mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-12-30 11:31:25 +00:00
Code Issues Projects Releases Wiki Activity

Merge branch 'yt-dlp:master' into pr/live-sections

Browse Source
This commit is contained in:
bashonly
2024-07-10 19:08:37 -05:00
parent 66a6e0a686 705f5b84de
commit 724a6cb2cb
18 changed files with 172 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
yt_dlp/extractor/box.py
View File

@@ -12,7 +12,7 @@ from ..utils.traversal import traverse_obj
class BoxIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^.]+\.)?app\.box\.com/s/(?P<shared_name>[^/?#]+)(?:/file/(?P<id>\d+))?'
_VALID_URL = r'https?://(?:[^.]+\.)?(?P<service>app|ent)\.box\.com/s/(?P<shared_name>[^/?#]+)(?:/file/(?P<id>\d+))?'
_TESTS = [{
'url': 'https://mlssoccer.app.box.com/s/0evd2o3e08l60lr4ygukepvnkord1o1x/file/510727257538',
'md5': '1f81b2fd3960f38a40a3b8823e5fcd43',
@@ -38,10 +38,22 @@ class BoxIE(InfoExtractor):
'uploader_id': '239068974',
},
'params': {'skip_download': 'dash fragment too small'},
}, {
'url': 'https://thejacksonlaboratory.ent.box.com/s/2x09dm6vcg6y28o0oox1so4l0t8wzt6l/file/1536173056065',
'info_dict': {
'id': '1536173056065',
'ext': 'mp4',
'uploader_id': '18523128264',
'uploader': 'Lexi Hennigan',
'title': 'iPSC Symposium recording part 1.mp4',
'timestamp': 1716228343,
'upload_date': '20240520',
},
'params': {'skip_download': 'dash fragment too small'},
}]
def _real_extract(self, url):
shared_name, file_id = self._match_valid_url(url).groups()
shared_name, file_id, service = self._match_valid_url(url).group('shared_name', 'id', 'service')
webpage = self._download_webpage(url, file_id or shared_name)
if not file_id:
@@ -57,14 +69,14 @@ class BoxIE(InfoExtractor):
request_token = self._search_json(
r'Box\.config\s*=', webpage, 'Box config', file_id)['requestToken']
access_token = self._download_json(
'https://app.box.com/app-api/enduserapp/elements/tokens', file_id,
f'https://{service}.box.com/app-api/enduserapp/elements/tokens', file_id,
'Downloading token JSON metadata',
data=json.dumps({'fileIDs': [file_id]}).encode(), headers={
'Content-Type': 'application/json',
'X-Request-Token': request_token,
'X-Box-EndUser-API': 'sharedName=' + shared_name,
})[file_id]['read']
shared_link = 'https://app.box.com/s/' + shared_name
shared_link = f'https://{service}.box.com/s/{shared_name}'
f = self._download_json(
'https://api.box.com/2.0/files/' + file_id, file_id,
'Downloading file JSON metadata', headers={

32
yt_dlp/extractor/soundcloud.py
View File

@@ -314,23 +314,11 @@ class SoundcloudBaseIE(InfoExtractor):
self.write_debug(f'"{identifier}" is not a requested format, skipping')
continue
stream = None
for retry in self.RetryManager(fatal=False):
try:
stream = self._call_api(
format_url, track_id, f'Downloading {identifier} format info JSON',
query=query, headers=self._HEADERS)
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 429:
self.report_warning(
'You have reached the API rate limit, which is ~600 requests per '
'10 minutes. Use the --extractor-retries and --retry-sleep options '
'to configure an appropriate retry count and wait time', only_once=True)
retry.error = e.cause
else:
self.report_warning(e.msg)
# XXX: if not extract_flat, 429 error must be caught where _extract_info_dict is called
stream_url = traverse_obj(self._call_api(
format_url, track_id, f'Downloading {identifier} format info JSON',
query=query, headers=self._HEADERS), ('url', {url_or_none}))
stream_url = traverse_obj(stream, ('url', {url_or_none}))
if invalid_url(stream_url):
continue
format_urls.add(stream_url)
@@ -647,7 +635,17 @@ class SoundcloudIE(SoundcloudBaseIE):
info = self._call_api(
info_json_url, full_title, 'Downloading info JSON', query=query, headers=self._HEADERS)
return self._extract_info_dict(info, full_title, token)
for retry in self.RetryManager():
try:
return self._extract_info_dict(info, full_title, token)
except ExtractorError as e:
if not isinstance(e.cause, HTTPError) or not e.cause.status == 429:
raise
self.report_warning(
'You have reached the API rate limit, which is ~600 requests per '
'10 minutes. Use the --extractor-retries and --retry-sleep options '
'to configure an appropriate retry count and wait time', only_once=True)
retry.error = e.cause
class SoundcloudPlaylistBaseIE(SoundcloudBaseIE):

8
yt_dlp/extractor/tiktok.py
View File

@@ -1458,9 +1458,11 @@ class TikTokLiveIE(TikTokBaseIE):
if webpage:
data = self._get_sigi_state(webpage, uploader or room_id)
room_id = (traverse_obj(data, ('UserModule', 'users', ..., 'roomId', {str_or_none}), get_all=False)
or self._search_regex(r'snssdk\d*://live\?room_id=(\d+)', webpage, 'room ID', default=None)
or room_id)
room_id = (
traverse_obj(data, ((
('LiveRoom', 'liveRoomUserInfo', 'user'),
('UserModule', 'users', ...)), 'roomId', {str}, any))
or self._search_regex(r'snssdk\d*://live\?room_id=(\d+)', webpage, 'room ID', default=room_id))
uploader = uploader or traverse_obj(
data, ('LiveRoom', 'liveRoomUserInfo', 'user', 'uniqueId'),
('UserModule', 'users', ..., 'uniqueId'), get_all=False, expected_type=str)

2
yt_dlp/extractor/tv5mondeplus.py
View File

@@ -96,7 +96,7 @@ class TV5MondePlusIE(InfoExtractor):
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
webpage = self._download_webpage(url, display_id, impersonate=True)
if ">Ce programme n'est malheureusement pas disponible pour votre zone géographique.<" in webpage:
self.raise_geo_restricted(countries=['FR'])

17
yt_dlp/extractor/youtube.py
View File

@@ -3159,7 +3159,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
def _extract_n_function_name(self, jscode):
funcname, idx = self._search_regex(
r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
r'''(?x)(?:\.get\("n"\)\)&&\(b=|b=String\.fromCharCode\(110\),c=a\.get\(b\)\)&&\(c=)
(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)''',
jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
if not idx:
return funcname
@@ -3170,7 +3171,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
def _extract_n_function_code(self, video_id, player_url):
player_id = self._extract_player_info(player_url)
func_code = self.cache.load('youtube-nsig', player_id, min_ver='2022.09.1')
func_code = self.cache.load('youtube-nsig', player_id, min_ver='2024.07.09')
jscode = func_code or self._load_player(video_id, player_url)
jsi = JSInterpreter(jscode)
@@ -3179,17 +3180,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
func_name = self._extract_n_function_name(jscode)
# For redundancy
func_code = self._search_regex(
rf'''(?xs){func_name}\s*=\s*function\s*\((?P<var>[\w$]+)\)\s*
# NB: The end of the regex is intentionally kept strict
{{(?P<code>.+?}}\s*return\ [\w$]+.join\(""\))}};''',
jscode, 'nsig function', group=('var', 'code'), default=None)
if func_code:
func_code = ([func_code[0]], func_code[1])
else:
self.write_debug('Extracting nsig function with jsinterp')
func_code = jsi.extract_function_code(func_name)
func_code = jsi.extract_function_code(func_name)
self.cache.store('youtube-nsig', player_id, func_code)
return jsi, player_id, func_code