[yt-dlp.git] / yt_dlp / extractor / tencent.py

import functools
import random
import re
import string
import time

from .common import InfoExtractor
from ..aes import aes_cbc_encrypt_bytes
from ..utils import (
    ExtractorError,
    determine_ext,
    int_or_none,
    js_to_json,
    traverse_obj,
    urljoin,
)


class TencentBaseIE(InfoExtractor):
    """Subclasses must set _API_URL, _APP_VERSION, _PLATFORM, _HOST, _REFERER"""

    def _get_ckey(self, video_id, url, guid):
        ua = self.get_param('http_headers')['User-Agent']

        payload = (f'{video_id}|{int(time.time())}|mg3c3b04ba|{self._APP_VERSION}|{guid}|'
                   f'{self._PLATFORM}|{url[:48]}|{ua.lower()[:48]}||Mozilla|Netscape|Windows x86_64|00|')

        return aes_cbc_encrypt_bytes(
            bytes(f'|{sum(map(ord, payload))}|{payload}', 'utf-8'),
            b'Ok\xda\xa3\x9e/\x8c\xb0\x7f^r-\x9e\xde\xf3\x14',
            b'\x01PJ\xf3V\xe6\x19\xcf.B\xbb\xa6\x8c?p\xf9',
            padding_mode='whitespace').hex().upper()

    def _get_video_api_response(self, video_url, video_id, series_id, subtitle_format, video_format, video_quality):
        guid = ''.join([random.choice(string.digits + string.ascii_lowercase) for _ in range(16)])
        ckey = self._get_ckey(video_id, video_url, guid)
        query = {
            'vid': video_id,
            'cid': series_id,
            'cKey': ckey,
            'encryptVer': '8.1',
            'spcaptiontype': '1' if subtitle_format == 'vtt' else '0',
            'sphls': '2' if video_format == 'hls' else '0',
            'dtype': '3' if video_format == 'hls' else '0',
            'defn': video_quality,
            'spsrt': '2',  # Enable subtitles
            'sphttps': '1',  # Enable HTTPS
            'otype': 'json',
            'spwm': '1',
            # For SHD
            'host': self._HOST,
            'referer': self._REFERER,
            'ehost': video_url,
            'appVer': self._APP_VERSION,
            'platform': self._PLATFORM,
            # For VQQ
            'guid': guid,
            'flowid': ''.join(random.choice(string.digits + string.ascii_lowercase) for _ in range(32)),
        }

        return self._search_json(r'QZOutputJson=', self._download_webpage(
            self._API_URL, video_id, query=query), 'api_response', video_id)

    def _extract_video_formats_and_subtitles(self, api_response, video_id):
        video_response = api_response['vl']['vi'][0]
        video_width, video_height = video_response.get('vw'), video_response.get('vh')

        formats, subtitles = [], {}
        for video_format in video_response['ul']['ui']:
            if video_format.get('hls'):
                fmts, subs = self._extract_m3u8_formats_and_subtitles(
                    video_format['url'] + video_format['hls']['pt'], video_id, 'mp4', fatal=False)
                for f in fmts:
                    f.update({'width': video_width, 'height': video_height})

                formats.extend(fmts)
                self._merge_subtitles(subs, target=subtitles)
            else:
                formats.append({
                    'url': f'{video_format["url"]}{video_response["fn"]}?vkey={video_response["fvkey"]}',
                    'width': video_width,
                    'height': video_height,
                    'ext': 'mp4',
                })

        return formats, subtitles

    def _extract_video_native_subtitles(self, api_response, subtitles_format):
        subtitles = {}
        for subtitle in traverse_obj(api_response, ('sfl', 'fi')) or ():
            subtitles.setdefault(subtitle['lang'].lower(), []).append({
                'url': subtitle['url'],
                'ext': subtitles_format,
                'protocol': 'm3u8_native' if determine_ext(subtitle['url']) == 'm3u8' else 'http',
            })

        return subtitles

    def _extract_all_video_formats_and_subtitles(self, url, video_id, series_id):
        formats, subtitles = [], {}
        for video_format, subtitle_format, video_quality in (
                # '': 480p, 'shd': 720p, 'fhd': 1080p
                ('mp4', 'srt', ''), ('hls', 'vtt', 'shd'), ('hls', 'vtt', 'fhd')):
            api_response = self._get_video_api_response(
                url, video_id, series_id, subtitle_format, video_format, video_quality)

            if api_response.get('em') != 0 and api_response.get('exem') != 0:
                if '您所在区域暂无此内容版权' in api_response.get('msg'):
                    self.raise_geo_restricted()
                raise ExtractorError(f'Tencent said: {api_response.get("msg")}')

            fmts, subs = self._extract_video_formats_and_subtitles(api_response, video_id)
            native_subtitles = self._extract_video_native_subtitles(api_response, subtitle_format)

            formats.extend(fmts)
            self._merge_subtitles(subs, native_subtitles, target=subtitles)

        self._sort_formats(formats)
        return formats, subtitles

    def _get_clean_title(self, title):
        return re.sub(
            r'\s*[_\-]\s*(?:Watch online|腾讯视频|(?:高清)?1080P在线观看平台).*?$',
            '', title or '').strip() or None


class VQQBaseIE(TencentBaseIE):
    _VALID_URL_BASE = r'https?://v\.qq\.com'

    _API_URL = 'https://h5vv6.video.qq.com/getvinfo'
    _APP_VERSION = '3.5.57'
    _PLATFORM = '10901'
    _HOST = 'v.qq.com'
    _REFERER = 'v.qq.com'

    def _get_webpage_metadata(self, webpage, video_id):
        return self._parse_json(
            self._search_regex(
                r'(?s)<script[^>]*>[^<]*window\.__pinia\s*=\s*([^<]+)</script>',
                webpage, 'pinia data', fatal=False),
            video_id, transform_source=js_to_json, fatal=False)


class VQQVideoIE(VQQBaseIE):
    IE_NAME = 'vqq:video'
    _VALID_URL = VQQBaseIE._VALID_URL_BASE + r'/x/(?:page|cover/(?P<series_id>\w+))/(?P<id>\w+)'

    _TESTS = [{
        'url': 'https://v.qq.com/x/page/q326831cny0.html',
        'md5': '826ef93682df09e3deac4a6e6e8cdb6e',
        'info_dict': {
            'id': 'q326831cny0',
            'ext': 'mp4',
            'title': '我是选手：雷霆裂阵，终极时刻',
            'description': 'md5:e7ed70be89244017dac2a835a10aeb1e',
            'thumbnail': r're:^https?://[^?#]+q326831cny0',
        },
    }, {
        'url': 'https://v.qq.com/x/page/o3013za7cse.html',
        'md5': 'b91cbbeada22ef8cc4b06df53e36fa21',
        'info_dict': {
            'id': 'o3013za7cse',
            'ext': 'mp4',
            'title': '欧阳娜娜VLOG',
            'description': 'md5:29fe847497a98e04a8c3826e499edd2e',
            'thumbnail': r're:^https?://[^?#]+o3013za7cse',
        },
    }, {
        'url': 'https://v.qq.com/x/cover/7ce5noezvafma27/a00269ix3l8.html',
        'md5': '71459c5375c617c265a22f083facce67',
        'info_dict': {
            'id': 'a00269ix3l8',
            'ext': 'mp4',
            'title': '鸡毛飞上天 第01集',
            'description': 'md5:8cae3534327315b3872fbef5e51b5c5b',
            'thumbnail': r're:^https?://[^?#]+7ce5noezvafma27',
            'series': '鸡毛飞上天',
        },
    }, {
        'url': 'https://v.qq.com/x/cover/mzc00200p29k31e/s0043cwsgj0.html',
        'md5': '96b9fd4a189fdd4078c111f21d7ac1bc',
        'info_dict': {
            'id': 's0043cwsgj0',
            'ext': 'mp4',
            'title': '第1集：如何快乐吃糖？',
            'description': 'md5:1d8c3a0b8729ae3827fa5b2d3ebd5213',
            'thumbnail': r're:^https?://[^?#]+s0043cwsgj0',
            'series': '青年理工工作者生活研究所',
        },
    }]

    def _real_extract(self, url):
        video_id, series_id = self._match_valid_url(url).group('id', 'series_id')
        webpage = self._download_webpage(url, video_id)
        webpage_metadata = self._get_webpage_metadata(webpage, video_id)

        formats, subtitles = self._extract_all_video_formats_and_subtitles(url, video_id, series_id)
        return {
            'id': video_id,
            'title': self._get_clean_title(self._og_search_title(webpage)
                                           or traverse_obj(webpage_metadata, ('global', 'videoInfo', 'title'))),
            'description': (self._og_search_description(webpage)
                            or traverse_obj(webpage_metadata, ('global', 'videoInfo', 'desc'))),
            'formats': formats,
            'subtitles': subtitles,
            'thumbnail': (self._og_search_thumbnail(webpage)
                          or traverse_obj(webpage_metadata, ('global', 'videoInfo', 'pic160x90'))),
            'series': traverse_obj(webpage_metadata, ('global', 'coverInfo', 'title')),
        }


class VQQSeriesIE(VQQBaseIE):
    IE_NAME = 'vqq:series'
    _VALID_URL = VQQBaseIE._VALID_URL_BASE + r'/x/cover/(?P<id>\w+)\.html/?(?:[?#]|$)'

    _TESTS = [{
        'url': 'https://v.qq.com/x/cover/7ce5noezvafma27.html',
        'info_dict': {
            'id': '7ce5noezvafma27',
            'title': '鸡毛飞上天',
            'description': 'md5:8cae3534327315b3872fbef5e51b5c5b',
        },
        'playlist_count': 55,
    }, {
        'url': 'https://v.qq.com/x/cover/oshd7r0vy9sfq8e.html',
        'info_dict': {
            'id': 'oshd7r0vy9sfq8e',
            'title': '恋爱细胞2',
            'description': 'md5:9d8a2245679f71ca828534b0f95d2a03',
        },
        'playlist_count': 12,
    }]

    def _real_extract(self, url):
        series_id = self._match_id(url)
        webpage = self._download_webpage(url, series_id)
        webpage_metadata = self._get_webpage_metadata(webpage, series_id)

        episode_paths = [f'/x/cover/{series_id}/{video_id}.html' for video_id in re.findall(
            r'<div[^>]+data-vid="(?P<video_id>[^"]+)"[^>]+class="[^"]+episode-item-rect--number',
            webpage)]

        return self.playlist_from_matches(
            episode_paths, series_id, ie=VQQVideoIE, getter=functools.partial(urljoin, url),
            title=self._get_clean_title(traverse_obj(webpage_metadata, ('coverInfo', 'title'))
                                        or self._og_search_title(webpage)),
            description=(traverse_obj(webpage_metadata, ('coverInfo', 'description'))
                         or self._og_search_description(webpage)))


class WeTvBaseIE(TencentBaseIE):
    _VALID_URL_BASE = r'https?://(?:www\.)?wetv\.vip/(?:[^?#]+/)?play'

    _API_URL = 'https://play.wetv.vip/getvinfo'
    _APP_VERSION = '3.5.57'
    _PLATFORM = '4830201'
    _HOST = 'wetv.vip'
    _REFERER = 'wetv.vip'

    def _get_webpage_metadata(self, webpage, video_id):
        return self._parse_json(
            traverse_obj(self._search_nextjs_data(webpage, video_id), ('props', 'pageProps', 'data')),
            video_id, fatal=False)

    def _extract_episode(self, url):
        video_id, series_id = self._match_valid_url(url).group('id', 'series_id')
        webpage = self._download_webpage(url, video_id)
        webpage_metadata = self._get_webpage_metadata(webpage, video_id)

        formats, subtitles = self._extract_all_video_formats_and_subtitles(url, video_id, series_id)
        return {
            'id': video_id,
            'title': self._get_clean_title(self._og_search_title(webpage)
                                           or traverse_obj(webpage_metadata, ('coverInfo', 'title'))),
            'description': (traverse_obj(webpage_metadata, ('coverInfo', 'description'))
                            or self._og_search_description(webpage)),
            'formats': formats,
            'subtitles': subtitles,
            'thumbnail': self._og_search_thumbnail(webpage),
            'duration': int_or_none(traverse_obj(webpage_metadata, ('videoInfo', 'duration'))),
            'series': traverse_obj(webpage_metadata, ('coverInfo', 'title')),
            'episode_number': int_or_none(traverse_obj(webpage_metadata, ('videoInfo', 'episode'))),
        }

    def _extract_series(self, url, ie):
        series_id = self._match_id(url)
        webpage = self._download_webpage(url, series_id)
        webpage_metadata = self._get_webpage_metadata(webpage, series_id)

        episode_paths = ([f'/play/{series_id}/{episode["vid"]}' for episode in webpage_metadata.get('videoList')]
                         or re.findall(r'<a[^>]+class="play-video__link"[^>]+href="(?P<path>[^"]+)', webpage))

        return self.playlist_from_matches(
            episode_paths, series_id, ie=ie, getter=functools.partial(urljoin, url),
            title=self._get_clean_title(traverse_obj(webpage_metadata, ('coverInfo', 'title'))
                                        or self._og_search_title(webpage)),
            description=(traverse_obj(webpage_metadata, ('coverInfo', 'description'))
                         or self._og_search_description(webpage)))


class WeTvEpisodeIE(WeTvBaseIE):
    IE_NAME = 'wetv:episode'
    _VALID_URL = WeTvBaseIE._VALID_URL_BASE + r'/(?P<series_id>\w+)(?:-[^?#]+)?/(?P<id>\w+)(?:-[^?#]+)?'

    _TESTS = [{
        'url': 'https://wetv.vip/en/play/air11ooo2rdsdi3-Cute-Programmer/v0040pr89t9-EP1-Cute-Programmer',
        'md5': '0c70fdfaa5011ab022eebc598e64bbbe',
        'info_dict': {
            'id': 'v0040pr89t9',
            'ext': 'mp4',
            'title': 'EP1: Cute Programmer',
            'description': 'md5:e87beab3bf9f392d6b9e541a63286343',
            'thumbnail': r're:^https?://[^?#]+air11ooo2rdsdi3',
            'series': 'Cute Programmer',
            'episode': 'Episode 1',
            'episode_number': 1,
            'duration': 2835,
        },
    }, {
        'url': 'https://wetv.vip/en/play/u37kgfnfzs73kiu/p0039b9nvik',
        'md5': '3b3c15ca4b9a158d8d28d5aa9d7c0a49',
        'info_dict': {
            'id': 'p0039b9nvik',
            'ext': 'mp4',
            'title': 'EP1: You Are My Glory',
            'description': 'md5:831363a4c3b4d7615e1f3854be3a123b',
            'thumbnail': r're:^https?://[^?#]+u37kgfnfzs73kiu',
            'series': 'You Are My Glory',
            'episode': 'Episode 1',
            'episode_number': 1,
            'duration': 2454,
        },
    }, {
        'url': 'https://wetv.vip/en/play/lcxgwod5hapghvw-WeTV-PICK-A-BOO/i0042y00lxp-Zhao-Lusi-Describes-The-First-Experiences-She-Had-In-Who-Rules-The-World-%7C-WeTV-PICK-A-BOO',
        'md5': '71133f5c2d5d6cad3427e1b010488280',
        'info_dict': {
            'id': 'i0042y00lxp',
            'ext': 'mp4',
            'title': 'md5:f7a0857dbe5fbbe2e7ad630b92b54e6a',
            'description': 'md5:76260cb9cdc0ef76826d7ca9d92fadfa',
            'thumbnail': r're:^https?://[^?#]+lcxgwod5hapghvw',
            'series': 'WeTV PICK-A-BOO',
            'episode': 'Episode 0',
            'episode_number': 0,
            'duration': 442,
        },
    }]

    def _real_extract(self, url):
        return self._extract_episode(url)


class WeTvSeriesIE(WeTvBaseIE):
    _VALID_URL = WeTvBaseIE._VALID_URL_BASE + r'/(?P<id>\w+)(?:-[^/?#]+)?/?(?:[?#]|$)'

    _TESTS = [{
        'url': 'https://wetv.vip/play/air11ooo2rdsdi3-Cute-Programmer',
        'info_dict': {
            'id': 'air11ooo2rdsdi3',
            'title': 'Cute Programmer',
            'description': 'md5:e87beab3bf9f392d6b9e541a63286343',
        },
        'playlist_count': 30,
    }, {
        'url': 'https://wetv.vip/en/play/u37kgfnfzs73kiu-You-Are-My-Glory',
        'info_dict': {
            'id': 'u37kgfnfzs73kiu',
            'title': 'You Are My Glory',
            'description': 'md5:831363a4c3b4d7615e1f3854be3a123b',
        },
        'playlist_count': 32,
    }]

    def _real_extract(self, url):
        return self._extract_series(url, WeTvEpisodeIE)


class IflixBaseIE(WeTvBaseIE):
    _VALID_URL_BASE = r'https?://(?:www\.)?iflix\.com/(?:[^?#]+/)?play'

    _API_URL = 'https://vplay.iflix.com/getvinfo'
    _APP_VERSION = '3.5.57'
    _PLATFORM = '330201'
    _HOST = 'www.iflix.com'
    _REFERER = 'www.iflix.com'


class IflixEpisodeIE(IflixBaseIE):
    IE_NAME = 'iflix:episode'
    _VALID_URL = IflixBaseIE._VALID_URL_BASE + r'/(?P<series_id>\w+)(?:-[^?#]+)?/(?P<id>\w+)(?:-[^?#]+)?'

    _TESTS = [{
        'url': 'https://www.iflix.com/en/play/daijrxu03yypu0s/a0040kvgaza',
        'md5': '9740f9338c3a2105290d16b68fb3262f',
        'info_dict': {
            'id': 'a0040kvgaza',
            'ext': 'mp4',
            'title': 'EP1: Put Your Head On My Shoulder 2021',
            'description': 'md5:c095a742d3b7da6dfedd0c8170727a42',
            'thumbnail': r're:^https?://[^?#]+daijrxu03yypu0s',
            'series': 'Put Your Head On My Shoulder 2021',
            'episode': 'Episode 1',
            'episode_number': 1,
            'duration': 2639,
        },
    }, {
        'url': 'https://www.iflix.com/en/play/fvvrcc3ra9lbtt1-Take-My-Brother-Away/i0029sd3gm1-EP1%EF%BC%9ATake-My-Brother-Away',
        'md5': '375c9b8478fdedca062274b2c2f53681',
        'info_dict': {
            'id': 'i0029sd3gm1',
            'ext': 'mp4',
            'title': 'EP1：Take My Brother Away',
            'description': 'md5:f0f7be1606af51cd94d5627de96b0c76',
            'thumbnail': r're:^https?://[^?#]+fvvrcc3ra9lbtt1',
            'series': 'Take My Brother Away',
            'episode': 'Episode 1',
            'episode_number': 1,
            'duration': 228,
        },
    }]

    def _real_extract(self, url):
        return self._extract_episode(url)


class IflixSeriesIE(IflixBaseIE):
    _VALID_URL = IflixBaseIE._VALID_URL_BASE + r'/(?P<id>\w+)(?:-[^/?#]+)?/?(?:[?#]|$)'

    _TESTS = [{
        'url': 'https://www.iflix.com/en/play/g21a6qk4u1s9x22-You-Are-My-Hero',
        'info_dict': {
            'id': 'g21a6qk4u1s9x22',
            'title': 'You Are My Hero',
            'description': 'md5:9c4d844bc0799cd3d2b5aed758a2050a',
        },
        'playlist_count': 40,
    }, {
        'url': 'https://www.iflix.com/play/0s682hc45t0ohll',
        'info_dict': {
            'id': '0s682hc45t0ohll',
            'title': 'Miss Gu Who Is Silent',
            'description': 'md5:a9651d0236f25af06435e845fa2f8c78',
        },
        'playlist_count': 20,
    }]

    def _real_extract(self, url):
        return self._extract_series(url, IflixEpisodeIE)
Commit	Line	Data
b2a4db42 E	1	import functools
	2	import random
	3	import re
	4	import string
	5	import time
	6
	7	from .common import InfoExtractor
	8	from ..aes import aes_cbc_encrypt_bytes
	9	from ..utils import (
	10	ExtractorError,
	11	determine_ext,
	12	int_or_none,
	13	js_to_json,
	14	traverse_obj,
	15	urljoin,
	16	)
	17
	18
	19	class TencentBaseIE(InfoExtractor):
	20	"""Subclasses must set _API_URL, _APP_VERSION, _PLATFORM, _HOST, _REFERER"""
	21
	22	def _get_ckey(self, video_id, url, guid):
	23	ua = self.get_param('http_headers')['User-Agent']
	24
	25	payload = (f'{video_id}\|{int(time.time())}\|mg3c3b04ba\|{self._APP_VERSION}\|{guid}\|'
	26	f'{self._PLATFORM}\|{url[:48]}\|{ua.lower()[:48]}\|\|Mozilla\|Netscape\|Windows x86_64\|00\|')
	27
	28	return aes_cbc_encrypt_bytes(
	29	bytes(f'\|{sum(map(ord, payload))}\|{payload}', 'utf-8'),
	30	b'Ok\xda\xa3\x9e/\x8c\xb0\x7f^r-\x9e\xde\xf3\x14',
	31	b'\x01PJ\xf3V\xe6\x19\xcf.B\xbb\xa6\x8c?p\xf9',
	32	padding_mode='whitespace').hex().upper()
	33
	34	def _get_video_api_response(self, video_url, video_id, series_id, subtitle_format, video_format, video_quality):
	35	guid = ''.join([random.choice(string.digits + string.ascii_lowercase) for _ in range(16)])
	36	ckey = self._get_ckey(video_id, video_url, guid)
	37	query = {
	38	'vid': video_id,
	39	'cid': series_id,
	40	'cKey': ckey,
	41	'encryptVer': '8.1',
	42	'spcaptiontype': '1' if subtitle_format == 'vtt' else '0',
	43	'sphls': '2' if video_format == 'hls' else '0',
	44	'dtype': '3' if video_format == 'hls' else '0',
	45	'defn': video_quality,
	46	'spsrt': '2', # Enable subtitles
	47	'sphttps': '1', # Enable HTTPS
	48	'otype': 'json',
	49	'spwm': '1',
	50	# For SHD
	51	'host': self._HOST,
	52	'referer': self._REFERER,
	53	'ehost': video_url,
	54	'appVer': self._APP_VERSION,
	55	'platform': self._PLATFORM,
	56	# For VQQ
	57	'guid': guid,
	58	'flowid': ''.join(random.choice(string.digits + string.ascii_lowercase) for _ in range(32)),
	59	}
	60
	61	return self._search_json(r'QZOutputJson=', self._download_webpage(
	62	self._API_URL, video_id, query=query), 'api_response', video_id)
	63
	64	def _extract_video_formats_and_subtitles(self, api_response, video_id):
65	video_response = api_response['vl']['vi'][0]
66	video_width, video_height = video_response.get('vw'), video_response.get('vh')
67
68	formats, subtitles = [], {}
69	for video_format in video_response['ul']['ui']:
70	if video_format.get('hls'):
71	fmts, subs = self._extract_m3u8_formats_and_subtitles(
72	video_format['url'] + video_format['hls']['pt'], video_id, 'mp4', fatal=False)
73	for f in fmts:
74	f.update({'width': video_width, 'height': video_height})
75
76	formats.extend(fmts)
77	self._merge_subtitles(subs, target=subtitles)
78	else:
79	formats.append({
80	'url': f'{video_format["url"]}{video_response["fn"]}?vkey={video_response["fvkey"]}',
81	'width': video_width,
82	'height': video_height,
83	'ext': 'mp4',
84	})
85
86	return formats, subtitles
87
88	def _extract_video_native_subtitles(self, api_response, subtitles_format):
89	subtitles = {}
90	for subtitle in traverse_obj(api_response, ('sfl', 'fi')) or ():
91	subtitles.setdefault(subtitle['lang'].lower(), []).append({
92	'url': subtitle['url'],
93	'ext': subtitles_format,
94	'protocol': 'm3u8_native' if determine_ext(subtitle['url']) == 'm3u8' else 'http',
95	})
96
97	return subtitles
98
99	def _extract_all_video_formats_and_subtitles(self, url, video_id, series_id):
100	formats, subtitles = [], {}
101	for video_format, subtitle_format, video_quality in (
102	# '': 480p, 'shd': 720p, 'fhd': 1080p
103	('mp4', 'srt', ''), ('hls', 'vtt', 'shd'), ('hls', 'vtt', 'fhd')):
104	api_response = self._get_video_api_response(
105	url, video_id, series_id, subtitle_format, video_format, video_quality)
106
107	if api_response.get('em') != 0 and api_response.get('exem') != 0:
108	if '您所在区域暂无此内容版权' in api_response.get('msg'):
109	self.raise_geo_restricted()
110	raise ExtractorError(f'Tencent said: {api_response.get("msg")}')
111
112	fmts, subs = self._extract_video_formats_and_subtitles(api_response, video_id)
113	native_subtitles = self._extract_video_native_subtitles(api_response, subtitle_format)
114
115	formats.extend(fmts)
116	self._merge_subtitles(subs, native_subtitles, target=subtitles)
117
118	self._sort_formats(formats)
119	return formats, subtitles
120
121	def _get_clean_title(self, title):
122	return re.sub(
123	r'\s[_\-]\s(?:Watch online\|腾讯视频\|(?:高清)?1080P在线观看平台).*?$',
124	'', title or '').strip() or None
125
126
127	class VQQBaseIE(TencentBaseIE):
128	_VALID_URL_BASE = r'https?://v\.qq\.com'
129
130	_API_URL = 'https://h5vv6.video.qq.com/getvinfo'
131	_APP_VERSION = '3.5.57'
132	_PLATFORM = '10901'
133	_HOST = 'v.qq.com'
134	_REFERER = 'v.qq.com'
135
136	def _get_webpage_metadata(self, webpage, video_id):
137	return self._parse_json(
138	self._search_regex(
139	r'(?s)<script[^>]>[^<]window\.__pinia\s=\s([^<]+)</script>',
140	webpage, 'pinia data', fatal=False),
141	video_id, transform_source=js_to_json, fatal=False)
142
143
144	class VQQVideoIE(VQQBaseIE):
145	IE_NAME = 'vqq:video'
146	_VALID_URL = VQQBaseIE._VALID_URL_BASE + r'/x/(?:page\|cover/(?P<series_id>\w+))/(?P<id>\w+)'
147
148	_TESTS = [{
149	'url': 'https://v.qq.com/x/page/q326831cny0.html',
150	'md5': '826ef93682df09e3deac4a6e6e8cdb6e',
151	'info_dict': {
152	'id': 'q326831cny0',
153	'ext': 'mp4',
154	'title': '我是选手：雷霆裂阵，终极时刻',
155	'description': 'md5:e7ed70be89244017dac2a835a10aeb1e',
156	'thumbnail': r're:^https?://[^?#]+q326831cny0',
157	},
158	}, {
159	'url': 'https://v.qq.com/x/page/o3013za7cse.html',
160	'md5': 'b91cbbeada22ef8cc4b06df53e36fa21',
161	'info_dict': {
162	'id': 'o3013za7cse',
163	'ext': 'mp4',
164	'title': '欧阳娜娜VLOG',
165	'description': 'md5:29fe847497a98e04a8c3826e499edd2e',
166	'thumbnail': r're:^https?://[^?#]+o3013za7cse',
167	},
168	}, {
169	'url': 'https://v.qq.com/x/cover/7ce5noezvafma27/a00269ix3l8.html',
170	'md5': '71459c5375c617c265a22f083facce67',
171	'info_dict': {
172	'id': 'a00269ix3l8',
173	'ext': 'mp4',
174	'title': '鸡毛飞上天第01集',
175	'description': 'md5:8cae3534327315b3872fbef5e51b5c5b',
176	'thumbnail': r're:^https?://[^?#]+7ce5noezvafma27',
177	'series': '鸡毛飞上天',
178	},
179	}, {
180	'url': 'https://v.qq.com/x/cover/mzc00200p29k31e/s0043cwsgj0.html',
181	'md5': '96b9fd4a189fdd4078c111f21d7ac1bc',
182	'info_dict': {
183	'id': 's0043cwsgj0',
184	'ext': 'mp4',
185	'title': '第1集：如何快乐吃糖？',
186	'description': 'md5:1d8c3a0b8729ae3827fa5b2d3ebd5213',
187	'thumbnail': r're:^https?://[^?#]+s0043cwsgj0',
188	'series': '青年理工工作者生活研究所',
189	},
190	}]
191
192	def _real_extract(self, url):
193	video_id, series_id = self._match_valid_url(url).group('id', 'series_id')
194	webpage = self._download_webpage(url, video_id)
195	webpage_metadata = self._get_webpage_metadata(webpage, video_id)
196
197	formats, subtitles = self._extract_all_video_formats_and_subtitles(url, video_id, series_id)
198	return {
199	'id': video_id,
200	'title': self._get_clean_title(self._og_search_title(webpage)
201	or traverse_obj(webpage_metadata, ('global', 'videoInfo', 'title'))),
202	'description': (self._og_search_description(webpage)
203	or traverse_obj(webpage_metadata, ('global', 'videoInfo', 'desc'))),
204	'formats': formats,
205	'subtitles': subtitles,
206	'thumbnail': (self._og_search_thumbnail(webpage)
207	or traverse_obj(webpage_metadata, ('global', 'videoInfo', 'pic160x90'))),
208	'series': traverse_obj(webpage_metadata, ('global', 'coverInfo', 'title')),
209	}
210
211
212	class VQQSeriesIE(VQQBaseIE):
213	IE_NAME = 'vqq:series'
214	_VALID_URL = VQQBaseIE._VALID_URL_BASE + r'/x/cover/(?P<id>\w+)\.html/?(?:[?#]\|$)'
215
216	_TESTS = [{
217	'url': 'https://v.qq.com/x/cover/7ce5noezvafma27.html',
218	'info_dict': {
219	'id': '7ce5noezvafma27',
220	'title': '鸡毛飞上天',
221	'description': 'md5:8cae3534327315b3872fbef5e51b5c5b',
222	},
223	'playlist_count': 55,
224	}, {
225	'url': 'https://v.qq.com/x/cover/oshd7r0vy9sfq8e.html',
226	'info_dict': {
227	'id': 'oshd7r0vy9sfq8e',
228	'title': '恋爱细胞2',
229	'description': 'md5:9d8a2245679f71ca828534b0f95d2a03',
230	},
231	'playlist_count': 12,
232	}]
233
234	def _real_extract(self, url):
235	series_id = self._match_id(url)
236	webpage = self._download_webpage(url, series_id)
237	webpage_metadata = self._get_webpage_metadata(webpage, series_id)
238
239	episode_paths = [f'/x/cover/{series_id}/{video_id}.html' for video_id in re.findall(
240	r'<div[^>]+data-vid="(?P<video_id>[^"]+)"[^>]+class="[^"]+episode-item-rect--number',
241	webpage)]
242
243	return self.playlist_from_matches(
244	episode_paths, series_id, ie=VQQVideoIE, getter=functools.partial(urljoin, url),
245	title=self._get_clean_title(traverse_obj(webpage_metadata, ('coverInfo', 'title'))
246	or self._og_search_title(webpage)),
247	description=(traverse_obj(webpage_metadata, ('coverInfo', 'description'))
248	or self._og_search_description(webpage)))
249
250
251	class WeTvBaseIE(TencentBaseIE):
252	_VALID_URL_BASE = r'https?://(?:www\.)?wetv\.vip/(?:[^?#]+/)?play'
253
254	_API_URL = 'https://play.wetv.vip/getvinfo'
255	_APP_VERSION = '3.5.57'
256	_PLATFORM = '4830201'
257	_HOST = 'wetv.vip'
258	_REFERER = 'wetv.vip'
259
260	def _get_webpage_metadata(self, webpage, video_id):
261	return self._parse_json(
262	traverse_obj(self._search_nextjs_data(webpage, video_id), ('props', 'pageProps', 'data')),
263	video_id, fatal=False)
264
48f535f5 E	265	def _extract_episode(self, url):
	266	video_id, series_id = self._match_valid_url(url).group('id', 'series_id')
	267	webpage = self._download_webpage(url, video_id)
	268	webpage_metadata = self._get_webpage_metadata(webpage, video_id)
	269
	270	formats, subtitles = self._extract_all_video_formats_and_subtitles(url, video_id, series_id)
	271	return {
	272	'id': video_id,
	273	'title': self._get_clean_title(self._og_search_title(webpage)
	274	or traverse_obj(webpage_metadata, ('coverInfo', 'title'))),
	275	'description': (traverse_obj(webpage_metadata, ('coverInfo', 'description'))
	276	or self._og_search_description(webpage)),
	277	'formats': formats,
	278	'subtitles': subtitles,
	279	'thumbnail': self._og_search_thumbnail(webpage),
	280	'duration': int_or_none(traverse_obj(webpage_metadata, ('videoInfo', 'duration'))),
	281	'series': traverse_obj(webpage_metadata, ('coverInfo', 'title')),
	282	'episode_number': int_or_none(traverse_obj(webpage_metadata, ('videoInfo', 'episode'))),
	283	}
	284
	285	def _extract_series(self, url, ie):
	286	series_id = self._match_id(url)
	287	webpage = self._download_webpage(url, series_id)
	288	webpage_metadata = self._get_webpage_metadata(webpage, series_id)
	289
	290	episode_paths = ([f'/play/{series_id}/{episode["vid"]}' for episode in webpage_metadata.get('videoList')]
	291	or re.findall(r'<a[^>]+class="play-video__link"[^>]+href="(?P<path>[^"]+)', webpage))
	292
	293	return self.playlist_from_matches(
	294	episode_paths, series_id, ie=ie, getter=functools.partial(urljoin, url),
	295	title=self._get_clean_title(traverse_obj(webpage_metadata, ('coverInfo', 'title'))
	296	or self._og_search_title(webpage)),
	297	description=(traverse_obj(webpage_metadata, ('coverInfo', 'description'))
	298	or self._og_search_description(webpage)))
	299
b2a4db42 E	300
	301	class WeTvEpisodeIE(WeTvBaseIE):
	302	IE_NAME = 'wetv:episode'
	303	_VALID_URL = WeTvBaseIE._VALID_URL_BASE + r'/(?P<series_id>\w+)(?:-[^?#]+)?/(?P<id>\w+)(?:-[^?#]+)?'
	304
	305	_TESTS = [{
	306	'url': 'https://wetv.vip/en/play/air11ooo2rdsdi3-Cute-Programmer/v0040pr89t9-EP1-Cute-Programmer',
	307	'md5': '0c70fdfaa5011ab022eebc598e64bbbe',
	308	'info_dict': {
	309	'id': 'v0040pr89t9',
	310	'ext': 'mp4',
	311	'title': 'EP1: Cute Programmer',
	312	'description': 'md5:e87beab3bf9f392d6b9e541a63286343',
	313	'thumbnail': r're:^https?://[^?#]+air11ooo2rdsdi3',
	314	'series': 'Cute Programmer',
	315	'episode': 'Episode 1',
	316	'episode_number': 1,
	317	'duration': 2835,
	318	},
	319	}, {
	320	'url': 'https://wetv.vip/en/play/u37kgfnfzs73kiu/p0039b9nvik',
	321	'md5': '3b3c15ca4b9a158d8d28d5aa9d7c0a49',
	322	'info_dict': {
	323	'id': 'p0039b9nvik',
	324	'ext': 'mp4',
	325	'title': 'EP1: You Are My Glory',
	326	'description': 'md5:831363a4c3b4d7615e1f3854be3a123b',
	327	'thumbnail': r're:^https?://[^?#]+u37kgfnfzs73kiu',
	328	'series': 'You Are My Glory',
	329	'episode': 'Episode 1',
	330	'episode_number': 1,
	331	'duration': 2454,
	332	},
	333	}, {
	334	'url': 'https://wetv.vip/en/play/lcxgwod5hapghvw-WeTV-PICK-A-BOO/i0042y00lxp-Zhao-Lusi-Describes-The-First-Experiences-She-Had-In-Who-Rules-The-World-%7C-WeTV-PICK-A-BOO',
	335	'md5': '71133f5c2d5d6cad3427e1b010488280',
	336	'info_dict': {
	337	'id': 'i0042y00lxp',
	338	'ext': 'mp4',
	339	'title': 'md5:f7a0857dbe5fbbe2e7ad630b92b54e6a',
	340	'description': 'md5:76260cb9cdc0ef76826d7ca9d92fadfa',
	341	'thumbnail': r're:^https?://[^?#]+lcxgwod5hapghvw',
	342	'series': 'WeTV PICK-A-BOO',
	343	'episode': 'Episode 0',
	344	'episode_number': 0,
	345	'duration': 442,
	346	},
	347	}]
	348
	349	def _real_extract(self, url):
48f535f5	350	return self._extract_episode(url)
b2a4db42 E	351
	352
	353	class WeTvSeriesIE(WeTvBaseIE):
	354	_VALID_URL = WeTvBaseIE._VALID_URL_BASE + r'/(?P<id>\w+)(?:-[^/?#]+)?/?(?:[?#]\|$)'
	355
	356	_TESTS = [{
	357	'url': 'https://wetv.vip/play/air11ooo2rdsdi3-Cute-Programmer',
	358	'info_dict': {
	359	'id': 'air11ooo2rdsdi3',
	360	'title': 'Cute Programmer',
	361	'description': 'md5:e87beab3bf9f392d6b9e541a63286343',
	362	},
	363	'playlist_count': 30,
	364	}, {
	365	'url': 'https://wetv.vip/en/play/u37kgfnfzs73kiu-You-Are-My-Glory',
	366	'info_dict': {
	367	'id': 'u37kgfnfzs73kiu',
	368	'title': 'You Are My Glory',
	369	'description': 'md5:831363a4c3b4d7615e1f3854be3a123b',
	370	},
	371	'playlist_count': 32,
	372	}]
	373
	374	def _real_extract(self, url):
48f535f5	375	return self._extract_series(url, WeTvEpisodeIE)
b2a4db42	376
b2a4db42	377
48f535f5 E	378	class IflixBaseIE(WeTvBaseIE):
	379	_VALID_URL_BASE = r'https?://(?:www\.)?iflix\.com/(?:[^?#]+/)?play'
	380
	381	_API_URL = 'https://vplay.iflix.com/getvinfo'
	382	_APP_VERSION = '3.5.57'
	383	_PLATFORM = '330201'
	384	_HOST = 'www.iflix.com'
	385	_REFERER = 'www.iflix.com'
	386
	387
	388	class IflixEpisodeIE(IflixBaseIE):
	389	IE_NAME = 'iflix:episode'
	390	_VALID_URL = IflixBaseIE._VALID_URL_BASE + r'/(?P<series_id>\w+)(?:-[^?#]+)?/(?P<id>\w+)(?:-[^?#]+)?'
	391
	392	_TESTS = [{
	393	'url': 'https://www.iflix.com/en/play/daijrxu03yypu0s/a0040kvgaza',
	394	'md5': '9740f9338c3a2105290d16b68fb3262f',
	395	'info_dict': {
	396	'id': 'a0040kvgaza',
	397	'ext': 'mp4',
	398	'title': 'EP1: Put Your Head On My Shoulder 2021',
	399	'description': 'md5:c095a742d3b7da6dfedd0c8170727a42',
	400	'thumbnail': r're:^https?://[^?#]+daijrxu03yypu0s',
	401	'series': 'Put Your Head On My Shoulder 2021',
	402	'episode': 'Episode 1',
	403	'episode_number': 1,
	404	'duration': 2639,
	405	},
	406	}, {
	407	'url': 'https://www.iflix.com/en/play/fvvrcc3ra9lbtt1-Take-My-Brother-Away/i0029sd3gm1-EP1%EF%BC%9ATake-My-Brother-Away',
	408	'md5': '375c9b8478fdedca062274b2c2f53681',
	409	'info_dict': {
	410	'id': 'i0029sd3gm1',
	411	'ext': 'mp4',
	412	'title': 'EP1：Take My Brother Away',
	413	'description': 'md5:f0f7be1606af51cd94d5627de96b0c76',
	414	'thumbnail': r're:^https?://[^?#]+fvvrcc3ra9lbtt1',
	415	'series': 'Take My Brother Away',
	416	'episode': 'Episode 1',
	417	'episode_number': 1,
	418	'duration': 228,
	419	},
	420	}]
	421
	422	def _real_extract(self, url):
	423	return self._extract_episode(url)
	424
	425
	426	class IflixSeriesIE(IflixBaseIE):
	427	_VALID_URL = IflixBaseIE._VALID_URL_BASE + r'/(?P<id>\w+)(?:-[^/?#]+)?/?(?:[?#]\|$)'
	428
	429	_TESTS = [{
	430	'url': 'https://www.iflix.com/en/play/g21a6qk4u1s9x22-You-Are-My-Hero',
	431	'info_dict': {
	432	'id': 'g21a6qk4u1s9x22',
	433	'title': 'You Are My Hero',
	434	'description': 'md5:9c4d844bc0799cd3d2b5aed758a2050a',
	435	},
	436	'playlist_count': 40,
	437	}, {
	438	'url': 'https://www.iflix.com/play/0s682hc45t0ohll',
	439	'info_dict': {
	440	'id': '0s682hc45t0ohll',
	441	'title': 'Miss Gu Who Is Silent',
442	'description': 'md5:a9651d0236f25af06435e845fa2f8c78',
443	},
444	'playlist_count': 20,
445	}]
446
447	def _real_extract(self, url):
448	return self._extract_series(url, IflixEpisodeIE)