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

import json

from .common import InfoExtractor
from ..utils import (
    int_or_none,
    js_to_json,
    parse_iso8601,
    str_or_none,
    traverse_obj,
)


class LikeeIE(InfoExtractor):
    IE_NAME = 'likee'
    _VALID_URL = r'(?x)https?://(www\.)?likee\.video/(?:(?P<channel_name>[^/]+)/video/|v/)(?P<id>\w+)'
    _TESTS = [{
        'url': 'https://likee.video/@huynh_hong_quan_/video/7093444807096327263',
        'info_dict': {
            'id': '7093444807096327263',
            'ext': 'mp4',
            'title': '🤴🤴🤴',
            'description': 'md5:9a7ebe816f0e78722ee5ed76f75983b4',
            'thumbnail': r're:^https?://.+\.jpg',
            'uploader': 'Huỳnh Hồng Qu&acirc;n ',
            'artist': 'Huỳnh Hồng Qu&acirc;n ',
            'timestamp': 1651571320,
            'upload_date': '20220503',
            'view_count': int,
            'uploader_id': 'huynh_hong_quan_',
            'duration': 12374,
            'comment_count': int,
            'like_count': int,
        },
    }, {
        'url': 'https://likee.video/@649222262/video/7093167848050058862',
        'info_dict': {
            'id': '7093167848050058862',
            'ext': 'mp4',
            'title': 'likee video #7093167848050058862',
            'description': 'md5:3f971c8c6ee8a216f2b1a9094c5de99f',
            'thumbnail': r're:^https?://.+\.jpg',
            'comment_count': int,
            'like_count': int,
            'uploader': 'Vương Phước Nhi',
            'timestamp': 1651506835,
            'upload_date': '20220502',
            'duration': 60024,
            'artist': 'Vương Phước Nhi',
            'uploader_id': '649222262',
            'view_count': int,
        },
    }, {
        'url': 'https://likee.video/@fernanda_rivasg/video/6932224568407629502',
        'info_dict': {
            'id': '6932224568407629502',
            'ext': 'mp4',
            'title': 'Un trend viejito🔥 #LIKEE #Ferlovers #trend ',
            'description': 'md5:c42b903a72a99d6d8b73e3d1126fbcef',
            'thumbnail': r're:^https?://.+\.jpg',
            'comment_count': int,
            'duration': 9684,
            'uploader_id': 'fernanda_rivasg',
            'view_count': int,
            'artist': 'La Cami La✨',
            'like_count': int,
            'uploader': 'Fernanda Rivas🎶',
            'timestamp': 1614034308,
            'upload_date': '20210222',
        },
    }, {
        'url': 'https://likee.video/v/k6QcOp',
        'info_dict': {
            'id': 'k6QcOp',
            'ext': 'mp4',
            'title': '#AguaChallenge t&uacute; ya lo intentaste?😱🤩',
            'description': 'md5:b0cc462689d4ff2b624daa4dba7640d9',
            'thumbnail': r're:^https?://.+\.jpg',
            'comment_count': int,
            'duration': 18014,
            'view_count': int,
            'timestamp': 1611694774,
            'like_count': int,
            'uploader': 'Fernanda Rivas🎶',
            'uploader_id': 'fernanda_rivasg',
            'artist': 'ʟᴇʀɪᴋ_ᴜɴɪᴄᴏʀɴ♡︎',
            'upload_date': '20210126',
        },
    }, {
        'url': 'https://www.likee.video/@649222262/video/7093167848050058862',
        'only_matching': True,
    }, {
        'url': 'https://www.likee.video/v/k6QcOp',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        video_id = self._match_id(url)
        webpage = self._download_webpage(url, video_id)
        info = self._parse_json(
            self._search_regex(r'window\.data\s=\s({.+?});', webpage, 'video info'),
            video_id, transform_source=js_to_json)
        video_url = traverse_obj(info, 'video_url', ('originVideoInfo', 'video_url'))
        if not video_url:
            self.raise_no_formats('Video was deleted', expected=True)
        formats = [{
            'format_id': 'mp4-with-watermark',
            'url': video_url,
            'height': info.get('video_height'),
            'width': info.get('video_width'),
        }, {
            'format_id': 'mp4-without-watermark',
            'url': video_url.replace('_4', ''),
            'height': info.get('video_height'),
            'width': info.get('video_width'),
            'quality': 1,
        }]
        return {
            'id': video_id,
            'title': info.get('msgText'),
            'description': info.get('share_desc'),
            'view_count': int_or_none(info.get('video_count')),
            'like_count': int_or_none(info.get('likeCount')),
            'comment_count': int_or_none(info.get('comment_count')),
            'uploader': str_or_none(info.get('nick_name')),
            'uploader_id': str_or_none(info.get('likeeId')),
            'artist': str_or_none(traverse_obj(info, ('sound', 'owner_name'))),
            'timestamp': parse_iso8601(info.get('uploadDate')),
            'thumbnail': info.get('coverUrl'),
            'duration': int_or_none(traverse_obj(info, ('option_data', 'dur'))),
            'formats': formats,
        }


class LikeeUserIE(InfoExtractor):
    IE_NAME = 'likee:user'
    _VALID_URL = r'https?://(www\.)?likee\.video/(?P<id>[^/]+)/?$'
    _TESTS = [{
        'url': 'https://likee.video/@fernanda_rivasg',
        'info_dict': {
            'id': '925638334',
            'title': 'fernanda_rivasg',
        },
        'playlist_mincount': 500,
    }, {
        'url': 'https://likee.video/@may_hmoob',
        'info_dict': {
            'id': '2943949041',
            'title': 'may_hmoob',
        },
        'playlist_mincount': 80,
    }]
    _PAGE_SIZE = 50
    _API_GET_USER_VIDEO = 'https://api.like-video.com/likee-activity-flow-micro/videoApi/getUserVideo'

    def _entries(self, user_name, user_id):
        last_post_id = ''
        while True:
            user_videos = self._download_json(
                self._API_GET_USER_VIDEO, user_name,
                data=json.dumps({
                    'uid': user_id,
                    'count': self._PAGE_SIZE,
                    'lastPostId': last_post_id,
                    'tabType': 0,
                }).encode('utf-8'),
                headers={'content-type': 'application/json'},
                note=f'Get user info with lastPostId #{last_post_id}')
            items = traverse_obj(user_videos, ('data', 'videoList'))
            if not items:
                break
            for item in items:
                last_post_id = item['postId']
                yield self.url_result(f'https://likee.video/{user_name}/video/{last_post_id}')

    def _real_extract(self, url):
        user_name = self._match_id(url)
        webpage = self._download_webpage(url, user_name)
        info = self._parse_json(
            self._search_regex(r'window\.data\s*=\s*({.+?});', webpage, 'user info'),
            user_name, transform_source=js_to_json)
        user_id = traverse_obj(info, ('userinfo', 'uid'))
        return self.playlist_result(self._entries(user_name, user_id), user_id, traverse_obj(info, ('userinfo', 'user_name')))
Commit	Line	Data
f963b7ab HTL	1	import json
	2
	3	from .common import InfoExtractor
	4	from ..utils import (
	5	int_or_none,
	6	js_to_json,
	7	parse_iso8601,
	8	str_or_none,
	9	traverse_obj,
	10	)
	11
	12
	13	class LikeeIE(InfoExtractor):
	14	IE_NAME = 'likee'
	15	_VALID_URL = r'(?x)https?://(www\.)?likee\.video/(?:(?P<channel_name>[^/]+)/video/\|v/)(?P<id>\w+)'
	16	_TESTS = [{
	17	'url': 'https://likee.video/@huynh_hong_quan_/video/7093444807096327263',
	18	'info_dict': {
	19	'id': '7093444807096327263',
	20	'ext': 'mp4',
	21	'title': '🤴🤴🤴',
	22	'description': 'md5:9a7ebe816f0e78722ee5ed76f75983b4',
	23	'thumbnail': r're:^https?://.+\.jpg',
	24	'uploader': 'Huỳnh Hồng Quân ',
f963b7ab HTL	25	'artist': 'Huỳnh Hồng Quân ',
	26	'timestamp': 1651571320,
	27	'upload_date': '20220503',
	28	'view_count': int,
	29	'uploader_id': 'huynh_hong_quan_',
	30	'duration': 12374,
	31	'comment_count': int,
	32	'like_count': int,
	33	},
	34	}, {
	35	'url': 'https://likee.video/@649222262/video/7093167848050058862',
	36	'info_dict': {
	37	'id': '7093167848050058862',
	38	'ext': 'mp4',
	39	'title': 'likee video #7093167848050058862',
	40	'description': 'md5:3f971c8c6ee8a216f2b1a9094c5de99f',
	41	'thumbnail': r're:^https?://.+\.jpg',
	42	'comment_count': int,
	43	'like_count': int,
	44	'uploader': 'Vương Phước Nhi',
f963b7ab HTL	45	'timestamp': 1651506835,
	46	'upload_date': '20220502',
	47	'duration': 60024,
f963b7ab HTL	48	'artist': 'Vương Phước Nhi',
	49	'uploader_id': '649222262',
	50	'view_count': int,
	51	},
	52	}, {
	53	'url': 'https://likee.video/@fernanda_rivasg/video/6932224568407629502',
	54	'info_dict': {
	55	'id': '6932224568407629502',
	56	'ext': 'mp4',
	57	'title': 'Un trend viejito🔥 #LIKEE #Ferlovers #trend ',
	58	'description': 'md5:c42b903a72a99d6d8b73e3d1126fbcef',
	59	'thumbnail': r're:^https?://.+\.jpg',
	60	'comment_count': int,
	61	'duration': 9684,
	62	'uploader_id': 'fernanda_rivasg',
	63	'view_count': int,
f963b7ab	64	'artist': 'La Cami La✨',
f963b7ab HTL	65	'like_count': int,
	66	'uploader': 'Fernanda Rivas🎶',
	67	'timestamp': 1614034308,
	68	'upload_date': '20210222',
	69	},
	70	}, {
	71	'url': 'https://likee.video/v/k6QcOp',
	72	'info_dict': {
	73	'id': 'k6QcOp',
	74	'ext': 'mp4',
	75	'title': '#AguaChallenge tú ya lo intentaste?😱🤩',
	76	'description': 'md5:b0cc462689d4ff2b624daa4dba7640d9',
	77	'thumbnail': r're:^https?://.+\.jpg',
	78	'comment_count': int,
	79	'duration': 18014,
f963b7ab HTL	80	'view_count': int,
	81	'timestamp': 1611694774,
	82	'like_count': int,
	83	'uploader': 'Fernanda Rivas🎶',
	84	'uploader_id': 'fernanda_rivasg',
f963b7ab HTL	85	'artist': 'ʟᴇʀɪᴋ_ᴜɴɪᴄᴏʀɴ♡︎',
	86	'upload_date': '20210126',
	87	},
	88	}, {
	89	'url': 'https://www.likee.video/@649222262/video/7093167848050058862',
	90	'only_matching': True,
	91	}, {
	92	'url': 'https://www.likee.video/v/k6QcOp',
	93	'only_matching': True,
	94	}]
	95
	96	def _real_extract(self, url):
	97	video_id = self._match_id(url)
	98	webpage = self._download_webpage(url, video_id)
	99	info = self._parse_json(
	100	self._search_regex(r'window\.data\s=\s({.+?});', webpage, 'video info'),
	101	video_id, transform_source=js_to_json)
	102	video_url = traverse_obj(info, 'video_url', ('originVideoInfo', 'video_url'))
	103	if not video_url:
	104	self.raise_no_formats('Video was deleted', expected=True)
	105	formats = [{
	106	'format_id': 'mp4-with-watermark',
	107	'url': video_url,
	108	'height': info.get('video_height'),
	109	'width': info.get('video_width'),
	110	}, {
	111	'format_id': 'mp4-without-watermark',
	112	'url': video_url.replace('_4', ''),
	113	'height': info.get('video_height'),
	114	'width': info.get('video_width'),
	115	'quality': 1,
	116	}]
f963b7ab HTL	117	return {
	118	'id': video_id,
	119	'title': info.get('msgText'),
	120	'description': info.get('share_desc'),
	121	'view_count': int_or_none(info.get('video_count')),
	122	'like_count': int_or_none(info.get('likeCount')),
f963b7ab HTL	123	'comment_count': int_or_none(info.get('comment_count')),
	124	'uploader': str_or_none(info.get('nick_name')),
	125	'uploader_id': str_or_none(info.get('likeeId')),
	126	'artist': str_or_none(traverse_obj(info, ('sound', 'owner_name'))),
	127	'timestamp': parse_iso8601(info.get('uploadDate')),
	128	'thumbnail': info.get('coverUrl'),
	129	'duration': int_or_none(traverse_obj(info, ('option_data', 'dur'))),
	130	'formats': formats,
	131	}
	132
	133
	134	class LikeeUserIE(InfoExtractor):
	135	IE_NAME = 'likee:user'
	136	_VALID_URL = r'https?://(www\.)?likee\.video/(?P<id>[^/]+)/?$'
	137	_TESTS = [{
	138	'url': 'https://likee.video/@fernanda_rivasg',
	139	'info_dict': {
	140	'id': '925638334',
	141	'title': 'fernanda_rivasg',
	142	},
	143	'playlist_mincount': 500,
	144	}, {
	145	'url': 'https://likee.video/@may_hmoob',
	146	'info_dict': {
	147	'id': '2943949041',
	148	'title': 'may_hmoob',
	149	},
	150	'playlist_mincount': 80,
	151	}]
	152	_PAGE_SIZE = 50
	153	_API_GET_USER_VIDEO = 'https://api.like-video.com/likee-activity-flow-micro/videoApi/getUserVideo'
	154
	155	def _entries(self, user_name, user_id):
	156	last_post_id = ''
	157	while True:
	158	user_videos = self._download_json(
	159	self._API_GET_USER_VIDEO, user_name,
	160	data=json.dumps({
	161	'uid': user_id,
	162	'count': self._PAGE_SIZE,
	163	'lastPostId': last_post_id,
	164	'tabType': 0,
	165	}).encode('utf-8'),
	166	headers={'content-type': 'application/json'},
	167	note=f'Get user info with lastPostId #{last_post_id}')
	168	items = traverse_obj(user_videos, ('data', 'videoList'))
	169	if not items:
	170	break
	171	for item in items:
	172	last_post_id = item['postId']
	173	yield self.url_result(f'https://likee.video/{user_name}/video/{last_post_id}')
	174
	175	def _real_extract(self, url):
	176	user_name = self._match_id(url)
	177	webpage = self._download_webpage(url, user_name)
	178	info = self._parse_json(
	179	self._search_regex(r'window\.data\s=\s({.+?});', webpage, 'user info'),
	180	user_name, transform_source=js_to_json)
	181	user_id = traverse_obj(info, ('userinfo', 'uid'))
	182	return self.playlist_result(self._entries(user_name, user_id), user_id, traverse_obj(info, ('userinfo', 'user_name')))