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

# encoding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
    determine_ext,
    ExtractorError,
    float_or_none,
    parse_duration,
    unified_strdate,
)


class NRKIE(InfoExtractor):
    _VALID_URL = r'(?:nrk:|https?://(?:www\.)?nrk\.no/video/PS\*)(?P<id>\d+)'

    _TESTS = [
        {
            'url': 'http://www.nrk.no/video/PS*150533',
            'md5': 'bccd850baebefe23b56d708a113229c2',
            'info_dict': {
                'id': '150533',
                'ext': 'flv',
                'title': 'Dompap og andre fugler i Piip-Show',
                'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',
                'duration': 263,
            }
        },
        {
            'url': 'http://www.nrk.no/video/PS*154915',
            'md5': '0b1493ba1aae7d9579a5ad5531bc395a',
            'info_dict': {
                'id': '154915',
                'ext': 'flv',
                'title': 'Slik høres internett ut når du er blind',
                'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
                'duration': 20,
            }
        },
    ]

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

        data = self._download_json(
            'http://v8.psapi.nrk.no/mediaelement/%s' % video_id,
            video_id, 'Downloading media JSON')

        media_url = data.get('mediaUrl')

        if not media_url:
            if data['usageRights']['isGeoBlocked']:
                raise ExtractorError(
                    'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
                    expected=True)

        if determine_ext(media_url) == 'f4m':
            formats = self._extract_f4m_formats(
                media_url + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81', video_id, f4m_id='hds')
        else:
            formats = [{
                'url': media_url,
                'ext': 'flv',
            }]

        duration = parse_duration(data.get('duration'))

        images = data.get('images')
        if images:
            thumbnails = images['webImages']
            thumbnails.sort(key=lambda image: image['pixelWidth'])
            thumbnail = thumbnails[-1]['imageUrl']
        else:
            thumbnail = None

        return {
            'id': video_id,
            'title': data['title'],
            'description': data['description'],
            'duration': duration,
            'thumbnail': thumbnail,
            'formats': formats,
        }


class NRKPlaylistIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video)(?:[^/]+/)+(?P<id>[^/]+)'

    _TESTS = [{
        'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
        'info_dict': {
            'id': 'gjenopplev-den-historiske-solformorkelsen-1.12270763',
            'title': 'Gjenopplev den historiske solformørkelsen',
            'description': 'md5:c2df8ea3bac5654a26fc2834a542feed',
        },
        'playlist_count': 2,
    }, {
        'url': 'http://www.nrk.no/kultur/bok/rivertonprisen-til-karin-fossum-1.12266449',
        'info_dict': {
            'id': 'rivertonprisen-til-karin-fossum-1.12266449',
            'title': 'Rivertonprisen til Karin Fossum',
            'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.',
        },
        'playlist_count': 5,
    }]

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

        webpage = self._download_webpage(url, playlist_id)

        entries = [
            self.url_result('nrk:%s' % video_id, 'NRK')
            for video_id in re.findall(
                r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"',
                webpage)
        ]

        playlist_title = self._og_search_title(webpage)
        playlist_description = self._og_search_description(webpage)

        return self.playlist_result(
            entries, playlist_id, playlist_title, playlist_description)


class NRKTVIE(InfoExtractor):
    IE_DESC = 'NRK TV and NRK Radio'
    _VALID_URL = r'(?P<baseurl>https?://(?:tv|radio)\.nrk(?:super)?\.no/)(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?'

    _TESTS = [
        {
            'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
            'md5': 'adf2c5454fa2bf032f47a9f8fb351342',
            'info_dict': {
                'id': 'MUHH48000314',
                'ext': 'flv',
                'title': '20 spørsmål',
                'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
                'upload_date': '20140523',
                'duration': 1741.52,
            },
        },
        {
            'url': 'https://tv.nrk.no/program/mdfp15000514',
            'md5': '383650ece2b25ecec996ad7b5bb2a384',
            'info_dict': {
                'id': 'mdfp15000514',
                'ext': 'flv',
                'title': 'Kunnskapskanalen: Grunnlovsjubiléet - Stor ståhei for ingenting',
                'description': 'md5:654c12511f035aed1e42bdf5db3b206a',
                'upload_date': '20140524',
                'duration': 4605.0,
            },
        },
        {
            # single playlist video
            'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
            'md5': 'adbd1dbd813edaf532b0a253780719c2',
            'info_dict': {
                'id': 'MSPO40010515-part2',
                'ext': 'flv',
                'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
                'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
                'upload_date': '20150106',
            },
            'skip': 'Only works from Norway',
        },
        {
            'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
            'playlist': [
                {
                    'md5': '9480285eff92d64f06e02a5367970a7a',
                    'info_dict': {
                        'id': 'MSPO40010515-part1',
                        'ext': 'flv',
                        'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 1:2)',
                        'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
                        'upload_date': '20150106',
                    },
                },
                {
                    'md5': 'adbd1dbd813edaf532b0a253780719c2',
                    'info_dict': {
                        'id': 'MSPO40010515-part2',
                        'ext': 'flv',
                        'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
                        'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
                        'upload_date': '20150106',
                    },
                },
            ],
            'info_dict': {
                'id': 'MSPO40010515',
                'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn',
                'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
                'upload_date': '20150106',
                'duration': 6947.5199999999995,
            },
            'skip': 'Only works from Norway',
        },
        {
            'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#',
            'only_matching': True,
        }
    ]

    def _extract_f4m(self, manifest_url, video_id):
        return self._extract_f4m_formats(
            manifest_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', video_id, f4m_id='hds')

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

        webpage = self._download_webpage(url, video_id)

        title = self._html_search_meta(
            'title', webpage, 'title')
        description = self._html_search_meta(
            'description', webpage, 'description')

        thumbnail = self._html_search_regex(
            r'data-posterimage="([^"]+)"',
            webpage, 'thumbnail', fatal=False)
        upload_date = unified_strdate(self._html_search_meta(
            'rightsfrom', webpage, 'upload date', fatal=False))
        duration = float_or_none(self._html_search_regex(
            r'data-duration="([^"]+)"',
            webpage, 'duration', fatal=False))

        # playlist
        parts = re.findall(
            r'<a href="#del=(\d+)"[^>]+data-argument="([^"]+)">([^<]+)</a>', webpage)
        if parts:
            entries = []
            for current_part_id, stream_url, part_title in parts:
                if part_id and current_part_id != part_id:
                    continue
                video_part_id = '%s-part%s' % (video_id, current_part_id)
                formats = self._extract_f4m(stream_url, video_part_id)
                entries.append({
                    'id': video_part_id,
                    'title': part_title,
                    'description': description,
                    'thumbnail': thumbnail,
                    'upload_date': upload_date,
                    'formats': formats,
                })
            if part_id:
                if entries:
                    return entries[0]
            else:
                playlist = self.playlist_result(entries, video_id, title, description)
                playlist.update({
                    'thumbnail': thumbnail,
                    'upload_date': upload_date,
                    'duration': duration,
                })
                return playlist

        formats = []

        f4m_url = re.search(r'data-media="([^"]+)"', webpage)
        if f4m_url:
            formats.extend(self._extract_f4m(f4m_url.group(1), video_id))

        m3u8_url = re.search(r'data-hls-media="([^"]+)"', webpage)
        if m3u8_url:
            formats.extend(self._extract_m3u8_formats(m3u8_url.group(1), video_id, 'mp4', m3u8_id='hls'))
        self._sort_formats(formats)

        subtitles_url = self._html_search_regex(
            r'data-subtitlesurl\s*=\s*(["\'])(?P<url>.+?)\1',
            webpage, 'subtitle URL', default=None, group='url')
        subtitles = {}
        if subtitles_url:
            subtitles['no'] = [{
                'ext': 'ttml',
                'url': compat_urlparse.urljoin(base_url, subtitles_url),
            }]

        return {
            'id': video_id,
            'title': title,
            'description': description,
            'thumbnail': thumbnail,
            'upload_date': upload_date,
            'duration': duration,
            'formats': formats,
            'subtitles': subtitles,
        }
Commit	Line	Data
d2176c80 S	1	# encoding: utf-8
	2	from __future__ import unicode_literals
	3
	4	import re
	5
	6	from .common import InfoExtractor
2b3f951a	7	from ..compat import compat_urlparse
dfb2e1a3	8	from ..utils import (
874ae035	9	determine_ext,
dfb2e1a3	10	ExtractorError,
94128d6b	11	float_or_none,
76bfaf6d	12	parse_duration,
dfb2e1a3 S	13	unified_strdate,
dfb2e1a3 S	14	)
d2176c80 S	15
	16
	17	class NRKIE(InfoExtractor):
c4bd188d	18	_VALID_URL = r'(?:nrk:\|https?://(?:www\.)?nrk\.no/video/PS\*)(?P<id>\d+)'
d2176c80 S	19
	20	_TESTS = [
	21	{
4e6a2286 S	22	'url': 'http://www.nrk.no/video/PS*150533',
4e6a2286 S	23	'md5': 'bccd850baebefe23b56d708a113229c2',
d2176c80 S	24	'info_dict': {
	25	'id': '150533',
	26	'ext': 'flv',
	27	'title': 'Dompap og andre fugler i Piip-Show',
4e6a2286	28	'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',
393d9fc6	29	'duration': 263,
d2176c80 S	30	}
	31	},
	32	{
4e6a2286 S	33	'url': 'http://www.nrk.no/video/PS*154915',
4e6a2286 S	34	'md5': '0b1493ba1aae7d9579a5ad5531bc395a',
d2176c80 S	35	'info_dict': {
	36	'id': '154915',
	37	'ext': 'flv',
	38	'title': 'Slik høres internett ut når du er blind',
	39	'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
393d9fc6	40	'duration': 20,
d2176c80 S	41	}
	42	},
	43	]
	44
	45	def _real_extract(self, url):
4e6a2286	46	video_id = self._match_id(url)
d2176c80 S	47
d2176c80 S	48	data = self._download_json(
4e6a2286 S	49	'http://v8.psapi.nrk.no/mediaelement/%s' % video_id,
4e6a2286 S	50	video_id, 'Downloading media JSON')
d2176c80	51
874ae035	52	media_url = data.get('mediaUrl')
d2176c80	53
874ae035 S	54	if not media_url:
	55	if data['usageRights']['isGeoBlocked']:
	56	raise ExtractorError(
	57	'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
	58	expected=True)
	59
	60	if determine_ext(media_url) == 'f4m':
	61	formats = self._extract_f4m_formats(
	62	media_url + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81', video_id, f4m_id='hds')
	63	else:
	64	formats = [{
	65	'url': media_url,
	66	'ext': 'flv',
	67	}]
d2176c80	68
393d9fc6 S	69	duration = parse_duration(data.get('duration'))
393d9fc6 S	70
d2176c80 S	71	images = data.get('images')
	72	if images:
	73	thumbnails = images['webImages']
	74	thumbnails.sort(key=lambda image: image['pixelWidth'])
	75	thumbnail = thumbnails[-1]['imageUrl']
	76	else:
	77	thumbnail = None
	78
	79	return {
	80	'id': video_id,
d2176c80 S	81	'title': data['title'],
d2176c80 S	82	'description': data['description'],
393d9fc6	83	'duration': duration,
d2176c80	84	'thumbnail': thumbnail,
874ae035	85	'formats': formats,
dfb2e1a3 S	86	}
	87
	88
faa1b5c2	89	class NRKPlaylistIE(InfoExtractor):
c4bd188d	90	_VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video)(?:[^/]+/)+(?P<id>[^/]+)'
faa1b5c2	91
a0914154	92	_TESTS = [{
faa1b5c2 S	93	'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
	94	'info_dict': {
	95	'id': 'gjenopplev-den-historiske-solformorkelsen-1.12270763',
	96	'title': 'Gjenopplev den historiske solformørkelsen',
	97	'description': 'md5:c2df8ea3bac5654a26fc2834a542feed',
	98	},
a0914154 S	99	'playlist_count': 2,
	100	}, {
	101	'url': 'http://www.nrk.no/kultur/bok/rivertonprisen-til-karin-fossum-1.12266449',
	102	'info_dict': {
	103	'id': 'rivertonprisen-til-karin-fossum-1.12266449',
	104	'title': 'Rivertonprisen til Karin Fossum',
	105	'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.',
	106	},
	107	'playlist_count': 5,
	108	}]
faa1b5c2 S	109
	110	def _real_extract(self, url):
	111	playlist_id = self._match_id(url)
	112
	113	webpage = self._download_webpage(url, playlist_id)
	114
	115	entries = [
	116	self.url_result('nrk:%s' % video_id, 'NRK')
	117	for video_id in re.findall(
a0914154 S	118	r'class="[^"]\brich\b[^"]"[^>]+data-video-id="([^"]+)"',
a0914154 S	119	webpage)
faa1b5c2 S	120	]
	121
	122	playlist_title = self._og_search_title(webpage)
	123	playlist_description = self._og_search_description(webpage)
	124
	125	return self.playlist_result(
	126	entries, playlist_id, playlist_title, playlist_description)
	127
	128
01561da1	129	class NRKTVIE(InfoExtractor):
667170e2 S	130	IE_DESC = 'NRK TV and NRK Radio'
667170e2 S	131	_VALID_URL = r'(?P<baseurl>https?://(?:tv\|radio)\.nrk(?:super)?\.no/)(?:serie/[^/]+\|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?'
dfb2e1a3 S	132
	133	_TESTS = [
	134	{
c4bd188d	135	'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
5878e639	136	'md5': 'adf2c5454fa2bf032f47a9f8fb351342',
dfb2e1a3	137	'info_dict': {
70126312	138	'id': 'MUHH48000314',
dfb2e1a3 S	139	'ext': 'flv',
	140	'title': '20 spørsmål',
	141	'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
	142	'upload_date': '20140523',
	143	'duration': 1741.52,
799d88d3	144	},
dfb2e1a3 S	145	},
dfb2e1a3 S	146	{
c4bd188d	147	'url': 'https://tv.nrk.no/program/mdfp15000514',
5878e639	148	'md5': '383650ece2b25ecec996ad7b5bb2a384',
dfb2e1a3 S	149	'info_dict': {
	150	'id': 'mdfp15000514',
	151	'ext': 'flv',
	152	'title': 'Kunnskapskanalen: Grunnlovsjubiléet - Stor ståhei for ingenting',
	153	'description': 'md5:654c12511f035aed1e42bdf5db3b206a',
	154	'upload_date': '20140524',
	155	'duration': 4605.0,
799d88d3	156	},
dfb2e1a3	157	},
799d88d3 S	158	{
799d88d3 S	159	# single playlist video
c4bd188d	160	'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
799d88d3 S	161	'md5': 'adbd1dbd813edaf532b0a253780719c2',
	162	'info_dict': {
	163	'id': 'MSPO40010515-part2',
	164	'ext': 'flv',
	165	'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
	166	'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
	167	'upload_date': '20150106',
	168	},
	169	'skip': 'Only works from Norway',
799d88d3 S	170	},
799d88d3 S	171	{
c4bd188d	172	'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
799d88d3 S	173	'playlist': [
	174	{
	175	'md5': '9480285eff92d64f06e02a5367970a7a',
	176	'info_dict': {
	177	'id': 'MSPO40010515-part1',
	178	'ext': 'flv',
	179	'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 1:2)',
	180	'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
	181	'upload_date': '20150106',
	182	},
	183	},
	184	{
	185	'md5': 'adbd1dbd813edaf532b0a253780719c2',
	186	'info_dict': {
	187	'id': 'MSPO40010515-part2',
	188	'ext': 'flv',
	189	'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
	190	'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
	191	'upload_date': '20150106',
	192	},
	193	},
	194	],
	195	'info_dict': {
	196	'id': 'MSPO40010515',
	197	'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn',
	198	'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
	199	'upload_date': '20150106',
	200	'duration': 6947.5199999999995,
	201	},
	202	'skip': 'Only works from Norway',
667170e2 S	203	},
	204	{
	205	'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#',
	206	'only_matching': True,
799d88d3	207	}
dfb2e1a3 S	208	]
dfb2e1a3 S	209
799d88d3	210	def _extract_f4m(self, manifest_url, video_id):
c4f1fde7 S	211	return self._extract_f4m_formats(
c4f1fde7 S	212	manifest_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', video_id, f4m_id='hds')
799d88d3	213
dfb2e1a3 S	214	def _real_extract(self, url):
	215	mobj = re.match(self._VALID_URL, url)
	216	video_id = mobj.group('id')
799d88d3	217	part_id = mobj.group('part_id')
2b3f951a	218	base_url = mobj.group('baseurl')
799d88d3 S	219
	220	webpage = self._download_webpage(url, video_id)
	221
	222	title = self._html_search_meta(
	223	'title', webpage, 'title')
	224	description = self._html_search_meta(
	225	'description', webpage, 'description')
	226
	227	thumbnail = self._html_search_regex(
	228	r'data-posterimage="([^"]+)"',
	229	webpage, 'thumbnail', fatal=False)
	230	upload_date = unified_strdate(self._html_search_meta(
	231	'rightsfrom', webpage, 'upload date', fatal=False))
	232	duration = float_or_none(self._html_search_regex(
	233	r'data-duration="([^"]+)"',
	234	webpage, 'duration', fatal=False))
	235
	236	# playlist
	237	parts = re.findall(
	238	r'<a href="#del=(\d+)"[^>]+data-argument="([^"]+)">([^<]+)</a>', webpage)
	239	if parts:
	240	entries = []
	241	for current_part_id, stream_url, part_title in parts:
	242	if part_id and current_part_id != part_id:
	243	continue
	244	video_part_id = '%s-part%s' % (video_id, current_part_id)
	245	formats = self._extract_f4m(stream_url, video_part_id)
	246	entries.append({
	247	'id': video_part_id,
	248	'title': part_title,
	249	'description': description,
	250	'thumbnail': thumbnail,
	251	'upload_date': upload_date,
	252	'formats': formats,
	253	})
	254	if part_id:
	255	if entries:
	256	return entries[0]
	257	else:
	258	playlist = self.playlist_result(entries, video_id, title, description)
	259	playlist.update({
	260	'thumbnail': thumbnail,
	261	'upload_date': upload_date,
	262	'duration': duration,
	263	})
	264	return playlist
dfb2e1a3 S	265
	266	formats = []
	267
799d88d3	268	f4m_url = re.search(r'data-media="([^"]+)"', webpage)
dfb2e1a3	269	if f4m_url:
799d88d3	270	formats.extend(self._extract_f4m(f4m_url.group(1), video_id))
dfb2e1a3	271
799d88d3	272	m3u8_url = re.search(r'data-hls-media="([^"]+)"', webpage)
dfb2e1a3	273	if m3u8_url:
c4f1fde7	274	formats.extend(self._extract_m3u8_formats(m3u8_url.group(1), video_id, 'mp4', m3u8_id='hls'))
dfb2e1a3 S	275	self._sort_formats(formats)
dfb2e1a3 S	276
76bfaf6d	277	subtitles_url = self._html_search_regex(
2b3f951a S	278	r'data-subtitlesurl\s=\s(["\'])(?P<url>.+?)\1',
	279	webpage, 'subtitle URL', default=None, group='url')
	280	subtitles = {}
76bfaf6d	281	if subtitles_url:
2b3f951a S	282	subtitles['no'] = [{
	283	'ext': 'ttml',
	284	'url': compat_urlparse.urljoin(base_url, subtitles_url),
	285	}]
76bfaf6d	286
dfb2e1a3 S	287	return {
	288	'id': video_id,
	289	'title': title,
	290	'description': description,
	291	'thumbnail': thumbnail,
	292	'upload_date': upload_date,
	293	'duration': duration,
	294	'formats': formats,
76bfaf6d	295	'subtitles': subtitles,
e6c9f80c	296	}