mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-12-31 20:11:26 +00:00
Code Issues Projects Releases Wiki Activity

Merge branch 'master' of https://github.com/yt-dlp/yt-dlp into ie/npo

Browse Source
This commit is contained in:
DTrombett
2025-03-20 14:35:48 +01:00
parent b4b09c8d68 2ee3a0aff9
commit 8623235006
296 changed files with 19642 additions and 14146 deletions
Download Patch File Download Diff File Expand all files Collapse all files

197
test/helper.py
View File

@@ -9,7 +9,6 @@ import types
import yt_dlp.extractor
from yt_dlp import YoutubeDL
from yt_dlp.compat import compat_os_name
from yt_dlp.utils import preferredencoding, try_call, write_string, find_available_port
if 'pytest' in sys.modules:
@@ -49,7 +48,7 @@ def report_warning(message, *args, **kwargs):
Print the message to stderr, it will be prefixed with 'WARNING:'
If stderr is a tty file the 'WARNING:' will be colored
"""
if sys.stderr.isatty() and compat_os_name != 'nt':
if sys.stderr.isatty() and os.name != 'nt':
_msg_header = '\033[0;33mWARNING:\033[0m'
else:
_msg_header = 'WARNING:'
@@ -102,87 +101,109 @@ def getwebpagetestcases():
md5 = lambda s: hashlib.md5(s.encode()).hexdigest()
def expect_value(self, got, expected, field):
if isinstance(expected, str) and expected.startswith('re:'):
match_str = expected[len('re:'):]
match_rex = re.compile(match_str)
def _iter_differences(got, expected, field):
if isinstance(expected, str):
op, _, val = expected.partition(':')
if op in ('mincount', 'maxcount', 'count'):
if not isinstance(got, (list, dict)):
yield field, f'expected either {list.__name__} or {dict.__name__}, got {type(got).__name__}'
return
self.assertTrue(
isinstance(got, str),
f'Expected a {str.__name__} object, but got {type(got).__name__} for field {field}')
self.assertTrue(
match_rex.match(got),
f'field {field} (value: {got!r}) should match {match_str!r}')
elif isinstance(expected, str) and expected.startswith('startswith:'):
start_str = expected[len('startswith:'):]
self.assertTrue(
isinstance(got, str),
f'Expected a {str.__name__} object, but got {type(got).__name__} for field {field}')
self.assertTrue(
got.startswith(start_str),
f'field {field} (value: {got!r}) should start with {start_str!r}')
elif isinstance(expected, str) and expected.startswith('contains:'):
contains_str = expected[len('contains:'):]
self.assertTrue(
isinstance(got, str),
f'Expected a {str.__name__} object, but got {type(got).__name__} for field {field}')
self.assertTrue(
contains_str in got,
f'field {field} (value: {got!r}) should contain {contains_str!r}')
elif isinstance(expected, type):
self.assertTrue(
isinstance(got, expected),
f'Expected type {expected!r} for field {field}, but got value {got!r} of type {type(got)!r}')
elif isinstance(expected, dict) and isinstance(got, dict):
expect_dict(self, got, expected)
elif isinstance(expected, list) and isinstance(got, list):
self.assertEqual(
len(expected), len(got),
f'Expect a list of length {len(expected)}, but got a list of length {len(got)} for field {field}')
for index, (item_got, item_expected) in enumerate(zip(got, expected)):
type_got = type(item_got)
type_expected = type(item_expected)
self.assertEqual(
type_expected, type_got,
f'Type mismatch for list item at index {index} for field {field}, '
f'expected {type_expected!r}, got {type_got!r}')
expect_value(self, item_got, item_expected, field)
else:
if isinstance(expected, str) and expected.startswith('md5:'):
self.assertTrue(
isinstance(got, str),
f'Expected field {field} to be a unicode object, but got value {got!r} of type {type(got)!r}')
got = 'md5:' + md5(got)
elif isinstance(expected, str) and re.match(r'^(?:min|max)?count:\d+', expected):
self.assertTrue(
isinstance(got, (list, dict)),
f'Expected field {field} to be a list or a dict, but it is of type {type(got).__name__}')
op, _, expected_num = expected.partition(':')
expected_num = int(expected_num)
expected_num = int(val)
got_num = len(got)
if op == 'mincount':
assert_func = assertGreaterEqual
msg_tmpl = 'Expected %d items in field %s, but only got %d'
elif op == 'maxcount':
assert_func = assertLessEqual
msg_tmpl = 'Expected maximum %d items in field %s, but got %d'
elif op == 'count':
assert_func = assertEqual
msg_tmpl = 'Expected exactly %d items in field %s, but got %d'
else:
assert False
assert_func(
self, len(got), expected_num,
msg_tmpl % (expected_num, field, len(got)))
if got_num < expected_num:
yield field, f'expected at least {val} items, got {got_num}'
return
if op == 'maxcount':
if got_num > expected_num:
yield field, f'expected at most {val} items, got {got_num}'
return
assert op == 'count'
if got_num != expected_num:
yield field, f'expected exactly {val} items, got {got_num}'
return
self.assertEqual(
expected, got,
f'Invalid value for field {field}, expected {expected!r}, got {got!r}')
if not isinstance(got, str):
yield field, f'expected {str.__name__}, got {type(got).__name__}'
return
if op == 're':
if not re.match(val, got):
yield field, f'should match {val!r}, got {got!r}'
return
if op == 'startswith':
if not val.startswith(got):
yield field, f'should start with {val!r}, got {got!r}'
return
if op == 'contains':
if not val.startswith(got):
yield field, f'should contain {val!r}, got {got!r}'
return
if op == 'md5':
hash_val = md5(got)
if hash_val != val:
yield field, f'expected hash {val}, got {hash_val}'
return
if got != expected:
yield field, f'expected {expected!r}, got {got!r}'
return
if isinstance(expected, dict) and isinstance(got, dict):
for key, expected_val in expected.items():
if key not in got:
yield field, f'missing key: {key!r}'
continue
field_name = key if field is None else f'{field}.{key}'
yield from _iter_differences(got[key], expected_val, field_name)
return
if isinstance(expected, type):
if not isinstance(got, expected):
yield field, f'expected {expected.__name__}, got {type(got).__name__}'
return
if isinstance(expected, list) and isinstance(got, list):
# TODO: clever diffing algorithm lmao
if len(expected) != len(got):
yield field, f'expected length of {len(expected)}, got {len(got)}'
return
for index, (got_val, expected_val) in enumerate(zip(got, expected)):
field_name = str(index) if field is None else f'{field}.{index}'
yield from _iter_differences(got_val, expected_val, field_name)
return
if got != expected:
yield field, f'expected {expected!r}, got {got!r}'
def _expect_value(message, got, expected, field):
mismatches = list(_iter_differences(got, expected, field))
if not mismatches:
return
fields = [field for field, _ in mismatches if field is not None]
return ''.join((
message, f' ({", ".join(fields)})' if fields else '',
*(f'\n\t{field}: {message}' for field, message in mismatches)))
def expect_value(self, got, expected, field):
if message := _expect_value('values differ', got, expected, field):
self.fail(message)
def expect_dict(self, got_dict, expected_dict):
for info_field, expected in expected_dict.items():
got = got_dict.get(info_field)
expect_value(self, got, expected, info_field)
if message := _expect_value('dictionaries differ', got_dict, expected_dict, None):
self.fail(message)
def sanitize_got_info_dict(got_dict):
@@ -238,6 +259,20 @@ def sanitize_got_info_dict(got_dict):
def expect_info_dict(self, got_dict, expected_dict):
ALLOWED_KEYS_SORT_ORDER = (
# NB: Keep in sync with the docstring of extractor/common.py
'id', 'ext', 'direct', 'display_id', 'title', 'alt_title', 'description', 'media_type',
'uploader', 'uploader_id', 'uploader_url', 'channel', 'channel_id', 'channel_url', 'channel_is_verified',
'channel_follower_count', 'comment_count', 'view_count', 'concurrent_view_count',
'like_count', 'dislike_count', 'repost_count', 'average_rating', 'age_limit', 'duration', 'thumbnail', 'heatmap',
'chapters', 'chapter', 'chapter_number', 'chapter_id', 'start_time', 'end_time', 'section_start', 'section_end',
'categories', 'tags', 'cast', 'composers', 'artists', 'album_artists', 'creators', 'genres',
'track', 'track_number', 'track_id', 'album', 'album_type', 'disc_number',
'series', 'series_id', 'season', 'season_number', 'season_id', 'episode', 'episode_number', 'episode_id',
'timestamp', 'upload_date', 'release_timestamp', 'release_date', 'release_year', 'modified_timestamp', 'modified_date',
'playable_in_embed', 'availability', 'live_status', 'location', 'license', '_old_archive_ids',
)
expect_dict(self, got_dict, expected_dict)
# Check for the presence of mandatory fields
if got_dict.get('_type') not in ('playlist', 'multi_video'):
@@ -253,7 +288,13 @@ def expect_info_dict(self, got_dict, expected_dict):
test_info_dict = sanitize_got_info_dict(got_dict)
missing_keys = set(test_info_dict.keys()) - set(expected_dict.keys())
# Check for invalid/misspelled field names being returned by the extractor
invalid_keys = sorted(test_info_dict.keys() - ALLOWED_KEYS_SORT_ORDER)
self.assertFalse(invalid_keys, f'Invalid fields returned by the extractor: {", ".join(invalid_keys)}')
missing_keys = sorted(
test_info_dict.keys() - expected_dict.keys(),
key=lambda x: ALLOWED_KEYS_SORT_ORDER.index(x))
if missing_keys:
def _repr(v):
if isinstance(v, str):

12
test/test_InfoExtractor.py
View File

@@ -53,6 +53,18 @@ class TestInfoExtractor(unittest.TestCase):
def test_ie_key(self):
self.assertEqual(get_info_extractor(YoutubeIE.ie_key()), YoutubeIE)
def test_get_netrc_login_info(self):
for params in [
{'usenetrc': True, 'netrc_location': './test/testdata/netrc/netrc'},
{'netrc_cmd': f'{sys.executable} ./test/testdata/netrc/print_netrc.py'},
]:
ie = DummyIE(FakeYDL(params))
self.assertEqual(ie._get_netrc_login_info(netrc_machine='normal_use'), ('user', 'pass'))
self.assertEqual(ie._get_netrc_login_info(netrc_machine='empty_user'), ('', 'pass'))
self.assertEqual(ie._get_netrc_login_info(netrc_machine='empty_pass'), ('user', ''))
self.assertEqual(ie._get_netrc_login_info(netrc_machine='both_empty'), ('', ''))
self.assertEqual(ie._get_netrc_login_info(netrc_machine='nonexistent'), (None, None))
def test_html_search_regex(self):
html = '<p id="foo">Watch this <a href="http://www.youtube.com/watch?v=BaW_jenozKc">video</a></p>'
search = lambda re, *args: self.ie._html_search_regex(re, html, *args)

59
test/test_YoutubeDL.py
View File

@@ -6,6 +6,8 @@ import sys
import unittest
from unittest.mock import patch
from yt_dlp.globals import all_plugins_loaded
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
@@ -15,7 +17,6 @@ import json
from test.helper import FakeYDL, assertRegexpMatches, try_rm
from yt_dlp import YoutubeDL
from yt_dlp.compat import compat_os_name
from yt_dlp.extractor import YoutubeIE
from yt_dlp.extractor.common import InfoExtractor
from yt_dlp.postprocessor.common import PostProcessor
@@ -487,11 +488,11 @@ class TestFormatSelection(unittest.TestCase):
def test_format_filtering(self):
formats = [
{'format_id': 'A', 'filesize': 500, 'width': 1000},
{'format_id': 'B', 'filesize': 1000, 'width': 500},
{'format_id': 'C', 'filesize': 1000, 'width': 400},
{'format_id': 'D', 'filesize': 2000, 'width': 600},
{'format_id': 'E', 'filesize': 3000},
{'format_id': 'A', 'filesize': 500, 'width': 1000, 'aspect_ratio': 1.0},
{'format_id': 'B', 'filesize': 1000, 'width': 500, 'aspect_ratio': 1.33},
{'format_id': 'C', 'filesize': 1000, 'width': 400, 'aspect_ratio': 1.5},
{'format_id': 'D', 'filesize': 2000, 'width': 600, 'aspect_ratio': 1.78},
{'format_id': 'E', 'filesize': 3000, 'aspect_ratio': 0.56},
{'format_id': 'F'},
{'format_id': 'G', 'filesize': 1000000},
]
@@ -550,6 +551,31 @@ class TestFormatSelection(unittest.TestCase):
ydl.process_ie_result(info_dict)
self.assertEqual(ydl.downloaded_info_dicts, [])
ydl = YDL({'format': 'best[aspect_ratio=1]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'A')
ydl = YDL({'format': 'all[aspect_ratio > 1.00]'})
ydl.process_ie_result(info_dict)
downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
self.assertEqual(downloaded_ids, ['D', 'C', 'B'])
ydl = YDL({'format': 'all[aspect_ratio < 1.00]'})
ydl.process_ie_result(info_dict)
downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
self.assertEqual(downloaded_ids, ['E'])
ydl = YDL({'format': 'best[aspect_ratio=1.5]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'C')
ydl = YDL({'format': 'all[aspect_ratio!=1]'})
ydl.process_ie_result(info_dict)
downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
self.assertEqual(downloaded_ids, ['E', 'D', 'C', 'B'])
@patch('yt_dlp.postprocessor.ffmpeg.FFmpegMergerPP.available', False)
def test_default_format_spec_without_ffmpeg(self):
ydl = YDL({})
@@ -762,6 +788,13 @@ class TestYoutubeDL(unittest.TestCase):
test('%(width)06d.%%(ext)s', 'NA.%(ext)s')
test('%%(width)06d.%(ext)s', '%(width)06d.mp4')
# Sanitization options
test('%(title3)s', (None, 'foo⧸bar⧹test'))
test('%(title5)s', (None, 'aei_A'), restrictfilenames=True)
test('%(title3)s', (None, 'foo_bar_test'), windowsfilenames=False, restrictfilenames=True)
if sys.platform != 'win32':
test('%(title3)s', (None, 'foo⧸bar\\test'), windowsfilenames=False)
# ID sanitization
test('%(id)s', '_abcd', info={'id': '_abcd'})
test('%(some_id)s', '_abcd', info={'some_id': '_abcd'})
@@ -839,8 +872,8 @@ class TestYoutubeDL(unittest.TestCase):
test('%(filesize)#D', '1Ki')
test('%(height)5.2D', ' 1.08k')
test('%(title4)#S', 'foo_bar_test')
test('%(title4).10S', ('foo ＂bar＂ ', 'foo ＂bar＂' + ('#' if compat_os_name == 'nt' else ' ')))
if compat_os_name == 'nt':
test('%(title4).10S', ('foo ＂bar＂ ', 'foo ＂bar＂' + ('#' if os.name == 'nt' else ' ')))
if os.name == 'nt':
test('%(title4)q', ('"foo ""bar"" test"', None))
test('%(formats.:.id)#q', ('"id 1" "id 2" "id 3"', None))
test('%(formats.0.id)#q', ('"id 1"', None))
@@ -903,9 +936,9 @@ class TestYoutubeDL(unittest.TestCase):
# Environment variable expansion for prepare_filename
os.environ['__yt_dlp_var'] = 'expanded'
envvar = '%__yt_dlp_var%' if compat_os_name == 'nt' else '$__yt_dlp_var'
envvar = '%__yt_dlp_var%' if os.name == 'nt' else '$__yt_dlp_var'
test(envvar, (envvar, 'expanded'))
if compat_os_name == 'nt':
if os.name == 'nt':
test('%s%', ('%s%', '%s%'))
os.environ['s'] = 'expanded'
test('%s%', ('%s%', 'expanded')) # %s% should be expanded before escaping %s
@@ -1396,6 +1429,12 @@ class TestYoutubeDL(unittest.TestCase):
self.assertFalse(result.get('cookies'), msg='Cookies set in cookies field for wrong domain')
self.assertFalse(ydl.cookiejar.get_cookie_header(fmt['url']), msg='Cookies set in cookiejar for wrong domain')
def test_load_plugins_compat(self):
# Should try to reload plugins if they haven't already been loaded
all_plugins_loaded.value = False
FakeYDL().close()
assert all_plugins_loaded.value
if __name__ == '__main__':
unittest.main()

57
test/test_aes.py
View File

@@ -27,7 +27,6 @@ from yt_dlp.aes import (
pad_block,
)
from yt_dlp.dependencies import Cryptodome
from yt_dlp.utils import bytes_to_intlist, intlist_to_bytes
# the encrypted data can be generate with 'devscripts/generate_aes_testdata.py'
@@ -40,33 +39,33 @@ class TestAES(unittest.TestCase):
def test_encrypt(self):
msg = b'message'
key = list(range(16))
encrypted = aes_encrypt(bytes_to_intlist(msg), key)
decrypted = intlist_to_bytes(aes_decrypt(encrypted, key))
encrypted = aes_encrypt(list(msg), key)
decrypted = bytes(aes_decrypt(encrypted, key))
self.assertEqual(decrypted, msg)
def test_cbc_decrypt(self):
data = b'\x97\x92+\xe5\x0b\xc3\x18\x91ky9m&\xb3\xb5@\xe6\x27\xc2\x96.\xc8u\x88\xab9-[\x9e|\xf1\xcd'
decrypted = intlist_to_bytes(aes_cbc_decrypt(bytes_to_intlist(data), self.key, self.iv))
decrypted = bytes(aes_cbc_decrypt(list(data), self.key, self.iv))
self.assertEqual(decrypted.rstrip(b'\x08'), self.secret_msg)
if Cryptodome.AES:
decrypted = aes_cbc_decrypt_bytes(data, intlist_to_bytes(self.key), intlist_to_bytes(self.iv))
decrypted = aes_cbc_decrypt_bytes(data, bytes(self.key), bytes(self.iv))
self.assertEqual(decrypted.rstrip(b'\x08'), self.secret_msg)
def test_cbc_encrypt(self):
data = bytes_to_intlist(self.secret_msg)
encrypted = intlist_to_bytes(aes_cbc_encrypt(data, self.key, self.iv))
data = list(self.secret_msg)
encrypted = bytes(aes_cbc_encrypt(data, self.key, self.iv))
self.assertEqual(
encrypted,
b'\x97\x92+\xe5\x0b\xc3\x18\x91ky9m&\xb3\xb5@\xe6\'\xc2\x96.\xc8u\x88\xab9-[\x9e|\xf1\xcd')
def test_ctr_decrypt(self):
data = bytes_to_intlist(b'\x03\xc7\xdd\xd4\x8e\xb3\xbc\x1a*O\xdc1\x12+8Aio\xd1z\xb5#\xaf\x08')
decrypted = intlist_to_bytes(aes_ctr_decrypt(data, self.key, self.iv))
data = list(b'\x03\xc7\xdd\xd4\x8e\xb3\xbc\x1a*O\xdc1\x12+8Aio\xd1z\xb5#\xaf\x08')
decrypted = bytes(aes_ctr_decrypt(data, self.key, self.iv))
self.assertEqual(decrypted.rstrip(b'\x08'), self.secret_msg)
def test_ctr_encrypt(self):
data = bytes_to_intlist(self.secret_msg)
encrypted = intlist_to_bytes(aes_ctr_encrypt(data, self.key, self.iv))
data = list(self.secret_msg)
encrypted = bytes(aes_ctr_encrypt(data, self.key, self.iv))
self.assertEqual(
encrypted,
b'\x03\xc7\xdd\xd4\x8e\xb3\xbc\x1a*O\xdc1\x12+8Aio\xd1z\xb5#\xaf\x08')
@@ -75,47 +74,59 @@ class TestAES(unittest.TestCase):
data = b'\x159Y\xcf5eud\x90\x9c\x85&]\x14\x1d\x0f.\x08\xb4T\xe4/\x17\xbd'
authentication_tag = b'\xe8&I\x80rI\x07\x9d}YWuU@:e'
decrypted = intlist_to_bytes(aes_gcm_decrypt_and_verify(
bytes_to_intlist(data), self.key, bytes_to_intlist(authentication_tag), self.iv[:12]))
decrypted = bytes(aes_gcm_decrypt_and_verify(
list(data), self.key, list(authentication_tag), self.iv[:12]))
self.assertEqual(decrypted.rstrip(b'\x08'), self.secret_msg)
if Cryptodome.AES:
decrypted = aes_gcm_decrypt_and_verify_bytes(
data, intlist_to_bytes(self.key), authentication_tag, intlist_to_bytes(self.iv[:12]))
data, bytes(self.key), authentication_tag, bytes(self.iv[:12]))
self.assertEqual(decrypted.rstrip(b'\x08'), self.secret_msg)
def test_gcm_aligned_decrypt(self):
data = b'\x159Y\xcf5eud\x90\x9c\x85&]\x14\x1d\x0f'
authentication_tag = b'\x08\xb1\x9d!&\x98\xd0\xeaRq\x90\xe6;\xb5]\xd8'
decrypted = bytes(aes_gcm_decrypt_and_verify(
list(data), self.key, list(authentication_tag), self.iv[:12]))
self.assertEqual(decrypted.rstrip(b'\x08'), self.secret_msg[:16])
if Cryptodome.AES:
decrypted = aes_gcm_decrypt_and_verify_bytes(
data, bytes(self.key), authentication_tag, bytes(self.iv[:12]))
self.assertEqual(decrypted.rstrip(b'\x08'), self.secret_msg[:16])
def test_decrypt_text(self):
password = intlist_to_bytes(self.key).decode()
password = bytes(self.key).decode()
encrypted = base64.b64encode(
intlist_to_bytes(self.iv[:8])
bytes(self.iv[:8])
+ b'\x17\x15\x93\xab\x8d\x80V\xcdV\xe0\t\xcdo\xc2\xa5\xd8ksM\r\xe27N\xae',
).decode()
decrypted = (aes_decrypt_text(encrypted, password, 16))
self.assertEqual(decrypted, self.secret_msg)
password = intlist_to_bytes(self.key).decode()
password = bytes(self.key).decode()
encrypted = base64.b64encode(
intlist_to_bytes(self.iv[:8])
bytes(self.iv[:8])
+ b'\x0b\xe6\xa4\xd9z\x0e\xb8\xb9\xd0\xd4i_\x85\x1d\x99\x98_\xe5\x80\xe7.\xbf\xa5\x83',
).decode()
decrypted = (aes_decrypt_text(encrypted, password, 32))
self.assertEqual(decrypted, self.secret_msg)
def test_ecb_encrypt(self):
data = bytes_to_intlist(self.secret_msg)
encrypted = intlist_to_bytes(aes_ecb_encrypt(data, self.key))
data = list(self.secret_msg)
encrypted = bytes(aes_ecb_encrypt(data, self.key))
self.assertEqual(
encrypted,
b'\xaa\x86]\x81\x97>\x02\x92\x9d\x1bR[[L/u\xd3&\xd1(h\xde{\x81\x94\xba\x02\xae\xbd\xa6\xd0:')
def test_ecb_decrypt(self):
data = bytes_to_intlist(b'\xaa\x86]\x81\x97>\x02\x92\x9d\x1bR[[L/u\xd3&\xd1(h\xde{\x81\x94\xba\x02\xae\xbd\xa6\xd0:')
decrypted = intlist_to_bytes(aes_ecb_decrypt(data, self.key, self.iv))
data = list(b'\xaa\x86]\x81\x97>\x02\x92\x9d\x1bR[[L/u\xd3&\xd1(h\xde{\x81\x94\xba\x02\xae\xbd\xa6\xd0:')
decrypted = bytes(aes_ecb_decrypt(data, self.key, self.iv))
self.assertEqual(decrypted.rstrip(b'\x08'), self.secret_msg)
def test_key_expansion(self):
key = '4f6bdaa39e2f8cb07f5e722d9edef314'
self.assertEqual(key_expansion(bytes_to_intlist(bytearray.fromhex(key))), [
self.assertEqual(key_expansion(list(bytearray.fromhex(key))), [
0x4F, 0x6B, 0xDA, 0xA3, 0x9E, 0x2F, 0x8C, 0xB0, 0x7F, 0x5E, 0x72, 0x2D, 0x9E, 0xDE, 0xF3, 0x14,
0x53, 0x66, 0x20, 0xA8, 0xCD, 0x49, 0xAC, 0x18, 0xB2, 0x17, 0xDE, 0x35, 0x2C, 0xC9, 0x2D, 0x21,
0x8C, 0xBE, 0xDD, 0xD9, 0x41, 0xF7, 0x71, 0xC1, 0xF3, 0xE0, 0xAF, 0xF4, 0xDF, 0x29, 0x82, 0xD5,

40
test/test_compat.py
View File

@@ -12,12 +12,7 @@ import struct
from yt_dlp import compat
from yt_dlp.compat import urllib # isort: split
from yt_dlp.compat import (
compat_etree_fromstring,
compat_expanduser,
compat_urllib_parse_unquote, # noqa: TID251
compat_urllib_parse_urlencode, # noqa: TID251
)
from yt_dlp.compat import compat_etree_fromstring, compat_expanduser
from yt_dlp.compat.urllib.request import getproxies
@@ -43,39 +38,6 @@ class TestCompat(unittest.TestCase):
finally:
os.environ['HOME'] = old_home or ''
def test_compat_urllib_parse_unquote(self):
self.assertEqual(compat_urllib_parse_unquote('abc%20def'), 'abc def')
self.assertEqual(compat_urllib_parse_unquote('%7e/abc+def'), '~/abc+def')
self.assertEqual(compat_urllib_parse_unquote(''), '')
self.assertEqual(compat_urllib_parse_unquote('%'), '%')
self.assertEqual(compat_urllib_parse_unquote('%%'), '%%')
self.assertEqual(compat_urllib_parse_unquote('%%%'), '%%%')
self.assertEqual(compat_urllib_parse_unquote('%2F'), '/')
self.assertEqual(compat_urllib_parse_unquote('%2f'), '/')
self.assertEqual(compat_urllib_parse_unquote('%E6%B4%A5%E6%B3%A2'), '津波')
self.assertEqual(
compat_urllib_parse_unquote('''<meta property="og:description" content="%E2%96%81%E2%96%82%E2%96%83%E2%96%84%25%E2%96%85%E2%96%86%E2%96%87%E2%96%88" />
%<a href="https://ar.wikipedia.org/wiki/%D8%AA%D8%B3%D9%88%D9%86%D8%A7%D9%85%D9%8A">%a'''),
'''<meta property="og:description" content="▁▂▃▄%▅▆▇█" />
%<a href="https://ar.wikipedia.org/wiki/تسونامي">%a''')
self.assertEqual(
compat_urllib_parse_unquote('''%28%5E%E2%97%A3_%E2%97%A2%5E%29%E3%81%A3%EF%B8%BB%E3%83%87%E2%95%90%E4%B8%80 %E2%87%80 %E2%87%80 %E2%87%80 %E2%87%80 %E2%87%80 %E2%86%B6%I%Break%25Things%'''),
'''(^◣_◢^)っ︻デ═一 ⇀ ⇀ ⇀ ⇀ ⇀ ↶%I%Break%Things%''')
def test_compat_urllib_parse_unquote_plus(self):
self.assertEqual(urllib.parse.unquote_plus('abc%20def'), 'abc def')
self.assertEqual(urllib.parse.unquote_plus('%7e/abc+def'), '~/abc def')
def test_compat_urllib_parse_urlencode(self):
self.assertEqual(compat_urllib_parse_urlencode({'abc': 'def'}), 'abc=def')
self.assertEqual(compat_urllib_parse_urlencode({'abc': b'def'}), 'abc=def')
self.assertEqual(compat_urllib_parse_urlencode({b'abc': 'def'}), 'abc=def')
self.assertEqual(compat_urllib_parse_urlencode({b'abc': b'def'}), 'abc=def')
self.assertEqual(compat_urllib_parse_urlencode([('abc', 'def')]), 'abc=def')
self.assertEqual(compat_urllib_parse_urlencode([('abc', b'def')]), 'abc=def')
self.assertEqual(compat_urllib_parse_urlencode([(b'abc', 'def')]), 'abc=def')
self.assertEqual(compat_urllib_parse_urlencode([(b'abc', b'def')]), 'abc=def')
def test_compat_etree_fromstring(self):
xml = '''
<root foo="bar" spam="中文">

16
test/test_cookies.py
View File

@@ -105,6 +105,13 @@ class TestCookies(unittest.TestCase):
decryptor = LinuxChromeCookieDecryptor('Chrome', Logger())
self.assertEqual(decryptor.decrypt(encrypted_value), value)
def test_chrome_cookie_decryptor_linux_v10_meta24(self):
with MonkeyPatch(cookies, {'_get_linux_keyring_password': lambda *args, **kwargs: b''}):
encrypted_value = b'v10\x1f\xe4\x0e[\x83\x0c\xcc*kPi \xce\x8d\x1d\xbb\x80\r\x11\t\xbb\x9e^Hy\x94\xf4\x963\x9f\x82\xba\xfe\xa1\xed\xb9\xf1)\x00710\x92\xc8/<\x96B'
value = 'DE'
decryptor = LinuxChromeCookieDecryptor('Chrome', Logger(), meta_version=24)
self.assertEqual(decryptor.decrypt(encrypted_value), value)
def test_chrome_cookie_decryptor_windows_v10(self):
with MonkeyPatch(cookies, {
'_get_windows_v10_key': lambda *args, **kwargs: b'Y\xef\xad\xad\xeerp\xf0Y\xe6\x9b\x12\xc2<z\x16]\n\xbb\xb8\xcb\xd7\x9bA\xc3\x14e\x99{\xd6\xf4&',
@@ -114,6 +121,15 @@ class TestCookies(unittest.TestCase):
decryptor = WindowsChromeCookieDecryptor('', Logger())
self.assertEqual(decryptor.decrypt(encrypted_value), value)
def test_chrome_cookie_decryptor_windows_v10_meta24(self):
with MonkeyPatch(cookies, {
'_get_windows_v10_key': lambda *args, **kwargs: b'\xea\x8b\x02\xc3\xc6\xc5\x99\xc3\xa3[ j\xfa\xf6\xfcU\xac\x13u\xdc\x0c\x0e\xf1\x03\x90\xb6\xdf\xbb\x8fL\xb1\xb2',
}):
encrypted_value = b'v10dN\xe1\xacy\x84^\xe1I\xact\x03r\xfb\xe2\xce{^\x0e<(\xb0y\xeb\x01\xfb@"\x9e\x8c\xa53~\xdb*\x8f\xac\x8b\xe3\xfd3\x06\xe5\x93\x19OyOG\xb2\xfb\x1d$\xc0\xda\x13j\x9e\xfe\xc5\xa3\xa8\xfe\xd9'
value = '1234'
decryptor = WindowsChromeCookieDecryptor('', Logger(), meta_version=24)
self.assertEqual(decryptor.decrypt(encrypted_value), value)
def test_chrome_cookie_decryptor_mac_v10(self):
with MonkeyPatch(cookies, {'_get_mac_keyring_password': lambda *args, **kwargs: b'6eIDUdtKAacvlHwBVwvg/Q=='}):
encrypted_value = b'v10\xb3\xbe\xad\xa1[\x9fC\xa1\x98\xe0\x9a\x01\xd9\xcf\xbfc'

7
test/test_downloader_http.py
View File

@@ -15,7 +15,6 @@ import threading
from test.helper import http_server_port, try_rm
from yt_dlp import YoutubeDL
from yt_dlp.downloader.http import HttpFD
from yt_dlp.utils import encodeFilename
from yt_dlp.utils._utils import _YDLLogger as FakeLogger
TEST_DIR = os.path.dirname(os.path.abspath(__file__))
@@ -82,12 +81,12 @@ class TestHttpFD(unittest.TestCase):
ydl = YoutubeDL(params)
downloader = HttpFD(ydl, params)
filename = 'testfile.mp4'
try_rm(encodeFilename(filename))
try_rm(filename)
self.assertTrue(downloader.real_download(filename, {
'url': f'http://127.0.0.1:{self.port}/{ep}',
}), ep)
self.assertEqual(os.path.getsize(encodeFilename(filename)), TEST_SIZE, ep)
try_rm(encodeFilename(filename))
self.assertEqual(os.path.getsize(filename), TEST_SIZE, ep)
try_rm(filename)
def download_all(self, params):
for ep in ('regular', 'no-content-length', 'no-range', 'no-range-no-content-length'):

33
test/test_jsinterp.py
View File

@@ -9,7 +9,7 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import math
from yt_dlp.jsinterp import JS_Undefined, JSInterpreter
from yt_dlp.jsinterp import JS_Undefined, JSInterpreter, js_number_to_string
class NaN:
@@ -93,6 +93,16 @@ class TestJSInterpreter(unittest.TestCase):
self._test('function f(){return 0 ?? 42;}', 0)
self._test('function f(){return "life, the universe and everything" < 42;}', False)
self._test('function f(){return 0 - 7 * - 6;}', 42)
self._test('function f(){return true << "5";}', 32)
self._test('function f(){return true << true;}', 2)
self._test('function f(){return "19" & "21.9";}', 17)
self._test('function f(){return "19" & false;}', 0)
self._test('function f(){return "11.0" >> "2.1";}', 2)
self._test('function f(){return 5 ^ 9;}', 12)
self._test('function f(){return 0.0 << NaN}', 0)
self._test('function f(){return null << undefined}', 0)
# TODO: Does not work due to number too large
# self._test('function f(){return 21 << 4294967297}', 42)
def test_array_access(self):
self._test('function f(){var x = [1,2,3]; x[0] = 4; x[0] = 5; x[2.0] = 7; return x;}', [5, 2, 7])
@@ -431,6 +441,27 @@ class TestJSInterpreter(unittest.TestCase):
self._test('function f(){return "012345678".slice(-1, 1)}', '')
self._test('function f(){return "012345678".slice(-3, -1)}', '67')
def test_js_number_to_string(self):
for test, radix, expected in [
(0, None, '0'),
(-0, None, '0'),
(0.0, None, '0'),
(-0.0, None, '0'),
(math.nan, None, 'NaN'),
(-math.nan, None, 'NaN'),
(math.inf, None, 'Infinity'),
(-math.inf, None, '-Infinity'),
(10 ** 21.5, 8, '526665530627250154000000'),
(6, 2, '110'),
(254, 16, 'fe'),
(-10, 2, '-1010'),
(-0xff, 2, '-11111111'),
(0.1 + 0.2, 16, '0.4cccccccccccd'),
(1234.1234, 10, '1234.1234'),
# (1000000000000000128, 10, '1000000000000000100')
]:
assert js_number_to_string(test, radix) == expected
if __name__ == '__main__':
unittest.main()

13
test/test_networking.py
View File

@@ -720,6 +720,15 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
rh, Request(
f'http://127.0.0.1:{self.http_port}/headers', proxies={'all': 'http://10.255.255.255'})).close()
@pytest.mark.skip_handlers_if(lambda _, handler: handler not in ['Urllib', 'CurlCFFI'], 'handler does not support keep_header_casing')
def test_keep_header_casing(self, handler):
with handler() as rh:
res = validate_and_send(
rh, Request(
f'http://127.0.0.1:{self.http_port}/headers', headers={'X-test-heaDer': 'test'}, extensions={'keep_header_casing': True})).read().decode()
assert 'X-test-heaDer: test' in res
@pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
class TestClientCertificate:
@@ -1289,6 +1298,7 @@ class TestRequestHandlerValidation:
({'legacy_ssl': False}, False),
({'legacy_ssl': True}, False),
({'legacy_ssl': 'notabool'}, AssertionError),
({'keep_header_casing': True}, UnsupportedRequest),
]),
('Requests', 'http', [
({'cookiejar': 'notacookiejar'}, AssertionError),
@@ -1299,6 +1309,9 @@ class TestRequestHandlerValidation:
({'legacy_ssl': False}, False),
({'legacy_ssl': True}, False),
({'legacy_ssl': 'notabool'}, AssertionError),
({'keep_header_casing': False}, False),
({'keep_header_casing': True}, False),
({'keep_header_casing': 'notabool'}, AssertionError),
]),
('CurlCFFI', 'http', [
({'cookiejar': 'notacookiejar'}, AssertionError),

189
test/test_plugins.py
View File

@@ -10,21 +10,71 @@ TEST_DATA_DIR = Path(os.path.dirname(os.path.abspath(__file__)), 'testdata')
sys.path.append(str(TEST_DATA_DIR))
importlib.invalidate_caches()
from yt_dlp.plugins import PACKAGE_NAME, directories, load_plugins
from yt_dlp.plugins import (
PACKAGE_NAME,
PluginSpec,
directories,
load_plugins,
load_all_plugins,
register_plugin_spec,
)
from yt_dlp.globals import (
extractors,
postprocessors,
plugin_dirs,
plugin_ies,
plugin_pps,
all_plugins_loaded,
plugin_specs,
)
EXTRACTOR_PLUGIN_SPEC = PluginSpec(
module_name='extractor',
suffix='IE',
destination=extractors,
plugin_destination=plugin_ies,
)
POSTPROCESSOR_PLUGIN_SPEC = PluginSpec(
module_name='postprocessor',
suffix='PP',
destination=postprocessors,
plugin_destination=plugin_pps,
)
def reset_plugins():
plugin_ies.value = {}
plugin_pps.value = {}
plugin_dirs.value = ['default']
plugin_specs.value = {}
all_plugins_loaded.value = False
# Clearing override plugins is probably difficult
for module_name in tuple(sys.modules):
for plugin_type in ('extractor', 'postprocessor'):
if module_name.startswith(f'{PACKAGE_NAME}.{plugin_type}.'):
del sys.modules[module_name]
importlib.invalidate_caches()
class TestPlugins(unittest.TestCase):
TEST_PLUGIN_DIR = TEST_DATA_DIR / PACKAGE_NAME
def setUp(self):
reset_plugins()
def tearDown(self):
reset_plugins()
def test_directories_containing_plugins(self):
self.assertIn(self.TEST_PLUGIN_DIR, map(Path, directories()))
def test_extractor_classes(self):
for module_name in tuple(sys.modules):
if module_name.startswith(f'{PACKAGE_NAME}.extractor'):
del sys.modules[module_name]
plugins_ie = load_plugins('extractor', 'IE')
plugins_ie = load_plugins(EXTRACTOR_PLUGIN_SPEC)
self.assertIn(f'{PACKAGE_NAME}.extractor.normal', sys.modules.keys())
self.assertIn('NormalPluginIE', plugins_ie.keys())
@@ -34,17 +84,29 @@ class TestPlugins(unittest.TestCase):
f'{PACKAGE_NAME}.extractor._ignore' in sys.modules,
'loaded module beginning with underscore')
self.assertNotIn('IgnorePluginIE', plugins_ie.keys())
self.assertNotIn('IgnorePluginIE', plugin_ies.value)
# Don't load extractors with underscore prefix
self.assertNotIn('_IgnoreUnderscorePluginIE', plugins_ie.keys())
self.assertNotIn('_IgnoreUnderscorePluginIE', plugin_ies.value)
# Don't load extractors not specified in __all__ (if supplied)
self.assertNotIn('IgnoreNotInAllPluginIE', plugins_ie.keys())
self.assertNotIn('IgnoreNotInAllPluginIE', plugin_ies.value)
self.assertIn('InAllPluginIE', plugins_ie.keys())
self.assertIn('InAllPluginIE', plugin_ies.value)
# Don't load override extractors
self.assertNotIn('OverrideGenericIE', plugins_ie.keys())
self.assertNotIn('OverrideGenericIE', plugin_ies.value)
self.assertNotIn('_UnderscoreOverrideGenericIE', plugins_ie.keys())
self.assertNotIn('_UnderscoreOverrideGenericIE', plugin_ies.value)
def test_postprocessor_classes(self):
plugins_pp = load_plugins('postprocessor', 'PP')
plugins_pp = load_plugins(POSTPROCESSOR_PLUGIN_SPEC)
self.assertIn('NormalPluginPP', plugins_pp.keys())
self.assertIn(f'{PACKAGE_NAME}.postprocessor.normal', sys.modules.keys())
self.assertIn('NormalPluginPP', plugin_pps.value)
def test_importing_zipped_module(self):
zip_path = TEST_DATA_DIR / 'zipped_plugins.zip'
@@ -57,10 +119,10 @@ class TestPlugins(unittest.TestCase):
package = importlib.import_module(f'{PACKAGE_NAME}.{plugin_type}')
self.assertIn(zip_path / PACKAGE_NAME / plugin_type, map(Path, package.__path__))
plugins_ie = load_plugins('extractor', 'IE')
plugins_ie = load_plugins(EXTRACTOR_PLUGIN_SPEC)
self.assertIn('ZippedPluginIE', plugins_ie.keys())
plugins_pp = load_plugins('postprocessor', 'PP')
plugins_pp = load_plugins(POSTPROCESSOR_PLUGIN_SPEC)
self.assertIn('ZippedPluginPP', plugins_pp.keys())
finally:
@@ -68,6 +130,117 @@ class TestPlugins(unittest.TestCase):
os.remove(zip_path)
importlib.invalidate_caches() # reset the import caches
def test_reloading_plugins(self):
reload_plugins_path = TEST_DATA_DIR / 'reload_plugins'
load_plugins(EXTRACTOR_PLUGIN_SPEC)
load_plugins(POSTPROCESSOR_PLUGIN_SPEC)
# Remove default folder and add reload_plugin path
sys.path.remove(str(TEST_DATA_DIR))
sys.path.append(str(reload_plugins_path))
importlib.invalidate_caches()
try:
for plugin_type in ('extractor', 'postprocessor'):
package = importlib.import_module(f'{PACKAGE_NAME}.{plugin_type}')
self.assertIn(reload_plugins_path / PACKAGE_NAME / plugin_type, map(Path, package.__path__))
plugins_ie = load_plugins(EXTRACTOR_PLUGIN_SPEC)
self.assertIn('NormalPluginIE', plugins_ie.keys())
self.assertTrue(
plugins_ie['NormalPluginIE'].REPLACED,
msg='Reloading has not replaced original extractor plugin')
self.assertTrue(
extractors.value['NormalPluginIE'].REPLACED,
msg='Reloading has not replaced original extractor plugin globally')
plugins_pp = load_plugins(POSTPROCESSOR_PLUGIN_SPEC)
self.assertIn('NormalPluginPP', plugins_pp.keys())
self.assertTrue(plugins_pp['NormalPluginPP'].REPLACED,
msg='Reloading has not replaced original postprocessor plugin')
self.assertTrue(
postprocessors.value['NormalPluginPP'].REPLACED,
msg='Reloading has not replaced original postprocessor plugin globally')
finally:
sys.path.remove(str(reload_plugins_path))
sys.path.append(str(TEST_DATA_DIR))
importlib.invalidate_caches()
def test_extractor_override_plugin(self):
load_plugins(EXTRACTOR_PLUGIN_SPEC)
from yt_dlp.extractor.generic import GenericIE
self.assertEqual(GenericIE.TEST_FIELD, 'override')
self.assertEqual(GenericIE.SECONDARY_TEST_FIELD, 'underscore-override')
self.assertEqual(GenericIE.IE_NAME, 'generic+override+underscore-override')
importlib.invalidate_caches()
# test that loading a second time doesn't wrap a second time
load_plugins(EXTRACTOR_PLUGIN_SPEC)
from yt_dlp.extractor.generic import GenericIE
self.assertEqual(GenericIE.IE_NAME, 'generic+override+underscore-override')
def test_load_all_plugin_types(self):
# no plugin specs registered
load_all_plugins()
self.assertNotIn(f'{PACKAGE_NAME}.extractor.normal', sys.modules.keys())
self.assertNotIn(f'{PACKAGE_NAME}.postprocessor.normal', sys.modules.keys())
register_plugin_spec(EXTRACTOR_PLUGIN_SPEC)
register_plugin_spec(POSTPROCESSOR_PLUGIN_SPEC)
load_all_plugins()
self.assertTrue(all_plugins_loaded.value)
self.assertIn(f'{PACKAGE_NAME}.extractor.normal', sys.modules.keys())
self.assertIn(f'{PACKAGE_NAME}.postprocessor.normal', sys.modules.keys())
def test_no_plugin_dirs(self):
register_plugin_spec(EXTRACTOR_PLUGIN_SPEC)
register_plugin_spec(POSTPROCESSOR_PLUGIN_SPEC)
plugin_dirs.value = []
load_all_plugins()
self.assertNotIn(f'{PACKAGE_NAME}.extractor.normal', sys.modules.keys())
self.assertNotIn(f'{PACKAGE_NAME}.postprocessor.normal', sys.modules.keys())
def test_set_plugin_dirs(self):
custom_plugin_dir = str(TEST_DATA_DIR / 'plugin_packages')
plugin_dirs.value = [custom_plugin_dir]
load_plugins(EXTRACTOR_PLUGIN_SPEC)
self.assertIn(f'{PACKAGE_NAME}.extractor.package', sys.modules.keys())
self.assertIn('PackagePluginIE', plugin_ies.value)
def test_invalid_plugin_dir(self):
plugin_dirs.value = ['invalid_dir']
with self.assertRaises(ValueError):
load_plugins(EXTRACTOR_PLUGIN_SPEC)
def test_append_plugin_dirs(self):
custom_plugin_dir = str(TEST_DATA_DIR / 'plugin_packages')
self.assertEqual(plugin_dirs.value, ['default'])
plugin_dirs.value.append(custom_plugin_dir)
self.assertEqual(plugin_dirs.value, ['default', custom_plugin_dir])
load_plugins(EXTRACTOR_PLUGIN_SPEC)
self.assertIn(f'{PACKAGE_NAME}.extractor.package', sys.modules.keys())
self.assertIn('PackagePluginIE', plugin_ies.value)
def test_get_plugin_spec(self):
register_plugin_spec(EXTRACTOR_PLUGIN_SPEC)
register_plugin_spec(POSTPROCESSOR_PLUGIN_SPEC)
self.assertEqual(plugin_specs.value.get('extractor'), EXTRACTOR_PLUGIN_SPEC)
self.assertEqual(plugin_specs.value.get('postprocessor'), POSTPROCESSOR_PLUGIN_SPEC)
self.assertIsNone(plugin_specs.value.get('invalid'))
if __name__ == '__main__':
unittest.main()

4
test/test_socks.py
View File

@@ -216,7 +216,9 @@ class SocksWebSocketTestRequestHandler(SocksTestRequestHandler):
protocol = websockets.ServerProtocol()
connection = websockets.sync.server.ServerConnection(socket=self.request, protocol=protocol, close_timeout=0)
connection.handshake()
connection.send(json.dumps(self.socks_info))
for message in connection:
if message == 'socks_info':
connection.send(json.dumps(self.socks_info))
connection.close()

207
test/test_traversal.py
View File

@@ -4,8 +4,23 @@ import xml.etree.ElementTree
import pytest
from yt_dlp.utils import dict_get, int_or_none, str_or_none
from yt_dlp.utils.traversal import traverse_obj
from yt_dlp.utils import (
ExtractorError,
determine_ext,
dict_get,
int_or_none,
join_nonempty,
str_or_none,
)
from yt_dlp.utils.traversal import (
find_element,
find_elements,
require,
subs_list_to_dict,
traverse_obj,
trim_str,
unpack,
)
_TEST_DATA = {
100: 100,
@@ -24,6 +39,14 @@ _TEST_DATA = {
'dict': {},
}
_TEST_HTML = '''<html><body>
<div class="a">1</div>
<div class="a" id="x" custom="z">2</div>
<div class="b" data-id="y" custom="z">3</div>
<p class="a">4</p>
<p id="d" custom="e">5</p>
</body></html>'''
class TestTraversal:
def test_traversal_base(self):
@@ -420,6 +443,186 @@ class TestTraversal:
assert traverse_obj(morsel, [(None,), any]) == morsel, \
'Morsel should not be implicitly changed to dict on usage'
def test_traversal_filter(self):
data = [None, False, True, 0, 1, 0.0, 1.1, '', 'str', {}, {0: 0}, [], [1]]
assert traverse_obj(data, [..., filter]) == [True, 1, 1.1, 'str', {0: 0}, [1]], \
'`filter` should filter falsy values'
class TestTraversalHelpers:
def test_traversal_require(self):
with pytest.raises(ExtractorError):
traverse_obj(_TEST_DATA, ['None', {require('value')}])
assert traverse_obj(_TEST_DATA, ['str', {require('value')}]) == 'str', \
'`require` should pass through non `None` values'
def test_subs_list_to_dict(self):
assert traverse_obj([
{'name': 'de', 'url': 'https://example.com/subs/de.vtt'},
{'name': 'en', 'url': 'https://example.com/subs/en1.ass'},
{'name': 'en', 'url': 'https://example.com/subs/en2.ass'},
], [..., {
'id': 'name',
'url': 'url',
}, all, {subs_list_to_dict}]) == {
'de': [{'url': 'https://example.com/subs/de.vtt'}],
'en': [
{'url': 'https://example.com/subs/en1.ass'},
{'url': 'https://example.com/subs/en2.ass'},
],
}, 'function should build subtitle dict from list of subtitles'
assert traverse_obj([
{'name': 'de', 'url': 'https://example.com/subs/de.ass'},
{'name': 'de'},
{'name': 'en', 'content': 'content'},
{'url': 'https://example.com/subs/en'},
], [..., {
'id': 'name',
'data': 'content',
'url': 'url',
}, all, {subs_list_to_dict(lang=None)}]) == {
'de': [{'url': 'https://example.com/subs/de.ass'}],
'en': [{'data': 'content'}],
}, 'subs with mandatory items missing should be filtered'
assert traverse_obj([
{'url': 'https://example.com/subs/de.ass', 'name': 'de'},
{'url': 'https://example.com/subs/en', 'name': 'en'},
], [..., {
'id': 'name',
'ext': ['url', {determine_ext(default_ext=None)}],
'url': 'url',
}, all, {subs_list_to_dict(ext='ext')}]) == {
'de': [{'url': 'https://example.com/subs/de.ass', 'ext': 'ass'}],
'en': [{'url': 'https://example.com/subs/en', 'ext': 'ext'}],
}, '`ext` should set default ext but leave existing value untouched'
assert traverse_obj([
{'name': 'en', 'url': 'https://example.com/subs/en2', 'prio': True},
{'name': 'en', 'url': 'https://example.com/subs/en1', 'prio': False},
], [..., {
'id': 'name',
'quality': ['prio', {int}],
'url': 'url',
}, all, {subs_list_to_dict(ext='ext')}]) == {'en': [
{'url': 'https://example.com/subs/en1', 'ext': 'ext'},
{'url': 'https://example.com/subs/en2', 'ext': 'ext'},
]}, '`quality` key should sort subtitle list accordingly'
assert traverse_obj([
{'name': 'de', 'url': 'https://example.com/subs/de.ass'},
{'name': 'de'},
{'name': 'en', 'content': 'content'},
{'url': 'https://example.com/subs/en'},
], [..., {
'id': 'name',
'url': 'url',
'data': 'content',
}, all, {subs_list_to_dict(lang='en')}]) == {
'de': [{'url': 'https://example.com/subs/de.ass'}],
'en': [
{'data': 'content'},
{'url': 'https://example.com/subs/en'},
],
}, 'optionally provided lang should be used if no id available'
assert traverse_obj([
{'name': 1, 'url': 'https://example.com/subs/de1'},
{'name': {}, 'url': 'https://example.com/subs/de2'},
{'name': 'de', 'ext': 1, 'url': 'https://example.com/subs/de3'},
{'name': 'de', 'ext': {}, 'url': 'https://example.com/subs/de4'},
], [..., {
'id': 'name',
'url': 'url',
'ext': 'ext',
}, all, {subs_list_to_dict(lang=None)}]) == {
'de': [
{'url': 'https://example.com/subs/de3'},
{'url': 'https://example.com/subs/de4'},
],
}, 'non str types should be ignored for id and ext'
assert traverse_obj([
{'name': 1, 'url': 'https://example.com/subs/de1'},
{'name': {}, 'url': 'https://example.com/subs/de2'},
{'name': 'de', 'ext': 1, 'url': 'https://example.com/subs/de3'},
{'name': 'de', 'ext': {}, 'url': 'https://example.com/subs/de4'},
], [..., {
'id': 'name',
'url': 'url',
'ext': 'ext',
}, all, {subs_list_to_dict(lang='de')}]) == {
'de': [
{'url': 'https://example.com/subs/de1'},
{'url': 'https://example.com/subs/de2'},
{'url': 'https://example.com/subs/de3'},
{'url': 'https://example.com/subs/de4'},
],
}, 'non str types should be replaced by default id'
def test_trim_str(self):
with pytest.raises(TypeError):
trim_str('positional')
assert callable(trim_str(start='a'))
assert trim_str(start='ab')('abc') == 'c'
assert trim_str(end='bc')('abc') == 'a'
assert trim_str(start='a', end='c')('abc') == 'b'
assert trim_str(start='ab', end='c')('abc') == ''
assert trim_str(start='a', end='bc')('abc') == ''
assert trim_str(start='ab', end='bc')('abc') == ''
assert trim_str(start='abc', end='abc')('abc') == ''
assert trim_str(start='', end='')('abc') == 'abc'
def test_unpack(self):
assert unpack(lambda *x: ''.join(map(str, x)))([1, 2, 3]) == '123'
assert unpack(join_nonempty)([1, 2, 3]) == '1-2-3'
assert unpack(join_nonempty, delim=' ')([1, 2, 3]) == '1 2 3'
with pytest.raises(TypeError):
unpack(join_nonempty)()
with pytest.raises(TypeError):
unpack()
def test_find_element(self):
for improper_kwargs in [
dict(attr='data-id'),
dict(value='y'),
dict(attr='data-id', value='y', cls='a'),
dict(attr='data-id', value='y', id='x'),
dict(cls='a', id='x'),
dict(cls='a', tag='p'),
dict(cls='[ab]', regex=True),
]:
with pytest.raises(AssertionError):
find_element(**improper_kwargs)(_TEST_HTML)
assert find_element(cls='a')(_TEST_HTML) == '1'
assert find_element(cls='a', html=True)(_TEST_HTML) == '<div class="a">1</div>'
assert find_element(id='x')(_TEST_HTML) == '2'
assert find_element(id='[ex]')(_TEST_HTML) is None
assert find_element(id='[ex]', regex=True)(_TEST_HTML) == '2'
assert find_element(id='x', html=True)(_TEST_HTML) == '<div class="a" id="x" custom="z">2</div>'
assert find_element(attr='data-id', value='y')(_TEST_HTML) == '3'
assert find_element(attr='data-id', value='y(?:es)?')(_TEST_HTML) is None
assert find_element(attr='data-id', value='y(?:es)?', regex=True)(_TEST_HTML) == '3'
assert find_element(
attr='data-id', value='y', html=True)(_TEST_HTML) == '<div class="b" data-id="y" custom="z">3</div>'
def test_find_elements(self):
for improper_kwargs in [
dict(tag='p'),
dict(attr='data-id'),
dict(value='y'),
dict(attr='data-id', value='y', cls='a'),
dict(cls='a', tag='div'),
dict(cls='[ab]', regex=True),
]:
with pytest.raises(AssertionError):
find_elements(**improper_kwargs)(_TEST_HTML)
assert find_elements(cls='a')(_TEST_HTML) == ['1', '2', '4']
assert find_elements(cls='a', html=True)(_TEST_HTML) == [
'<div class="a">1</div>', '<div class="a" id="x" custom="z">2</div>', '<p class="a">4</p>']
assert find_elements(attr='custom', value='z')(_TEST_HTML) == ['2', '3']
assert find_elements(attr='custom', value='[ez]')(_TEST_HTML) == []
assert find_elements(attr='custom', value='[ez]', regex=True)(_TEST_HTML) == ['2', '3', '5']
class TestDictGet:
def test_dict_get(self):

89
test/test_update.py
View File

@@ -82,16 +82,32 @@ TEST_LOCKFILE_V1 = rf'''{TEST_LOCKFILE_COMMENT}
lock 2022.08.18.36 .+ Python 3\.6
lock 2023.11.16 (?!win_x86_exe).+ Python 3\.7
lock 2023.11.16 win_x86_exe .+ Windows-(?:Vista|2008Server)
lock 2024.10.22 py2exe .+
lock 2024.10.22 linux_(?:armv7l|aarch64)_exe .+-glibc2\.(?:[12]?\d|30)\b
lock 2024.10.22 (?!\w+_exe).+ Python 3\.8
lock 2024.10.22 win(?:_x86)?_exe Python 3\.[78].+ Windows-(?:7-|2008ServerR2)
'''
TEST_LOCKFILE_V2_TMPL = r'''%s
lockV2 yt-dlp/yt-dlp 2022.08.18.36 .+ Python 3\.6
lockV2 yt-dlp/yt-dlp 2023.11.16 (?!win_x86_exe).+ Python 3\.7
lockV2 yt-dlp/yt-dlp 2023.11.16 win_x86_exe .+ Windows-(?:Vista|2008Server)
lockV2 yt-dlp/yt-dlp 2024.10.22 py2exe .+
lockV2 yt-dlp/yt-dlp 2024.10.22 linux_(?:armv7l|aarch64)_exe .+-glibc2\.(?:[12]?\d|30)\b
lockV2 yt-dlp/yt-dlp 2024.10.22 (?!\w+_exe).+ Python 3\.8
lockV2 yt-dlp/yt-dlp 2024.10.22 win(?:_x86)?_exe Python 3\.[78].+ Windows-(?:7-|2008ServerR2)
lockV2 yt-dlp/yt-dlp-nightly-builds 2023.11.15.232826 (?!win_x86_exe).+ Python 3\.7
lockV2 yt-dlp/yt-dlp-nightly-builds 2023.11.15.232826 win_x86_exe .+ Windows-(?:Vista|2008Server)
lockV2 yt-dlp/yt-dlp-nightly-builds 2024.10.22.051025 py2exe .+
lockV2 yt-dlp/yt-dlp-nightly-builds 2024.10.22.051025 linux_(?:armv7l|aarch64)_exe .+-glibc2\.(?:[12]?\d|30)\b
lockV2 yt-dlp/yt-dlp-nightly-builds 2024.10.22.051025 (?!\w+_exe).+ Python 3\.8
lockV2 yt-dlp/yt-dlp-nightly-builds 2024.10.22.051025 win(?:_x86)?_exe Python 3\.[78].+ Windows-(?:7-|2008ServerR2)
lockV2 yt-dlp/yt-dlp-master-builds 2023.11.15.232812 (?!win_x86_exe).+ Python 3\.7
lockV2 yt-dlp/yt-dlp-master-builds 2023.11.15.232812 win_x86_exe .+ Windows-(?:Vista|2008Server)
lockV2 yt-dlp/yt-dlp-master-builds 2024.10.22.045052 py2exe .+
lockV2 yt-dlp/yt-dlp-master-builds 2024.10.22.060347 linux_(?:armv7l|aarch64)_exe .+-glibc2\.(?:[12]?\d|30)\b
lockV2 yt-dlp/yt-dlp-master-builds 2024.10.22.060347 (?!\w+_exe).+ Python 3\.8
lockV2 yt-dlp/yt-dlp-master-builds 2024.10.22.060347 win(?:_x86)?_exe Python 3\.[78].+ Windows-(?:7-|2008ServerR2)
'''
TEST_LOCKFILE_V2 = TEST_LOCKFILE_V2_TMPL % TEST_LOCKFILE_COMMENT
@@ -145,43 +161,76 @@ class TestUpdate(unittest.TestCase):
for lockfile in (TEST_LOCKFILE_V1, TEST_LOCKFILE_V2, TEST_LOCKFILE_ACTUAL, TEST_LOCKFILE_FORK):
# Normal operation
test(lockfile, 'zip Python 3.12.0', '2023.12.31', '2023.12.31')
test(lockfile, 'zip stable Python 3.12.0', '2023.12.31', '2023.12.31', exact=True)
# Python 3.6 --update should update only to its lock
test(lockfile, 'zip Python 3.12.0', '2023.12.31', '2023.12.31', exact=True)
# py2exe should never update beyond 2024.10.22
test(lockfile, 'py2exe Python 3.8', '2025.01.01', '2024.10.22')
test(lockfile, 'py2exe Python 3.8', '2025.01.01', None, exact=True)
# Python 3.6 --update should update only to the py3.6 lock
test(lockfile, 'zip Python 3.6.0', '2023.11.16', '2022.08.18.36')
# --update-to an exact version later than the lock should return None
test(lockfile, 'zip stable Python 3.6.0', '2023.11.16', None, exact=True)
# Python 3.7 should be able to update to its lock
# Python 3.6 --update-to an exact version later than the py3.6 lock should return None
test(lockfile, 'zip Python 3.6.0', '2023.11.16', None, exact=True)
# Python 3.7 should be able to update to the py3.7 lock
test(lockfile, 'zip Python 3.7.0', '2023.11.16', '2023.11.16')
test(lockfile, 'zip stable Python 3.7.1', '2023.11.16', '2023.11.16', exact=True)
# Non-win_x86_exe builds on py3.7 must be locked
test(lockfile, 'zip Python 3.7.1', '2023.11.16', '2023.11.16', exact=True)
# Non-win_x86_exe builds on py3.7 must be locked at py3.7 lock
test(lockfile, 'zip Python 3.7.1', '2023.12.31', '2023.11.16')
test(lockfile, 'zip stable Python 3.7.1', '2023.12.31', None, exact=True)
test( # Windows Vista w/ win_x86_exe must be locked
lockfile, 'win_x86_exe stable Python 3.7.9 (CPython x86 32bit) - Windows-Vista-6.0.6003-SP2',
test(lockfile, 'zip Python 3.7.1', '2023.12.31', None, exact=True)
# Python 3.8 should only update to the py3.8 lock
test(lockfile, 'zip Python 3.8.10', '2025.01.01', '2024.10.22')
test(lockfile, 'zip Python 3.8.110', '2025.01.01', None, exact=True)
test( # Windows Vista w/ win_x86_exe must be locked at Vista lock
lockfile, 'win_x86_exe Python 3.7.9 (CPython x86 32bit) - Windows-Vista-6.0.6003-SP2',
'2023.12.31', '2023.11.16')
test( # Windows 2008Server w/ win_x86_exe must be locked
test( # Windows 2008Server w/ win_x86_exe must be locked at Vista lock
lockfile, 'win_x86_exe Python 3.7.9 (CPython x86 32bit) - Windows-2008Server',
'2023.12.31', None, exact=True)
test( # Windows 7 w/ win_x86_exe py3.7 build should be able to update beyond lock
lockfile, 'win_x86_exe stable Python 3.7.9 (CPython x86 32bit) - Windows-7-6.1.7601-SP1',
'2023.12.31', '2023.12.31')
test( # Windows 8.1 w/ '2008Server' in platform string should be able to update beyond lock
test( # Windows 7 w/ win_x86_exe py3.7 build should be able to update beyond py3.7 lock
lockfile, 'win_x86_exe Python 3.7.9 (CPython x86 32bit) - Windows-7-6.1.7601-SP1',
'2023.12.31', '2023.12.31', exact=True)
test( # Windows 7 win_x86_exe should only update to Win7 lock
lockfile, 'win_x86_exe Python 3.7.9 (CPython x86 32bit) - Windows-7-6.1.7601-SP1',
'2025.01.01', '2024.10.22')
test( # Windows 2008ServerR2 win_exe should only update to Win7 lock
lockfile, 'win_exe Python 3.8.10 (CPython x86 32bit) - Windows-2008ServerR2',
'2025.12.31', '2024.10.22')
test( # Windows 8.1 w/ '2008Server' in platform string should be able to update beyond py3.7 lock
lockfile, 'win_x86_exe Python 3.7.9 (CPython x86 32bit) - Windows-post2008Server-6.2.9200',
'2023.12.31', '2023.12.31', exact=True)
test( # win_exe built w/Python 3.8 on Windows>=8 should be able to update beyond py3.8 lock
lockfile, 'win_exe Python 3.8.10 (CPython AMD64 64bit) - Windows-10-10.0.20348-SP0',
'2025.01.01', '2025.01.01', exact=True)
test( # linux_armv7l_exe w/glibc2.7 should only update to glibc<2.31 lock
lockfile, 'linux_armv7l_exe Python 3.8.0 (CPython armv7l 32bit) - Linux-6.5.0-1025-azure-armv7l-with-glibc2.7',
'2025.01.01', '2024.10.22')
test( # linux_armv7l_exe w/Python 3.8 and glibc>=2.31 should be able to update beyond py3.8 and glibc<2.31 locks
lockfile, 'linux_armv7l_exe Python 3.8.0 (CPython armv7l 32bit) - Linux-6.5.0-1025-azure-armv7l-with-glibc2.31',
'2025.01.01', '2025.01.01')
test( # linux_armv7l_exe w/glibc2.30 should only update to glibc<2.31 lock
lockfile, 'linux_armv7l_exe Python 3.8.0 (CPython armv7l 64bit) - Linux-6.5.0-1025-azure-aarch64-with-glibc2.30 (OpenSSL',
'2025.01.01', '2024.10.22')
test( # linux_aarch64_exe w/glibc2.17 should only update to glibc<2.31 lock
lockfile, 'linux_aarch64_exe Python 3.8.0 (CPython aarch64 64bit) - Linux-6.5.0-1025-azure-aarch64-with-glibc2.17',
'2025.01.01', '2024.10.22')
test( # linux_aarch64_exe w/glibc2.40 and glibc>=2.31 should be able to update beyond py3.8 and glibc<2.31 locks
lockfile, 'linux_aarch64_exe Python 3.8.0 (CPython aarch64 64bit) - Linux-6.5.0-1025-azure-aarch64-with-glibc2.40',
'2025.01.01', '2025.01.01')
test( # linux_aarch64_exe w/glibc2.3 should only update to glibc<2.31 lock
lockfile, 'linux_aarch64_exe Python 3.8.0 (CPython aarch64 64bit) - Linux-6.5.0-1025-azure-aarch64-with-glibc2.3 (OpenSSL',
'2025.01.01', '2024.10.22')
# Forks can block updates to non-numeric tags rather than lock
test(TEST_LOCKFILE_FORK, 'zip Python 3.6.3', 'pr0000', None, repo='fork/yt-dlp')
test(TEST_LOCKFILE_FORK, 'zip stable Python 3.7.4', 'pr0000', 'pr0000', repo='fork/yt-dlp')
test(TEST_LOCKFILE_FORK, 'zip stable Python 3.7.4', 'pr1234', None, repo='fork/yt-dlp')
test(TEST_LOCKFILE_FORK, 'zip Python 3.7.4', 'pr0000', 'pr0000', repo='fork/yt-dlp')
test(TEST_LOCKFILE_FORK, 'zip Python 3.7.4', 'pr1234', None, repo='fork/yt-dlp')
test(TEST_LOCKFILE_FORK, 'zip Python 3.8.1', 'pr1234', 'pr1234', repo='fork/yt-dlp', exact=True)
test(
TEST_LOCKFILE_FORK, 'win_x86_exe stable Python 3.7.9 (CPython x86 32bit) - Windows-Vista-6.0.6003-SP2',
TEST_LOCKFILE_FORK, 'win_x86_exe Python 3.7.9 (CPython x86 32bit) - Windows-Vista-6.0.6003-SP2',
'pr1234', None, repo='fork/yt-dlp')
test(
TEST_LOCKFILE_FORK, 'win_x86_exe stable Python 3.7.9 (CPython x86 32bit) - Windows-7-6.1.7601-SP1',
TEST_LOCKFILE_FORK, 'win_x86_exe Python 3.7.9 (CPython x86 32bit) - Windows-7-6.1.7601-SP1',
'2023.12.31', '2023.12.31', repo='fork/yt-dlp')
test(TEST_LOCKFILE_FORK, 'zip Python 3.11.2', 'pr9999', None, repo='fork/yt-dlp', exact=True)
test(TEST_LOCKFILE_FORK, 'zip stable Python 3.12.0', 'pr9999', 'pr9999', repo='fork/yt-dlp')
test(TEST_LOCKFILE_FORK, 'zip Python 3.12.0', 'pr9999', 'pr9999', repo='fork/yt-dlp')
def test_query_update(self):
ydl = FakeYDL()

83
test/test_utils.py
View File

@@ -3,24 +3,25 @@
# Allow direct execution
import os
import sys
import unittest
import warnings
import datetime as dt
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import contextlib
import datetime as dt
import io
import itertools
import json
import pickle
import subprocess
import unittest
import unittest.mock
import warnings
import xml.etree.ElementTree
from yt_dlp.compat import (
compat_etree_fromstring,
compat_HTMLParseError,
compat_os_name,
)
from yt_dlp.utils import (
Config,
@@ -48,7 +49,6 @@ from yt_dlp.utils import (
dfxp2srt,
encode_base_n,
encode_compat_str,
encodeFilename,
expand_path,
extract_attributes,
extract_basic_auth,
@@ -68,7 +68,6 @@ from yt_dlp.utils import (
get_elements_html_by_class,
get_elements_text_and_html_by_attribute,
int_or_none,
intlist_to_bytes,
iri_to_uri,
is_html,
js_to_json,
@@ -221,9 +220,10 @@ class TestUtil(unittest.TestCase):
self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
def test_sanitize_path(self):
if sys.platform != 'win32':
return
with unittest.mock.patch('sys.platform', 'win32'):
self._test_sanitize_path()
def _test_sanitize_path(self):
self.assertEqual(sanitize_path('abc'), 'abc')
self.assertEqual(sanitize_path('abc/def'), 'abc\\def')
self.assertEqual(sanitize_path('abc\\def'), 'abc\\def')
@@ -250,11 +250,35 @@ class TestUtil(unittest.TestCase):
self.assertEqual(sanitize_path('abc/def...'), 'abc\\def..#')
self.assertEqual(sanitize_path('abc.../def'), 'abc..#\\def')
self.assertEqual(sanitize_path('abc.../def...'), 'abc..#\\def..#')
self.assertEqual(sanitize_path('C:\\abc:%(title)s.%(ext)s'), 'C:\\abc#%(title)s.%(ext)s')
self.assertEqual(sanitize_path('../abc'), '..\\abc')
self.assertEqual(sanitize_path('../../abc'), '..\\..\\abc')
self.assertEqual(sanitize_path('./abc'), 'abc')
self.assertEqual(sanitize_path('./../abc'), '..\\abc')
# Check with nt._path_normpath if available
try:
import nt
nt_path_normpath = getattr(nt, '_path_normpath', None)
except Exception:
nt_path_normpath = None
for test, expected in [
('C:\\', 'C:\\'),
('../abc', '..\\abc'),
('../../abc', '..\\..\\abc'),
('./abc', 'abc'),
('./../abc', '..\\abc'),
('\\abc', '\\abc'),
('C:abc', 'C:abc'),
('C:abc\\..\\', 'C:'),
('C:abc\\..\\def\\..\\..\\', 'C:..'),
('C:\\abc\\xyz///..\\def\\', 'C:\\abc\\def'),
('abc/../', '.'),
('./abc/../', '.'),
]:
result = sanitize_path(test)
assert result == expected, f'{test} was incorrectly resolved'
assert result == sanitize_path(result), f'{test} changed after sanitizing again'
if nt_path_normpath:
assert result == nt_path_normpath(test), f'{test} does not match nt._path_normpath'
def test_sanitize_url(self):
self.assertEqual(sanitize_url('//foo.bar'), 'http://foo.bar')
@@ -337,11 +361,13 @@ class TestUtil(unittest.TestCase):
self.assertEqual(remove_start(None, 'A - '), None)
self.assertEqual(remove_start('A - B', 'A - '), 'B')
self.assertEqual(remove_start('B - A', 'A - '), 'B - A')
self.assertEqual(remove_start('non-empty', ''), 'non-empty')
def test_remove_end(self):
self.assertEqual(remove_end(None, ' - B'), None)
self.assertEqual(remove_end('A - B', ' - B'), 'A')
self.assertEqual(remove_end('B - A', ' - B'), 'B - A')
self.assertEqual(remove_end('non-empty', ''), 'non-empty')
def test_remove_quotes(self):
self.assertEqual(remove_quotes(None), None)
@@ -557,10 +583,10 @@ class TestUtil(unittest.TestCase):
self.assertEqual(res_data, {'a': 'b', 'c': 'd'})
def test_shell_quote(self):
args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
args = ['ffmpeg', '-i', 'ñ€ß\'.mp4']
self.assertEqual(
shell_quote(args),
"""ffmpeg -i 'ñ€ß'"'"'.mp4'""" if compat_os_name != 'nt' else '''ffmpeg -i "ñ€ß'.mp4"''')
"""ffmpeg -i 'ñ€ß'"'"'.mp4'""" if os.name != 'nt' else '''ffmpeg -i "ñ€ß'.mp4"''')
def test_float_or_none(self):
self.assertEqual(float_or_none('42.42'), 42.42)
@@ -1300,15 +1326,10 @@ class TestUtil(unittest.TestCase):
self.assertEqual(clean_html('a:\n "b"'), 'a: "b"')
self.assertEqual(clean_html('a<br>\xa0b'), 'a\nb')
def test_intlist_to_bytes(self):
self.assertEqual(
intlist_to_bytes([0, 1, 127, 128, 255]),
b'\x00\x01\x7f\x80\xff')
def test_args_to_str(self):
self.assertEqual(
args_to_str(['foo', 'ba/r', '-baz', '2 be', '']),
'foo ba/r -baz \'2 be\' \'\'' if compat_os_name != 'nt' else 'foo ba/r -baz "2 be" ""',
'foo ba/r -baz \'2 be\' \'\'' if os.name != 'nt' else 'foo ba/r -baz "2 be" ""',
)
def test_parse_filesize(self):
@@ -2067,21 +2088,26 @@ Line 1
headers = HTTPHeaderDict()
headers['ytdl-test'] = b'0'
self.assertEqual(list(headers.items()), [('Ytdl-Test', '0')])
self.assertEqual(list(headers.sensitive().items()), [('ytdl-test', '0')])
headers['ytdl-test'] = 1
self.assertEqual(list(headers.items()), [('Ytdl-Test', '1')])
self.assertEqual(list(headers.sensitive().items()), [('ytdl-test', '1')])
headers['Ytdl-test'] = '2'
self.assertEqual(list(headers.items()), [('Ytdl-Test', '2')])
self.assertEqual(list(headers.sensitive().items()), [('Ytdl-test', '2')])
self.assertTrue('ytDl-Test' in headers)
self.assertEqual(str(headers), str(dict(headers)))
self.assertEqual(repr(headers), str(dict(headers)))
headers.update({'X-dlp': 'data'})
self.assertEqual(set(headers.items()), {('Ytdl-Test', '2'), ('X-Dlp', 'data')})
self.assertEqual(set(headers.sensitive().items()), {('Ytdl-test', '2'), ('X-dlp', 'data')})
self.assertEqual(dict(headers), {'Ytdl-Test': '2', 'X-Dlp': 'data'})
self.assertEqual(len(headers), 2)
self.assertEqual(headers.copy(), headers)
headers2 = HTTPHeaderDict({'X-dlp': 'data3'}, **headers, **{'X-dlp': 'data2'})
headers2 = HTTPHeaderDict({'X-dlp': 'data3'}, headers, **{'X-dlP': 'data2'})
self.assertEqual(set(headers2.items()), {('Ytdl-Test', '2'), ('X-Dlp', 'data2')})
self.assertEqual(set(headers2.sensitive().items()), {('Ytdl-test', '2'), ('X-dlP', 'data2')})
self.assertEqual(len(headers2), 2)
headers2.clear()
self.assertEqual(len(headers2), 0)
@@ -2089,16 +2115,23 @@ Line 1
# ensure we prefer latter headers
headers3 = HTTPHeaderDict({'Ytdl-TeSt': 1}, {'Ytdl-test': 2})
self.assertEqual(set(headers3.items()), {('Ytdl-Test', '2')})
self.assertEqual(set(headers3.sensitive().items()), {('Ytdl-test', '2')})
del headers3['ytdl-tesT']
self.assertEqual(dict(headers3), {})
headers4 = HTTPHeaderDict({'ytdl-test': 'data;'})
self.assertEqual(set(headers4.items()), {('Ytdl-Test', 'data;')})
self.assertEqual(set(headers4.sensitive().items()), {('ytdl-test', 'data;')})
# common mistake: strip whitespace from values
# https://github.com/yt-dlp/yt-dlp/issues/8729
headers5 = HTTPHeaderDict({'ytdl-test': ' data; '})
self.assertEqual(set(headers5.items()), {('Ytdl-Test', 'data;')})
self.assertEqual(set(headers5.sensitive().items()), {('ytdl-test', 'data;')})
# test if picklable
headers6 = HTTPHeaderDict(a=1, b=2)
self.assertEqual(pickle.loads(pickle.dumps(headers6)), headers6)
def test_extract_basic_auth(self):
assert extract_basic_auth('http://:foo.bar') == ('http://:foo.bar', None)
@@ -2108,7 +2141,7 @@ Line 1
assert extract_basic_auth('http://user:@foo.bar') == ('http://foo.bar', 'Basic dXNlcjo=')
assert extract_basic_auth('http://user:pass@foo.bar') == ('http://foo.bar', 'Basic dXNlcjpwYXNz')
@unittest.skipUnless(compat_os_name == 'nt', 'Only relevant on Windows')
@unittest.skipUnless(os.name == 'nt', 'Only relevant on Windows')
def test_windows_escaping(self):
tests = [
'test"&',
@@ -2142,6 +2175,12 @@ Line 1
assert run_shell(args) == expected
assert run_shell(shell_quote(args, shell=True)) == expected
def test_partial_application(self):
assert callable(int_or_none(scale=10)), 'missing positional parameter should apply partially'
assert int_or_none(10, scale=0.1) == 100, 'positionally passed argument should call function'
assert int_or_none(v=10) == 10, 'keyword passed positional should call function'
assert int_or_none(scale=0.1)(10) == 100, 'call after partial application should call the function'
if __name__ == '__main__':
unittest.main()

22
test/test_websockets.py
View File

@@ -44,7 +44,7 @@ def websocket_handler(websocket):
return websocket.send('2')
elif isinstance(message, str):
if message == 'headers':
return websocket.send(json.dumps(dict(websocket.request.headers)))
return websocket.send(json.dumps(dict(websocket.request.headers.raw_items())))
elif message == 'path':
return websocket.send(websocket.request.path)
elif message == 'source_address':
@@ -266,18 +266,18 @@ class TestWebsSocketRequestHandlerConformance:
with handler(cookiejar=cookiejar) as rh:
ws = ws_validate_and_send(rh, Request(self.ws_base_url))
ws.send('headers')
assert json.loads(ws.recv())['cookie'] == 'test=ytdlp'
assert HTTPHeaderDict(json.loads(ws.recv()))['cookie'] == 'test=ytdlp'
ws.close()
with handler() as rh:
ws = ws_validate_and_send(rh, Request(self.ws_base_url))
ws.send('headers')
assert 'cookie' not in json.loads(ws.recv())
assert 'cookie' not in HTTPHeaderDict(json.loads(ws.recv()))
ws.close()
ws = ws_validate_and_send(rh, Request(self.ws_base_url, extensions={'cookiejar': cookiejar}))
ws.send('headers')
assert json.loads(ws.recv())['cookie'] == 'test=ytdlp'
assert HTTPHeaderDict(json.loads(ws.recv()))['cookie'] == 'test=ytdlp'
ws.close()
@pytest.mark.skip_handler('Websockets', 'Set-Cookie not supported by websockets')
@@ -287,7 +287,7 @@ class TestWebsSocketRequestHandlerConformance:
ws_validate_and_send(rh, Request(f'{self.ws_base_url}/get_cookie', extensions={'cookiejar': YoutubeDLCookieJar()}))
ws = ws_validate_and_send(rh, Request(self.ws_base_url, extensions={'cookiejar': YoutubeDLCookieJar()}))
ws.send('headers')
assert 'cookie' not in json.loads(ws.recv())
assert 'cookie' not in HTTPHeaderDict(json.loads(ws.recv()))
ws.close()
@pytest.mark.skip_handler('Websockets', 'Set-Cookie not supported by websockets')
@@ -298,12 +298,12 @@ class TestWebsSocketRequestHandlerConformance:
ws_validate_and_send(rh, Request(f'{self.ws_base_url}/get_cookie'))
ws = ws_validate_and_send(rh, Request(self.ws_base_url))
ws.send('headers')
assert json.loads(ws.recv())['cookie'] == 'test=ytdlp'
assert HTTPHeaderDict(json.loads(ws.recv()))['cookie'] == 'test=ytdlp'
ws.close()
cookiejar.clear_session_cookies()
ws = ws_validate_and_send(rh, Request(self.ws_base_url))
ws.send('headers')
assert 'cookie' not in json.loads(ws.recv())
assert 'cookie' not in HTTPHeaderDict(json.loads(ws.recv()))
ws.close()
def test_source_address(self, handler):
@@ -341,6 +341,14 @@ class TestWebsSocketRequestHandlerConformance:
assert headers['test3'] == 'test3'
ws.close()
def test_keep_header_casing(self, handler):
with handler(headers=HTTPHeaderDict({'x-TeSt1': 'test'})) as rh:
ws = ws_validate_and_send(rh, Request(self.ws_base_url, headers={'x-TeSt2': 'test'}, extensions={'keep_header_casing': True}))
ws.send('headers')
headers = json.loads(ws.recv())
assert 'x-TeSt1' in headers
assert 'x-TeSt2' in headers
@pytest.mark.parametrize('client_cert', (
{'client_certificate': os.path.join(MTLS_CERT_DIR, 'clientwithkey.crt')},
{

29
test/test_youtube_signature.py
View File

@@ -68,6 +68,16 @@ _SIG_TESTS = [
'2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
'AOq0QJ8wRAIgXmPlOPSBkkUs1bYFYlJCfe29xx8j7v1pDL2QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJoOySqa0',
),
(
'https://www.youtube.com/s/player/3bb1f723/player_ias.vflset/en_US/base.js',
'2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
'MyOSJXtKI3m-uME_jv7-pT12gOFC02RFkGoqWpzE0Cs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
),
(
'https://www.youtube.com/s/player/2f1832d2/player_ias.vflset/en_US/base.js',
'2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
'0QJ8wRAIgXmPlOPSBkkUs1bYFYlJCfe29xxAj7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJ2OySqa0q',
),
]
_NSIG_TESTS = [
@@ -183,6 +193,18 @@ _NSIG_TESTS = [
'https://www.youtube.com/s/player/b12cc44b/player_ias.vflset/en_US/base.js',
'keLa5R2U00sR9SQK', 'N1OGyujjEwMnLw',
),
(
'https://www.youtube.com/s/player/3bb1f723/player_ias.vflset/en_US/base.js',
'gK15nzVyaXE9RsMP3z', 'ZFFWFLPWx9DEgQ',
),
(
'https://www.youtube.com/s/player/2f1832d2/player_ias.vflset/en_US/base.js',
'YWt1qdbe8SAfkoPHW5d', 'RrRjWQOJmBiP',
),
(
'https://www.youtube.com/s/player/9c6dfc4a/player_ias.vflset/en_US/base.js',
'jbu7ylIosQHyJyJV', 'uwI0ESiynAmhNg',
),
]
@@ -254,8 +276,11 @@ def signature(jscode, sig_input):
def n_sig(jscode, sig_input):
funcname = YoutubeIE(FakeYDL())._extract_n_function_name(jscode)
return JSInterpreter(jscode).call_function(funcname, sig_input)
ie = YoutubeIE(FakeYDL())
funcname = ie._extract_n_function_name(jscode)
jsi = JSInterpreter(jscode)
func = jsi.extract_function_from_code(*ie._fixup_n_function_code(*jsi.extract_function_code(funcname)))
return func([sig_input])
make_sig_test = t_factory(

4
test/testdata/netrc/netrc vendored Normal file
View File

@@ -0,0 +1,4 @@
machine normal_use login user password pass
machine empty_user login "" password pass
machine empty_pass login user password ""
machine both_empty login "" password ""

2
test/testdata/netrc/print_netrc.py vendored Normal file
View File

@@ -0,0 +1,2 @@
with open('./test/testdata/netrc/netrc', encoding='utf-8') as fp:
print(fp.read())

6
test/testdata/plugin_packages/testpackage/yt_dlp_plugins/extractor/package.py vendored Normal file
View File

@@ -0,0 +1,6 @@
from yt_dlp.extractor.common import InfoExtractor
class PackagePluginIE(InfoExtractor):
_VALID_URL = 'package'
pass

10
test/testdata/reload_plugins/yt_dlp_plugins/extractor/normal.py vendored Normal file
View File

@@ -0,0 +1,10 @@
from yt_dlp.extractor.common import InfoExtractor
class NormalPluginIE(InfoExtractor):
_VALID_URL = 'normal'
REPLACED = True
class _IgnoreUnderscorePluginIE(InfoExtractor):
pass

5
test/testdata/reload_plugins/yt_dlp_plugins/postprocessor/normal.py vendored Normal file
View File

@@ -0,0 +1,5 @@
from yt_dlp.postprocessor.common import PostProcessor
class NormalPluginPP(PostProcessor):
REPLACED = True

1
test/testdata/yt_dlp_plugins/extractor/ignore.py vendored
View File

@@ -6,6 +6,7 @@ class IgnoreNotInAllPluginIE(InfoExtractor):
class InAllPluginIE(InfoExtractor):
_VALID_URL = 'inallpluginie'
pass

4
test/testdata/yt_dlp_plugins/extractor/normal.py vendored
View File

@@ -2,8 +2,10 @@ from yt_dlp.extractor.common import InfoExtractor
class NormalPluginIE(InfoExtractor):
pass
_VALID_URL = 'normalpluginie'
REPLACED = False
class _IgnoreUnderscorePluginIE(InfoExtractor):
_VALID_URL = 'ignoreunderscorepluginie'
pass

5
test/testdata/yt_dlp_plugins/extractor/override.py vendored Normal file
View File

@@ -0,0 +1,5 @@
from yt_dlp.extractor.generic import GenericIE
class OverrideGenericIE(GenericIE, plugin_name='override'):
TEST_FIELD = 'override'

5
test/testdata/yt_dlp_plugins/extractor/overridetwo.py vendored Normal file
View File

@@ -0,0 +1,5 @@
from yt_dlp.extractor.generic import GenericIE
class _UnderscoreOverrideGenericIE(GenericIE, plugin_name='underscore-override'):
SECONDARY_TEST_FIELD = 'underscore-override'

2
test/testdata/yt_dlp_plugins/postprocessor/normal.py vendored
View File

@@ -2,4 +2,4 @@ from yt_dlp.postprocessor.common import PostProcessor
class NormalPluginPP(PostProcessor):
pass
REPLACED = False

1
test/testdata/zipped_plugins/yt_dlp_plugins/extractor/zipped.py vendored
View File

@@ -2,4 +2,5 @@ from yt_dlp.extractor.common import InfoExtractor
class ZippedPluginIE(InfoExtractor):
_VALID_URL = 'zippedpluginie'
pass