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

# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
    HEADRequest,
    unified_strdate,
    strip_jsonp,
    int_or_none,
    float_or_none,
    determine_ext,
    remove_end,
    unescapeHTML,
)


class ORFTVthekIE(InfoExtractor):
    IE_NAME = 'orf:tvthek'
    IE_DESC = 'ORF TVthek'
    _VALID_URL = r'https?://tvthek\.orf\.at/(?:[^/]+/)+(?P<id>\d+)'

    _TESTS = [{
        'url': 'http://tvthek.orf.at/program/Aufgetischt/2745173/Aufgetischt-Mit-der-Steirischen-Tafelrunde/8891389',
        'playlist': [{
            'md5': '2942210346ed779588f428a92db88712',
            'info_dict': {
                'id': '8896777',
                'ext': 'mp4',
                'title': 'Aufgetischt: Mit der Steirischen Tafelrunde',
                'description': 'md5:c1272f0245537812d4e36419c207b67d',
                'duration': 2668,
                'upload_date': '20141208',
            },
        }],
        'skip': 'Blocked outside of Austria / Germany',
    }, {
        'url': 'http://tvthek.orf.at/topic/Im-Wandel-der-Zeit/8002126/Best-of-Ingrid-Thurnher/7982256',
        'info_dict': {
            'id': '7982259',
            'ext': 'mp4',
            'title': 'Best of Ingrid Thurnher',
            'upload_date': '20140527',
            'description': 'Viele Jahre war Ingrid Thurnher das "Gesicht" der ZIB 2. Vor ihrem Wechsel zur ZIB 2 im Jahr 1995 moderierte sie unter anderem "Land und Leute", "Österreich-Bild" und "Niederösterreich heute".',
        },
        'params': {
            'skip_download': True,  # rtsp downloads
        },
        '_skip': 'Blocked outside of Austria / Germany',
    }, {
        'url': 'http://tvthek.orf.at/topic/Fluechtlingskrise/10463081/Heimat-Fremde-Heimat/13879132/Senioren-betreuen-Migrantenkinder/13879141',
        'skip_download': True,
    }, {
        'url': 'http://tvthek.orf.at/profile/Universum/35429',
        'skip_download': True,
    }]

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

        data_jsb = self._parse_json(
            self._search_regex(
                r'<div[^>]+class=(["\']).*?VideoPlaylist.*?\1[^>]+data-jsb=(["\'])(?P<json>.+?)\2',
                webpage, 'playlist', group='json'),
            playlist_id, transform_source=unescapeHTML)['playlist']['videos']

        def quality_to_int(s):
            m = re.search('([0-9]+)', s)
            if m is None:
                return -1
            return int(m.group(1))

        entries = []
        for sd in data_jsb:
            video_id, title = sd.get('id'), sd.get('title')
            if not video_id or not title:
                continue
            video_id = compat_str(video_id)
            formats = [{
                'preference': -10 if fd['delivery'] == 'hls' else None,
                'format_id': '%s-%s-%s' % (
                    fd['delivery'], fd['quality'], fd['quality_string']),
                'url': fd['src'],
                'protocol': fd['protocol'],
                'quality': quality_to_int(fd['quality']),
            } for fd in sd['sources']]

            # Check for geoblocking.
            # There is a property is_geoprotection, but that's always false
            geo_str = sd.get('geoprotection_string')
            if geo_str:
                try:
                    http_url = next(
                        f['url']
                        for f in formats
                        if re.match(r'^https?://.*\.mp4$', f['url']))
                except StopIteration:
                    pass
                else:
                    req = HEADRequest(http_url)
                    self._request_webpage(
                        req, video_id,
                        note='Testing for geoblocking',
                        errnote=((
                            'This video seems to be blocked outside of %s. '
                            'You may want to try the streaming-* formats.')
                            % geo_str),
                        fatal=False)

            self._check_formats(formats, video_id)
            self._sort_formats(formats)

            subtitles = {}
            for sub in sd.get('subtitles', []):
                sub_src = sub.get('src')
                if not sub_src:
                    continue
                subtitles.setdefault(sub.get('lang', 'de-AT'), []).append({
                    'url': sub_src,
                })

            upload_date = unified_strdate(sd.get('created_date'))
            entries.append({
                '_type': 'video',
                'id': video_id,
                'title': title,
                'formats': formats,
                'subtitles': subtitles,
                'description': sd.get('description'),
                'duration': int_or_none(sd.get('duration_in_seconds')),
                'upload_date': upload_date,
                'thumbnail': sd.get('image_full_url'),
            })

        return {
            '_type': 'playlist',
            'entries': entries,
            'id': playlist_id,
        }


class ORFRadioIE(InfoExtractor):
    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        station = mobj.group('station')
        show_date = mobj.group('date')
        show_id = mobj.group('show')

        if station == 'fm4':
            show_id = '4%s' % show_id

        data = self._download_json(
            'http://audioapi.orf.at/%s/api/json/current/broadcast/%s/%s' % (station, show_id, show_date),
            show_id
        )

        def extract_entry_dict(info, title, subtitle):
            return {
                'id': info['loopStreamId'].replace('.mp3', ''),
                'url': 'http://loopstream01.apa.at/?channel=%s&id=%s' % (station, info['loopStreamId']),
                'title': title,
                'description': subtitle,
                'duration': (info['end'] - info['start']) / 1000,
                'timestamp': info['start'] / 1000,
                'ext': 'mp3'
            }

        entries = [extract_entry_dict(t, data['title'], data['subtitle']) for t in data['streams']]

        return {
            '_type': 'playlist',
            'id': show_id,
            'title': data['title'],
            'description': data['subtitle'],
            'entries': entries
        }


class ORFFM4IE(ORFRadioIE):
    IE_NAME = 'orf:fm4'
    IE_DESC = 'radio FM4'
    _VALID_URL = r'https?://(?P<station>fm4)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'

    _TEST = {
        'url': 'http://fm4.orf.at/player/20170107/CC',
        'md5': '2b0be47375432a7ef104453432a19212',
        'info_dict': {
            'id': '2017-01-07_2100_tl_54_7DaysSat18_31295',
            'ext': 'mp3',
            'title': 'Solid Steel Radioshow',
            'description': 'Die Mixshow von Coldcut und Ninja Tune.',
            'duration': 3599,
            'timestamp': 1483819257,
            'upload_date': '20170107',
        },
        'skip': 'Shows from ORF radios are only available for 7 days.'
    }


class ORFOE1IE(ORFRadioIE):
    IE_NAME = 'orf:oe1'
    IE_DESC = 'Radio Österreich 1'
    _VALID_URL = r'https?://(?P<station>oe1)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'

    _TEST = {
        'url': 'http://oe1.orf.at/player/20170108/456544',
        'md5': '34d8a6e67ea888293741c86a099b745b',
        'info_dict': {
            'id': '2017-01-08_0759_tl_51_7DaysSun6_256141',
            'ext': 'mp3',
            'title': 'Morgenjournal',
            'duration': 609,
            'timestamp': 1483858796,
            'upload_date': '20170108',
        },
        'skip': 'Shows from ORF radios are only available for 7 days.'
    }


class ORFIPTVIE(InfoExtractor):
    IE_NAME = 'orf:iptv'
    IE_DESC = 'iptv.ORF.at'
    _VALID_URL = r'https?://iptv\.orf\.at/(?:#/)?stories/(?P<id>\d+)'

    _TEST = {
        'url': 'http://iptv.orf.at/stories/2275236/',
        'md5': 'c8b22af4718a4b4af58342529453e3e5',
        'info_dict': {
            'id': '350612',
            'ext': 'flv',
            'title': 'Weitere Evakuierungen um Vulkan Calbuco',
            'description': 'md5:d689c959bdbcf04efeddedbf2299d633',
            'duration': 68.197,
            'thumbnail': r're:^https?://.*\.jpg$',
            'upload_date': '20150425',
        },
    }

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

        webpage = self._download_webpage(
            'http://iptv.orf.at/stories/%s' % story_id, story_id)

        video_id = self._search_regex(
            r'data-video(?:id)?="(\d+)"', webpage, 'video id')

        data = self._download_json(
            'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id,
            video_id)[0]

        duration = float_or_none(data['duration'], 1000)

        video = data['sources']['default']
        load_balancer_url = video['loadBalancerUrl']
        abr = int_or_none(video.get('audioBitrate'))
        vbr = int_or_none(video.get('bitrate'))
        fps = int_or_none(video.get('videoFps'))
        width = int_or_none(video.get('videoWidth'))
        height = int_or_none(video.get('videoHeight'))
        thumbnail = video.get('preview')

        rendition = self._download_json(
            load_balancer_url, video_id, transform_source=strip_jsonp)

        f = {
            'abr': abr,
            'vbr': vbr,
            'fps': fps,
            'width': width,
            'height': height,
        }

        formats = []
        for format_id, format_url in rendition['redirect'].items():
            if format_id == 'rtmp':
                ff = f.copy()
                ff.update({
                    'url': format_url,
                    'format_id': format_id,
                })
                formats.append(ff)
            elif determine_ext(format_url) == 'f4m':
                formats.extend(self._extract_f4m_formats(
                    format_url, video_id, f4m_id=format_id))
            elif determine_ext(format_url) == 'm3u8':
                formats.extend(self._extract_m3u8_formats(
                    format_url, video_id, 'mp4', m3u8_id=format_id))
            else:
                continue
        self._sort_formats(formats)

        title = remove_end(self._og_search_title(webpage), ' - iptv.ORF.at')
        description = self._og_search_description(webpage)
        upload_date = unified_strdate(self._html_search_meta(
            'dc.date', webpage, 'upload date'))

        return {
            'id': video_id,
            'title': title,
            'description': description,
            'duration': duration,
            'thumbnail': thumbnail,
            'upload_date': upload_date,
            'formats': formats,
        }
Commit	Line	Data
89284910	1	# coding: utf-8
5d73273f	2	from __future__ import unicode_literals
89284910	3
5d73273f	4	import re
54543467 JMF	5
54543467 JMF	6	from .common import InfoExtractor
73c801d6	7	from ..compat import compat_str
54543467	8	from ..utils import (
5d73273f PH	9	HEADRequest,
5d73273f PH	10	unified_strdate,
14137b57 S	11	strip_jsonp,
	12	int_or_none,
	13	float_or_none,
	14	determine_ext,
	15	remove_end,
73c801d6	16	unescapeHTML,
54543467 JMF	17	)
54543467 JMF	18
5d73273f	19
eb368012 S	20	class ORFTVthekIE(InfoExtractor):
	21	IE_NAME = 'orf:tvthek'
	22	IE_DESC = 'ORF TVthek'
73c801d6	23	_VALID_URL = r'https?://tvthek\.orf\.at/(?:[^/]+/)+(?P<id>\d+)'
5d73273f	24
13d27a42	25	_TESTS = [{
a6620ac2 PH	26	'url': 'http://tvthek.orf.at/program/Aufgetischt/2745173/Aufgetischt-Mit-der-Steirischen-Tafelrunde/8891389',
	27	'playlist': [{
	28	'md5': '2942210346ed779588f428a92db88712',
	29	'info_dict': {
	30	'id': '8896777',
	31	'ext': 'mp4',
	32	'title': 'Aufgetischt: Mit der Steirischen Tafelrunde',
	33	'description': 'md5:c1272f0245537812d4e36419c207b67d',
	34	'duration': 2668,
	35	'upload_date': '20141208',
	36	},
	37	}],
13d27a42 PH	38	'skip': 'Blocked outside of Austria / Germany',
	39	}, {
	40	'url': 'http://tvthek.orf.at/topic/Im-Wandel-der-Zeit/8002126/Best-of-Ingrid-Thurnher/7982256',
7b0d333a NP	41	'info_dict': {
	42	'id': '7982259',
	43	'ext': 'mp4',
	44	'title': 'Best of Ingrid Thurnher',
	45	'upload_date': '20140527',
	46	'description': 'Viele Jahre war Ingrid Thurnher das "Gesicht" der ZIB 2. Vor ihrem Wechsel zur ZIB 2 im Jahr 1995 moderierte sie unter anderem "Land und Leute", "Österreich-Bild" und "Niederösterreich heute".',
	47	},
	48	'params': {
	49	'skip_download': True, # rtsp downloads
	50	},
13d27a42	51	'_skip': 'Blocked outside of Austria / Germany',
73c801d6 S	52	}, {
	53	'url': 'http://tvthek.orf.at/topic/Fluechtlingskrise/10463081/Heimat-Fremde-Heimat/13879132/Senioren-betreuen-Migrantenkinder/13879141',
	54	'skip_download': True,
	55	}, {
	56	'url': 'http://tvthek.orf.at/profile/Universum/35429',
	57	'skip_download': True,
13d27a42	58	}]
54543467	59
54543467	60	def _real_extract(self, url):
a6620ac2	61	playlist_id = self._match_id(url)
54543467 JMF	62	webpage = self._download_webpage(url, playlist_id)
54543467 JMF	63
73c801d6 S	64	data_jsb = self._parse_json(
	65	self._search_regex(
	66	r'<div[^>]+class=(["\']).?VideoPlaylist.?\1[^>]+data-jsb=(["\'])(?P<json>.+?)\2',
	67	webpage, 'playlist', group='json'),
	68	playlist_id, transform_source=unescapeHTML)['playlist']['videos']
5d73273f PH	69
	70	def quality_to_int(s):
	71	m = re.search('([0-9]+)', s)
	72	if m is None:
	73	return -1
	74	return int(m.group(1))
	75
	76	entries = []
73c801d6 S	77	for sd in data_jsb:
	78	video_id, title = sd.get('id'), sd.get('title')
	79	if not video_id or not title:
	80	continue
	81	video_id = compat_str(video_id)
5d73273f PH	82	formats = [{
	83	'preference': -10 if fd['delivery'] == 'hls' else None,
	84	'format_id': '%s-%s-%s' % (
	85	fd['delivery'], fd['quality'], fd['quality_string']),
	86	'url': fd['src'],
	87	'protocol': fd['protocol'],
	88	'quality': quality_to_int(fd['quality']),
73c801d6	89	} for fd in sd['sources']]
5d73273f PH	90
	91	# Check for geoblocking.
	92	# There is a property is_geoprotection, but that's always false
	93	geo_str = sd.get('geoprotection_string')
	94	if geo_str:
	95	try:
	96	http_url = next(
	97	f['url']
	98	for f in formats
	99	if re.match(r'^https?://.*\.mp4$', f['url']))
	100	except StopIteration:
	101	pass
	102	else:
	103	req = HEADRequest(http_url)
4f81667d	104	self._request_webpage(
5d73273f PH	105	req, video_id,
	106	note='Testing for geoblocking',
	107	errnote=((
	108	'This video seems to be blocked outside of %s. '
	109	'You may want to try the streaming-* formats.')
	110	% geo_str),
	111	fatal=False)
	112
e277f2a6	113	self._check_formats(formats, video_id)
5d73273f PH	114	self._sort_formats(formats)
5d73273f PH	115
791d29db RA	116	subtitles = {}
	117	for sub in sd.get('subtitles', []):
	118	sub_src = sub.get('src')
	119	if not sub_src:
	120	continue
	121	subtitles.setdefault(sub.get('lang', 'de-AT'), []).append({
	122	'url': sub_src,
	123	})
	124
73c801d6	125	upload_date = unified_strdate(sd.get('created_date'))
5d73273f	126	entries.append({
54543467	127	'_type': 'video',
5d73273f	128	'id': video_id,
73c801d6	129	'title': title,
5d73273f	130	'formats': formats,
791d29db	131	'subtitles': subtitles,
5d73273f	132	'description': sd.get('description'),
73c801d6	133	'duration': int_or_none(sd.get('duration_in_seconds')),
5d73273f PH	134	'upload_date': upload_date,
	135	'thumbnail': sd.get('image_full_url'),
	136	})
	137
	138	return {
	139	'_type': 'playlist',
	140	'entries': entries,
	141	'id': playlist_id,
	142	}
eb368012 S	143
eb368012 S	144
efe93167	145	class ORFRadioIE(InfoExtractor):
eb368012 S	146	def _real_extract(self, url):
eb368012 S	147	mobj = re.match(self._VALID_URL, url)
efe93167	148	station = mobj.group('station')
eb368012 S	149	show_date = mobj.group('date')
	150	show_id = mobj.group('show')
	151
efe93167	152	if station == 'fm4':
	153	show_id = '4%s' % show_id
	154
eb368012	155	data = self._download_json(
efe93167	156	'http://audioapi.orf.at/%s/api/json/current/broadcast/%s/%s' % (station, show_id, show_date),
eb368012 S	157	show_id
	158	)
	159
	160	def extract_entry_dict(info, title, subtitle):
	161	return {
	162	'id': info['loopStreamId'].replace('.mp3', ''),
efe93167	163	'url': 'http://loopstream01.apa.at/?channel=%s&id=%s' % (station, info['loopStreamId']),
eb368012 S	164	'title': title,
	165	'description': subtitle,
	166	'duration': (info['end'] - info['start']) / 1000,
	167	'timestamp': info['start'] / 1000,
	168	'ext': 'mp3'
	169	}
	170
	171	entries = [extract_entry_dict(t, data['title'], data['subtitle']) for t in data['streams']]
	172
	173	return {
	174	'_type': 'playlist',
	175	'id': show_id,
	176	'title': data['title'],
	177	'description': data['subtitle'],
	178	'entries': entries
5f6a1245	179	}
14137b57 S	180
14137b57 S	181
efe93167	182	class ORFFM4IE(ORFRadioIE):
	183	IE_NAME = 'orf:fm4'
	184	IE_DESC = 'radio FM4'
1339ecb2	185	_VALID_URL = r'https?://(?P<station>fm4)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
efe93167	186
1339ecb2 S	187	_TEST = {
	188	'url': 'http://fm4.orf.at/player/20170107/CC',
	189	'md5': '2b0be47375432a7ef104453432a19212',
	190	'info_dict': {
	191	'id': '2017-01-07_2100_tl_54_7DaysSat18_31295',
	192	'ext': 'mp3',
	193	'title': 'Solid Steel Radioshow',
	194	'description': 'Die Mixshow von Coldcut und Ninja Tune.',
	195	'duration': 3599,
	196	'timestamp': 1483819257,
	197	'upload_date': '20170107',
	198	},
	199	'skip': 'Shows from ORF radios are only available for 7 days.'
	200	}
efe93167	201
	202
	203	class ORFOE1IE(ORFRadioIE):
	204	IE_NAME = 'orf:oe1'
	205	IE_DESC = 'Radio Österreich 1'
1339ecb2	206	_VALID_URL = r'https?://(?P<station>oe1)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
efe93167	207
1339ecb2 S	208	_TEST = {
	209	'url': 'http://oe1.orf.at/player/20170108/456544',
	210	'md5': '34d8a6e67ea888293741c86a099b745b',
	211	'info_dict': {
	212	'id': '2017-01-08_0759_tl_51_7DaysSun6_256141',
	213	'ext': 'mp3',
	214	'title': 'Morgenjournal',
	215	'duration': 609,
	216	'timestamp': 1483858796,
	217	'upload_date': '20170108',
	218	},
	219	'skip': 'Shows from ORF radios are only available for 7 days.'
	220	}
efe93167	221
efe93167	222
14137b57 S	223	class ORFIPTVIE(InfoExtractor):
	224	IE_NAME = 'orf:iptv'
	225	IE_DESC = 'iptv.ORF.at'
5886b38d	226	_VALID_URL = r'https?://iptv\.orf\.at/(?:#/)?stories/(?P<id>\d+)'
14137b57 S	227
14137b57 S	228	_TEST = {
529d26c3 S	229	'url': 'http://iptv.orf.at/stories/2275236/',
529d26c3 S	230	'md5': 'c8b22af4718a4b4af58342529453e3e5',
14137b57	231	'info_dict': {
529d26c3	232	'id': '350612',
14137b57	233	'ext': 'flv',
529d26c3 S	234	'title': 'Weitere Evakuierungen um Vulkan Calbuco',
	235	'description': 'md5:d689c959bdbcf04efeddedbf2299d633',
	236	'duration': 68.197,
ec85ded8	237	'thumbnail': r're:^https?://.*\.jpg$',
529d26c3	238	'upload_date': '20150425',
14137b57 S	239	},
	240	}
	241
	242	def _real_extract(self, url):
	243	story_id = self._match_id(url)
	244
	245	webpage = self._download_webpage(
	246	'http://iptv.orf.at/stories/%s' % story_id, story_id)
	247
	248	video_id = self._search_regex(
	249	r'data-video(?:id)?="(\d+)"', webpage, 'video id')
	250
	251	data = self._download_json(
	252	'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id,
	253	video_id)[0]
	254
	255	duration = float_or_none(data['duration'], 1000)
	256
	257	video = data['sources']['default']
	258	load_balancer_url = video['loadBalancerUrl']
	259	abr = int_or_none(video.get('audioBitrate'))
	260	vbr = int_or_none(video.get('bitrate'))
	261	fps = int_or_none(video.get('videoFps'))
	262	width = int_or_none(video.get('videoWidth'))
	263	height = int_or_none(video.get('videoHeight'))
	264	thumbnail = video.get('preview')
	265
	266	rendition = self._download_json(
	267	load_balancer_url, video_id, transform_source=strip_jsonp)
	268
	269	f = {
	270	'abr': abr,
	271	'vbr': vbr,
	272	'fps': fps,
	273	'width': width,
	274	'height': height,
	275	}
	276
	277	formats = []
	278	for format_id, format_url in rendition['redirect'].items():
	279	if format_id == 'rtmp':
	280	ff = f.copy()
	281	ff.update({
	282	'url': format_url,
	283	'format_id': format_id,
	284	})
	285	formats.append(ff)
	286	elif determine_ext(format_url) == 'f4m':
	287	formats.extend(self._extract_f4m_formats(
	288	format_url, video_id, f4m_id=format_id))
	289	elif determine_ext(format_url) == 'm3u8':
	290	formats.extend(self._extract_m3u8_formats(
	291	format_url, video_id, 'mp4', m3u8_id=format_id))
	292	else:
	293	continue
	294	self._sort_formats(formats)
	295
	296	title = remove_end(self._og_search_title(webpage), ' - iptv.ORF.at')
	297	description = self._og_search_description(webpage)
	298	upload_date = unified_strdate(self._html_search_meta(
	299	'dc.date', webpage, 'upload date'))
	300
	301	return {
	302	'id': video_id,
303	'title': title,
304	'description': description,
305	'duration': duration,
306	'thumbnail': thumbnail,
307	'upload_date': upload_date,
308	'formats': formats,
309	}