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

import re

from .common import InfoExtractor
from ..utils import (
    ExtractorError,
    determine_ext,
    int_or_none,
    parse_iso8601,
    traverse_obj,
    variadic,
)


class OpencastBaseIE(InfoExtractor):
    _INSTANCES_RE = r'''(?:
                            opencast\.informatik\.kit\.edu|
                            electures\.uni-muenster\.de|
                            oc-presentation\.ltcc\.tuwien\.ac\.at|
                            medien\.ph-noe\.ac\.at|
                            oc-video\.ruhr-uni-bochum\.de|
                            oc-video1\.ruhr-uni-bochum\.de|
                            opencast\.informatik\.uni-goettingen\.de|
                            heicast\.uni-heidelberg\.de|
                            opencast\.hawk\.de:8080|
                            opencast\.hs-osnabrueck\.de|
                            video[0-9]+\.virtuos\.uni-osnabrueck\.de|
                            opencast\.uni-koeln\.de|
                            media\.opencast\.hochschule-rhein-waal\.de|
                            matterhorn\.dce\.harvard\.edu|
                            hs-harz\.opencast\.uni-halle\.de|
                            videocampus\.urz\.uni-leipzig\.de|
                            media\.uct\.ac\.za|
                            vid\.igb\.illinois\.edu|
                            cursosabertos\.c3sl\.ufpr\.br|
                            mcmedia\.missioncollege\.org|
                            clases\.odon\.edu\.uy
                        )'''
    _UUID_RE = r'[\da-fA-F]{8}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{12}'

    def _call_api(self, host, video_id, **kwargs):
        return self._download_json(self._API_BASE % (host, video_id), video_id, **kwargs)

    def _parse_mediapackage(self, video):
        video_id = video.get('id')
        if video_id is None:
            raise ExtractorError('Video id was not found')

        formats = []
        for track in variadic(traverse_obj(video, ('media', 'track')) or []):
            href = track.get('url')
            if href is None:
                continue
            ext = determine_ext(href, None)

            transport = track.get('transport')

            if transport == 'DASH' or ext == 'mpd':
                formats.extend(self._extract_mpd_formats(href, video_id, mpd_id='dash', fatal=False))
            elif transport == 'HLS' or ext == 'm3u8':
                formats.extend(self._extract_m3u8_formats(
                    href, video_id, m3u8_id='hls', entry_protocol='m3u8_native', fatal=False))
            elif transport == 'HDS' or ext == 'f4m':
                formats.extend(self._extract_f4m_formats(href, video_id, f4m_id='hds', fatal=False))
            elif transport == 'SMOOTH':
                formats.extend(self._extract_ism_formats(href, video_id, ism_id='smooth', fatal=False))
            elif ext == 'smil':
                formats.extend(self._extract_smil_formats(href, video_id, fatal=False))
            else:
                track_obj = {
                    'url': href,
                    'ext': ext,
                    'format_note': track.get('transport'),
                    'resolution': traverse_obj(track, ('video', 'resolution')),
                    'fps': int_or_none(traverse_obj(track, ('video', 'framerate'))),
                    'vbr': int_or_none(traverse_obj(track, ('video', 'bitrate')), scale=1000),
                    'vcodec': traverse_obj(track, ('video', 'encoder', 'type')) if track.get('video') else 'none',
                    'abr': int_or_none(traverse_obj(track, ('audio', 'bitrate')), scale=1000),
                    'asr': int_or_none(traverse_obj(track, ('audio', 'samplingrate'))),
                    'acodec': traverse_obj(track, ('audio', 'encoder', 'type')) if track.get('audio') else 'none',
                }

                if transport == 'RTMP':
                    m_obj = re.search(r'(?:rtmp://[^/]+/(?P<app>[^/]+))/(?P<ext>.+):(?P<playpath>.+)', href)
                    if not m_obj:
                        continue
                    track_obj.update({
                        'app': m_obj.group('app'),
                        'ext': m_obj.group('ext'),
                        'play_path': m_obj.group('ext') + ':' + m_obj.group('playpath'),
                        'rtmp_live': True,
                        'preference': -2,
                    })
                formats.append(track_obj)

        return {
            'id': video_id,
            'formats': formats,
            'title': video.get('title'),
            'series': video.get('seriestitle'),
            'season_id': video.get('series'),
            'creator': traverse_obj(video, ('creators', 'creator')),
            'timestamp': parse_iso8601(video.get('start')),
            'thumbnail': traverse_obj(video, ('attachments', 'attachment', ..., 'url'), get_all=False),
        }


class OpencastIE(OpencastBaseIE):
    _VALID_URL = rf'''(?x)
        https?://(?P<host>{OpencastBaseIE._INSTANCES_RE})/paella/ui/watch\.html\?
        (?:[^#]+&)?id=(?P<id>{OpencastBaseIE._UUID_RE})'''

    _API_BASE = 'https://%s/search/episode.json?id=%s'

    _TESTS = [
        {
            'url': 'https://oc-video1.ruhr-uni-bochum.de/paella/ui/watch.html?id=ed063cd5-72c8-46b5-a60a-569243edcea8',
            'md5': '554c8e99a90f7be7e874619fcf2a3bc9',
            'info_dict': {
                'id': 'ed063cd5-72c8-46b5-a60a-569243edcea8',
                'ext': 'mp4',
                'title': '11 - Kryptographie - 24.11.2015',
                'thumbnail': r're:^https?://.*\.jpg$',
                'timestamp': 1606208400,
                'upload_date': '20201124',
                'season_id': 'cf68a4a1-36b1-4a53-a6ba-61af5705a0d0',
                'series': 'Kryptographie - WiSe 15/16',
                'creator': 'Alexander May',
            },
        }
    ]

    def _real_extract(self, url):
        host, video_id = self._match_valid_url(url).group('host', 'id')
        return self._parse_mediapackage(
            self._call_api(host, video_id)['search-results']['result']['mediapackage'])


class OpencastPlaylistIE(OpencastBaseIE):
    _VALID_URL = rf'''(?x)
        https?://(?P<host>{OpencastBaseIE._INSTANCES_RE})(?:
            /engage/ui/index\.html\?(?:[^#]+&)?epFrom=|
            /ltitools/index\.html\?(?:[^#]+&)?series=
        )(?P<id>{OpencastBaseIE._UUID_RE})'''

    _API_BASE = 'https://%s/search/episode.json?sid=%s'

    _TESTS = [
        {
            'url': 'https://oc-video1.ruhr-uni-bochum.de/engage/ui/index.html?epFrom=cf68a4a1-36b1-4a53-a6ba-61af5705a0d0',
            'info_dict': {
                'id': 'cf68a4a1-36b1-4a53-a6ba-61af5705a0d0',
                'title': 'Kryptographie - WiSe 15/16',
            },
            'playlist_mincount': 29,
        },
        {
            'url': 'https://oc-video1.ruhr-uni-bochum.de/ltitools/index.html?subtool=series&series=cf68a4a1-36b1-4a53-a6ba-61af5705a0d0&lng=de',
            'info_dict': {
                'id': 'cf68a4a1-36b1-4a53-a6ba-61af5705a0d0',
                'title': 'Kryptographie - WiSe 15/16',
            },
            'playlist_mincount': 29,
        },
        {
            'url': 'https://electures.uni-muenster.de/engage/ui/index.html?e=1&p=1&epFrom=39391d10-a711-4d23-b21d-afd2ed7d758c',
            'info_dict': {
                'id': '39391d10-a711-4d23-b21d-afd2ed7d758c',
                'title': '021670 Theologische Themen bei Hans Blumenberg WiSe 2017/18',
            },
            'playlist_mincount': 13,
        },
    ]

    def _real_extract(self, url):
        host, video_id = self._match_valid_url(url).group('host', 'id')

        entries = [
            self._parse_mediapackage(episode['mediapackage'])
            for episode in variadic(self._call_api(host, video_id)['search-results']['result'])
            if episode.get('mediapackage')
        ]

        return self.playlist_result(entries, video_id, traverse_obj(entries, (0, 'series')))
Commit	Line	Data
4b4b7f74 BW	1	import re
	2
	3	from .common import InfoExtractor
	4	from ..utils import (
4b4b7f74	5	ExtractorError,
e897bd82	6	determine_ext,
4b4b7f74 BW	7	int_or_none,
	8	parse_iso8601,
	9	traverse_obj,
	10	variadic,
	11	)
	12
	13
	14	class OpencastBaseIE(InfoExtractor):
	15	_INSTANCES_RE = r'''(?:
	16	opencast\.informatik\.kit\.edu\|
	17	electures\.uni-muenster\.de\|
	18	oc-presentation\.ltcc\.tuwien\.ac\.at\|
	19	medien\.ph-noe\.ac\.at\|
	20	oc-video\.ruhr-uni-bochum\.de\|
	21	oc-video1\.ruhr-uni-bochum\.de\|
	22	opencast\.informatik\.uni-goettingen\.de\|
	23	heicast\.uni-heidelberg\.de\|
	24	opencast\.hawk\.de:8080\|
	25	opencast\.hs-osnabrueck\.de\|
	26	video[0-9]+\.virtuos\.uni-osnabrueck\.de\|
	27	opencast\.uni-koeln\.de\|
	28	media\.opencast\.hochschule-rhein-waal\.de\|
	29	matterhorn\.dce\.harvard\.edu\|
	30	hs-harz\.opencast\.uni-halle\.de\|
	31	videocampus\.urz\.uni-leipzig\.de\|
	32	media\.uct\.ac\.za\|
	33	vid\.igb\.illinois\.edu\|
	34	cursosabertos\.c3sl\.ufpr\.br\|
	35	mcmedia\.missioncollege\.org\|
	36	clases\.odon\.edu\.uy
	37	)'''
	38	_UUID_RE = r'[\da-fA-F]{8}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{12}'
	39
	40	def _call_api(self, host, video_id, **kwargs):
	41	return self._download_json(self._API_BASE % (host, video_id), video_id, **kwargs)
	42
	43	def _parse_mediapackage(self, video):
	44	video_id = video.get('id')
	45	if video_id is None:
	46	raise ExtractorError('Video id was not found')
	47
	48	formats = []
	49	for track in variadic(traverse_obj(video, ('media', 'track')) or []):
	50	href = track.get('url')
	51	if href is None:
	52	continue
	53	ext = determine_ext(href, None)
	54
	55	transport = track.get('transport')
	56
	57	if transport == 'DASH' or ext == 'mpd':
89dbf084	58	formats.extend(self._extract_mpd_formats(href, video_id, mpd_id='dash', fatal=False))
4b4b7f74	59	elif transport == 'HLS' or ext == 'm3u8':
89dbf084	60	formats.extend(self._extract_m3u8_formats(
4b4b7f74 BW	61	href, video_id, m3u8_id='hls', entry_protocol='m3u8_native', fatal=False))
	62	elif transport == 'HDS' or ext == 'f4m':
	63	formats.extend(self._extract_f4m_formats(href, video_id, f4m_id='hds', fatal=False))
	64	elif transport == 'SMOOTH':
	65	formats.extend(self._extract_ism_formats(href, video_id, ism_id='smooth', fatal=False))
	66	elif ext == 'smil':
	67	formats.extend(self._extract_smil_formats(href, video_id, fatal=False))
	68	else:
	69	track_obj = {
	70	'url': href,
	71	'ext': ext,
	72	'format_note': track.get('transport'),
	73	'resolution': traverse_obj(track, ('video', 'resolution')),
	74	'fps': int_or_none(traverse_obj(track, ('video', 'framerate'))),
	75	'vbr': int_or_none(traverse_obj(track, ('video', 'bitrate')), scale=1000),
	76	'vcodec': traverse_obj(track, ('video', 'encoder', 'type')) if track.get('video') else 'none',
	77	'abr': int_or_none(traverse_obj(track, ('audio', 'bitrate')), scale=1000),
	78	'asr': int_or_none(traverse_obj(track, ('audio', 'samplingrate'))),
	79	'acodec': traverse_obj(track, ('audio', 'encoder', 'type')) if track.get('audio') else 'none',
	80	}
	81
	82	if transport == 'RTMP':
	83	m_obj = re.search(r'(?:rtmp://[^/]+/(?P<app>[^/]+))/(?P<ext>.+):(?P<playpath>.+)', href)
	84	if not m_obj:
	85	continue
	86	track_obj.update({
	87	'app': m_obj.group('app'),
	88	'ext': m_obj.group('ext'),
	89	'play_path': m_obj.group('ext') + ':' + m_obj.group('playpath'),
	90	'rtmp_live': True,
	91	'preference': -2,
	92	})
	93	formats.append(track_obj)
	94
4b4b7f74 BW	95	return {
	96	'id': video_id,
	97	'formats': formats,
	98	'title': video.get('title'),
	99	'series': video.get('seriestitle'),
	100	'season_id': video.get('series'),
	101	'creator': traverse_obj(video, ('creators', 'creator')),
	102	'timestamp': parse_iso8601(video.get('start')),
	103	'thumbnail': traverse_obj(video, ('attachments', 'attachment', ..., 'url'), get_all=False),
	104	}
	105
	106
	107	class OpencastIE(OpencastBaseIE):
3588be59 DV	108	_VALID_URL = rf'''(?x)
	109	https?://(?P<host>{OpencastBaseIE._INSTANCES_RE})/paella/ui/watch\.html\?
	110	(?:[^#]+&)?id=(?P<id>{OpencastBaseIE._UUID_RE})'''
4b4b7f74 BW	111
	112	_API_BASE = 'https://%s/search/episode.json?id=%s'
	113
	114	_TESTS = [
	115	{
	116	'url': 'https://oc-video1.ruhr-uni-bochum.de/paella/ui/watch.html?id=ed063cd5-72c8-46b5-a60a-569243edcea8',
	117	'md5': '554c8e99a90f7be7e874619fcf2a3bc9',
	118	'info_dict': {
	119	'id': 'ed063cd5-72c8-46b5-a60a-569243edcea8',
	120	'ext': 'mp4',
	121	'title': '11 - Kryptographie - 24.11.2015',
	122	'thumbnail': r're:^https?://.*\.jpg$',
	123	'timestamp': 1606208400,
	124	'upload_date': '20201124',
3588be59 DV	125	'season_id': 'cf68a4a1-36b1-4a53-a6ba-61af5705a0d0',
	126	'series': 'Kryptographie - WiSe 15/16',
	127	'creator': 'Alexander May',
4b4b7f74 BW	128	},
	129	}
	130	]
	131
	132	def _real_extract(self, url):
	133	host, video_id = self._match_valid_url(url).group('host', 'id')
	134	return self._parse_mediapackage(
	135	self._call_api(host, video_id)['search-results']['result']['mediapackage'])
	136
	137
	138	class OpencastPlaylistIE(OpencastBaseIE):
3588be59 DV	139	_VALID_URL = rf'''(?x)
	140	https?://(?P<host>{OpencastBaseIE._INSTANCES_RE})(?:
	141	/engage/ui/index\.html\?(?:[^#]+&)?epFrom=\|
	142	/ltitools/index\.html\?(?:[^#]+&)?series=
	143	)(?P<id>{OpencastBaseIE._UUID_RE})'''
4b4b7f74 BW	144
	145	_API_BASE = 'https://%s/search/episode.json?sid=%s'
	146
	147	_TESTS = [
	148	{
	149	'url': 'https://oc-video1.ruhr-uni-bochum.de/engage/ui/index.html?epFrom=cf68a4a1-36b1-4a53-a6ba-61af5705a0d0',
	150	'info_dict': {
	151	'id': 'cf68a4a1-36b1-4a53-a6ba-61af5705a0d0',
	152	'title': 'Kryptographie - WiSe 15/16',
	153	},
3588be59	154	'playlist_mincount': 29,
4b4b7f74 BW	155	},
4b4b7f74 BW	156	{
3588be59	157	'url': 'https://oc-video1.ruhr-uni-bochum.de/ltitools/index.html?subtool=series&series=cf68a4a1-36b1-4a53-a6ba-61af5705a0d0&lng=de',
4b4b7f74	158	'info_dict': {
3588be59 DV	159	'id': 'cf68a4a1-36b1-4a53-a6ba-61af5705a0d0',
	160	'title': 'Kryptographie - WiSe 15/16',
	161	},
	162	'playlist_mincount': 29,
	163	},
	164	{
	165	'url': 'https://electures.uni-muenster.de/engage/ui/index.html?e=1&p=1&epFrom=39391d10-a711-4d23-b21d-afd2ed7d758c',
	166	'info_dict': {
	167	'id': '39391d10-a711-4d23-b21d-afd2ed7d758c',
	168	'title': '021670 Theologische Themen bei Hans Blumenberg WiSe 2017/18',
4b4b7f74	169	},
3588be59	170	'playlist_mincount': 13,
4b4b7f74 BW	171	},
	172	]
	173
	174	def _real_extract(self, url):
	175	host, video_id = self._match_valid_url(url).group('host', 'id')
	176
	177	entries = [
	178	self._parse_mediapackage(episode['mediapackage'])
	179	for episode in variadic(self._call_api(host, video_id)['search-results']['result'])
	180	if episode.get('mediapackage')
	181	]
	182
	183	return self.playlist_result(entries, video_id, traverse_obj(entries, (0, 'series')))