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

# coding: utf-8
from __future__ import unicode_literals

import json
import re

from .common import InfoExtractor
from ..utils import (
    ExtractorError,
    int_or_none,
    qualities,
)


class IviIE(InfoExtractor):
    IE_DESC = 'ivi.ru'
    IE_NAME = 'ivi'
    _VALID_URL = r'https?://(?:www\.)?ivi\.(?:ru|tv)/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<id>\d+)'
    _GEO_BYPASS = False
    _GEO_COUNTRIES = ['RU']
    _LIGHT_KEY = b'\xf1\x02\x32\xb7\xbc\x5c\x7a\xe8\xf7\x96\xc1\x33\x2b\x27\xa1\x8c'
    _LIGHT_URL = 'https://api.ivi.ru/light/'

    _TESTS = [
        # Single movie
        {
            'url': 'http://www.ivi.ru/watch/53141',
            'md5': '6ff5be2254e796ed346251d117196cf4',
            'info_dict': {
                'id': '53141',
                'ext': 'mp4',
                'title': 'Иван Васильевич меняет профессию',
                'description': 'md5:b924063ea1677c8fe343d8a72ac2195f',
                'duration': 5498,
                'thumbnail': r're:^https?://.*\.jpg$',
            },
            'skip': 'Only works from Russia',
        },
        # Serial's series
        {
            'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/9549',
            'md5': '221f56b35e3ed815fde2df71032f4b3e',
            'info_dict': {
                'id': '9549',
                'ext': 'mp4',
                'title': 'Двое из ларца - Дело Гольдберга (1 часть)',
                'series': 'Двое из ларца',
                'season': 'Сезон 1',
                'season_number': 1,
                'episode': 'Дело Гольдберга (1 часть)',
                'episode_number': 1,
                'duration': 2655,
                'thumbnail': r're:^https?://.*\.jpg$',
            },
            'skip': 'Only works from Russia',
        },
        {
            # with MP4-HD720 format
            'url': 'http://www.ivi.ru/watch/146500',
            'md5': 'd63d35cdbfa1ea61a5eafec7cc523e1e',
            'info_dict': {
                'id': '146500',
                'ext': 'mp4',
                'title': 'Кукла',
                'description': 'md5:ffca9372399976a2d260a407cc74cce6',
                'duration': 5599,
                'thumbnail': r're:^https?://.*\.jpg$',
            },
            'skip': 'Only works from Russia',
        },
        {
            'url': 'https://www.ivi.tv/watch/33560/',
            'only_matching': True,
        },
    ]

    # Sorted by quality
    _KNOWN_FORMATS = (
        'MP4-low-mobile', 'MP4-mobile', 'FLV-lo', 'MP4-lo', 'FLV-hi', 'MP4-hi',
        'MP4-SHQ', 'MP4-HD720', 'MP4-HD1080')

    def _real_extract(self, url):
        video_id = self._match_id(url)

        data = json.dumps({
            'method': 'da.content.get',
            'params': [
                video_id, {
                    'site': 's%d',
                    'referrer': 'http://www.ivi.ru/watch/%s' % video_id,
                    'contentid': video_id
                }
            ]
        })

        for site in (353, 183):
            content_data = (data % site).encode()
            if site == 353:
                try:
                    from Cryptodome.Cipher import Blowfish
                    from Cryptodome.Hash import CMAC
                    pycryptodome_found = True
                except ImportError:
                    try:
                        from Crypto.Cipher import Blowfish
                        from Crypto.Hash import CMAC
                        pycryptodome_found = True
                    except ImportError:
                        pycryptodome_found = False
                        continue

                timestamp = (self._download_json(
                    self._LIGHT_URL, video_id,
                    'Downloading timestamp JSON', data=json.dumps({
                        'method': 'da.timestamp.get',
                        'params': []
                    }).encode(), fatal=False) or {}).get('result')
                if not timestamp:
                    continue

                query = {
                    'ts': timestamp,
                    'sign': CMAC.new(self._LIGHT_KEY, timestamp.encode() + content_data, Blowfish).hexdigest(),
                }
            else:
                query = {}

            video_json = self._download_json(
                self._LIGHT_URL, video_id,
                'Downloading video JSON', data=content_data, query=query)

            error = video_json.get('error')
            if error:
                origin = error.get('origin')
                message = error.get('message') or error.get('user_message')
                extractor_msg = 'Unable to download video %s'
                if origin == 'NotAllowedForLocation':
                    self.raise_geo_restricted(message, self._GEO_COUNTRIES)
                elif origin == 'NoRedisValidData':
                    extractor_msg = 'Video %s does not exist'
                elif site == 353:
                    continue
                elif not pycryptodome_found:
                    raise ExtractorError('pycryptodomex not found. Please install', expected=True)
                elif message:
                    extractor_msg += ': ' + message
                raise ExtractorError(extractor_msg % video_id, expected=True)
            else:
                break

        result = video_json['result']
        title = result['title']

        quality = qualities(self._KNOWN_FORMATS)

        formats = []
        for f in result.get('files', []):
            f_url = f.get('url')
            content_format = f.get('content_format')
            if not f_url:
                continue
            if (not self.get_param('allow_unplayable_formats')
                    and ('-MDRM-' in content_format or '-FPS-' in content_format)):
                continue
            formats.append({
                'url': f_url,
                'format_id': content_format,
                'quality': quality(content_format),
                'filesize': int_or_none(f.get('size_in_bytes')),
            })
        self._sort_formats(formats)

        compilation = result.get('compilation')
        episode = title if compilation else None

        title = '%s - %s' % (compilation, title) if compilation is not None else title

        thumbnails = [{
            'url': preview['url'],
            'id': preview.get('content_format'),
        } for preview in result.get('preview', []) if preview.get('url')]

        webpage = self._download_webpage(url, video_id)

        season = self._search_regex(
            r'<li[^>]+class="season active"[^>]*><a[^>]+>([^<]+)',
            webpage, 'season', default=None)
        season_number = int_or_none(self._search_regex(
            r'<li[^>]+class="season active"[^>]*><a[^>]+data-season(?:-index)?="(\d+)"',
            webpage, 'season number', default=None))

        episode_number = int_or_none(self._search_regex(
            r'[^>]+itemprop="episode"[^>]*>\s*<meta[^>]+itemprop="episodeNumber"[^>]+content="(\d+)',
            webpage, 'episode number', default=None))

        description = self._og_search_description(webpage, default=None) or self._html_search_meta(
            'description', webpage, 'description', default=None)

        return {
            'id': video_id,
            'title': title,
            'series': compilation,
            'season': season,
            'season_number': season_number,
            'episode': episode,
            'episode_number': episode_number,
            'thumbnails': thumbnails,
            'description': description,
            'duration': int_or_none(result.get('duration')),
            'formats': formats,
        }


class IviCompilationIE(InfoExtractor):
    IE_DESC = 'ivi.ru compilations'
    IE_NAME = 'ivi:compilation'
    _VALID_URL = r'https?://(?:www\.)?ivi\.ru/watch/(?!\d+)(?P<compilationid>[a-z\d_-]+)(?:/season(?P<seasonid>\d+))?$'
    _TESTS = [{
        'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa',
        'info_dict': {
            'id': 'dvoe_iz_lartsa',
            'title': 'Двое из ларца (2006 - 2008)',
        },
        'playlist_mincount': 24,
    }, {
        'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/season1',
        'info_dict': {
            'id': 'dvoe_iz_lartsa/season1',
            'title': 'Двое из ларца (2006 - 2008) 1 сезон',
        },
        'playlist_mincount': 12,
    }]

    def _extract_entries(self, html, compilation_id):
        return [
            self.url_result(
                'http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), IviIE.ie_key())
            for serie in re.findall(
                r'<a\b[^>]+\bhref=["\']/watch/%s/(\d+)["\']' % compilation_id, html)]

    def _real_extract(self, url):
        mobj = self._match_valid_url(url)
        compilation_id = mobj.group('compilationid')
        season_id = mobj.group('seasonid')

        if season_id is not None:  # Season link
            season_page = self._download_webpage(
                url, compilation_id, 'Downloading season %s web page' % season_id)
            playlist_id = '%s/season%s' % (compilation_id, season_id)
            playlist_title = self._html_search_meta('title', season_page, 'title')
            entries = self._extract_entries(season_page, compilation_id)
        else:  # Compilation link
            compilation_page = self._download_webpage(url, compilation_id, 'Downloading compilation web page')
            playlist_id = compilation_id
            playlist_title = self._html_search_meta('title', compilation_page, 'title')
            seasons = re.findall(
                r'<a href="/watch/%s/season(\d+)' % compilation_id, compilation_page)
            if not seasons:  # No seasons in this compilation
                entries = self._extract_entries(compilation_page, compilation_id)
            else:
                entries = []
                for season_id in seasons:
                    season_page = self._download_webpage(
                        'http://www.ivi.ru/watch/%s/season%s' % (compilation_id, season_id),
                        compilation_id, 'Downloading season %s web page' % season_id)
                    entries.extend(self._extract_entries(season_page, compilation_id))

        return self.playlist_result(entries, playlist_id, playlist_title)
Commit	Line	Data
cf143c4d	1	# coding: utf-8
ceb2b7d2	2	from __future__ import unicode_literals
77aa6b32	3
77aa6b32	4	import json
80a51fc2	5	import re
77aa6b32	6
77aa6b32	7	from .common import InfoExtractor
1cc79574	8	from ..utils import (
77aa6b32	9	ExtractorError,
ab3176af	10	int_or_none,
cf143c4d	11	qualities,
77aa6b32	12	)
	13
	14
	15	class IviIE(InfoExtractor):
ceb2b7d2	16	IE_DESC = 'ivi.ru'
ceb2b7d2	17	IE_NAME = 'ivi'
022218f2	18	_VALID_URL = r'https?://(?:www\.)?ivi\.(?:ru\|tv)/(?:watch/(?:[^/]+/)?\|video/player\?.*?videoId=)(?P<id>\d+)'
42dcdbe1 S	19	_GEO_BYPASS = False
42dcdbe1 S	20	_GEO_COUNTRIES = ['RU']
656c2001 RA	21	_LIGHT_KEY = b'\xf1\x02\x32\xb7\xbc\x5c\x7a\xe8\xf7\x96\xc1\x33\x2b\x27\xa1\x8c'
656c2001 RA	22	_LIGHT_URL = 'https://api.ivi.ru/light/'
77aa6b32	23
	24	_TESTS = [
	25	# Single movie
	26	{
ceb2b7d2	27	'url': 'http://www.ivi.ru/watch/53141',
ceb2b7d2	28	'md5': '6ff5be2254e796ed346251d117196cf4',
ceb2b7d2	29	'info_dict': {
84dd7031 S	30	'id': '53141',
84dd7031 S	31	'ext': 'mp4',
ceb2b7d2	32	'title': 'Иван Васильевич меняет профессию',
	33	'description': 'md5:b924063ea1677c8fe343d8a72ac2195f',
	34	'duration': 5498,
ec85ded8	35	'thumbnail': r're:^https?://.*\.jpg$',
77aa6b32	36	},
ceb2b7d2	37	'skip': 'Only works from Russia',
77aa6b32	38	},
dfb1b146	39	# Serial's series
77aa6b32	40	{
6ebb46c1 S	41	'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/9549',
6ebb46c1 S	42	'md5': '221f56b35e3ed815fde2df71032f4b3e',
ceb2b7d2	43	'info_dict': {
6ebb46c1	44	'id': '9549',
84dd7031	45	'ext': 'mp4',
ab3176af S	46	'title': 'Двое из ларца - Дело Гольдберга (1 часть)',
ab3176af S	47	'series': 'Двое из ларца',
1463c5b9 S	48	'season': 'Сезон 1',
1463c5b9 S	49	'season_number': 1,
ab3176af S	50	'episode': 'Дело Гольдберга (1 часть)',
ab3176af S	51	'episode_number': 1,
6ebb46c1	52	'duration': 2655,
ec85ded8	53	'thumbnail': r're:^https?://.*\.jpg$',
77aa6b32	54	},
ceb2b7d2	55	'skip': 'Only works from Russia',
cf143c4d S	56	},
	57	{
	58	# with MP4-HD720 format
	59	'url': 'http://www.ivi.ru/watch/146500',
	60	'md5': 'd63d35cdbfa1ea61a5eafec7cc523e1e',
	61	'info_dict': {
	62	'id': '146500',
	63	'ext': 'mp4',
	64	'title': 'Кукла',
	65	'description': 'md5:ffca9372399976a2d260a407cc74cce6',
	66	'duration': 5599,
ec85ded8	67	'thumbnail': r're:^https?://.*\.jpg$',
cf143c4d S	68	},
cf143c4d S	69	'skip': 'Only works from Russia',
022218f2 S	70	},
	71	{
	72	'url': 'https://www.ivi.tv/watch/33560/',
	73	'only_matching': True,
	74	},
77aa6b32	75	]
ceb2b7d2	76
77aa6b32	77	# Sorted by quality
cf143c4d S	78	_KNOWN_FORMATS = (
	79	'MP4-low-mobile', 'MP4-mobile', 'FLV-lo', 'MP4-lo', 'FLV-hi', 'MP4-hi',
	80	'MP4-SHQ', 'MP4-HD720', 'MP4-HD1080')
77aa6b32	81
77aa6b32	82	def _real_extract(self, url):
63be3b89	83	video_id = self._match_id(url)
77aa6b32	84
656c2001	85	data = json.dumps({
63be3b89 S	86	'method': 'da.content.get',
	87	'params': [
	88	video_id, {
1bba88ef	89	'site': 's%d',
63be3b89 S	90	'referrer': 'http://www.ivi.ru/watch/%s' % video_id,
63be3b89 S	91	'contentid': video_id
77aa6b32	92	}
63be3b89	93	]
f8015c15	94	})
77aa6b32	95
76d9eca4	96	for site in (353, 183):
f8015c15	97	content_data = (data % site).encode()
76d9eca4 RA	98	if site == 353:
	99	try:
	100	from Cryptodome.Cipher import Blowfish
	101	from Cryptodome.Hash import CMAC
edf65256	102	pycryptodome_found = True
76d9eca4	103	except ImportError:
edf65256	104	try:
	105	from Crypto.Cipher import Blowfish
	106	from Crypto.Hash import CMAC
	107	pycryptodome_found = True
	108	except ImportError:
	109	pycryptodome_found = False
	110	continue
76d9eca4 RA	111
	112	timestamp = (self._download_json(
	113	self._LIGHT_URL, video_id,
	114	'Downloading timestamp JSON', data=json.dumps({
	115	'method': 'da.timestamp.get',
	116	'params': []
	117	}).encode(), fatal=False) or {}).get('result')
	118	if not timestamp:
	119	continue
	120
	121	query = {
	122	'ts': timestamp,
	123	'sign': CMAC.new(self._LIGHT_KEY, timestamp.encode() + content_data, Blowfish).hexdigest(),
	124	}
	125	else:
	126	query = {}
1bba88ef	127
76d9eca4	128	video_json = self._download_json(
1bba88ef	129	self._LIGHT_URL, video_id,
76d9eca4 RA	130	'Downloading video JSON', data=content_data, query=query)
	131
	132	error = video_json.get('error')
	133	if error:
	134	origin = error.get('origin')
	135	message = error.get('message') or error.get('user_message')
	136	extractor_msg = 'Unable to download video %s'
	137	if origin == 'NotAllowedForLocation':
	138	self.raise_geo_restricted(message, self._GEO_COUNTRIES)
	139	elif origin == 'NoRedisValidData':
	140	extractor_msg = 'Video %s does not exist'
	141	elif site == 353:
	142	continue
edf65256	143	elif not pycryptodome_found:
49e7e9c3	144	raise ExtractorError('pycryptodomex not found. Please install', expected=True)
76d9eca4 RA	145	elif message:
	146	extractor_msg += ': ' + message
	147	raise ExtractorError(extractor_msg % video_id, expected=True)
	148	else:
	149	break
77aa6b32	150
ceb2b7d2	151	result = video_json['result']
656c2001	152	title = result['title']
77aa6b32	153
cf143c4d S	154	quality = qualities(self._KNOWN_FORMATS)
cf143c4d S	155
656c2001 RA	156	formats = []
	157	for f in result.get('files', []):
	158	f_url = f.get('url')
	159	content_format = f.get('content_format')
06869367	160	if not f_url:
06869367	161	continue
a06916d9	162	if (not self.get_param('allow_unplayable_formats')
06869367	163	and ('-MDRM-' in content_format or '-FPS-' in content_format)):
656c2001 RA	164	continue
	165	formats.append({
	166	'url': f_url,
	167	'format_id': content_format,
	168	'quality': quality(content_format),
	169	'filesize': int_or_none(f.get('size_in_bytes')),
	170	})
bf5b0a1b PH	171	self._sort_formats(formats)
bf5b0a1b PH	172
ab3176af S	173	compilation = result.get('compilation')
	174	episode = title if compilation else None
	175
5f6a1245	176	title = '%s - %s' % (compilation, title) if compilation is not None else title
77aa6b32	177
ab3176af S	178	thumbnails = [{
	179	'url': preview['url'],
	180	'id': preview.get('content_format'),
	181	} for preview in result.get('preview', []) if preview.get('url')]
	182
	183	webpage = self._download_webpage(url, video_id)
	184
1463c5b9 S	185	season = self._search_regex(
	186	r'<li[^>]+class="season active"[^>]*><a[^>]+>([^<]+)',
	187	webpage, 'season', default=None)
	188	season_number = int_or_none(self._search_regex(
	189	r'<li[^>]+class="season active"[^>]*><a[^>]+data-season(?:-index)?="(\d+)"',
	190	webpage, 'season number', default=None))
	191
ab3176af	192	episode_number = int_or_none(self._search_regex(
3d897cc7	193	r'[^>]+itemprop="episode"[^>]>\s<meta[^>]+itemprop="episodeNumber"[^>]+content="(\d+)',
ab3176af	194	webpage, 'episode number', default=None))
77aa6b32	195
ab3176af S	196	description = self._og_search_description(webpage, default=None) or self._html_search_meta(
ab3176af S	197	'description', webpage, 'description', default=None)
77aa6b32	198
	199	return {
	200	'id': video_id,
	201	'title': title,
ab3176af	202	'series': compilation,
1463c5b9 S	203	'season': season,
1463c5b9 S	204	'season_number': season_number,
ab3176af S	205	'episode': episode,
	206	'episode_number': episode_number,
	207	'thumbnails': thumbnails,
77aa6b32	208	'description': description,
656c2001	209	'duration': int_or_none(result.get('duration')),
77aa6b32	210	'formats': formats,
	211	}
	212
	213
	214	class IviCompilationIE(InfoExtractor):
ceb2b7d2	215	IE_DESC = 'ivi.ru compilations'
ceb2b7d2	216	IE_NAME = 'ivi:compilation'
84dd7031	217	_VALID_URL = r'https?://(?:www\.)?ivi\.ru/watch/(?!\d+)(?P<compilationid>[a-z\d_-]+)(?:/season(?P<seasonid>\d+))?$'
22a6f150 PH	218	_TESTS = [{
	219	'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa',
	220	'info_dict': {
	221	'id': 'dvoe_iz_lartsa',
	222	'title': 'Двое из ларца (2006 - 2008)',
	223	},
	224	'playlist_mincount': 24,
	225	}, {
	226	'url': 'http://www.ivi.ru/watch/dvoe_iz_lartsa/season1',
	227	'info_dict': {
	228	'id': 'dvoe_iz_lartsa/season1',
	229	'title': 'Двое из ларца (2006 - 2008) 1 сезон',
	230	},
	231	'playlist_mincount': 12,
	232	}]
77aa6b32	233
77aa6b32	234	def _extract_entries(self, html, compilation_id):
c6270b2e S	235	return [
	236	self.url_result(
	237	'http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), IviIE.ie_key())
	238	for serie in re.findall(
d9a2f867	239	r'<a\b[^>]+\bhref=["\']/watch/%s/(\d+)["\']' % compilation_id, html)]
77aa6b32	240
77aa6b32	241	def _real_extract(self, url):
5ad28e7f	242	mobj = self._match_valid_url(url)
77aa6b32	243	compilation_id = mobj.group('compilationid')
	244	season_id = mobj.group('seasonid')
	245
5f6a1245	246	if season_id is not None: # Season link
c6270b2e S	247	season_page = self._download_webpage(
c6270b2e S	248	url, compilation_id, 'Downloading season %s web page' % season_id)
77aa6b32	249	playlist_id = '%s/season%s' % (compilation_id, season_id)
ceb2b7d2	250	playlist_title = self._html_search_meta('title', season_page, 'title')
77aa6b32	251	entries = self._extract_entries(season_page, compilation_id)
5f6a1245	252	else: # Compilation link
ceb2b7d2	253	compilation_page = self._download_webpage(url, compilation_id, 'Downloading compilation web page')
77aa6b32	254	playlist_id = compilation_id
ceb2b7d2	255	playlist_title = self._html_search_meta('title', compilation_page, 'title')
c6270b2e S	256	seasons = re.findall(
	257	r'<a href="/watch/%s/season(\d+)' % compilation_id, compilation_page)
	258	if not seasons: # No seasons in this compilation
77aa6b32	259	entries = self._extract_entries(compilation_page, compilation_id)
	260	else:
	261	entries = []
	262	for season_id in seasons:
ceb2b7d2	263	season_page = self._download_webpage(
	264	'http://www.ivi.ru/watch/%s/season%s' % (compilation_id, season_id),
	265	compilation_id, 'Downloading season %s web page' % season_id)
77aa6b32	266	entries.extend(self._extract_entries(season_page, compilation_id))
77aa6b32	267
5f6a1245	268	return self.playlist_result(entries, playlist_id, playlist_title)