+import enum
+import json
import os.path
import re
import subprocess
import sys
import time
+import uuid
from .fragment import FragmentFD
-from ..compat import compat_setenv, compat_str
+from ..compat import functools
from ..postprocessor.ffmpeg import EXT_TO_OUT_FORMATS, FFmpegPostProcessor
from ..utils import (
Popen,
+ RetryManager,
_configuration_args,
check_executable,
classproperty,
determine_ext,
encodeArgument,
encodeFilename,
+ find_available_port,
handle_youtubedl_headers,
remove_end,
+ sanitized_Request,
traverse_obj,
)
+class Features(enum.Enum):
+ TO_STDOUT = enum.auto()
+ MULTIPLE_FORMATS = enum.auto()
+
+
class ExternalFD(FragmentFD):
SUPPORTED_PROTOCOLS = ('http', 'https', 'ftp', 'ftps')
- can_download_to_stdout = False
+ SUPPORTED_FEATURES = ()
+ _CAPTURE_STDERR = True
def real_download(self, filename, info_dict):
self.report_destination(filename)
}
if filename != '-':
fsize = os.path.getsize(encodeFilename(tmpfilename))
- self.to_screen(f'\r[{self.get_basename()}] Downloaded {fsize} bytes')
self.try_rename(tmpfilename, filename)
status.update({
'downloaded_bytes': fsize,
def EXE_NAME(cls):
return cls.get_basename()
- @property
+ @functools.cached_property
def exe(self):
return self.EXE_NAME
@classmethod
def supports(cls, info_dict):
- return (
- (cls.can_download_to_stdout or not info_dict.get('to_stdout'))
- and info_dict['protocol'] in cls.SUPPORTED_PROTOCOLS)
+ return all((
+ not info_dict.get('to_stdout') or Features.TO_STDOUT in cls.SUPPORTED_FEATURES,
+ '+' not in info_dict['protocol'] or Features.MULTIPLE_FORMATS in cls.SUPPORTED_FEATURES,
+ all(proto in cls.SUPPORTED_PROTOCOLS for proto in info_dict['protocol'].split('+')),
+ ))
@classmethod
def can_download(cls, info_dict, path=None):
self._debug_cmd(cmd)
if 'fragments' not in info_dict:
- p = Popen(cmd, stderr=subprocess.PIPE)
- _, stderr = p.communicate_or_kill()
- if p.returncode != 0:
- self.to_stderr(stderr.decode('utf-8', 'replace'))
- return p.returncode
+ _, stderr, returncode = self._call_process(cmd, info_dict)
+ if returncode and stderr:
+ self.to_stderr(stderr)
+ return returncode
- fragment_retries = self.params.get('fragment_retries', 0)
skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
- count = 0
- while count <= fragment_retries:
- p = Popen(cmd, stderr=subprocess.PIPE)
- _, stderr = p.communicate_or_kill()
- if p.returncode == 0:
+ retry_manager = RetryManager(self.params.get('fragment_retries'), self.report_retry,
+ frag_index=None, fatal=not skip_unavailable_fragments)
+ for retry in retry_manager:
+ _, stderr, returncode = self._call_process(cmd, info_dict)
+ if not returncode:
break
# TODO: Decide whether to retry based on error code
# https://aria2.github.io/manual/en/html/aria2c.html#exit-status
- self.to_stderr(stderr.decode('utf-8', 'replace'))
- count += 1
- if count <= fragment_retries:
- self.to_screen(
- '[%s] Got error. Retrying fragments (attempt %d of %s)...'
- % (self.get_basename(), count, self.format_retries(fragment_retries)))
- if count > fragment_retries:
- if not skip_unavailable_fragments:
- self.report_error('Giving up after %s fragment retries' % fragment_retries)
- return -1
+ if stderr:
+ self.to_stderr(stderr)
+ retry.error = Exception()
+ continue
+ if not skip_unavailable_fragments and retry_manager.error:
+ return -1
decrypt_fragment = self.decrypter(info_dict)
dest, _ = self.sanitize_open(tmpfilename, 'wb')
self.try_remove(encodeFilename('%s.frag.urls' % tmpfilename))
return 0
+ def _call_process(self, cmd, info_dict):
+ return Popen.run(cmd, text=True, stderr=subprocess.PIPE)
+
class CurlFD(ExternalFD):
AVAILABLE_OPT = '-V'
+ _CAPTURE_STDERR = False # curl writes the progress to stderr
def _make_cmd(self, tmpfilename, info_dict):
cmd = [self.exe, '--location', '-o', tmpfilename, '--compressed']
cmd += ['--', info_dict['url']]
return cmd
- def _call_downloader(self, tmpfilename, info_dict):
- cmd = [encodeArgument(a) for a in self._make_cmd(tmpfilename, info_dict)]
-
- self._debug_cmd(cmd)
-
- # curl writes the progress to stderr so don't capture it.
- p = Popen(cmd)
- p.communicate_or_kill()
- return p.returncode
-
class AxelFD(ExternalFD):
AVAILABLE_OPT = '-V'
check_results = (not re.search(feature, manifest) for feature in UNSUPPORTED_FEATURES)
return all(check_results)
+ @staticmethod
+ def _aria2c_filename(fn):
+ return fn if os.path.isabs(fn) else f'.{os.path.sep}{fn}'
+
+ def _call_downloader(self, tmpfilename, info_dict):
+ # FIXME: Disabled due to https://github.com/yt-dlp/yt-dlp/issues/5931
+ if False and 'no-external-downloader-progress' not in self.params.get('compat_opts', []):
+ info_dict['__rpc'] = {
+ 'port': find_available_port() or 19190,
+ 'secret': str(uuid.uuid4()),
+ }
+ return super()._call_downloader(tmpfilename, info_dict)
+
def _make_cmd(self, tmpfilename, info_dict):
cmd = [self.exe, '-c',
'--console-log-level=warn', '--summary-interval=0', '--download-result=hide',
cmd += self._bool_option('--show-console-readout', 'noprogress', 'false', 'true', '=')
cmd += self._configuration_args()
+ if '__rpc' in info_dict:
+ cmd += [
+ '--enable-rpc',
+ f'--rpc-listen-port={info_dict["__rpc"]["port"]}',
+ f'--rpc-secret={info_dict["__rpc"]["secret"]}']
+
# aria2c strips out spaces from the beginning/end of filenames and paths.
# We work around this issue by adding a "./" to the beginning of the
# filename and relative path, and adding a "/" at the end of the path.
# https://github.com/aria2/aria2/issues/1373
dn = os.path.dirname(tmpfilename)
if dn:
- if not os.path.isabs(dn):
- dn = f'.{os.path.sep}{dn}'
- cmd += ['--dir', dn + os.path.sep]
+ cmd += ['--dir', self._aria2c_filename(dn) + os.path.sep]
if 'fragments' not in info_dict:
- cmd += ['--out', f'.{os.path.sep}{os.path.basename(tmpfilename)}']
+ cmd += ['--out', self._aria2c_filename(os.path.basename(tmpfilename))]
cmd += ['--auto-file-renaming=false']
if 'fragments' in info_dict:
url_list = []
for frag_index, fragment in enumerate(info_dict['fragments']):
fragment_filename = '%s-Frag%d' % (os.path.basename(tmpfilename), frag_index)
- url_list.append('%s\n\tout=%s' % (fragment['url'], fragment_filename))
+ url_list.append('%s\n\tout=%s' % (fragment['url'], self._aria2c_filename(fragment_filename)))
stream, _ = self.sanitize_open(url_list_file, 'wb')
- stream.write('\n'.join(url_list).encode('utf-8'))
+ stream.write('\n'.join(url_list).encode())
stream.close()
- cmd += ['-i', url_list_file]
+ cmd += ['-i', self._aria2c_filename(url_list_file)]
else:
cmd += ['--', info_dict['url']]
return cmd
+ def aria2c_rpc(self, rpc_port, rpc_secret, method, params=()):
+ # Does not actually need to be UUID, just unique
+ sanitycheck = str(uuid.uuid4())
+ d = json.dumps({
+ 'jsonrpc': '2.0',
+ 'id': sanitycheck,
+ 'method': method,
+ 'params': [f'token:{rpc_secret}', *params],
+ }).encode('utf-8')
+ request = sanitized_Request(
+ f'http://localhost:{rpc_port}/jsonrpc',
+ data=d, headers={
+ 'Content-Type': 'application/json',
+ 'Content-Length': f'{len(d)}',
+ 'Ytdl-request-proxy': '__noproxy__',
+ })
+ with self.ydl.urlopen(request) as r:
+ resp = json.load(r)
+ assert resp.get('id') == sanitycheck, 'Something went wrong with RPC server'
+ return resp['result']
+
+ def _call_process(self, cmd, info_dict):
+ if '__rpc' not in info_dict:
+ return super()._call_process(cmd, info_dict)
+
+ send_rpc = functools.partial(self.aria2c_rpc, info_dict['__rpc']['port'], info_dict['__rpc']['secret'])
+ started = time.time()
+
+ fragmented = 'fragments' in info_dict
+ frag_count = len(info_dict['fragments']) if fragmented else 1
+ status = {
+ 'filename': info_dict.get('_filename'),
+ 'status': 'downloading',
+ 'elapsed': 0,
+ 'downloaded_bytes': 0,
+ 'fragment_count': frag_count if fragmented else None,
+ 'fragment_index': 0 if fragmented else None,
+ }
+ self._hook_progress(status, info_dict)
+
+ def get_stat(key, *obj, average=False):
+ val = tuple(filter(None, map(float, traverse_obj(obj, (..., ..., key))))) or [0]
+ return sum(val) / (len(val) if average else 1)
+
+ with Popen(cmd, text=True, stdout=subprocess.DEVNULL, stderr=subprocess.PIPE) as p:
+ # Add a small sleep so that RPC client can receive response,
+ # or the connection stalls infinitely
+ time.sleep(0.2)
+ retval = p.poll()
+ while retval is None:
+ # We don't use tellStatus as we won't know the GID without reading stdout
+ # Ref: https://aria2.github.io/manual/en/html/aria2c.html#aria2.tellActive
+ active = send_rpc('aria2.tellActive')
+ completed = send_rpc('aria2.tellStopped', [0, frag_count])
+
+ downloaded = get_stat('totalLength', completed) + get_stat('completedLength', active)
+ speed = get_stat('downloadSpeed', active)
+ total = frag_count * get_stat('totalLength', active, completed, average=True)
+ if total < downloaded:
+ total = None
+
+ status.update({
+ 'downloaded_bytes': int(downloaded),
+ 'speed': speed,
+ 'total_bytes': None if fragmented else total,
+ 'total_bytes_estimate': total,
+ 'eta': (total - downloaded) / (speed or 1),
+ 'fragment_index': min(frag_count, len(completed) + 1) if fragmented else None,
+ 'elapsed': time.time() - started
+ })
+ self._hook_progress(status, info_dict)
+
+ if not active and len(completed) >= frag_count:
+ send_rpc('aria2.shutdown')
+ retval = p.wait()
+ break
+
+ time.sleep(0.1)
+ retval = p.poll()
+
+ return '', p.stderr.read(), retval
+
class HttpieFD(ExternalFD):
AVAILABLE_OPT = '--version'
class FFmpegFD(ExternalFD):
SUPPORTED_PROTOCOLS = ('http', 'https', 'ftp', 'ftps', 'm3u8', 'm3u8_native', 'rtsp', 'rtmp', 'rtmp_ffmpeg', 'mms', 'http_dash_segments')
- can_download_to_stdout = True
+ SUPPORTED_FEATURES = (Features.TO_STDOUT, Features.MULTIPLE_FORMATS)
@classmethod
def available(cls, path=None):
# Fixme: This may be wrong when --ffmpeg-location is used
return FFmpegPostProcessor().available
- @classmethod
- def supports(cls, info_dict):
- return all(proto in cls.SUPPORTED_PROTOCOLS for proto in info_dict['protocol'].split('+'))
-
def on_process_started(self, proc, stdin):
""" Override this in subclasses """
pass
and cls.can_download(info_dict))
def _call_downloader(self, tmpfilename, info_dict):
- urls = [f['url'] for f in info_dict.get('requested_formats', [])] or [info_dict['url']]
ffpp = FFmpegPostProcessor(downloader=self)
if not ffpp.available:
self.report_error('m3u8 download detected but ffmpeg could not be found. Please install')
# http://trac.ffmpeg.org/ticket/6125#comment:10
args += ['-seekable', '1' if seekable else '0']
- # start_time = info_dict.get('start_time') or 0
- # if start_time:
- # args += ['-ss', compat_str(start_time)]
- # end_time = info_dict.get('end_time')
- # if end_time:
- # args += ['-t', compat_str(end_time - start_time)]
-
- http_headers = None
- if info_dict.get('http_headers'):
- youtubedl_headers = handle_youtubedl_headers(info_dict['http_headers'])
- http_headers = [
- # Trailing \r\n after each HTTP header is important to prevent warning from ffmpeg/avconv:
- # [http @ 00000000003d2fa0] No trailing CRLF found in HTTP header.
- '-headers',
- ''.join(f'{key}: {val}\r\n' for key, val in youtubedl_headers.items())
- ]
-
env = None
proxy = self.params.get('proxy')
if proxy:
# We could switch to the following code if we are able to detect version properly
# args += ['-http_proxy', proxy]
env = os.environ.copy()
- compat_setenv('HTTP_PROXY', proxy, env=env)
- compat_setenv('http_proxy', proxy, env=env)
+ env['HTTP_PROXY'] = proxy
+ env['http_proxy'] = proxy
protocol = info_dict.get('protocol')
if isinstance(conn, list):
for entry in conn:
args += ['-rtmp_conn', entry]
- elif isinstance(conn, compat_str):
+ elif isinstance(conn, str):
args += ['-rtmp_conn', conn]
- for i, url in enumerate(urls):
- # We need to specify headers for each http input stream
- # otherwise, it will only be applied to the first.
- # https://github.com/yt-dlp/yt-dlp/issues/2696
- if http_headers is not None and re.match(r'^https?://', url):
- args += http_headers
- args += self._configuration_args((f'_i{i + 1}', '_i')) + ['-i', url]
+ start_time, end_time = info_dict.get('section_start') or 0, info_dict.get('section_end')
+
+ selected_formats = info_dict.get('requested_formats') or [info_dict]
+ for i, fmt in enumerate(selected_formats):
+ if fmt.get('http_headers') and re.match(r'^https?://', fmt['url']):
+ headers_dict = handle_youtubedl_headers(fmt['http_headers'])
+ # Trailing \r\n after each HTTP header is important to prevent warning from ffmpeg/avconv:
+ # [http @ 00000000003d2fa0] No trailing CRLF found in HTTP header.
+ args.extend(['-headers', ''.join(f'{key}: {val}\r\n' for key, val in headers_dict.items())])
+
+ if start_time:
+ args += ['-ss', str(start_time)]
+ if end_time:
+ args += ['-t', str(end_time - start_time)]
+
+ args += self._configuration_args((f'_i{i + 1}', '_i')) + ['-i', fmt['url']]
+
+ if not (start_time or end_time) or not self.params.get('force_keyframes_at_cuts'):
+ args += ['-c', 'copy']
- args += ['-c', 'copy']
if info_dict.get('requested_formats') or protocol == 'http_dash_segments':
- for (i, fmt) in enumerate(info_dict.get('requested_formats') or [info_dict]):
+ for i, fmt in enumerate(selected_formats):
stream_number = fmt.get('manifest_stream_number', 0)
args.extend(['-map', f'{i}:{stream_number}'])
if self.params.get('test', False):
- args += ['-fs', compat_str(self._TEST_FILE_SIZE)]
+ args += ['-fs', str(self._TEST_FILE_SIZE)]
ext = info_dict['ext']
if protocol in ('m3u8', 'm3u8_native'):
args.append(encodeFilename(ffpp._ffmpeg_filename_argument(tmpfilename), True))
self._debug_cmd(args)
- proc = Popen(args, stdin=subprocess.PIPE, env=env)
- if url in ('-', 'pipe:'):
- self.on_process_started(proc, proc.stdin)
- try:
- retval = proc.wait()
- except BaseException as e:
- # subprocces.run would send the SIGKILL signal to ffmpeg and the
- # mp4 file couldn't be played, but if we ask ffmpeg to quit it
- # produces a file that is playable (this is mostly useful for live
- # streams). Note that Windows is not affected and produces playable
- # files (see https://github.com/ytdl-org/youtube-dl/issues/8300).
- if isinstance(e, KeyboardInterrupt) and sys.platform != 'win32' and url not in ('-', 'pipe:'):
- proc.communicate_or_kill(b'q')
- else:
- proc.kill()
- proc.wait()
- raise
- return retval
+ piped = any(fmt['url'] in ('-', 'pipe:') for fmt in selected_formats)
+ with Popen(args, stdin=subprocess.PIPE, env=env) as proc:
+ if piped:
+ self.on_process_started(proc, proc.stdin)
+ try:
+ retval = proc.wait()
+ except BaseException as e:
+ # subprocces.run would send the SIGKILL signal to ffmpeg and the
+ # mp4 file couldn't be played, but if we ask ffmpeg to quit it
+ # produces a file that is playable (this is mostly useful for live
+ # streams). Note that Windows is not affected and produces playable
+ # files (see https://github.com/ytdl-org/youtube-dl/issues/8300).
+ if isinstance(e, KeyboardInterrupt) and sys.platform != 'win32' and not piped:
+ proc.communicate_or_kill(b'q')
+ else:
+ proc.kill(timeout=None)
+ raise
+ return retval
class AVconvFD(FFmpegFD):
if name.endswith('FD') and name not in ('ExternalFD', 'FragmentFD')
}
-_BY_EXE = {klass.EXE_NAME: klass for klass in _BY_NAME.values()}
-
def list_external_downloaders():
return sorted(_BY_NAME.keys())
def get_external_downloader(external_downloader):
- """ Given the name of the executable, see whether we support the given
- downloader . """
- # Drop .exe extension on Windows
+ """ Given the name of the executable, see whether we support the given downloader """
bn = os.path.splitext(os.path.basename(external_downloader))[0]
- return _BY_NAME.get(bn, _BY_EXE.get(bn))
+ return _BY_NAME.get(bn) or next((
+ klass for klass in _BY_NAME.values() if klass.EXE_NAME in bn
+ ), None)
projects / yt-dlp.git / blobdiff