Merge 501c9d5267 into a9f85670d0

[ie/Chaturbate] Support alternate domains (#10595 )
Closes #10594 Authored by: manavchaudhary1
2024-11-26 09:11:25 +01:00 · 2024-11-12 13:40:11 -08:00 · 2024-11-11 23:41:56 +01:00 · 2024-11-11 22:03:31 +00:00 · 2024-11-11 22:00:05 +00:00 · 2024-11-11 21:19:03 +00:00
9 changed files with 493 additions and 51 deletions
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@ -411,7 +411,7 @@ jobs:
        run: | # Custom pyinstaller built with https://github.com/yt-dlp/pyinstaller-builds
          python devscripts/install_deps.py -o --include build
          python devscripts/install_deps.py --include curl-cffi
-          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/x86_64/pyinstaller-6.10.0-py3-none-any.whl"
+          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/x86_64/pyinstaller-6.11.1-py3-none-any.whl"

      - name: Prepare
        run: |
@ -460,7 +460,7 @@ jobs:
        run: |
          python devscripts/install_deps.py -o --include build
          python devscripts/install_deps.py
-          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/i686/pyinstaller-6.10.0-py3-none-any.whl"
+          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/i686/pyinstaller-6.11.1-py3-none-any.whl"

      - name: Prepare
        run: |
--- a/README.md
+++ b/README.md
@ -1869,6 +1869,10 @@ The following extractors use this feature:
 #### digitalconcerthall
 * `prefer_combined_hls`: Prefer extracting combined/pre-merged video and audio HLS formats. This will exclude 4K/HEVC video and lossless/FLAC audio formats, which are only available as split video/audio HLS formats

+#### rplaylive
+
+* `jwt_token`: JWT token that can be found as value of `_AUTHORIZATION_` entry from the browser local storage. This can be used as an alternative login method.
+
 **Note**: These options may be changed/removed in the future without concern for backward compatibility

 <!-- MANPAGE: MOVE "INSTALLATION" SECTION HERE -->
--- a/pyproject.toml
+++ b/pyproject.toml
@ -83,7 +83,7 @@ test = [
    "pytest-rerunfailures~=14.0",
 ]
 pyinstaller = [
-    "pyinstaller>=6.10.0",  # Windows temp cleanup fixed in 6.10.0
+    "pyinstaller>=6.11.1",  # Windows temp cleanup fixed in 6.11.1
 ]

 [project.urls]
--- a/yt_dlp/extractor/_extractors.py
+++ b/yt_dlp/extractor/_extractors.py
@ -1156,6 +1156,7 @@ from .mitele import MiTeleIE
 from .mixch import (
    MixchArchiveIE,
    MixchIE,
+    MixchMovieIE,
 )
 from .mixcloud import (
    MixcloudIE,
@ -1735,6 +1736,11 @@ from .rozhlas import (
    RozhlasIE,
    RozhlasVltavaIE,
 )
+from .rplaylive import (
+    RPlayLiveIE,
+    RPlayUserIE,
+    RPlayVideoIE,
+)
 from .rte import (
    RteIE,
    RteRadioIE,
--- a/yt_dlp/extractor/chaturbate.py
+++ b/yt_dlp/extractor/chaturbate.py
@ -9,7 +9,7 @@ from ..utils import (


 class ChaturbateIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?:fullvideo/?\?.*?\bb=)?(?P<id>[^/?&#]+)'
+    _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.(?P<tld>com|eu|global)/(?:fullvideo/?\?.*?\bb=)?(?P<id>[^/?&#]+)'
    _TESTS = [{
        'url': 'https://www.chaturbate.com/siswet19/',
        'info_dict': {
@ -29,15 +29,24 @@ class ChaturbateIE(InfoExtractor):
    }, {
        'url': 'https://en.chaturbate.com/siswet19/',
        'only_matching': True,
+    }, {
+        'url': 'https://chaturbate.eu/siswet19/',
+        'only_matching': True,
+    }, {
+        'url': 'https://chaturbate.eu/fullvideo/?b=caylin',
+        'only_matching': True,
+    }, {
+        'url': 'https://chaturbate.global/siswet19/',
+        'only_matching': True,
    }]

    _ROOM_OFFLINE = 'Room is currently offline'

    def _real_extract(self, url):
-        video_id = self._match_id(url)
+        video_id, tld = self._match_valid_url(url).group('id', 'tld')

        webpage = self._download_webpage(
-            f'https://chaturbate.com/{video_id}/', video_id,
+            f'https://chaturbate.{tld}/{video_id}/', video_id,
            headers=self.geo_verification_headers())

        found_m3u8_urls = []
--- a/yt_dlp/extractor/cloudflarestream.py
+++ b/yt_dlp/extractor/cloudflarestream.py
@ -8,7 +8,7 @@ class CloudflareStreamIE(InfoExtractor):
    _DOMAIN_RE = r'(?:cloudflarestream\.com|(?:videodelivery|bytehighway)\.net)'
    _EMBED_RE = rf'(?:embed\.|{_SUBDOMAIN_RE}){_DOMAIN_RE}/embed/[^/?#]+\.js\?(?:[^#]+&)?video='
    _ID_RE = r'[\da-f]{32}|eyJ[\w-]+\.[\w-]+\.[\w-]+'
-    _VALID_URL = rf'https?://(?:{_SUBDOMAIN_RE}{_DOMAIN_RE}/|{_EMBED_RE})(?P<id>{_ID_RE})'
+    _VALID_URL = rf'https?://(?:{_SUBDOMAIN_RE}(?P<domain>{_DOMAIN_RE})/|{_EMBED_RE})(?P<id>{_ID_RE})'
    _EMBED_REGEX = [
        rf'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//{_EMBED_RE}(?:{_ID_RE})(?:(?!\1).)*)\1',
        rf'<iframe[^>]+\bsrc=["\'](?P<url>https?://{_SUBDOMAIN_RE}{_DOMAIN_RE}/[\da-f]{{32}})',
@ -19,7 +19,7 @@ class CloudflareStreamIE(InfoExtractor):
            'id': '31c9291ab41fac05471db4e73aa11717',
            'ext': 'mp4',
            'title': '31c9291ab41fac05471db4e73aa11717',
-            'thumbnail': 'https://videodelivery.net/31c9291ab41fac05471db4e73aa11717/thumbnails/thumbnail.jpg',
+            'thumbnail': 'https://cloudflarestream.com/31c9291ab41fac05471db4e73aa11717/thumbnails/thumbnail.jpg',
        },
        'params': {
            'skip_download': 'm3u8',
@ -30,7 +30,7 @@ class CloudflareStreamIE(InfoExtractor):
            'id': '0e8e040aec776862e1d632a699edf59e',
            'ext': 'mp4',
            'title': '0e8e040aec776862e1d632a699edf59e',
-            'thumbnail': 'https://videodelivery.net/0e8e040aec776862e1d632a699edf59e/thumbnails/thumbnail.jpg',
+            'thumbnail': 'https://cloudflarestream.com/0e8e040aec776862e1d632a699edf59e/thumbnails/thumbnail.jpg',
        },
    }, {
        'url': 'https://watch.cloudflarestream.com/9df17203414fd1db3e3ed74abbe936c1',
@ -54,7 +54,7 @@ class CloudflareStreamIE(InfoExtractor):
            'id': 'eaef9dea5159cf968be84241b5cedfe7',
            'ext': 'mp4',
            'title': 'eaef9dea5159cf968be84241b5cedfe7',
-            'thumbnail': 'https://videodelivery.net/eaef9dea5159cf968be84241b5cedfe7/thumbnails/thumbnail.jpg',
+            'thumbnail': 'https://cloudflarestream.com/eaef9dea5159cf968be84241b5cedfe7/thumbnails/thumbnail.jpg',
        },
        'params': {
            'skip_download': 'm3u8',
@ -62,8 +62,9 @@ class CloudflareStreamIE(InfoExtractor):
    }]

    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        domain = 'bytehighway.net' if 'bytehighway.net/' in url else 'videodelivery.net'
+        video_id, domain = self._match_valid_url(url).group('id', 'domain')
+        if domain != 'bytehighway.net':
+            domain = 'cloudflarestream.com'
        base_url = f'https://{domain}/{video_id}/'
        if '.' in video_id:
            video_id = self._parse_json(base64.urlsafe_b64decode(
--- a/yt_dlp/extractor/goplay.py
+++ b/yt_dlp/extractor/goplay.py
@ -5,56 +5,63 @@ import hashlib
 import hmac
 import json
 import os
+import re
+import urllib.parse

 from .common import InfoExtractor
 from ..utils import (
    ExtractorError,
+    int_or_none,
+    js_to_json,
+    remove_end,
    traverse_obj,
-    unescapeHTML,
 )


 class GoPlayIE(InfoExtractor):
-    _VALID_URL = r'https?://(www\.)?goplay\.be/video/([^/]+/[^/]+/|)(?P<display_id>[^/#]+)'
+    _VALID_URL = r'https?://(www\.)?goplay\.be/video/([^/?#]+/[^/?#]+/|)(?P<id>[^/#]+)'

    _NETRC_MACHINE = 'goplay'

    _TESTS = [{
-        'url': 'https://www.goplay.be/video/de-container-cup/de-container-cup-s3/de-container-cup-s3-aflevering-2#autoplay',
+        'url': 'https://www.goplay.be/video/de-slimste-mens-ter-wereld/de-slimste-mens-ter-wereld-s22/de-slimste-mens-ter-wereld-s22-aflevering-1',
        'info_dict': {
-            'id': '9c4214b8-e55d-4e4b-a446-f015f6c6f811',
+            'id': '2baa4560-87a0-421b-bffc-359914e3c387',
            'ext': 'mp4',
-            'title': 'S3 - Aflevering 2',
-            'series': 'De Container Cup',
-            'season': 'Season 3',
-            'season_number': 3,
-            'episode': 'Episode 2',
-            'episode_number': 2,
+            'title': 'S22 - Aflevering 1',
+            'description': r're:In aflevering 1 nemen Daan Alferink, Tess Elst en Xander De Rycke .{66}',
+            'series': 'De Slimste Mens ter Wereld',
+            'episode': 'Episode 1',
+            'season_number': 22,
+            'episode_number': 1,
+            'season': 'Season 22',
        },
+        'params': {'skip_download': True},
        'skip': 'This video is only available for registered users',
    }, {
-        'url': 'https://www.goplay.be/video/a-family-for-thr-holidays-s1-aflevering-1#autoplay',
+        'url': 'https://www.goplay.be/video/1917',
        'info_dict': {
-            'id': '74e3ed07-748c-49e4-85a0-393a93337dbf',
+            'id': '40cac41d-8d29-4ef5-aa11-75047b9f0907',
            'ext': 'mp4',
-            'title': 'A Family for the Holidays',
+            'title': '1917',
+            'description': r're:Op het hoogtepunt van de Eerste Wereldoorlog krijgen twee jonge .{94}',
        },
+        'params': {'skip_download': True},
        'skip': 'This video is only available for registered users',
    }, {
        'url': 'https://www.goplay.be/video/de-mol/de-mol-s11/de-mol-s11-aflevering-1#autoplay',
        'info_dict': {
-            'id': '03eb8f2f-153e-41cb-9805-0d3a29dab656',
+            'id': 'ecb79672-92b9-4cd9-a0d7-e2f0250681ee',
            'ext': 'mp4',
            'title': 'S11 - Aflevering 1',
+            'description': r're:Tien kandidaten beginnen aan hun verovering van Amerika en ontmoeten .{102}',
            'episode': 'Episode 1',
            'series': 'De Mol',
            'season_number': 11,
            'episode_number': 1,
            'season': 'Season 11',
        },
-        'params': {
-            'skip_download': True,
-        },
+        'params': {'skip_download': True},
        'skip': 'This video is only available for registered users',
    }]

@ -69,27 +76,42 @@ class GoPlayIE(InfoExtractor):
        if not self._id_token:
            raise self.raise_login_required(method='password')

-    def _real_extract(self, url):
-        url, display_id = self._match_valid_url(url).group(0, 'display_id')
-        webpage = self._download_webpage(url, display_id)
-        video_data_json = self._html_search_regex(r'<div\s+data-hero="([^"]+)"', webpage, 'video_data')
-        video_data = self._parse_json(unescapeHTML(video_data_json), display_id).get('data')
+    def _find_json(self, s):
+        return self._search_json(
+            r'\w+\s*:\s*', s, 'next js data', None, contains_pattern=r'\[(?s:.+)\]', default=None)

-        movie = video_data.get('movie')
-        if movie:
-            video_id = movie['videoUuid']
-            info_dict = {
-                'title': movie.get('title'),
-            }
-        else:
-            episode = traverse_obj(video_data, ('playlists', ..., 'episodes', lambda _, v: v['pageInfo']['url'] == url), get_all=False)
-            video_id = episode['videoUuid']
-            info_dict = {
-                'title': episode.get('episodeTitle'),
-                'series': traverse_obj(episode, ('program', 'title')),
-                'season_number': episode.get('seasonNumber'),
-                'episode_number': episode.get('episodeNumber'),
-            }
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        nextjs_data = traverse_obj(
+            re.findall(r'<script[^>]*>\s*self\.__next_f\.push\(\s*(\[.+?\])\s*\);?\s*</script>', webpage),
+            (..., {js_to_json}, {json.loads}, ..., {self._find_json}, ...))
+        meta = traverse_obj(nextjs_data, (
+            ..., lambda _, v: v['meta']['path'] == urllib.parse.urlparse(url).path, 'meta', any))
+
+        video_id = meta['uuid']
+        info_dict = traverse_obj(meta, {
+            'title': ('title', {str}),
+            'description': ('description', {str.strip}),
+        })
+
+        if traverse_obj(meta, ('program', 'subtype')) != 'movie':
+            for season_data in traverse_obj(nextjs_data, (..., 'children', ..., 'playlists', ...)):
+                episode_data = traverse_obj(
+                    season_data, ('videos', lambda _, v: v['videoId'] == video_id, any))
+                if not episode_data:
+                    continue
+
+                episode_title = traverse_obj(
+                    episode_data, 'contextualTitle', 'episodeTitle', expected_type=str)
+                info_dict.update({
+                    'title': episode_title or info_dict.get('title'),
+                    'series': remove_end(info_dict.get('title'), f' - {episode_title}'),
+                    'season_number': traverse_obj(season_data, ('season', {int_or_none})),
+                    'episode_number': traverse_obj(episode_data, ('episodeNumber', {int_or_none})),
+                })
+                break

        api = self._download_json(
            f'https://api.goplay.be/web/v1/videos/long-form/{video_id}',
--- a/yt_dlp/extractor/mixch.py
+++ b/yt_dlp/extractor/mixch.py
@ -12,7 +12,7 @@ from ..utils.traversal import traverse_obj

 class MixchIE(InfoExtractor):
    IE_NAME = 'mixch'
-    _VALID_URL = r'https?://(?:www\.)?mixch\.tv/u/(?P<id>\d+)'
+    _VALID_URL = r'https?://mixch\.tv/u/(?P<id>\d+)'

    _TESTS = [{
        'url': 'https://mixch.tv/u/16943797/live',
@ -74,7 +74,7 @@ class MixchIE(InfoExtractor):

 class MixchArchiveIE(InfoExtractor):
    IE_NAME = 'mixch:archive'
-    _VALID_URL = r'https?://(?:www\.)?mixch\.tv/archive/(?P<id>\d+)'
+    _VALID_URL = r'https?://mixch\.tv/archive/(?P<id>\d+)'

    _TESTS = [{
        'url': 'https://mixch.tv/archive/421',
@ -116,3 +116,56 @@ class MixchArchiveIE(InfoExtractor):
            'formats': self._extract_m3u8_formats(info_json['archiveURL'], video_id),
            'thumbnail': traverse_obj(info_json, ('thumbnailURL', {url_or_none})),
        }
+
+
+class MixchMovieIE(InfoExtractor):
+    IE_NAME = 'mixch:movie'
+    _VALID_URL = r'https?://mixch\.tv/m/(?P<id>\w+)'
+
+    _TESTS = [{
+        'url': 'https://mixch.tv/m/Ve8KNkJ5',
+        'info_dict': {
+            'id': 'Ve8KNkJ5',
+            'title': '夏☀️\nムービーへのポイントは本イベントに加算されないので配信にてお願い致します🙇🏻\u200d♀️\n#TGCCAMPUS #ミス東大 #ミス東大2024 ',
+            'ext': 'mp4',
+            'uploader': 'ミス東大No.5 松藤百香🍑💫',
+            'uploader_id': '12299174',
+            'channel_follower_count': int,
+            'view_count': int,
+            'like_count': int,
+            'comment_count': int,
+            'timestamp': 1724070828,
+            'uploader_url': 'https://mixch.tv/u/12299174',
+            'live_status': 'not_live',
+            'upload_date': '20240819',
+        },
+    }, {
+        'url': 'https://mixch.tv/m/61DzpIKE',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        data = self._download_json(
+            f'https://mixch.tv/api-web/movies/{video_id}', video_id)
+        return {
+            'id': video_id,
+            'formats': [{
+                'format_id': 'mp4',
+                'url': data['movie']['file'],
+                'ext': 'mp4',
+            }],
+            **traverse_obj(data, {
+                'title': ('movie', 'title', {str}),
+                'thumbnail': ('movie', 'thumbnailURL', {url_or_none}),
+                'uploader': ('ownerInfo', 'name', {str}),
+                'uploader_id': ('ownerInfo', 'id', {int}, {str_or_none}),
+                'channel_follower_count': ('ownerInfo', 'fan', {int_or_none}),
+                'view_count': ('ownerInfo', 'view', {int_or_none}),
+                'like_count': ('movie', 'favCount', {int_or_none}),
+                'comment_count': ('movie', 'commentCount', {int_or_none}),
+                'timestamp': ('movie', 'published', {int_or_none}),
+                'uploader_url': ('ownerInfo', 'id', {lambda x: x and f'https://mixch.tv/u/{x}'}, filter),
+            }),
+            'live_status': 'not_live',
+        }
--- a/yt_dlp/extractor/rplaylive.py
+++ b/yt_dlp/extractor/rplaylive.py
@ -0,0 +1,347 @@
+import base64
+import datetime as dt
+import hashlib
+import hmac
+import json
+import random
+import re
+import time
+
+from .common import InfoExtractor
+from ..aes import aes_cbc_encrypt_bytes
+from ..utils import (
+    ExtractorError,
+    UserNotLive,
+    encode_data_uri,
+    float_or_none,
+    parse_iso8601,
+    parse_qs,
+    traverse_obj,
+    url_or_none,
+)
+
+
+class RPlayBaseIE(InfoExtractor):
+    _NETRC_MACHINE = 'rplaylive'
+    _TOKEN_CACHE = {}
+    _user_id = None
+    _login_type = None
+    _jwt_token = None
+    _tested_jwt = False
+
+    def _check_jwt_args(self):
+        jwt_arg = self._configuration_arg('jwt_token', ie_key='rplaylive', casesense=True)
+        if self._jwt_token is None and jwt_arg and not self._tested_jwt:
+            self._login_by_token(jwt_arg[0], raw_token_hint=True)
+            self._tested_jwt = True
+
+    @property
+    def user_id(self):
+        self._check_jwt_args()
+        return self._user_id
+
+    @property
+    def login_type(self):
+        self._check_jwt_args()
+        return self._login_type
+
+    @property
+    def jwt_token(self):
+        self._check_jwt_args()
+        return self._jwt_token
+
+    @property
+    def requestor_query(self):
+        return {
+            'requestorOid': self.user_id,
+            'loginType': self.login_type,
+        } if self.user_id else {}
+
+    @property
+    def jwt_header(self):
+        return {
+            'Origin': 'https://rplay.live',
+            'Referer': 'https://rplay.live/',
+            'Authorization': self.jwt_token or 'null',
+        }
+
+    @property
+    def butter_header(self):
+        return {
+            'Origin': 'https://rplay.live',
+            'Referer': 'https://rplay.live/',
+            'Butter': self.get_butter_token(),
+        }
+
+    def _login_hint(self, **kwargs):
+        return (f'Use --username and --password, --netrc-cmd, --netrc ({self._NETRC_MACHINE}) '
+                'or --extractor-args "rplaylive:jwt_token=xxx" to provide account credentials')
+
+    def _jwt_encode_hs256(self, payload: dict, key: str):
+        # yt_dlp.utils.jwt_encode_hs256() uses slightly different details that would fails
+        # and we need to re-implement it with minor changes
+        b64encode = lambda x: base64.urlsafe_b64encode(
+            json.dumps(x, separators=(',', ':')).encode()).strip(b'=')
+
+        header_b64 = b64encode({'alg': 'HS256', 'typ': 'JWT'})
+        payload_b64 = b64encode(payload)
+        h = hmac.new(key.encode(), header_b64 + b'.' + payload_b64, hashlib.sha256)
+        signature_b64 = base64.urlsafe_b64encode(h.digest()).strip(b'=')
+        return header_b64 + b'.' + payload_b64 + b'.' + signature_b64
+
+    def _perform_login(self, username, password):
+        payload = {
+            'eml': username,
+            'dat': dt.datetime.now(dt.timezone.utc).isoformat(timespec='milliseconds').replace('+00:00', 'Z'),
+            'iat': int(time.time()),
+        }
+        key = hashlib.sha256(password.encode()).hexdigest()
+        self._login_by_token(self._jwt_encode_hs256(payload, key).decode())
+
+    def _login_by_token(self, jwt_token, raw_token_hint=False):
+        user_info = self._download_json(
+            'https://api.rplay.live/account/login', 'login', note='performing login', errnote='login failed',
+            data=f'{{"token":"{jwt_token}","loginType":null,"checkAdmin":null}}'.encode(),
+            headers={'Content-Type': 'application/json', 'Authorization': 'null'}, fatal=False)
+
+        if user_info:
+            self._user_id = traverse_obj(user_info, 'oid')
+            self._login_type = traverse_obj(user_info, 'accountType')
+            self._jwt_token = jwt_token if self._user_id else None
+        if not self._user_id:
+            if raw_token_hint:
+                self.report_warning('Login failed, possibly due to wrong or expired JWT token')
+            else:
+                self.report_warning('Login failed, possibly due to wrong password or website change')
+
+    def get_butter_token(self):
+        salt = 'QWI@(!WAS)Dj1AA(!@*DJ#@$@~1)P'
+        key = 'S%M@#H#B(!@()a2@'
+        ts_value = str(int(time.time() / 360))
+        enc = aes_cbc_encrypt_bytes(f'{salt}https://rplay.live{ts_value}', key, ts_value.zfill(16))
+        return enc.hex()
+
+
+class RPlayVideoIE(RPlayBaseIE):
+    _VALID_URL = r'https://rplay.live/play/(?P<id>[\d\w]+)'
+    _TESTS = [{
+        'url': 'https://rplay.live/play/669203d25223214e67579dc3/',
+        'info_dict': {
+            'id': '669203d25223214e67579dc3',
+            'ext': 'mp4',
+            'title': 'md5:6ab0a76410b40b1f5fb48a2ad7571264',
+            'description': 'md5:d2fb2f74a623be439cf454df5ff3344a',
+            'timestamp': 1720845266,
+            'upload_date': '20240713',
+            'release_timestamp': 1720846360,
+            'release_date': '20240713',
+            'duration': 5349.0,
+            'thumbnail': 'https://pb.rplay.live/thumbnail/669203d25223214e67579dc3',
+            'uploader': '杏都める',
+            'uploader_id': '667adc9e9aa7f739a2158ff3',
+            'tags': ['杏都める', 'めいどるーちぇ', '無料', '耳舐め', 'ASMR'],
+        },
+    }, {
+        'url': 'https://rplay.live/play/66783c65dcd1c768a8a69f24/',
+        'info_dict': {
+            'id': '66783c65dcd1c768a8a69f24',
+            'ext': 'mp4',
+            'title': 'md5:9be2febe48cee1b7536e3e9d4d5f8e56',
+            'description': 'md5:a71374d3dcd1db0f852b96a69b41b699',
+            'timestamp': 1719155813,
+            'upload_date': '20240623',
+            'release_timestamp': 1719155813,
+            'release_date': '20240623',
+            'duration': 4237.0,
+            'thumbnail': 'https://pb.rplay.live/thumbnail/66783c65dcd1c768a8a69f24',
+            'uploader': '狐月れんげ',
+            'uploader_id': '65eeb4b237043dc0b5654f86',
+            'tags': 'count:4',
+            'age_limit': 18,
+            'live_status': 'was_live',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        playlist_id = traverse_obj(parse_qs(url), ('playlist', ..., any))
+        if playlist_id and self._yes_playlist(playlist_id, video_id):
+            playlist_info = self._download_json(
+                'https://api.rplay.live/content/playlist', playlist_id,
+                query={'playlistOid': playlist_id, **self.requestor_query},
+                headers=self.jwt_header, fatal=False)
+            if playlist_info:
+                entries = traverse_obj(playlist_info, ('contentData', ..., '_id', {
+                    lambda x: self.url_result(f'https://rplay.live/play/{x}/', ie=RPlayVideoIE, video_id=x)}))
+                return self.playlist_result(entries, playlist_id, playlist_info.get('name'))
+            else:
+                self.report_warning('Failed to get playlist, downloading video only')
+
+        video_info = self._download_json('https://api.rplay.live/content', video_id, query={
+            'contentOid': video_id,
+            'status': 'published',
+            'withComments': True,
+            'requestCanView': True,
+            **self.requestor_query,
+        }, headers=self.jwt_header)
+        if video_info.get('drm'):
+            raise ExtractorError('This video is DRM-protected')
+
+        metainfo = traverse_obj(video_info, {
+            'title': ('title', {str}),
+            'description': ('introText', {str}),
+            'release_timestamp': ('publishedAt', {parse_iso8601}),
+            'timestamp': ('createdAt', {parse_iso8601}),
+            'duration': ('length', {float_or_none}),
+            'uploader': ('creatorInfo', 'nickname', {str}),
+            'uploader_id': ('creatorOid', {str}),
+            'tags': ('hashtags', lambda _, v: v[0] != '_'),
+            'age_limit': (('hideContent', 'isAdultContent'), {lambda x: 18 if x else None}, any),
+            'live_status': ('isReplayContent', {lambda x: 'was_live' if x else None}),
+        })
+
+        m3u8_url = traverse_obj(video_info, ('canView', 'url', {url_or_none}))
+        if not m3u8_url:
+            msg = 'You do not have access to this video'
+            if traverse_obj(video_info, ('viewableTiers', 'free')):
+                msg = 'This video requires a free subscription to access'
+            if not self.user_id:
+                msg += f'. {self._login_hint()}'
+            raise ExtractorError(msg, expected=True)
+
+        formats = self._extract_m3u8_formats(m3u8_url, video_id, headers=self.butter_header)
+        for fmt in formats:
+            m3u8_doc = self._download_webpage(fmt['url'], video_id, 'getting m3u8 contents', headers=self.butter_header)
+            fmt['url'] = encode_data_uri(m3u8_doc.encode(), 'application/x-mpegurl')
+            match = re.search(r'^#EXT-X-KEY.*?URI="([^"]+)"', m3u8_doc, flags=re.M)
+            if match:
+                urlh = self._request_webpage(match[1], video_id, 'getting hls key', headers={
+                    'Origin': 'https://rplay.live',
+                    'Referer': 'https://rplay.live/',
+                    'rplay-private-content-requestor': self.user_id or 'not-logged-in',
+                    'age': random.randint(1, 4999),
+                })
+                fmt['hls_aes'] = {'key': urlh.read().hex()}
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            **metainfo,
+            'thumbnail': f'https://pb.rplay.live/thumbnail/{video_id}',
+            'http_headers': {'Referer': 'https://rplay.live/'},
+        }
+
+
+class RPlayUserIE(InfoExtractor):
+    _VALID_URL = r'https://rplay.live/(?P<short>c|creatorhome)/(?P<id>[\d\w]+)/?(?:[#?]|$)'
+    _TESTS = [{
+        'url': 'https://rplay.live/creatorhome/667adc9e9aa7f739a2158ff3?page=contents',
+        'info_dict': {
+            'id': '667adc9e9aa7f739a2158ff3',
+            'title': '杏都める',
+        },
+        'playlist_mincount': 35,
+    }, {
+        'url': 'https://rplay.live/c/furachi',
+        'info_dict': {
+            'id': '65e07e60850f4527aab74757',
+            'title': '逢瀬ふらち OuseFurachi',
+        },
+        'playlist_mincount': 94,
+    }]
+
+    def _real_extract(self, url):
+        user_id, short = self._match_valid_url(url).group('id', 'short')
+
+        user_info = self._download_json('https://api.rplay.live/account/getuser', user_id, query={
+            'customUrl' if short == 'c' else 'userOid': user_id, 'options': '{"includeContentMetadata":true}'})
+        replays = self._download_json(
+            'https://api.rplay.live/live/replays', user_id, query={'creatorOid': user_info.get('_id')})
+
+        def _entries():
+            def _entry_ids():
+                for entry in traverse_obj(user_info, ('metadataSet', ..., lambda _, v: v['_id'])):
+                    yield entry['_id'], entry.get('title')
+                for entry in traverse_obj(replays, lambda _, v: v['_id']):
+                    yield entry['_id'], entry.get('title')
+            for vid, title in dict(_entry_ids()).items():
+                yield self.url_result(f'https://rplay.live/play/{vid}', ie=RPlayVideoIE, id=vid, title=title)
+
+        return self.playlist_result(_entries(), user_info.get('_id', user_id), user_info.get('nickname'))
+
+
+class RPlayLiveIE(RPlayBaseIE):
+    _VALID_URL = [
+        r'https://rplay.live/(?P<short>c)/(?P<id>[\d\w]+)/live',
+        r'https://rplay.live/(?P<short>live)/(?P<id>[\d\w]+)',
+    ]
+    _TESTS = [{
+        'url': 'https://rplay.live/c/chachamaru/live',
+        'info_dict': {
+            'id': '667e4cd99aa7f739a2c91852',
+            'ext': 'mp4',
+            'title': r're:【ASMR】ん～っやば//スキスキ耐久.*',
+            'description': 'md5:7f88ac0a7a3d5d0b926a0baecd1d40e1',
+            'timestamp': 1721739947,
+            'upload_date': '20240723',
+            'live_status': 'is_live',
+            'thumbnail': 'https://pb.rplay.live/liveChannelThumbnails/667e4cd99aa7f739a2c91852',
+            'uploader': '愛犬茶々丸',
+            'uploader_id': '667e4cd99aa7f739a2c91852',
+            'tags': 'count:9',
+        },
+        'skip': 'live',
+    }, {
+        'url': 'https://rplay.live/live/667adc9e9aa7f739a2158ff3',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        user_id, short = self._match_valid_url(url).group('id', 'short')
+
+        user_info = self._download_json('https://api.rplay.live/account/getuser', user_id, query={
+            'customUrl' if short == 'c' else 'userOid': user_id})
+        if user_info.get('isLive') is False:
+            raise UserNotLive
+        user_id = user_info['_id']
+
+        live_info = self._download_json('https://api.rplay.live/live/play', user_id, query={'creatorOid': user_id})
+
+        stream_state = live_info['streamState']
+        if stream_state == 'youtube':
+            return self.url_result(f'https://www.youtube.com/watch?v={live_info["liveStreamId"]}')
+        elif stream_state == 'twitch':
+            return self.url_result(f'https://www.twitch.tv/{live_info["twitchLogin"]}')
+        elif stream_state == 'live':
+            if not self.user_id and not live_info.get('allowAnonymous'):
+                self.raise_login_required(method='password')
+            key2 = traverse_obj(self._download_json(
+                'https://api.rplay.live/live/key2', user_id, 'getting live key',
+                headers=self.jwt_header, query=self.requestor_query), ('authKey', {str})) if self.user_id else ''
+            if key2 is None:
+                raise ExtractorError('Failed to get playlist key')
+            formats = self._extract_m3u8_formats(
+                'https://api.rplay.live/live/stream/playlist.m3u8', user_id,
+                query={'creatorOid': user_id, 'key2': key2}, headers={'Referer': 'https://rplay.live'})
+
+            return {
+                'id': user_id,
+                'formats': formats,
+                'is_live': True,
+                'http_headers': {'Referer': 'https://rplay.live'},
+                'thumbnail': f'https://pb.rplay.live/liveChannelThumbnails/{user_id}',
+                'uploader': traverse_obj(user_info, ('nickname', {str})),
+                'uploader_id': user_id,
+                **traverse_obj(live_info, {
+                    'title': ('title', {str}),
+                    'description': ('description', {str}),
+                    'timestamp': ('streamStartTime', {parse_iso8601}),
+                    'tags': ('hashtags', ..., {str}),
+                    'age_limit': ('isAdultContent', {lambda x: 18 if x else None}),
+                }),
+            }
+        elif stream_state == 'offline':
+            raise UserNotLive
+        else:
+            raise ExtractorError(f'Unknow streamState: {stream_state}')
Author	SHA1	Message	Date
c-basalt	447e063c45	Merge `501c9d5267` into `a9f85670d0`	2024-11-12 13:40:11 -08:00
manav_chaudhary	a9f85670d0	[ie/Chaturbate] Support alternate domains (#10595 ) Closes #10594 Authored by: manavchaudhary1	2024-11-11 23:41:56 +01:00
Sam	6b43a8d84b	[ie/goplay] Fix extractor (#11466 ) Closes #10857 Authored by: SamDecrock, bashonly Co-authored-by: bashonly <88596187+bashonly@users.noreply.github.com>	2024-11-11 22:03:31 +00:00
Hugo	2db8c2e7d5	[ie/CloudflareStream] Avoid extraction via videodelivery.net (#11478 ) Closes #11477 Authored by: hugovdev	2024-11-11 22:00:05 +00:00
bashonly	f9c8deb4e5	[build] Bump PyInstaller version pin to `>=6.11.1` (#11507 ) Authored by: bashonly	2024-11-11 21:19:03 +00:00
Sakura286	0ec9bfed4d	[ie/MixchMovie] Add extractor (#10897 ) Closes #10765 Authored by: Sakura286	2024-11-11 21:40:29 +01:00
c-basalt	501c9d5267	update headers	2024-10-07 12:47:47 -04:00
c-basalt	9d4497e13e	fix for api change	2024-10-06 10:45:54 -04:00
c-basalt	dcd2e93fa0	support jwt arg	2024-09-19 20:09:48 -04:00
c-basalt	02f4b25227	update	2024-08-11 10:45:10 -04:00
c-basalt	388dc541da	improve	2024-08-11 04:36:38 -04:00
c-basalt	d9fd3dbdfa	improve user video list	2024-08-11 03:38:25 -04:00
c-basalt	d92f6fbaea	fix	2024-08-09 18:28:08 -04:00
c-basalt	ee838b418c	vod fix	2024-08-08 17:14:42 -04:00
c-basalt	7c97ead1b0	migrate from old rplay branch	2024-08-08 11:48:21 -04:00