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

import itertools

from .common import InfoExtractor
from ..utils import (
    bool_or_none,
    determine_ext,
    int_or_none,
    parse_qs,
    try_get,
    unified_timestamp,
    url_or_none,
)


class RutubeBaseIE(InfoExtractor):
    def _download_api_info(self, video_id, query=None):
        if not query:
            query = {}
        query['format'] = 'json'
        return self._download_json(
            f'http://rutube.ru/api/video/{video_id}/',
            video_id, 'Downloading video JSON',
            'Unable to download video JSON', query=query)

    def _extract_info(self, video, video_id=None, require_title=True):
        title = video['title'] if require_title else video.get('title')

        age_limit = video.get('is_adult')
        if age_limit is not None:
            age_limit = 18 if age_limit is True else 0

        uploader_id = try_get(video, lambda x: x['author']['id'])
        category = try_get(video, lambda x: x['category']['name'])
        description = video.get('description')
        duration = int_or_none(video.get('duration'))

        return {
            'id': video.get('id') or video_id if video_id else video['id'],
            'title': title,
            'description': description,
            'thumbnail': video.get('thumbnail_url'),
            'duration': duration,
            'uploader': try_get(video, lambda x: x['author']['name']),
            'uploader_id': str(uploader_id) if uploader_id else None,
            'timestamp': unified_timestamp(video.get('created_ts')),
            'categories': [category] if category else None,
            'age_limit': age_limit,
            'view_count': int_or_none(video.get('hits')),
            'comment_count': int_or_none(video.get('comments_count')),
            'is_live': bool_or_none(video.get('is_livestream')),
            'chapters': self._extract_chapters_from_description(description, duration),
        }

    def _download_and_extract_info(self, video_id, query=None):
        return self._extract_info(
            self._download_api_info(video_id, query=query), video_id)

    def _download_api_options(self, video_id, query=None):
        if not query:
            query = {}
        query['format'] = 'json'
        return self._download_json(
            f'http://rutube.ru/api/play/options/{video_id}/',
            video_id, 'Downloading options JSON',
            'Unable to download options JSON',
            headers=self.geo_verification_headers(), query=query)

    def _extract_formats(self, options, video_id):
        formats = []
        for format_id, format_url in options['video_balancer'].items():
            ext = determine_ext(format_url)
            if ext == 'm3u8':
                formats.extend(self._extract_m3u8_formats(
                    format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))
            elif ext == 'f4m':
                formats.extend(self._extract_f4m_formats(
                    format_url, video_id, f4m_id=format_id, fatal=False))
            else:
                formats.append({
                    'url': format_url,
                    'format_id': format_id,
                })
        return formats

    def _download_and_extract_formats(self, video_id, query=None):
        return self._extract_formats(
            self._download_api_options(video_id, query=query), video_id)


class RutubeIE(RutubeBaseIE):
    IE_NAME = 'rutube'
    IE_DESC = 'Rutube videos'
    _VALID_URL = r'https?://rutube\.ru/(?:video(?:/private)?|(?:play/)?embed)/(?P<id>[\da-z]{32})'
    _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//rutube\.ru/(?:play/)?embed/[\da-z]{32}.*?)\1']

    _TESTS = [{
        'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
        'md5': 'e33ac625efca66aba86cbec9851f2692',
        'info_dict': {
            'id': '3eac3b4561676c17df9132a9a1e62e3e',
            'ext': 'mp4',
            'title': 'Раненный кенгуру забежал в аптеку',
            'description': 'http://www.ntdtv.ru ',
            'duration': 81,
            'uploader': 'NTDRussian',
            'uploader_id': '29790',
            'timestamp': 1381943602,
            'upload_date': '20131016',
            'age_limit': 0,
            'view_count': int,
            'thumbnail': 'http://pic.rutubelist.ru/video/d2/a0/d2a0aec998494a396deafc7ba2c82add.jpg',
            'categories': ['Новости и СМИ'],
            'chapters': [],
        },
        'expected_warnings': ['Unable to download f4m'],
    }, {
        'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
        'only_matching': True,
    }, {
        'url': 'http://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661',
        'only_matching': True,
    }, {
        'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252',
        'only_matching': True,
    }, {
        'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_type=source',
        'only_matching': True,
    }, {
        'url': 'https://rutube.ru/video/private/884fb55f07a97ab673c7d654553e0f48/?p=x2QojCumHTS3rsKHWXN8Lg',
        'md5': 'd106225f15d625538fe22971158e896f',
        'info_dict': {
            'id': '884fb55f07a97ab673c7d654553e0f48',
            'ext': 'mp4',
            'title': 'Яцуноками, Nioh2',
            'description': 'Nioh2: финал сражения с боссом Яцуноками',
            'duration': 15,
            'uploader': 'mexus',
            'uploader_id': '24222106',
            'timestamp': 1670646232,
            'upload_date': '20221210',
            'age_limit': 0,
            'view_count': int,
            'thumbnail': 'http://pic.rutubelist.ru/video/f2/d4/f2d42b54be0a6e69c1c22539e3152156.jpg',
            'categories': ['Видеоигры'],
            'chapters': [],
        },
        'expected_warnings': ['Unable to download f4m'],
    }, {
        'url': 'https://rutube.ru/video/c65b465ad0c98c89f3b25cb03dcc87c6/',
        'info_dict': {
            'id': 'c65b465ad0c98c89f3b25cb03dcc87c6',
            'ext': 'mp4',
            'chapters': 'count:4',
            'categories': ['Бизнес и предпринимательство'],
            'description': 'md5:252feac1305257d8c1bab215cedde75d',
            'thumbnail': 'http://pic.rutubelist.ru/video/71/8f/718f27425ea9706073eb80883dd3787b.png',
            'duration': 782,
            'age_limit': 0,
            'uploader_id': '23491359',
            'timestamp': 1677153329,
            'view_count': int,
            'upload_date': '20230223',
            'title': 'Бизнес с нуля: найм сотрудников. Интервью с директором строительной компании',
            'uploader': 'Стас Быков',
        },
        'expected_warnings': ['Unable to download f4m'],
    }]

    @classmethod
    def suitable(cls, url):
        return False if RutubePlaylistIE.suitable(url) else super().suitable(url)

    def _real_extract(self, url):
        video_id = self._match_id(url)
        query = parse_qs(url)
        info = self._download_and_extract_info(video_id, query)
        info['formats'] = self._download_and_extract_formats(video_id, query)
        return info


class RutubeEmbedIE(RutubeBaseIE):
    IE_NAME = 'rutube:embed'
    IE_DESC = 'Rutube embedded videos'
    _VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'

    _TESTS = [{
        'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
        'info_dict': {
            'id': 'a10e53b86e8f349080f718582ce4c661',
            'ext': 'mp4',
            'timestamp': 1387830582,
            'upload_date': '20131223',
            'uploader_id': '297833',
            'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
            'uploader': 'subziro89 ILya',
            'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
        },
        'params': {
            'skip_download': True,
        },
    }, {
        'url': 'http://rutube.ru/play/embed/8083783',
        'only_matching': True,
    }, {
        # private video
        'url': 'https://rutube.ru/play/embed/10631925?p=IbAigKqWd1do4mjaM5XLIQ',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        embed_id = self._match_id(url)
        # Query may contain private videos token and should be passed to API
        # requests (see #19163)
        query = parse_qs(url)
        options = self._download_api_options(embed_id, query)
        video_id = options['effective_video']
        formats = self._extract_formats(options, video_id)
        info = self._download_and_extract_info(video_id, query)
        info.update({
            'extractor_key': 'Rutube',
            'formats': formats,
        })
        return info


class RutubePlaylistBaseIE(RutubeBaseIE):
    def _next_page_url(self, page_num, playlist_id, *args, **kwargs):
        return self._PAGE_TEMPLATE % (playlist_id, page_num)

    def _entries(self, playlist_id, *args, **kwargs):
        next_page_url = None
        for pagenum in itertools.count(1):
            page = self._download_json(
                next_page_url or self._next_page_url(
                    pagenum, playlist_id, *args, **kwargs),
                playlist_id, f'Downloading page {pagenum}')

            results = page.get('results')
            if not results or not isinstance(results, list):
                break

            for result in results:
                video_url = url_or_none(result.get('video_url'))
                if not video_url:
                    continue
                entry = self._extract_info(result, require_title=False)
                entry.update({
                    '_type': 'url',
                    'url': video_url,
                    'ie_key': RutubeIE.ie_key(),
                })
                yield entry

            next_page_url = page.get('next')
            if not next_page_url or not page.get('has_next'):
                break

    def _extract_playlist(self, playlist_id, *args, **kwargs):
        return self.playlist_result(
            self._entries(playlist_id, *args, **kwargs),
            playlist_id, kwargs.get('playlist_name'))

    def _real_extract(self, url):
        return self._extract_playlist(self._match_id(url))


class RutubeTagsIE(RutubePlaylistBaseIE):
    IE_NAME = 'rutube:tags'
    IE_DESC = 'Rutube tags'
    _VALID_URL = r'https?://rutube\.ru/tags/video/(?P<id>\d+)'
    _TESTS = [{
        'url': 'http://rutube.ru/tags/video/1800/',
        'info_dict': {
            'id': '1800',
        },
        'playlist_mincount': 68,
    }]

    _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'


class RutubeMovieIE(RutubePlaylistBaseIE):
    IE_NAME = 'rutube:movie'
    IE_DESC = 'Rutube movies'
    _VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P<id>\d+)'

    _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
    _PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'

    def _real_extract(self, url):
        movie_id = self._match_id(url)
        movie = self._download_json(
            self._MOVIE_TEMPLATE % movie_id, movie_id,
            'Downloading movie JSON')
        return self._extract_playlist(
            movie_id, playlist_name=movie.get('name'))


class RutubePersonIE(RutubePlaylistBaseIE):
    IE_NAME = 'rutube:person'
    IE_DESC = 'Rutube person videos'
    _VALID_URL = r'https?://rutube\.ru/video/person/(?P<id>\d+)'
    _TESTS = [{
        'url': 'http://rutube.ru/video/person/313878/',
        'info_dict': {
            'id': '313878',
        },
        'playlist_mincount': 37,
    }]

    _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'


class RutubePlaylistIE(RutubePlaylistBaseIE):
    IE_NAME = 'rutube:playlist'
    IE_DESC = 'Rutube playlists'
    _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/[\da-z]{32}/\?.*?\bpl_id=(?P<id>\d+)'
    _TESTS = [{
        'url': 'https://rutube.ru/video/cecd58ed7d531fc0f3d795d51cee9026/?pl_id=3097&pl_type=tag',
        'info_dict': {
            'id': '3097',
        },
        'playlist_count': 27,
    }, {
        'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_id=4252&pl_type=source',
        'only_matching': True,
    }]

    _PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/%s/%s/?page=%s&format=json'

    @classmethod
    def suitable(cls, url):
        from ..utils import int_or_none, parse_qs

        if not super().suitable(url):
            return False
        params = parse_qs(url)
        return params.get('pl_type', [None])[0] and int_or_none(params.get('pl_id', [None])[0])

    def _next_page_url(self, page_num, playlist_id, item_kind):
        return self._PAGE_TEMPLATE % (item_kind, playlist_id, page_num)

    def _real_extract(self, url):
        qs = parse_qs(url)
        playlist_kind = qs['pl_type'][0]
        playlist_id = qs['pl_id'][0]
        return self._extract_playlist(playlist_id, item_kind=playlist_kind)


class RutubeChannelIE(RutubePlaylistBaseIE):
    IE_NAME = 'rutube:channel'
    IE_DESC = 'Rutube channel'
    _VALID_URL = r'https?://rutube\.ru/channel/(?P<id>\d+)/videos'
    _TESTS = [{
        'url': 'https://rutube.ru/channel/639184/videos/',
        'info_dict': {
            'id': '639184',
        },
        'playlist_mincount': 133,
    }]

    _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'
Commit	Line	Data
1547c8cc	1	import itertools
bfd14b1b JMF	2
bfd14b1b JMF	3	from .common import InfoExtractor
1cc79574	4	from ..utils import (
c3dd44e0	5	bool_or_none,
e897bd82	6	determine_ext,
debed8d7	7	int_or_none,
4dfbf869	8	parse_qs,
c3dd44e0 S	9	try_get,
c3dd44e0 S	10	unified_timestamp,
3052a30d	11	url_or_none,
bfd14b1b JMF	12	)
	13
	14
48b81374	15	class RutubeBaseIE(InfoExtractor):
4c0e0dc9 S	16	def _download_api_info(self, video_id, query=None):
	17	if not query:
	18	query = {}
	19	query['format'] = 'json'
	20	return self._download_json(
add96eb9	21	f'http://rutube.ru/api/video/{video_id}/',
4c0e0dc9 S	22	video_id, 'Downloading video JSON',
	23	'Unable to download video JSON', query=query)
	24
22ccd542	25	def _extract_info(self, video, video_id=None, require_title=True):
48b81374 S	26	title = video['title'] if require_title else video.get('title')
	27
	28	age_limit = video.get('is_adult')
	29	if age_limit is not None:
	30	age_limit = 18 if age_limit is True else 0
	31
	32	uploader_id = try_get(video, lambda x: x['author']['id'])
	33	category = try_get(video, lambda x: x['category']['name'])
22ccd542	34	description = video.get('description')
22ccd542	35	duration = int_or_none(video.get('duration'))
48b81374 S	36
48b81374 S	37	return {
4c0e0dc9	38	'id': video.get('id') or video_id if video_id else video['id'],
48b81374	39	'title': title,
22ccd542	40	'description': description,
48b81374	41	'thumbnail': video.get('thumbnail_url'),
22ccd542	42	'duration': duration,
48b81374	43	'uploader': try_get(video, lambda x: x['author']['name']),
add96eb9	44	'uploader_id': str(uploader_id) if uploader_id else None,
48b81374	45	'timestamp': unified_timestamp(video.get('created_ts')),
f4f9f6d0	46	'categories': [category] if category else None,
48b81374 S	47	'age_limit': age_limit,
	48	'view_count': int_or_none(video.get('hits')),
	49	'comment_count': int_or_none(video.get('comments_count')),
c3dd44e0	50	'is_live': bool_or_none(video.get('is_livestream')),
22ccd542	51	'chapters': self._extract_chapters_from_description(description, duration),
48b81374 S	52	}
48b81374 S	53
4c0e0dc9 S	54	def _download_and_extract_info(self, video_id, query=None):
	55	return self._extract_info(
	56	self._download_api_info(video_id, query=query), video_id)
	57
	58	def _download_api_options(self, video_id, query=None):
	59	if not query:
	60	query = {}
	61	query['format'] = 'json'
	62	return self._download_json(
add96eb9	63	f'http://rutube.ru/api/play/options/{video_id}/',
4c0e0dc9 S	64	video_id, 'Downloading options JSON',
	65	'Unable to download options JSON',
	66	headers=self.geo_verification_headers(), query=query)
	67
	68	def _extract_formats(self, options, video_id):
	69	formats = []
	70	for format_id, format_url in options['video_balancer'].items():
	71	ext = determine_ext(format_url)
	72	if ext == 'm3u8':
	73	formats.extend(self._extract_m3u8_formats(
	74	format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))
	75	elif ext == 'f4m':
	76	formats.extend(self._extract_f4m_formats(
	77	format_url, video_id, f4m_id=format_id, fatal=False))
	78	else:
	79	formats.append({
	80	'url': format_url,
	81	'format_id': format_id,
	82	})
4c0e0dc9 S	83	return formats
	84
	85	def _download_and_extract_formats(self, video_id, query=None):
	86	return self._extract_formats(
	87	self._download_api_options(video_id, query=query), video_id)
	88
48b81374 S	89
48b81374 S	90	class RutubeIE(RutubeBaseIE):
1547c8cc	91	IE_NAME = 'rutube'
37e3b90d	92	IE_DESC = 'Rutube videos'
df10bad2	93	_VALID_URL = r'https?://rutube\.ru/(?:video(?:/private)?\|(?:play/)?embed)/(?P<id>[\da-z]{32})'
d42763a4	94	_EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//rutube\.ru/(?:play/)?embed/[\da-z]{32}.*?)\1']
bfd14b1b	95
2d3b7027	96	_TESTS = [{
1547c8cc	97	'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
df10bad2	98	'md5': 'e33ac625efca66aba86cbec9851f2692',
1547c8cc	99	'info_dict': {
c72477bd	100	'id': '3eac3b4561676c17df9132a9a1e62e3e',
4c0e0dc9	101	'ext': 'mp4',
1547c8cc	102	'title': 'Раненный кенгуру забежал в аптеку',
00ff8f92	103	'description': 'http://www.ntdtv.ru ',
4c0e0dc9	104	'duration': 81,
1547c8cc	105	'uploader': 'NTDRussian',
1547c8cc	106	'uploader_id': '29790',
48b81374	107	'timestamp': 1381943602,
00ff8f92	108	'upload_date': '20131016',
c8d1be77	109	'age_limit': 0,
df10bad2 D	110	'view_count': int,
df10bad2 D	111	'thumbnail': 'http://pic.rutubelist.ru/video/d2/a0/d2a0aec998494a396deafc7ba2c82add.jpg',
f4f9f6d0	112	'categories': ['Новости и СМИ'],
22ccd542	113	'chapters': [],
bfd14b1b	114	},
22ccd542	115	'expected_warnings': ['Unable to download f4m'],
2d3b7027 S	116	}, {
	117	'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
	118	'only_matching': True,
bc82f228 S	119	}, {
	120	'url': 'http://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661',
	121	'only_matching': True,
debed8d7	122	}, {
	123	'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252',
	124	'only_matching': True,
48b81374 S	125	}, {
	126	'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_type=source',
	127	'only_matching': True,
df10bad2 D	128	}, {
	129	'url': 'https://rutube.ru/video/private/884fb55f07a97ab673c7d654553e0f48/?p=x2QojCumHTS3rsKHWXN8Lg',
	130	'md5': 'd106225f15d625538fe22971158e896f',
	131	'info_dict': {
	132	'id': '884fb55f07a97ab673c7d654553e0f48',
	133	'ext': 'mp4',
	134	'title': 'Яцуноками, Nioh2',
	135	'description': 'Nioh2: финал сражения с боссом Яцуноками',
	136	'duration': 15,
	137	'uploader': 'mexus',
	138	'uploader_id': '24222106',
	139	'timestamp': 1670646232,
	140	'upload_date': '20221210',
	141	'age_limit': 0,
	142	'view_count': int,
	143	'thumbnail': 'http://pic.rutubelist.ru/video/f2/d4/f2d42b54be0a6e69c1c22539e3152156.jpg',
f4f9f6d0	144	'categories': ['Видеоигры'],
22ccd542	145	'chapters': [],
	146	},
	147	'expected_warnings': ['Unable to download f4m'],
	148	}, {
	149	'url': 'https://rutube.ru/video/c65b465ad0c98c89f3b25cb03dcc87c6/',
	150	'info_dict': {
	151	'id': 'c65b465ad0c98c89f3b25cb03dcc87c6',
	152	'ext': 'mp4',
	153	'chapters': 'count:4',
f4f9f6d0	154	'categories': ['Бизнес и предпринимательство'],
22ccd542	155	'description': 'md5:252feac1305257d8c1bab215cedde75d',
	156	'thumbnail': 'http://pic.rutubelist.ru/video/71/8f/718f27425ea9706073eb80883dd3787b.png',
	157	'duration': 782,
	158	'age_limit': 0,
	159	'uploader_id': '23491359',
	160	'timestamp': 1677153329,
	161	'view_count': int,
	162	'upload_date': '20230223',
	163	'title': 'Бизнес с нуля: найм сотрудников. Интервью с директором строительной компании',
	164	'uploader': 'Стас Быков',
df10bad2	165	},
22ccd542	166	'expected_warnings': ['Unable to download f4m'],
2d3b7027	167	}]
bfd14b1b	168
debed8d7	169	@classmethod
debed8d7	170	def suitable(cls, url):
add96eb9	171	return False if RutubePlaylistIE.suitable(url) else super().suitable(url)
debed8d7	172
bfd14b1b	173	def _real_extract(self, url):
1cc79574	174	video_id = self._match_id(url)
df10bad2 D	175	query = parse_qs(url)
	176	info = self._download_and_extract_info(video_id, query)
	177	info['formats'] = self._download_and_extract_formats(video_id, query)
48b81374	178	return info
1547c8cc	179
1547c8cc	180
4c0e0dc9	181	class RutubeEmbedIE(RutubeBaseIE):
7a1818c9 PH	182	IE_NAME = 'rutube:embed'
7a1818c9 PH	183	IE_DESC = 'Rutube embedded videos'
25042f73	184	_VALID_URL = r'https?://rutube\.ru/(?:video\|play)/embed/(?P<id>[0-9]+)'
7a1818c9	185
f52183a8	186	_TESTS = [{
7a1818c9 PH	187	'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
	188	'info_dict': {
	189	'id': 'a10e53b86e8f349080f718582ce4c661',
4c0e0dc9	190	'ext': 'mp4',
48b81374	191	'timestamp': 1387830582,
7a1818c9 PH	192	'upload_date': '20131223',
	193	'uploader_id': '297833',
	194	'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
	195	'uploader': 'subziro89 ILya',
	196	'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
	197	},
	198	'params': {
48b81374	199	'skip_download': True,
7a1818c9	200	},
f52183a8 S	201	}, {
	202	'url': 'http://rutube.ru/play/embed/8083783',
	203	'only_matching': True,
4c0e0dc9 S	204	}, {
	205	# private video
	206	'url': 'https://rutube.ru/play/embed/10631925?p=IbAigKqWd1do4mjaM5XLIQ',
	207	'only_matching': True,
f52183a8	208	}]
7a1818c9 PH	209
	210	def _real_extract(self, url):
	211	embed_id = self._match_id(url)
4c0e0dc9 S	212	# Query may contain private videos token and should be passed to API
4c0e0dc9 S	213	# requests (see #19163)
4dfbf869	214	query = parse_qs(url)
4c0e0dc9 S	215	options = self._download_api_options(embed_id, query)
	216	video_id = options['effective_video']
	217	formats = self._extract_formats(options, video_id)
	218	info = self._download_and_extract_info(video_id, query)
	219	info.update({
	220	'extractor_key': 'Rutube',
	221	'formats': formats,
	222	})
	223	return info
7a1818c9 PH	224
7a1818c9 PH	225
48b81374 S	226	class RutubePlaylistBaseIE(RutubeBaseIE):
	227	def _next_page_url(self, page_num, playlist_id, args, *kwargs):
	228	return self._PAGE_TEMPLATE % (playlist_id, page_num)
	229
	230	def _entries(self, playlist_id, args, *kwargs):
	231	next_page_url = None
	232	for pagenum in itertools.count(1):
	233	page = self._download_json(
	234	next_page_url or self._next_page_url(
	235	pagenum, playlist_id, args, *kwargs),
add96eb9	236	playlist_id, f'Downloading page {pagenum}')
48b81374 S	237
	238	results = page.get('results')
	239	if not results or not isinstance(results, list):
	240	break
	241
	242	for result in results:
3052a30d S	243	video_url = url_or_none(result.get('video_url'))
3052a30d S	244	if not video_url:
48b81374	245	continue
4c0e0dc9	246	entry = self._extract_info(result, require_title=False)
48b81374 S	247	entry.update({
	248	'_type': 'url',
	249	'url': video_url,
	250	'ie_key': RutubeIE.ie_key(),
	251	})
	252	yield entry
	253
	254	next_page_url = page.get('next')
	255	if not next_page_url or not page.get('has_next'):
	256	break
	257
	258	def _extract_playlist(self, playlist_id, args, *kwargs):
	259	return self.playlist_result(
	260	self._entries(playlist_id, args, *kwargs),
	261	playlist_id, kwargs.get('playlist_name'))
	262
	263	def _real_extract(self, url):
	264	return self._extract_playlist(self._match_id(url))
	265
	266
13debc86 AG	267	class RutubeTagsIE(RutubePlaylistBaseIE):
	268	IE_NAME = 'rutube:tags'
	269	IE_DESC = 'Rutube tags'
5886b38d	270	_VALID_URL = r'https?://rutube\.ru/tags/video/(?P<id>\d+)'
22a6f150 PH	271	_TESTS = [{
	272	'url': 'http://rutube.ru/tags/video/1800/',
	273	'info_dict': {
	274	'id': '1800',
	275	},
	276	'playlist_mincount': 68,
	277	}]
1547c8cc	278
	279	_PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
	280
1547c8cc	281
48b81374	282	class RutubeMovieIE(RutubePlaylistBaseIE):
1547c8cc	283	IE_NAME = 'rutube:movie'
37e3b90d	284	IE_DESC = 'Rutube movies'
5886b38d	285	_VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P<id>\d+)'
1547c8cc	286
	287	_MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
	288	_PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
	289
	290	def _real_extract(self, url):
1cc79574	291	movie_id = self._match_id(url)
18c95c1a	292	movie = self._download_json(
37e3b90d PH	293	self._MOVIE_TEMPLATE % movie_id, movie_id,
37e3b90d PH	294	'Downloading movie JSON')
48b81374 S	295	return self._extract_playlist(
48b81374 S	296	movie_id, playlist_name=movie.get('name'))
e3a9f32f	297
e3a9f32f	298
48b81374	299	class RutubePersonIE(RutubePlaylistBaseIE):
e3a9f32f	300	IE_NAME = 'rutube:person'
e3a9f32f	301	IE_DESC = 'Rutube person videos'
5886b38d	302	_VALID_URL = r'https?://rutube\.ru/video/person/(?P<id>\d+)'
22a6f150 PH	303	_TESTS = [{
	304	'url': 'http://rutube.ru/video/person/313878/',
	305	'info_dict': {
	306	'id': '313878',
	307	},
	308	'playlist_mincount': 37,
	309	}]
e3a9f32f	310
37e3b90d	311	_PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'
debed8d7	312
debed8d7	313
48b81374	314	class RutubePlaylistIE(RutubePlaylistBaseIE):
debed8d7	315	IE_NAME = 'rutube:playlist'
debed8d7	316	IE_DESC = 'Rutube playlists'
48b81374	317	_VALID_URL = r'https?://rutube\.ru/(?:video\|(?:play/)?embed)/[\da-z]{32}/\?.*?\bpl_id=(?P<id>\d+)'
debed8d7	318	_TESTS = [{
48b81374	319	'url': 'https://rutube.ru/video/cecd58ed7d531fc0f3d795d51cee9026/?pl_id=3097&pl_type=tag',
debed8d7	320	'info_dict': {
48b81374	321	'id': '3097',
debed8d7	322	},
48b81374 S	323	'playlist_count': 27,
	324	}, {
	325	'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_id=4252&pl_type=source',
	326	'only_matching': True,
debed8d7	327	}]
debed8d7	328
48b81374	329	_PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/%s/%s/?page=%s&format=json'
debed8d7	330
f12a6e88 S	331	@classmethod
f12a6e88 S	332	def suitable(cls, url):
3fb4e21b	333	from ..utils import int_or_none, parse_qs
3fb4e21b	334
add96eb9	335	if not super().suitable(url):
f12a6e88	336	return False
4dfbf869	337	params = parse_qs(url)
48b81374	338	return params.get('pl_type', [None])[0] and int_or_none(params.get('pl_id', [None])[0])
debed8d7	339
48b81374 S	340	def _next_page_url(self, page_num, playlist_id, item_kind):
48b81374 S	341	return self._PAGE_TEMPLATE % (item_kind, playlist_id, page_num)
debed8d7	342
48b81374	343	def _real_extract(self, url):
4dfbf869	344	qs = parse_qs(url)
48b81374 S	345	playlist_kind = qs['pl_type'][0]
	346	playlist_id = qs['pl_id'][0]
	347	return self._extract_playlist(playlist_id, item_kind=playlist_kind)
13debc86 AG	348
	349
	350	class RutubeChannelIE(RutubePlaylistBaseIE):
	351	IE_NAME = 'rutube:channel'
	352	IE_DESC = 'Rutube channel'
	353	_VALID_URL = r'https?://rutube\.ru/channel/(?P<id>\d+)/videos'
	354	_TESTS = [{
	355	'url': 'https://rutube.ru/channel/639184/videos/',
	356	'info_dict': {
	357	'id': '639184',
	358	},
	359	'playlist_mincount': 133,
	360	}]
	361
	362	_PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'