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

# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import compat_urllib_parse_urlparse
from ..utils import (
    ExtractorError,
    parse_iso8601,
    qualities,
)


class SRGSSRIE(InfoExtractor):
    _VALID_URL = r'(?:https?://tp\.srgssr\.ch/p(?:/[^/]+)+\?urn=urn|srgssr):(?P<bu>srf|rts|rsi|rtr|swi):(?:[^:]+:)?(?P<type>video|audio):(?P<id>[0-9a-f\-]{36}|\d+)'
    _GEO_BYPASS = False
    _GEO_COUNTRIES = ['CH']

    _ERRORS = {
        'AGERATING12': 'To protect children under the age of 12, this video is only available between 8 p.m. and 6 a.m.',
        'AGERATING18': 'To protect children under the age of 18, this video is only available between 11 p.m. and 5 a.m.',
        # 'ENDDATE': 'For legal reasons, this video was only available for a specified period of time.',
        'GEOBLOCK': 'For legal reasons, this video is only available in Switzerland.',
        'LEGAL': 'The video cannot be transmitted for legal reasons.',
        'STARTDATE': 'This video is not yet available. Please try again later.',
    }

    def _get_tokenized_src(self, url, video_id, format_id):
        sp = compat_urllib_parse_urlparse(url).path.split('/')
        token = self._download_json(
            'http://tp.srgssr.ch/akahd/token?acl=/%s/%s/*' % (sp[1], sp[2]),
            video_id, 'Downloading %s token' % format_id, fatal=False) or {}
        auth_params = token.get('token', {}).get('authparams')
        if auth_params:
            url += '?' + auth_params
        return url

    def get_media_data(self, bu, media_type, media_id):
        media_data = self._download_json(
            'http://il.srgssr.ch/integrationlayer/1.0/ue/%s/%s/play/%s.json' % (bu, media_type, media_id),
            media_id)[media_type.capitalize()]

        if media_data.get('block') and media_data['block'] in self._ERRORS:
            message = self._ERRORS[media_data['block']]
            if media_data['block'] == 'GEOBLOCK':
                self.raise_geo_restricted(
                    msg=message, countries=self._GEO_COUNTRIES)
            raise ExtractorError(
                '%s said: %s' % (self.IE_NAME, message), expected=True)

        return media_data

    def _real_extract(self, url):
        bu, media_type, media_id = re.match(self._VALID_URL, url).groups()

        media_data = self.get_media_data(bu, media_type, media_id)

        metadata = media_data['AssetMetadatas']['AssetMetadata'][0]
        title = metadata['title']
        description = metadata.get('description')
        created_date = media_data.get('createdDate') or metadata.get('createdDate')
        timestamp = parse_iso8601(created_date)

        thumbnails = [{
            'id': image.get('id'),
            'url': image['url'],
        } for image in media_data.get('Image', {}).get('ImageRepresentations', {}).get('ImageRepresentation', [])]

        preference = qualities(['LQ', 'MQ', 'SD', 'HQ', 'HD'])
        formats = []
        for source in media_data.get('Playlists', {}).get('Playlist', []) + media_data.get('Downloads', {}).get('Download', []):
            protocol = source.get('@protocol')
            for asset in source['url']:
                asset_url = asset['text']
                quality = asset['@quality']
                format_id = '%s-%s' % (protocol, quality)
                if protocol.startswith('HTTP-HDS') or protocol.startswith('HTTP-HLS'):
                    asset_url = self._get_tokenized_src(asset_url, media_id, format_id)
                    if protocol.startswith('HTTP-HDS'):
                        formats.extend(self._extract_f4m_formats(
                            asset_url + ('?' if '?' not in asset_url else '&') + 'hdcore=3.4.0',
                            media_id, f4m_id=format_id, fatal=False))
                    elif protocol.startswith('HTTP-HLS'):
                        formats.extend(self._extract_m3u8_formats(
                            asset_url, media_id, 'mp4', 'm3u8_native',
                            m3u8_id=format_id, fatal=False))
                else:
                    formats.append({
                        'format_id': format_id,
                        'url': asset_url,
                        'quality': preference(quality),
                        'ext': 'flv' if protocol == 'RTMP' else None,
                    })
        self._sort_formats(formats)

        return {
            'id': media_id,
            'title': title,
            'description': description,
            'timestamp': timestamp,
            'thumbnails': thumbnails,
            'formats': formats,
        }


class SRGSSRPlayIE(InfoExtractor):
    IE_DESC = 'srf.ch, rts.ch, rsi.ch, rtr.ch and swissinfo.ch play sites'
    _VALID_URL = r'''(?x)
                    https?://
                        (?:(?:www|play)\.)?
                        (?P<bu>srf|rts|rsi|rtr|swissinfo)\.ch/play/(?:tv|radio)/
                        (?:
                            [^/]+/(?P<type>video|audio)/[^?]+|
                            popup(?P<type_2>video|audio)player
                        )
                        \?.*?\b(?:id=|urn=urn:[^:]+:video:)(?P<id>[0-9a-f\-]{36}|\d+)
                    '''

    _TESTS = [{
        'url': 'http://www.srf.ch/play/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5',
        'md5': 'da6b5b3ac9fa4761a942331cef20fcb3',
        'info_dict': {
            'id': '28e1a57d-5b76-4399-8ab3-9097f071e6c5',
            'ext': 'mp4',
            'upload_date': '20130701',
            'title': 'Snowden beantragt Asyl in Russland',
            'timestamp': 1372713995,
        }
    }, {
        # No Speichern (Save) button
        'url': 'http://www.srf.ch/play/tv/top-gear/video/jaguar-xk120-shadow-und-tornado-dampflokomotive?id=677f5829-e473-4823-ac83-a1087fe97faa',
        'md5': '0a274ce38fda48c53c01890651985bc6',
        'info_dict': {
            'id': '677f5829-e473-4823-ac83-a1087fe97faa',
            'ext': 'flv',
            'upload_date': '20130710',
            'title': 'Jaguar XK120, Shadow und Tornado-Dampflokomotive',
            'description': 'md5:88604432b60d5a38787f152dec89cd56',
            'timestamp': 1373493600,
        },
    }, {
        'url': 'http://www.rtr.ch/play/radio/actualitad/audio/saira-tujetsch-tuttina-cuntinuar-cun-sedrun-muster-turissem?id=63cb0778-27f8-49af-9284-8c7a8c6d15fc',
        'info_dict': {
            'id': '63cb0778-27f8-49af-9284-8c7a8c6d15fc',
            'ext': 'mp3',
            'upload_date': '20151013',
            'title': 'Saira: Tujetsch - tuttina cuntinuar cun Sedrun Mustér Turissem',
            'timestamp': 1444750398,
        },
        'params': {
            # rtmp download
            'skip_download': True,
        },
    }, {
        'url': 'http://www.rts.ch/play/tv/-/video/le-19h30?id=6348260',
        'md5': '67a2a9ae4e8e62a68d0e9820cc9782df',
        'info_dict': {
            'id': '6348260',
            'display_id': '6348260',
            'ext': 'mp4',
            'duration': 1796,
            'title': 'Le 19h30',
            'description': '',
            'uploader': '19h30',
            'upload_date': '20141201',
            'timestamp': 1417458600,
            'thumbnail': r're:^https?://.*\.image',
            'view_count': int,
        },
        'params': {
            # m3u8 download
            'skip_download': True,
        }
    }, {
        'url': 'https://www.srf.ch/play/tv/popupvideoplayer?id=c4dba0ca-e75b-43b2-a34f-f708a4932e01',
        'only_matching': True,
    }, {
        'url': 'https://www.srf.ch/play/tv/10vor10/video/snowden-beantragt-asyl-in-russland?urn=urn:srf:video:28e1a57d-5b76-4399-8ab3-9097f071e6c5',
        'only_matching': True,
    }, {
        'url': 'https://www.rts.ch/play/tv/19h30/video/le-19h30?urn=urn:rts:video:6348260',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        bu = mobj.group('bu')
        media_type = mobj.group('type') or mobj.group('type_2')
        media_id = mobj.group('id')
        # other info can be extracted from url + '&layout=json'
        return self.url_result('srgssr:%s:%s:%s' % (bu[:3], media_type, media_id), 'SRGSSR')
Commit	Line	Data
1ef15636	1	# coding: utf-8
	2	from __future__ import unicode_literals
	3
	4	import re
	5
	6	from .common import InfoExtractor
68601ef3	7	from ..compat import compat_urllib_parse_urlparse
1ef15636	8	from ..utils import (
	9	ExtractorError,
	10	parse_iso8601,
	11	qualities,
	12	)
	13
	14
	15	class SRGSSRIE(InfoExtractor):
e09f58b3	16	_VALID_URL = r'(?:https?://tp\.srgssr\.ch/p(?:/[^/]+)+\?urn=urn\|srgssr):(?P<bu>srf\|rts\|rsi\|rtr\|swi):(?:[^:]+:)?(?P<type>video\|audio):(?P<id>[0-9a-f\-]{36}\|\d+)'
4248dad9 S	17	_GEO_BYPASS = False
4248dad9 S	18	_GEO_COUNTRIES = ['CH']
1ef15636	19
	20	_ERRORS = {
	21	'AGERATING12': 'To protect children under the age of 12, this video is only available between 8 p.m. and 6 a.m.',
	22	'AGERATING18': 'To protect children under the age of 18, this video is only available between 11 p.m. and 5 a.m.',
7db2897d	23	# 'ENDDATE': 'For legal reasons, this video was only available for a specified period of time.',
1ef15636	24	'GEOBLOCK': 'For legal reasons, this video is only available in Switzerland.',
	25	'LEGAL': 'The video cannot be transmitted for legal reasons.',
	26	'STARTDATE': 'This video is not yet available. Please try again later.',
	27	}
	28
68601ef3 RA	29	def _get_tokenized_src(self, url, video_id, format_id):
	30	sp = compat_urllib_parse_urlparse(url).path.split('/')
	31	token = self._download_json(
	32	'http://tp.srgssr.ch/akahd/token?acl=/%s/%s/*' % (sp[1], sp[2]),
	33	video_id, 'Downloading %s token' % format_id, fatal=False) or {}
	34	auth_params = token.get('token', {}).get('authparams')
	35	if auth_params:
	36	url += '?' + auth_params
	37	return url
	38
7db2897d	39	def get_media_data(self, bu, media_type, media_id):
1ef15636	40	media_data = self._download_json(
	41	'http://il.srgssr.ch/integrationlayer/1.0/ue/%s/%s/play/%s.json' % (bu, media_type, media_id),
	42	media_id)[media_type.capitalize()]
	43
	44	if media_data.get('block') and media_data['block'] in self._ERRORS:
71631862 S	45	message = self._ERRORS[media_data['block']]
71631862 S	46	if media_data['block'] == 'GEOBLOCK':
4248dad9 S	47	self.raise_geo_restricted(
4248dad9 S	48	msg=message, countries=self._GEO_COUNTRIES)
71631862 S	49	raise ExtractorError(
71631862 S	50	'%s said: %s' % (self.IE_NAME, message), expected=True)
7db2897d	51
	52	return media_data
	53
	54	def _real_extract(self, url):
	55	bu, media_type, media_id = re.match(self._VALID_URL, url).groups()
	56
7db2897d	57	media_data = self.get_media_data(bu, media_type, media_id)
1ef15636	58
	59	metadata = media_data['AssetMetadatas']['AssetMetadata'][0]
	60	title = metadata['title']
	61	description = metadata.get('description')
	62	created_date = media_data.get('createdDate') or metadata.get('createdDate')
	63	timestamp = parse_iso8601(created_date)
	64
422f7c11	65	thumbnails = [{
	66	'id': image.get('id'),
	67	'url': image['url'],
	68	} for image in media_data.get('Image', {}).get('ImageRepresentations', {}).get('ImageRepresentation', [])]
1ef15636	69
	70	preference = qualities(['LQ', 'MQ', 'SD', 'HQ', 'HD'])
	71	formats = []
422f7c11	72	for source in media_data.get('Playlists', {}).get('Playlist', []) + media_data.get('Downloads', {}).get('Download', []):
1ef15636	73	protocol = source.get('@protocol')
0d8a0fdc	74	for asset in source['url']:
	75	asset_url = asset['text']
	76	quality = asset['@quality']
	77	format_id = '%s-%s' % (protocol, quality)
68601ef3 RA	78	if protocol.startswith('HTTP-HDS') or protocol.startswith('HTTP-HLS'):
	79	asset_url = self._get_tokenized_src(asset_url, media_id, format_id)
	80	if protocol.startswith('HTTP-HDS'):
	81	formats.extend(self._extract_f4m_formats(
	82	asset_url + ('?' if '?' not in asset_url else '&') + 'hdcore=3.4.0',
	83	media_id, f4m_id=format_id, fatal=False))
	84	elif protocol.startswith('HTTP-HLS'):
	85	formats.extend(self._extract_m3u8_formats(
	86	asset_url, media_id, 'mp4', 'm3u8_native',
	87	m3u8_id=format_id, fatal=False))
0d8a0fdc	88	else:
1ef15636	89	formats.append({
0d8a0fdc	90	'format_id': format_id,
1ef15636	91	'url': asset_url,
f983b875	92	'quality': preference(quality),
6ad2b01e	93	'ext': 'flv' if protocol == 'RTMP' else None,
1ef15636	94	})
1ef15636	95	self._sort_formats(formats)
	96
	97	return {
	98	'id': media_id,
	99	'title': title,
	100	'description': description,
	101	'timestamp': timestamp,
	102	'thumbnails': thumbnails,
	103	'formats': formats,
	104	}
	105
	106
	107	class SRGSSRPlayIE(InfoExtractor):
ce7d243c	108	IE_DESC = 'srf.ch, rts.ch, rsi.ch, rtr.ch and swissinfo.ch play sites'
25b83c2a S	109	_VALID_URL = r'''(?x)
	110	https?://
	111	(?:(?:www\|play)\.)?
	112	(?P<bu>srf\|rts\|rsi\|rtr\|swissinfo)\.ch/play/(?:tv\|radio)/
	113	(?:
	114	[^/]+/(?P<type>video\|audio)/[^?]+\|
	115	popup(?P<type_2>video\|audio)player
	116	)
06cd4cdb	117	\?.*?\b(?:id=\|urn=urn:[^:]+:video:)(?P<id>[0-9a-f\-]{36}\|\d+)
25b83c2a	118	'''
1ef15636	119
	120	_TESTS = [{
	121	'url': 'http://www.srf.ch/play/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5',
68601ef3	122	'md5': 'da6b5b3ac9fa4761a942331cef20fcb3',
1ef15636	123	'info_dict': {
1ef15636	124	'id': '28e1a57d-5b76-4399-8ab3-9097f071e6c5',
68601ef3	125	'ext': 'mp4',
1ef15636	126	'upload_date': '20130701',
	127	'title': 'Snowden beantragt Asyl in Russland',
	128	'timestamp': 1372713995,
	129	}
	130	}, {
	131	# No Speichern (Save) button
	132	'url': 'http://www.srf.ch/play/tv/top-gear/video/jaguar-xk120-shadow-und-tornado-dampflokomotive?id=677f5829-e473-4823-ac83-a1087fe97faa',
	133	'md5': '0a274ce38fda48c53c01890651985bc6',
	134	'info_dict': {
	135	'id': '677f5829-e473-4823-ac83-a1087fe97faa',
	136	'ext': 'flv',
	137	'upload_date': '20130710',
	138	'title': 'Jaguar XK120, Shadow und Tornado-Dampflokomotive',
	139	'description': 'md5:88604432b60d5a38787f152dec89cd56',
	140	'timestamp': 1373493600,
	141	},
7db2897d	142	}, {
e09f58b3	143	'url': 'http://www.rtr.ch/play/radio/actualitad/audio/saira-tujetsch-tuttina-cuntinuar-cun-sedrun-muster-turissem?id=63cb0778-27f8-49af-9284-8c7a8c6d15fc',
	144	'info_dict': {
	145	'id': '63cb0778-27f8-49af-9284-8c7a8c6d15fc',
	146	'ext': 'mp3',
	147	'upload_date': '20151013',
	148	'title': 'Saira: Tujetsch - tuttina cuntinuar cun Sedrun Mustér Turissem',
	149	'timestamp': 1444750398,
	150	},
	151	'params': {
	152	# rtmp download
	153	'skip_download': True,
	154	},
7db2897d	155	}, {
	156	'url': 'http://www.rts.ch/play/tv/-/video/le-19h30?id=6348260',
	157	'md5': '67a2a9ae4e8e62a68d0e9820cc9782df',
	158	'info_dict': {
	159	'id': '6348260',
	160	'display_id': '6348260',
422f7c11	161	'ext': 'mp4',
7db2897d	162	'duration': 1796,
	163	'title': 'Le 19h30',
	164	'description': '',
	165	'uploader': '19h30',
	166	'upload_date': '20141201',
	167	'timestamp': 1417458600,
ec85ded8	168	'thumbnail': r're:^https?://.*\.image',
7db2897d	169	'view_count': int,
7db2897d	170	},
422f7c11	171	'params': {
	172	# m3u8 download
	173	'skip_download': True,
	174	}
3fe77472 SP	175	}, {
3fe77472 SP	176	'url': 'https://www.srf.ch/play/tv/popupvideoplayer?id=c4dba0ca-e75b-43b2-a34f-f708a4932e01',
25b83c2a	177	'only_matching': True,
06cd4cdb S	178	}, {
	179	'url': 'https://www.srf.ch/play/tv/10vor10/video/snowden-beantragt-asyl-in-russland?urn=urn:srf:video:28e1a57d-5b76-4399-8ab3-9097f071e6c5',
	180	'only_matching': True,
	181	}, {
	182	'url': 'https://www.rts.ch/play/tv/19h30/video/le-19h30?urn=urn:rts:video:6348260',
	183	'only_matching': True,
1ef15636	184	}]
	185
	186	def _real_extract(self, url):
25b83c2a S	187	mobj = re.match(self._VALID_URL, url)
	188	bu = mobj.group('bu')
	189	media_type = mobj.group('type') or mobj.group('type_2')
	190	media_id = mobj.group('id')
7db2897d	191	# other info can be extracted from url + '&layout=json'
e09f58b3	192	return self.url_result('srgssr:%s:%s:%s' % (bu[:3], media_type, media_id), 'SRGSSR')