'むじな de なじむ feat. 六科なじむ (CV: 日高里菜 )',
'track_number': 2,
},
@@ -149,7 +147,7 @@ class NekoHackerIE(InfoExtractor):
'acodec': 'mp3',
'release_date': '20210115',
'album': '進め！むじなカンパニー',
'artist': 'Neko Hacker',
'artists': ['Neko Hacker'],
'track': '進め！むじなカンパニー (instrumental)',
'track_number': 3,
},
@@ -166,7 +164,7 @@ class NekoHackerIE(InfoExtractor):
'acodec': 'mp3',
'release_date': '20210115',
'album': '進め！むじなカンパニー',
'artist': 'Neko Hacker',
'artists': ['Neko Hacker'],
'track': 'むじな de なじむ (instrumental)',
'track_number': 4,
},
@@ -181,14 +179,17 @@ class NekoHackerIE(InfoExtractor):
playlist = get_element_by_class('playlist', webpage)
if not playlist:
iframe = try_call(lambda: get_element_text_and_html_by_tag('iframe', webpage)[1]) or ''
iframe_src = url_or_none(extract_attributes(iframe).get('src'))
iframe_src = traverse_obj(webpage, (
{find_element(tag='iframe', html=True)}, {extract_attributes}, 'src', {url_or_none}))
if not iframe_src:
raise ExtractorError('No playlist or embed found in webpage')
elif re.match(r'https?://(?:\w+\.)?spotify\.com/', iframe_src):
raise ExtractorError('Spotify embeds are not supported', expected=True)
return self.url_result(url, 'Generic')
player_params = self._search_json(
r'var srp_player_params_[\da-f]+\s*=', webpage, 'player params', playlist_id, default={})
entries = []
for track_number, track in enumerate(re.findall(r'(<li[^>]+data-audiopath[^>]+>)', playlist), 1):
entry = traverse_obj(extract_attributes(track), {
@@ -200,12 +201,12 @@ class NekoHackerIE(InfoExtractor):
'album': 'data-albumtitle',
'duration': ('data-tracktime', {parse_duration}),
'release_date': ('data-releasedate', {lambda x: re.match(r'\d{8}', x.replace('.', ''))}, 0),
'thumbnail': ('data-albumart', {url_or_none}),
})
entries.append({
**entry,
'thumbnail': url_or_none(player_params.get('artwork')),
'track_number': track_number,
'artist': 'Neko Hacker',
'artists': ['Neko Hacker'],
'vcodec': 'none',
'acodec': 'mp3' if entry['ext'] == 'mp3' else None,
})

20
yt_dlp/extractor/neteasemusic.py
View File

@@ -36,10 +36,6 @@ class NetEaseMusicBaseIE(InfoExtractor):
_API_BASE = 'http://music.163.com/api/'
_GEO_BYPASS = False
@staticmethod
def _kilo_or_none(value):
return int_or_none(value, scale=1000)
def _create_eapi_cipher(self, api_path, query_body, cookies):
request_text = json.dumps({**query_body, 'header': cookies}, separators=(',', ':'))
@@ -101,7 +97,7 @@ class NetEaseMusicBaseIE(InfoExtractor):
'vcodec': 'none',
**traverse_obj(song, {
'ext': ('type', {str}),
'abr': ('br', {self._kilo_or_none}),
'abr': ('br', {int_or_none(scale=1000)}),
'filesize': ('size', {int_or_none}),
}),
})
@@ -282,9 +278,9 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
**lyric_data,
**traverse_obj(info, {
'title': ('name', {str}),
'timestamp': ('album', 'publishTime', {self._kilo_or_none}),
'timestamp': ('album', 'publishTime', {int_or_none(scale=1000)}),
'thumbnail': ('album', 'picUrl', {url_or_none}),
'duration': ('duration', {self._kilo_or_none}),
'duration': ('duration', {int_or_none(scale=1000)}),
'album': ('album', 'name', {str}),
'average_rating': ('score', {int_or_none}),
}),
@@ -440,7 +436,7 @@ 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', {int_or_none(scale=1000)}),
}))
if traverse_obj(info, ('playlist', 'specialType')) == 10:
metainfo['title'] = f'{metainfo.get("title")} {strftime_or_none(metainfo.get("timestamp"), "%Y-%m-%d")}'
@@ -517,10 +513,10 @@ class NetEaseMusicMvIE(NetEaseMusicBaseIE):
'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}),
'description': (('desc', 'briefDesc'), {str}, filter),
'upload_date': ('publishTime', {unified_strdate}),
'thumbnail': ('cover', {url_or_none}),
'duration': ('duration', {self._kilo_or_none}),
'duration': ('duration', {int_or_none(scale=1000)}),
'view_count': ('playCount', {int_or_none}),
'like_count': ('likeCount', {int_or_none}),
'comment_count': ('commentCount', {int_or_none}),
@@ -588,7 +584,7 @@ class NetEaseMusicProgramIE(NetEaseMusicBaseIE):
'description': ('description', {str}),
'creator': ('dj', 'brand', {str}),
'thumbnail': ('coverUrl', {url_or_none}),
'timestamp': ('createTime', {self._kilo_or_none}),
'timestamp': ('createTime', {int_or_none(scale=1000)}),
})
if not self._yes_playlist(
@@ -598,7 +594,7 @@ class NetEaseMusicProgramIE(NetEaseMusicBaseIE):
return {
'id': str(info['mainSong']['id']),
'formats': formats,
'duration': traverse_obj(info, ('mainSong', 'duration', {self._kilo_or_none})),
'duration': traverse_obj(info, ('mainSong', 'duration', {int_or_none(scale=1000)})),
**metainfo,
}

153
yt_dlp/extractor/nfl.py
View File

@@ -11,9 +11,12 @@ from ..utils import (
clean_html,
determine_ext,
get_element_by_class,
traverse_obj,
int_or_none,
make_archive_id,
url_or_none,
urlencode_postdata,
)
from ..utils.traversal import traverse_obj
class NFLBaseIE(InfoExtractor):
@@ -75,22 +78,15 @@ class NFLBaseIE(InfoExtractor):
'osVersion': '10.0',
}, separators=(',', ':')).encode()).decode(),
'networkType': 'other',
'nflClaimGroupsToAdd': [],
'nflClaimGroupsToRemove': [],
'peacockUUID': 'undefined',
}
_ACCOUNT_INFO = {}
_API_KEY = None
_API_KEY = '3_Qa8TkWpIB8ESCBT8tY2TukbVKgO5F6BJVc7N1oComdwFzI7H2L9NOWdm11i_BY9f'
_TOKEN = None
_TOKEN_EXPIRY = 0
def _get_account_info(self, url, slug):
if not self._API_KEY:
webpage = self._download_webpage(url, slug, fatal=False) or ''
self._API_KEY = self._search_regex(
r'window\.gigyaApiKey\s*=\s*["\'](\w+)["\'];', webpage, 'API key',
fatal=False) or '3_Qa8TkWpIB8ESCBT8tY2TukbVKgO5F6BJVc7N1oComdwFzI7H2L9NOWdm11i_BY9f'
def _get_account_info(self):
cookies = self._get_cookies('https://auth-id.nfl.com/')
login_token = traverse_obj(cookies, (
(f'glt_{self._API_KEY}', lambda k, _: k.startswith('glt_')), {lambda x: x.value}), get_all=False)
@@ -103,7 +99,7 @@ class NFLBaseIE(InfoExtractor):
'or else try using --cookies-from-browser instead', expected=True)
account = self._download_json(
'https://auth-id.nfl.com/accounts.getAccountInfo', slug,
'https://auth-id.nfl.com/accounts.getAccountInfo', None,
note='Downloading account info', data=urlencode_postdata({
'include': 'profile,data',
'lang': 'en',
@@ -111,7 +107,7 @@ class NFLBaseIE(InfoExtractor):
'sdk': 'js_latest',
'login_token': login_token,
'authMode': 'cookie',
'pageURL': url,
'pageURL': 'https://www.nfl.com/',
'sdkBuild': traverse_obj(cookies, (
'gig_canary_ver', {lambda x: x.value.partition('-')[0]}), default='15170'),
'format': 'json',
@@ -126,55 +122,78 @@ class NFLBaseIE(InfoExtractor):
if len(self._ACCOUNT_INFO) != 3:
raise ExtractorError('Failed to retrieve account info with provided cookies', expected=True)
def _get_auth_token(self, url, slug):
def _get_auth_token(self):
if self._TOKEN and self._TOKEN_EXPIRY > int(time.time() + 30):
return
if not self._ACCOUNT_INFO:
self._get_account_info(url, slug)
token = self._download_json(
'https://api.nfl.com/identity/v3/token%s' % (
'/refresh' if self._ACCOUNT_INFO.get('refreshToken') else ''),
slug, headers={'Content-Type': 'application/json'}, note='Downloading access token',
None, headers={'Content-Type': 'application/json'}, note='Downloading access token',
data=json.dumps({**self._CLIENT_DATA, **self._ACCOUNT_INFO}, separators=(',', ':')).encode())
self._TOKEN = token['accessToken']
self._TOKEN_EXPIRY = token['expiresIn']
self._ACCOUNT_INFO['refreshToken'] = token['refreshToken']
def _extract_video(self, mcp_id, is_live=False):
self._get_auth_token()
data = self._download_json(
f'https://api.nfl.com/play/v1/asset/{mcp_id}', mcp_id, headers={
'Authorization': f'Bearer {self._TOKEN}',
'Accept': 'application/json',
'Content-Type': 'application/json',
}, data=json.dumps({'init': True, 'live': is_live}, separators=(',', ':')).encode())
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
data['accessUrl'], mcp_id, 'mp4', m3u8_id='hls')
return {
'id': mcp_id,
'formats': formats,
'subtitles': subtitles,
'is_live': is_live,
'_old_archive_ids': [make_archive_id(AnvatoIE, mcp_id)],
**traverse_obj(data, ('metadata', {
'title': ('event', ('def_title', 'friendlyName'), {str}, any),
'description': ('event', 'def_description', {str}),
'duration': ('event', 'duration', {int_or_none}),
'thumbnails': ('thumbnails', ..., 'url', {'url': {url_or_none}}),
})),
}
def _parse_video_config(self, video_config, display_id):
video_config = self._parse_json(video_config, display_id)
is_live = traverse_obj(video_config, ('live', {bool})) or False
item = video_config['playlist'][0]
mcp_id = item.get('mcpID')
if mcp_id:
info = self.url_result(f'{self._ANVATO_PREFIX}{mcp_id}', AnvatoIE, mcp_id)
if mcp_id := item.get('mcpID'):
return self._extract_video(mcp_id, is_live=is_live)
info = {'id': item.get('id') or item['entityId']}
item_url = item['url']
ext = determine_ext(item_url)
if ext == 'm3u8':
info['formats'] = self._extract_m3u8_formats(item_url, info['id'], 'mp4')
else:
media_id = item.get('id') or item['entityId']
title = item.get('title')
item_url = item['url']
info = {'id': media_id}
ext = determine_ext(item_url)
if ext == 'm3u8':
info['formats'] = self._extract_m3u8_formats(item_url, media_id, 'mp4')
else:
info['url'] = item_url
if item.get('audio') is True:
info['vcodec'] = 'none'
is_live = video_config.get('live') is True
thumbnails = None
image_url = item.get(item.get('imageSrc')) or item.get(item.get('posterImage'))
if image_url:
thumbnails = [{
'url': image_url,
'ext': determine_ext(image_url, 'jpg'),
}]
info.update({
'title': title,
'is_live': is_live,
'description': clean_html(item.get('description')),
'thumbnails': thumbnails,
})
info['url'] = item_url
if item.get('audio') is True:
info['vcodec'] = 'none'
thumbnails = None
if image_url := traverse_obj(item, 'imageSrc', 'posterImage', expected_type=url_or_none):
thumbnails = [{
'url': image_url,
'ext': determine_ext(image_url, 'jpg'),
}]
info.update({
**traverse_obj(item, {
'title': ('title', {str}),
'description': ('description', {clean_html}),
}),
'is_live': is_live,
'thumbnails': thumbnails,
})
return info
@@ -188,24 +207,20 @@ class NFLIE(NFLBaseIE):
'ext': 'mp4',
'title': "Baker Mayfield's game-changing plays from 3-TD game Week 14",
'description': 'md5:85e05a3cc163f8c344340f220521136d',
'upload_date': '20201215',
'timestamp': 1608009755,
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'NFL',
'tags': 'count:6',
'thumbnail': r're:https?://.+\.jpg',
'duration': 157,
'categories': 'count:3',
'_old_archive_ids': ['anvato 899441'],
},
}, {
'url': 'https://www.chiefs.com/listen/patrick-mahomes-travis-kelce-react-to-win-over-dolphins-the-breakdown',
'md5': '6886b32c24b463038c760ceb55a34566',
'md5': '92a517f05bd3eb50fe50244bc621aec8',
'info_dict': {
'id': 'd87e8790-3e14-11eb-8ceb-ff05c2867f99',
'id': '8b7c3625-a461-4751-8db4-85f536f2bbd0',
'ext': 'mp3',
'title': 'Patrick Mahomes, Travis Kelce React to Win Over Dolphins | The Breakdown',
'description': 'md5:12ada8ee70e6762658c30e223e095075',
'thumbnail': 'https://static.clubs.nfl.com/image/private/t_editorial_landscape_12_desktop/v1571153441/chiefs/rfljejccnyhhkpkfq855',
},
'skip': 'HTTP Error 404: Not Found',
}, {
'url': 'https://www.buffalobills.com/video/buffalo-bills-military-recognition-week-14',
'only_matching': True,
@@ -236,13 +251,16 @@ class NFLArticleIE(NFLBaseIE):
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
entries = []
for video_config in re.findall(self._VIDEO_CONFIG_REGEX, webpage):
entries.append(self._parse_video_config(video_config, display_id))
def entries():
for video_config in re.findall(self._VIDEO_CONFIG_REGEX, webpage):
yield self._parse_video_config(video_config, display_id)
title = clean_html(get_element_by_class(
'nfl-c-article__title', webpage)) or self._html_search_meta(
['og:title', 'twitter:title'], webpage)
return self.playlist_result(entries, display_id, title)
return self.playlist_result(entries(), display_id, title)
class NFLPlusReplayIE(NFLBaseIE):
@@ -307,6 +325,9 @@ class NFLPlusReplayIE(NFLBaseIE):
'all_22': 'All-22',
}
def _real_initialize(self):
self._get_account_info()
def _real_extract(self, url):
slug, video_id = self._match_valid_url(url).group('slug', 'id')
requested_types = self._configuration_arg('type', ['all'])
@@ -315,7 +336,7 @@ class NFLPlusReplayIE(NFLBaseIE):
requested_types = traverse_obj(self._REPLAY_TYPES, (None, requested_types))
if not video_id:
self._get_auth_token(url, slug)
self._get_auth_token()
headers = {'Authorization': f'Bearer {self._TOKEN}'}
game_id = self._download_json(
f'https://api.nfl.com/football/v2/games/externalId/slug/{slug}', slug,
@@ -328,14 +349,13 @@ class NFLPlusReplayIE(NFLBaseIE):
'items', lambda _, v: v['subType'] == requested_types[0], 'mcpPlaybackId'), get_all=False)
if video_id:
return self.url_result(f'{self._ANVATO_PREFIX}{video_id}', AnvatoIE, video_id)
return self._extract_video(video_id)
def entries():
for replay in traverse_obj(
replays, ('items', lambda _, v: v['mcpPlaybackId'] and v['subType'] in requested_types),
):
video_id = replay['mcpPlaybackId']
yield self.url_result(f'{self._ANVATO_PREFIX}{video_id}', AnvatoIE, video_id)
yield self._extract_video(replay['mcpPlaybackId'])
return self.playlist_result(entries(), slug)
@@ -362,12 +382,15 @@ class NFLPlusEpisodeIE(NFLBaseIE):
'params': {'skip_download': 'm3u8'},
}]
def _real_initialize(self):
self._get_account_info()
def _real_extract(self, url):
slug = self._match_id(url)
self._get_auth_token(url, slug)
self._get_auth_token()
video_id = self._download_json(
f'https://api.nfl.com/content/v1/videos/episodes/{slug}', slug, headers={
'Authorization': f'Bearer {self._TOKEN}',
})['mcpPlaybackId']
return self.url_result(f'{self._ANVATO_PREFIX}{video_id}', AnvatoIE, video_id)
return self._extract_video(video_id)

6
yt_dlp/extractor/niconico.py
View File

@@ -371,11 +371,11 @@ class NiconicoIE(InfoExtractor):
'acodec': 'aac',
'vcodec': 'h264',
**traverse_obj(audio_quality, ('metadata', {
'abr': ('bitrate', {functools.partial(float_or_none, scale=1000)}),
'abr': ('bitrate', {float_or_none(scale=1000)}),
'asr': ('samplingRate', {int_or_none}),
})),
**traverse_obj(video_quality, ('metadata', {
'vbr': ('bitrate', {functools.partial(float_or_none, scale=1000)}),
'vbr': ('bitrate', {float_or_none(scale=1000)}),
'height': ('resolution', 'height', {int_or_none}),
'width': ('resolution', 'width', {int_or_none}),
})),
@@ -428,7 +428,7 @@ class NiconicoIE(InfoExtractor):
**audio_fmt,
**traverse_obj(audios, (lambda _, v: audio_fmt['format_id'].startswith(v['id']), {
'format_id': ('id', {str}),
'abr': ('bitRate', {functools.partial(float_or_none, scale=1000)}),
'abr': ('bitRate', {float_or_none(scale=1000)}),
'asr': ('samplingRate', {int_or_none}),
}), get_all=False),
'acodec': 'aac',

11
yt_dlp/extractor/nubilesporn.py
View File

@@ -10,10 +10,10 @@ from ..utils import (
get_element_html_by_class,
get_elements_by_class,
int_or_none,
try_call,
unified_timestamp,
urlencode_postdata,
)
from ..utils.traversal import find_element, find_elements, traverse_obj
class NubilesPornIE(InfoExtractor):
@@ -70,9 +70,8 @@ class NubilesPornIE(InfoExtractor):
url, get_element_by_class('watch-page-video-wrapper', page), video_id)[0]
channel_id, channel_name = self._search_regex(
r'/video/website/(?P<id>\d+).+>(?P<name>\w+).com', get_element_html_by_class('site-link', page),
r'/video/website/(?P<id>\d+).+>(?P<name>\w+).com', get_element_html_by_class('site-link', page) or '',
'channel', fatal=False, group=('id', 'name')) or (None, None)
channel_name = re.sub(r'([^A-Z]+)([A-Z]+)', r'\1 \2', channel_name)
return {
'id': video_id,
@@ -82,14 +81,14 @@ class NubilesPornIE(InfoExtractor):
'thumbnail': media_entries.get('thumbnail'),
'description': clean_html(get_element_html_by_class('content-pane-description', page)),
'timestamp': unified_timestamp(get_element_by_class('date', page)),
'channel': channel_name,
'channel': re.sub(r'([^A-Z]+)([A-Z]+)', r'\1 \2', channel_name) if channel_name else None,
'channel_id': channel_id,
'channel_url': format_field(channel_id, None, 'https://members.nubiles-porn.com/video/website/%s'),
'like_count': int_or_none(get_element_by_id('likecount', page)),
'average_rating': float_or_none(get_element_by_class('score', page)),
'age_limit': 18,
'categories': try_call(lambda: list(map(clean_html, get_elements_by_class('btn', get_element_by_class('categories', page))))),
'tags': try_call(lambda: list(map(clean_html, get_elements_by_class('btn', get_elements_by_class('tags', page)[1])))),
'categories': traverse_obj(page, ({find_element(cls='categories')}, {find_elements(cls='btn')}, ..., {clean_html})),
'tags': traverse_obj(page, ({find_elements(cls='tags')}, 1, {find_elements(cls='btn')}, ..., {clean_html})),
'cast': get_elements_by_class('content-pane-performer', page),
'availability': 'needs_auth',
'series': channel_name,

2
yt_dlp/extractor/nytimes.py
View File

@@ -235,7 +235,7 @@ class NYTimesArticleIE(NYTimesBaseIE):
details = traverse_obj(block, {
'id': ('sourceId', {str}),
'uploader': ('bylines', ..., 'renderedRepresentation', {str}),
'duration': (None, (('duration', {lambda x: float_or_none(x, scale=1000)}), ('length', {int_or_none}))),
'duration': (None, (('duration', {float_or_none(scale=1000)}), ('length', {int_or_none}))),
'timestamp': ('firstPublished', {parse_iso8601}),
'series': ('podcastSeries', {str}),
}, get_all=False)

2
yt_dlp/extractor/ondemandkorea.py
View File

@@ -115,7 +115,7 @@ class OnDemandKoreaIE(InfoExtractor):
**traverse_obj(data, {
'thumbnail': ('episode', 'images', 'thumbnail', {url_or_none}),
'release_date': ('episode', 'release_date', {lambda x: x.replace('-', '')}, {unified_strdate}),
'duration': ('duration', {functools.partial(float_or_none, scale=1000)}),
'duration': ('duration', {float_or_none(scale=1000)}),
'age_limit': ('age_rating', 'name', {lambda x: x.replace('R', '')}, {parse_age_limit}),
'series': ('episode', {if_series(key='program')}, 'title'),
'series_id': ('episode', {if_series(key='program')}, 'id', {str_or_none}),

5
yt_dlp/extractor/orf.py
View File

@@ -1,5 +1,4 @@
import base64
import functools
import re
from .common import InfoExtractor
@@ -192,7 +191,7 @@ class ORFPodcastIE(InfoExtractor):
'ext': ('enclosures', 0, 'type', {mimetype2ext}),
'title': 'title',
'description': ('description', {clean_html}),
'duration': ('duration', {functools.partial(float_or_none, scale=1000)}),
'duration': ('duration', {float_or_none(scale=1000)}),
'series': ('podcast', 'title'),
})),
}
@@ -494,7 +493,7 @@ class ORFONIE(InfoExtractor):
return traverse_obj(api_json, {
'id': ('id', {int}, {str_or_none}),
'age_limit': ('age_classification', {parse_age_limit}),
'duration': ('exact_duration', {functools.partial(float_or_none, scale=1000)}),
'duration': ('exact_duration', {float_or_none(scale=1000)}),
'title': (('title', 'headline'), {str}),
'description': (('description', 'teaser_text'), {str}),
'media_type': ('video_type', {str}),

4
yt_dlp/extractor/parler.py
View File

@@ -1,5 +1,3 @@
import functools
from .common import InfoExtractor
from .youtube import YoutubeIE
from ..utils import (
@@ -83,7 +81,7 @@ class ParlerIE(InfoExtractor):
'timestamp': ('date_created', {unified_timestamp}),
'uploader': ('user', 'name', {strip_or_none}),
'uploader_id': ('user', 'username', {str}),
'uploader_url': ('user', 'username', {functools.partial(urljoin, 'https://parler.com/')}),
'uploader_url': ('user', 'username', {urljoin('https://parler.com/')}),
'view_count': ('views', {int_or_none}),
'comment_count': ('total_comments', {int_or_none}),
'repost_count': ('echos', {int_or_none}),

51
yt_dlp/extractor/patreon.py
View File

@@ -16,10 +16,10 @@ from ..utils import (
parse_iso8601,
smuggle_url,
str_or_none,
traverse_obj,
url_or_none,
urljoin,
)
from ..utils.traversal import traverse_obj, value
class PatreonBaseIE(InfoExtractor):
@@ -252,6 +252,27 @@ class PatreonIE(PatreonBaseIE):
'thumbnail': r're:^https?://.+',
},
'skip': 'Patron-only content',
}, {
# Contains a comment reply in the 'included' section
'url': 'https://www.patreon.com/posts/114721679',
'info_dict': {
'id': '114721679',
'ext': 'mp4',
'upload_date': '20241025',
'uploader': 'Japanalysis',
'like_count': int,
'thumbnail': r're:^https?://.+',
'comment_count': int,
'title': 'Karasawa Part 2',
'description': 'Part 2 of this video https://www.youtube.com/watch?v=Azms2-VTASk',
'uploader_url': 'https://www.patreon.com/japanalysis',
'uploader_id': '80504268',
'channel_url': 'https://www.patreon.com/japanalysis',
'channel_follower_count': int,
'timestamp': 1729897015,
'channel_id': '9346307',
},
'params': {'getcomments': True},
}]
_RETURN_TYPE = 'video'
@@ -404,26 +425,24 @@ class PatreonIE(PatreonBaseIE):
f'posts/{post_id}/comments', post_id, query=params, note=f'Downloading comments page {page}')
cursor = None
for comment in traverse_obj(response, (('data', ('included', lambda _, v: v['type'] == 'comment')), ...)):
for comment in traverse_obj(response, (('data', 'included'), lambda _, v: v['type'] == 'comment' and v['id'])):
count += 1
comment_id = comment.get('id')
attributes = comment.get('attributes') or {}
if comment_id is None:
continue
author_id = traverse_obj(comment, ('relationships', 'commenter', 'data', 'id'))
author_info = traverse_obj(
response, ('included', lambda _, v: v['id'] == author_id and v['type'] == 'user', 'attributes'),
get_all=False, expected_type=dict, default={})
yield {
'id': comment_id,
'text': attributes.get('body'),
'timestamp': parse_iso8601(attributes.get('created')),
'parent': traverse_obj(comment, ('relationships', 'parent', 'data', 'id'), default='root'),
'author_is_uploader': attributes.get('is_by_creator'),
**traverse_obj(comment, {
'id': ('id', {str_or_none}),
'text': ('attributes', 'body', {str}),
'timestamp': ('attributes', 'created', {parse_iso8601}),
'parent': ('relationships', 'parent', 'data', ('id', {value('root')}), {str}, any),
'author_is_uploader': ('attributes', 'is_by_creator', {bool}),
}),
**traverse_obj(response, (
'included', lambda _, v: v['id'] == author_id and v['type'] == 'user', 'attributes', {
'author': ('full_name', {str}),
'author_thumbnail': ('image_url', {url_or_none}),
}), get_all=False),
'author_id': author_id,
'author': author_info.get('full_name'),
'author_thumbnail': author_info.get('image_url'),
}
if count < traverse_obj(response, ('meta', 'count')):

136
yt_dlp/extractor/pokemon.py
View File

@@ -1,136 +0,0 @@
from .common import InfoExtractor
from ..utils import (
ExtractorError,
extract_attributes,
int_or_none,
js_to_json,
merge_dicts,
)
class PokemonIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?pokemon\.com/[a-z]{2}(?:.*?play=(?P<id>[a-z0-9]{32})|/(?:[^/]+/)+(?P<display_id>[^/?#&]+))'
_TESTS = [{
'url': 'https://www.pokemon.com/us/pokemon-episodes/20_30-the-ol-raise-and-switch/',
'md5': '2fe8eaec69768b25ef898cda9c43062e',
'info_dict': {
'id': 'afe22e30f01c41f49d4f1d9eab5cd9a4',
'ext': 'mp4',
'title': 'The Ol’ Raise and Switch!',
'description': 'md5:7db77f7107f98ba88401d3adc80ff7af',
},
'add_id': ['LimelightMedia'],
}, {
# no data-video-title
'url': 'https://www.pokemon.com/fr/episodes-pokemon/films-pokemon/pokemon-lascension-de-darkrai-2008',
'info_dict': {
'id': 'dfbaf830d7e54e179837c50c0c6cc0e1',
'ext': 'mp4',
'title': "Pokémon : L'ascension de Darkrai",
'description': 'md5:d1dbc9e206070c3e14a06ff557659fb5',
},
'add_id': ['LimelightMedia'],
'params': {
'skip_download': True,
},
}, {
'url': 'http://www.pokemon.com/uk/pokemon-episodes/?play=2e8b5c761f1d4a9286165d7748c1ece2',
'only_matching': True,
}, {
'url': 'http://www.pokemon.com/fr/episodes-pokemon/18_09-un-hiver-inattendu/',
'only_matching': True,
}, {
'url': 'http://www.pokemon.com/de/pokemon-folgen/01_20-bye-bye-smettbo/',
'only_matching': True,
}]
def _real_extract(self, url):
video_id, display_id = self._match_valid_url(url).groups()
webpage = self._download_webpage(url, video_id or display_id)
video_data = extract_attributes(self._search_regex(
r'(<[^>]+data-video-id="{}"[^>]*>)'.format(video_id if video_id else '[a-z0-9]{32}'),
webpage, 'video data element'))
video_id = video_data['data-video-id']
title = video_data.get('data-video-title') or self._html_search_meta(
'pkm-title', webpage, ' title', default=None) or self._search_regex(
r'<h1[^>]+\bclass=["\']us-title[^>]+>([^<]+)', webpage, 'title')
return {
'_type': 'url_transparent',
'id': video_id,
'url': f'limelight:media:{video_id}',
'title': title,
'description': video_data.get('data-video-summary'),
'thumbnail': video_data.get('data-video-poster'),
'series': 'Pokémon',
'season_number': int_or_none(video_data.get('data-video-season')),
'episode': title,
'episode_number': int_or_none(video_data.get('data-video-episode')),
'ie_key': 'LimelightMedia',
}
class PokemonWatchIE(InfoExtractor):
_VALID_URL = r'https?://watch\.pokemon\.com/[a-z]{2}-[a-z]{2}/(?:#/)?player(?:\.html)?\?id=(?P<id>[a-z0-9]{32})'
_API_URL = 'https://www.pokemon.com/api/pokemontv/v2/channels/{0:}'
_TESTS = [{
'url': 'https://watch.pokemon.com/en-us/player.html?id=8309a40969894a8e8d5bc1311e9c5667',
'md5': '62833938a31e61ab49ada92f524c42ff',
'info_dict': {
'id': '8309a40969894a8e8d5bc1311e9c5667',
'ext': 'mp4',
'title': 'Lillier and the Staff!',
'description': 'md5:338841b8c21b283d24bdc9b568849f04',
},
}, {
'url': 'https://watch.pokemon.com/en-us/#/player?id=3fe7752ba09141f0b0f7756d1981c6b2',
'only_matching': True,
}, {
'url': 'https://watch.pokemon.com/de-de/player.html?id=b3c402e111a4459eb47e12160ab0ba07',
'only_matching': True,
}]
def _extract_media(self, channel_array, video_id):
for channel in channel_array:
for media in channel.get('media'):
if media.get('id') == video_id:
return media
return None
def _real_extract(self, url):
video_id = self._match_id(url)
info = {
'_type': 'url',
'id': video_id,
'url': f'limelight:media:{video_id}',
'ie_key': 'LimelightMedia',
}
# API call can be avoided entirely if we are listing formats
if self.get_param('listformats', False):
return info
webpage = self._download_webpage(url, video_id)
build_vars = self._parse_json(self._search_regex(
r'(?s)buildVars\s*=\s*({.*?})', webpage, 'build vars'),
video_id, transform_source=js_to_json)
region = build_vars.get('region')
channel_array = self._download_json(self._API_URL.format(region), video_id)
video_data = self._extract_media(channel_array, video_id)
if video_data is None:
raise ExtractorError(
f'Video {video_id} does not exist', expected=True)
info['_type'] = 'url_transparent'
images = video_data.get('images')
return merge_dicts(info, {
'title': video_data.get('title'),
'description': video_data.get('description'),
'thumbnail': images.get('medium') or images.get('small'),
'series': 'Pokémon',
'season_number': int_or_none(video_data.get('season')),
'episode': video_data.get('title'),
'episode_number': int_or_none(video_data.get('episode')),
})

3
yt_dlp/extractor/pornbox.py
View File

@@ -1,4 +1,3 @@
import functools
from .common import InfoExtractor
from ..utils import (
@@ -105,7 +104,7 @@ class PornboxIE(InfoExtractor):
get_quality = qualities(['web', 'vga', 'hd', '1080p', '4k', '8k'])
metadata['formats'] = traverse_obj(stream_data, ('qualities', lambda _, v: v['src'], {
'url': 'src',
'vbr': ('bitrate', {functools.partial(int_or_none, scale=1000)}),
'vbr': ('bitrate', {int_or_none(scale=1000)}),
'format_id': ('quality', {str_or_none}),
'quality': ('quality', {get_quality}),
'width': ('size', {lambda x: int(x[:-1])}),

2
yt_dlp/extractor/pr0gramm.py
View File

@@ -198,6 +198,6 @@ class Pr0grammIE(InfoExtractor):
'dislike_count': ('down', {int}),
'timestamp': ('created', {int}),
'upload_date': ('created', {int}, {dt.date.fromtimestamp}, {lambda x: x.strftime('%Y%m%d')}),
'thumbnail': ('thumb', {lambda x: urljoin('https://thumb.pr0gramm.com', x)}),
'thumbnail': ('thumb', {urljoin('https://thumb.pr0gramm.com')}),
}),
}

2
yt_dlp/extractor/qdance.py
View File

@@ -140,7 +140,7 @@ class QDanceIE(InfoExtractor):
'description': ('description', {str.strip}),
'display_id': ('slug', {str}),
'thumbnail': ('thumbnail', {url_or_none}),
'duration': ('durationInSeconds', {int_or_none}, {lambda x: x or None}),
'duration': ('durationInSeconds', {int_or_none}, filter),
'availability': ('subscription', 'level', {extract_availability}),
'is_live': ('type', {lambda x: x.lower() == 'live'}),
'artist': ('acts', ..., {str}),

4
yt_dlp/extractor/qqmusic.py
View File

@@ -211,10 +211,10 @@ class QQMusicIE(QQMusicBaseIE):
'formats': formats,
**traverse_obj(info_data, {
'title': ('title', {str}),
'album': ('album', 'title', {str}, {lambda x: x or None}),
'album': ('album', 'title', {str}, filter),
'release_date': ('time_public', {lambda x: x.replace('-', '') or None}),
'creators': ('singer', ..., 'name', {str}),
'alt_title': ('subtitle', {str}, {lambda x: x or None}),
'alt_title': ('subtitle', {str}, filter),
'duration': ('interval', {int_or_none}),
}),
**traverse_obj(init_data, ('detail', {

105
yt_dlp/extractor/radioradicale.py Normal file
View File

@@ -0,0 +1,105 @@
from .common import InfoExtractor
from ..utils import url_or_none
from ..utils.traversal import traverse_obj
class RadioRadicaleIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?radioradicale\.it/scheda/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'https://www.radioradicale.it/scheda/471591',
'md5': 'eb0fbe43a601f1a361cbd00f3c45af4a',
'info_dict': {
'id': '471591',
'ext': 'mp4',
'title': 'md5:e8fbb8de57011a3255db0beca69af73d',
'description': 'md5:5e15a789a2fe4d67da8d1366996e89ef',
'location': 'Napoli',
'duration': 2852.0,
'timestamp': 1459987200,
'upload_date': '20160407',
'thumbnail': 'https://www.radioradicale.it/photo400/0/0/9/0/1/00901768.jpg',
},
}, {
'url': 'https://www.radioradicale.it/scheda/742783/parlamento-riunito-in-seduta-comune-11a-della-xix-legislatura',
'info_dict': {
'id': '742783',
'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
'description': '-) Votazione per l\'elezione di un giudice della Corte Costituzionale (nono scrutinio)',
'location': 'CAMERA',
'duration': 5868.0,
'timestamp': 1730246400,
'upload_date': '20241030',
},
'playlist': [{
'md5': 'aa48de55dcc45478e4cd200f299aab7d',
'info_dict': {
'id': '742783-0',
'ext': 'mp4',
'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
},
}, {
'md5': 'be915c189c70ad2920e5810f32260ff5',
'info_dict': {
'id': '742783-1',
'ext': 'mp4',
'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
},
}, {
'md5': 'f0ee4047342baf8ed3128a8417ac5e0a',
'info_dict': {
'id': '742783-2',
'ext': 'mp4',
'title': 'Parlamento riunito in seduta comune (11ª della XIX legislatura)',
},
}],
}]
def _entries(self, videos_info, page_id):
for idx, video in enumerate(traverse_obj(
videos_info, ('playlist', lambda _, v: v['sources']))):
video_id = f'{page_id}-{idx}'
formats = []
subtitles = {}
for m3u8_url in traverse_obj(video, ('sources', ..., 'src', {url_or_none})):
fmts, subs = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
for sub in traverse_obj(video, ('subtitles', ..., lambda _, v: url_or_none(v['src']))):
self._merge_subtitles({sub.get('srclang') or 'und': [{
'url': sub['src'],
'name': sub.get('label'),
}]}, target=subtitles)
yield {
'id': video_id,
'title': video.get('title'),
'formats': formats,
'subtitles': subtitles,
}
def _real_extract(self, url):
page_id = self._match_id(url)
webpage = self._download_webpage(url, page_id)
videos_info = self._search_json(
r'jQuery\.extend\(Drupal\.settings\s*,',
webpage, 'videos_info', page_id)['RRscheda']
entries = list(self._entries(videos_info, page_id))
common_info = {
'id': page_id,
'title': self._og_search_title(webpage),
'description': self._og_search_description(webpage),
'location': videos_info.get('luogo'),
**self._search_json_ld(webpage, page_id),
}
if len(entries) == 1:
return {
**entries[0],
**common_info,
}
return self.playlist_result(entries, multi_video=True, **common_info)

3
yt_dlp/extractor/redge.py
View File

@@ -1,4 +1,3 @@
import functools
from .common import InfoExtractor
from ..networking import HEADRequest
@@ -118,7 +117,7 @@ class RedCDNLivxIE(InfoExtractor):
time_scale = traverse_obj(ism_doc, ('@TimeScale', {int_or_none})) or 10000000
duration = traverse_obj(
ism_doc, ('@Duration', {functools.partial(float_or_none, scale=time_scale)})) or None
ism_doc, ('@Duration', {float_or_none(scale=time_scale)})) or None
live_status = None
if traverse_obj(ism_doc, '@IsLive') == 'TRUE':

18
yt_dlp/extractor/redgifs.py
View File

@@ -213,7 +213,7 @@ class RedGifsSearchIE(RedGifsBaseInfoExtractor):
class RedGifsUserIE(RedGifsBaseInfoExtractor):
IE_DESC = 'Redgifs user'
_VALID_URL = r'https?://(?:www\.)?redgifs\.com/users/(?P<username>[^/?#]+)(?:\?(?P<query>[^#]+))?'
_PAGE_SIZE = 30
_PAGE_SIZE = 80
_TESTS = [
{
'url': 'https://www.redgifs.com/users/lamsinka89',
@@ -222,7 +222,7 @@ class RedGifsUserIE(RedGifsBaseInfoExtractor):
'title': 'lamsinka89',
'description': 'RedGifs user lamsinka89, ordered by recent',
},
'playlist_mincount': 100,
'playlist_mincount': 391,
},
{
'url': 'https://www.redgifs.com/users/lamsinka89?page=3',
@@ -231,7 +231,7 @@ class RedGifsUserIE(RedGifsBaseInfoExtractor):
'title': 'lamsinka89',
'description': 'RedGifs user lamsinka89, ordered by recent',
},
'playlist_count': 30,
'playlist_count': 80,
},
{
'url': 'https://www.redgifs.com/users/lamsinka89?order=best&type=g',
@@ -240,7 +240,17 @@ class RedGifsUserIE(RedGifsBaseInfoExtractor):
'title': 'lamsinka89',
'description': 'RedGifs user lamsinka89, ordered by best',
},
'playlist_mincount': 100,
'playlist_mincount': 391,
},
{
'url': 'https://www.redgifs.com/users/ignored52',
'note': 'https://github.com/yt-dlp/yt-dlp/issues/7382',
'info_dict': {
'id': 'ignored52',
'title': 'ignored52',
'description': 'RedGifs user ignored52, ordered by recent',
},
'playlist_mincount': 121,
},
]

2
yt_dlp/extractor/rtvslo.py
View File

@@ -187,4 +187,4 @@ class RTVSLOShowIE(InfoExtractor):
return self.playlist_from_matches(
re.findall(r'<a [^>]*\bhref="(/arhiv/[^"]+)"', webpage),
playlist_id, self._html_extract_title(webpage),
getter=lambda x: urljoin('https://365.rtvslo.si', x), ie=RTVSLOIE)
getter=urljoin('https://365.rtvslo.si'), ie=RTVSLOIE)

202
yt_dlp/extractor/rutube.py
View File

@@ -2,15 +2,18 @@ import itertools
from .common import InfoExtractor
from ..utils import (
UnsupportedError,
bool_or_none,
determine_ext,
int_or_none,
js_to_json,
parse_qs,
traverse_obj,
str_or_none,
try_get,
unified_timestamp,
url_or_none,
)
from ..utils.traversal import traverse_obj
class RutubeBaseIE(InfoExtractor):
@@ -19,7 +22,7 @@ class RutubeBaseIE(InfoExtractor):
query = {}
query['format'] = 'json'
return self._download_json(
f'http://rutube.ru/api/video/{video_id}/',
f'https://rutube.ru/api/video/{video_id}/',
video_id, 'Downloading video JSON',
'Unable to download video JSON', query=query)
@@ -61,18 +64,21 @@ class RutubeBaseIE(InfoExtractor):
query = {}
query['format'] = 'json'
return self._download_json(
f'http://rutube.ru/api/play/options/{video_id}/',
f'https://rutube.ru/api/play/options/{video_id}/',
video_id, 'Downloading options JSON',
'Unable to download options JSON',
headers=self.geo_verification_headers(), query=query)
def _extract_formats(self, options, video_id):
def _extract_formats_and_subtitles(self, options, video_id):
formats = []
subtitles = {}
for format_id, format_url in options['video_balancer'].items():
ext = determine_ext(format_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))
fmts, subs = self._extract_m3u8_formats_and_subtitles(
format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
elif ext == 'f4m':
formats.extend(self._extract_f4m_formats(
format_url, video_id, f4m_id=format_id, fatal=False))
@@ -82,11 +88,19 @@ class RutubeBaseIE(InfoExtractor):
'format_id': format_id,
})
for hls_url in traverse_obj(options, ('live_streams', 'hls', ..., 'url', {url_or_none})):
formats.extend(self._extract_m3u8_formats(hls_url, video_id, ext='mp4', fatal=False))
return formats
fmts, subs = self._extract_m3u8_formats_and_subtitles(
hls_url, video_id, 'mp4', fatal=False, m3u8_id='hls')
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
for caption in traverse_obj(options, ('captions', lambda _, v: url_or_none(v['file']))):
subtitles.setdefault(caption.get('code') or 'ru', []).append({
'url': caption['file'],
'name': caption.get('langTitle'),
})
return formats, subtitles
def _download_and_extract_formats(self, video_id, query=None):
return self._extract_formats(
def _download_and_extract_formats_and_subtitles(self, video_id, query=None):
return self._extract_formats_and_subtitles(
self._download_api_options(video_id, query=query), video_id)
@@ -97,8 +111,8 @@ class RutubeIE(RutubeBaseIE):
_EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//rutube\.ru/(?:play/)?embed/[\da-z]{32}.*?)\1']
_TESTS = [{
'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
'md5': 'e33ac625efca66aba86cbec9851f2692',
'url': 'https://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
'md5': '3d73fdfe5bb81b9aef139e22ef3de26a',
'info_dict': {
'id': '3eac3b4561676c17df9132a9a1e62e3e',
'ext': 'mp4',
@@ -111,26 +125,25 @@ class RutubeIE(RutubeBaseIE):
'upload_date': '20131016',
'age_limit': 0,
'view_count': int,
'thumbnail': 'http://pic.rutubelist.ru/video/d2/a0/d2a0aec998494a396deafc7ba2c82add.jpg',
'thumbnail': 'https://pic.rutubelist.ru/video/d2/a0/d2a0aec998494a396deafc7ba2c82add.jpg',
'categories': ['Новости и СМИ'],
'chapters': [],
},
'expected_warnings': ['Unable to download f4m'],
}, {
'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
'url': 'https://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
'only_matching': True,
}, {
'url': 'http://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661',
'url': 'https://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661',
'only_matching': True,
}, {
'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252',
'url': 'https://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252',
'only_matching': True,
}, {
'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_type=source',
'only_matching': True,
}, {
'url': 'https://rutube.ru/video/private/884fb55f07a97ab673c7d654553e0f48/?p=x2QojCumHTS3rsKHWXN8Lg',
'md5': 'd106225f15d625538fe22971158e896f',
'md5': '4fce7b4fcc7b1bcaa3f45eb1e1ad0dd7',
'info_dict': {
'id': '884fb55f07a97ab673c7d654553e0f48',
'ext': 'mp4',
@@ -143,11 +156,10 @@ class RutubeIE(RutubeBaseIE):
'upload_date': '20221210',
'age_limit': 0,
'view_count': int,
'thumbnail': 'http://pic.rutubelist.ru/video/f2/d4/f2d42b54be0a6e69c1c22539e3152156.jpg',
'thumbnail': 'https://pic.rutubelist.ru/video/f2/d4/f2d42b54be0a6e69c1c22539e3152156.jpg',
'categories': ['Видеоигры'],
'chapters': [],
},
'expected_warnings': ['Unable to download f4m'],
}, {
'url': 'https://rutube.ru/video/c65b465ad0c98c89f3b25cb03dcc87c6/',
'info_dict': {
@@ -156,17 +168,16 @@ class RutubeIE(RutubeBaseIE):
'chapters': 'count:4',
'categories': ['Бизнес и предпринимательство'],
'description': 'md5:252feac1305257d8c1bab215cedde75d',
'thumbnail': 'http://pic.rutubelist.ru/video/71/8f/718f27425ea9706073eb80883dd3787b.png',
'thumbnail': 'https://pic.rutubelist.ru/video/71/8f/718f27425ea9706073eb80883dd3787b.png',
'duration': 782,
'age_limit': 0,
'uploader_id': '23491359',
'timestamp': 1677153329,
'view_count': int,
'upload_date': '20230223',
'title': 'Бизнес с нуля: найм сотрудников. Интервью с директором строительной компании',
'title': 'Бизнес с нуля: найм сотрудников. Интервью с директором строительной компании #1',
'uploader': 'Стас Быков',
},
'expected_warnings': ['Unable to download f4m'],
}, {
'url': 'https://rutube.ru/live/video/c58f502c7bb34a8fcdd976b221fca292/',
'info_dict': {
@@ -174,7 +185,7 @@ class RutubeIE(RutubeBaseIE):
'ext': 'mp4',
'categories': ['Телепередачи'],
'description': '',
'thumbnail': 'http://pic.rutubelist.ru/video/14/19/14190807c0c48b40361aca93ad0867c7.jpg',
'thumbnail': 'https://pic.rutubelist.ru/video/14/19/14190807c0c48b40361aca93ad0867c7.jpg',
'live_status': 'is_live',
'age_limit': 0,
'uploader_id': '23460655',
@@ -184,6 +195,24 @@ class RutubeIE(RutubeBaseIE):
'title': r're:Первый канал. Прямой эфир \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
'uploader': 'Первый канал',
},
}, {
'url': 'https://rutube.ru/play/embed/03a9cb54bac3376af4c5cb0f18444e01/',
'info_dict': {
'id': '03a9cb54bac3376af4c5cb0f18444e01',
'ext': 'mp4',
'age_limit': 0,
'description': '',
'title': 'Церемония начала торгов акциями ПАО «ЕвроТранс»',
'chapters': [],
'upload_date': '20240829',
'duration': 293,
'uploader': 'MOEX - Московская биржа',
'timestamp': 1724946628,
'thumbnail': 'https://pic.rutubelist.ru/video/2e/24/2e241fddb459baf0fa54acfca44874f4.jpg',
'view_count': int,
'uploader_id': '38420507',
'categories': ['Интервью'],
},
}, {
'url': 'https://rutube.ru/video/5ab908fccfac5bb43ef2b1e4182256b0/',
'only_matching': True,
@@ -192,40 +221,46 @@ class RutubeIE(RutubeBaseIE):
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
return False if RutubePlaylistIE.suitable(url) else super().suitable(url)
def _real_extract(self, url):
video_id = self._match_id(url)
query = parse_qs(url)
info = self._download_and_extract_info(video_id, query)
info['formats'] = self._download_and_extract_formats(video_id, query)
return info
formats, subtitles = self._download_and_extract_formats_and_subtitles(video_id, query)
return {
**info,
'formats': formats,
'subtitles': subtitles,
}
class RutubeEmbedIE(RutubeBaseIE):
IE_NAME = 'rutube:embed'
IE_DESC = 'Rutube embedded videos'
_VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'
_VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)(?:[?#/]|$)'
_TESTS = [{
'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
'url': 'https://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
'info_dict': {
'id': 'a10e53b86e8f349080f718582ce4c661',
'ext': 'mp4',
'timestamp': 1387830582,
'upload_date': '20131223',
'uploader_id': '297833',
'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
'uploader': 'subziro89 ILya',
'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
'age_limit': 0,
'duration': 1395,
'chapters': [],
'description': 'md5:a5acea57bbc3ccdc3cacd1f11a014b5b',
'view_count': int,
'thumbnail': 'https://pic.rutubelist.ru/video/d3/03/d3031f4670a6e6170d88fb3607948418.jpg',
'categories': ['Сериалы'],
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://rutube.ru/play/embed/8083783',
'url': 'https://rutube.ru/play/embed/8083783',
'only_matching': True,
}, {
# private video
@@ -240,11 +275,12 @@ class RutubeEmbedIE(RutubeBaseIE):
query = parse_qs(url)
options = self._download_api_options(embed_id, query)
video_id = options['effective_video']
formats = self._extract_formats(options, video_id)
formats, subtitles = self._extract_formats_and_subtitles(options, video_id)
info = self._download_and_extract_info(video_id, query)
info.update({
'extractor_key': 'Rutube',
'formats': formats,
'subtitles': subtitles,
})
return info
@@ -295,14 +331,14 @@ class RutubeTagsIE(RutubePlaylistBaseIE):
IE_DESC = 'Rutube tags'
_VALID_URL = r'https?://rutube\.ru/tags/video/(?P<id>\d+)'
_TESTS = [{
'url': 'http://rutube.ru/tags/video/1800/',
'url': 'https://rutube.ru/tags/video/1800/',
'info_dict': {
'id': '1800',
},
'playlist_mincount': 68,
}]
_PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
_PAGE_TEMPLATE = 'https://rutube.ru/api/tags/video/%s/?page=%s&format=json'
class RutubeMovieIE(RutubePlaylistBaseIE):
@@ -310,8 +346,8 @@ class RutubeMovieIE(RutubePlaylistBaseIE):
IE_DESC = 'Rutube movies'
_VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P<id>\d+)'
_MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
_PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
_MOVIE_TEMPLATE = 'https://rutube.ru/api/metainfo/tv/%s/?format=json'
_PAGE_TEMPLATE = 'https://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
def _real_extract(self, url):
movie_id = self._match_id(url)
@@ -327,62 +363,82 @@ class RutubePersonIE(RutubePlaylistBaseIE):
IE_DESC = 'Rutube person videos'
_VALID_URL = r'https?://rutube\.ru/video/person/(?P<id>\d+)'
_TESTS = [{
'url': 'http://rutube.ru/video/person/313878/',
'url': 'https://rutube.ru/video/person/313878/',
'info_dict': {
'id': '313878',
},
'playlist_mincount': 37,
'playlist_mincount': 36,
}]
_PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'
_PAGE_TEMPLATE = 'https://rutube.ru/api/video/person/%s/?page=%s&format=json'
class RutubePlaylistIE(RutubePlaylistBaseIE):
IE_NAME = 'rutube:playlist'
IE_DESC = 'Rutube playlists'
_VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/[\da-z]{32}/\?.*?\bpl_id=(?P<id>\d+)'
_VALID_URL = r'https?://rutube\.ru/plst/(?P<id>\d+)'
_TESTS = [{
'url': 'https://rutube.ru/video/cecd58ed7d531fc0f3d795d51cee9026/?pl_id=3097&pl_type=tag',
'url': 'https://rutube.ru/plst/308547/',
'info_dict': {
'id': '3097',
'id': '308547',
},
'playlist_count': 27,
}, {
'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_id=4252&pl_type=source',
'only_matching': True,
'playlist_mincount': 22,
}]
_PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/%s/%s/?page=%s&format=json'
@classmethod
def suitable(cls, url):
from ..utils import int_or_none, parse_qs
if not super().suitable(url):
return False
params = parse_qs(url)
return params.get('pl_type', [None])[0] and int_or_none(params.get('pl_id', [None])[0])
def _next_page_url(self, page_num, playlist_id, item_kind):
return self._PAGE_TEMPLATE % (item_kind, playlist_id, page_num)
def _real_extract(self, url):
qs = parse_qs(url)
playlist_kind = qs['pl_type'][0]
playlist_id = qs['pl_id'][0]
return self._extract_playlist(playlist_id, item_kind=playlist_kind)
_PAGE_TEMPLATE = 'https://rutube.ru/api/playlist/custom/%s/videos?page=%s&format=json'
class RutubeChannelIE(RutubePlaylistBaseIE):
IE_NAME = 'rutube:channel'
IE_DESC = 'Rutube channel'
_VALID_URL = r'https?://rutube\.ru/channel/(?P<id>\d+)/videos'
_VALID_URL = r'https?://rutube\.ru/(?:channel/(?P<id>\d+)|u/(?P<slug>\w+))(?:/(?P<section>videos|shorts|playlists))?'
_TESTS = [{
'url': 'https://rutube.ru/channel/639184/videos/',
'info_dict': {
'id': '639184',
'id': '639184_videos',
},
'playlist_mincount': 133,
'playlist_mincount': 129,
}, {
'url': 'https://rutube.ru/channel/25902603/shorts/',
'info_dict': {
'id': '25902603_shorts',
},
'playlist_mincount': 277,
}, {
'url': 'https://rutube.ru/channel/25902603/',
'info_dict': {
'id': '25902603',
},
'playlist_mincount': 406,
}, {
'url': 'https://rutube.ru/u/rutube/videos/',
'info_dict': {
'id': '23704195_videos',
},
'playlist_mincount': 113,
}]
_PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'
_PAGE_TEMPLATE = 'https://rutube.ru/api/video/person/%s/?page=%s&format=json&origin__type=%s'
def _next_page_url(self, page_num, playlist_id, section):
origin_type = {
'videos': 'rtb,rst,ifrm,rspa',
'shorts': 'rshorts',
None: '',
}.get(section)
return self._PAGE_TEMPLATE % (playlist_id, page_num, origin_type)
def _real_extract(self, url):
playlist_id, slug, section = self._match_valid_url(url).group('id', 'slug', 'section')
if section == 'playlists':
raise UnsupportedError(url)
if slug:
webpage = self._download_webpage(url, slug)
redux_state = self._search_json(
r'window\.reduxState\s*=', webpage, 'redux state', slug, transform_source=js_to_json)
playlist_id = traverse_obj(redux_state, (
'api', 'queries', lambda k, _: k.startswith('channelIdBySlug'),
'data', 'channel_id', {int}, {str_or_none}, any))
playlist = self._extract_playlist(playlist_id, section=section)
if section:
playlist['id'] = f'{playlist_id}_{section}'
return playlist

12
yt_dlp/extractor/shemaroome.py
View File

@@ -1,11 +1,9 @@
import base64
from .common import InfoExtractor
from ..aes import aes_cbc_decrypt, unpad_pkcs7
from ..aes import aes_cbc_decrypt_bytes, unpad_pkcs7
from ..utils import (
ExtractorError,
bytes_to_intlist,
intlist_to_bytes,
unified_strdate,
)
@@ -68,10 +66,10 @@ class ShemarooMeIE(InfoExtractor):
data_json = self._download_json('https://www.shemaroome.com/users/user_all_lists', video_id, data=data.encode())
if not data_json.get('status'):
raise ExtractorError('Premium videos cannot be downloaded yet.', expected=True)
url_data = bytes_to_intlist(base64.b64decode(data_json['new_play_url']))
key = bytes_to_intlist(base64.b64decode(data_json['key']))
iv = [0] * 16
m3u8_url = unpad_pkcs7(intlist_to_bytes(aes_cbc_decrypt(url_data, key, iv))).decode('ascii')
url_data = base64.b64decode(data_json['new_play_url'])
key = base64.b64decode(data_json['key'])
iv = bytes(16)
m3u8_url = unpad_pkcs7(aes_cbc_decrypt_bytes(url_data, key, iv)).decode('ascii')
headers = {'stream_key': data_json['stream_key']}
formats, m3u8_subs = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, fatal=False, headers=headers)
for fmt in formats:

4
yt_dlp/extractor/snapchat.py
View File

@@ -56,13 +56,13 @@ class SnapchatSpotlightIE(InfoExtractor):
**traverse_obj(video_data, ('videoMetadata', {
'title': ('name', {str}),
'description': ('description', {str}),
'timestamp': ('uploadDateMs', {lambda x: float_or_none(x, 1000)}),
'timestamp': ('uploadDateMs', {float_or_none(scale=1000)}),
'view_count': ('viewCount', {int_or_none}, {lambda x: None if x == -1 else x}),
'repost_count': ('shareCount', {int_or_none}),
'url': ('contentUrl', {url_or_none}),
'width': ('width', {int_or_none}),
'height': ('height', {int_or_none}),
'duration': ('durationMs', {lambda x: float_or_none(x, 1000)}),
'duration': ('durationMs', {float_or_none(scale=1000)}),
'thumbnail': ('thumbnailUrl', {url_or_none}),
'uploader': ('creator', 'personCreator', 'username', {str}),
'uploader_url': ('creator', 'personCreator', 'url', {url_or_none}),

4
yt_dlp/extractor/spankbang.py
View File

@@ -71,9 +71,11 @@ class SpankBangIE(InfoExtractor):
def _real_extract(self, url):
mobj = self._match_valid_url(url)
video_id = mobj.group('id') or mobj.group('id_2')
country = self.get_param('geo_bypass_country') or 'US'
self._set_cookie('.spankbang.com', 'country', country.upper())
webpage = self._download_webpage(
url.replace(f'/{video_id}/embed', f'/{video_id}/video'),
video_id, headers={'Cookie': 'country=US'})
video_id, impersonate=True)
if re.search(r'<[^>]+\b(?:id|class)=["\']video_removed', webpage):
raise ExtractorError(

111
yt_dlp/extractor/spreaker.py
View File

@@ -2,13 +2,16 @@ import itertools
from .common import InfoExtractor
from ..utils import (
filter_dict,
float_or_none,
int_or_none,
parse_qs,
str_or_none,
try_get,
unified_timestamp,
url_or_none,
)
from ..utils.traversal import traverse_obj
def _extract_episode(data, episode_id=None):
@@ -58,15 +61,10 @@ def _extract_episode(data, episode_id=None):
class SpreakerIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
api\.spreaker\.com/
(?:
(?:download/)?episode|
v2/episodes
)/
(?P<id>\d+)
'''
_VALID_URL = [
r'https?://api\.spreaker\.com/(?:(?:download/)?episode|v2/episodes)/(?P<id>\d+)',
r'https?://(?:www\.)?spreaker\.com/episode/[^#?/]*?(?P<id>\d+)/?(?:[?#]|$)',
]
_TESTS = [{
'url': 'https://api.spreaker.com/episode/12534508',
'info_dict': {
@@ -83,7 +81,9 @@ class SpreakerIE(InfoExtractor):
'view_count': int,
'like_count': int,
'comment_count': int,
'series': 'Success With Music (SWM)',
'series': 'Success With Music | SWM',
'thumbnail': 'https://d3wo5wojvuv7l.cloudfront.net/t_square_limited_160/images.spreaker.com/original/777ce4f96b71b0e1b7c09a5e625210e3.jpg',
'creators': ['SWM'],
},
}, {
'url': 'https://api.spreaker.com/download/episode/12534508/swm_ep15_how_to_market_your_music_part_2.mp3',
@@ -91,52 +91,75 @@ class SpreakerIE(InfoExtractor):
}, {
'url': 'https://api.spreaker.com/v2/episodes/12534508?export=episode_segments',
'only_matching': True,
}, {
'note': 'episode',
'url': 'https://www.spreaker.com/episode/grunge-music-origins-the-raw-sound-that-defined-a-generation--60269615',
'info_dict': {
'id': '60269615',
'display_id': 'grunge-music-origins-the-raw-sound-that-',
'ext': 'mp3',
'title': 'Grunge Music Origins - The Raw Sound that Defined a Generation',
'description': str,
'timestamp': 1717468905,
'upload_date': '20240604',
'uploader': 'Katie Brown 2',
'uploader_id': '17733249',
'duration': 818.83,
'view_count': int,
'like_count': int,
'comment_count': int,
'series': '90s Grunge',
'thumbnail': 'https://d3wo5wojvuv7l.cloudfront.net/t_square_limited_160/images.spreaker.com/original/bb0d4178f7cf57cc8786dedbd9c5d969.jpg',
'creators': ['Katie Brown 2'],
},
}, {
'url': 'https://www.spreaker.com/episode/60269615',
'only_matching': True,
}]
def _real_extract(self, url):
episode_id = self._match_id(url)
data = self._download_json(
f'https://api.spreaker.com/v2/episodes/{episode_id}',
episode_id)['response']['episode']
f'https://api.spreaker.com/v2/episodes/{episode_id}', episode_id,
query=traverse_obj(parse_qs(url), {'key': ('key', 0)}))['response']['episode']
return _extract_episode(data, episode_id)
class SpreakerPageIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?spreaker\.com/user/[^/]+/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://www.spreaker.com/user/9780658/swm-ep15-how-to-market-your-music-part-2',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
episode_id = self._search_regex(
(r'data-episode_id=["\'](?P<id>\d+)',
r'episode_id\s*:\s*(?P<id>\d+)'), webpage, 'episode id')
return self.url_result(
f'https://api.spreaker.com/episode/{episode_id}',
ie=SpreakerIE.ie_key(), video_id=episode_id)
class SpreakerShowIE(InfoExtractor):
_VALID_URL = r'https?://api\.spreaker\.com/show/(?P<id>\d+)'
_VALID_URL = [
r'https?://api\.spreaker\.com/show/(?P<id>\d+)',
r'https?://(?:www\.)?spreaker\.com/podcast/[\w-]+--(?P<id>[\d]+)',
r'https?://(?:www\.)?spreaker\.com/show/(?P<id>\d+)/episodes/feed',
]
_TESTS = [{
'url': 'https://api.spreaker.com/show/4652058',
'info_dict': {
'id': '4652058',
},
'playlist_mincount': 118,
}, {
'url': 'https://www.spreaker.com/podcast/health-wealth--5918323',
'info_dict': {
'id': '5918323',
},
'playlist_mincount': 60,
}, {
'url': 'https://www.spreaker.com/show/5887186/episodes/feed',
'info_dict': {
'id': '5887186',
},
'playlist_mincount': 290,
}]
def _entries(self, show_id):
def _entries(self, show_id, key=None):
for page_num in itertools.count(1):
episodes = self._download_json(
f'https://api.spreaker.com/show/{show_id}/episodes',
show_id, note=f'Downloading JSON page {page_num}', query={
show_id, note=f'Downloading JSON page {page_num}', query=filter_dict({
'page': page_num,
'max_per_page': 100,
})
'key': key,
}))
pager = try_get(episodes, lambda x: x['response']['pager'], dict)
if not pager:
break
@@ -152,21 +175,5 @@ class SpreakerShowIE(InfoExtractor):
def _real_extract(self, url):
show_id = self._match_id(url)
return self.playlist_result(self._entries(show_id), playlist_id=show_id)
class SpreakerShowPageIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?spreaker\.com/show/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://www.spreaker.com/show/success-with-music',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
show_id = self._search_regex(
r'show_id\s*:\s*(?P<id>\d+)', webpage, 'show id')
return self.url_result(
f'https://api.spreaker.com/show/{show_id}',
ie=SpreakerShowIE.ie_key(), video_id=show_id)
key = traverse_obj(parse_qs(url), ('key', 0))
return self.playlist_result(self._entries(show_id, key), playlist_id=show_id)

6
yt_dlp/extractor/tbsjp.py
View File

@@ -3,14 +3,12 @@ from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
clean_html,
get_element_text_and_html_by_tag,
int_or_none,
str_or_none,
traverse_obj,
try_call,
unified_timestamp,
urljoin,
)
from ..utils.traversal import find_element, traverse_obj
class TBSJPEpisodeIE(InfoExtractor):
@@ -64,7 +62,7 @@ class TBSJPEpisodeIE(InfoExtractor):
self._merge_subtitles(subs, target=subtitles)
return {
'title': try_call(lambda: clean_html(get_element_text_and_html_by_tag('h3', webpage)[0])),
'title': traverse_obj(webpage, ({find_element(tag='h3')}, {clean_html})),
'id': video_id,
**traverse_obj(episode, {
'categories': ('keywords', {list}),

2
yt_dlp/extractor/teamcoco.py
View File

@@ -136,7 +136,7 @@ class TeamcocoIE(TeamcocoBaseIE):
'blocks', lambda _, v: v['name'] in ('meta-tags', 'video-player', 'video-info'), 'props', {dict})))
thumbnail = traverse_obj(
info, (('image', 'poster'), {lambda x: urljoin('https://teamcoco.com/', x)}), get_all=False)
info, (('image', 'poster'), {urljoin('https://teamcoco.com/')}), get_all=False)
video_id = traverse_obj(parse_qs(thumbnail), ('id', 0)) or display_id
formats, subtitles = self._get_formats_and_subtitles(info, video_id)

3
yt_dlp/extractor/telewebion.py
View File

@@ -10,10 +10,11 @@ from ..utils.traversal import traverse_obj
def _fmt_url(url):
return functools.partial(format_field, template=url, default=None)
return format_field(template=url, default=None)
class TelewebionIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?telewebion\.com/episode/(?P<id>(?:0x[a-fA-F\d]+|\d+))'
_TESTS = [{
'url': 'http://www.telewebion.com/episode/0x1b3139c/',

5
yt_dlp/extractor/tencent.py
View File

@@ -1,4 +1,3 @@
import functools
import random
import re
import string
@@ -278,7 +277,7 @@ class VQQSeriesIE(VQQBaseIE):
webpage)]
return self.playlist_from_matches(
episode_paths, series_id, ie=VQQVideoIE, getter=functools.partial(urljoin, url),
episode_paths, series_id, ie=VQQVideoIE, getter=urljoin(url),
title=self._get_clean_title(traverse_obj(webpage_metadata, ('coverInfo', 'title'))
or self._og_search_title(webpage)),
description=(traverse_obj(webpage_metadata, ('coverInfo', 'description'))
@@ -328,7 +327,7 @@ class WeTvBaseIE(TencentBaseIE):
or re.findall(r'<a[^>]+class="play-video__link"[^>]+href="(?P<path>[^"]+)', webpage))
return self.playlist_from_matches(
episode_paths, series_id, ie=ie, getter=functools.partial(urljoin, url),
episode_paths, series_id, ie=ie, getter=urljoin(url),
title=self._get_clean_title(traverse_obj(webpage_metadata, ('coverInfo', 'title'))
or self._og_search_title(webpage)),
description=(traverse_obj(webpage_metadata, ('coverInfo', 'description'))

3
yt_dlp/extractor/tenplay.py
View File

@@ -1,4 +1,3 @@
import functools
import itertools
from .common import InfoExtractor
@@ -161,4 +160,4 @@ class TenPlaySeasonIE(InfoExtractor):
return self.playlist_from_matches(
self._entries(urljoin(url, episodes_carousel['loadMoreUrl']), playlist_id),
playlist_id, traverse_obj(season_info, ('content', 0, 'title', {str})),
getter=functools.partial(urljoin, url))
getter=urljoin(url))

2
yt_dlp/extractor/theguardian.py
View File

@@ -131,4 +131,4 @@ class TheGuardianPodcastPlaylistIE(InfoExtractor):
return self.playlist_from_matches(
self._entries(url, podcast_id), podcast_id, title, description=description,
ie=TheGuardianPodcastIE, getter=lambda x: urljoin('https://www.theguardian.com', x))
ie=TheGuardianPodcastIE, getter=urljoin('https://www.theguardian.com'))

8
yt_dlp/extractor/tiktok.py
View File

@@ -469,7 +469,7 @@ class TikTokBaseIE(InfoExtractor):
aweme_detail, aweme_id, traverse_obj(author_info, 'uploader', 'uploader_id', 'channel_id')),
'thumbnails': thumbnails,
'duration': (traverse_obj(video_info, (
(None, 'download_addr'), 'duration', {functools.partial(int_or_none, scale=1000)}, any))
(None, 'download_addr'), 'duration', {int_or_none(scale=1000)}, any))
or traverse_obj(music_info, ('duration', {int_or_none}))),
'availability': self._availability(
is_private='Private' in labels,
@@ -583,7 +583,7 @@ class TikTokBaseIE(InfoExtractor):
author_info, ['uploader', 'uploader_id'], self._UPLOADER_URL_FORMAT, default=None),
**traverse_obj(aweme_detail, ('music', {
'track': ('title', {str}),
'album': ('album', {str}, {lambda x: x or None}),
'album': ('album', {str}, filter),
'artists': ('authorName', {str}, {lambda x: re.split(r'(?:, | & )', x) if x else None}),
'duration': ('duration', {int_or_none}),
})),
@@ -591,7 +591,7 @@ class TikTokBaseIE(InfoExtractor):
'title': ('desc', {str}),
'description': ('desc', {str}),
# audio-only slideshows have a video duration of 0 and an actual audio duration
'duration': ('video', 'duration', {int_or_none}, {lambda x: x or None}),
'duration': ('video', 'duration', {int_or_none}, filter),
'timestamp': ('createTime', {int_or_none}),
}),
**traverse_obj(aweme_detail, ('stats', {
@@ -1493,7 +1493,7 @@ class TikTokLiveIE(TikTokBaseIE):
sdk_params = traverse_obj(stream, ('main', 'sdk_params', {parse_inner}, {
'vcodec': ('VCodec', {str}),
'tbr': ('vbitrate', {lambda x: int_or_none(x, 1000)}),
'tbr': ('vbitrate', {int_or_none(scale=1000)}),
'resolution': ('resolution', {lambda x: re.match(r'(?i)\d+x\d+|\d+p', x).group().lower()}),
}))

372
yt_dlp/extractor/tumblr.py
View File

@@ -3,12 +3,13 @@ from ..utils import (
ExtractorError,
int_or_none,
traverse_obj,
url_or_none,
urlencode_postdata,
)
class TumblrIE(InfoExtractor):
_VALID_URL = r'https?://(?P<blog_name>[^/?#&]+)\.tumblr\.com/(?:post|video)/(?P<id>[0-9]+)(?:$|[/?#])'
_VALID_URL = r'https?://(?P<blog_name_1>[^/?#&]+)\.tumblr\.com/(?:post|video|(?P<blog_name_2>[a-zA-Z\d-]+))/(?P<id>[0-9]+)(?:$|[/?#])'
_NETRC_MACHINE = 'tumblr'
_LOGIN_URL = 'https://www.tumblr.com/login'
_OAUTH_URL = 'https://www.tumblr.com/api/v2/oauth2/token'
@@ -66,6 +67,7 @@ class TumblrIE(InfoExtractor):
'age_limit': 0,
'tags': [],
},
'skip': '404',
}, {
'note': 'dashboard only (original post)',
'url': 'https://jujanon.tumblr.com/post/159704441298/my-baby-eating',
@@ -98,7 +100,6 @@ class TumblrIE(InfoExtractor):
'like_count': int,
'repost_count': int,
'age_limit': 0,
'tags': [],
},
}, {
'note': 'dashboard only (external)',
@@ -109,14 +110,13 @@ class TumblrIE(InfoExtractor):
'title': 'The Blues Remembers Everything the Country Forgot',
'alt_title': 'The Blues Remembers Everything the Country Forgot',
'description': 'md5:1a6b4097e451216835a24c1023707c79',
'release_date': '20201224',
'creator': 'md5:c2239ba15430e87c3b971ba450773272',
'uploader': 'Moor Mother - Topic',
'upload_date': '20201223',
'uploader_id': 'UCxrMtFBRkFvQJ_vVM4il08w',
'uploader_url': 'http://www.youtube.com/channel/UCxrMtFBRkFvQJ_vVM4il08w',
'thumbnail': r're:^https?://i.ytimg.com/.*',
'channel': 'Moor Mother - Topic',
'channel': 'Moor Mother',
'channel_id': 'UCxrMtFBRkFvQJ_vVM4il08w',
'channel_url': 'https://www.youtube.com/channel/UCxrMtFBRkFvQJ_vVM4il08w',
'channel_follower_count': int,
@@ -135,24 +135,10 @@ class TumblrIE(InfoExtractor):
'release_year': 2020,
},
'add_ie': ['Youtube'],
}, {
'url': 'http://naked-yogi.tumblr.com/post/118312946248/naked-smoking-stretching',
'md5': 'de07e5211d60d4f3a2c3df757ea9f6ab',
'info_dict': {
'id': 'Wmur',
'ext': 'mp4',
'title': 'naked smoking & stretching',
'upload_date': '20150506',
'timestamp': 1430931613,
'age_limit': 18,
'uploader_id': '1638622',
'uploader': 'naked-yogi',
},
# 'add_ie': ['Vidme'],
'skip': 'dead embedded video host',
'skip': 'Video Unavailable',
}, {
'url': 'https://prozdvoices.tumblr.com/post/673201091169681408/what-recording-voice-acting-sounds-like',
'md5': 'a0063fc8110e6c9afe44065b4ea68177',
'md5': 'cb8328a6723c30556cef59e370202918',
'info_dict': {
'id': 'eomhW5MLGWA',
'ext': 'mp4',
@@ -160,8 +146,8 @@ class TumblrIE(InfoExtractor):
'description': 'md5:1da3faa22d0e0b1d8b50216c284ee798',
'uploader': 'ProZD',
'upload_date': '20220112',
'uploader_id': 'ProZD',
'uploader_url': 'http://www.youtube.com/user/ProZD',
'uploader_id': '@ProZD',
'uploader_url': 'https://www.youtube.com/@ProZD',
'thumbnail': r're:^https?://i.ytimg.com/.*',
'channel': 'ProZD',
'channel_id': 'UC6MFZAOHXlKK1FI7V0XQVeA',
@@ -176,6 +162,10 @@ class TumblrIE(InfoExtractor):
'live_status': 'not_live',
'playable_in_embed': True,
'availability': 'public',
'heatmap': 'count:100',
'channel_is_verified': True,
'timestamp': 1642014562,
'comment_count': int,
},
'add_ie': ['Youtube'],
}, {
@@ -183,16 +173,20 @@ class TumblrIE(InfoExtractor):
'md5': '203e9eb8077e3f45bfaeb4c86c1467b8',
'info_dict': {
'id': '87816359',
'ext': 'mov',
'ext': 'mp4',
'title': 'Harold Ramis',
'description': 'md5:be8e68cbf56ce0785c77f0c6c6dfaf2c',
'description': 'md5:c99882405fcca0b1d348ad093f8f1672',
'uploader': 'Resolution Productions Group',
'uploader_id': 'resolutionproductions',
'uploader_url': 'https://vimeo.com/resolutionproductions',
'upload_date': '20140227',
'thumbnail': r're:^https?://i.vimeocdn.com/video/.*',
'timestamp': 1393523719,
'timestamp': 1393541719,
'duration': 291,
'comment_count': int,
'like_count': int,
'release_timestamp': 1393541719,
'release_date': '20140227',
},
'add_ie': ['Vimeo'],
}, {
@@ -214,6 +208,7 @@ class TumblrIE(InfoExtractor):
'view_count': int,
},
'add_ie': ['Vine'],
'skip': 'Vine is unavailable',
}, {
'url': 'https://silami.tumblr.com/post/84250043974/my-bad-river-flows-in-you-impression-on-maschine',
'md5': '3c92d7c3d867f14ccbeefa2119022277',
@@ -232,6 +227,140 @@ class TumblrIE(InfoExtractor):
'upload_date': '20140429',
},
'add_ie': ['Instagram'],
}, {
'note': 'new url scheme',
'url': 'https://www.tumblr.com/autumnsister/765162750456578048?source=share',
'info_dict': {
'id': '765162750456578048',
'ext': 'mp4',
'uploader_url': 'https://autumnsister.tumblr.com/',
'tags': ['autumn', 'food', 'curators on tumblr'],
'like_count': int,
'thumbnail': 'https://64.media.tumblr.com/tumblr_sklad89N3x1ygquow_frame1.jpg',
'title': '🪹',
'uploader_id': 'autumnsister',
'repost_count': int,
'age_limit': 0,
},
}, {
'note': 'bandcamp album embed',
'url': 'https://patricia-taxxon.tumblr.com/post/704473755725004800/patricia-taxxon-agnes-hilda-patricia-taxxon',
'info_dict': {
'id': 'agnes-hilda',
'title': 'Agnes & Hilda',
'description': 'The inexplicable joy of an artist. Wash paws after listening.',
'uploader_id': 'patriciataxxon',
},
'playlist_count': 8,
}, {
'note': 'bandcamp track embeds (many)',
'url': 'https://www.tumblr.com/felixcosm/730460905855467520/if-youre-looking-for-new-music-to-write-or',
'info_dict': {
'id': '730460905855467520',
'uploader_id': 'felixcosm',
'repost_count': int,
'tags': 'count:15',
'description': 'md5:2eb3482a3c6987280cbefb6839068f32',
'like_count': int,
'age_limit': 0,
'title': 'If you\'re looking for new music to write or imagine scenerios to: STOP. This is for you.',
'uploader_url': 'https://felixcosm.tumblr.com/',
},
'playlist_count': 10,
}, {
'note': 'soundcloud track embed',
'url': 'https://silverfoxstole.tumblr.com/post/765305403763556352/jamie-robertson-doctor-who-8th-doctor',
'info_dict': {
'id': '1218136399',
'ext': 'opus',
'comment_count': int,
'genres': [],
'repost_count': int,
'uploader': 'Jamie Robertson',
'title': 'Doctor Who - 8th doctor - Stranded Theme never released and used.',
'duration': 46.106,
'uploader_id': '2731064',
'thumbnail': 'https://i1.sndcdn.com/artworks-MVgcPm5jN42isC5M-6Dz22w-original.jpg',
'timestamp': 1645181261,
'uploader_url': 'https://soundcloud.com/jamierobertson',
'view_count': int,
'upload_date': '20220218',
'description': 'md5:ab924dd9994d0a7d64d6d31bf2af4625',
'license': 'all-rights-reserved',
'like_count': int,
},
}, {
'note': 'soundcloud set embed',
'url': 'https://www.tumblr.com/beyourselfchulanmaria/703505323122638848/chu-lan-maria-the-playlist-%E5%BF%83%E7%9A%84%E5%91%BC%E5%96%9A-call-of-the',
'info_dict': {
'id': '691222680',
'title': '心的呼喚 Call of the heart I',
'description': 'md5:25952a8d178a3aa55e40fcbb646a38c3',
},
'playlist_mincount': 19,
}, {
'note': 'dailymotion video embed',
'url': 'https://www.tumblr.com/funvibecentral/759390024460632064',
'info_dict': {
'id': 'x94cnnk',
'ext': 'mp4',
'description': 'Funny dailymotion shorts.\n#funny #fun#comedy #romantic #exciting',
'uploader': 'FunVibe Central',
'like_count': int,
'view_count': int,
'timestamp': 1724210553,
'title': 'Woman watching other Woman',
'tags': [],
'upload_date': '20240821',
'age_limit': 0,
'uploader_id': 'x32m6ye',
'duration': 20,
'thumbnail': r're:https://(?:s[12]\.)dmcdn\.net/v/Wtqh01cnxKNXLG1N8/x1080',
},
}, {
'note': 'tiktok video embed',
'url': 'https://fansofcolor.tumblr.com/post/660637918605475840/blockquote-class-tiktok-embed',
'info_dict': {
'id': '7000937272010935558',
'ext': 'mp4',
'artists': ['Alicia Dreaming'],
'like_count': int,
'repost_count': int,
'thumbnail': r're:^https?://[\w\/\.\-]+(~[\w\-]+\.image)?',
'channel_id': 'MS4wLjABAAAAsJohwz_dU4KfAOc61cbGDAZ46-5hg2ANTXVQlRe1ipDhpX08PywR3PPiple1NTAo',
'uploader': 'aliciadreaming',
'description': 'huge casting news Greyworm will be #louisdulac #racebending #interviewwiththevampire',
'title': 'huge casting news Greyworm will be #louisdulac #racebending #interviewwiththevampire',
'channel_url': 'https://www.tiktok.com/@MS4wLjABAAAAsJohwz_dU4KfAOc61cbGDAZ46-5hg2ANTXVQlRe1ipDhpX08PywR3PPiple1NTAo',
'uploader_id': '7000478462196990982',
'uploader_url': 'https://www.tiktok.com/@aliciadreaming',
'timestamp': 1630032733,
'channel': 'Alicia Dreaming',
'track': 'original sound',
'upload_date': '20210827',
'view_count': int,
'comment_count': int,
'duration': 59,
},
}, {
'note': 'tumblr video AND youtube embed',
'url': 'https://www.tumblr.com/anyaboz/765332564457209856/my-music-video-for-selkie-by-nobodys-wolf-child',
'info_dict': {
'id': '765332564457209856',
'uploader_id': 'anyaboz',
'repost_count': int,
'age_limit': 0,
'uploader_url': 'https://anyaboz.tumblr.com/',
'description': 'md5:9a129cf6ce9d87a80ffd3c6dedd4d1e6',
'like_count': int,
'title': 'md5:b18a2ac9387681d20303e485db85c1b5',
'tags': ['music video', 'nobodys wolf child', 'selkie', 'Stop Motion Animation', 'stop Motion', 'room guardians', 'Youtube'],
},
'playlist_count': 2,
}, {
# twitch_live provider - error when linked account is not live
'url': 'https://www.tumblr.com/anarcho-skamunist/722224493650722816/hollow-knight-stream-right-now-going-to-fight',
'only_matching': True,
}]
_providers = {
@@ -239,6 +368,16 @@ class TumblrIE(InfoExtractor):
'vimeo': 'Vimeo',
'vine': 'Vine',
'youtube': 'Youtube',
'dailymotion': 'Dailymotion',
'tiktok': 'TikTok',
'twitch_live': 'TwitchStream',
'bandcamp': None,
'soundcloud': None,
}
# known not to be supported
_unsupported_providers = {
# seems like podcasts can't be embedded
'spotify',
}
_ACCESS_TOKEN = None
@@ -256,23 +395,40 @@ class TumblrIE(InfoExtractor):
if not self._ACCESS_TOKEN:
return
self._download_json(
self._OAUTH_URL, None, 'Logging in',
data=urlencode_postdata({
'password': password,
'grant_type': 'password',
'username': username,
}), headers={
'Content-Type': 'application/x-www-form-urlencoded',
'Authorization': f'Bearer {self._ACCESS_TOKEN}',
},
errnote='Login failed', fatal=False)
data = {
'password': password,
'grant_type': 'password',
'username': username,
}
if self.get_param('twofactor'):
data['tfa_token'] = self.get_param('twofactor')
def _call_login():
return self._download_json(
self._OAUTH_URL, None, 'Logging in',
data=urlencode_postdata(data),
headers={
'Content-Type': 'application/x-www-form-urlencoded',
'Authorization': f'Bearer {self._ACCESS_TOKEN}',
},
errnote='Login failed', fatal=False,
expected_status=lambda s: 400 <= s < 500)
response = _call_login()
if traverse_obj(response, 'error') == 'tfa_required':
data['tfa_token'] = self._get_tfa_info()
response = _call_login()
if traverse_obj(response, 'error'):
raise ExtractorError(
f'API returned error {": ".join(traverse_obj(response, (("error", "error_description"), {str})))}')
def _real_extract(self, url):
blog, video_id = self._match_valid_url(url).groups()
blog_1, blog_2, video_id = self._match_valid_url(url).groups()
blog = blog_2 or blog_1
url = f'http://{blog}.tumblr.com/post/{video_id}/'
webpage, urlh = self._download_webpage_handle(url, video_id)
url = f'http://{blog}.tumblr.com/post/{video_id}'
webpage, urlh = self._download_webpage_handle(
url, video_id, headers={'User-Agent': 'WhatsApp/2.0'}) # whatsapp ua bypasses problems
redirect_url = urlh.url
@@ -289,23 +445,69 @@ class TumblrIE(InfoExtractor):
self._download_json(
f'https://www.tumblr.com/api/v2/blog/{blog}/posts/{video_id}/permalink',
video_id, headers={'Authorization': f'Bearer {self._ACCESS_TOKEN}'}, fatal=False),
('response', 'timeline', 'elements', 0)) or {}
content_json = traverse_obj(post_json, ('trail', 0, 'content'), ('content')) or []
video_json = next(
(item for item in content_json if item.get('type') == 'video'), {})
media_json = video_json.get('media') or {}
if api_only and not media_json.get('url') and not video_json.get('url'):
raise ExtractorError('Failed to find video data for dashboard-only post')
('response', 'timeline', 'elements', 0, {dict})) or {}
content_json = traverse_obj(post_json, ((('trail', 0), None), 'content', ..., {dict}))
if not media_json.get('url') and video_json.get('url'):
# external video host
return self.url_result(
video_json['url'],
self._providers.get(video_json.get('provider'), 'Generic'))
# the url we're extracting from might be an original post or it might be a reblog.
# if it's a reblog, og:description will be the reblogger's comment, not the uploader's.
# content_json is always the op, so if it exists but has no text, there's no description
if content_json:
description = '\n\n'.join(
item.get('text') for item in content_json if item.get('type') == 'text') or None
else:
description = self._og_search_description(webpage, default=None)
uploader_id = traverse_obj(post_json, 'reblogged_root_name', 'blog_name')
video_url = self._og_search_video_url(webpage, default=None)
duration = None
info_dict = {
'id': video_id,
'title': post_json.get('summary') or (blog if api_only else self._html_search_regex(
r'(?s)<title>(?P<title>.*?)(?: \| Tumblr)?</title>', webpage, 'title', default=blog)),
'description': description,
'uploader_id': uploader_id,
'uploader_url': f'https://{uploader_id}.tumblr.com/' if uploader_id else None,
**traverse_obj(post_json, {
'like_count': ('like_count', {int_or_none}),
'repost_count': ('reblog_count', {int_or_none}),
'tags': ('tags', ..., {str}),
}),
'age_limit': {True: 18, False: 0}.get(post_json.get('is_nsfw')),
}
# for tumblr's own video hosting
fallback_format = None
formats = []
video_url = self._og_search_video_url(webpage, default=None)
# for external video hosts
entries = []
ignored_providers = set()
unknown_providers = set()
for video_json in traverse_obj(content_json, lambda _, v: v['type'] in ('video', 'audio')):
media_json = video_json.get('media') or {}
if api_only and not media_json.get('url') and not video_json.get('url'):
raise ExtractorError('Failed to find video data for dashboard-only post')
provider = video_json.get('provider')
if provider in ('tumblr', None):
fallback_format = {
'url': media_json.get('url') or video_url,
'width': int_or_none(
media_json.get('width') or self._og_search_property('video:width', webpage, default=None)),
'height': int_or_none(
media_json.get('height') or self._og_search_property('video:height', webpage, default=None)),
}
continue
elif provider in self._unsupported_providers:
ignored_providers.add(provider)
continue
elif provider and provider not in self._providers:
unknown_providers.add(provider)
if video_json.get('url'):
# external video host
entries.append(self.url_result(
video_json['url'], self._providers.get(provider)))
duration = None
# iframes can supply duration and sometimes additional formats, so check for one
iframe_url = self._search_regex(
@@ -344,44 +546,36 @@ class TumblrIE(InfoExtractor):
'quality': quality,
} for quality, (video_url, format_id) in enumerate(sources)]
if not media_json.get('url') and not video_url and not iframe_url:
# external video host (but we weren't able to figure it out from the api)
iframe_url = self._search_regex(
r'src=["\'](https?://safe\.txmblr\.com/svc/embed/inline/[^"\']+)["\']',
webpage, 'embed iframe url', default=None)
return self.url_result(iframe_url or redirect_url, 'Generic')
if not formats and fallback_format:
formats.append(fallback_format)
formats = formats or [{
'url': media_json.get('url') or video_url,
'width': int_or_none(
media_json.get('width') or self._og_search_property('video:width', webpage, default=None)),
'height': int_or_none(
media_json.get('height') or self._og_search_property('video:height', webpage, default=None)),
}]
if formats:
# tumblr's own video is always above embeds
entries.insert(0, {
**info_dict,
'formats': formats,
'duration': duration,
'thumbnail': (traverse_obj(video_json, ('poster', 0, 'url', {url_or_none}))
or self._og_search_thumbnail(webpage, default=None)),
})
# the url we're extracting from might be an original post or it might be a reblog.
# if it's a reblog, og:description will be the reblogger's comment, not the uploader's.
# content_json is always the op, so if it exists but has no text, there's no description
if content_json:
description = '\n\n'.join(
item.get('text') for item in content_json if item.get('type') == 'text') or None
else:
description = self._og_search_description(webpage, default=None)
uploader_id = traverse_obj(post_json, 'reblogged_root_name', 'blog_name')
if ignored_providers:
if not entries:
raise ExtractorError(f'None of embed providers are supported: {", ".join(ignored_providers)!s}', video_id=video_id, expected=True)
else:
self.report_warning(f'Skipped embeds from unsupported providers: {", ".join(ignored_providers)!s}', video_id)
if unknown_providers:
self.report_warning(f'Unrecognized providers, please report: {", ".join(unknown_providers)!s}', video_id)
if not entries:
self.raise_no_formats('No video could be found in this post', expected=True, video_id=video_id)
if len(entries) == 1:
return {
**info_dict,
**entries[0],
}
return {
'id': video_id,
'title': post_json.get('summary') or (blog if api_only else self._html_search_regex(
r'(?s)<title>(?P<title>.*?)(?: \| Tumblr)?</title>', webpage, 'title')),
'description': description,
'thumbnail': (traverse_obj(video_json, ('poster', 0, 'url'))
or self._og_search_thumbnail(webpage, default=None)),
'uploader_id': uploader_id,
'uploader_url': f'https://{uploader_id}.tumblr.com/' if uploader_id else None,
'duration': duration,
'like_count': post_json.get('like_count'),
'repost_count': post_json.get('reblog_count'),
'age_limit': {True: 18, False: 0}.get(post_json.get('is_nsfw')),
'tags': post_json.get('tags'),
'formats': formats,
**info_dict,
'_type': 'playlist',
'entries': entries,
}

3
yt_dlp/extractor/tva.py
View File

@@ -1,4 +1,3 @@
import functools
import re
from .brightcove import BrightcoveNewIE
@@ -68,7 +67,7 @@ class TVAIE(InfoExtractor):
'episode': episode,
**traverse_obj(entity, {
'description': ('longDescription', {str}),
'duration': ('durationMillis', {functools.partial(float_or_none, scale=1000)}),
'duration': ('durationMillis', {float_or_none(scale=1000)}),
'channel': ('knownEntities', 'channel', 'name', {str}),
'series': ('knownEntities', 'videoShow', 'name', {str}),
'season_number': ('slug', {lambda x: re.search(r'/s(?:ai|ea)son-(\d+)/', x)}, 1, {int_or_none}),

8
yt_dlp/extractor/twitter.py
View File

@@ -150,14 +150,6 @@ class TwitterBaseIE(InfoExtractor):
def is_logged_in(self):
return bool(self._get_cookies(self._API_BASE).get('auth_token'))
# XXX: Temporary workaround until twitter.com => x.com migration is completed
def _real_initialize(self):
if self.is_logged_in or not self._get_cookies('https://twitter.com/').get('auth_token'):
return
# User has not yet been migrated to x.com and has passed twitter.com cookies
TwitterBaseIE._API_BASE = 'https://api.twitter.com/1.1/'
TwitterBaseIE._GRAPHQL_API_BASE = 'https://twitter.com/i/api/graphql/'
@functools.cached_property
def _selected_api(self):
return self._configuration_arg('api', ['graphql'], ie_key='Twitter')[0]

189
yt_dlp/extractor/veoh.py
View File

@@ -1,189 +0,0 @@
import functools
import json
from .common import InfoExtractor
from ..utils import (
ExtractorError,
OnDemandPagedList,
int_or_none,
parse_duration,
qualities,
remove_start,
strip_or_none,
)
class VeohIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?veoh\.com/(?:watch|videos|embed|iphone/#_Watch)/(?P<id>(?:v|e|yapi-)[\da-zA-Z]+)'
_TESTS = [{
'url': 'http://www.veoh.com/watch/v56314296nk7Zdmz3',
'md5': '620e68e6a3cff80086df3348426c9ca3',
'info_dict': {
'id': 'v56314296nk7Zdmz3',
'ext': 'mp4',
'title': 'Straight Backs Are Stronger',
'description': 'md5:203f976279939a6dc664d4001e13f5f4',
'thumbnail': 're:https://fcache\\.veoh\\.com/file/f/th56314296\\.jpg(\\?.*)?',
'uploader': 'LUMOback',
'duration': 46,
'view_count': int,
'average_rating': int,
'comment_count': int,
'age_limit': 0,
'categories': ['technology_and_gaming'],
'tags': ['posture', 'posture', 'sensor', 'back', 'pain', 'wearable', 'tech', 'lumo'],
},
}, {
'url': 'http://www.veoh.com/embed/v56314296nk7Zdmz3',
'only_matching': True,
}, {
'url': 'http://www.veoh.com/watch/v27701988pbTc4wzN?h1=Chile+workers+cover+up+to+avoid+skin+damage',
'md5': '4a6ff84b87d536a6a71e6aa6c0ad07fa',
'info_dict': {
'id': '27701988',
'ext': 'mp4',
'title': 'Chile workers cover up to avoid skin damage',
'description': 'md5:2bd151625a60a32822873efc246ba20d',
'uploader': 'afp-news',
'duration': 123,
},
'skip': 'This video has been deleted.',
}, {
'url': 'http://www.veoh.com/watch/v69525809F6Nc4frX',
'md5': '4fde7b9e33577bab2f2f8f260e30e979',
'note': 'Embedded ooyala video',
'info_dict': {
'id': '69525809',
'ext': 'mp4',
'title': 'Doctors Alter Plan For Preteen\'s Weight Loss Surgery',
'description': 'md5:f5a11c51f8fb51d2315bca0937526891',
'uploader': 'newsy-videos',
},
'skip': 'This video has been deleted.',
}, {
'url': 'http://www.veoh.com/watch/e152215AJxZktGS',
'only_matching': True,
}, {
'url': 'https://www.veoh.com/videos/v16374379WA437rMH',
'md5': 'cceb73f3909063d64f4b93d4defca1b3',
'info_dict': {
'id': 'v16374379WA437rMH',
'ext': 'mp4',
'title': 'Phantasmagoria 2, pt. 1-3',
'description': 'Phantasmagoria: a Puzzle of Flesh',
'thumbnail': 're:https://fcache\\.veoh\\.com/file/f/th16374379\\.jpg(\\?.*)?',
'uploader': 'davidspackage',
'duration': 968,
'view_count': int,
'average_rating': int,
'comment_count': int,
'age_limit': 18,
'categories': ['technology_and_gaming', 'gaming'],
'tags': ['puzzle', 'of', 'flesh'],
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
metadata = self._download_json(
'https://www.veoh.com/watch/getVideo/' + video_id,
video_id)
video = metadata['video']
title = video['title']
thumbnail_url = None
q = qualities(['Regular', 'HQ'])
formats = []
for f_id, f_url in video.get('src', {}).items():
if not f_url:
continue
if f_id == 'poster':
thumbnail_url = f_url
else:
formats.append({
'format_id': f_id,
'quality': q(f_id),
'url': f_url,
})
categories = metadata.get('categoryPath')
if not categories:
category = remove_start(strip_or_none(video.get('category')), 'category_')
categories = [category] if category else None
tags = video.get('tags')
return {
'id': video_id,
'title': title,
'description': video.get('description'),
'thumbnail': thumbnail_url,
'uploader': video.get('author', {}).get('nickname'),
'duration': int_or_none(video.get('lengthBySec')) or parse_duration(video.get('length')),
'view_count': int_or_none(video.get('views')),
'formats': formats,
'average_rating': int_or_none(video.get('rating')),
'comment_count': int_or_none(video.get('numOfComments')),
'age_limit': 18 if video.get('contentRatingId') == 2 else 0,
'categories': categories,
'tags': tags.split(', ') if tags else None,
}
class VeohUserIE(VeohIE): # XXX: Do not subclass from concrete IE
_VALID_URL = r'https?://(?:www\.)?veoh\.com/users/(?P<id>[\w-]+)'
IE_NAME = 'veoh:user'
_TESTS = [
{
'url': 'https://www.veoh.com/users/valentinazoe',
'info_dict': {
'id': 'valentinazoe',
'title': 'valentinazoe (Uploads)',
},
'playlist_mincount': 75,
},
{
'url': 'https://www.veoh.com/users/PiensaLibre',
'info_dict': {
'id': 'PiensaLibre',
'title': 'PiensaLibre (Uploads)',
},
'playlist_mincount': 2,
}]
_PAGE_SIZE = 16
def _fetch_page(self, uploader, page):
response = self._download_json(
'https://www.veoh.com/users/published/videos', uploader,
note=f'Downloading videos page {page + 1}',
headers={
'x-csrf-token': self._TOKEN,
'content-type': 'application/json;charset=UTF-8',
},
data=json.dumps({
'username': uploader,
'maxResults': self._PAGE_SIZE,
'page': page + 1,
'requestName': 'userPage',
}).encode())
if not response.get('success'):
raise ExtractorError(response['message'])
for video in response['videos']:
yield self.url_result(f'https://www.veoh.com/watch/{video["permalinkId"]}', VeohIE,
video['permalinkId'], video.get('title'))
def _real_initialize(self):
webpage = self._download_webpage(
'https://www.veoh.com', None, note='Downloading authorization token')
self._TOKEN = self._search_regex(
r'csrfToken:\s*(["\'])(?P<token>[0-9a-zA-Z]{40})\1', webpage,
'request token', group='token')
def _real_extract(self, url):
uploader = self._match_id(url)
return self.playlist_result(OnDemandPagedList(
functools.partial(self._fetch_page, uploader),
self._PAGE_SIZE), uploader, f'{uploader} (Uploads)')

5
yt_dlp/extractor/vidyard.py
View File

@@ -1,4 +1,3 @@
import functools
import re
from .common import InfoExtractor
@@ -72,9 +71,9 @@ class VidyardBaseIE(InfoExtractor):
'id': ('facadeUuid', {str}),
'display_id': ('videoId', {int}, {str_or_none}),
'title': ('name', {str}),
'description': ('description', {str}, {unescapeHTML}, {lambda x: x or None}),
'description': ('description', {str}, {unescapeHTML}, filter),
'duration': ((
('milliseconds', {functools.partial(float_or_none, scale=1000)}),
('milliseconds', {float_or_none(scale=1000)}),
('seconds', {int_or_none})), any),
'thumbnails': ('thumbnailUrls', ('small', 'normal'), {'url': {url_or_none}}),
'tags': ('tags', ..., 'name', {str}),

3
yt_dlp/extractor/vrt.py
View File

@@ -1,4 +1,3 @@
import functools
import json
import time
import urllib.parse
@@ -171,7 +170,7 @@ class VRTIE(VRTBaseIE):
**traverse_obj(data, {
'title': ('title', {str}),
'description': ('shortDescription', {str}),
'duration': ('duration', {functools.partial(float_or_none, scale=1000)}),
'duration': ('duration', {float_or_none(scale=1000)}),
'thumbnail': ('posterImageUrl', {url_or_none}),
}),
}

6
yt_dlp/extractor/weibo.py
View File

@@ -67,7 +67,7 @@ class WeiboBaseIE(InfoExtractor):
'format': ('quality_desc', {str}),
'format_id': ('label', {str}),
'ext': ('mime', {mimetype2ext}),
'tbr': ('bitrate', {int_or_none}, {lambda x: x or None}),
'tbr': ('bitrate', {int_or_none}, filter),
'vcodec': ('video_codecs', {str}),
'fps': ('fps', {int_or_none}),
'width': ('width', {int_or_none}),
@@ -107,14 +107,14 @@ class WeiboBaseIE(InfoExtractor):
**traverse_obj(video_info, {
'id': (('id', 'id_str', 'mid'), {str_or_none}),
'display_id': ('mblogid', {str_or_none}),
'title': ('page_info', 'media_info', ('video_title', 'kol_title', 'name'), {str}, {lambda x: x or None}),
'title': ('page_info', 'media_info', ('video_title', 'kol_title', 'name'), {str}, filter),
'description': ('text_raw', {str}),
'duration': ('page_info', 'media_info', 'duration', {int_or_none}),
'timestamp': ('page_info', 'media_info', 'video_publish_time', {int_or_none}),
'thumbnail': ('page_info', 'page_pic', {url_or_none}),
'uploader': ('user', 'screen_name', {str}),
'uploader_id': ('user', ('id', 'id_str'), {str_or_none}),
'uploader_url': ('user', 'profile_url', {lambda x: urljoin('https://weibo.com/', x)}),
'uploader_url': ('user', 'profile_url', {urljoin('https://weibo.com/')}),
'view_count': ('page_info', 'media_info', 'online_users_number', {int_or_none}),
'like_count': ('attitudes_count', {int_or_none}),
'repost_count': ('reposts_count', {int_or_none}),

6
yt_dlp/extractor/weverse.py
View File

@@ -159,8 +159,8 @@ class WeverseBaseIE(InfoExtractor):
'creators': ('community', 'communityName', {str}, all),
'channel_id': (('community', 'author'), 'communityId', {str_or_none}),
'duration': ('extension', 'video', 'playTime', {float_or_none}),
'timestamp': ('publishedAt', {lambda x: int_or_none(x, 1000)}),
'release_timestamp': ('extension', 'video', 'onAirStartAt', {lambda x: int_or_none(x, 1000)}),
'timestamp': ('publishedAt', {int_or_none(scale=1000)}),
'release_timestamp': ('extension', 'video', 'onAirStartAt', {int_or_none(scale=1000)}),
'thumbnail': ('extension', (('mediaInfo', 'thumbnail', 'url'), ('video', 'thumb')), {url_or_none}),
'view_count': ('extension', 'video', 'playCount', {int_or_none}),
'like_count': ('extension', 'video', 'likeCount', {int_or_none}),
@@ -469,7 +469,7 @@ class WeverseMomentIE(WeverseBaseIE):
'creator': (('community', 'author'), 'communityName', {str}),
'channel_id': (('community', 'author'), 'communityId', {str_or_none}),
'duration': ('extension', 'moment', 'video', 'uploadInfo', 'playTime', {float_or_none}),
'timestamp': ('publishedAt', {lambda x: int_or_none(x, 1000)}),
'timestamp': ('publishedAt', {int_or_none(scale=1000)}),
'thumbnail': ('extension', 'moment', 'video', 'uploadInfo', 'imageUrl', {url_or_none}),
'like_count': ('emotionCount', {int_or_none}),
'comment_count': ('commentCount', {int_or_none}),

2
yt_dlp/extractor/wevidi.py
View File

@@ -78,7 +78,7 @@ class WeVidiIE(InfoExtractor):
}
src_path = f'{wvplayer_props["srcVID"]}/{wvplayer_props["srcUID"]}/{wvplayer_props["srcNAME"]}'
for res in traverse_obj(wvplayer_props, ('resolutions', ..., {int}, {lambda x: x or None})):
for res in traverse_obj(wvplayer_props, ('resolutions', ..., {int}, filter)):
format_id = str(-(res // -2) - 1)
yield {
'acodec': 'mp4a.40.2',

3
yt_dlp/extractor/xiaohongshu.py
View File

@@ -1,4 +1,3 @@
import functools
from .common import InfoExtractor
from ..utils import (
@@ -51,7 +50,7 @@ class XiaoHongShuIE(InfoExtractor):
'tbr': ('avgBitrate', {int_or_none}),
'format': ('qualityType', {str}),
'filesize': ('size', {int_or_none}),
'duration': ('duration', {functools.partial(float_or_none, scale=1000)}),
'duration': ('duration', {float_or_none(scale=1000)}),
})
formats.extend(traverse_obj(info, (('mediaUrl', ('backupUrls', ...)), {

158
yt_dlp/extractor/yle_areena.py
View File

@@ -1,12 +1,13 @@
from .common import InfoExtractor
from .kaltura import KalturaIE
from ..utils import (
ExtractorError,
int_or_none,
parse_iso8601,
smuggle_url,
traverse_obj,
unified_strdate,
url_or_none,
)
from ..utils.traversal import traverse_obj
class YleAreenaIE(InfoExtractor):
@@ -15,9 +16,9 @@ class YleAreenaIE(InfoExtractor):
_TESTS = [
{
'url': 'https://areena.yle.fi/1-4371942',
'md5': '932edda0ecf5dfd6423804182d32f8ac',
'md5': 'd87e9a1e74e67e009990ddd413e426b4',
'info_dict': {
'id': '0_a3tjk92c',
'id': '1-4371942',
'ext': 'mp4',
'title': 'Pouchit',
'description': 'md5:01071d7056ceec375f63960f90c35366',
@@ -26,37 +27,27 @@ class YleAreenaIE(InfoExtractor):
'season_number': 1,
'episode': 'Episode 2',
'episode_number': 2,
'thumbnail': 'http://cfvod.kaltura.com/p/1955031/sp/195503100/thumbnail/entry_id/0_a3tjk92c/version/100061',
'uploader_id': 'ovp@yle.fi',
'duration': 1435,
'view_count': int,
'upload_date': '20181204',
'release_date': '20190106',
'timestamp': 1543916210,
'subtitles': {'fin': [{'url': r're:^https?://', 'ext': 'srt'}]},
'thumbnail': r're:https://images\.cdn\.yle\.fi/image/upload/.+\.jpg',
'age_limit': 7,
'webpage_url': 'https://areena.yle.fi/1-4371942',
'release_date': '20190105',
'release_timestamp': 1546725660,
'duration': 1435,
},
},
{
'url': 'https://areena.yle.fi/1-2158940',
'md5': 'cecb603661004e36af8c5188b5212b12',
'md5': '6369ddc5e07b5fdaeda27a495184143c',
'info_dict': {
'id': '1_l38iz9ur',
'id': '1-2158940',
'ext': 'mp4',
'title': 'Albi haluaa vessan',
'description': 'md5:15236d810c837bed861fae0e88663c33',
'description': 'Albi haluaa vessan.',
'series': 'Albi Lumiukko',
'thumbnail': 'http://cfvod.kaltura.com/p/1955031/sp/195503100/thumbnail/entry_id/1_l38iz9ur/version/100021',
'uploader_id': 'ovp@yle.fi',
'duration': 319,
'view_count': int,
'upload_date': '20211202',
'release_date': '20211215',
'timestamp': 1638448202,
'subtitles': {},
'thumbnail': r're:https://images\.cdn\.yle\.fi/image/upload/.+\.jpg',
'age_limit': 0,
'webpage_url': 'https://areena.yle.fi/1-2158940',
'release_date': '20211215',
'release_timestamp': 1639555200,
'duration': 319,
},
},
{
@@ -67,72 +58,125 @@ class YleAreenaIE(InfoExtractor):
'title': 'HKO & Mälkki & Tanner',
'description': 'md5:b4f1b1af2c6569b33f75179a86eea156',
'series': 'Helsingin kaupunginorkesterin konsertteja',
'thumbnail': r're:^https?://.+\.jpg$',
'thumbnail': r're:https://images\.cdn\.yle\.fi/image/upload/.+\.jpg',
'release_date': '20230120',
'release_timestamp': 1674242079,
'duration': 8004,
},
'params': {
'skip_download': 'm3u8',
},
},
{
'url': 'https://areena.yle.fi/1-72251830',
'info_dict': {
'id': '1-72251830',
'ext': 'mp4',
'title': r're:Pentulive 2024 | Pentulive \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
'description': 'md5:1f118707d9093bf894a34fbbc865397b',
'series': 'Pentulive',
'thumbnail': r're:https://images\.cdn\.yle\.fi/image/upload/.+\.jpg',
'live_status': 'is_live',
'release_date': '20241025',
'release_timestamp': 1729875600,
},
'params': {
'skip_download': 'livestream',
},
},
{
'url': 'https://areena.yle.fi/podcastit/1-71022852',
'info_dict': {
'id': '1-71022852',
'ext': 'mp3',
'title': 'Värityspäivä',
'description': 'md5:c3a02b0455ec71d32cbe09d32ec161e2',
'series': 'Murun ja Paukun ikioma kaupunki',
'episode': 'Episode 1',
'episode_number': 1,
'release_date': '20240607',
'release_timestamp': 1717736400,
'duration': 442,
},
},
]
def _real_extract(self, url):
video_id, is_podcast = self._match_valid_url(url).group('id', 'podcast')
info = self._search_json_ld(self._download_webpage(url, video_id), video_id, default={})
json_ld = self._search_json_ld(self._download_webpage(url, video_id), video_id, default={})
video_data = self._download_json(
f'https://player.api.yle.fi/v1/preview/{video_id}.json?app_id=player_static_prod&app_key=8930d72170e48303cf5f3867780d549b',
video_id, headers={
'origin': 'https://areena.yle.fi',
'referer': 'https://areena.yle.fi/',
'content-type': 'application/json',
})
})['data']
# Example title: 'K1, J2: Pouchit | Modernit miehet'
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'),
json_ld.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)
description = traverse_obj(video_data, ('ongoing_ondemand', 'description', 'fin', {str}))
subtitles = {}
for sub in traverse_obj(video_data, ('data', 'ongoing_ondemand', 'subtitles', ...)):
if url_or_none(sub.get('uri')):
subtitles.setdefault(sub.get('language') or 'und', []).append({
'url': sub['uri'],
'ext': 'srt',
'name': sub.get('kind'),
})
for sub in traverse_obj(video_data, ('ongoing_ondemand', 'subtitles', lambda _, v: url_or_none(v['uri']))):
subtitles.setdefault(sub.get('language') or 'und', []).append({
'url': sub['uri'],
'ext': 'srt',
'name': sub.get('kind'),
})
if is_podcast:
info_dict = {
'url': video_data['data']['ongoing_ondemand']['media_url'],
}
elif kaltura_id := traverse_obj(video_data, ('data', 'ongoing_ondemand', 'kaltura', 'id', {str})):
info_dict = {
info_dict, metadata = {}, {}
if is_podcast and traverse_obj(video_data, ('ongoing_ondemand', 'media_url', {url_or_none})):
metadata = video_data['ongoing_ondemand']
info_dict['url'] = metadata['media_url']
elif traverse_obj(video_data, ('ongoing_event', 'manifest_url', {url_or_none})):
metadata = video_data['ongoing_event']
metadata.pop('duration', None) # Duration is not accurate for livestreams
info_dict['live_status'] = 'is_live'
elif traverse_obj(video_data, ('ongoing_ondemand', 'manifest_url', {url_or_none})):
metadata = video_data['ongoing_ondemand']
# XXX: Has all externally-hosted Kaltura content been moved to native hosting?
elif kaltura_id := traverse_obj(video_data, ('ongoing_ondemand', 'kaltura', 'id', {str})):
metadata = video_data['ongoing_ondemand']
info_dict.update({
'_type': 'url_transparent',
'url': smuggle_url(f'kaltura:1955031:{kaltura_id}', {'source_url': url}),
'ie_key': KalturaIE.ie_key(),
}
})
elif traverse_obj(video_data, ('gone', {dict})):
self.raise_no_formats('The content is no longer available', expected=True, video_id=video_id)
metadata = video_data['gone']
else:
formats, subs = self._extract_m3u8_formats_and_subtitles(
video_data['data']['ongoing_ondemand']['manifest_url'], video_id, 'mp4', m3u8_id='hls')
raise ExtractorError('Unable to extract content')
if not info_dict.get('url') and metadata.get('manifest_url'):
info_dict['formats'], subs = self._extract_m3u8_formats_and_subtitles(
metadata['manifest_url'], video_id, 'mp4', m3u8_id='hls')
self._merge_subtitles(subs, target=subtitles)
info_dict = {'formats': formats}
return {
**info_dict,
**traverse_obj(json_ld, {
'title': 'title',
'thumbnails': ('thumbnails', ..., {'url': 'url'}),
}),
'id': video_id,
'title': (traverse_obj(video_data, ('data', 'ongoing_ondemand', 'title', 'fin'), expected_type=str)
or episode or info.get('title')),
'title': episode,
'description': description,
'series': (traverse_obj(video_data, ('data', 'ongoing_ondemand', 'series', 'title', 'fin'), expected_type=str)
or series),
'series': series,
'season_number': (int_or_none(self._search_regex(r'Kausi (\d+)', description, 'season number', default=None))
or int_or_none(season_number)),
'episode_number': (traverse_obj(video_data, ('data', 'ongoing_ondemand', 'episode_number'), expected_type=int_or_none)
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),
'episode_number': int_or_none(episode_number),
'subtitles': subtitles or None,
'release_date': unified_strdate(traverse_obj(video_data, ('data', 'ongoing_ondemand', 'start_time'), expected_type=str)),
**traverse_obj(metadata, {
'title': ('title', 'fin', {str}),
'description': ('description', 'fin', {str}),
'series': ('series', 'title', 'fin', {str}),
'episode_number': ('episode_number', {int_or_none}),
'age_limit': ('content_rating', 'age_restriction', {int_or_none}),
'release_timestamp': ('start_time', {parse_iso8601}),
'duration': ('duration', 'duration_in_seconds', {int_or_none}),
}),
**info_dict,
}

2
yt_dlp/extractor/youporn.py
View File

@@ -247,7 +247,7 @@ class YouPornListBase(InfoExtractor):
if not html:
return
for element in get_elements_html_by_class('video-title', html):
if video_url := traverse_obj(element, ({extract_attributes}, 'href', {lambda x: urljoin(url, x)})):
if video_url := traverse_obj(element, ({extract_attributes}, 'href', {urljoin(url)})):
yield self.url_result(video_url)
if page_num is not None:

322
yt_dlp/extractor/youtube.py
View File

@@ -22,7 +22,7 @@ import urllib.parse
from .common import InfoExtractor, SearchInfoExtractor
from .openload import PhantomJSwrapper
from ..jsinterp import JSInterpreter
from ..networking.exceptions import HTTPError, TransportError, network_exceptions
from ..networking.exceptions import HTTPError, network_exceptions
from ..utils import (
NO_DEFAULT,
ExtractorError,
@@ -50,12 +50,12 @@ from ..utils import (
parse_iso8601,
parse_qs,
qualities,
remove_end,
remove_start,
smuggle_url,
str_or_none,
str_to_int,
strftime_or_none,
time_seconds,
traverse_obj,
try_call,
try_get,
@@ -124,14 +124,15 @@ INNERTUBE_CLIENTS = {
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
'REQUIRE_AUTH': True,
},
'android': {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'ANDROID',
'clientVersion': '19.29.37',
'clientVersion': '19.44.38',
'androidSdkVersion': 30,
'userAgent': 'com.google.android.youtube/19.29.37 (Linux; U; Android 11) gzip',
'userAgent': 'com.google.android.youtube/19.44.38 (Linux; U; Android 11) gzip',
'osName': 'Android',
'osVersion': '11',
},
@@ -140,13 +141,14 @@ INNERTUBE_CLIENTS = {
'REQUIRE_JS_PLAYER': False,
'REQUIRE_PO_TOKEN': True,
},
# This client now requires sign-in for every video
'android_music': {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'ANDROID_MUSIC',
'clientVersion': '7.11.50',
'clientVersion': '7.27.52',
'androidSdkVersion': 30,
'userAgent': 'com.google.android.apps.youtube.music/7.11.50 (Linux; U; Android 11) gzip',
'userAgent': 'com.google.android.apps.youtube.music/7.27.52 (Linux; U; Android 11) gzip',
'osName': 'Android',
'osVersion': '11',
},
@@ -154,15 +156,16 @@ INNERTUBE_CLIENTS = {
'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
'REQUIRE_JS_PLAYER': False,
'REQUIRE_PO_TOKEN': True,
'REQUIRE_AUTH': True,
},
# This client now requires sign-in for every video
'android_creator': {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'ANDROID_CREATOR',
'clientVersion': '24.30.100',
'clientVersion': '24.45.100',
'androidSdkVersion': 30,
'userAgent': 'com.google.android.apps.youtube.creator/24.30.100 (Linux; U; Android 11) gzip',
'userAgent': 'com.google.android.apps.youtube.creator/24.45.100 (Linux; U; Android 11) gzip',
'osName': 'Android',
'osVersion': '11',
},
@@ -170,17 +173,18 @@ INNERTUBE_CLIENTS = {
'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
'REQUIRE_JS_PLAYER': False,
'REQUIRE_PO_TOKEN': True,
'REQUIRE_AUTH': True,
},
# YouTube Kids videos aren't returned on this client for some reason
'android_vr': {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'ANDROID_VR',
'clientVersion': '1.57.29',
'clientVersion': '1.60.19',
'deviceMake': 'Oculus',
'deviceModel': 'Quest 3',
'androidSdkVersion': 32,
'userAgent': 'com.google.android.apps.youtube.vr.oculus/1.57.29 (Linux; U; Android 12L; eureka-user Build/SQ3A.220605.009.A1) gzip',
'userAgent': 'com.google.android.apps.youtube.vr.oculus/1.60.19 (Linux; U; Android 12L; eureka-user Build/SQ3A.220605.009.A1) gzip',
'osName': 'Android',
'osVersion': '12L',
},
@@ -188,68 +192,56 @@ INNERTUBE_CLIENTS = {
'INNERTUBE_CONTEXT_CLIENT_NAME': 28,
'REQUIRE_JS_PLAYER': False,
},
'android_testsuite': {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'ANDROID_TESTSUITE',
'clientVersion': '1.9',
'androidSdkVersion': 30,
'userAgent': 'com.google.android.youtube/1.9 (Linux; U; Android 11) gzip',
'osName': 'Android',
'osVersion': '11',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 30,
'REQUIRE_JS_PLAYER': False,
'PLAYER_PARAMS': '2AMB',
},
# iOS clients have HLS live streams. Setting device model to get 60fps formats.
# See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
'ios': {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'IOS',
'clientVersion': '19.29.1',
'clientVersion': '19.45.4',
'deviceMake': 'Apple',
'deviceModel': 'iPhone16,2',
'userAgent': 'com.google.ios.youtube/19.29.1 (iPhone16,2; U; CPU iOS 17_5_1 like Mac OS X;)',
'userAgent': 'com.google.ios.youtube/19.45.4 (iPhone16,2; U; CPU iOS 18_1_0 like Mac OS X;)',
'osName': 'iPhone',
'osVersion': '17.5.1.21F90',
'osVersion': '18.1.0.22B83',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
'REQUIRE_JS_PLAYER': False,
},
# This client now requires sign-in for every video
'ios_music': {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'IOS_MUSIC',
'clientVersion': '7.08.2',
'clientVersion': '7.27.0',
'deviceMake': 'Apple',
'deviceModel': 'iPhone16,2',
'userAgent': 'com.google.ios.youtubemusic/7.08.2 (iPhone16,2; U; CPU iOS 17_5_1 like Mac OS X;)',
'userAgent': 'com.google.ios.youtubemusic/7.27.0 (iPhone16,2; U; CPU iOS 18_1_0 like Mac OS X;)',
'osName': 'iPhone',
'osVersion': '17.5.1.21F90',
'osVersion': '18.1.0.22B83',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
'REQUIRE_JS_PLAYER': False,
'REQUIRE_AUTH': True,
},
# This client now requires sign-in for every video
'ios_creator': {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'IOS_CREATOR',
'clientVersion': '24.30.100',
'clientVersion': '24.45.100',
'deviceMake': 'Apple',
'deviceModel': 'iPhone16,2',
'userAgent': 'com.google.ios.ytcreator/24.30.100 (iPhone16,2; U; CPU iOS 17_5_1 like Mac OS X;)',
'userAgent': 'com.google.ios.ytcreator/24.45.100 (iPhone16,2; U; CPU iOS 18_1_0 like Mac OS X;)',
'osName': 'iPhone',
'osVersion': '17.5.1.21F90',
'osVersion': '18.1.0.22B83',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
'REQUIRE_JS_PLAYER': False,
'REQUIRE_AUTH': True,
},
# mweb has 'ultralow' formats
# See: https://github.com/yt-dlp/yt-dlp/pull/557
@@ -282,8 +274,10 @@ INNERTUBE_CLIENTS = {
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 85,
'REQUIRE_AUTH': True,
},
# This client has pre-merged video+audio 720p/1080p streams
# This client now requires sign-in for every video
# It may be able to receive pre-merged video+audio 720p/1080p streams
'mediaconnect': {
'INNERTUBE_CONTEXT': {
'client': {
@@ -293,6 +287,7 @@ INNERTUBE_CLIENTS = {
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 95,
'REQUIRE_JS_PLAYER': False,
'REQUIRE_AUTH': True,
},
}
@@ -321,6 +316,7 @@ def build_innertube_clients():
ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
ytcfg.setdefault('REQUIRE_PO_TOKEN', False)
ytcfg.setdefault('REQUIRE_AUTH', False)
ytcfg.setdefault('PLAYER_PARAMS', None)
ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
@@ -577,207 +573,18 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
self._check_login_required()
def _perform_login(self, username, password):
auth_type, _, user = (username or '').partition('+')
if auth_type != 'oauth':
raise ExtractorError(self._youtube_login_hint, expected=True)
self._initialize_oauth(user, password)
'''
OAuth 2.0 Device Authorization Grant flow, used by the YouTube TV client (youtube.com/tv).
For more information regarding OAuth 2.0 and the Device Authorization Grant flow in general, see:
- https://developers.google.com/identity/protocols/oauth2/limited-input-device
- https://accounts.google.com/.well-known/openid-configuration
- https://www.rfc-editor.org/rfc/rfc8628
- https://www.rfc-editor.org/rfc/rfc6749
Note: The official client appears to use a proxied version of the oauth2 endpoints on youtube.com/o/oauth2,
which applies some modifications to the response (such as returning errors as 200 OK).
Since the client works with the standard API, we will use that as it is well-documented.
'''
_OAUTH_PROFILE = None
_OAUTH_ACCESS_TOKEN_CACHE = {}
_OAUTH_DISPLAY_ID = 'oauth'
# YouTube TV (TVHTML5) client. You can find these at youtube.com/tv
_OAUTH_CLIENT_ID = '861556708454-d6dlm3lh05idd8npek18k6be8ba3oc68.apps.googleusercontent.com'
_OAUTH_CLIENT_SECRET = 'SboVhoG9s0rNafixCSGGKXAT'
_OAUTH_SCOPE = 'http://gdata.youtube.com https://www.googleapis.com/auth/youtube-paid-content'
# From https://accounts.google.com/.well-known/openid-configuration
# Technically, these should be fetched dynamically and not hard-coded.
# However, as these endpoints rarely change, we can risk saving an extra request for every invocation.
_OAUTH_DEVICE_AUTHORIZATION_ENDPOINT = 'https://oauth2.googleapis.com/device/code'
_OAUTH_TOKEN_ENDPOINT = 'https://oauth2.googleapis.com/token'
@property
def _oauth_cache_key(self):
return f'oauth_refresh_token_{self._OAUTH_PROFILE}'
def _read_oauth_error_response(self, response):
return traverse_obj(
self._webpage_read_content(response, self._OAUTH_TOKEN_ENDPOINT, self._OAUTH_DISPLAY_ID, fatal=False),
({json.loads}, 'error', {str}))
def _set_oauth_info(self, token_response):
YoutubeBaseInfoExtractor._OAUTH_ACCESS_TOKEN_CACHE.setdefault(self._OAUTH_PROFILE, {}).update({
'access_token': token_response['access_token'],
'token_type': token_response['token_type'],
'expiry': time_seconds(
seconds=traverse_obj(token_response, ('expires_in', {float_or_none}), default=300) - 10),
})
refresh_token = traverse_obj(token_response, ('refresh_token', {str}))
if refresh_token:
self.cache.store(self._NETRC_MACHINE, self._oauth_cache_key, refresh_token)
YoutubeBaseInfoExtractor._OAUTH_ACCESS_TOKEN_CACHE[self._OAUTH_PROFILE]['refresh_token'] = refresh_token
def _initialize_oauth(self, user, refresh_token):
self._OAUTH_PROFILE = user or 'default'
if self._OAUTH_PROFILE in YoutubeBaseInfoExtractor._OAUTH_ACCESS_TOKEN_CACHE:
self.write_debug(f'{self._OAUTH_DISPLAY_ID}: Using cached access token for profile "{self._OAUTH_PROFILE}"')
return
YoutubeBaseInfoExtractor._OAUTH_ACCESS_TOKEN_CACHE[self._OAUTH_PROFILE] = {}
if refresh_token:
refresh_token = refresh_token.strip('\'') or None
# Allow refresh token passed to initialize cache
if refresh_token:
self.cache.store(self._NETRC_MACHINE, self._oauth_cache_key, refresh_token)
refresh_token = refresh_token or self.cache.load(self._NETRC_MACHINE, self._oauth_cache_key)
if refresh_token:
YoutubeBaseInfoExtractor._OAUTH_ACCESS_TOKEN_CACHE[self._OAUTH_PROFILE]['refresh_token'] = refresh_token
try:
token_response = self._refresh_token(refresh_token)
except ExtractorError as e:
error_msg = str(e.orig_msg).replace('Failed to refresh access token: ', '')
self.report_warning(f'{self._OAUTH_DISPLAY_ID}: Failed to refresh access token: {error_msg}')
token_response = self._oauth_authorize
else:
token_response = self._oauth_authorize
self._set_oauth_info(token_response)
self.write_debug(f'{self._OAUTH_DISPLAY_ID}: Logged in using profile "{self._OAUTH_PROFILE}"')
def _refresh_token(self, refresh_token):
try:
token_response = self._download_json(
self._OAUTH_TOKEN_ENDPOINT,
video_id=self._OAUTH_DISPLAY_ID,
note='Refreshing access token',
data=json.dumps({
'client_id': self._OAUTH_CLIENT_ID,
'client_secret': self._OAUTH_CLIENT_SECRET,
'refresh_token': refresh_token,
'grant_type': 'refresh_token',
}).encode(),
headers={'Content-Type': 'application/json'})
except ExtractorError as e:
if isinstance(e.cause, HTTPError):
error = self._read_oauth_error_response(e.cause.response)
if error == 'invalid_grant':
# RFC6749 § 5.2
raise ExtractorError(
'Failed to refresh access token: Refresh token is invalid, revoked, or expired (invalid_grant)',
expected=True, video_id=self._OAUTH_DISPLAY_ID)
raise ExtractorError(
f'Failed to refresh access token: Authorization server returned error {error}',
video_id=self._OAUTH_DISPLAY_ID)
raise
return token_response
@property
def _oauth_authorize(self):
code_response = self._download_json(
self._OAUTH_DEVICE_AUTHORIZATION_ENDPOINT,
video_id=self._OAUTH_DISPLAY_ID,
note='Initializing authorization flow',
data=json.dumps({
'client_id': self._OAUTH_CLIENT_ID,
'scope': self._OAUTH_SCOPE,
}).encode(),
headers={'Content-Type': 'application/json'})
verification_url = traverse_obj(code_response, ('verification_url', {str}))
user_code = traverse_obj(code_response, ('user_code', {str}))
if not verification_url or not user_code:
if username.startswith('oauth'):
raise ExtractorError(
'Authorization server did not provide verification_url or user_code', video_id=self._OAUTH_DISPLAY_ID)
f'Login with OAuth is no longer supported. {self._youtube_login_hint}', expected=True)
# note: The whitespace is intentional
self.to_screen(
f'{self._OAUTH_DISPLAY_ID}: To give yt-dlp access to your account, '
f'go to {verification_url} and enter code {user_code}')
# RFC8628 § 3.5: default poll interval is 5 seconds if not provided
poll_interval = traverse_obj(code_response, ('interval', {int}), default=5)
for retry in self.RetryManager():
while True:
try:
token_response = self._download_json(
self._OAUTH_TOKEN_ENDPOINT,
video_id=self._OAUTH_DISPLAY_ID,
note=False,
errnote='Failed to request access token',
data=json.dumps({
'client_id': self._OAUTH_CLIENT_ID,
'client_secret': self._OAUTH_CLIENT_SECRET,
'device_code': code_response['device_code'],
'grant_type': 'urn:ietf:params:oauth:grant-type:device_code',
}).encode(),
headers={'Content-Type': 'application/json'})
except ExtractorError as e:
if isinstance(e.cause, TransportError):
retry.error = e
break
elif isinstance(e.cause, HTTPError):
error = self._read_oauth_error_response(e.cause.response)
if not error:
retry.error = e
break
if error == 'authorization_pending':
time.sleep(poll_interval)
continue
elif error == 'expired_token':
raise ExtractorError(
'Authorization timed out', expected=True, video_id=self._OAUTH_DISPLAY_ID)
elif error == 'access_denied':
raise ExtractorError(
'You denied access to an account', expected=True, video_id=self._OAUTH_DISPLAY_ID)
elif error == 'slow_down':
# RFC8628 § 3.5: add 5 seconds to the poll interval
poll_interval += 5
time.sleep(poll_interval)
continue
else:
raise ExtractorError(
f'Authorization server returned an error when fetching access token: {error}',
video_id=self._OAUTH_DISPLAY_ID)
raise
return token_response
def _update_oauth(self):
token = YoutubeBaseInfoExtractor._OAUTH_ACCESS_TOKEN_CACHE.get(self._OAUTH_PROFILE)
if token is None or token['expiry'] > time.time():
return
self._set_oauth_info(self._refresh_token(token['refresh_token']))
self.report_warning(
f'Login with password is not supported for YouTube. {self._youtube_login_hint}')
@property
def _youtube_login_hint(self):
return ('Use --username=oauth[+PROFILE] --password="" to log in using oauth, '
f'or else u{self._login_hint(method="cookies")[1:]}. '
'See https://github.com/yt-dlp/yt-dlp/wiki/Extractors#logging-in-with-oauth for more on how to use oauth. '
'See https://github.com/yt-dlp/yt-dlp/wiki/Extractors#exporting-youtube-cookies for help with cookies')
return (f'{self._login_hint(method="cookies")}. Also see '
'https://github.com/yt-dlp/yt-dlp/wiki/Extractors#exporting-youtube-cookies '
'for tips on effectively exporting YouTube cookies')
def _check_login_required(self):
if self._LOGIN_REQUIRED and not self.is_authenticated:
@@ -927,7 +734,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
@functools.cached_property
def is_authenticated(self):
return self._OAUTH_PROFILE or bool(self._generate_sapisidhash_header())
return bool(self._generate_sapisidhash_header())
def extract_ytcfg(self, video_id, webpage):
if not webpage:
@@ -937,16 +744,6 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
default='{}'), video_id, fatal=False) or {}
def _generate_oauth_headers(self):
self._update_oauth()
oauth_token = YoutubeBaseInfoExtractor._OAUTH_ACCESS_TOKEN_CACHE.get(self._OAUTH_PROFILE)
if not oauth_token:
return {}
return {
'Authorization': f'{oauth_token["token_type"]} {oauth_token["access_token"]}',
}
def _generate_cookie_auth_headers(self, *, ytcfg=None, account_syncid=None, session_index=None, origin=None, **kwargs):
headers = {}
account_syncid = account_syncid or self._extract_account_syncid(ytcfg)
@@ -976,14 +773,10 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
'Origin': origin,
'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg),
'User-Agent': self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT']['client']['userAgent'], default_client=default_client),
**self._generate_oauth_headers(),
**self._generate_cookie_auth_headers(ytcfg=ytcfg, account_syncid=account_syncid, session_index=session_index, origin=origin),
}
return filter_dict(headers)
def _generate_webpage_headers(self):
return self._generate_oauth_headers()
def _download_ytcfg(self, client, video_id):
url = {
'web': 'https://www.youtube.com',
@@ -993,8 +786,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
if not url:
return {}
webpage = self._download_webpage(
url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config',
headers=self._generate_webpage_headers())
url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
return self.extract_ytcfg(video_id, webpage) or {}
@staticmethod
@@ -3259,8 +3051,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
code = self._download_webpage(
player_url, video_id, fatal=fatal,
note='Downloading player ' + player_id,
errnote=f'Download of {player_url} failed',
headers=self._generate_webpage_headers())
errnote=f'Download of {player_url} failed')
if code:
self._code_cache[player_id] = code
return self._code_cache.get(player_id)
@@ -3543,8 +3334,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
self._download_webpage(
url, video_id, f'Marking {label}watched',
'Unable to mark watched', fatal=False,
headers=self._generate_webpage_headers())
'Unable to mark watched', fatal=False)
@classmethod
def _extract_from_webpage(cls, url, webpage):
@@ -3610,7 +3400,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'frameworkUpdates', 'entityBatchUpdate', 'mutations',
lambda _, v: v['payload']['macroMarkersListEntity']['markersList']['markerType'] == 'MARKER_TYPE_HEATMAP',
'payload', 'macroMarkersListEntity', 'markersList', 'markers', ..., {
'start_time': ('startMillis', {functools.partial(float_or_none, scale=1000)}),
'start_time': ('startMillis', {float_or_none(scale=1000)}),
'end_time': {lambda x: (int(x['startMillis']) + int(x['durationMillis'])) / 1000},
'value': ('intensityScoreNormalized', {float_or_none}),
})) or None
@@ -3636,7 +3426,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'author_is_verified': ('author', 'isVerified', {bool}),
'author_url': ('author', 'channelCommand', 'innertubeCommand', (
('browseEndpoint', 'canonicalBaseUrl'), ('commandMetadata', 'webCommandMetadata', 'url'),
), {lambda x: urljoin('https://www.youtube.com', x)}),
), {urljoin('https://www.youtube.com')}),
}, get_all=False),
'is_favorited': (None if toolbar_entity_payload is None else
toolbar_entity_payload.get('heartState') == 'TOOLBAR_HEART_STATE_HEARTED'),
@@ -4058,9 +3848,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
if smuggled_data.get('is_music_url') or self.is_music_url(url):
for requested_client in requested_clients:
_, base_client, variant = _split_innertube_client(requested_client)
music_client = f'{base_client}_music'
music_client = f'{base_client}_music' if base_client != 'mweb' else 'web_music'
if variant != 'music' and music_client in INNERTUBE_CLIENTS:
requested_clients.append(music_client)
if not INNERTUBE_CLIENTS[music_client]['REQUIRE_AUTH'] or self.is_authenticated:
requested_clients.append(music_client)
return orderedSet(requested_clients)
@@ -4173,10 +3964,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
self.to_screen(
f'{video_id}: This video is age-restricted and YouTube is requiring '
'account age-verification; some formats may be missing', only_once=True)
# web_creator and mediaconnect can work around the age-verification requirement
# _testsuite & _vr variants can also work around age-verification
# web_creator can work around the age-verification requirement
# android_vr and mediaconnect may also be able to work around age-verification
# tv_embedded may(?) still work around age-verification if the video is embeddable
append_client('web_creator', 'mediaconnect')
append_client('web_creator')
prs.extend(deprioritized_prs)
@@ -4303,7 +4094,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
continue
tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
format_duration = traverse_obj(fmt, ('approxDurationMs', {lambda x: float_or_none(x, 1000)}))
format_duration = traverse_obj(fmt, ('approxDurationMs', {float_or_none(scale=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
# Make sure to avoid false positives with small duration differences.
@@ -4525,7 +4316,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
if pp:
query['pp'] = pp
webpage = self._download_webpage(
webpage_url, video_id, fatal=False, query=query, headers=self._generate_webpage_headers())
webpage_url, video_id, fatal=False, query=query)
master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
@@ -4668,6 +4459,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
self.raise_geo_restricted(subreason, countries, metadata_available=True)
reason += f'. {subreason}'
if reason:
if 'sign in' in reason.lower():
reason = remove_end(reason, 'This helps protect our community. Learn more')
reason = f'{remove_end(reason.strip(), ".")}. {self._youtube_login_hint}'
self.raise_no_formats(reason, expected=True)
keywords = get_first(video_details, 'keywords', expected_type=list) or []
@@ -4776,7 +4570,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'live_status': live_status,
'release_timestamp': live_start_time,
'_format_sort_fields': ( # source_preference is lower for potentially damaged formats
'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto'),
'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec', 'channels', 'acodec', 'lang', 'proto'),
}
subtitles = {}
@@ -5813,7 +5607,7 @@ class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
webpage, data = None, None
for retry in self.RetryManager(fatal=fatal):
try:
webpage = self._download_webpage(url, item_id, note='Downloading webpage', headers=self._generate_webpage_headers())
webpage = self._download_webpage(url, item_id, note='Downloading webpage')
data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
except ExtractorError as e:
if isinstance(e.cause, network_exceptions):
@@ -7857,7 +7651,7 @@ class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
'section_start': int(clip_data['startTimeMs']) / 1000,
'section_end': int(clip_data['endTimeMs']) / 1000,
'_format_sort_fields': ( # https protocol is prioritized for ffmpeg compatibility
'proto:https', 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang'),
'proto:https', 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec', 'channels', 'acodec', 'lang'),
}

2
yt_dlp/extractor/zaiko.py
View File

@@ -109,7 +109,7 @@ class ZaikoIE(ZaikoBaseIE):
'uploader': ('profile', 'name', {str}),
'uploader_id': ('profile', 'id', {str_or_none}),
'release_timestamp': ('stream', 'start', 'timestamp', {int_or_none}),
'categories': ('event', 'genres', ..., {lambda x: x or None}),
'categories': ('event', 'genres', ..., filter),
}),
'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)],