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

# coding: utf-8
from __future__ import unicode_literals

import base64
import io
import re
import sys

from .common import InfoExtractor
from ..compat import (
    compat_b64decode,
    compat_struct_unpack,
)
from ..utils import (
    determine_ext,
    ExtractorError,
    float_or_none,
    qualities,
    remove_end,
    remove_start,
    std_headers,
)

_bytes_to_chr = (lambda x: x) if sys.version_info[0] == 2 else (lambda x: map(chr, x))


class RTVEALaCartaIE(InfoExtractor):
    IE_NAME = 'rtve.es:alacarta'
    IE_DESC = 'RTVE a la carta'
    _VALID_URL = r'https?://(?:www\.)?rtve\.es/(m/)?(alacarta/videos|filmoteca)/[^/]+/[^/]+/(?P<id>\d+)'

    _TESTS = [{
        'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
        'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43',
        'info_dict': {
            'id': '2491869',
            'ext': 'mp4',
            'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia',
            'duration': 5024.566,
            'series': 'Balonmano',
        },
        'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
    }, {
        'note': 'Live stream',
        'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/',
        'info_dict': {
            'id': '1694255',
            'ext': 'mp4',
            'title': 're:^24H LIVE [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
            'is_live': True,
        },
        'params': {
            'skip_download': 'live stream',
        },
    }, {
        'url': 'http://www.rtve.es/alacarta/videos/servir-y-proteger/servir-proteger-capitulo-104/4236788/',
        'md5': 'd850f3c8731ea53952ebab489cf81cbf',
        'info_dict': {
            'id': '4236788',
            'ext': 'mp4',
            'title': 'Servir y proteger - Capítulo 104',
            'duration': 3222.0,
        },
        'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
    }, {
        'url': 'http://www.rtve.es/m/alacarta/videos/cuentame-como-paso/cuentame-como-paso-t16-ultimo-minuto-nuestra-vida-capitulo-276/2969138/?media=tve',
        'only_matching': True,
    }, {
        'url': 'http://www.rtve.es/filmoteca/no-do/not-1-introduccion-primer-noticiario-espanol/1465256/',
        'only_matching': True,
    }]

    def _real_initialize(self):
        user_agent_b64 = base64.b64encode(std_headers['User-Agent'].encode('utf-8')).decode('utf-8')
        self._manager = self._download_json(
            'http://www.rtve.es/odin/loki/' + user_agent_b64,
            None, 'Fetching manager info')['manager']

    @staticmethod
    def _decrypt_url(png):
        encrypted_data = io.BytesIO(compat_b64decode(png)[8:])
        while True:
            length = compat_struct_unpack('!I', encrypted_data.read(4))[0]
            chunk_type = encrypted_data.read(4)
            if chunk_type == b'IEND':
                break
            data = encrypted_data.read(length)
            if chunk_type == b'tEXt':
                alphabet_data, text = data.split(b'\0')
                quality, url_data = text.split(b'%%')
                alphabet = []
                e = 0
                d = 0
                for l in _bytes_to_chr(alphabet_data):
                    if d == 0:
                        alphabet.append(l)
                        d = e = (e + 1) % 4
                    else:
                        d -= 1
                url = ''
                f = 0
                e = 3
                b = 1
                for letter in _bytes_to_chr(url_data):
                    if f == 0:
                        l = int(letter) * 10
                        f = 1
                    else:
                        if e == 0:
                            l += int(letter)
                            url += alphabet[l]
                            e = (b + 3) % 4
                            f = 0
                            b += 1
                        else:
                            e -= 1

                yield quality.decode(), url
            encrypted_data.read(4)  # CRC

    def _extract_png_formats(self, video_id):
        png = self._download_webpage(
            'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id),
            video_id, 'Downloading url information', query={'q': 'v2'})
        q = qualities(['Media', 'Alta', 'HQ', 'HD_READY', 'HD_FULL'])
        formats = []
        for quality, video_url in self._decrypt_url(png):
            ext = determine_ext(video_url)
            if ext == 'm3u8':
                formats.extend(self._extract_m3u8_formats(
                    video_url, video_id, 'mp4', 'm3u8_native',
                    m3u8_id='hls', fatal=False))
            elif ext == 'mpd':
                formats.extend(self._extract_mpd_formats(
                    video_url, video_id, 'dash', fatal=False))
            else:
                formats.append({
                    'format_id': quality,
                    'quality': q(quality),
                    'url': video_url,
                })
        self._sort_formats(formats)
        return formats

    def _real_extract(self, url):
        video_id = self._match_id(url)
        info = self._download_json(
            'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
            video_id)['page']['items'][0]
        if info['state'] == 'DESPU':
            raise ExtractorError('The video is no longer available', expected=True)
        title = info['title'].strip()
        formats = self._extract_png_formats(video_id)

        subtitles = None
        sbt_file = info.get('sbtFile')
        if sbt_file:
            subtitles = self.extract_subtitles(video_id, sbt_file)

        is_live = info.get('live') is True

        return {
            'id': video_id,
            'title': self._live_title(title) if is_live else title,
            'formats': formats,
            'thumbnail': info.get('image'),
            'subtitles': subtitles,
            'duration': float_or_none(info.get('duration'), 1000),
            'is_live': is_live,
            'series': info.get('programTitle'),
        }

    def _get_subtitles(self, video_id, sub_file):
        subs = self._download_json(
            sub_file + '.json', video_id,
            'Downloading subtitles info')['page']['items']
        return dict(
            (s['lang'], [{'ext': 'vtt', 'url': s['src']}])
            for s in subs)


class RTVEInfantilIE(RTVEALaCartaIE):
    IE_NAME = 'rtve.es:infantil'
    IE_DESC = 'RTVE infantil'
    _VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/[^/]+/video/[^/]+/(?P<id>[0-9]+)/'

    _TESTS = [{
        'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/',
        'md5': '5747454717aedf9f9fdf212d1bcfc48d',
        'info_dict': {
            'id': '3040283',
            'ext': 'mp4',
            'title': 'Maneras de vivir',
            'thumbnail': r're:https?://.+/1426182947956\.JPG',
            'duration': 357.958,
        },
        'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
    }]


class RTVELiveIE(RTVEALaCartaIE):
    IE_NAME = 'rtve.es:live'
    IE_DESC = 'RTVE.es live streams'
    _VALID_URL = r'https?://(?:www\.)?rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)'

    _TESTS = [{
        'url': 'http://www.rtve.es/directo/la-1/',
        'info_dict': {
            'id': 'la-1',
            'ext': 'mp4',
            'title': 're:^La 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
        },
        'params': {
            'skip_download': 'live stream',
        }
    }]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        video_id = mobj.group('id')

        webpage = self._download_webpage(url, video_id)
        title = remove_end(self._og_search_title(webpage), ' en directo en RTVE.es')
        title = remove_start(title, 'Estoy viendo ')

        vidplayer_id = self._search_regex(
            (r'playerId=player([0-9]+)',
             r'class=["\'].*?\blive_mod\b.*?["\'][^>]+data-assetid=["\'](\d+)',
             r'data-id=["\'](\d+)'),
            webpage, 'internal video ID')

        return {
            'id': video_id,
            'title': self._live_title(title),
            'formats': self._extract_png_formats(vidplayer_id),
            'is_live': True,
        }


class RTVETelevisionIE(InfoExtractor):
    IE_NAME = 'rtve.es:television'
    _VALID_URL = r'https?://(?:www\.)?rtve\.es/television/[^/]+/[^/]+/(?P<id>\d+).shtml'

    _TEST = {
        'url': 'http://www.rtve.es/television/20160628/revolucion-del-movil/1364141.shtml',
        'info_dict': {
            'id': '3069778',
            'ext': 'mp4',
            'title': 'Documentos TV - La revolución del móvil',
            'duration': 3496.948,
        },
        'params': {
            'skip_download': True,
        },
    }

    def _real_extract(self, url):
        page_id = self._match_id(url)
        webpage = self._download_webpage(url, page_id)

        alacarta_url = self._search_regex(
            r'data-location="alacarta_videos"[^<]+url&quot;:&quot;(http://www\.rtve\.es/alacarta.+?)&',
            webpage, 'alacarta url', default=None)
        if alacarta_url is None:
            raise ExtractorError(
                'The webpage doesn\'t contain any video', expected=True)

        return self.url_result(alacarta_url, ie=RTVEALaCartaIE.ie_key())
Commit	Line	Data
dcdb292f	1	# coding: utf-8
91a6adde JMF	2	from __future__ import unicode_literals
91a6adde JMF	3
91a6adde	4	import base64
10db0d2f	5	import io
2b9faf55	6	import re
10db0d2f	7	import sys
91a6adde JMF	8
91a6adde JMF	9	from .common import InfoExtractor
dab0daee	10	from ..compat import (
cf282071	11	compat_b64decode,
edaa23f8	12	compat_struct_unpack,
dab0daee	13	)
91a6adde	14	from ..utils import (
2c53bd51	15	determine_ext,
ce73839f	16	ExtractorError,
f3bff94c	17	float_or_none,
10db0d2f	18	qualities,
2b9faf55	19	remove_end,
3e769682	20	remove_start,
e9f65f87	21	std_headers,
91a6adde JMF	22	)
91a6adde JMF	23
10db0d2f	24	_bytes_to_chr = (lambda x: x) if sys.version_info[0] == 2 else (lambda x: map(chr, x))
2b9faf55 PH	25
2b9faf55 PH	26
91a6adde JMF	27	class RTVEALaCartaIE(InfoExtractor):
	28	IE_NAME = 'rtve.es:alacarta'
	29	IE_DESC = 'RTVE a la carta'
92519402	30	_VALID_URL = r'https?://(?:www\.)?rtve\.es/(m/)?(alacarta/videos\|filmoteca)/[^/]+/[^/]+/(?P<id>\d+)'
91a6adde	31
2b9faf55	32	_TESTS = [{
91a6adde	33	'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
9aeaf730	34	'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43',
91a6adde JMF	35	'info_dict': {
	36	'id': '2491869',
	37	'ext': 'mp4',
	38	'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia',
f3bff94c	39	'duration': 5024.566,
10db0d2f	40	'series': 'Balonmano',
91a6adde	41	},
10db0d2f	42	'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
2b9faf55 PH	43	}, {
	44	'note': 'Live stream',
	45	'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/',
	46	'info_dict': {
	47	'id': '1694255',
10db0d2f	48	'ext': 'mp4',
	49	'title': 're:^24H LIVE [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
	50	'is_live': True,
	51	},
	52	'params': {
	53	'skip_download': 'live stream',
cc57bd33	54	},
2c53bd51 GF	55	}, {
2c53bd51 GF	56	'url': 'http://www.rtve.es/alacarta/videos/servir-y-proteger/servir-proteger-capitulo-104/4236788/',
10db0d2f	57	'md5': 'd850f3c8731ea53952ebab489cf81cbf',
2c53bd51 GF	58	'info_dict': {
	59	'id': '4236788',
	60	'ext': 'mp4',
10db0d2f	61	'title': 'Servir y proteger - Capítulo 104',
2c53bd51 GF	62	'duration': 3222.0,
2c53bd51 GF	63	},
10db0d2f	64	'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
cd596028 JMF	65	}, {
	66	'url': 'http://www.rtve.es/m/alacarta/videos/cuentame-como-paso/cuentame-como-paso-t16-ultimo-minuto-nuestra-vida-capitulo-276/2969138/?media=tve',
	67	'only_matching': True,
4c718d3c JMF	68	}, {
	69	'url': 'http://www.rtve.es/filmoteca/no-do/not-1-introduccion-primer-noticiario-espanol/1465256/',
	70	'only_matching': True,
2b9faf55	71	}]
91a6adde	72
e9f65f87 JMF	73	def _real_initialize(self):
e9f65f87 JMF	74	user_agent_b64 = base64.b64encode(std_headers['User-Agent'].encode('utf-8')).decode('utf-8')
10db0d2f	75	self._manager = self._download_json(
e9f65f87	76	'http://www.rtve.es/odin/loki/' + user_agent_b64,
10db0d2f	77	None, 'Fetching manager info')['manager']
	78
	79	@staticmethod
	80	def _decrypt_url(png):
	81	encrypted_data = io.BytesIO(compat_b64decode(png)[8:])
	82	while True:
	83	length = compat_struct_unpack('!I', encrypted_data.read(4))[0]
	84	chunk_type = encrypted_data.read(4)
	85	if chunk_type == b'IEND':
	86	break
	87	data = encrypted_data.read(length)
	88	if chunk_type == b'tEXt':
	89	alphabet_data, text = data.split(b'\0')
	90	quality, url_data = text.split(b'%%')
	91	alphabet = []
	92	e = 0
	93	d = 0
	94	for l in _bytes_to_chr(alphabet_data):
	95	if d == 0:
	96	alphabet.append(l)
	97	d = e = (e + 1) % 4
	98	else:
	99	d -= 1
	100	url = ''
	101	f = 0
	102	e = 3
	103	b = 1
	104	for letter in _bytes_to_chr(url_data):
	105	if f == 0:
	106	l = int(letter) * 10
	107	f = 1
	108	else:
	109	if e == 0:
	110	l += int(letter)
	111	url += alphabet[l]
	112	e = (b + 3) % 4
	113	f = 0
	114	b += 1
	115	else:
	116	e -= 1
	117
	118	yield quality.decode(), url
	119	encrypted_data.read(4) # CRC
	120
	121	def _extract_png_formats(self, video_id):
	122	png = self._download_webpage(
	123	'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id),
	124	video_id, 'Downloading url information', query={'q': 'v2'})
	125	q = qualities(['Media', 'Alta', 'HQ', 'HD_READY', 'HD_FULL'])
	126	formats = []
	127	for quality, video_url in self._decrypt_url(png):
	128	ext = determine_ext(video_url)
	129	if ext == 'm3u8':
	130	formats.extend(self._extract_m3u8_formats(
	131	video_url, video_id, 'mp4', 'm3u8_native',
	132	m3u8_id='hls', fatal=False))
	133	elif ext == 'mpd':
	134	formats.extend(self._extract_mpd_formats(
	135	video_url, video_id, 'dash', fatal=False))
	136	else:
	137	formats.append({
	138	'format_id': quality,
	139	'quality': q(quality),
	140	'url': video_url,
141	})
142	self._sort_formats(formats)
143	return formats
e9f65f87	144
91a6adde	145	def _real_extract(self, url):
10db0d2f	146	video_id = self._match_id(url)
91a6adde JMF	147	info = self._download_json(
	148	'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
	149	video_id)['page']['items'][0]
ce73839f JMF	150	if info['state'] == 'DESPU':
ce73839f JMF	151	raise ExtractorError('The video is no longer available', expected=True)
10db0d2f	152	title = info['title'].strip()
10db0d2f	153	formats = self._extract_png_formats(video_id)
2c53bd51	154
25ac63ed	155	subtitles = None
10db0d2f	156	sbt_file = info.get('sbtFile')
	157	if sbt_file:
	158	subtitles = self.extract_subtitles(video_id, sbt_file)
	159
	160	is_live = info.get('live') is True
25ac63ed	161
91a6adde JMF	162	return {
91a6adde JMF	163	'id': video_id,
10db0d2f	164	'title': self._live_title(title) if is_live else title,
2c53bd51	165	'formats': formats,
2b9faf55	166	'thumbnail': info.get('image'),
25ac63ed	167	'subtitles': subtitles,
10db0d2f	168	'duration': float_or_none(info.get('duration'), 1000),
	169	'is_live': is_live,
	170	'series': info.get('programTitle'),
2b9faf55 PH	171	}
2b9faf55 PH	172
25ac63ed JMF	173	def _get_subtitles(self, video_id, sub_file):
	174	subs = self._download_json(
	175	sub_file + '.json', video_id,
	176	'Downloading subtitles info')['page']['items']
9c665ab7 PH	177	return dict(
9c665ab7 PH	178	(s['lang'], [{'ext': 'vtt', 'url': s['src']}])
25ac63ed JMF	179	for s in subs)
25ac63ed JMF	180
b68eedba	181
10db0d2f	182	class RTVEInfantilIE(RTVEALaCartaIE):
b68eedba JMF	183	IE_NAME = 'rtve.es:infantil'
b68eedba JMF	184	IE_DESC = 'RTVE infantil'
10db0d2f	185	_VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/[^/]+/video/[^/]+/(?P<id>[0-9]+)/'
d5b55939 EF	186
	187	_TESTS = [{
	188	'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/',
10db0d2f	189	'md5': '5747454717aedf9f9fdf212d1bcfc48d',
d5b55939 EF	190	'info_dict': {
	191	'id': '3040283',
	192	'ext': 'mp4',
	193	'title': 'Maneras de vivir',
10db0d2f	194	'thumbnail': r're:https?://.+/1426182947956\.JPG',
d5b55939 EF	195	'duration': 357.958,
d5b55939 EF	196	},
10db0d2f	197	'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
b68eedba	198	}]
d5b55939	199
d5b55939	200
10db0d2f	201	class RTVELiveIE(RTVEALaCartaIE):
2b9faf55 PH	202	IE_NAME = 'rtve.es:live'
2b9faf55 PH	203	IE_DESC = 'RTVE.es live streams'
92519402	204	_VALID_URL = r'https?://(?:www\.)?rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)'
2b9faf55 PH	205
2b9faf55 PH	206	_TESTS = [{
3e769682	207	'url': 'http://www.rtve.es/directo/la-1/',
2b9faf55	208	'info_dict': {
3e769682 JMF	209	'id': 'la-1',
3e769682 JMF	210	'ext': 'mp4',
10db0d2f	211	'title': 're:^La 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
2b9faf55 PH	212	},
	213	'params': {
	214	'skip_download': 'live stream',
	215	}
	216	}]
	217
	218	def _real_extract(self, url):
	219	mobj = re.match(self._VALID_URL, url)
2b9faf55 PH	220	video_id = mobj.group('id')
	221
	222	webpage = self._download_webpage(url, video_id)
3e769682 JMF	223	title = remove_end(self._og_search_title(webpage), ' en directo en RTVE.es')
3e769682 JMF	224	title = remove_start(title, 'Estoy viendo ')
2b9faf55 PH	225
2b9faf55 PH	226	vidplayer_id = self._search_regex(
b63005f5 S	227	(r'playerId=player([0-9]+)',
	228	r'class=["\'].?\blive_mod\b.?["\'][^>]+data-assetid=["\'](\d+)',
	229	r'data-id=["\'](\d+)'),
	230	webpage, 'internal video ID')
2b9faf55	231
2b9faf55 PH	232	return {
2b9faf55 PH	233	'id': video_id,
10db0d2f	234	'title': self._live_title(title),
10db0d2f	235	'formats': self._extract_png_formats(vidplayer_id),
3e769682	236	'is_live': True,
91a6adde	237	}
233b58de JMF	238
	239
	240	class RTVETelevisionIE(InfoExtractor):
	241	IE_NAME = 'rtve.es:television'
92519402	242	_VALID_URL = r'https?://(?:www\.)?rtve\.es/television/[^/]+/[^/]+/(?P<id>\d+).shtml'
233b58de JMF	243
	244	_TEST = {
	245	'url': 'http://www.rtve.es/television/20160628/revolucion-del-movil/1364141.shtml',
	246	'info_dict': {
	247	'id': '3069778',
	248	'ext': 'mp4',
	249	'title': 'Documentos TV - La revolución del móvil',
	250	'duration': 3496.948,
	251	},
	252	'params': {
	253	'skip_download': True,
	254	},
	255	}
	256
	257	def _real_extract(self, url):
	258	page_id = self._match_id(url)
	259	webpage = self._download_webpage(url, page_id)
	260
	261	alacarta_url = self._search_regex(
	262	r'data-location="alacarta_videos"[^<]+url":"(http://www\.rtve\.es/alacarta.+?)&',
	263	webpage, 'alacarta url', default=None)
	264	if alacarta_url is None:
	265	raise ExtractorError(
	266	'The webpage doesn\'t contain any video', expected=True)
	267
	268	return self.url_result(alacarta_url, ie=RTVEALaCartaIE.ie_key())