Compare commits

...

9 Commits

Author SHA1 Message Date
HobbyistDev 2002d3990d
Merge 4741aded6f into 64766459e3 2024-04-28 02:45:07 +05:30
Simon Sawicki 64766459e3
[core/windows] Improve shell quoting and tests (#9802)
Authored by: Grub4K
2024-04-27 10:37:26 +02:00
HobbyistDev 4741aded6f add `md5` key for mp4 link test case 2024-04-11 08:01:24 +08:00
HobbyistDev d493ce72b6 Change test value 2024-04-11 07:29:12 +08:00
HobbyistDev f326e05e9f Add `formats` and `subtitles` in return 2024-04-11 07:25:54 +08:00
HobbyistDev 89cb7f7d98
Simplify extraction process
Co-authored-by: pukkandan <pukkandan.ytdlp@gmail.com>
2024-04-11 07:22:56 +08:00
HobbyistDev 08563a1cad
Remove unneccassry `webpage` extraction
Co-authored-by: pukkandan <pukkandan.ytdlp@gmail.com>
2024-04-11 07:22:28 +08:00
HobbyistDev 6c311b14c6
Use auto-generated title instead of `title` tag of the website
Co-authored-by: pukkandan <pukkandan.ytdlp@gmail.com>
2024-04-11 07:21:59 +08:00
HobbyistDev eb2969d324 [extractor/godresource] Add GodResource extractor 2024-04-06 13:19:42 +08:00
4 changed files with 111 additions and 22 deletions

View File

@ -2059,7 +2059,22 @@ Line 1
assert extract_basic_auth('http://user:pass@foo.bar') == ('http://foo.bar', 'Basic dXNlcjpwYXNz')
@unittest.skipUnless(compat_os_name == 'nt', 'Only relevant on Windows')
def test_Popen_windows_escaping(self):
def test_windows_escaping(self):
tests = [
'test"&',
'%CMDCMDLINE:~-1%&',
'a\nb',
'"',
'\\',
'!',
'^!',
'a \\ b',
'a \\" b',
'a \\ b\\',
# We replace \r with \n
('a\r\ra', 'a\n\na'),
]
def run_shell(args):
stdout, stderr, error = Popen.run(
args, text=True, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
@ -2067,15 +2082,18 @@ Line 1
assert not error
return stdout
# Test escaping
assert run_shell(['echo', 'test"&']) == '"test""&"\n'
assert run_shell(['echo', '%CMDCMDLINE:~-1%&']) == '"%CMDCMDLINE:~-1%&"\n'
assert run_shell(['echo', 'a\nb']) == '"a"\n"b"\n'
assert run_shell(['echo', '"']) == '""""\n'
assert run_shell(['echo', '\\']) == '\\\n'
# Test if delayed expansion is disabled
assert run_shell(['echo', '^!']) == '"^!"\n'
assert run_shell('echo "^!"') == '"^!"\n'
for argument in tests:
if isinstance(argument, str):
expected = argument
else:
argument, expected = argument
args = [sys.executable, '-c', 'import sys; print(end=sys.argv[1])', argument, 'end']
assert run_shell(args) == expected
escaped = shell_quote(argument, shell=True)
args = f'{sys.executable} -c "import sys; print(end=sys.argv[1])" {escaped} end'
assert run_shell(args) == expected
if __name__ == '__main__':

View File

@ -713,6 +713,7 @@ from .globo import (
from .gmanetwork import GMANetworkVideoIE
from .go import GoIE
from .godtube import GodTubeIE
from .godresource import GodResourceIE
from .gofile import GofileIE
from .golem import GolemIE
from .goodgame import GoodGameIE

View File

@ -0,0 +1,77 @@
from .common import InfoExtractor
from ..utils import (
ExtractorError,
determine_ext,
str_or_none,
unified_timestamp,
url_or_none
)
from ..utils.traversal import traverse_obj
class GodResourceIE(InfoExtractor):
_VALID_URL = r'https?://new\.godresource\.com/video/(?P<id>\w+)'
_TESTS = [{
# hls stream
'url': 'https://new.godresource.com/video/A01mTKjyf6w',
'info_dict': {
'id': 'A01mTKjyf6w',
'ext': 'mp4',
'view_count': int,
'timestamp': 1710978666,
'channel_id': '5',
'thumbnail': 'https://cdn-02.godresource.com/e42968ac-9e8b-4231-ab86-f4f9d775841f/thumbnail.jpg',
'channel': 'Stedfast Baptist Church',
'upload_date': '20240320',
'title': 'GodResource video #A01mTKjyf6w',
}
}, {
# mp4 link
'url': 'https://new.godresource.com/video/01DXmBbQv_X',
'md5': '0e8f72aa89a106b9d5c011ba6f8717b7',
'info_dict': {
'id': '01DXmBbQv_X',
'ext': 'mp4',
'channel_id': '12',
'view_count': int,
'timestamp': 1687996800,
'thumbnail': 'https://cdn-02.godresource.com/sodomitedeception/thumbnail.jpg',
'channel': 'Documentaries',
'title': 'The Sodomite Deception',
'upload_date': '20230629',
}
}]
def _real_extract(self, url):
display_id = self._match_id(url)
api_data = self._download_json(
f'https://api.godresource.com/api/Streams/{display_id}', display_id)
video_url = api_data['streamUrl']
if (ext := determine_ext(video_url)) == 'm3u8':
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
api_data['streamUrl'], display_id)
elif ext == 'mp4':
formats, subtitles = [{
'url': video_url,
'ext': ext
}], {}
else:
raise ExtractorError(f'Unexpected video format {ext}')
return {
'id': display_id,
'formats': formats,
'subtitles': subtitles,
'title': '',
**traverse_obj(api_data, {
'title': ('title', {str}),
'thumbnail': ('thumbnail', {url_or_none}),
'view_count': ('views', {int}),
'channel': ('channelName', {str}),
'channel_id': ('channelId', {str_or_none}),
'timestamp': ('streamDateCreated', {unified_timestamp}),
'modified_timestamp': ('streamDataModified', {unified_timestamp})
})
}

View File

@ -1638,16 +1638,14 @@ def get_filesystem_encoding():
return encoding if encoding is not None else 'utf-8'
_WINDOWS_QUOTE_TRANS = str.maketrans({'"': '\\"', '\\': '\\\\'})
_WINDOWS_QUOTE_TRANS = str.maketrans({'"': R'\"'})
_CMD_QUOTE_TRANS = str.maketrans({
# Keep quotes balanced by replacing them with `""` instead of `\\"`
'"': '""',
# Requires a variable `=` containing `"^\n\n"` (set in `utils.Popen`)
# These require an env-variable `=` containing `"^\n\n"` (set in `utils.Popen`)
# `=` should be unique since variables containing `=` cannot be set using cmd
'\n': '%=%',
# While we are only required to escape backslashes immediately before quotes,
# we instead escape all of 'em anyways to be consistent
'\\': '\\\\',
'\r': '%=%',
# Use zero length variable replacement so `%` doesn't get expanded
# `cd` is always set as long as extensions are enabled (`/E:ON` in `utils.Popen`)
'%': '%%cd:~,%',
@ -1656,19 +1654,14 @@ _CMD_QUOTE_TRANS = str.maketrans({
def shell_quote(args, *, shell=False):
args = list(variadic(args))
if any(isinstance(item, bytes) for item in args):
deprecation_warning('Passing bytes to utils.shell_quote is deprecated')
encoding = get_filesystem_encoding()
for index, item in enumerate(args):
if isinstance(item, bytes):
args[index] = item.decode(encoding)
if compat_os_name != 'nt':
return shlex.join(args)
trans = _CMD_QUOTE_TRANS if shell else _WINDOWS_QUOTE_TRANS
return ' '.join(
s if re.fullmatch(r'[\w#$*\-+./:?@\\]+', s, re.ASCII) else s.translate(trans).join('""')
s if re.fullmatch(r'[\w#$*\-+./:?@\\]+', s, re.ASCII)
else re.sub(r'(\\+)("|$)', r'\1\1\2', s).translate(trans).join('""')
for s in args)