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

# coding: utf-8
from __future__ import unicode_literals

import base64
import re
import time

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


def _decrypt_url(png):
    encrypted_data = base64.b64decode(png.encode('utf-8'))
    text_index = encrypted_data.find(b'tEXt')
    text_chunk = encrypted_data[text_index - 4:]
    length = compat_struct_unpack('!I', text_chunk[:4])[0]
    # Use bytearray to get integers when iterating in both python 2.x and 3.x
    data = bytearray(text_chunk[8:8 + length])
    data = [chr(b) for b in data if b != 0]
    hash_index = data.index('#')
    alphabet_data = data[:hash_index]
    url_data = data[hash_index + 1:]
    if url_data[0] == 'H' and url_data[3] == '%':
        # remove useless HQ%% at the start
        url_data = url_data[4:]

    alphabet = []
    e = 0
    d = 0
    for l in 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 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

    return url


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,
        },
    }, {
        'note': 'Live stream',
        'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/',
        'info_dict': {
            'id': '1694255',
            'ext': 'flv',
            'title': 'TODO',
        },
        'skip': 'The f4m manifest can\'t be used yet',
    }, {
        'url': 'http://www.rtve.es/alacarta/videos/servir-y-proteger/servir-proteger-capitulo-104/4236788/',
        'md5': 'e55e162379ad587e9640eda4f7353c0f',
        'info_dict': {
            'id': '4236788',
            'ext': 'mp4',
            'title': 'Servir y proteger - Capítulo 104 ',
            'duration': 3222.0,
        },
        'params': {
            'skip_download': True,  # requires ffmpeg
        },
    }, {
        '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')
        manager_info = self._download_json(
            'http://www.rtve.es/odin/loki/' + user_agent_b64,
            None, 'Fetching manager info')
        self._manager = manager_info['manager']

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        video_id = mobj.group('id')
        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']
        png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id)
        png_request = sanitized_Request(png_url)
        png_request.add_header('Referer', url)
        png = self._download_webpage(png_request, video_id, 'Downloading url information')
        video_url = _decrypt_url(png)
        ext = determine_ext(video_url)

        formats = []
        if not video_url.endswith('.f4m') and ext != 'm3u8':
            if '?' not in video_url:
                video_url = video_url.replace('resources/', 'auth/resources/')
            video_url = video_url.replace('.net.rtve', '.multimedia.cdn.rtve')

        if ext == 'm3u8':
            formats.extend(self._extract_m3u8_formats(
                video_url, video_id, ext='mp4', entry_protocol='m3u8_native',
                m3u8_id='hls', fatal=False))
        elif ext == 'f4m':
            formats.extend(self._extract_f4m_formats(
                video_url, video_id, f4m_id='hds', fatal=False))
        else:
            formats.append({
                'url': video_url,
            })
        self._sort_formats(formats)

        subtitles = None
        if info.get('sbtFile') is not None:
            subtitles = self.extract_subtitles(video_id, info['sbtFile'])

        return {
            'id': video_id,
            'title': title,
            'formats': formats,
            'thumbnail': info.get('image'),
            'page_url': url,
            'subtitles': subtitles,
            'duration': float_or_none(info.get('duration'), scale=1000),
        }

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

    _TESTS = [{
        'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/',
        'md5': '915319587b33720b8e0357caaa6617e6',
        'info_dict': {
            'id': '3040283',
            'ext': 'mp4',
            'title': 'Maneras de vivir',
            'thumbnail': 'http://www.rtve.es/resources/jpg/6/5/1426182947956.JPG',
            'duration': 357.958,
        },
    }]

    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]

        webpage = self._download_webpage(url, video_id)
        vidplayer_id = self._search_regex(
            r' id="vidplayer([0-9]+)"', webpage, 'internal video ID')

        png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % vidplayer_id
        png = self._download_webpage(png_url, video_id, 'Downloading url information')
        video_url = _decrypt_url(png)

        return {
            'id': video_id,
            'ext': 'mp4',
            'title': info['title'],
            'url': video_url,
            'thumbnail': info.get('image'),
            'duration': float_or_none(info.get('duration'), scale=1000),
        }


class RTVELiveIE(InfoExtractor):
    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}Z[0-9]{6}$',
        },
        'params': {
            'skip_download': 'live stream',
        }
    }]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        start_time = time.gmtime()
        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 ')
        title += ' ' + time.strftime('%Y-%m-%dZ%H%M%S', start_time)

        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')
        png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/amonet/videos/%s.png' % vidplayer_id
        png = self._download_webpage(png_url, video_id, 'Downloading url information')
        m3u8_url = _decrypt_url(png)
        formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
        self._sort_formats(formats)

        return {
            'id': video_id,
            'title': title,
            'formats': formats,
            '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
2b9faf55 PH	5	import re
2b9faf55 PH	6	import time
91a6adde JMF	7
91a6adde JMF	8	from .common import InfoExtractor
dab0daee	9	from ..compat import (
edaa23f8	10	compat_struct_unpack,
dab0daee	11	)
91a6adde	12	from ..utils import (
2c53bd51	13	determine_ext,
ce73839f	14	ExtractorError,
f3bff94c	15	float_or_none,
2b9faf55	16	remove_end,
3e769682	17	remove_start,
5c2266df	18	sanitized_Request,
e9f65f87	19	std_headers,
91a6adde JMF	20	)
	21
	22
2b9faf55	23	def _decrypt_url(png):
afe8b594	24	encrypted_data = base64.b64decode(png.encode('utf-8'))
2b9faf55 PH	25	text_index = encrypted_data.find(b'tEXt')
2b9faf55 PH	26	text_chunk = encrypted_data[text_index - 4:]
edaa23f8	27	length = compat_struct_unpack('!I', text_chunk[:4])[0]
2b9faf55 PH	28	# Use bytearray to get integers when iterating in both python 2.x and 3.x
	29	data = bytearray(text_chunk[8:8 + length])
	30	data = [chr(b) for b in data if b != 0]
	31	hash_index = data.index('#')
	32	alphabet_data = data[:hash_index]
	33	url_data = data[hash_index + 1:]
9650c3e9 JMF	34	if url_data[0] == 'H' and url_data[3] == '%':
	35	# remove useless HQ%% at the start
	36	url_data = url_data[4:]
2b9faf55 PH	37
	38	alphabet = []
	39	e = 0
	40	d = 0
	41	for l in alphabet_data:
	42	if d == 0:
	43	alphabet.append(l)
	44	d = e = (e + 1) % 4
	45	else:
	46	d -= 1
	47	url = ''
	48	f = 0
	49	e = 3
	50	b = 1
	51	for letter in url_data:
	52	if f == 0:
	53	l = int(letter) * 10
	54	f = 1
	55	else:
	56	if e == 0:
	57	l += int(letter)
	58	url += alphabet[l]
	59	e = (b + 3) % 4
	60	f = 0
	61	b += 1
	62	else:
	63	e -= 1
	64
	65	return url
	66
	67
91a6adde JMF	68	class RTVEALaCartaIE(InfoExtractor):
	69	IE_NAME = 'rtve.es:alacarta'
	70	IE_DESC = 'RTVE a la carta'
92519402	71	_VALID_URL = r'https?://(?:www\.)?rtve\.es/(m/)?(alacarta/videos\|filmoteca)/[^/]+/[^/]+/(?P<id>\d+)'
91a6adde	72
2b9faf55	73	_TESTS = [{
91a6adde	74	'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
9aeaf730	75	'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43',
91a6adde JMF	76	'info_dict': {
	77	'id': '2491869',
	78	'ext': 'mp4',
	79	'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia',
f3bff94c	80	'duration': 5024.566,
91a6adde	81	},
2b9faf55 PH	82	}, {
	83	'note': 'Live stream',
	84	'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/',
	85	'info_dict': {
	86	'id': '1694255',
	87	'ext': 'flv',
	88	'title': 'TODO',
cc57bd33 JMF	89	},
cc57bd33 JMF	90	'skip': 'The f4m manifest can\'t be used yet',
2c53bd51 GF	91	}, {
	92	'url': 'http://www.rtve.es/alacarta/videos/servir-y-proteger/servir-proteger-capitulo-104/4236788/',
	93	'md5': 'e55e162379ad587e9640eda4f7353c0f',
	94	'info_dict': {
	95	'id': '4236788',
	96	'ext': 'mp4',
	97	'title': 'Servir y proteger - Capítulo 104 ',
	98	'duration': 3222.0,
	99	},
	100	'params': {
	101	'skip_download': True, # requires ffmpeg
	102	},
cd596028 JMF	103	}, {
	104	'url': 'http://www.rtve.es/m/alacarta/videos/cuentame-como-paso/cuentame-como-paso-t16-ultimo-minuto-nuestra-vida-capitulo-276/2969138/?media=tve',
	105	'only_matching': True,
4c718d3c JMF	106	}, {
	107	'url': 'http://www.rtve.es/filmoteca/no-do/not-1-introduccion-primer-noticiario-espanol/1465256/',
	108	'only_matching': True,
2b9faf55	109	}]
91a6adde	110
e9f65f87 JMF	111	def _real_initialize(self):
	112	user_agent_b64 = base64.b64encode(std_headers['User-Agent'].encode('utf-8')).decode('utf-8')
	113	manager_info = self._download_json(
	114	'http://www.rtve.es/odin/loki/' + user_agent_b64,
	115	None, 'Fetching manager info')
	116	self._manager = manager_info['manager']
	117
91a6adde JMF	118	def _real_extract(self, url):
	119	mobj = re.match(self._VALID_URL, url)
	120	video_id = mobj.group('id')
	121	info = self._download_json(
	122	'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
	123	video_id)['page']['items'][0]
ce73839f JMF	124	if info['state'] == 'DESPU':
ce73839f JMF	125	raise ExtractorError('The video is no longer available', expected=True)
2c53bd51	126	title = info['title']
e9f65f87	127	png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id)
5c2266df	128	png_request = sanitized_Request(png_url)
080997b8 JMF	129	png_request.add_header('Referer', url)
080997b8 JMF	130	png = self._download_webpage(png_request, video_id, 'Downloading url information')
2b9faf55	131	video_url = _decrypt_url(png)
2c53bd51 GF	132	ext = determine_ext(video_url)
	133
	134	formats = []
	135	if not video_url.endswith('.f4m') and ext != 'm3u8':
da0baba5 JMF	136	if '?' not in video_url:
	137	video_url = video_url.replace('resources/', 'auth/resources/')
	138	video_url = video_url.replace('.net.rtve', '.multimedia.cdn.rtve')
91a6adde	139
2c53bd51 GF	140	if ext == 'm3u8':
	141	formats.extend(self._extract_m3u8_formats(
	142	video_url, video_id, ext='mp4', entry_protocol='m3u8_native',
	143	m3u8_id='hls', fatal=False))
	144	elif ext == 'f4m':
	145	formats.extend(self._extract_f4m_formats(
	146	video_url, video_id, f4m_id='hds', fatal=False))
	147	else:
	148	formats.append({
	149	'url': video_url,
	150	})
	151	self._sort_formats(formats)
	152
25ac63ed JMF	153	subtitles = None
	154	if info.get('sbtFile') is not None:
	155	subtitles = self.extract_subtitles(video_id, info['sbtFile'])
	156
91a6adde JMF	157	return {
91a6adde JMF	158	'id': video_id,
2c53bd51 GF	159	'title': title,
2c53bd51 GF	160	'formats': formats,
2b9faf55 PH	161	'thumbnail': info.get('image'),
2b9faf55 PH	162	'page_url': url,
25ac63ed	163	'subtitles': subtitles,
f3bff94c	164	'duration': float_or_none(info.get('duration'), scale=1000),
2b9faf55 PH	165	}
2b9faf55 PH	166
25ac63ed JMF	167	def _get_subtitles(self, video_id, sub_file):
	168	subs = self._download_json(
	169	sub_file + '.json', video_id,
	170	'Downloading subtitles info')['page']['items']
9c665ab7 PH	171	return dict(
9c665ab7 PH	172	(s['lang'], [{'ext': 'vtt', 'url': s['src']}])
25ac63ed JMF	173	for s in subs)
25ac63ed JMF	174
b68eedba	175
d5b55939	176	class RTVEInfantilIE(InfoExtractor):
b68eedba JMF	177	IE_NAME = 'rtve.es:infantil'
	178	IE_DESC = 'RTVE infantil'
	179	_VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/(?P<show>[^/])/video/(?P<short_title>[^/])/(?P<id>[0-9]+)/'
d5b55939 EF	180
	181	_TESTS = [{
	182	'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/',
	183	'md5': '915319587b33720b8e0357caaa6617e6',
	184	'info_dict': {
	185	'id': '3040283',
	186	'ext': 'mp4',
	187	'title': 'Maneras de vivir',
	188	'thumbnail': 'http://www.rtve.es/resources/jpg/6/5/1426182947956.JPG',
	189	'duration': 357.958,
	190	},
b68eedba	191	}]
d5b55939 EF	192
d5b55939 EF	193	def _real_extract(self, url):
b68eedba	194	video_id = self._match_id(url)
d5b55939 EF	195	info = self._download_json(
	196	'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
	197	video_id)['page']['items'][0]
	198
	199	webpage = self._download_webpage(url, video_id)
	200	vidplayer_id = self._search_regex(
	201	r' id="vidplayer([0-9]+)"', webpage, 'internal video ID')
	202
	203	png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % vidplayer_id
	204	png = self._download_webpage(png_url, video_id, 'Downloading url information')
	205	video_url = _decrypt_url(png)
	206
	207	return {
	208	'id': video_id,
	209	'ext': 'mp4',
	210	'title': info['title'],
	211	'url': video_url,
	212	'thumbnail': info.get('image'),
	213	'duration': float_or_none(info.get('duration'), scale=1000),
	214	}
	215
	216
2b9faf55 PH	217	class RTVELiveIE(InfoExtractor):
	218	IE_NAME = 'rtve.es:live'
	219	IE_DESC = 'RTVE.es live streams'
92519402	220	_VALID_URL = r'https?://(?:www\.)?rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)'
2b9faf55 PH	221
2b9faf55 PH	222	_TESTS = [{
3e769682	223	'url': 'http://www.rtve.es/directo/la-1/',
2b9faf55	224	'info_dict': {
3e769682 JMF	225	'id': 'la-1',
	226	'ext': 'mp4',
	227	'title': 're:^La 1 [0-9]{4}-[0-9]{2}-[0-9]{2}Z[0-9]{6}$',
2b9faf55 PH	228	},
	229	'params': {
	230	'skip_download': 'live stream',
	231	}
	232	}]
	233
	234	def _real_extract(self, url):
	235	mobj = re.match(self._VALID_URL, url)
	236	start_time = time.gmtime()
	237	video_id = mobj.group('id')
	238
	239	webpage = self._download_webpage(url, video_id)
3e769682 JMF	240	title = remove_end(self._og_search_title(webpage), ' en directo en RTVE.es')
3e769682 JMF	241	title = remove_start(title, 'Estoy viendo ')
2b9faf55 PH	242	title += ' ' + time.strftime('%Y-%m-%dZ%H%M%S', start_time)
	243
	244	vidplayer_id = self._search_regex(
b63005f5 S	245	(r'playerId=player([0-9]+)',
	246	r'class=["\'].?\blive_mod\b.?["\'][^>]+data-assetid=["\'](\d+)',
	247	r'data-id=["\'](\d+)'),
	248	webpage, 'internal video ID')
3e769682	249	png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/amonet/videos/%s.png' % vidplayer_id
2b9faf55	250	png = self._download_webpage(png_url, video_id, 'Downloading url information')
3e769682 JMF	251	m3u8_url = _decrypt_url(png)
3e769682 JMF	252	formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
19dbaeec	253	self._sort_formats(formats)
2b9faf55	254
2b9faf55 PH	255	return {
2b9faf55 PH	256	'id': video_id,
2b9faf55	257	'title': title,
3e769682 JMF	258	'formats': formats,
3e769682 JMF	259	'is_live': True,
91a6adde	260	}
233b58de JMF	261
	262
	263	class RTVETelevisionIE(InfoExtractor):
	264	IE_NAME = 'rtve.es:television'
92519402	265	_VALID_URL = r'https?://(?:www\.)?rtve\.es/television/[^/]+/[^/]+/(?P<id>\d+).shtml'
233b58de JMF	266
	267	_TEST = {
	268	'url': 'http://www.rtve.es/television/20160628/revolucion-del-movil/1364141.shtml',
	269	'info_dict': {
	270	'id': '3069778',
	271	'ext': 'mp4',
	272	'title': 'Documentos TV - La revolución del móvil',
	273	'duration': 3496.948,
	274	},
	275	'params': {
	276	'skip_download': True,
	277	},
	278	}
	279
	280	def _real_extract(self, url):
	281	page_id = self._match_id(url)
	282	webpage = self._download_webpage(url, page_id)
	283
	284	alacarta_url = self._search_regex(
	285	r'data-location="alacarta_videos"[^<]+url":"(http://www\.rtve\.es/alacarta.+?)&',
	286	webpage, 'alacarta url', default=None)
	287	if alacarta_url is None:
	288	raise ExtractorError(
	289	'The webpage doesn\'t contain any video', expected=True)
	290
	291	return self.url_result(alacarta_url, ie=RTVEALaCartaIE.ie_key())