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

import itertools

from .common import InfoExtractor
from ..compat import (
    compat_str,
)
from ..utils import (
    determine_ext,
    bool_or_none,
    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(
            'http://rutube.ru/api/video/%s/' % 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': compat_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(
            'http://rutube.ru/api/play/options/%s/' % 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(RutubeIE, cls).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, 'Downloading page %s' % 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(RutubePlaylistIE, cls).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 ..compat import (
bfd14b1b	5	compat_str,
1cc79574 PH	6	)
1cc79574 PH	7	from ..utils import (
41371968	8	determine_ext,
c3dd44e0	9	bool_or_none,
debed8d7	10	int_or_none,
4dfbf869	11	parse_qs,
c3dd44e0 S	12	try_get,
c3dd44e0 S	13	unified_timestamp,
3052a30d	14	url_or_none,
bfd14b1b JMF	15	)
	16
	17
48b81374	18	class RutubeBaseIE(InfoExtractor):
4c0e0dc9 S	19	def _download_api_info(self, video_id, query=None):
	20	if not query:
	21	query = {}
	22	query['format'] = 'json'
	23	return self._download_json(
	24	'http://rutube.ru/api/video/%s/' % video_id,
	25	video_id, 'Downloading video JSON',
	26	'Unable to download video JSON', query=query)
	27
22ccd542	28	def _extract_info(self, video, video_id=None, require_title=True):
48b81374 S	29	title = video['title'] if require_title else video.get('title')
	30
	31	age_limit = video.get('is_adult')
	32	if age_limit is not None:
	33	age_limit = 18 if age_limit is True else 0
	34
	35	uploader_id = try_get(video, lambda x: x['author']['id'])
	36	category = try_get(video, lambda x: x['category']['name'])
22ccd542	37	description = video.get('description')
22ccd542	38	duration = int_or_none(video.get('duration'))
48b81374 S	39
48b81374 S	40	return {
4c0e0dc9	41	'id': video.get('id') or video_id if video_id else video['id'],
48b81374	42	'title': title,
22ccd542	43	'description': description,
48b81374	44	'thumbnail': video.get('thumbnail_url'),
22ccd542	45	'duration': duration,
48b81374 S	46	'uploader': try_get(video, lambda x: x['author']['name']),
	47	'uploader_id': compat_str(uploader_id) if uploader_id else None,
	48	'timestamp': unified_timestamp(video.get('created_ts')),
f4f9f6d0	49	'categories': [category] if category else None,
48b81374 S	50	'age_limit': age_limit,
	51	'view_count': int_or_none(video.get('hits')),
	52	'comment_count': int_or_none(video.get('comments_count')),
c3dd44e0	53	'is_live': bool_or_none(video.get('is_livestream')),
22ccd542	54	'chapters': self._extract_chapters_from_description(description, duration),
48b81374 S	55	}
48b81374 S	56
4c0e0dc9 S	57	def _download_and_extract_info(self, video_id, query=None):
	58	return self._extract_info(
	59	self._download_api_info(video_id, query=query), video_id)
	60
	61	def _download_api_options(self, video_id, query=None):
	62	if not query:
	63	query = {}
	64	query['format'] = 'json'
	65	return self._download_json(
	66	'http://rutube.ru/api/play/options/%s/' % video_id,
	67	video_id, 'Downloading options JSON',
	68	'Unable to download options JSON',
	69	headers=self.geo_verification_headers(), query=query)
	70
	71	def _extract_formats(self, options, video_id):
	72	formats = []
	73	for format_id, format_url in options['video_balancer'].items():
	74	ext = determine_ext(format_url)
	75	if ext == 'm3u8':
	76	formats.extend(self._extract_m3u8_formats(
	77	format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))
	78	elif ext == 'f4m':
	79	formats.extend(self._extract_f4m_formats(
	80	format_url, video_id, f4m_id=format_id, fatal=False))
	81	else:
	82	formats.append({
	83	'url': format_url,
	84	'format_id': format_id,
	85	})
4c0e0dc9 S	86	return formats
	87
	88	def _download_and_extract_formats(self, video_id, query=None):
	89	return self._extract_formats(
	90	self._download_api_options(video_id, query=query), video_id)
	91
48b81374 S	92
48b81374 S	93	class RutubeIE(RutubeBaseIE):
1547c8cc	94	IE_NAME = 'rutube'
37e3b90d	95	IE_DESC = 'Rutube videos'
df10bad2	96	_VALID_URL = r'https?://rutube\.ru/(?:video(?:/private)?\|(?:play/)?embed)/(?P<id>[\da-z]{32})'
d42763a4	97	_EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//rutube\.ru/(?:play/)?embed/[\da-z]{32}.*?)\1']
bfd14b1b	98
2d3b7027	99	_TESTS = [{
1547c8cc	100	'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
df10bad2	101	'md5': 'e33ac625efca66aba86cbec9851f2692',
1547c8cc	102	'info_dict': {
c72477bd	103	'id': '3eac3b4561676c17df9132a9a1e62e3e',
4c0e0dc9	104	'ext': 'mp4',
1547c8cc	105	'title': 'Раненный кенгуру забежал в аптеку',
00ff8f92	106	'description': 'http://www.ntdtv.ru ',
4c0e0dc9	107	'duration': 81,
1547c8cc	108	'uploader': 'NTDRussian',
1547c8cc	109	'uploader_id': '29790',
48b81374	110	'timestamp': 1381943602,
00ff8f92	111	'upload_date': '20131016',
c8d1be77	112	'age_limit': 0,
df10bad2 D	113	'view_count': int,
df10bad2 D	114	'thumbnail': 'http://pic.rutubelist.ru/video/d2/a0/d2a0aec998494a396deafc7ba2c82add.jpg',
f4f9f6d0	115	'categories': ['Новости и СМИ'],
22ccd542	116	'chapters': [],
bfd14b1b	117	},
22ccd542	118	'expected_warnings': ['Unable to download f4m'],
2d3b7027 S	119	}, {
	120	'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
	121	'only_matching': True,
bc82f228 S	122	}, {
	123	'url': 'http://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661',
	124	'only_matching': True,
debed8d7	125	}, {
	126	'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252',
	127	'only_matching': True,
48b81374 S	128	}, {
	129	'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_type=source',
	130	'only_matching': True,
df10bad2 D	131	}, {
	132	'url': 'https://rutube.ru/video/private/884fb55f07a97ab673c7d654553e0f48/?p=x2QojCumHTS3rsKHWXN8Lg',
	133	'md5': 'd106225f15d625538fe22971158e896f',
	134	'info_dict': {
	135	'id': '884fb55f07a97ab673c7d654553e0f48',
	136	'ext': 'mp4',
	137	'title': 'Яцуноками, Nioh2',
	138	'description': 'Nioh2: финал сражения с боссом Яцуноками',
	139	'duration': 15,
	140	'uploader': 'mexus',
	141	'uploader_id': '24222106',
	142	'timestamp': 1670646232,
	143	'upload_date': '20221210',
	144	'age_limit': 0,
	145	'view_count': int,
	146	'thumbnail': 'http://pic.rutubelist.ru/video/f2/d4/f2d42b54be0a6e69c1c22539e3152156.jpg',
f4f9f6d0	147	'categories': ['Видеоигры'],
22ccd542	148	'chapters': [],
	149	},
	150	'expected_warnings': ['Unable to download f4m'],
	151	}, {
	152	'url': 'https://rutube.ru/video/c65b465ad0c98c89f3b25cb03dcc87c6/',
	153	'info_dict': {
	154	'id': 'c65b465ad0c98c89f3b25cb03dcc87c6',
	155	'ext': 'mp4',
	156	'chapters': 'count:4',
f4f9f6d0	157	'categories': ['Бизнес и предпринимательство'],
22ccd542	158	'description': 'md5:252feac1305257d8c1bab215cedde75d',
	159	'thumbnail': 'http://pic.rutubelist.ru/video/71/8f/718f27425ea9706073eb80883dd3787b.png',
	160	'duration': 782,
	161	'age_limit': 0,
	162	'uploader_id': '23491359',
	163	'timestamp': 1677153329,
	164	'view_count': int,
	165	'upload_date': '20230223',
	166	'title': 'Бизнес с нуля: найм сотрудников. Интервью с директором строительной компании',
	167	'uploader': 'Стас Быков',
df10bad2	168	},
22ccd542	169	'expected_warnings': ['Unable to download f4m'],
2d3b7027	170	}]
bfd14b1b	171
debed8d7	172	@classmethod
debed8d7	173	def suitable(cls, url):
48b81374	174	return False if RutubePlaylistIE.suitable(url) else super(RutubeIE, cls).suitable(url)
debed8d7	175
bfd14b1b	176	def _real_extract(self, url):
1cc79574	177	video_id = self._match_id(url)
df10bad2 D	178	query = parse_qs(url)
	179	info = self._download_and_extract_info(video_id, query)
	180	info['formats'] = self._download_and_extract_formats(video_id, query)
48b81374	181	return info
1547c8cc	182
1547c8cc	183
4c0e0dc9	184	class RutubeEmbedIE(RutubeBaseIE):
7a1818c9 PH	185	IE_NAME = 'rutube:embed'
7a1818c9 PH	186	IE_DESC = 'Rutube embedded videos'
25042f73	187	_VALID_URL = r'https?://rutube\.ru/(?:video\|play)/embed/(?P<id>[0-9]+)'
7a1818c9	188
f52183a8	189	_TESTS = [{
7a1818c9 PH	190	'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
	191	'info_dict': {
	192	'id': 'a10e53b86e8f349080f718582ce4c661',
4c0e0dc9	193	'ext': 'mp4',
48b81374	194	'timestamp': 1387830582,
7a1818c9 PH	195	'upload_date': '20131223',
	196	'uploader_id': '297833',
	197	'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
	198	'uploader': 'subziro89 ILya',
	199	'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
	200	},
	201	'params': {
48b81374	202	'skip_download': True,
7a1818c9	203	},
f52183a8 S	204	}, {
	205	'url': 'http://rutube.ru/play/embed/8083783',
	206	'only_matching': True,
4c0e0dc9 S	207	}, {
	208	# private video
	209	'url': 'https://rutube.ru/play/embed/10631925?p=IbAigKqWd1do4mjaM5XLIQ',
	210	'only_matching': True,
f52183a8	211	}]
7a1818c9 PH	212
	213	def _real_extract(self, url):
	214	embed_id = self._match_id(url)
4c0e0dc9 S	215	# Query may contain private videos token and should be passed to API
4c0e0dc9 S	216	# requests (see #19163)
4dfbf869	217	query = parse_qs(url)
4c0e0dc9 S	218	options = self._download_api_options(embed_id, query)
	219	video_id = options['effective_video']
	220	formats = self._extract_formats(options, video_id)
	221	info = self._download_and_extract_info(video_id, query)
	222	info.update({
	223	'extractor_key': 'Rutube',
	224	'formats': formats,
	225	})
	226	return info
7a1818c9 PH	227
7a1818c9 PH	228
48b81374 S	229	class RutubePlaylistBaseIE(RutubeBaseIE):
	230	def _next_page_url(self, page_num, playlist_id, args, *kwargs):
	231	return self._PAGE_TEMPLATE % (playlist_id, page_num)
	232
	233	def _entries(self, playlist_id, args, *kwargs):
	234	next_page_url = None
	235	for pagenum in itertools.count(1):
	236	page = self._download_json(
	237	next_page_url or self._next_page_url(
	238	pagenum, playlist_id, args, *kwargs),
	239	playlist_id, 'Downloading page %s' % pagenum)
	240
	241	results = page.get('results')
	242	if not results or not isinstance(results, list):
	243	break
	244
	245	for result in results:
3052a30d S	246	video_url = url_or_none(result.get('video_url'))
3052a30d S	247	if not video_url:
48b81374	248	continue
4c0e0dc9	249	entry = self._extract_info(result, require_title=False)
48b81374 S	250	entry.update({
	251	'_type': 'url',
	252	'url': video_url,
	253	'ie_key': RutubeIE.ie_key(),
	254	})
	255	yield entry
	256
	257	next_page_url = page.get('next')
	258	if not next_page_url or not page.get('has_next'):
	259	break
	260
	261	def _extract_playlist(self, playlist_id, args, *kwargs):
	262	return self.playlist_result(
	263	self._entries(playlist_id, args, *kwargs),
	264	playlist_id, kwargs.get('playlist_name'))
	265
	266	def _real_extract(self, url):
	267	return self._extract_playlist(self._match_id(url))
	268
	269
13debc86 AG	270	class RutubeTagsIE(RutubePlaylistBaseIE):
	271	IE_NAME = 'rutube:tags'
	272	IE_DESC = 'Rutube tags'
5886b38d	273	_VALID_URL = r'https?://rutube\.ru/tags/video/(?P<id>\d+)'
22a6f150 PH	274	_TESTS = [{
	275	'url': 'http://rutube.ru/tags/video/1800/',
	276	'info_dict': {
	277	'id': '1800',
	278	},
	279	'playlist_mincount': 68,
	280	}]
1547c8cc	281
	282	_PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
	283
1547c8cc	284
48b81374	285	class RutubeMovieIE(RutubePlaylistBaseIE):
1547c8cc	286	IE_NAME = 'rutube:movie'
37e3b90d	287	IE_DESC = 'Rutube movies'
5886b38d	288	_VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P<id>\d+)'
1547c8cc	289
	290	_MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
	291	_PAGE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/video?page=%s&format=json'
	292
	293	def _real_extract(self, url):
1cc79574	294	movie_id = self._match_id(url)
18c95c1a	295	movie = self._download_json(
37e3b90d PH	296	self._MOVIE_TEMPLATE % movie_id, movie_id,
37e3b90d PH	297	'Downloading movie JSON')
48b81374 S	298	return self._extract_playlist(
48b81374 S	299	movie_id, playlist_name=movie.get('name'))
e3a9f32f	300
e3a9f32f	301
48b81374	302	class RutubePersonIE(RutubePlaylistBaseIE):
e3a9f32f	303	IE_NAME = 'rutube:person'
e3a9f32f	304	IE_DESC = 'Rutube person videos'
5886b38d	305	_VALID_URL = r'https?://rutube\.ru/video/person/(?P<id>\d+)'
22a6f150 PH	306	_TESTS = [{
	307	'url': 'http://rutube.ru/video/person/313878/',
	308	'info_dict': {
	309	'id': '313878',
	310	},
	311	'playlist_mincount': 37,
	312	}]
e3a9f32f	313
37e3b90d	314	_PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'
debed8d7	315
debed8d7	316
48b81374	317	class RutubePlaylistIE(RutubePlaylistBaseIE):
debed8d7	318	IE_NAME = 'rutube:playlist'
debed8d7	319	IE_DESC = 'Rutube playlists'
48b81374	320	_VALID_URL = r'https?://rutube\.ru/(?:video\|(?:play/)?embed)/[\da-z]{32}/\?.*?\bpl_id=(?P<id>\d+)'
debed8d7	321	_TESTS = [{
48b81374	322	'url': 'https://rutube.ru/video/cecd58ed7d531fc0f3d795d51cee9026/?pl_id=3097&pl_type=tag',
debed8d7	323	'info_dict': {
48b81374	324	'id': '3097',
debed8d7	325	},
48b81374 S	326	'playlist_count': 27,
	327	}, {
	328	'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_id=4252&pl_type=source',
	329	'only_matching': True,
debed8d7	330	}]
debed8d7	331
48b81374	332	_PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/%s/%s/?page=%s&format=json'
debed8d7	333
f12a6e88 S	334	@classmethod
f12a6e88 S	335	def suitable(cls, url):
3fb4e21b	336	from ..utils import int_or_none, parse_qs
3fb4e21b	337
f12a6e88 S	338	if not super(RutubePlaylistIE, cls).suitable(url):
f12a6e88 S	339	return False
4dfbf869	340	params = parse_qs(url)
48b81374	341	return params.get('pl_type', [None])[0] and int_or_none(params.get('pl_id', [None])[0])
debed8d7	342
48b81374 S	343	def _next_page_url(self, page_num, playlist_id, item_kind):
48b81374 S	344	return self._PAGE_TEMPLATE % (item_kind, playlist_id, page_num)
debed8d7	345
48b81374	346	def _real_extract(self, url):
4dfbf869	347	qs = parse_qs(url)
48b81374 S	348	playlist_kind = qs['pl_type'][0]
	349	playlist_id = qs['pl_id'][0]
	350	return self._extract_playlist(playlist_id, item_kind=playlist_kind)
13debc86 AG	351
	352
	353	class RutubeChannelIE(RutubePlaylistBaseIE):
	354	IE_NAME = 'rutube:channel'
	355	IE_DESC = 'Rutube channel'
	356	_VALID_URL = r'https?://rutube\.ru/channel/(?P<id>\d+)/videos'
	357	_TESTS = [{
	358	'url': 'https://rutube.ru/channel/639184/videos/',
	359	'info_dict': {
	360	'id': '639184',
	361	},
	362	'playlist_mincount': 133,
	363	}]
	364
	365	_PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'