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

import functools
import re
import time

from .common import InfoExtractor
from ..aes import aes_cbc_encrypt
from ..utils import bytes_to_intlist, determine_ext, intlist_to_bytes, int_or_none, traverse_obj, urljoin


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

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

        payload = (f'{video_id}|{int(time.time())}|mg3c3b04ba|{app_version}|0000000000000000|'
                   f'{platform}|{url[:48]}|{ua.lower()[:48]}||Mozilla|Netscape|Win32|00|')

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

        return intlist_to_bytes(ciphertext_int_bytes).hex()

    def _get_video_api_response(self, video_url, video_id, series_id, subtitle_format, video_format, video_quality):
        app_version = '3.5.57'
        platform = '4830201'

        ckey = self._get_ckey(video_id, video_url, app_version, platform)
        query = {
            'vid': video_id,
            'cid': series_id,
            'cKey': ckey,
            'encryptVer': '8.1',
            'spcaptiontype': '1' if subtitle_format == 'vtt' else '0',  # 0 - SRT, 1 - VTT
            'sphls': '1' if video_format == 'hls' else '0',  # 0 - MP4, 1 - HLS
            'defn': video_quality,  # '': 480p, 'shd': 720p, 'fhd': 1080p
            'spsrt': '1',  # Enable subtitles
            'sphttps': '1',  # Enable HTTPS
            'otype': 'json',  # Response format: xml, json,
            'dtype': '1',
            'spwm': '1',
            'host': 'wetv.vip',  # These three values are needed for SHD
            'referer': 'wetv.vip',
            'ehost': video_url,
            'appVer': app_version,
            'platform': platform,
        }

        return self._search_json(r'QZOutputJson=', self._download_webpage(
            'https://play.wetv.vip/getvinfo', video_id, query=query), 'api_response', video_id)

    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)


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': 'a046f565c9dce9b263a0465a422cd7bf',
        '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': '4d9d69bcfd11da61f4aae64fc6b316b3',
        '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 _extract_video_formats_and_subtitles(self, api_response, video_id, video_quality):
        video_response = api_response['vl']['vi'][0]
        video_width = video_response.get('vw')
        video_height = 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']['pname'], video_id, 'mp4', fatal=False)
                for f in fmts:
                    f['width'] = video_width
                    f['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_subtitles(self, api_response, subtitles_format):
        subtitles = {}
        for subtitle in traverse_obj(api_response, ('sfl', 'fi')):
            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 _real_extract(self, url):
        video_id, series_id = self._match_valid_url(url).group('id', 'series_id')
        webpage = self._download_webpage(url, video_id)

        formats, subtitles = [], {}
        for video_format, subtitle_format, video_quality in (('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)

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

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

        self._sort_formats(formats)
        webpage_metadata = self._get_webpage_metadata(webpage, video_id)

        return {
            'id': video_id,
            'title': (self._og_search_title(webpage)
                      or traverse_obj(webpage_metadata, ('coverInfo', 'description'))),
            'description': (self._og_search_description(webpage)
                            or traverse_obj(webpage_metadata, ('coverInfo', 'description'))),
            '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'))),
        }


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

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

        return self.playlist_from_matches(
            episode_paths, series_id, ie=WeTvEpisodeIE, getter=functools.partial(urljoin, url),
            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))
Commit	Line	Data
ce7f6aa6	1	import functools
2aab569f E	2	import re
	3	import time
	4
	5	from .common import InfoExtractor
	6	from ..aes import aes_cbc_encrypt
ce7f6aa6	7	from ..utils import bytes_to_intlist, determine_ext, intlist_to_bytes, int_or_none, traverse_obj, urljoin
2aab569f E	8
	9
	10	class WeTvBaseIE(InfoExtractor):
	11	_VALID_URL_BASE = r'https?://(?:www\.)?wetv\.vip/(?:[^?#]+/)?play'
	12
	13	def _get_ckey(self, video_id, url, app_version, platform):
	14	ua = self.get_param('http_headers')['User-Agent']
	15
	16	payload = (f'{video_id}\|{int(time.time())}\|mg3c3b04ba\|{app_version}\|0000000000000000\|'
	17	f'{platform}\|{url[:48]}\|{ua.lower()[:48]}\|\|Mozilla\|Netscape\|Win32\|00\|')
	18
	19	ciphertext_int_bytes = aes_cbc_encrypt(
	20	bytes_to_intlist(bytes(f'\|{sum(map(ord, payload))}\|{payload}', 'utf-8')),
	21	bytes_to_intlist(b'Ok\xda\xa3\x9e/\x8c\xb0\x7f^r-\x9e\xde\xf3\x14'),
	22	bytes_to_intlist(b'\x01PJ\xf3V\xe6\x19\xcf.B\xbb\xa6\x8c?p\xf9'),
	23	'whitespace')
	24
	25	return intlist_to_bytes(ciphertext_int_bytes).hex()
	26
	27	def _get_video_api_response(self, video_url, video_id, series_id, subtitle_format, video_format, video_quality):
	28	app_version = '3.5.57'
	29	platform = '4830201'
	30
	31	ckey = self._get_ckey(video_id, video_url, app_version, platform)
	32	query = {
	33	'vid': video_id,
	34	'cid': series_id,
	35	'cKey': ckey,
	36	'encryptVer': '8.1',
	37	'spcaptiontype': '1' if subtitle_format == 'vtt' else '0', # 0 - SRT, 1 - VTT
	38	'sphls': '1' if video_format == 'hls' else '0', # 0 - MP4, 1 - HLS
	39	'defn': video_quality, # '': 480p, 'shd': 720p, 'fhd': 1080p
	40	'spsrt': '1', # Enable subtitles
	41	'sphttps': '1', # Enable HTTPS
	42	'otype': 'json', # Response format: xml, json,
	43	'dtype': '1',
	44	'spwm': '1',
	45	'host': 'wetv.vip', # These three values are needed for SHD
	46	'referer': 'wetv.vip',
	47	'ehost': video_url,
	48	'appVer': app_version,
	49	'platform': platform,
	50	}
	51
	52	return self._search_json(r'QZOutputJson=', self._download_webpage(
	53	'https://play.wetv.vip/getvinfo', video_id, query=query), 'api_response', video_id)
	54
	55	def _get_webpage_metadata(self, webpage, video_id):
	56	return self._parse_json(
	57	traverse_obj(self._search_nextjs_data(webpage, video_id), ('props', 'pageProps', 'data')),
	58	video_id, fatal=False)
	59
	60
	61	class WeTvEpisodeIE(WeTvBaseIE):
	62	IE_NAME = 'wetv:episode'
	63	_VALID_URL = WeTvBaseIE._VALID_URL_BASE + r'/(?P<series_id>\w+)(?:-[^?#]+)?/(?P<id>\w+)(?:-[^?#]+)?'
	64
	65	_TESTS = [{
	66	'url': 'https://wetv.vip/en/play/air11ooo2rdsdi3-Cute-Programmer/v0040pr89t9-EP1-Cute-Programmer',
	67	'md5': 'a046f565c9dce9b263a0465a422cd7bf',
	68	'info_dict': {
	69	'id': 'v0040pr89t9',
	70	'ext': 'mp4',
	71	'title': 'EP1: Cute Programmer',
72	'description': 'md5:e87beab3bf9f392d6b9e541a63286343',
73	'thumbnail': r're:^https?://[^?#]+air11ooo2rdsdi3',
74	'series': 'Cute Programmer',
75	'episode': 'Episode 1',
76	'episode_number': 1,
77	'duration': 2835,
78	},
79	}, {
80	'url': 'https://wetv.vip/en/play/u37kgfnfzs73kiu/p0039b9nvik',
81	'md5': '4d9d69bcfd11da61f4aae64fc6b316b3',
82	'info_dict': {
83	'id': 'p0039b9nvik',
84	'ext': 'mp4',
85	'title': 'EP1: You Are My Glory',
86	'description': 'md5:831363a4c3b4d7615e1f3854be3a123b',
87	'thumbnail': r're:^https?://[^?#]+u37kgfnfzs73kiu',
88	'series': 'You Are My Glory',
89	'episode': 'Episode 1',
90	'episode_number': 1,
91	'duration': 2454,
92	},
93	}, {
94	'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',
95	'md5': '71133f5c2d5d6cad3427e1b010488280',
96	'info_dict': {
97	'id': 'i0042y00lxp',
98	'ext': 'mp4',
99	'title': 'md5:f7a0857dbe5fbbe2e7ad630b92b54e6a',
100	'description': 'md5:76260cb9cdc0ef76826d7ca9d92fadfa',
101	'thumbnail': r're:^https?://[^?#]+lcxgwod5hapghvw',
102	'series': 'WeTV PICK-A-BOO',
103	'episode': 'Episode 0',
104	'episode_number': 0,
105	'duration': 442,
106	},
107	}]
108
109	def _extract_video_formats_and_subtitles(self, api_response, video_id, video_quality):
110	video_response = api_response['vl']['vi'][0]
111	video_width = video_response.get('vw')
112	video_height = video_response.get('vh')
113
114	formats, subtitles = [], {}
115	for video_format in video_response['ul']['ui']:
116	if video_format.get('hls'):
117	fmts, subs = self._extract_m3u8_formats_and_subtitles(
118	video_format['url'] + video_format['hls']['pname'], video_id, 'mp4', fatal=False)
119	for f in fmts:
120	f['width'] = video_width
121	f['height'] = video_height
122
123	formats.extend(fmts)
124	self._merge_subtitles(subs, target=subtitles)
125	else:
126	formats.append({
127	'url': f'{video_format["url"]}{video_response["fn"]}?vkey={video_response["fvkey"]}',
128	'width': video_width,
129	'height': video_height,
130	'ext': 'mp4',
131	})
132
133	return formats, subtitles
134
135	def _extract_video_subtitles(self, api_response, subtitles_format):
136	subtitles = {}
137	for subtitle in traverse_obj(api_response, ('sfl', 'fi')):
138	subtitles.setdefault(subtitle['lang'].lower(), []).append({
139	'url': subtitle['url'],
140	'ext': subtitles_format,
141	'protocol': 'm3u8_native' if determine_ext(subtitle['url']) == 'm3u8' else 'http',
142	})
143
144	return subtitles
145
146	def _real_extract(self, url):
147	video_id, series_id = self._match_valid_url(url).group('id', 'series_id')
148	webpage = self._download_webpage(url, video_id)
149
150	formats, subtitles = [], {}
151	for video_format, subtitle_format, video_quality in (('mp4', 'srt', ''), ('hls', 'vtt', 'shd'), ('hls', 'vtt', 'fhd')):
152	api_response = self._get_video_api_response(url, video_id, series_id, subtitle_format, video_format, video_quality)
153
154	fmts, subs = self._extract_video_formats_and_subtitles(api_response, video_id, video_quality)
155	native_subtitles = self._extract_video_subtitles(api_response, subtitle_format)
156
157	formats.extend(fmts)
158	self._merge_subtitles(subs, native_subtitles, target=subtitles)
159
160	self._sort_formats(formats)
161	webpage_metadata = self._get_webpage_metadata(webpage, video_id)
162
163	return {
164	'id': video_id,
165	'title': (self._og_search_title(webpage)
166	or traverse_obj(webpage_metadata, ('coverInfo', 'description'))),
167	'description': (self._og_search_description(webpage)
168	or traverse_obj(webpage_metadata, ('coverInfo', 'description'))),
169	'formats': formats,
170	'subtitles': subtitles,
171	'thumbnail': self._og_search_thumbnail(webpage),
172	'duration': int_or_none(traverse_obj(webpage_metadata, ('videoInfo', 'duration'))),
173	'series': traverse_obj(webpage_metadata, ('coverInfo', 'title')),
174	'episode_number': int_or_none(traverse_obj(webpage_metadata, ('videoInfo', 'episode'))),
175	}
176
177
178	class WeTvSeriesIE(WeTvBaseIE):
179	_VALID_URL = WeTvBaseIE._VALID_URL_BASE + r'/(?P<id>\w+)(?:-[^/?#]+)?/?(?:[?#]\|$)'
180
181	_TESTS = [{
182	'url': 'https://wetv.vip/play/air11ooo2rdsdi3-Cute-Programmer',
183	'info_dict': {
184	'id': 'air11ooo2rdsdi3',
185	'title': 'Cute Programmer',
186	'description': 'md5:e87beab3bf9f392d6b9e541a63286343',
187	},
188	'playlist_count': 30,
189	}, {
190	'url': 'https://wetv.vip/en/play/u37kgfnfzs73kiu-You-Are-My-Glory',
191	'info_dict': {
192	'id': 'u37kgfnfzs73kiu',
193	'title': 'You Are My Glory',
194	'description': 'md5:831363a4c3b4d7615e1f3854be3a123b',
195	},
196	'playlist_count': 32,
197	}]
198
199	def _real_extract(self, url):
200	series_id = self._match_id(url)
201	webpage = self._download_webpage(url, series_id)
202	webpage_metadata = self._get_webpage_metadata(webpage, series_id)
203
204	episode_paths = (re.findall(r'<a[^>]+class="play-video__link"[^>]+href="(?P<path>[^"]+)', webpage)
205	or [f'/{series_id}/{episode["vid"]}' for episode in webpage_metadata.get('videoList')])
206
207	return self.playlist_from_matches(
ce7f6aa6	208	episode_paths, series_id, ie=WeTvEpisodeIE, getter=functools.partial(urljoin, url),
2aab569f E	209	title=traverse_obj(webpage_metadata, ('coverInfo', 'title')) or self._og_search_title(webpage),
2aab569f E	210	description=traverse_obj(webpage_metadata, ('coverInfo', 'description')) or self._og_search_description(webpage))