[cleanup] Misc (#8968)

Authored by: pukkandan, bashonly, seproDev
This commit is contained in:
pukkandan 2024-03-10 20:48:44 +05:30
parent ed3bb2b0a1
commit 615a84447e
No known key found for this signature in database
GPG Key ID: 7EEE9E1E817D0A39
19 changed files with 80 additions and 94 deletions

3
.gitignore vendored
View File

@ -33,6 +33,7 @@ cookies
*.gif
*.jpeg
*.jpg
*.lrc
*.m4a
*.m4v
*.mhtml
@ -40,6 +41,7 @@ cookies
*.mov
*.mp3
*.mp4
*.mpg
*.mpga
*.oga
*.ogg
@ -47,6 +49,7 @@ cookies
*.png
*.sbv
*.srt
*.ssa
*.swf
*.swp
*.tt

View File

@ -17,8 +17,8 @@ pypi-files: AUTHORS Changelog.md LICENSE README.md README.txt supportedsites \
clean-test:
rm -rf test/testdata/sigs/player-*.js tmp/ *.annotations.xml *.aria2 *.description *.dump *.frag \
*.frag.aria2 *.frag.urls *.info.json *.live_chat.json *.meta *.part* *.tmp *.temp *.unknown_video *.ytdl \
*.3gp *.ape *.ass *.avi *.desktop *.f4v *.flac *.flv *.gif *.jpeg *.jpg *.m4a *.m4v *.mhtml *.mkv *.mov *.mp3 \
*.mp4 *.mpga *.oga *.ogg *.opus *.png *.sbv *.srt *.swf *.swp *.tt *.ttml *.url *.vtt *.wav *.webloc *.webm *.webp
*.3gp *.ape *.ass *.avi *.desktop *.f4v *.flac *.flv *.gif *.jpeg *.jpg *.lrc *.m4a *.m4v *.mhtml *.mkv *.mov *.mp3 *.mp4 \
*.mpg *.mpga *.oga *.ogg *.opus *.png *.sbv *.srt *.ssa *.swf *.swp *.tt *.ttml *.url *.vtt *.wav *.webloc *.webm *.webp
clean-dist:
rm -rf yt-dlp.1.temp.md yt-dlp.1 README.txt MANIFEST build/ dist/ .coverage cover/ yt-dlp.tar.gz completions/ \
yt_dlp/extractor/lazy_extractors.py *.spec CONTRIBUTING.md.tmp yt-dlp yt-dlp.exe yt_dlp.egg-info/ AUTHORS

View File

@ -1 +0,0 @@
# Empty file

View File

@ -20,7 +20,7 @@ def main():
'py2exe builds do not support pycryptodomex and needs VC++14 to run. '
'It is recommended to run "pyinst.py" to build using pyinstaller instead')
return freeze(
freeze(
console=[{
'script': './yt_dlp/__main__.py',
'dest_base': 'yt-dlp',

View File

@ -1 +0,0 @@
# Empty file needed to make devscripts.utils properly importable from outside

View File

@ -120,5 +120,11 @@
"when": "15f22b4880b6b3f71f350c64d70976ae65b9f1ca",
"short": "[webvtt] Allow spaces before newlines for CueBlock (#7681)",
"authors": ["TSRBerry"]
},
{
"action": "change",
"when": "4ce57d3b873c2887814cbec03d029533e82f7db5",
"short": "[ie] Support multi-period MPD streams (#6654)",
"authors": ["alard", "pukkandan"]
}
]

View File

@ -253,7 +253,7 @@ class CommitRange:
''', re.VERBOSE | re.DOTALL)
EXTRACTOR_INDICATOR_RE = re.compile(r'(?:Fix|Add)\s+Extractors?', re.IGNORECASE)
REVERT_RE = re.compile(r'(?:\[[^\]]+\]\s+)?(?i:Revert)\s+([\da-f]{40})')
FIXES_RE = re.compile(r'(?i:Fix(?:es)?(?:\s+bugs?)?(?:\s+in|\s+for)?|Revert)\s+([\da-f]{40})')
FIXES_RE = re.compile(r'(?i:Fix(?:es)?(?:\s+bugs?)?(?:\s+in|\s+for)?|Revert|Improve)\s+([\da-f]{40})')
UPSTREAM_MERGE_RE = re.compile(r'Update to ytdl-commit-([\da-f]+)')
def __init__(self, start, end, default_author=None):

View File

@ -69,7 +69,7 @@ def do_GET(self):
self.send_response(200)
self.send_header('Content-Type', 'text/plain; charset=utf-8')
self.end_headers()
self.wfile.write('{self.proxy_name}: {self.path}'.format(self=self).encode())
self.wfile.write(f'{self.proxy_name}: {self.path}'.encode())
return HTTPTestRequestHandler

View File

@ -575,7 +575,7 @@ class YoutubeDL:
'url', 'manifest_url', 'manifest_stream_number', 'ext', 'format', 'format_id', 'format_note',
'width', 'height', 'aspect_ratio', 'resolution', 'dynamic_range', 'tbr', 'abr', 'acodec', 'asr', 'audio_channels',
'vbr', 'fps', 'vcodec', 'container', 'filesize', 'filesize_approx', 'rows', 'columns',
'player_url', 'protocol', 'fragment_base_url', 'fragments', 'is_from_start',
'player_url', 'protocol', 'fragment_base_url', 'fragments', 'is_from_start', 'is_dash_periods', 'request_data',
'preference', 'language', 'language_preference', 'quality', 'source_preference', 'cookies',
'http_headers', 'stretched_ratio', 'no_resume', 'has_drm', 'extra_param_to_segment_url', 'hls_aes', 'downloader_options',
'page_url', 'app', 'play_path', 'tc_url', 'flash_version', 'rtmp_live', 'rtmp_conn', 'rtmp_protocol', 'rtmp_real_time'

View File

@ -4,6 +4,7 @@
from .common import InfoExtractor
from ..utils import (
InAdvancePagedList,
clean_html,
int_or_none,
orderedSet,
str_to_int,
@ -32,13 +33,15 @@ class AltCensoredIE(InfoExtractor):
'duration': 926.09,
'thumbnail': 'https://archive.org/download/youtube-k0srjLSkga8/youtube-k0srjLSkga8.thumbs/k0srjLSkga8_000925.jpg',
'view_count': int,
'categories': ['News & Politics'], # FIXME
'categories': ['News & Politics'],
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
category = clean_html(self._html_search_regex(
r'<a href="/category/\d+">([^<]+)</a>', webpage, 'category', default=None))
return {
'_type': 'url_transparent',
@ -46,9 +49,7 @@ def _real_extract(self, url):
'ie_key': ArchiveOrgIE.ie_key(),
'view_count': str_to_int(self._html_search_regex(
r'YouTube Views:(?:\s|&nbsp;)*([\d,]+)', webpage, 'view count', default=None)),
'categories': self._html_search_regex(
r'<a href="/category/\d+">\s*\n?\s*([^<]+)</a>',
webpage, 'category', default='').split() or None,
'categories': [category] if category else None,
}

View File

@ -142,10 +142,10 @@ class ArteTVIE(ArteTVBaseIE):
def _fix_accessible_subs_locale(subs):
updated_subs = {}
for lang, sub_formats in subs.items():
for format in sub_formats:
if format.get('url', '').endswith('-MAL.m3u8'):
for fmt in sub_formats:
if fmt.get('url', '').endswith('-MAL.m3u8'):
lang += '-acc'
updated_subs.setdefault(lang, []).append(format)
updated_subs.setdefault(lang, []).append(fmt)
return updated_subs
def _real_extract(self, url):

View File

@ -160,9 +160,8 @@ def _real_extract(self, url):
self._login(hostname, username, password)
display_id = self._match_id(url)
# NB: 404 is returned due to yt-dlp not properly following redirects #9020
webpage, urlh = self._download_webpage_handle(url, display_id, expected_status=404)
if self._LOGIN_URL_PATH in urlh.url or urlh.status == 404:
webpage, urlh = self._download_webpage_handle(url, display_id)
if self._LOGIN_URL_PATH in urlh.url:
raise ExtractorError(
f'This video is only available for registered users. {self._login_hint("any", netrc=hostname)}',
expected=True)

View File

@ -9,7 +9,6 @@
int_or_none,
str_or_none,
traverse_obj,
update_url_query,
)
@ -82,7 +81,7 @@ class MedalTVIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(update_url_query(url, {'mobilebypass': 'true'}), video_id)
webpage = self._download_webpage(url, video_id, query={'mobilebypass': 'true'})
hydration_data = self._search_json(
r'<script[^>]*>[^<]*\bhydrationData\s*=', webpage,

View File

@ -162,10 +162,8 @@ def _extract_formats(self, video_id, station, is_onair, ft, cursor, auth_token,
return formats
def _extract_performers(self, prog):
performers = traverse_obj(prog, (
'pfm/text()', ..., {lambda x: re.split(r'[//、 ,]', x)}, ..., {str.strip}))
# TODO: change 'artist' fields to 'artists' and return traversal list instead of str
return ', '.join(performers) or None
return traverse_obj(prog, (
'pfm/text()', ..., {lambda x: re.split(r'[//、 ,]', x)}, ..., {str.strip})) or None
class RadikoIE(RadikoBaseIE):
@ -194,7 +192,7 @@ def _real_extract(self, url):
return {
'id': video_id,
'title': try_call(lambda: prog.find('title').text),
'artist': self._extract_performers(prog),
'cast': self._extract_performers(prog),
'description': clean_html(try_call(lambda: prog.find('info').text)),
'uploader': try_call(lambda: station_program.find('.//name').text),
'uploader_id': station,
@ -253,7 +251,7 @@ def _real_extract(self, url):
return {
'id': station,
'title': title,
'artist': self._extract_performers(prog),
'cast': self._extract_performers(prog),
'description': description,
'uploader': station_name,
'uploader_id': station,

View File

@ -25,8 +25,8 @@ class SlidesLiveIE(InfoExtractor):
'id': '38902413',
'ext': 'mp4',
'title': 'GCC IA16 backend',
'timestamp': 1648189972,
'upload_date': '20220325',
'timestamp': 1697793372,
'upload_date': '20231020',
'thumbnail': r're:^https?://.*\.jpg',
'thumbnails': 'count:42',
'chapters': 'count:41',
@ -42,8 +42,8 @@ class SlidesLiveIE(InfoExtractor):
'id': '38935785',
'ext': 'mp4',
'title': 'Offline Reinforcement Learning: From Algorithms to Practical Challenges',
'upload_date': '20211115',
'timestamp': 1636996003,
'upload_date': '20231020',
'timestamp': 1697807002,
'thumbnail': r're:^https?://.*\.(?:jpg|png)',
'thumbnails': 'count:640',
'chapters': 'count:639',
@ -59,9 +59,9 @@ class SlidesLiveIE(InfoExtractor):
'id': '38973182',
'ext': 'mp4',
'title': 'How Should a Machine Learning Researcher Think About AI Ethics?',
'upload_date': '20220201',
'upload_date': '20231020',
'thumbnail': r're:^https?://.*\.jpg',
'timestamp': 1643728135,
'timestamp': 1697822521,
'thumbnails': 'count:3',
'chapters': 'count:2',
'duration': 5889,
@ -70,37 +70,22 @@ class SlidesLiveIE(InfoExtractor):
'skip_download': 'm3u8',
},
}, {
# service_name = youtube, only XML slides info
# formerly youtube, converted to native
'url': 'https://slideslive.com/38897546/special-metaprednaska-petra-ludwiga-hodnoty-pro-lepsi-spolecnost',
'md5': '8a79b5e3d700837f40bd2afca3c8fa01',
'info_dict': {
'id': 'jmg02wCJD5M',
'display_id': '38897546',
'id': '38897546',
'ext': 'mp4',
'title': 'SPECIÁL: Meta-přednáška Petra Ludwiga - Hodnoty pro lepší společnost',
'description': 'Watch full version of this video at https://slideslive.com/38897546.',
'channel_url': 'https://www.youtube.com/channel/UCZWdAkNYFncuX0khyvhqnxw',
'channel': 'SlidesLive Videos - G1',
'channel_id': 'UCZWdAkNYFncuX0khyvhqnxw',
'uploader_id': 'UCZWdAkNYFncuX0khyvhqnxw',
'uploader': 'SlidesLive Videos - G1',
'uploader_url': 'http://www.youtube.com/channel/UCZWdAkNYFncuX0khyvhqnxw',
'live_status': 'not_live',
'upload_date': '20160710',
'timestamp': 1618786715,
'duration': 6827,
'like_count': int,
'view_count': int,
'comment_count': int,
'channel_follower_count': int,
'age_limit': 0,
'thumbnail': r're:^https?://.*\.(?:jpg|webp)',
'thumbnail': r're:^https?://.*\.jpg',
'upload_date': '20231029',
'timestamp': 1698588144,
'thumbnails': 'count:169',
'playable_in_embed': True,
'availability': 'unlisted',
'tags': [],
'categories': ['People & Blogs'],
'chapters': 'count:168',
'duration': 6827,
},
'params': {
'skip_download': 'm3u8',
},
}, {
# embed-only presentation, only XML slides info
@ -111,8 +96,8 @@ class SlidesLiveIE(InfoExtractor):
'title': 'Towards a Deep Network Architecture for Structured Smoothness',
'thumbnail': r're:^https?://.*\.jpg',
'thumbnails': 'count:8',
'timestamp': 1629671508,
'upload_date': '20210822',
'timestamp': 1697803109,
'upload_date': '20231020',
'chapters': 'count:7',
'duration': 326,
},
@ -128,8 +113,8 @@ class SlidesLiveIE(InfoExtractor):
'title': 'MoReL: Multi-omics Relational Learning',
'thumbnail': r're:^https?://.*\.(?:jpg|png)',
'thumbnails': 'count:7',
'timestamp': 1654714970,
'upload_date': '20220608',
'timestamp': 1697824939,
'upload_date': '20231020',
'chapters': 'count:6',
'duration': 171,
},
@ -145,8 +130,8 @@ class SlidesLiveIE(InfoExtractor):
'title': 'Decentralized Attribution of Generative Models',
'thumbnail': r're:^https?://.*\.jpg',
'thumbnails': 'count:16',
'timestamp': 1622806321,
'upload_date': '20210604',
'timestamp': 1697814901,
'upload_date': '20231020',
'chapters': 'count:15',
'duration': 306,
},
@ -162,8 +147,8 @@ class SlidesLiveIE(InfoExtractor):
'title': 'Efficient Active Search for Combinatorial Optimization Problems',
'thumbnail': r're:^https?://.*\.(?:jpg|png)',
'thumbnails': 'count:9',
'timestamp': 1654714896,
'upload_date': '20220608',
'timestamp': 1697824757,
'upload_date': '20231020',
'chapters': 'count:8',
'duration': 295,
},
@ -177,10 +162,10 @@ class SlidesLiveIE(InfoExtractor):
'id': '38979880',
'ext': 'mp4',
'title': 'The Representation Power of Neural Networks',
'timestamp': 1654714962,
'timestamp': 1697824919,
'thumbnail': r're:^https?://.*\.(?:jpg|png)',
'thumbnails': 'count:22',
'upload_date': '20220608',
'upload_date': '20231020',
'chapters': 'count:21',
'duration': 294,
},
@ -200,10 +185,10 @@ class SlidesLiveIE(InfoExtractor):
'id': '38979682',
'ext': 'mp4',
'title': 'LoRA: Low-Rank Adaptation of Large Language Models',
'timestamp': 1654714920,
'timestamp': 1697824815,
'thumbnail': r're:^https?://.*\.(?:jpg|png)',
'thumbnails': 'count:30',
'upload_date': '20220608',
'upload_date': '20231020',
'chapters': 'count:31',
'duration': 272,
},
@ -213,8 +198,8 @@ class SlidesLiveIE(InfoExtractor):
'ext': 'mp4',
'title': 'LoRA: Low-Rank Adaptation of Large Language Models - Slide 021',
'duration': 3,
'timestamp': 1654714920,
'upload_date': '20220608',
'timestamp': 1697824815,
'upload_date': '20231020',
},
}, {
'info_dict': {
@ -222,8 +207,8 @@ class SlidesLiveIE(InfoExtractor):
'ext': 'mp4',
'title': 'LoRA: Low-Rank Adaptation of Large Language Models - Slide 024',
'duration': 4,
'timestamp': 1654714920,
'upload_date': '20220608',
'timestamp': 1697824815,
'upload_date': '20231020',
},
}],
'params': {
@ -242,10 +227,10 @@ class SlidesLiveIE(InfoExtractor):
'id': '38979481',
'ext': 'mp4',
'title': 'How to Train Your MAML to Excel in Few-Shot Classification',
'timestamp': 1654714877,
'timestamp': 1697824716,
'thumbnail': r're:^https?://.*\.(?:jpg|png)',
'thumbnails': 'count:43',
'upload_date': '20220608',
'upload_date': '20231020',
'chapters': 'count:43',
'duration': 315,
},
@ -255,8 +240,8 @@ class SlidesLiveIE(InfoExtractor):
'ext': 'mp4',
'title': 'How to Train Your MAML to Excel in Few-Shot Classification - Slide 013',
'duration': 3,
'timestamp': 1654714877,
'upload_date': '20220608',
'timestamp': 1697824716,
'upload_date': '20231020',
},
}],
'params': {
@ -275,10 +260,10 @@ class SlidesLiveIE(InfoExtractor):
'channel_id': 'UC62SdArr41t_-_fX40QCLRw',
'channel_url': 'https://www.youtube.com/channel/UC62SdArr41t_-_fX40QCLRw',
'uploader': 'SlidesLive Videos - A',
'uploader_id': 'UC62SdArr41t_-_fX40QCLRw',
'uploader_url': 'http://www.youtube.com/channel/UC62SdArr41t_-_fX40QCLRw',
'uploader_id': '@slideslivevideos-a6075',
'uploader_url': 'https://www.youtube.com/@slideslivevideos-a6075',
'upload_date': '20200903',
'timestamp': 1602599092,
'timestamp': 1697805922,
'duration': 942,
'age_limit': 0,
'live_status': 'not_live',
@ -303,8 +288,8 @@ class SlidesLiveIE(InfoExtractor):
'id': '38983994',
'ext': 'mp4',
'title': 'Zero-Shot AutoML with Pretrained Models',
'timestamp': 1662384834,
'upload_date': '20220905',
'timestamp': 1697826708,
'upload_date': '20231020',
'thumbnail': r're:^https?://.*\.(?:jpg|png)',
'thumbnails': 'count:23',
'chapters': 'count:22',
@ -336,8 +321,8 @@ class SlidesLiveIE(InfoExtractor):
'title': 'Towards a Deep Network Architecture for Structured Smoothness',
'thumbnail': r're:^https?://.*\.jpg',
'thumbnails': 'count:8',
'timestamp': 1629671508,
'upload_date': '20210822',
'timestamp': 1697803109,
'upload_date': '20231020',
'chapters': 'count:7',
'duration': 326,
},

View File

@ -190,10 +190,9 @@ def _get_thumbnails(self, thumbnail):
'url': thumbnail,
}] if thumbnail else None
def _extract_twitch_m3u8_formats(self, video_id, token, signature):
"""Subclasses must define _M3U8_PATH"""
def _extract_twitch_m3u8_formats(self, path, video_id, token, signature):
return self._extract_m3u8_formats(
f'{self._USHER_BASE}/{self._M3U8_PATH}/{video_id}.m3u8', video_id, 'mp4', query={
f'{self._USHER_BASE}/{path}/{video_id}.m3u8', video_id, 'mp4', query={
'allow_source': 'true',
'allow_audio_only': 'true',
'allow_spectre': 'true',
@ -216,7 +215,6 @@ class TwitchVodIE(TwitchBaseIE):
)
(?P<id>\d+)
'''
_M3U8_PATH = 'vod'
_TESTS = [{
'url': 'http://www.twitch.tv/riotgames/v/6528877?t=5m10s',
@ -547,7 +545,7 @@ def _real_extract(self, url):
access_token = self._download_access_token(vod_id, 'video', 'id')
formats = self._extract_twitch_m3u8_formats(
vod_id, access_token['value'], access_token['signature'])
'vod', vod_id, access_token['value'], access_token['signature'])
formats.extend(self._extract_storyboard(vod_id, video.get('storyboard'), info.get('duration')))
self._prefer_source(formats)
@ -926,7 +924,6 @@ class TwitchStreamIE(TwitchBaseIE):
)
(?P<id>[^/#?]+)
'''
_M3U8_PATH = 'api/channel/hls'
_TESTS = [{
'url': 'http://www.twitch.tv/shroomztv',
@ -1032,7 +1029,7 @@ def _real_extract(self, url):
stream_id = stream.get('id') or channel_name
formats = self._extract_twitch_m3u8_formats(
channel_name, access_token['value'], access_token['signature'])
'api/channel/hls', channel_name, access_token['value'], access_token['signature'])
self._prefer_source(formats)
view_count = stream.get('viewers')

View File

@ -43,7 +43,7 @@ class Vbox7IE(InfoExtractor):
'uploader': 'svideteliat_ot_varshava',
'view_count': int,
'timestamp': 1360215023,
'thumbnail': 'https://i49.vbox7.com/design/iconci/png/noimg6.png',
'thumbnail': 'https://i49.vbox7.com/o/249/249bb972c20.jpg',
'description': 'Смях! Чудо - чист за секунди - Скрита камера',
'upload_date': '20130207',
'duration': 83,

View File

@ -10,14 +10,14 @@
import zlib
from ._utils import Popen, decode_base_n, preferredencoding
from .networking import escape_rfc3986 # noqa: F401
from .networking import normalize_url as escape_url # noqa: F401
from .traversal import traverse_obj
from ..dependencies import certifi, websockets
from ..networking._helper import make_ssl_context
from ..networking._urllib import HTTPHandler
# isort: split
from .networking import escape_rfc3986 # noqa: F401
from .networking import normalize_url as escape_url # noqa: F401
from .networking import random_user_agent, std_headers # noqa: F401
from ..cookies import YoutubeDLCookieJar # noqa: F401
from ..networking._urllib import PUTRequest # noqa: F401

View File

@ -78,7 +78,7 @@ def commit(self):
class ParseError(Exception):
def __init__(self, parser):
super().__init__("Parse error at position %u (near %r)" % (
parser._pos, parser._data[parser._pos:parser._pos + 20]
parser._pos, parser._data[parser._pos:parser._pos + 100]
))