1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-06-26 05:39:34 +00:00

Compare commits

...

12 commits

Author SHA1 Message Date
Deleted user c66983b489
Merge 9824085514 into 0153b387e5 2024-06-14 12:00:22 +00:00
Paper 0153b387e5
[VidLii] Add 720p support (#30924)
* [VidLii] Add HD support  (yt-dlp backport-ish)

* Also fix a bug with the view count

---------

Co-authored-by: dirkf <fieldhouse@gmx.net>
2024-06-11 13:21:39 +01:00
dirkf a48fe7491d [ORF] Skip tests with limited availability 2024-06-11 12:52:13 +01:00
dirkf e20ca543f0 [ORF] Re-factor and updateORFFM4StoryIE
* fix getting media via DASH instead of inaccessible mp4
* also get in-page YT media
2024-06-11 12:52:13 +01:00
dirkf e39466051f [ORF] Support sound.orf.at, updating ORFRadioIE
* maintain support for xx.orf.at/player/... URLs
* add `ORFRadioCollectionIE` to support playlists in ORF Sound
* back-port and re-work `ORFPodcastIE` from https://github.com/yt-dlp/yt-dlp/pull/8486, thx Esokrates
2024-06-11 12:52:13 +01:00
dirkf d95c0d203f [ORF] Support on.orf.at, replacing ORFTVthekIE
* add `ORFONIE`, back-porting yt-dlp PR https://github.com/yt-dlp/yt-dlp/pull/9113 and friends: thx HobbyistDev, TuxCoder, seproDev
* re-factor to support livestreams via new `ORFONliveIE`
2024-06-11 12:52:13 +01:00
dirkf 3bde6a5752 [test] Improve download test
* skip reason can't be unicode in Py2
* remove duplicate assert...Equal functions
2024-06-11 12:52:13 +01:00
dirkf 50f6c5668a [core] Re-factor with _fill_common_fields() as used in yt-dlp 2024-06-11 12:52:13 +01:00
dirkf b4ff08bd2d [core] Safer handling of nested playlist data 2024-06-11 12:52:13 +01:00
kmnx 88bd8b9f87
[mixcloud] updated mixcloud API server address (#32557)
* updated mixcloud API server address
* fix tests
* etc

---------

Co-authored-by: dirkf <fieldhouse@gmx.net>
2024-06-11 12:38:24 +01:00
kikuyan 9824085514
Merge branch 'ytdl-org:master' into macos-spotlight 2021-07-04 11:46:18 +09:00
kikuyan 6879cf950d Write --xattrs metadata as macOS Spotlight metadata 2021-06-25 13:51:14 +09:00
10 changed files with 928 additions and 584 deletions

View file

@ -5,9 +5,9 @@ import hashlib
import json
import os.path
import re
import types
import ssl
import sys
import types
import unittest
import youtube_dl.extractor
@ -181,18 +181,18 @@ def expect_value(self, got, expected, field):
op, _, expected_num = expected.partition(':')
expected_num = int(expected_num)
if op == 'mincount':
assert_func = assertGreaterEqual
assert_func = self.assertGreaterEqual
msg_tmpl = 'Expected %d items in field %s, but only got %d'
elif op == 'maxcount':
assert_func = assertLessEqual
assert_func = self.assertLessEqual
msg_tmpl = 'Expected maximum %d items in field %s, but got %d'
elif op == 'count':
assert_func = assertEqual
assert_func = self.assertEqual
msg_tmpl = 'Expected exactly %d items in field %s, but got %d'
else:
assert False
assert_func(
self, len(got), expected_num,
len(got), expected_num,
msg_tmpl % (expected_num, field, len(got)))
return
self.assertEqual(
@ -262,27 +262,6 @@ def assertRegexpMatches(self, text, regexp, msg=None):
self.assertTrue(m, msg)
def assertGreaterEqual(self, got, expected, msg=None):
if not (got >= expected):
if msg is None:
msg = '%r not greater than or equal to %r' % (got, expected)
self.assertTrue(got >= expected, msg)
def assertLessEqual(self, got, expected, msg=None):
if not (got <= expected):
if msg is None:
msg = '%r not less than or equal to %r' % (got, expected)
self.assertTrue(got <= expected, msg)
def assertEqual(self, got, expected, msg=None):
if not (got == expected):
if msg is None:
msg = '%r not equal to %r' % (got, expected)
self.assertTrue(got == expected, msg)
def expect_warnings(ydl, warnings_re):
real_warning = ydl.report_warning

View file

@ -9,8 +9,6 @@ import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import (
assertGreaterEqual,
assertLessEqual,
expect_warnings,
get_params,
gettestcases,
@ -36,12 +34,20 @@ from youtube_dl.utils import (
ExtractorError,
error_to_compat_str,
format_bytes,
IDENTITY,
preferredencoding,
UnavailableVideoError,
)
from youtube_dl.extractor import get_info_extractor
RETRIES = 3
# Some unittest APIs require actual str
if not isinstance('TEST', str):
_encode_str = lambda s: s.encode(preferredencoding())
else:
_encode_str = IDENTITY
class YoutubeDL(youtube_dl.YoutubeDL):
def __init__(self, *args, **kwargs):
@ -102,7 +108,7 @@ def generator(test_case, tname):
def print_skipping(reason):
print('Skipping %s: %s' % (test_case['name'], reason))
self.skipTest(reason)
self.skipTest(_encode_str(reason))
if not ie.working():
print_skipping('IE marked as not _WORKING')
@ -187,16 +193,14 @@ def generator(test_case, tname):
expect_info_dict(self, res_dict, test_case.get('info_dict', {}))
if 'playlist_mincount' in test_case:
assertGreaterEqual(
self,
self.assertGreaterEqual(
len(res_dict['entries']),
test_case['playlist_mincount'],
'Expected at least %d in playlist %s, but got only %d' % (
test_case['playlist_mincount'], test_case['url'],
len(res_dict['entries'])))
if 'playlist_maxcount' in test_case:
assertLessEqual(
self,
self.assertLessEqual(
len(res_dict['entries']),
test_case['playlist_maxcount'],
'Expected at most %d in playlist %s, but got %d' % (
@ -243,8 +247,8 @@ def generator(test_case, tname):
if params.get('test'):
expected_minsize = max(expected_minsize, 10000)
got_fsize = os.path.getsize(tc_filename)
assertGreaterEqual(
self, got_fsize, expected_minsize,
self.assertGreaterEqual(
got_fsize, expected_minsize,
'Expected %s to be at least %s, but it\'s only %s ' %
(tc_filename, format_bytes(expected_minsize),
format_bytes(got_fsize)))

View file

@ -1039,8 +1039,8 @@ class YoutubeDL(object):
elif result_type in ('playlist', 'multi_video'):
# Protect from infinite recursion due to recursively nested playlists
# (see https://github.com/ytdl-org/youtube-dl/issues/27833)
webpage_url = ie_result['webpage_url']
if webpage_url in self._playlist_urls:
webpage_url = ie_result.get('webpage_url') # not all pl/mv have this
if webpage_url and webpage_url in self._playlist_urls:
self.to_screen(
'[download] Skipping already downloaded playlist: %s'
% ie_result.get('title') or ie_result.get('id'))
@ -1048,6 +1048,10 @@ class YoutubeDL(object):
self._playlist_level += 1
self._playlist_urls.add(webpage_url)
new_result = dict((k, v) for k, v in extra_info.items() if k not in ie_result)
if new_result:
new_result.update(ie_result)
ie_result = new_result
try:
return self.__process_playlist(ie_result, download)
finally:
@ -1593,6 +1597,28 @@ class YoutubeDL(object):
self.cookiejar.add_cookie_header(pr)
return pr.get_header('Cookie')
def _fill_common_fields(self, info_dict, final=True):
for ts_key, date_key in (
('timestamp', 'upload_date'),
('release_timestamp', 'release_date'),
):
if info_dict.get(date_key) is None and info_dict.get(ts_key) is not None:
# Working around out-of-range timestamp values (e.g. negative ones on Windows,
# see http://bugs.python.org/issue1646728)
try:
upload_date = datetime.datetime.utcfromtimestamp(info_dict[ts_key])
info_dict[date_key] = compat_str(upload_date.strftime('%Y%m%d'))
except (ValueError, OverflowError, OSError):
pass
# Auto generate title fields corresponding to the *_number fields when missing
# in order to always have clean titles. This is very common for TV series.
if final:
for field in ('chapter', 'season', 'episode'):
if info_dict.get('%s_number' % field) is not None and not info_dict.get(field):
info_dict[field] = '%s %d' % (field.capitalize(), info_dict['%s_number' % field])
def process_video_result(self, info_dict, download=True):
assert info_dict.get('_type', 'video') == 'video'
@ -1660,24 +1686,7 @@ class YoutubeDL(object):
if 'display_id' not in info_dict and 'id' in info_dict:
info_dict['display_id'] = info_dict['id']
for ts_key, date_key in (
('timestamp', 'upload_date'),
('release_timestamp', 'release_date'),
):
if info_dict.get(date_key) is None and info_dict.get(ts_key) is not None:
# Working around out-of-range timestamp values (e.g. negative ones on Windows,
# see http://bugs.python.org/issue1646728)
try:
upload_date = datetime.datetime.utcfromtimestamp(info_dict[ts_key])
info_dict[date_key] = compat_str(upload_date.strftime('%Y%m%d'))
except (ValueError, OverflowError, OSError):
pass
# Auto generate title fields corresponding to the *_number fields when missing
# in order to always have clean titles. This is very common for TV series.
for field in ('chapter', 'season', 'episode'):
if info_dict.get('%s_number' % field) is not None and not info_dict.get(field):
info_dict[field] = '%s %d' % (field.capitalize(), info_dict['%s_number' % field])
self._fill_common_fields(info_dict)
for cc_kind in ('subtitles', 'automatic_captions'):
cc = info_dict.get(cc_kind)

View file

@ -898,21 +898,13 @@ from .ooyala import (
)
from .ora import OraTVIE
from .orf import (
ORFTVthekIE,
ORFFM4IE,
ORFONIE,
ORFONLiveIE,
ORFFM4StoryIE,
ORFOE1IE,
ORFOE3IE,
ORFNOEIE,
ORFWIEIE,
ORFBGLIE,
ORFOOEIE,
ORFSTMIE,
ORFKTNIE,
ORFSBGIE,
ORFTIRIE,
ORFVBGIE,
ORFIPTVIE,
ORFPodcastIE,
ORFRadioIE,
ORFRadioCollectionIE,
)
from .outsidetv import OutsideTVIE
from .packtpub import (

View file

@ -1,3 +1,4 @@
# coding: utf-8
from __future__ import unicode_literals
import itertools
@ -10,7 +11,7 @@ from ..compat import (
compat_ord,
compat_str,
compat_urllib_parse_unquote,
compat_zip
compat_zip as zip,
)
from ..utils import (
int_or_none,
@ -24,7 +25,7 @@ class MixcloudBaseIE(InfoExtractor):
def _call_api(self, object_type, object_fields, display_id, username, slug=None):
lookup_key = object_type + 'Lookup'
return self._download_json(
'https://www.mixcloud.com/graphql', display_id, query={
'https://app.mixcloud.com/graphql', display_id, query={
'query': '''{
%s(lookup: {username: "%s"%s}) {
%s
@ -44,7 +45,7 @@ class MixcloudIE(MixcloudBaseIE):
'ext': 'm4a',
'title': 'Cryptkeeper',
'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
'uploader': 'Daniel Holbach',
'uploader': 'dholbach', # was: 'Daniel Holbach',
'uploader_id': 'dholbach',
'thumbnail': r're:https?://.*\.jpg',
'view_count': int,
@ -57,7 +58,7 @@ class MixcloudIE(MixcloudBaseIE):
'id': 'gillespeterson_caribou-7-inch-vinyl-mix-chat',
'ext': 'mp3',
'title': 'Caribou 7 inch Vinyl Mix & Chat',
'description': 'md5:2b8aec6adce69f9d41724647c65875e8',
'description': r're:Last week Dan Snaith aka Caribou swung by the Brownswood.{136}',
'uploader': 'Gilles Peterson Worldwide',
'uploader_id': 'gillespeterson',
'thumbnail': 're:https?://.*',
@ -65,6 +66,23 @@ class MixcloudIE(MixcloudBaseIE):
'timestamp': 1422987057,
'upload_date': '20150203',
},
'params': {
'skip_download': '404 not found',
},
}, {
'url': 'https://www.mixcloud.com/gillespeterson/carnival-m%C3%BAsica-popular-brasileira-mix/',
'info_dict': {
'id': 'gillespeterson_carnival-música-popular-brasileira-mix',
'ext': 'm4a',
'title': 'Carnival Música Popular Brasileira Mix',
'description': r're:Gilles was recently in Brazil to play at Boiler Room.{208}',
'timestamp': 1454347174,
'upload_date': '20160201',
'uploader': 'Gilles Peterson Worldwide',
'uploader_id': 'gillespeterson',
'thumbnail': 're:https?://.*',
'view_count': int,
},
}, {
'url': 'https://beta.mixcloud.com/RedLightRadio/nosedrip-15-red-light-radio-01-18-2016/',
'only_matching': True,
@ -76,10 +94,10 @@ class MixcloudIE(MixcloudBaseIE):
"""Encrypt/Decrypt XOR cipher. Both ways are possible because it's XOR."""
return ''.join([
compat_chr(compat_ord(ch) ^ compat_ord(k))
for ch, k in compat_zip(ciphertext, itertools.cycle(key))])
for ch, k in zip(ciphertext, itertools.cycle(key))])
def _real_extract(self, url):
username, slug = re.match(self._VALID_URL, url).groups()
username, slug = self._match_valid_url(url).groups()
username, slug = compat_urllib_parse_unquote(username), compat_urllib_parse_unquote(slug)
track_id = '%s_%s' % (username, slug)

File diff suppressed because it is too large Load diff

View file

@ -4,6 +4,7 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
float_or_none,
get_element_by_id,
@ -11,6 +12,7 @@ from ..utils import (
strip_or_none,
unified_strdate,
urljoin,
str_to_int,
)
@ -35,6 +37,26 @@ class VidLiiIE(InfoExtractor):
'categories': ['News & Politics'],
'tags': ['Vidlii', 'Jan', 'Videogames'],
}
}, {
# HD
'url': 'https://www.vidlii.com/watch?v=2Ng8Abj2Fkl',
'md5': '450e7da379c884788c3a4fa02a3ce1a4',
'info_dict': {
'id': '2Ng8Abj2Fkl',
'ext': 'mp4',
'title': 'test',
'description': 'md5:cc55a86032a7b6b3cbfd0f6b155b52e9',
'thumbnail': 'https://www.vidlii.com/usfi/thmp/2Ng8Abj2Fkl.jpg',
'uploader': 'VidLii',
'uploader_url': 'https://www.vidlii.com/user/VidLii',
'upload_date': '20200927',
'duration': 5,
'view_count': int,
'comment_count': int,
'average_rating': float,
'categories': ['Film & Animation'],
'tags': list,
},
}, {
'url': 'https://www.vidlii.com/embed?v=tJluaH4BJ3v&a=0',
'only_matching': True,
@ -46,11 +68,32 @@ class VidLiiIE(InfoExtractor):
webpage = self._download_webpage(
'https://www.vidlii.com/watch?v=%s' % video_id, video_id)
video_url = self._search_regex(
r'src\s*:\s*(["\'])(?P<url>(?:https?://)?(?:(?!\1).)+)\1', webpage,
'video url', group='url')
formats = []
title = self._search_regex(
def add_format(format_url, height=None):
height = int(self._search_regex(r'(\d+)\.mp4',
format_url, 'height', default=360))
formats.append({
'url': format_url,
'format_id': '%dp' % height if height else None,
'height': height,
})
sources = re.findall(
r'src\s*:\s*(["\'])(?P<url>(?:https?://)?(?:(?!\1).)+)\1',
webpage)
formats = []
if len(sources) > 1:
add_format(sources[1][1])
self._check_formats(formats, video_id)
if len(sources) > 0:
add_format(sources[0][1])
self._sort_formats(formats)
title = self._html_search_regex(
(r'<h1>([^<]+)</h1>', r'<title>([^<]+) - VidLii<'), webpage,
'title')
@ -82,9 +125,9 @@ class VidLiiIE(InfoExtractor):
default=None) or self._search_regex(
r'duration\s*:\s*(\d+)', webpage, 'duration', fatal=False))
view_count = int_or_none(self._search_regex(
(r'<strong>(\d+)</strong> views',
r'Views\s*:\s*<strong>(\d+)</strong>'),
view_count = str_to_int(self._html_search_regex(
(r'<strong>([\d,.]+)</strong> views',
r'Views\s*:\s*<strong>([\d,.]+)</strong>'),
webpage, 'view count', fatal=False))
comment_count = int_or_none(self._search_regex(
@ -109,7 +152,7 @@ class VidLiiIE(InfoExtractor):
return {
'id': video_id,
'url': video_url,
'formats': formats,
'title': title,
'description': description,
'thumbnail': thumbnail,

View file

@ -839,7 +839,7 @@ def parseOpts(overrideArguments=None):
postproc.add_option(
'--xattrs',
action='store_true', dest='xattrs', default=False,
help='Write metadata to the video file\'s xattrs (using dublin core and xdg standards)')
help='Write metadata to the video file\'s xattrs (using dublin core and xdg standards, or macOS Spotlight)')
postproc.add_option(
'--fixup',
metavar='POLICY', dest='fixup', default='detect_or_warn',

View file

@ -1,8 +1,17 @@
from __future__ import unicode_literals
import plistlib
import subprocess
import sys
from xml.sax.saxutils import escape
from .common import PostProcessor
from ..compat import compat_os_name
from ..utils import (
check_executable,
encodeArgument,
encodeFilename,
hyphenate_date,
write_xattr,
XAttrMetadataError,
@ -32,15 +41,26 @@ class XAttrMetadataPP(PostProcessor):
filename = info['filepath']
try:
xattr_mapping = {
'user.xdg.referrer.url': 'webpage_url',
# 'user.xdg.comment': 'description',
'user.dublincore.title': 'title',
'user.dublincore.date': 'upload_date',
'user.dublincore.description': 'description',
'user.dublincore.contributor': 'uploader',
'user.dublincore.format': 'format',
}
if sys.platform != 'darwin': # other than macOS
xattr_mapping = {
'user.xdg.referrer.url': 'webpage_url',
# 'user.xdg.comment': 'description',
'user.dublincore.title': 'title',
'user.dublincore.date': 'upload_date',
'user.dublincore.description': 'description',
'user.dublincore.contributor': 'uploader',
'user.dublincore.format': 'format',
}
else: # macOS
xattr_mapping = {
'com.apple.metadata:kMDItemWhereFroms': 'webpage_url',
# 'user.xdg.comment': 'description',
'com.apple.metadata:kMDItemTitle': 'title',
'user.dublincore.date': 'upload_date', # no corresponding attr
'com.apple.metadata:kMDItemDescription': 'description',
'com.apple.metadata:kMDItemContributors': 'uploader',
'user.dublincore.format': 'format', # no corresponding attr
}
num_written = 0
for xattrname, infoname in xattr_mapping.items():
@ -48,10 +68,15 @@ class XAttrMetadataPP(PostProcessor):
value = info.get(infoname)
if value:
if infoname == 'upload_date':
value = hyphenate_date(value)
if not xattrname.startswith('com.apple.metadata:'):
if infoname == 'upload_date':
value = hyphenate_date(value)
byte_value = value.encode('utf-8')
else: # macOS Spotlight metadata
byte_value = self.make_mditem(xattrname, value)
byte_value = value.encode('utf-8')
write_xattr(filename, xattrname, byte_value)
num_written += 1
@ -77,3 +102,59 @@ class XAttrMetadataPP(PostProcessor):
msg += '(You may have to enable them in your /etc/fstab)'
self._downloader.report_error(msg)
return [], info
def make_mditem(self, attrname, value):
# Info about macOS Spotlight metadata:
# https://developer.apple.com/library/archive/documentation/CoreServices/Reference/MetadataAttributesRef/Reference/CommonAttrs.html
attr_is_cfarray = attrname in (
'com.apple.metadata:kMDItemContributors',
'com.apple.metadata:kMDItemWhereFroms')
if hasattr(plistlib, 'dumps'): # Python >= 3.4, need new api to make binary plist
if attr_is_cfarray:
value = [value]
return plistlib.dumps(value, fmt=plistlib.FMT_BINARY)
else:
# try PyObjC (or pyobjc-framework-Cocoa)
try:
from Foundation import NSPropertyListSerialization, NSPropertyListBinaryFormat_v1_0
if attr_is_cfarray:
data = [value]
else:
data = value
plist, err = NSPropertyListSerialization.dataWithPropertyList_format_options_error_(
data, NSPropertyListBinaryFormat_v1_0, 0, None)
if not err and plist:
return bytes(plist)
except (ImportError, ValueError):
pass # go on to try plutil command
# make xml plist first to convert to binary plist with plutil command,
# or to use as a fallback if conversion failed
plist = '<string>' + escape(value) + '</string>\n'
if attr_is_cfarray:
plist = '<array>\n\t' + plist + '</array>\n'
plist = (
'<?xml version="1.0" encoding="UTF-8"?>\n'
'<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">\n'
'<plist version="1.0">\n') + plist + '</plist>'
xmlplist = plist.encode('utf-8')
# try plutil command (like `cat xmlplist | plutil -convert binary1 -o - -`)
plutil = check_executable('plutil', ['-help'])
if plutil:
cmd = ([encodeFilename(plutil, True)]
+ [encodeArgument(o) for o in ['-convert', 'binary1', '-o', '-', '-']])
try:
p = subprocess.Popen(
cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdin=subprocess.PIPE)
stdout, stderr = p.communicate(input=xmlplist)
if p.returncode == 0:
return bytes(stdout)
except EnvironmentError:
pass # fallback to xml plist
return xmlplist

View file

@ -6151,7 +6151,9 @@ def write_xattr(path, key, value):
f.write(value)
except EnvironmentError as e:
raise XAttrMetadataError(e.errno, e.strerror)
else:
elif not (key.startswith('com.apple.metadata:') and value[:8] == b'bplist00'):
# other than macOS binary plist
user_has_setfattr = check_executable('setfattr', ['--version'])
user_has_xattr = check_executable('xattr', ['-h'])
@ -6192,6 +6194,49 @@ def write_xattr(path, key, value):
"Couldn't find a tool to set the xattrs. "
"Install either the python 'xattr' module, "
"or the 'xattr' binary.")
else:
# macOS binary plist
# find Apple version xattr command to set binary data in hex string
# original xattr project's xattr command doesn't have this feature
xattr_bin = None
for _bin in ('xattr', '/usr/bin/xattr'):
cmd = [encodeFilename(_bin, True), encodeArgument('-h')]
try:
p = subprocess.Popen(
cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
except EnvironmentError:
continue
stdout, stderr = p.communicate()
if p.returncode != 0:
continue
stdout = stdout.decode('utf-8', 'replace')
# help text must contain '-x: ... hex string for input' line
if re.search('-x: .*? hex string for input', stdout):
xattr_bin = _bin
break
if xattr_bin:
hexvalue = binascii.hexlify(value)
opts = ['-w', '-x', key, hexvalue]
cmd = ([encodeFilename(xattr_bin, True)]
+ [encodeArgument(o) for o in opts]
+ [encodeFilename(path, True)])
try:
p = subprocess.Popen(
cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
except EnvironmentError as e:
raise XAttrMetadataError(e.errno, e.strerror)
stdout, stderr = p.communicate()
if p.returncode != 0:
stderr = stderr.decode('utf-8', 'replace')
raise XAttrMetadataError(p.returncode, stderr)
else:
raise XAttrUnavailableError(
"Couldn't find a tool to set the xattrs. "
"Install either the python 'xattr' module, "
"or the Apple version 'xattr' command.")
def random_birthday(year_field, month_field, day_field):