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

import re
import urllib.parse

from .common import InfoExtractor
from ..utils import ExtractorError, int_or_none, urlencode_postdata


class CuriosityStreamBaseIE(InfoExtractor):
    _NETRC_MACHINE = 'curiositystream'
    _auth_token = None

    def _handle_errors(self, result):
        error = result.get('error', {}).get('message')
        if error:
            if isinstance(error, dict):
                error = ', '.join(error.values())
            raise ExtractorError(
                f'{self.IE_NAME} said: {error}', expected=True)

    def _call_api(self, path, video_id, query=None):
        headers = {}
        if not self._auth_token:
            auth_cookie = self._get_cookies('https://curiositystream.com').get('auth_token')
            if auth_cookie:
                self.write_debug('Obtained auth_token cookie')
                self._auth_token = urllib.parse.unquote(auth_cookie.value)
        if self._auth_token:
            headers['X-Auth-Token'] = self._auth_token
        result = self._download_json(
            self._API_BASE_URL + path, video_id, headers=headers, query=query)
        self._handle_errors(result)
        return result['data']

    def _perform_login(self, username, password):
        result = self._download_json(
            'https://api.curiositystream.com/v1/login', None,
            note='Logging in', data=urlencode_postdata({
                'email': username,
                'password': password,
            }))
        self._handle_errors(result)
        CuriosityStreamBaseIE._auth_token = result['message']['auth_token']


class CuriosityStreamIE(CuriosityStreamBaseIE):
    IE_NAME = 'curiositystream'
    _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/video/(?P<id>\d+)'
    _TESTS = [{
        'url': 'http://app.curiositystream.com/video/2',
        'info_dict': {
            'id': '2',
            'ext': 'mp4',
            'title': 'How Did You Develop The Internet?',
            'description': 'Vint Cerf, Google\'s Chief Internet Evangelist, describes how he and Bob Kahn created the internet.',
            'channel': 'Curiosity Stream',
            'categories': ['Technology', 'Interview'],
            'average_rating': float,
            'series_id': '2',
            'thumbnail': r're:https://img.curiositystream.com/.+\.jpg',
            'tags': [],
            'duration': 158,
        },
        'params': {
            # m3u8 download
            'skip_download': True,
        },
    }]

    _API_BASE_URL = 'https://api.curiositystream.com/v1/media/'

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

        formats = []
        for encoding_format in ('m3u8', 'mpd'):
            media = self._call_api(video_id, video_id, query={
                'encodingsNew': 'true',
                'encodingsFormat': encoding_format,
            })
            for encoding in media.get('encodings', []):
                playlist_url = encoding.get('master_playlist_url')
                if encoding_format == 'm3u8':
                    # use `m3u8` entry_protocol until EXT-X-MAP is properly supported by `m3u8_native` entry_protocol
                    formats.extend(self._extract_m3u8_formats(
                        playlist_url, video_id, 'mp4',
                        m3u8_id='hls', fatal=False))
                elif encoding_format == 'mpd':
                    formats.extend(self._extract_mpd_formats(
                        playlist_url, video_id, mpd_id='dash', fatal=False))
                encoding_url = encoding.get('url')
                file_url = encoding.get('file_url')
                if not encoding_url and not file_url:
                    continue
                f = {
                    'width': int_or_none(encoding.get('width')),
                    'height': int_or_none(encoding.get('height')),
                    'vbr': int_or_none(encoding.get('video_bitrate')),
                    'abr': int_or_none(encoding.get('audio_bitrate')),
                    'filesize': int_or_none(encoding.get('size_in_bytes')),
                    'vcodec': encoding.get('video_codec'),
                    'acodec': encoding.get('audio_codec'),
                    'container': encoding.get('container_type'),
                }
                for f_url in (encoding_url, file_url):
                    if not f_url:
                        continue
                    fmt = f.copy()
                    rtmp = re.search(r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+))/(?P<playpath>mp[34]:.+)$', f_url)
                    if rtmp:
                        fmt.update({
                            'url': rtmp.group('url'),
                            'play_path': rtmp.group('playpath'),
                            'app': rtmp.group('app'),
                            'ext': 'flv',
                            'format_id': 'rtmp',
                        })
                    else:
                        fmt.update({
                            'url': f_url,
                            'format_id': 'http',
                        })
                    formats.append(fmt)

        title = media['title']

        subtitles = {}
        for closed_caption in media.get('closed_captions', []):
            sub_url = closed_caption.get('file')
            if not sub_url:
                continue
            lang = closed_caption.get('code') or closed_caption.get('language') or 'en'
            subtitles.setdefault(lang, []).append({
                'url': sub_url,
            })

        return {
            'id': video_id,
            'formats': formats,
            'title': title,
            'description': media.get('description'),
            'thumbnail': media.get('image_large') or media.get('image_medium') or media.get('image_small'),
            'duration': int_or_none(media.get('duration')),
            'tags': media.get('tags'),
            'subtitles': subtitles,
            'channel': media.get('producer'),
            'categories': [media.get('primary_category'), media.get('type')],
            'average_rating': media.get('rating_percentage'),
            'series_id': str(media.get('collection_id') or '') or None,
        }


class CuriosityStreamCollectionBaseIE(CuriosityStreamBaseIE):

    def _real_extract(self, url):
        collection_id = self._match_id(url)
        collection = self._call_api(collection_id, collection_id)
        entries = []
        for media in collection.get('media', []):
            media_id = str(media.get('id'))
            media_type, ie = ('series', CuriosityStreamSeriesIE) if media.get('is_collection') else ('video', CuriosityStreamIE)
            entries.append(self.url_result(
                f'https://curiositystream.com/{media_type}/{media_id}',
                ie=ie.ie_key(), video_id=media_id))
        return self.playlist_result(
            entries, collection_id,
            collection.get('title'), collection.get('description'))


class CuriosityStreamCollectionsIE(CuriosityStreamCollectionBaseIE):
    IE_NAME = 'curiositystream:collections'
    _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/collections/(?P<id>\d+)'
    _API_BASE_URL = 'https://api.curiositystream.com/v2/collections/'
    _TESTS = [{
        'url': 'https://curiositystream.com/collections/86',
        'info_dict': {
            'id': '86',
            'title': 'Staff Picks',
            'description': 'Wondering where to start? Here are a few of our favorite series and films... from our couch to yours.',
        },
        'playlist_mincount': 7,
    }, {
        'url': 'https://curiositystream.com/collections/36',
        'only_matching': True,
    }]


class CuriosityStreamSeriesIE(CuriosityStreamCollectionBaseIE):
    IE_NAME = 'curiositystream:series'
    _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/(?:series|collection)/(?P<id>\d+)'
    _API_BASE_URL = 'https://api.curiositystream.com/v2/series/'
    _TESTS = [{
        'url': 'https://curiositystream.com/series/2',
        'info_dict': {
            'id': '2',
            'title': 'Curious Minds: The Internet',
            'description': 'How is the internet shaping our lives in the 21st Century?',
        },
        'playlist_mincount': 16,
    }, {
        'url': 'https://curiositystream.com/collection/2',
        'only_matching': True,
    }]
Commit	Line	Data
a206ef62	1	import re
6b71d186	2	import urllib.parse
a206ef62	3
f096ec26	4	from .common import InfoExtractor
14f25df2	5	from ..utils import ExtractorError, int_or_none, urlencode_postdata
f096ec26 RA	6
	7
	8	class CuriosityStreamBaseIE(InfoExtractor):
	9	_NETRC_MACHINE = 'curiositystream'
	10	_auth_token = None
f096ec26 RA	11
	12	def _handle_errors(self, result):
	13	error = result.get('error', {}).get('message')
	14	if error:
	15	if isinstance(error, dict):
	16	error = ', '.join(error.values())
	17	raise ExtractorError(
add96eb9	18	f'{self.IE_NAME} said: {error}', expected=True)
f096ec26	19
f7ad7160	20	def _call_api(self, path, video_id, query=None):
f096ec26	21	headers = {}
d2ff2c91	22	if not self._auth_token:
	23	auth_cookie = self._get_cookies('https://curiositystream.com').get('auth_token')
	24	if auth_cookie:
	25	self.write_debug('Obtained auth_token cookie')
6b71d186	26	self._auth_token = urllib.parse.unquote(auth_cookie.value)
f096ec26 RA	27	if self._auth_token:
	28	headers['X-Auth-Token'] = self._auth_token
	29	result = self._download_json(
f7ad7160	30	self._API_BASE_URL + path, video_id, headers=headers, query=query)
f096ec26 RA	31	self._handle_errors(result)
	32	return result['data']
	33
52efa4b3	34	def _perform_login(self, username, password):
b207d5eb	35	result = self._download_json(
d0e6121a	36	'https://api.curiositystream.com/v1/login', None,
d0e6121a	37	note='Logging in', data=urlencode_postdata({
52efa4b3	38	'email': username,
b207d5eb RA	39	'password': password,
	40	}))
	41	self._handle_errors(result)
92775d8a	42	CuriosityStreamBaseIE._auth_token = result['message']['auth_token']
f096ec26	43
3b983ee4 RA	44
	45	class CuriosityStreamIE(CuriosityStreamBaseIE):
	46	IE_NAME = 'curiositystream'
	47	_VALID_URL = r'https?://(?:app\.)?curiositystream\.com/video/(?P<id>\d+)'
9ac24e23	48	_TESTS = [{
14f25df2	49	'url': 'http://app.curiositystream.com/video/2',
3b983ee4 RA	50	'info_dict': {
	51	'id': '2',
	52	'ext': 'mp4',
	53	'title': 'How Did You Develop The Internet?',
	54	'description': 'Vint Cerf, Google\'s Chief Internet Evangelist, describes how he and Bob Kahn created the internet.',
9ac24e23	55	'channel': 'Curiosity Stream',
9ac24e23	56	'categories': ['Technology', 'Interview'],
6b71d186	57	'average_rating': float,
9ac24e23	58	'series_id': '2',
6b71d186	59	'thumbnail': r're:https://img.curiositystream.com/.+\.jpg',
6b71d186	60	'tags': [],
add96eb9	61	'duration': 158,
f7ad7160	62	},
f7ad7160	63	'params': {
f7ad7160	64	# m3u8 download
	65	'skip_download': True,
	66	},
9ac24e23	67	}]
3b983ee4	68
d0e6121a	69	_API_BASE_URL = 'https://api.curiositystream.com/v1/media/'
d0e6121a	70
3b983ee4 RA	71	def _real_extract(self, url):
3b983ee4 RA	72	video_id = self._match_id(url)
f096ec26	73
a206ef62	74	formats = []
f7ad7160	75	for encoding_format in ('m3u8', 'mpd'):
d0e6121a	76	media = self._call_api(video_id, video_id, query={
f7ad7160	77	'encodingsNew': 'true',
	78	'encodingsFormat': encoding_format,
	79	})
	80	for encoding in media.get('encodings', []):
	81	playlist_url = encoding.get('master_playlist_url')
	82	if encoding_format == 'm3u8':
	83	# use `m3u8` entry_protocol until EXT-X-MAP is properly supported by `m3u8_native` entry_protocol
	84	formats.extend(self._extract_m3u8_formats(
	85	playlist_url, video_id, 'mp4',
	86	m3u8_id='hls', fatal=False))
	87	elif encoding_format == 'mpd':
	88	formats.extend(self._extract_mpd_formats(
	89	playlist_url, video_id, mpd_id='dash', fatal=False))
	90	encoding_url = encoding.get('url')
	91	file_url = encoding.get('file_url')
	92	if not encoding_url and not file_url:
a206ef62	93	continue
f7ad7160	94	f = {
	95	'width': int_or_none(encoding.get('width')),
	96	'height': int_or_none(encoding.get('height')),
	97	'vbr': int_or_none(encoding.get('video_bitrate')),
	98	'abr': int_or_none(encoding.get('audio_bitrate')),
	99	'filesize': int_or_none(encoding.get('size_in_bytes')),
	100	'vcodec': encoding.get('video_codec'),
	101	'acodec': encoding.get('audio_codec'),
	102	'container': encoding.get('container_type'),
	103	}
	104	for f_url in (encoding_url, file_url):
	105	if not f_url:
	106	continue
	107	fmt = f.copy()
	108	rtmp = re.search(r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+))/(?P<playpath>mp[34]:.+)$', f_url)
	109	if rtmp:
	110	fmt.update({
	111	'url': rtmp.group('url'),
	112	'play_path': rtmp.group('playpath'),
	113	'app': rtmp.group('app'),
	114	'ext': 'flv',
	115	'format_id': 'rtmp',
	116	})
	117	else:
	118	fmt.update({
	119	'url': f_url,
	120	'format_id': 'http',
	121	})
	122	formats.append(fmt)
a206ef62	123
f7ad7160	124	title = media['title']
f7ad7160	125
f096ec26 RA	126	subtitles = {}
	127	for closed_caption in media.get('closed_captions', []):
	128	sub_url = closed_caption.get('file')
	129	if not sub_url:
	130	continue
	131	lang = closed_caption.get('code') or closed_caption.get('language') or 'en'
	132	subtitles.setdefault(lang, []).append({
	133	'url': sub_url,
	134	})
	135
	136	return {
f096ec26	137	'id': video_id,
a206ef62	138	'formats': formats,
f096ec26 RA	139	'title': title,
	140	'description': media.get('description'),
	141	'thumbnail': media.get('image_large') or media.get('image_medium') or media.get('image_small'),
	142	'duration': int_or_none(media.get('duration')),
	143	'tags': media.get('tags'),
	144	'subtitles': subtitles,
9ac24e23	145	'channel': media.get('producer'),
	146	'categories': [media.get('primary_category'), media.get('type')],
	147	'average_rating': media.get('rating_percentage'),
	148	'series_id': str(media.get('collection_id') or '') or None,
f096ec26 RA	149	}
	150
	151
92775d8a	152	class CuriosityStreamCollectionBaseIE(CuriosityStreamBaseIE):
	153
	154	def _real_extract(self, url):
	155	collection_id = self._match_id(url)
	156	collection = self._call_api(collection_id, collection_id)
	157	entries = []
	158	for media in collection.get('media', []):
add96eb9	159	media_id = str(media.get('id'))
92775d8a	160	media_type, ie = ('series', CuriosityStreamSeriesIE) if media.get('is_collection') else ('video', CuriosityStreamIE)
92775d8a	161	entries.append(self.url_result(
add96eb9	162	f'https://curiositystream.com/{media_type}/{media_id}',
92775d8a	163	ie=ie.ie_key(), video_id=media_id))
	164	return self.playlist_result(
	165	entries, collection_id,
	166	collection.get('title'), collection.get('description'))
	167
	168
	169	class CuriosityStreamCollectionsIE(CuriosityStreamCollectionBaseIE):
	170	IE_NAME = 'curiositystream:collections'
	171	_VALID_URL = r'https?://(?:app\.)?curiositystream\.com/collections/(?P<id>\d+)'
ef39f860	172	_API_BASE_URL = 'https://api.curiositystream.com/v2/collections/'
3b983ee4	173	_TESTS = [{
ef39f860	174	'url': 'https://curiositystream.com/collections/86',
f096ec26	175	'info_dict': {
ef39f860	176	'id': '86',
	177	'title': 'Staff Picks',
	178	'description': 'Wondering where to start? Here are a few of our favorite series and films... from our couch to yours.',
f096ec26	179	},
ef39f860	180	'playlist_mincount': 7,
ed807c18	181	}, {
92775d8a	182	'url': 'https://curiositystream.com/collections/36',
	183	'only_matching': True,
	184	}]
	185
	186
	187	class CuriosityStreamSeriesIE(CuriosityStreamCollectionBaseIE):
	188	IE_NAME = 'curiositystream:series'
	189	_VALID_URL = r'https?://(?:app\.)?curiositystream\.com/(?:series\|collection)/(?P<id>\d+)'
	190	_API_BASE_URL = 'https://api.curiositystream.com/v2/series/'
	191	_TESTS = [{
	192	'url': 'https://curiositystream.com/series/2',
ed807c18	193	'info_dict': {
	194	'id': '2',
	195	'title': 'Curious Minds: The Internet',
	196	'description': 'How is the internet shaping our lives in the 21st Century?',
	197	},
	198	'playlist_mincount': 16,
	199	}, {
92775d8a	200	'url': 'https://curiositystream.com/collection/2',
ed807c18	201	'only_matching': True,
3b983ee4	202	}]