[yt-dlp.git] / yt_dlp / 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 (
    clean_html,
    determine_ext,
    float_or_none,
    HEADRequest,
    int_or_none,
    join_nonempty,
    orderedSet,
    remove_end,
    str_or_none,
    strip_jsonp,
    unescapeHTML,
    unified_strdate,
    url_or_none,
)


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',
        'only_matching': True,
    }, {
        'url': 'http://tvthek.orf.at/profile/Universum/35429',
        'only_matching': 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']

        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 = []
            for fd in sd['sources']:
                src = url_or_none(fd.get('src'))
                if not src:
                    continue
                format_id = join_nonempty('delivery', 'quality', 'quality_string', from_dict=fd)
                ext = determine_ext(src)
                if ext == 'm3u8':
                    m3u8_formats = self._extract_m3u8_formats(
                        src, video_id, 'mp4', m3u8_id=format_id, fatal=False)
                    if any('/geoprotection' in f['url'] for f in m3u8_formats):
                        self.raise_geo_restricted()
                    formats.extend(m3u8_formats)
                elif ext == 'f4m':
                    formats.extend(self._extract_f4m_formats(
                        src, video_id, f4m_id=format_id, fatal=False))
                elif ext == 'mpd':
                    formats.extend(self._extract_mpd_formats(
                        src, video_id, mpd_id=format_id, fatal=False))
                else:
                    formats.append({
                        'format_id': format_id,
                        'url': src,
                        'protocol': fd.get('protocol'),
                    })

            # 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'))

            thumbnails = []
            preview = sd.get('preview_image_url')
            if preview:
                thumbnails.append({
                    'id': 'preview',
                    'url': preview,
                    'preference': 0,
                })
            image = sd.get('image_full_url')
            if not image and len(data_jsb) == 1:
                image = self._og_search_thumbnail(webpage)
            if image:
                thumbnails.append({
                    'id': 'full',
                    'url': image,
                    'preference': 1,
                })

            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,
                'thumbnails': thumbnails,
            })

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


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

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

        entries = []
        for info in data['streams']:
            loop_stream_id = str_or_none(info.get('loopStreamId'))
            if not loop_stream_id:
                continue
            title = str_or_none(data.get('title'))
            if not title:
                continue
            start = int_or_none(info.get('start'), scale=1000)
            end = int_or_none(info.get('end'), scale=1000)
            duration = end - start if end and start else None
            entries.append({
                'id': loop_stream_id.replace('.mp3', ''),
                'url': 'https://loopstream01.apa.at/?channel=%s&id=%s' % (self._LOOP_STATION, loop_stream_id),
                'title': title,
                'description': clean_html(data.get('subtitle')),
                'duration': duration,
                'timestamp': start,
                'ext': 'mp3',
                'series': data.get('programTitle'),
            })

        return {
            '_type': 'playlist',
            'id': show_id,
            'title': data.get('title'),
            'description': clean_html(data.get('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>4\w+)'
    _API_STATION = 'fm4'
    _LOOP_STATION = 'fm4'

    _TEST = {
        'url': 'http://fm4.orf.at/player/20170107/4CC',
        '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.',
        'only_matching': True,
    }


class ORFNOEIE(ORFRadioIE):
    IE_NAME = 'orf:noe'
    IE_DESC = 'Radio Niederösterreich'
    _VALID_URL = r'https?://(?P<station>noe)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
    _API_STATION = 'noe'
    _LOOP_STATION = 'oe2n'

    _TEST = {
        'url': 'https://noe.orf.at/player/20200423/NGM',
        'only_matching': True,
    }


class ORFWIEIE(ORFRadioIE):
    IE_NAME = 'orf:wien'
    IE_DESC = 'Radio Wien'
    _VALID_URL = r'https?://(?P<station>wien)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
    _API_STATION = 'wie'
    _LOOP_STATION = 'oe2w'

    _TEST = {
        'url': 'https://wien.orf.at/player/20200423/WGUM',
        'only_matching': True,
    }


class ORFBGLIE(ORFRadioIE):
    IE_NAME = 'orf:burgenland'
    IE_DESC = 'Radio Burgenland'
    _VALID_URL = r'https?://(?P<station>burgenland)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
    _API_STATION = 'bgl'
    _LOOP_STATION = 'oe2b'

    _TEST = {
        'url': 'https://burgenland.orf.at/player/20200423/BGM',
        'only_matching': True,
    }


class ORFOOEIE(ORFRadioIE):
    IE_NAME = 'orf:oberoesterreich'
    IE_DESC = 'Radio Oberösterreich'
    _VALID_URL = r'https?://(?P<station>ooe)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
    _API_STATION = 'ooe'
    _LOOP_STATION = 'oe2o'

    _TEST = {
        'url': 'https://ooe.orf.at/player/20200423/OGMO',
        'only_matching': True,
    }


class ORFSTMIE(ORFRadioIE):
    IE_NAME = 'orf:steiermark'
    IE_DESC = 'Radio Steiermark'
    _VALID_URL = r'https?://(?P<station>steiermark)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
    _API_STATION = 'stm'
    _LOOP_STATION = 'oe2st'

    _TEST = {
        'url': 'https://steiermark.orf.at/player/20200423/STGMS',
        'only_matching': True,
    }


class ORFKTNIE(ORFRadioIE):
    IE_NAME = 'orf:kaernten'
    IE_DESC = 'Radio Kärnten'
    _VALID_URL = r'https?://(?P<station>kaernten)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
    _API_STATION = 'ktn'
    _LOOP_STATION = 'oe2k'

    _TEST = {
        'url': 'https://kaernten.orf.at/player/20200423/KGUMO',
        'only_matching': True,
    }


class ORFSBGIE(ORFRadioIE):
    IE_NAME = 'orf:salzburg'
    IE_DESC = 'Radio Salzburg'
    _VALID_URL = r'https?://(?P<station>salzburg)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
    _API_STATION = 'sbg'
    _LOOP_STATION = 'oe2s'

    _TEST = {
        'url': 'https://salzburg.orf.at/player/20200423/SGUM',
        'only_matching': True,
    }


class ORFTIRIE(ORFRadioIE):
    IE_NAME = 'orf:tirol'
    IE_DESC = 'Radio Tirol'
    _VALID_URL = r'https?://(?P<station>tirol)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
    _API_STATION = 'tir'
    _LOOP_STATION = 'oe2t'

    _TEST = {
        'url': 'https://tirol.orf.at/player/20200423/TGUMO',
        'only_matching': True,
    }


class ORFVBGIE(ORFRadioIE):
    IE_NAME = 'orf:vorarlberg'
    IE_DESC = 'Radio Vorarlberg'
    _VALID_URL = r'https?://(?P<station>vorarlberg)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
    _API_STATION = 'vbg'
    _LOOP_STATION = 'oe2v'

    _TEST = {
        'url': 'https://vorarlberg.orf.at/player/20200423/VGUM',
        'only_matching': True,
    }


class ORFOE3IE(ORFRadioIE):
    IE_NAME = 'orf:oe3'
    IE_DESC = 'Radio Österreich 3'
    _VALID_URL = r'https?://(?P<station>oe3)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
    _API_STATION = 'oe3'
    _LOOP_STATION = 'oe3'

    _TEST = {
        'url': 'https://oe3.orf.at/player/20200424/3WEK',
        'only_matching': True,
    }


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+)'
    _API_STATION = 'oe1'
    _LOOP_STATION = 'oe1'

    _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,
        }


class ORFFM4StoryIE(InfoExtractor):
    IE_NAME = 'orf:fm4:story'
    IE_DESC = 'fm4.orf.at stories'
    _VALID_URL = r'https?://fm4\.orf\.at/stories/(?P<id>\d+)'

    _TEST = {
        'url': 'http://fm4.orf.at/stories/2865738/',
        'playlist': [{
            'md5': 'e1c2c706c45c7b34cf478bbf409907ca',
            'info_dict': {
                'id': '547792',
                'ext': 'flv',
                'title': 'Manu Delago und Inner Tongue live',
                'description': 'Manu Delago und Inner Tongue haben bei der FM4 Soundpark Session live alles gegeben. Hier gibt es Fotos und die gesamte Session als Video.',
                'duration': 1748.52,
                'thumbnail': r're:^https?://.*\.jpg$',
                'upload_date': '20170913',
            },
        }, {
            'md5': 'c6dd2179731f86f4f55a7b49899d515f',
            'info_dict': {
                'id': '547798',
                'ext': 'flv',
                'title': 'Manu Delago und Inner Tongue live (2)',
                'duration': 1504.08,
                'thumbnail': r're:^https?://.*\.jpg$',
                'upload_date': '20170913',
                'description': 'Manu Delago und Inner Tongue haben bei der FM4 Soundpark Session live alles gegeben. Hier gibt es Fotos und die gesamte Session als Video.',
            },
        }],
    }

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

        entries = []
        all_ids = orderedSet(re.findall(r'data-video(?:id)?="(\d+)"', webpage))
        for idx, video_id in enumerate(all_ids):
            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']['q8c']
            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), ' - fm4.ORF.at')
            if idx >= 1:
                # Titles are duplicates, make them unique
                title += ' (' + str(idx + 1) + ')'
            description = self._og_search_description(webpage)
            upload_date = unified_strdate(self._html_search_meta(
                'dc.date', webpage, 'upload date'))

            entries.append({
                'id': video_id,
                'title': title,
                'description': description,
                'duration': duration,
                'thumbnail': thumbnail,
                'upload_date': upload_date,
                'formats': formats,
            })

        return self.playlist_result(entries)
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 (
aca2fd22	9	clean_html,
0732a905 PH	10	determine_ext,
0732a905 PH	11	float_or_none,
5d73273f	12	HEADRequest,
14137b57	13	int_or_none,
34921b43	14	join_nonempty,
0732a905	15	orderedSet,
14137b57	16	remove_end,
aca2fd22	17	str_or_none,
0732a905	18	strip_jsonp,
73c801d6	19	unescapeHTML,
0732a905	20	unified_strdate,
4b6aca17	21	url_or_none,
54543467 JMF	22	)
54543467 JMF	23
5d73273f	24
eb368012 S	25	class ORFTVthekIE(InfoExtractor):
	26	IE_NAME = 'orf:tvthek'
	27	IE_DESC = 'ORF TVthek'
73c801d6	28	_VALID_URL = r'https?://tvthek\.orf\.at/(?:[^/]+/)+(?P<id>\d+)'
5d73273f	29
13d27a42	30	_TESTS = [{
a6620ac2 PH	31	'url': 'http://tvthek.orf.at/program/Aufgetischt/2745173/Aufgetischt-Mit-der-Steirischen-Tafelrunde/8891389',
	32	'playlist': [{
	33	'md5': '2942210346ed779588f428a92db88712',
	34	'info_dict': {
	35	'id': '8896777',
	36	'ext': 'mp4',
	37	'title': 'Aufgetischt: Mit der Steirischen Tafelrunde',
	38	'description': 'md5:c1272f0245537812d4e36419c207b67d',
	39	'duration': 2668,
	40	'upload_date': '20141208',
	41	},
	42	}],
13d27a42 PH	43	'skip': 'Blocked outside of Austria / Germany',
	44	}, {
	45	'url': 'http://tvthek.orf.at/topic/Im-Wandel-der-Zeit/8002126/Best-of-Ingrid-Thurnher/7982256',
7b0d333a NP	46	'info_dict': {
	47	'id': '7982259',
	48	'ext': 'mp4',
	49	'title': 'Best of Ingrid Thurnher',
	50	'upload_date': '20140527',
	51	'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".',
	52	},
	53	'params': {
	54	'skip_download': True, # rtsp downloads
	55	},
7512aa98	56	'skip': 'Blocked outside of Austria / Germany',
73c801d6 S	57	}, {
73c801d6 S	58	'url': 'http://tvthek.orf.at/topic/Fluechtlingskrise/10463081/Heimat-Fremde-Heimat/13879132/Senioren-betreuen-Migrantenkinder/13879141',
7512aa98	59	'only_matching': True,
73c801d6 S	60	}, {
73c801d6 S	61	'url': 'http://tvthek.orf.at/profile/Universum/35429',
7512aa98	62	'only_matching': True,
13d27a42	63	}]
54543467	64
54543467	65	def _real_extract(self, url):
a6620ac2	66	playlist_id = self._match_id(url)
54543467 JMF	67	webpage = self._download_webpage(url, playlist_id)
54543467 JMF	68
73c801d6 S	69	data_jsb = self._parse_json(
	70	self._search_regex(
	71	r'<div[^>]+class=(["\']).?VideoPlaylist.?\1[^>]+data-jsb=(["\'])(?P<json>.+?)\2',
	72	webpage, 'playlist', group='json'),
	73	playlist_id, transform_source=unescapeHTML)['playlist']['videos']
5d73273f	74
5d73273f	75	entries = []
73c801d6 S	76	for sd in data_jsb:
	77	video_id, title = sd.get('id'), sd.get('title')
	78	if not video_id or not title:
	79	continue
	80	video_id = compat_str(video_id)
c620694c SH	81	formats = []
c620694c SH	82	for fd in sd['sources']:
4b6aca17 S	83	src = url_or_none(fd.get('src'))
	84	if not src:
	85	continue
34921b43	86	format_id = join_nonempty('delivery', 'quality', 'quality_string', from_dict=fd)
aaf9d904 S	87	ext = determine_ext(src)
aaf9d904 S	88	if ext == 'm3u8':
90ea83c6 S	89	m3u8_formats = self._extract_m3u8_formats(
	90	src, video_id, 'mp4', m3u8_id=format_id, fatal=False)
	91	if any('/geoprotection' in f['url'] for f in m3u8_formats):
	92	self.raise_geo_restricted()
	93	formats.extend(m3u8_formats)
aaf9d904	94	elif ext == 'f4m':
c620694c	95	formats.extend(self._extract_f4m_formats(
aaf9d904	96	src, video_id, f4m_id=format_id, fatal=False))
ed807c18	97	elif ext == 'mpd':
	98	formats.extend(self._extract_mpd_formats(
	99	src, video_id, mpd_id=format_id, fatal=False))
4b6aca17 S	100	else:
	101	formats.append({
	102	'format_id': format_id,
	103	'url': src,
	104	'protocol': fd.get('protocol'),
	105	})
5d73273f PH	106
	107	# Check for geoblocking.
	108	# There is a property is_geoprotection, but that's always false
	109	geo_str = sd.get('geoprotection_string')
	110	if geo_str:
	111	try:
	112	http_url = next(
	113	f['url']
	114	for f in formats
	115	if re.match(r'^https?://.*\.mp4$', f['url']))
	116	except StopIteration:
	117	pass
	118	else:
	119	req = HEADRequest(http_url)
4f81667d	120	self._request_webpage(
5d73273f PH	121	req, video_id,
	122	note='Testing for geoblocking',
	123	errnote=((
	124	'This video seems to be blocked outside of %s. '
	125	'You may want to try the streaming-* formats.')
	126	% geo_str),
	127	fatal=False)
	128
e277f2a6	129	self._check_formats(formats, video_id)
5d73273f PH	130	self._sort_formats(formats)
5d73273f PH	131
791d29db RA	132	subtitles = {}
	133	for sub in sd.get('subtitles', []):
	134	sub_src = sub.get('src')
	135	if not sub_src:
	136	continue
	137	subtitles.setdefault(sub.get('lang', 'de-AT'), []).append({
	138	'url': sub_src,
	139	})
	140
73c801d6	141	upload_date = unified_strdate(sd.get('created_date'))
46358f64	142
	143	thumbnails = []
	144	preview = sd.get('preview_image_url')
	145	if preview:
	146	thumbnails.append({
	147	'id': 'preview',
	148	'url': preview,
	149	'preference': 0,
	150	})
	151	image = sd.get('image_full_url')
	152	if not image and len(data_jsb) == 1:
	153	image = self._og_search_thumbnail(webpage)
	154	if image:
	155	thumbnails.append({
	156	'id': 'full',
	157	'url': image,
	158	'preference': 1,
	159	})
	160
5d73273f	161	entries.append({
54543467	162	'_type': 'video',
5d73273f	163	'id': video_id,
73c801d6	164	'title': title,
5d73273f	165	'formats': formats,
791d29db	166	'subtitles': subtitles,
5d73273f	167	'description': sd.get('description'),
73c801d6	168	'duration': int_or_none(sd.get('duration_in_seconds')),
5d73273f	169	'upload_date': upload_date,
46358f64	170	'thumbnails': thumbnails,
5d73273f PH	171	})
	172
	173	return {
	174	'_type': 'playlist',
	175	'entries': entries,
	176	'id': playlist_id,
	177	}
eb368012 S	178
eb368012 S	179
efe93167	180	class ORFRadioIE(InfoExtractor):
eb368012	181	def _real_extract(self, url):
5ad28e7f	182	mobj = self._match_valid_url(url)
eb368012 S	183	show_date = mobj.group('date')
	184	show_id = mobj.group('show')
	185
	186	data = self._download_json(
aca2fd22	187	'http://audioapi.orf.at/%s/api/json/current/broadcast/%s/%s'
13283058	188	% (self._API_STATION, show_id, show_date), show_id)
aca2fd22 S	189
	190	entries = []
	191	for info in data['streams']:
	192	loop_stream_id = str_or_none(info.get('loopStreamId'))
	193	if not loop_stream_id:
	194	continue
	195	title = str_or_none(data.get('title'))
	196	if not title:
	197	continue
	198	start = int_or_none(info.get('start'), scale=1000)
	199	end = int_or_none(info.get('end'), scale=1000)
	200	duration = end - start if end and start else None
	201	entries.append({
	202	'id': loop_stream_id.replace('.mp3', ''),
b73612a2	203	'url': 'https://loopstream01.apa.at/?channel=%s&id=%s' % (self._LOOP_STATION, loop_stream_id),
eb368012	204	'title': title,
aca2fd22 S	205	'description': clean_html(data.get('subtitle')),
	206	'duration': duration,
	207	'timestamp': start,
0146c6cd	208	'ext': 'mp3',
aca2fd22 S	209	'series': data.get('programTitle'),
aca2fd22 S	210	})
eb368012 S	211
	212	return {
	213	'_type': 'playlist',
	214	'id': show_id,
aca2fd22 S	215	'title': data.get('title'),
	216	'description': clean_html(data.get('subtitle')),
	217	'entries': entries,
5f6a1245	218	}
14137b57 S	219
14137b57 S	220
efe93167	221	class ORFFM4IE(ORFRadioIE):
	222	IE_NAME = 'orf:fm4'
	223	IE_DESC = 'radio FM4'
9ba179c1	224	_VALID_URL = r'https?://(?P<station>fm4)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>4\w+)'
13283058	225	_API_STATION = 'fm4'
13283058	226	_LOOP_STATION = 'fm4'
efe93167	227
1339ecb2	228	_TEST = {
9ba179c1	229	'url': 'http://fm4.orf.at/player/20170107/4CC',
1339ecb2 S	230	'md5': '2b0be47375432a7ef104453432a19212',
	231	'info_dict': {
	232	'id': '2017-01-07_2100_tl_54_7DaysSat18_31295',
	233	'ext': 'mp3',
	234	'title': 'Solid Steel Radioshow',
	235	'description': 'Die Mixshow von Coldcut und Ninja Tune.',
	236	'duration': 3599,
	237	'timestamp': 1483819257,
	238	'upload_date': '20170107',
	239	},
aca2fd22 S	240	'skip': 'Shows from ORF radios are only available for 7 days.',
aca2fd22 S	241	'only_matching': True,
1339ecb2	242	}
efe93167	243
efe93167	244
13283058	245	class ORFNOEIE(ORFRadioIE):
	246	IE_NAME = 'orf:noe'
	247	IE_DESC = 'Radio Niederösterreich'
	248	_VALID_URL = r'https?://(?P<station>noe)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
	249	_API_STATION = 'noe'
	250	_LOOP_STATION = 'oe2n'
	251
	252	_TEST = {
	253	'url': 'https://noe.orf.at/player/20200423/NGM',
	254	'only_matching': True,
	255	}
	256
	257
	258	class ORFWIEIE(ORFRadioIE):
	259	IE_NAME = 'orf:wien'
	260	IE_DESC = 'Radio Wien'
	261	_VALID_URL = r'https?://(?P<station>wien)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
	262	_API_STATION = 'wie'
	263	_LOOP_STATION = 'oe2w'
	264
	265	_TEST = {
	266	'url': 'https://wien.orf.at/player/20200423/WGUM',
	267	'only_matching': True,
	268	}
	269
	270
	271	class ORFBGLIE(ORFRadioIE):
	272	IE_NAME = 'orf:burgenland'
	273	IE_DESC = 'Radio Burgenland'
	274	_VALID_URL = r'https?://(?P<station>burgenland)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
	275	_API_STATION = 'bgl'
	276	_LOOP_STATION = 'oe2b'
	277
	278	_TEST = {
	279	'url': 'https://burgenland.orf.at/player/20200423/BGM',
	280	'only_matching': True,
	281	}
	282
	283
	284	class ORFOOEIE(ORFRadioIE):
	285	IE_NAME = 'orf:oberoesterreich'
	286	IE_DESC = 'Radio Oberösterreich'
	287	_VALID_URL = r'https?://(?P<station>ooe)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
	288	_API_STATION = 'ooe'
	289	_LOOP_STATION = 'oe2o'
	290
	291	_TEST = {
	292	'url': 'https://ooe.orf.at/player/20200423/OGMO',
	293	'only_matching': True,
	294	}
	295
	296
	297	class ORFSTMIE(ORFRadioIE):
	298	IE_NAME = 'orf:steiermark'
	299	IE_DESC = 'Radio Steiermark'
	300	_VALID_URL = r'https?://(?P<station>steiermark)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
	301	_API_STATION = 'stm'
	302	_LOOP_STATION = 'oe2st'
	303
	304	_TEST = {
	305	'url': 'https://steiermark.orf.at/player/20200423/STGMS',
	306	'only_matching': True,
	307	}
	308
309
310	class ORFKTNIE(ORFRadioIE):
311	IE_NAME = 'orf:kaernten'
312	IE_DESC = 'Radio Kärnten'
313	_VALID_URL = r'https?://(?P<station>kaernten)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
314	_API_STATION = 'ktn'
315	_LOOP_STATION = 'oe2k'
316
317	_TEST = {
318	'url': 'https://kaernten.orf.at/player/20200423/KGUMO',
319	'only_matching': True,
320	}
321
322
323	class ORFSBGIE(ORFRadioIE):
324	IE_NAME = 'orf:salzburg'
325	IE_DESC = 'Radio Salzburg'
326	_VALID_URL = r'https?://(?P<station>salzburg)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
327	_API_STATION = 'sbg'
328	_LOOP_STATION = 'oe2s'
329
330	_TEST = {
331	'url': 'https://salzburg.orf.at/player/20200423/SGUM',
332	'only_matching': True,
333	}
334
335
336	class ORFTIRIE(ORFRadioIE):
337	IE_NAME = 'orf:tirol'
338	IE_DESC = 'Radio Tirol'
339	_VALID_URL = r'https?://(?P<station>tirol)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
340	_API_STATION = 'tir'
341	_LOOP_STATION = 'oe2t'
342
343	_TEST = {
344	'url': 'https://tirol.orf.at/player/20200423/TGUMO',
345	'only_matching': True,
346	}
347
348
349	class ORFVBGIE(ORFRadioIE):
350	IE_NAME = 'orf:vorarlberg'
351	IE_DESC = 'Radio Vorarlberg'
352	_VALID_URL = r'https?://(?P<station>vorarlberg)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
353	_API_STATION = 'vbg'
354	_LOOP_STATION = 'oe2v'
355
356	_TEST = {
357	'url': 'https://vorarlberg.orf.at/player/20200423/VGUM',
358	'only_matching': True,
359	}
360
361
362	class ORFOE3IE(ORFRadioIE):
363	IE_NAME = 'orf:oe3'
364	IE_DESC = 'Radio Österreich 3'
365	_VALID_URL = r'https?://(?P<station>oe3)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
366	_API_STATION = 'oe3'
367	_LOOP_STATION = 'oe3'
368
369	_TEST = {
370	'url': 'https://oe3.orf.at/player/20200424/3WEK',
371	'only_matching': True,
372	}
373
374
efe93167	375	class ORFOE1IE(ORFRadioIE):
	376	IE_NAME = 'orf:oe1'
	377	IE_DESC = 'Radio Österreich 1'
1339ecb2	378	_VALID_URL = r'https?://(?P<station>oe1)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
13283058	379	_API_STATION = 'oe1'
13283058	380	_LOOP_STATION = 'oe1'
efe93167	381
1339ecb2 S	382	_TEST = {
	383	'url': 'http://oe1.orf.at/player/20170108/456544',
	384	'md5': '34d8a6e67ea888293741c86a099b745b',
	385	'info_dict': {
	386	'id': '2017-01-08_0759_tl_51_7DaysSun6_256141',
	387	'ext': 'mp3',
	388	'title': 'Morgenjournal',
	389	'duration': 609,
	390	'timestamp': 1483858796,
	391	'upload_date': '20170108',
	392	},
	393	'skip': 'Shows from ORF radios are only available for 7 days.'
	394	}
efe93167	395
efe93167	396
14137b57 S	397	class ORFIPTVIE(InfoExtractor):
	398	IE_NAME = 'orf:iptv'
	399	IE_DESC = 'iptv.ORF.at'
5886b38d	400	_VALID_URL = r'https?://iptv\.orf\.at/(?:#/)?stories/(?P<id>\d+)'
14137b57 S	401
14137b57 S	402	_TEST = {
529d26c3 S	403	'url': 'http://iptv.orf.at/stories/2275236/',
529d26c3 S	404	'md5': 'c8b22af4718a4b4af58342529453e3e5',
14137b57	405	'info_dict': {
529d26c3	406	'id': '350612',
14137b57	407	'ext': 'flv',
529d26c3 S	408	'title': 'Weitere Evakuierungen um Vulkan Calbuco',
	409	'description': 'md5:d689c959bdbcf04efeddedbf2299d633',
	410	'duration': 68.197,
ec85ded8	411	'thumbnail': r're:^https?://.*\.jpg$',
529d26c3	412	'upload_date': '20150425',
14137b57 S	413	},
	414	}
	415
	416	def _real_extract(self, url):
	417	story_id = self._match_id(url)
	418
	419	webpage = self._download_webpage(
	420	'http://iptv.orf.at/stories/%s' % story_id, story_id)
	421
	422	video_id = self._search_regex(
	423	r'data-video(?:id)?="(\d+)"', webpage, 'video id')
	424
	425	data = self._download_json(
	426	'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id,
	427	video_id)[0]
	428
	429	duration = float_or_none(data['duration'], 1000)
	430
	431	video = data['sources']['default']
	432	load_balancer_url = video['loadBalancerUrl']
	433	abr = int_or_none(video.get('audioBitrate'))
	434	vbr = int_or_none(video.get('bitrate'))
	435	fps = int_or_none(video.get('videoFps'))
	436	width = int_or_none(video.get('videoWidth'))
	437	height = int_or_none(video.get('videoHeight'))
	438	thumbnail = video.get('preview')
	439
	440	rendition = self._download_json(
	441	load_balancer_url, video_id, transform_source=strip_jsonp)
	442
	443	f = {
	444	'abr': abr,
	445	'vbr': vbr,
	446	'fps': fps,
	447	'width': width,
	448	'height': height,
	449	}
	450
	451	formats = []
	452	for format_id, format_url in rendition['redirect'].items():
	453	if format_id == 'rtmp':
	454	ff = f.copy()
	455	ff.update({
	456	'url': format_url,
	457	'format_id': format_id,
	458	})
	459	formats.append(ff)
	460	elif determine_ext(format_url) == 'f4m':
	461	formats.extend(self._extract_f4m_formats(
	462	format_url, video_id, f4m_id=format_id))
	463	elif determine_ext(format_url) == 'm3u8':
	464	formats.extend(self._extract_m3u8_formats(
	465	format_url, video_id, 'mp4', m3u8_id=format_id))
	466	else:
	467	continue
	468	self._sort_formats(formats)
	469
	470	title = remove_end(self._og_search_title(webpage), ' - iptv.ORF.at')
	471	description = self._og_search_description(webpage)
	472	upload_date = unified_strdate(self._html_search_meta(
	473	'dc.date', webpage, 'upload date'))
	474
	475	return {
	476	'id': video_id,
477	'title': title,
478	'description': description,
479	'duration': duration,
480	'thumbnail': thumbnail,
481	'upload_date': upload_date,
482	'formats': formats,
483	}
0732a905 PH	484
	485
	486	class ORFFM4StoryIE(InfoExtractor):
	487	IE_NAME = 'orf:fm4:story'
	488	IE_DESC = 'fm4.orf.at stories'
	489	_VALID_URL = r'https?://fm4\.orf\.at/stories/(?P<id>\d+)'
	490
	491	_TEST = {
	492	'url': 'http://fm4.orf.at/stories/2865738/',
	493	'playlist': [{
	494	'md5': 'e1c2c706c45c7b34cf478bbf409907ca',
	495	'info_dict': {
	496	'id': '547792',
	497	'ext': 'flv',
	498	'title': 'Manu Delago und Inner Tongue live',
	499	'description': 'Manu Delago und Inner Tongue haben bei der FM4 Soundpark Session live alles gegeben. Hier gibt es Fotos und die gesamte Session als Video.',
	500	'duration': 1748.52,
	501	'thumbnail': r're:^https?://.*\.jpg$',
	502	'upload_date': '20170913',
	503	},
	504	}, {
	505	'md5': 'c6dd2179731f86f4f55a7b49899d515f',
	506	'info_dict': {
	507	'id': '547798',
	508	'ext': 'flv',
	509	'title': 'Manu Delago und Inner Tongue live (2)',
	510	'duration': 1504.08,
	511	'thumbnail': r're:^https?://.*\.jpg$',
	512	'upload_date': '20170913',
	513	'description': 'Manu Delago und Inner Tongue haben bei der FM4 Soundpark Session live alles gegeben. Hier gibt es Fotos und die gesamte Session als Video.',
	514	},
	515	}],
	516	}
	517
	518	def _real_extract(self, url):
	519	story_id = self._match_id(url)
	520	webpage = self._download_webpage(url, story_id)
	521
	522	entries = []
	523	all_ids = orderedSet(re.findall(r'data-video(?:id)?="(\d+)"', webpage))
	524	for idx, video_id in enumerate(all_ids):
	525	data = self._download_json(
	526	'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id,
	527	video_id)[0]
	528
	529	duration = float_or_none(data['duration'], 1000)
	530
	531	video = data['sources']['q8c']
	532	load_balancer_url = video['loadBalancerUrl']
	533	abr = int_or_none(video.get('audioBitrate'))
	534	vbr = int_or_none(video.get('bitrate'))
	535	fps = int_or_none(video.get('videoFps'))
	536	width = int_or_none(video.get('videoWidth'))
	537	height = int_or_none(video.get('videoHeight'))
	538	thumbnail = video.get('preview')
	539
	540	rendition = self._download_json(
	541	load_balancer_url, video_id, transform_source=strip_jsonp)
	542
	543	f = {
	544	'abr': abr,
	545	'vbr': vbr,
	546	'fps': fps,
	547	'width': width,
548	'height': height,
549	}
550
551	formats = []
552	for format_id, format_url in rendition['redirect'].items():
553	if format_id == 'rtmp':
554	ff = f.copy()
555	ff.update({
556	'url': format_url,
557	'format_id': format_id,
558	})
559	formats.append(ff)
560	elif determine_ext(format_url) == 'f4m':
561	formats.extend(self._extract_f4m_formats(
562	format_url, video_id, f4m_id=format_id))
563	elif determine_ext(format_url) == 'm3u8':
564	formats.extend(self._extract_m3u8_formats(
565	format_url, video_id, 'mp4', m3u8_id=format_id))
566	else:
567	continue
568	self._sort_formats(formats)
569
570	title = remove_end(self._og_search_title(webpage), ' - fm4.ORF.at')
571	if idx >= 1:
572	# Titles are duplicates, make them unique
573	title += ' (' + str(idx + 1) + ')'
574	description = self._og_search_description(webpage)
575	upload_date = unified_strdate(self._html_search_meta(
576	'dc.date', webpage, 'upload date'))
577
578	entries.append({
579	'id': video_id,
580	'title': title,
581	'description': description,
582	'duration': duration,
583	'thumbnail': thumbnail,
584	'upload_date': upload_date,
585	'formats': formats,
586	})
587
588	return self.playlist_result(entries)