mirror of https://github.com/yt-dlp/yt-dlp
Merge branch 'yt-dlp:master' into pr/live-sections
bashonly
1 year ago
commit
54ad67d785
@ -0,0 +1,379 @@
|
||||
import abc
|
||||
import base64
|
||||
import contextlib
|
||||
import functools
|
||||
import json
|
||||
import os
|
||||
import random
|
||||
import ssl
|
||||
import threading
|
||||
from http.server import BaseHTTPRequestHandler
|
||||
from socketserver import ThreadingTCPServer
|
||||
|
||||
import pytest
|
||||
|
||||
from test.helper import http_server_port, verify_address_availability
|
||||
from test.test_networking import TEST_DIR
|
||||
from test.test_socks import IPv6ThreadingTCPServer
|
||||
from yt_dlp.dependencies import urllib3
|
||||
from yt_dlp.networking import Request
|
||||
from yt_dlp.networking.exceptions import HTTPError, ProxyError, SSLError
|
||||
|
||||
|
||||
class HTTPProxyAuthMixin:
|
||||
|
||||
def proxy_auth_error(self):
|
||||
self.send_response(407)
|
||||
self.send_header('Proxy-Authenticate', 'Basic realm="test http proxy"')
|
||||
self.end_headers()
|
||||
return False
|
||||
|
||||
def do_proxy_auth(self, username, password):
|
||||
if username is None and password is None:
|
||||
return True
|
||||
|
||||
proxy_auth_header = self.headers.get('Proxy-Authorization', None)
|
||||
if proxy_auth_header is None:
|
||||
return self.proxy_auth_error()
|
||||
|
||||
if not proxy_auth_header.startswith('Basic '):
|
||||
return self.proxy_auth_error()
|
||||
|
||||
auth = proxy_auth_header[6:]
|
||||
|
||||
try:
|
||||
auth_username, auth_password = base64.b64decode(auth).decode().split(':', 1)
|
||||
except Exception:
|
||||
return self.proxy_auth_error()
|
||||
|
||||
if auth_username != (username or '') or auth_password != (password or ''):
|
||||
return self.proxy_auth_error()
|
||||
return True
|
||||
|
||||
|
||||
class HTTPProxyHandler(BaseHTTPRequestHandler, HTTPProxyAuthMixin):
|
||||
def __init__(self, *args, proxy_info=None, username=None, password=None, request_handler=None, **kwargs):
|
||||
self.username = username
|
||||
self.password = password
|
||||
self.proxy_info = proxy_info
|
||||
super().__init__(*args, **kwargs)
|
||||
|
||||
def do_GET(self):
|
||||
if not self.do_proxy_auth(self.username, self.password):
|
||||
self.server.close_request(self.request)
|
||||
return
|
||||
if self.path.endswith('/proxy_info'):
|
||||
payload = json.dumps(self.proxy_info or {
|
||||
'client_address': self.client_address,
|
||||
'connect': False,
|
||||
'connect_host': None,
|
||||
'connect_port': None,
|
||||
'headers': dict(self.headers),
|
||||
'path': self.path,
|
||||
'proxy': ':'.join(str(y) for y in self.connection.getsockname()),
|
||||
})
|
||||
self.send_response(200)
|
||||
self.send_header('Content-Type', 'application/json; charset=utf-8')
|
||||
self.send_header('Content-Length', str(len(payload)))
|
||||
self.end_headers()
|
||||
self.wfile.write(payload.encode())
|
||||
else:
|
||||
self.send_response(404)
|
||||
self.end_headers()
|
||||
|
||||
self.server.close_request(self.request)
|
||||
|
||||
|
||||
if urllib3:
|
||||
import urllib3.util.ssltransport
|
||||
|
||||
class SSLTransport(urllib3.util.ssltransport.SSLTransport):
|
||||
"""
|
||||
Modified version of urllib3 SSLTransport to support server side SSL
|
||||
|
||||
This allows us to chain multiple TLS connections.
|
||||
"""
|
||||
def __init__(self, socket, ssl_context, server_hostname=None, suppress_ragged_eofs=True, server_side=False):
|
||||
self.incoming = ssl.MemoryBIO()
|
||||
self.outgoing = ssl.MemoryBIO()
|
||||
|
||||
self.suppress_ragged_eofs = suppress_ragged_eofs
|
||||
self.socket = socket
|
||||
|
||||
self.sslobj = ssl_context.wrap_bio(
|
||||
self.incoming,
|
||||
self.outgoing,
|
||||
server_hostname=server_hostname,
|
||||
server_side=server_side
|
||||
)
|
||||
self._ssl_io_loop(self.sslobj.do_handshake)
|
||||
|
||||
@property
|
||||
def _io_refs(self):
|
||||
return self.socket._io_refs
|
||||
|
||||
@_io_refs.setter
|
||||
def _io_refs(self, value):
|
||||
self.socket._io_refs = value
|
||||
|
||||
def shutdown(self, *args, **kwargs):
|
||||
self.socket.shutdown(*args, **kwargs)
|
||||
else:
|
||||
SSLTransport = None
|
||||
|
||||
|
||||
class HTTPSProxyHandler(HTTPProxyHandler):
|
||||
def __init__(self, request, *args, **kwargs):
|
||||
certfn = os.path.join(TEST_DIR, 'testcert.pem')
|
||||
sslctx = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
|
||||
sslctx.load_cert_chain(certfn, None)
|
||||
if isinstance(request, ssl.SSLSocket):
|
||||
request = SSLTransport(request, ssl_context=sslctx, server_side=True)
|
||||
else:
|
||||
request = sslctx.wrap_socket(request, server_side=True)
|
||||
super().__init__(request, *args, **kwargs)
|
||||
|
||||
|
||||
class HTTPConnectProxyHandler(BaseHTTPRequestHandler, HTTPProxyAuthMixin):
|
||||
protocol_version = 'HTTP/1.1'
|
||||
default_request_version = 'HTTP/1.1'
|
||||
|
||||
def __init__(self, *args, username=None, password=None, request_handler=None, **kwargs):
|
||||
self.username = username
|
||||
self.password = password
|
||||
self.request_handler = request_handler
|
||||
super().__init__(*args, **kwargs)
|
||||
|
||||
def do_CONNECT(self):
|
||||
if not self.do_proxy_auth(self.username, self.password):
|
||||
self.server.close_request(self.request)
|
||||
return
|
||||
self.send_response(200)
|
||||
self.end_headers()
|
||||
proxy_info = {
|
||||
'client_address': self.client_address,
|
||||
'connect': True,
|
||||
'connect_host': self.path.split(':')[0],
|
||||
'connect_port': int(self.path.split(':')[1]),
|
||||
'headers': dict(self.headers),
|
||||
'path': self.path,
|
||||
'proxy': ':'.join(str(y) for y in self.connection.getsockname()),
|
||||
}
|
||||
self.request_handler(self.request, self.client_address, self.server, proxy_info=proxy_info)
|
||||
self.server.close_request(self.request)
|
||||
|
||||
|
||||
class HTTPSConnectProxyHandler(HTTPConnectProxyHandler):
|
||||
def __init__(self, request, *args, **kwargs):
|
||||
certfn = os.path.join(TEST_DIR, 'testcert.pem')
|
||||
sslctx = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
|
||||
sslctx.load_cert_chain(certfn, None)
|
||||
request = sslctx.wrap_socket(request, server_side=True)
|
||||
self._original_request = request
|
||||
super().__init__(request, *args, **kwargs)
|
||||
|
||||
def do_CONNECT(self):
|
||||
super().do_CONNECT()
|
||||
self.server.close_request(self._original_request)
|
||||
|
||||
|
||||
@contextlib.contextmanager
|
||||
def proxy_server(proxy_server_class, request_handler, bind_ip=None, **proxy_server_kwargs):
|
||||
server = server_thread = None
|
||||
try:
|
||||
bind_address = bind_ip or '127.0.0.1'
|
||||
server_type = ThreadingTCPServer if '.' in bind_address else IPv6ThreadingTCPServer
|
||||
server = server_type(
|
||||
(bind_address, 0), functools.partial(proxy_server_class, request_handler=request_handler, **proxy_server_kwargs))
|
||||
server_port = http_server_port(server)
|
||||
server_thread = threading.Thread(target=server.serve_forever)
|
||||
server_thread.daemon = True
|
||||
server_thread.start()
|
||||
if '.' not in bind_address:
|
||||
yield f'[{bind_address}]:{server_port}'
|
||||
else:
|
||||
yield f'{bind_address}:{server_port}'
|
||||
finally:
|
||||
server.shutdown()
|
||||
server.server_close()
|
||||
server_thread.join(2.0)
|
||||
|
||||
|
||||
class HTTPProxyTestContext(abc.ABC):
|
||||
REQUEST_HANDLER_CLASS = None
|
||||
REQUEST_PROTO = None
|
||||
|
||||
def http_server(self, server_class, *args, **kwargs):
|
||||
return proxy_server(server_class, self.REQUEST_HANDLER_CLASS, *args, **kwargs)
|
||||
|
||||
@abc.abstractmethod
|
||||
def proxy_info_request(self, handler, target_domain=None, target_port=None, **req_kwargs) -> dict:
|
||||
"""return a dict of proxy_info"""
|
||||
|
||||
|
||||
class HTTPProxyHTTPTestContext(HTTPProxyTestContext):
|
||||
# Standard HTTP Proxy for http requests
|
||||
REQUEST_HANDLER_CLASS = HTTPProxyHandler
|
||||
REQUEST_PROTO = 'http'
|
||||
|
||||
def proxy_info_request(self, handler, target_domain=None, target_port=None, **req_kwargs):
|
||||
request = Request(f'http://{target_domain or "127.0.0.1"}:{target_port or "40000"}/proxy_info', **req_kwargs)
|
||||
handler.validate(request)
|
||||
return json.loads(handler.send(request).read().decode())
|
||||
|
||||
|
||||
class HTTPProxyHTTPSTestContext(HTTPProxyTestContext):
|
||||
# HTTP Connect proxy, for https requests
|
||||
REQUEST_HANDLER_CLASS = HTTPSProxyHandler
|
||||
REQUEST_PROTO = 'https'
|
||||
|
||||
def proxy_info_request(self, handler, target_domain=None, target_port=None, **req_kwargs):
|
||||
request = Request(f'https://{target_domain or "127.0.0.1"}:{target_port or "40000"}/proxy_info', **req_kwargs)
|
||||
handler.validate(request)
|
||||
return json.loads(handler.send(request).read().decode())
|
||||
|
||||
|
||||
CTX_MAP = {
|
||||
'http': HTTPProxyHTTPTestContext,
|
||||
'https': HTTPProxyHTTPSTestContext,
|
||||
}
|
||||
|
||||
|
||||
@pytest.fixture(scope='module')
|
||||
def ctx(request):
|
||||
return CTX_MAP[request.param]()
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
'handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
|
||||
@pytest.mark.parametrize('ctx', ['http'], indirect=True) # pure http proxy can only support http
|
||||
class TestHTTPProxy:
|
||||
def test_http_no_auth(self, handler, ctx):
|
||||
with ctx.http_server(HTTPProxyHandler) as server_address:
|
||||
with handler(proxies={ctx.REQUEST_PROTO: f'http://{server_address}'}) as rh:
|
||||
proxy_info = ctx.proxy_info_request(rh)
|
||||
assert proxy_info['proxy'] == server_address
|
||||
assert proxy_info['connect'] is False
|
||||
assert 'Proxy-Authorization' not in proxy_info['headers']
|
||||
|
||||
def test_http_auth(self, handler, ctx):
|
||||
with ctx.http_server(HTTPProxyHandler, username='test', password='test') as server_address:
|
||||
with handler(proxies={ctx.REQUEST_PROTO: f'http://test:test@{server_address}'}) as rh:
|
||||
proxy_info = ctx.proxy_info_request(rh)
|
||||
assert proxy_info['proxy'] == server_address
|
||||
assert 'Proxy-Authorization' in proxy_info['headers']
|
||||
|
||||
def test_http_bad_auth(self, handler, ctx):
|
||||
with ctx.http_server(HTTPProxyHandler, username='test', password='test') as server_address:
|
||||
with handler(proxies={ctx.REQUEST_PROTO: f'http://test:bad@{server_address}'}) as rh:
|
||||
with pytest.raises(HTTPError) as exc_info:
|
||||
ctx.proxy_info_request(rh)
|
||||
assert exc_info.value.response.status == 407
|
||||
exc_info.value.response.close()
|
||||
|
||||
def test_http_source_address(self, handler, ctx):
|
||||
with ctx.http_server(HTTPProxyHandler) as server_address:
|
||||
source_address = f'127.0.0.{random.randint(5, 255)}'
|
||||
verify_address_availability(source_address)
|
||||
with handler(proxies={ctx.REQUEST_PROTO: f'http://{server_address}'},
|
||||
source_address=source_address) as rh:
|
||||
proxy_info = ctx.proxy_info_request(rh)
|
||||
assert proxy_info['proxy'] == server_address
|
||||
assert proxy_info['client_address'][0] == source_address
|
||||
|
||||
@pytest.mark.skip_handler('Urllib', 'urllib does not support https proxies')
|
||||
def test_https(self, handler, ctx):
|
||||
with ctx.http_server(HTTPSProxyHandler) as server_address:
|
||||
with handler(verify=False, proxies={ctx.REQUEST_PROTO: f'https://{server_address}'}) as rh:
|
||||
proxy_info = ctx.proxy_info_request(rh)
|
||||
assert proxy_info['proxy'] == server_address
|
||||
assert proxy_info['connect'] is False
|
||||
assert 'Proxy-Authorization' not in proxy_info['headers']
|
||||
|
||||
@pytest.mark.skip_handler('Urllib', 'urllib does not support https proxies')
|
||||
def test_https_verify_failed(self, handler, ctx):
|
||||
with ctx.http_server(HTTPSProxyHandler) as server_address:
|
||||
with handler(verify=True, proxies={ctx.REQUEST_PROTO: f'https://{server_address}'}) as rh:
|
||||
# Accept SSLError as may not be feasible to tell if it is proxy or request error.
|
||||
# note: if request proto also does ssl verification, this may also be the error of the request.
|
||||
# Until we can support passing custom cacerts to handlers, we cannot properly test this for all cases.
|
||||
with pytest.raises((ProxyError, SSLError)):
|
||||
ctx.proxy_info_request(rh)
|
||||
|
||||
def test_http_with_idn(self, handler, ctx):
|
||||
with ctx.http_server(HTTPProxyHandler) as server_address:
|
||||
with handler(proxies={ctx.REQUEST_PROTO: f'http://{server_address}'}) as rh:
|
||||
proxy_info = ctx.proxy_info_request(rh, target_domain='中文.tw')
|
||||
assert proxy_info['proxy'] == server_address
|
||||
assert proxy_info['path'].startswith('http://xn--fiq228c.tw')
|
||||
assert proxy_info['headers']['Host'].split(':', 1)[0] == 'xn--fiq228c.tw'
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
'handler,ctx', [
|
||||
('Requests', 'https'),
|
||||
('CurlCFFI', 'https'),
|
||||
], indirect=True)
|
||||
class TestHTTPConnectProxy:
|
||||
def test_http_connect_no_auth(self, handler, ctx):
|
||||
with ctx.http_server(HTTPConnectProxyHandler) as server_address:
|
||||
with handler(verify=False, proxies={ctx.REQUEST_PROTO: f'http://{server_address}'}) as rh:
|
||||
proxy_info = ctx.proxy_info_request(rh)
|
||||
assert proxy_info['proxy'] == server_address
|
||||
assert proxy_info['connect'] is True
|
||||
assert 'Proxy-Authorization' not in proxy_info['headers']
|
||||
|
||||
def test_http_connect_auth(self, handler, ctx):
|
||||
with ctx.http_server(HTTPConnectProxyHandler, username='test', password='test') as server_address:
|
||||
with handler(verify=False, proxies={ctx.REQUEST_PROTO: f'http://test:test@{server_address}'}) as rh:
|
||||
proxy_info = ctx.proxy_info_request(rh)
|
||||
assert proxy_info['proxy'] == server_address
|
||||
assert 'Proxy-Authorization' in proxy_info['headers']
|
||||
|
||||
@pytest.mark.skip_handler(
|
||||
'Requests',
|
||||
'bug in urllib3 causes unclosed socket: https://github.com/urllib3/urllib3/issues/3374'
|
||||
)
|
||||
def test_http_connect_bad_auth(self, handler, ctx):
|
||||
with ctx.http_server(HTTPConnectProxyHandler, username='test', password='test') as server_address:
|
||||
with handler(verify=False, proxies={ctx.REQUEST_PROTO: f'http://test:bad@{server_address}'}) as rh:
|
||||
with pytest.raises(ProxyError):
|
||||
ctx.proxy_info_request(rh)
|
||||
|
||||
def test_http_connect_source_address(self, handler, ctx):
|
||||
with ctx.http_server(HTTPConnectProxyHandler) as server_address:
|
||||
source_address = f'127.0.0.{random.randint(5, 255)}'
|
||||
verify_address_availability(source_address)
|
||||
with handler(proxies={ctx.REQUEST_PROTO: f'http://{server_address}'},
|
||||
source_address=source_address,
|
||||
verify=False) as rh:
|
||||
proxy_info = ctx.proxy_info_request(rh)
|
||||
assert proxy_info['proxy'] == server_address
|
||||
assert proxy_info['client_address'][0] == source_address
|
||||
|
||||
@pytest.mark.skipif(urllib3 is None, reason='requires urllib3 to test')
|
||||
def test_https_connect_proxy(self, handler, ctx):
|
||||
with ctx.http_server(HTTPSConnectProxyHandler) as server_address:
|
||||
with handler(verify=False, proxies={ctx.REQUEST_PROTO: f'https://{server_address}'}) as rh:
|
||||
proxy_info = ctx.proxy_info_request(rh)
|
||||
assert proxy_info['proxy'] == server_address
|
||||
assert proxy_info['connect'] is True
|
||||
assert 'Proxy-Authorization' not in proxy_info['headers']
|
||||
|
||||
@pytest.mark.skipif(urllib3 is None, reason='requires urllib3 to test')
|
||||
def test_https_connect_verify_failed(self, handler, ctx):
|
||||
with ctx.http_server(HTTPSConnectProxyHandler) as server_address:
|
||||
with handler(verify=True, proxies={ctx.REQUEST_PROTO: f'https://{server_address}'}) as rh:
|
||||
# Accept SSLError as may not be feasible to tell if it is proxy or request error.
|
||||
# note: if request proto also does ssl verification, this may also be the error of the request.
|
||||
# Until we can support passing custom cacerts to handlers, we cannot properly test this for all cases.
|
||||
with pytest.raises((ProxyError, SSLError)):
|
||||
ctx.proxy_info_request(rh)
|
||||
|
||||
@pytest.mark.skipif(urllib3 is None, reason='requires urllib3 to test')
|
||||
def test_https_connect_proxy_auth(self, handler, ctx):
|
||||
with ctx.http_server(HTTPSConnectProxyHandler, username='test', password='test') as server_address:
|
||||
with handler(verify=False, proxies={ctx.REQUEST_PROTO: f'https://test:test@{server_address}'}) as rh:
|
||||
proxy_info = ctx.proxy_info_request(rh)
|
||||
assert proxy_info['proxy'] == server_address
|
||||
assert 'Proxy-Authorization' in proxy_info['headers']
|
||||
@ -1,32 +0,0 @@
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class CableAVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://cableav\.tv/(?P<id>[a-zA-Z0-9]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://cableav.tv/lS4iR9lWjN8/',
|
||||
'md5': '7e3fe5e49d61c4233b7f5b0f69b15e18',
|
||||
'info_dict': {
|
||||
'id': 'lS4iR9lWjN8',
|
||||
'ext': 'mp4',
|
||||
'title': '國產麻豆AV 叮叮映畫 DDF001 情欲小說家 - CableAV',
|
||||
'description': '國產AV 480p, 720p 国产麻豆AV 叮叮映画 DDF001 情欲小说家',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
}
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
video_url = self._og_search_video_url(webpage, secure=False)
|
||||
|
||||
formats = self._extract_m3u8_formats(video_url, video_id, 'mp4')
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': self._og_search_title(webpage),
|
||||
'description': self._og_search_description(webpage),
|
||||
'thumbnail': self._og_search_thumbnail(webpage),
|
||||
'formats': formats,
|
||||
}
|
||||
@ -1,105 +0,0 @@
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_b64decode,
|
||||
compat_str,
|
||||
compat_urlparse,
|
||||
)
|
||||
from ..utils import (
|
||||
extract_attributes,
|
||||
ExtractorError,
|
||||
get_elements_by_class,
|
||||
urlencode_postdata,
|
||||
)
|
||||
|
||||
|
||||
class EinthusanIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?P<host>einthusan\.(?:tv|com|ca))/movie/watch/(?P<id>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://einthusan.tv/movie/watch/9097/',
|
||||
'md5': 'ff0f7f2065031b8a2cf13a933731c035',
|
||||
'info_dict': {
|
||||
'id': '9097',
|
||||
'ext': 'mp4',
|
||||
'title': 'Ae Dil Hai Mushkil',
|
||||
'description': 'md5:33ef934c82a671a94652a9b4e54d931b',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
}
|
||||
}, {
|
||||
'url': 'https://einthusan.tv/movie/watch/51MZ/?lang=hindi',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://einthusan.com/movie/watch/9097/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://einthusan.ca/movie/watch/4E9n/?lang=hindi',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
# reversed from jsoncrypto.prototype.decrypt() in einthusan-PGMovieWatcher.js
|
||||
def _decrypt(self, encrypted_data, video_id):
|
||||
return self._parse_json(compat_b64decode((
|
||||
encrypted_data[:10] + encrypted_data[-1] + encrypted_data[12:-1]
|
||||
)).decode('utf-8'), video_id)
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = self._match_valid_url(url)
|
||||
host = mobj.group('host')
|
||||
video_id = mobj.group('id')
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
title = self._html_search_regex(r'<h3>([^<]+)</h3>', webpage, 'title')
|
||||
|
||||
player_params = extract_attributes(self._search_regex(
|
||||
r'(<section[^>]+id="UIVideoPlayer"[^>]+>)', webpage, 'player parameters'))
|
||||
|
||||
page_id = self._html_search_regex(
|
||||
'<html[^>]+data-pageid="([^"]+)"', webpage, 'page ID')
|
||||
video_data = self._download_json(
|
||||
'https://%s/ajax/movie/watch/%s/' % (host, video_id), video_id,
|
||||
data=urlencode_postdata({
|
||||
'xEvent': 'UIVideoPlayer.PingOutcome',
|
||||
'xJson': json.dumps({
|
||||
'EJOutcomes': player_params['data-ejpingables'],
|
||||
'NativeHLS': False
|
||||
}),
|
||||
'arcVersion': 3,
|
||||
'appVersion': 59,
|
||||
'gorilla.csrf.Token': page_id,
|
||||
}))['Data']
|
||||
|
||||
if isinstance(video_data, compat_str) and video_data.startswith('/ratelimited/'):
|
||||
raise ExtractorError(
|
||||
'Download rate reached. Please try again later.', expected=True)
|
||||
|
||||
ej_links = self._decrypt(video_data['EJLinks'], video_id)
|
||||
|
||||
formats = []
|
||||
|
||||
m3u8_url = ej_links.get('HLSLink')
|
||||
if m3u8_url:
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native'))
|
||||
|
||||
mp4_url = ej_links.get('MP4Link')
|
||||
if mp4_url:
|
||||
formats.append({
|
||||
'url': mp4_url,
|
||||
})
|
||||
|
||||
description = get_elements_by_class('synopsis', webpage)[0]
|
||||
thumbnail = self._html_search_regex(
|
||||
r'''<img[^>]+src=(["'])(?P<url>(?!\1).+?/moviecovers/(?!\1).+?)\1''',
|
||||
webpage, 'thumbnail url', fatal=False, group='url')
|
||||
if thumbnail is not None:
|
||||
thumbnail = compat_urlparse.urljoin(url, thumbnail)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'thumbnail': thumbnail,
|
||||
'description': description,
|
||||
}
|
||||
@ -0,0 +1,79 @@
|
||||
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']
|
||||
is_live = api_data.get('isLive') or False
|
||||
if (ext := determine_ext(video_url)) == 'm3u8':
|
||||
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
|
||||
video_url, display_id, live=is_live)
|
||||
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': '',
|
||||
'is_live': is_live,
|
||||
**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})
|
||||
})
|
||||
}
|
||||
@ -1,103 +0,0 @@
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
InAdvancePagedList,
|
||||
int_or_none,
|
||||
orderedSet,
|
||||
unified_strdate,
|
||||
)
|
||||
|
||||
|
||||
class JableIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?jable\.tv/videos/(?P<id>[\w-]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://jable.tv/videos/pppd-812/',
|
||||
'md5': 'f1537283a9bc073c31ff86ca35d9b2a6',
|
||||
'info_dict': {
|
||||
'id': 'pppd-812',
|
||||
'ext': 'mp4',
|
||||
'title': 'PPPD-812 只要表現好巨乳女教師吉根柚莉愛就獎勵學生們在白虎穴內射出精液',
|
||||
'description': 'md5:5b6d4199a854f62c5e56e26ccad19967',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'age_limit': 18,
|
||||
'like_count': int,
|
||||
'view_count': int,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://jable.tv/videos/apak-220/',
|
||||
'md5': '71f9239d69ced58ab74a816908847cc1',
|
||||
'info_dict': {
|
||||
'id': 'apak-220',
|
||||
'ext': 'mp4',
|
||||
'title': 'md5:5c3861b7cf80112a6e2b70bccf170824',
|
||||
'description': '',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'age_limit': 18,
|
||||
'like_count': int,
|
||||
'view_count': int,
|
||||
'upload_date': '20220319',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
formats = self._extract_m3u8_formats(
|
||||
self._search_regex(r'var\s+hlsUrl\s*=\s*\'([^\']+)', webpage, 'hls_url'), video_id, 'mp4', m3u8_id='hls')
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': self._og_search_title(webpage),
|
||||
'description': self._og_search_description(webpage, default=''),
|
||||
'thumbnail': self._og_search_thumbnail(webpage, default=None),
|
||||
'formats': formats,
|
||||
'age_limit': 18,
|
||||
'upload_date': unified_strdate(self._search_regex(
|
||||
r'class="inactive-color">\D+\s+(\d{4}-\d+-\d+)', webpage, 'upload_date', default=None)),
|
||||
'view_count': int_or_none(self._search_regex(
|
||||
r'#icon-eye"></use></svg>\n*<span class="mr-3">([\d ]+)',
|
||||
webpage, 'view_count', default='').replace(' ', '')),
|
||||
'like_count': int_or_none(self._search_regex(
|
||||
r'#icon-heart"></use></svg><span class="count">(\d+)', webpage, 'link_count', default=None)),
|
||||
}
|
||||
|
||||
|
||||
class JablePlaylistIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?jable\.tv/(?:categories|models|tags)/(?P<id>[\w-]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://jable.tv/models/kaede-karen/',
|
||||
'info_dict': {
|
||||
'id': 'kaede-karen',
|
||||
'title': '楓カレン',
|
||||
},
|
||||
'playlist_count': 34,
|
||||
}, {
|
||||
'url': 'https://jable.tv/categories/roleplay/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://jable.tv/tags/girl/',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
playlist_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, playlist_id)
|
||||
|
||||
def page_func(page_num):
|
||||
return [
|
||||
self.url_result(player_url, JableIE)
|
||||
for player_url in orderedSet(re.findall(
|
||||
r'href="(https://jable.tv/videos/[\w-]+/?)"',
|
||||
self._download_webpage(url, playlist_id, query={
|
||||
'mode': 'async',
|
||||
'from': page_num + 1,
|
||||
'function': 'get_block',
|
||||
'block_id': 'list_videos_common_videos_list',
|
||||
}, note=f'Downloading page {page_num + 1}')))]
|
||||
|
||||
return self.playlist_result(
|
||||
InAdvancePagedList(page_func, int_or_none(self._search_regex(
|
||||
r'from:(\d+)">[^<]+\s*»', webpage, 'last page number', default=1)), 24),
|
||||
playlist_id, self._search_regex(
|
||||
r'<h2 class="h3-md mb-1">([^<]+)', webpage, 'playlist title', default=None))
|
||||
@ -0,0 +1,76 @@
|
||||
from .common import InfoExtractor
|
||||
from ..utils import parse_iso8601, url_or_none
|
||||
from ..utils.traversal import traverse_obj
|
||||
|
||||
|
||||
class NTSLiveIE(InfoExtractor):
|
||||
IE_NAME = 'nts.live'
|
||||
_VALID_URL = r'https?://(?:www\.)?nts\.live/shows/[^/?#]+/episodes/(?P<id>[^/?#]+)'
|
||||
_TESTS = [
|
||||
{
|
||||
# embedded soundcloud
|
||||
'url': 'https://www.nts.live/shows/yu-su/episodes/yu-su-2nd-april-2024',
|
||||
'md5': 'b5444c04888c869d68758982de1a27d8',
|
||||
'info_dict': {
|
||||
'id': '1791563518',
|
||||
'ext': 'opus',
|
||||
'uploader_id': '995579326',
|
||||
'title': 'Pender Street Steppers & YU SU',
|
||||
'timestamp': 1712073600,
|
||||
'upload_date': '20240402',
|
||||
'thumbnail': 'https://i1.sndcdn.com/artworks-qKcNO0z0AQGGbv9s-GljJCw-original.jpg',
|
||||
'license': 'all-rights-reserved',
|
||||
'repost_count': int,
|
||||
'uploader_url': 'https://soundcloud.com/user-643553014',
|
||||
'uploader': 'NTS Latest',
|
||||
'description': 'md5:cd00ac535a63caaad722483ae3ff802a',
|
||||
'duration': 10784.157,
|
||||
'genres': ['Deep House', 'House', 'Leftfield Disco', 'Jazz Fusion', 'Dream Pop'],
|
||||
'modified_timestamp': 1712564687,
|
||||
'modified_date': '20240408',
|
||||
},
|
||||
},
|
||||
{
|
||||
# embedded mixcloud
|
||||
'url': 'https://www.nts.live/shows/absolute-fiction/episodes/absolute-fiction-23rd-july-2022',
|
||||
'info_dict': {
|
||||
'id': 'NTSRadio_absolute-fiction-23rd-july-2022',
|
||||
'ext': 'webm',
|
||||
'like_count': int,
|
||||
'title': 'Absolute Fiction',
|
||||
'comment_count': int,
|
||||
'uploader_url': 'https://www.mixcloud.com/NTSRadio/',
|
||||
'description': 'md5:ba49da971ae8d71ee45813c52c5e2a04',
|
||||
'tags': [],
|
||||
'duration': 3529,
|
||||
'timestamp': 1658588400,
|
||||
'repost_count': int,
|
||||
'upload_date': '20220723',
|
||||
'uploader_id': 'NTSRadio',
|
||||
'thumbnail': 'https://thumbnailer.mixcloud.com/unsafe/1024x1024/extaudio/5/1/a/d/ae3e-1be9-4fd4-983e-9c3294226eac',
|
||||
'uploader': 'Mixcloud NTS Radio',
|
||||
'genres': ['Minimal Synth', 'Post Punk', 'Industrial '],
|
||||
'modified_timestamp': 1658842165,
|
||||
'modified_date': '20220726',
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
},
|
||||
]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
data = self._search_json(r'window\._REACT_STATE_\s*=', webpage, 'react state', video_id)
|
||||
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
**traverse_obj(data, ('episode', {
|
||||
'url': ('audio_sources', ..., 'url', {url_or_none}, any),
|
||||
'title': ('name', {str}),
|
||||
'description': ('description', {str}),
|
||||
'genres': ('genres', ..., 'value', {str}),
|
||||
'timestamp': ('broadcast', {parse_iso8601}),
|
||||
'modified_timestamp': ('updated', {parse_iso8601}),
|
||||
})),
|
||||
}
|
||||
@ -1,198 +0,0 @@
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
decode_packed_codes,
|
||||
determine_ext,
|
||||
int_or_none,
|
||||
js_to_json,
|
||||
urlencode_postdata,
|
||||
)
|
||||
|
||||
|
||||
# based on openload_decode from 2bfeee69b976fe049761dd3012e30b637ee05a58
|
||||
def aa_decode(aa_code):
|
||||
symbol_table = [
|
||||
('7', '((ﾟｰﾟ) + (o^_^o))'),
|
||||
('6', '((o^_^o) +(o^_^o))'),
|
||||
('5', '((ﾟｰﾟ) + (ﾟΘﾟ))'),
|
||||
('2', '((o^_^o) - (ﾟΘﾟ))'),
|
||||
('4', '(ﾟｰﾟ)'),
|
||||
('3', '(o^_^o)'),
|
||||
('1', '(ﾟΘﾟ)'),
|
||||
('0', '(c^_^o)'),
|
||||
]
|
||||
delim = '(ﾟДﾟ)[ﾟεﾟ]+'
|
||||
ret = ''
|
||||
for aa_char in aa_code.split(delim):
|
||||
for val, pat in symbol_table:
|
||||
aa_char = aa_char.replace(pat, val)
|
||||
aa_char = aa_char.replace('+ ', '')
|
||||
m = re.match(r'^\d+', aa_char)
|
||||
if m:
|
||||
ret += chr(int(m.group(0), 8))
|
||||
else:
|
||||
m = re.match(r'^u([\da-f]+)', aa_char)
|
||||
if m:
|
||||
ret += chr(int(m.group(1), 16))
|
||||
return ret
|
||||
|
||||
|
||||
class XFileShareIE(InfoExtractor):
|
||||
_SITES = (
|
||||
(r'aparat\.cam', 'Aparat'),
|
||||
(r'clipwatching\.com', 'ClipWatching'),
|
||||
(r'gounlimited\.to', 'GoUnlimited'),
|
||||
(r'govid\.me', 'GoVid'),
|
||||
(r'holavid\.com', 'HolaVid'),
|
||||
(r'streamty\.com', 'Streamty'),
|
||||
(r'thevideobee\.to', 'TheVideoBee'),
|
||||
(r'uqload\.com', 'Uqload'),
|
||||
(r'vidbom\.com', 'VidBom'),
|
||||
(r'vidlo\.us', 'vidlo'),
|
||||
(r'vidlocker\.xyz', 'VidLocker'),
|
||||
(r'vidshare\.tv', 'VidShare'),
|
||||
(r'vup\.to', 'VUp'),
|
||||
(r'wolfstream\.tv', 'WolfStream'),
|
||||
(r'xvideosharing\.com', 'XVideoSharing'),
|
||||
)
|
||||
|
||||
IE_DESC = 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES))[1])
|
||||
_VALID_URL = (r'https?://(?:www\.)?(?P<host>%s)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
|
||||
% '|'.join(site for site in list(zip(*_SITES))[0]))
|
||||
_EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:%s)/embed-[0-9a-zA-Z]+.*?)\1' % '|'.join(site for site in list(zip(*_SITES))[0])]
|
||||
|
||||
_FILE_NOT_FOUND_REGEXES = (
|
||||
r'>(?:404 - )?File Not Found<',
|
||||
r'>The file was removed by administrator<',
|
||||
)
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://uqload.com/dltx1wztngdz',
|
||||
'md5': '3cfbb65e4c90e93d7b37bcb65a595557',
|
||||
'info_dict': {
|
||||
'id': 'dltx1wztngdz',
|
||||
'ext': 'mp4',
|
||||
'title': 'Rick Astley Never Gonna Give You mp4',
|
||||
'thumbnail': r're:https://.*\.jpg'
|
||||
}
|
||||
}, {
|
||||
'url': 'http://xvideosharing.com/fq65f94nd2ve',
|
||||
'md5': '4181f63957e8fe90ac836fa58dc3c8a6',
|
||||
'info_dict': {
|
||||
'id': 'fq65f94nd2ve',
|
||||
'ext': 'mp4',
|
||||
'title': 'sample',
|
||||
'thumbnail': r're:http://.*\.jpg',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://aparat.cam/n4d6dh0wvlpr',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://wolfstream.tv/nthme29v9u2x',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
host, video_id = self._match_valid_url(url).groups()
|
||||
|
||||
url = 'https://%s/' % host + ('embed-%s.html' % video_id if host in ('govid.me', 'vidlo.us') else video_id)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
if any(re.search(p, webpage) for p in self._FILE_NOT_FOUND_REGEXES):
|
||||
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
|
||||
|
||||
fields = self._hidden_inputs(webpage)
|
||||
|
||||
if fields.get('op') == 'download1':
|
||||
countdown = int_or_none(self._search_regex(
|
||||
r'<span id="countdown_str">(?:[Ww]ait)?\s*<span id="cxc">(\d+)</span>\s*(?:seconds?)?</span>',
|
||||
webpage, 'countdown', default=None))
|
||||
if countdown:
|
||||
self._sleep(countdown, video_id)
|
||||
|
||||
webpage = self._download_webpage(
|
||||
url, video_id, 'Downloading video page',
|
||||
data=urlencode_postdata(fields), headers={
|
||||
'Referer': url,
|
||||
'Content-type': 'application/x-www-form-urlencoded',
|
||||
})
|
||||
|
||||
title = (self._search_regex(
|
||||
(r'style="z-index: [0-9]+;">([^<]+)</span>',
|
||||
r'<td nowrap>([^<]+)</td>',
|
||||
r'h4-fine[^>]*>([^<]+)<',
|
||||
r'>Watch (.+)[ <]',
|
||||
r'<h2 class="video-page-head">([^<]+)</h2>',
|
||||
r'<h2 style="[^"]*color:#403f3d[^"]*"[^>]*>([^<]+)<', # streamin.to
|
||||
r'title\s*:\s*"([^"]+)"'), # govid.me
|
||||
webpage, 'title', default=None) or self._og_search_title(
|
||||
webpage, default=None) or video_id).strip()
|
||||
|
||||
for regex, func in (
|
||||
(r'(eval\(function\(p,a,c,k,e,d\){.+)', decode_packed_codes),
|
||||
(r'(ﾟ.+)', aa_decode)):
|
||||
obf_code = self._search_regex(regex, webpage, 'obfuscated code', default=None)
|
||||
if obf_code:
|
||||
webpage = webpage.replace(obf_code, func(obf_code))
|
||||
|
||||
formats = []
|
||||
|
||||
jwplayer_data = self._search_regex(
|
||||
[
|
||||
r'jwplayer\("[^"]+"\)\.load\(\[({.+?})\]\);',
|
||||
r'jwplayer\("[^"]+"\)\.setup\(({.+?})\);',
|
||||
], webpage,
|
||||
'jwplayer data', default=None)
|
||||
if jwplayer_data:
|
||||
jwplayer_data = self._parse_json(
|
||||
jwplayer_data.replace(r"\'", "'"), video_id, js_to_json)
|
||||
if jwplayer_data:
|
||||
formats = self._parse_jwplayer_data(
|
||||
jwplayer_data, video_id, False,
|
||||
m3u8_id='hls', mpd_id='dash')['formats']
|
||||
|
||||
if not formats:
|
||||
urls = []
|
||||
for regex in (
|
||||
r'(?:file|src)\s*:\s*(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1',
|
||||
r'file_link\s*=\s*(["\'])(?P<url>http(?:(?!\1).)+)\1',
|
||||
r'addVariable\((\\?["\'])file\1\s*,\s*(\\?["\'])(?P<url>http(?:(?!\2).)+)\2\)',
|
||||
r'<embed[^>]+src=(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1'):
|
||||
for mobj in re.finditer(regex, webpage):
|
||||
video_url = mobj.group('url')
|
||||
if video_url not in urls:
|
||||
urls.append(video_url)
|
||||
|
||||
sources = self._search_regex(
|
||||
r'sources\s*:\s*(\[(?!{)[^\]]+\])', webpage, 'sources', default=None)
|
||||
if sources:
|
||||
urls.extend(self._parse_json(sources, video_id))
|
||||
|
||||
formats = []
|
||||
for video_url in urls:
|
||||
if determine_ext(video_url) == 'm3u8':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
video_url, video_id, 'mp4',
|
||||
entry_protocol='m3u8_native', m3u8_id='hls',
|
||||
fatal=False))
|
||||
else:
|
||||
formats.append({
|
||||
'url': video_url,
|
||||
'format_id': 'sd',
|
||||
})
|
||||
|
||||
thumbnail = self._search_regex(
|
||||
[
|
||||
r'<video[^>]+poster="([^"]+)"',
|
||||
r'(?:image|poster)\s*:\s*["\'](http[^"\']+)["\'],',
|
||||
], webpage, 'thumbnail', default=None)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'thumbnail': thumbnail,
|
||||
'formats': formats,
|
||||
'http_headers': {'Referer': url}
|
||||
}
|
||||
@ -1,65 +0,0 @@
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
parse_duration,
|
||||
urljoin,
|
||||
)
|
||||
|
||||
|
||||
class YourPornIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?sxyprn\.com/post/(?P<id>[^/?#&.]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://sxyprn.com/post/57ffcb2e1179b.html',
|
||||
'md5': '6f8682b6464033d87acaa7a8ff0c092e',
|
||||
'info_dict': {
|
||||
'id': '57ffcb2e1179b',
|
||||
'ext': 'mp4',
|
||||
'title': 'md5:c9f43630bd968267672651ba905a7d35',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'duration': 165,
|
||||
'age_limit': 18,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://sxyprn.com/post/57ffcb2e1179b.html',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
parts = self._parse_json(
|
||||
self._search_regex(
|
||||
r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info',
|
||||
group='data'),
|
||||
video_id)[video_id].split('/')
|
||||
|
||||
num = 0
|
||||
for c in parts[6] + parts[7]:
|
||||
if c.isnumeric():
|
||||
num += int(c)
|
||||
parts[5] = compat_str(int(parts[5]) - num)
|
||||
parts[1] += '8'
|
||||
video_url = urljoin(url, '/'.join(parts))
|
||||
|
||||
title = (self._search_regex(
|
||||
r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title',
|
||||
default=None) or self._og_search_description(webpage)).strip()
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
duration = parse_duration(self._search_regex(
|
||||
r'duration\s*:\s*<[^>]+>([\d:]+)', webpage, 'duration',
|
||||
default=None))
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'title': title,
|
||||
'thumbnail': thumbnail,
|
||||
'duration': duration,
|
||||
'age_limit': 18,
|
||||
'ext': 'mp4',
|
||||
}
|
||||
@ -1,43 +0,0 @@
|
||||
from .common import InfoExtractor
|
||||
from ..utils import urljoin
|
||||
|
||||
|
||||
class YourUploadIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:yourupload\.com/(?:watch|embed)|embed\.yourupload\.com)/(?P<id>[A-Za-z0-9]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://yourupload.com/watch/14i14h',
|
||||
'md5': '5e2c63385454c557f97c4c4131a393cd',
|
||||
'info_dict': {
|
||||
'id': '14i14h',
|
||||
'ext': 'mp4',
|
||||
'title': 'BigBuckBunny_320x180.mp4',
|
||||
'thumbnail': r're:^https?://.*\.jpe?g',
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.yourupload.com/embed/14i14h',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://embed.yourupload.com/14i14h',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
embed_url = 'http://www.yourupload.com/embed/%s' % video_id
|
||||
|
||||
webpage = self._download_webpage(embed_url, video_id)
|
||||
|
||||
title = self._og_search_title(webpage)
|
||||
video_url = urljoin(embed_url, self._og_search_video_url(webpage))
|
||||
thumbnail = self._og_search_thumbnail(webpage, default=None)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'url': video_url,
|
||||
'thumbnail': thumbnail,
|
||||
'http_headers': {
|
||||
'Referer': embed_url,
|
||||
},
|
||||
}
|
||||
Loading…
Reference in New Issue