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

import base64
import functools
import re

from .common import InfoExtractor
from ..utils import (
    clean_html,
    determine_ext,
    float_or_none,
    int_or_none,
    make_archive_id,
    mimetype2ext,
    orderedSet,
    parse_age_limit,
    remove_end,
    strip_jsonp,
    try_call,
    unified_strdate,
    url_or_none,
)
from ..utils.traversal import traverse_obj


class ORFRadioIE(InfoExtractor):
    IE_NAME = 'orf:radio'

    STATION_INFO = {
        'fm4': ('fm4', 'fm4', 'orffm4'),
        'noe': ('noe', 'oe2n', 'orfnoe'),
        'wien': ('wie', 'oe2w', 'orfwie'),
        'burgenland': ('bgl', 'oe2b', 'orfbgl'),
        'ooe': ('ooe', 'oe2o', 'orfooe'),
        'steiermark': ('stm', 'oe2st', 'orfstm'),
        'kaernten': ('ktn', 'oe2k', 'orfktn'),
        'salzburg': ('sbg', 'oe2s', 'orfsbg'),
        'tirol': ('tir', 'oe2t', 'orftir'),
        'vorarlberg': ('vbg', 'oe2v', 'orfvbg'),
        'oe3': ('oe3', 'oe3', 'orfoe3'),
        'oe1': ('oe1', 'oe1', 'orfoe1'),
    }
    _STATION_RE = '|'.join(map(re.escape, STATION_INFO.keys()))

    _VALID_URL = rf'''(?x)
        https?://(?:
            (?P<station>{_STATION_RE})\.orf\.at/player|
            radiothek\.orf\.at/(?P<station2>{_STATION_RE})
        )/(?P<date>[0-9]+)/(?P<show>\w+)'''

    _TESTS = [{
        'url': 'https://radiothek.orf.at/ooe/20220801/OGMO',
        'info_dict': {
            'id': 'OGMO',
            'title': 'Guten Morgen OÖ',
            'description': 'md5:a3f6083399ef92b8cbe2d421b180835a',
        },
        'playlist': [{
            'md5': 'f33147d954a326e338ea52572c2810e8',
            'info_dict': {
                'id': '2022-08-01_0459_tl_66_7DaysMon1_319062',
                'ext': 'mp3',
                'title': 'Guten Morgen OÖ',
                'upload_date': '20220801',
                'duration': 18000,
                'timestamp': 1659322789,
                'description': 'md5:a3f6083399ef92b8cbe2d421b180835a',
            }
        }]
    }, {
        'url': 'https://ooe.orf.at/player/20220801/OGMO',
        'info_dict': {
            'id': 'OGMO',
            'title': 'Guten Morgen OÖ',
            'description': 'md5:a3f6083399ef92b8cbe2d421b180835a',
        },
        'playlist': [{
            'md5': 'f33147d954a326e338ea52572c2810e8',
            'info_dict': {
                'id': '2022-08-01_0459_tl_66_7DaysMon1_319062',
                'ext': 'mp3',
                'title': 'Guten Morgen OÖ',
                'upload_date': '20220801',
                'duration': 18000,
                'timestamp': 1659322789,
                'description': 'md5:a3f6083399ef92b8cbe2d421b180835a',
            }
        }]
    }, {
        'url': 'http://fm4.orf.at/player/20170107/4CC',
        'only_matching': True,
    }, {
        'url': 'https://noe.orf.at/player/20200423/NGM',
        'only_matching': True,
    }, {
        'url': 'https://wien.orf.at/player/20200423/WGUM',
        'only_matching': True,
    }, {
        'url': 'https://burgenland.orf.at/player/20200423/BGM',
        'only_matching': True,
    }, {
        'url': 'https://steiermark.orf.at/player/20200423/STGMS',
        'only_matching': True,
    }, {
        'url': 'https://kaernten.orf.at/player/20200423/KGUMO',
        'only_matching': True,
    }, {
        'url': 'https://salzburg.orf.at/player/20200423/SGUM',
        'only_matching': True,
    }, {
        'url': 'https://tirol.orf.at/player/20200423/TGUMO',
        'only_matching': True,
    }, {
        'url': 'https://vorarlberg.orf.at/player/20200423/VGUM',
        'only_matching': True,
    }, {
        'url': 'https://oe3.orf.at/player/20200424/3WEK',
        'only_matching': True,
    }, {
        '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.'
    }]

    def _entries(self, data, station):
        _, loop_station, old_ie = self.STATION_INFO[station]
        for info in data['streams']:
            item_id = info.get('loopStreamId')
            if not item_id:
                continue
            video_id = item_id.replace('.mp3', '')
            yield {
                'id': video_id,
                'ext': 'mp3',
                'url': f'https://loopstream01.apa.at/?channel={loop_station}&id={item_id}',
                '_old_archive_ids': [make_archive_id(old_ie, video_id)],
                'title': data.get('title'),
                'description': clean_html(data.get('subtitle')),
                'duration': try_call(lambda: (info['end'] - info['start']) / 1000),
                'timestamp': int_or_none(info.get('start'), scale=1000),
                'series': data.get('programTitle'),
            }

    def _real_extract(self, url):
        station, station2, show_date, show_id = self._match_valid_url(url).group('station', 'station2', 'date', 'show')
        api_station, _, _ = self.STATION_INFO[station or station2]
        data = self._download_json(
            f'http://audioapi.orf.at/{api_station}/api/json/current/broadcast/{show_id}/{show_date}', show_id)

        return self.playlist_result(
            self._entries(data, station or station2), show_id, data.get('title'), clean_html(data.get('subtitle')))


class ORFPodcastIE(InfoExtractor):
    IE_NAME = 'orf:podcast'
    _STATION_RE = '|'.join(map(re.escape, (
        'bgl', 'fm4', 'ktn', 'noe', 'oe1', 'oe3',
        'ooe', 'sbg', 'stm', 'tir', 'tv', 'vbg', 'wie')))
    _VALID_URL = rf'https?://sound\.orf\.at/podcast/(?P<station>{_STATION_RE})/(?P<show>[\w-]+)/(?P<id>[\w-]+)'
    _TESTS = [{
        'url': 'https://sound.orf.at/podcast/oe3/fruehstueck-bei-mir/nicolas-stockhammer-15102023',
        'md5': '526a5700e03d271a1505386a8721ab9b',
        'info_dict': {
            'id': 'nicolas-stockhammer-15102023',
            'ext': 'mp3',
            'title': 'Nicolas Stockhammer (15.10.2023)',
            'duration': 3396.0,
            'series': 'Frühstück bei mir',
        },
        'skip': 'ORF podcasts are only available for a limited time'
    }]

    def _real_extract(self, url):
        station, show, show_id = self._match_valid_url(url).group('station', 'show', 'id')
        data = self._download_json(
            f'https://audioapi.orf.at/radiothek/api/2.0/podcast/{station}/{show}/{show_id}', show_id)

        return {
            'id': show_id,
            'ext': 'mp3',
            'vcodec': 'none',
            **traverse_obj(data, ('payload', {
                'url': ('enclosures', 0, 'url'),
                'ext': ('enclosures', 0, 'type', {mimetype2ext}),
                'title': 'title',
                'description': ('description', {clean_html}),
                'duration': ('duration', {functools.partial(float_or_none, scale=1000)}),
                'series': ('podcast', 'title'),
            })),
        }


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

        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

            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)


class ORFONIE(InfoExtractor):
    IE_NAME = 'orf:on'
    _VALID_URL = r'https?://on\.orf\.at/video/(?P<id>\d+)'
    _TESTS = [{
        'url': 'https://on.orf.at/video/14210000/school-of-champions-48',
        'info_dict': {
            'id': '14210000',
            'ext': 'mp4',
            'duration': 2651.08,
            'thumbnail': 'https://api-tvthek.orf.at/assets/segments/0167/98/thumb_16697671_segments_highlight_teaser.jpeg',
            'title': 'School of Champions (4/8)',
            'description': 'md5:d09ad279fc2e8502611e7648484b6afd',
            'media_type': 'episode',
            'timestamp': 1706472362,
            'upload_date': '20240128',
            '_old_archive_ids': ['orftvthek 14210000'],
        }
    }, {
        'url': 'https://on.orf.at/video/3220355',
        'md5': 'f94d98e667cf9a3851317efb4e136662',
        'info_dict': {
            'id': '3220355',
            'ext': 'mp4',
            'duration': 445.04,
            'thumbnail': 'https://api-tvthek.orf.at/assets/segments/0002/60/thumb_159573_segments_highlight_teaser.png',
            'title': '50 Jahre Burgenland: Der Festumzug',
            'description': 'md5:1560bf855119544ee8c4fa5376a2a6b0',
            'media_type': 'episode',
            'timestamp': 52916400,
            'upload_date': '19710905',
            '_old_archive_ids': ['orftvthek 3220355'],
        }
    }]

    def _extract_video(self, video_id):
        encrypted_id = base64.b64encode(f'3dSlfek03nsLKdj4Jsd{video_id}'.encode()).decode()
        api_json = self._download_json(
            f'https://api-tvthek.orf.at/api/v4.3/public/episode/encrypted/{encrypted_id}', video_id)

        if traverse_obj(api_json, 'is_drm_protected'):
            self.report_drm(video_id)

        formats, subtitles = [], {}
        for manifest_type in traverse_obj(api_json, ('sources', {dict.keys}, ...)):
            for manifest_url in traverse_obj(api_json, ('sources', manifest_type, ..., 'src', {url_or_none})):
                if manifest_type == 'hls':
                    fmts, subs = self._extract_m3u8_formats_and_subtitles(
                        manifest_url, video_id, fatal=False, m3u8_id='hls')
                elif manifest_type == 'dash':
                    fmts, subs = self._extract_mpd_formats_and_subtitles(
                        manifest_url, video_id, fatal=False, mpd_id='dash')
                else:
                    continue
                formats.extend(fmts)
                self._merge_subtitles(subs, target=subtitles)

        for sub_url in traverse_obj(api_json, (
                '_embedded', 'subtitle',
                ('xml_url', 'sami_url', 'stl_url', 'ttml_url', 'srt_url', 'vtt_url'), {url_or_none})):
            self._merge_subtitles({'de': [{'url': sub_url}]}, target=subtitles)

        return {
            'id': video_id,
            'formats': formats,
            'subtitles': subtitles,
            '_old_archive_ids': [make_archive_id('ORFTVthek', video_id)],
            **traverse_obj(api_json, {
                'age_limit': ('age_classification', {parse_age_limit}),
                'duration': ('duration_second', {float_or_none}),
                'title': (('title', 'headline'), {str}),
                'description': (('description', 'teaser_text'), {str}),
                'media_type': ('video_type', {str}),
            }, get_all=False),
        }

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

        return {
            'id': video_id,
            'title': self._html_search_meta(['og:title', 'twitter:title'], webpage, default=None),
            'description': self._html_search_meta(
                ['description', 'og:description', 'twitter:description'], webpage, default=None),
            **self._search_json_ld(webpage, video_id, fatal=False),
            **self._extract_video(video_id),
        }
Commit	Line	Data
a0d50aab	1	import base64
b695e3f9	2	import functools
5d73273f	3	import re
54543467 JMF	4
	5	from .common import InfoExtractor
	6	from ..utils import (
aca2fd22	7	clean_html,
0732a905 PH	8	determine_ext,
0732a905 PH	9	float_or_none,
14137b57	10	int_or_none,
6ba30856 E	11	make_archive_id,
6ba30856 E	12	mimetype2ext,
0732a905	13	orderedSet,
0dd53fae	14	parse_age_limit,
14137b57	15	remove_end,
0732a905	16	strip_jsonp,
5770293d	17	try_call,
0732a905	18	unified_strdate,
4b6aca17	19	url_or_none,
54543467	20	)
6ba30856	21	from ..utils.traversal import traverse_obj
54543467	22
5d73273f	23
efe93167	24	class ORFRadioIE(InfoExtractor):
5770293d	25	IE_NAME = 'orf:radio'
	26
	27	STATION_INFO = {
	28	'fm4': ('fm4', 'fm4', 'orffm4'),
	29	'noe': ('noe', 'oe2n', 'orfnoe'),
	30	'wien': ('wie', 'oe2w', 'orfwie'),
	31	'burgenland': ('bgl', 'oe2b', 'orfbgl'),
	32	'ooe': ('ooe', 'oe2o', 'orfooe'),
	33	'steiermark': ('stm', 'oe2st', 'orfstm'),
	34	'kaernten': ('ktn', 'oe2k', 'orfktn'),
	35	'salzburg': ('sbg', 'oe2s', 'orfsbg'),
	36	'tirol': ('tir', 'oe2t', 'orftir'),
	37	'vorarlberg': ('vbg', 'oe2v', 'orfvbg'),
	38	'oe3': ('oe3', 'oe3', 'orfoe3'),
	39	'oe1': ('oe1', 'oe1', 'orfoe1'),
	40	}
	41	_STATION_RE = '\|'.join(map(re.escape, STATION_INFO.keys()))
eb368012	42
5770293d	43	_VALID_URL = rf'''(?x)
	44	https?://(?:
	45	(?P<station>{_STATION_RE})\.orf\.at/player\|
	46	radiothek\.orf\.at/(?P<station2>{_STATION_RE})
	47	)/(?P<date>[0-9]+)/(?P<show>\w+)'''
aca2fd22	48
5770293d	49	_TESTS = [{
	50	'url': 'https://radiothek.orf.at/ooe/20220801/OGMO',
	51	'info_dict': {
	52	'id': 'OGMO',
	53	'title': 'Guten Morgen OÖ',
	54	'description': 'md5:a3f6083399ef92b8cbe2d421b180835a',
	55	},
	56	'playlist': [{
	57	'md5': 'f33147d954a326e338ea52572c2810e8',
	58	'info_dict': {
	59	'id': '2022-08-01_0459_tl_66_7DaysMon1_319062',
0146c6cd	60	'ext': 'mp3',
5770293d	61	'title': 'Guten Morgen OÖ',
	62	'upload_date': '20220801',
	63	'duration': 18000,
	64	'timestamp': 1659322789,
	65	'description': 'md5:a3f6083399ef92b8cbe2d421b180835a',
	66	}
	67	}]
	68	}, {
	69	'url': 'https://ooe.orf.at/player/20220801/OGMO',
1339ecb2	70	'info_dict': {
5770293d	71	'id': 'OGMO',
	72	'title': 'Guten Morgen OÖ',
	73	'description': 'md5:a3f6083399ef92b8cbe2d421b180835a',
1339ecb2	74	},
5770293d	75	'playlist': [{
	76	'md5': 'f33147d954a326e338ea52572c2810e8',
	77	'info_dict': {
	78	'id': '2022-08-01_0459_tl_66_7DaysMon1_319062',
	79	'ext': 'mp3',
	80	'title': 'Guten Morgen OÖ',
	81	'upload_date': '20220801',
	82	'duration': 18000,
	83	'timestamp': 1659322789,
	84	'description': 'md5:a3f6083399ef92b8cbe2d421b180835a',
	85	}
	86	}]
	87	}, {
	88	'url': 'http://fm4.orf.at/player/20170107/4CC',
aca2fd22	89	'only_matching': True,
5770293d	90	}, {
13283058	91	'url': 'https://noe.orf.at/player/20200423/NGM',
13283058	92	'only_matching': True,
5770293d	93	}, {
13283058	94	'url': 'https://wien.orf.at/player/20200423/WGUM',
13283058	95	'only_matching': True,
5770293d	96	}, {
13283058	97	'url': 'https://burgenland.orf.at/player/20200423/BGM',
13283058	98	'only_matching': True,
5770293d	99	}, {
13283058	100	'url': 'https://steiermark.orf.at/player/20200423/STGMS',
13283058	101	'only_matching': True,
5770293d	102	}, {
13283058	103	'url': 'https://kaernten.orf.at/player/20200423/KGUMO',
13283058	104	'only_matching': True,
5770293d	105	}, {
13283058	106	'url': 'https://salzburg.orf.at/player/20200423/SGUM',
13283058	107	'only_matching': True,
5770293d	108	}, {
13283058	109	'url': 'https://tirol.orf.at/player/20200423/TGUMO',
13283058	110	'only_matching': True,
5770293d	111	}, {
13283058	112	'url': 'https://vorarlberg.orf.at/player/20200423/VGUM',
13283058	113	'only_matching': True,
5770293d	114	}, {
13283058	115	'url': 'https://oe3.orf.at/player/20200424/3WEK',
13283058	116	'only_matching': True,
5770293d	117	}, {
1339ecb2 S	118	'url': 'http://oe1.orf.at/player/20170108/456544',
	119	'md5': '34d8a6e67ea888293741c86a099b745b',
	120	'info_dict': {
	121	'id': '2017-01-08_0759_tl_51_7DaysSun6_256141',
	122	'ext': 'mp3',
	123	'title': 'Morgenjournal',
	124	'duration': 609,
	125	'timestamp': 1483858796,
	126	'upload_date': '20170108',
	127	},
	128	'skip': 'Shows from ORF radios are only available for 7 days.'
5770293d	129	}]
	130
	131	def _entries(self, data, station):
	132	_, loop_station, old_ie = self.STATION_INFO[station]
	133	for info in data['streams']:
	134	item_id = info.get('loopStreamId')
	135	if not item_id:
	136	continue
	137	video_id = item_id.replace('.mp3', '')
	138	yield {
	139	'id': video_id,
	140	'ext': 'mp3',
	141	'url': f'https://loopstream01.apa.at/?channel={loop_station}&id={item_id}',
	142	'_old_archive_ids': [make_archive_id(old_ie, video_id)],
	143	'title': data.get('title'),
	144	'description': clean_html(data.get('subtitle')),
	145	'duration': try_call(lambda: (info['end'] - info['start']) / 1000),
	146	'timestamp': int_or_none(info.get('start'), scale=1000),
	147	'series': data.get('programTitle'),
	148	}
	149
	150	def _real_extract(self, url):
	151	station, station2, show_date, show_id = self._match_valid_url(url).group('station', 'station2', 'date', 'show')
	152	api_station, _, _ = self.STATION_INFO[station or station2]
	153	data = self._download_json(
	154	f'http://audioapi.orf.at/{api_station}/api/json/current/broadcast/{show_id}/{show_date}', show_id)
	155
	156	return self.playlist_result(
	157	self._entries(data, station or station2), show_id, data.get('title'), clean_html(data.get('subtitle')))
efe93167	158
efe93167	159
6ba30856 E	160	class ORFPodcastIE(InfoExtractor):
	161	IE_NAME = 'orf:podcast'
	162	_STATION_RE = '\|'.join(map(re.escape, (
	163	'bgl', 'fm4', 'ktn', 'noe', 'oe1', 'oe3',
	164	'ooe', 'sbg', 'stm', 'tir', 'tv', 'vbg', 'wie')))
	165	_VALID_URL = rf'https?://sound\.orf\.at/podcast/(?P<station>{_STATION_RE})/(?P<show>[\w-]+)/(?P<id>[\w-]+)'
	166	_TESTS = [{
	167	'url': 'https://sound.orf.at/podcast/oe3/fruehstueck-bei-mir/nicolas-stockhammer-15102023',
	168	'md5': '526a5700e03d271a1505386a8721ab9b',
	169	'info_dict': {
	170	'id': 'nicolas-stockhammer-15102023',
	171	'ext': 'mp3',
	172	'title': 'Nicolas Stockhammer (15.10.2023)',
	173	'duration': 3396.0,
	174	'series': 'Frühstück bei mir',
	175	},
	176	'skip': 'ORF podcasts are only available for a limited time'
	177	}]
	178
	179	def _real_extract(self, url):
	180	station, show, show_id = self._match_valid_url(url).group('station', 'show', 'id')
	181	data = self._download_json(
	182	f'https://audioapi.orf.at/radiothek/api/2.0/podcast/{station}/{show}/{show_id}', show_id)
	183
	184	return {
	185	'id': show_id,
	186	'ext': 'mp3',
	187	'vcodec': 'none',
	188	**traverse_obj(data, ('payload', {
	189	'url': ('enclosures', 0, 'url'),
	190	'ext': ('enclosures', 0, 'type', {mimetype2ext}),
	191	'title': 'title',
	192	'description': ('description', {clean_html}),
	193	'duration': ('duration', {functools.partial(float_or_none, scale=1000)}),
	194	'series': ('podcast', 'title'),
	195	})),
	196	}
	197
	198
14137b57 S	199	class ORFIPTVIE(InfoExtractor):
	200	IE_NAME = 'orf:iptv'
	201	IE_DESC = 'iptv.ORF.at'
5886b38d	202	_VALID_URL = r'https?://iptv\.orf\.at/(?:#/)?stories/(?P<id>\d+)'
14137b57 S	203
14137b57 S	204	_TEST = {
529d26c3 S	205	'url': 'http://iptv.orf.at/stories/2275236/',
529d26c3 S	206	'md5': 'c8b22af4718a4b4af58342529453e3e5',
14137b57	207	'info_dict': {
529d26c3	208	'id': '350612',
14137b57	209	'ext': 'flv',
529d26c3 S	210	'title': 'Weitere Evakuierungen um Vulkan Calbuco',
	211	'description': 'md5:d689c959bdbcf04efeddedbf2299d633',
	212	'duration': 68.197,
ec85ded8	213	'thumbnail': r're:^https?://.*\.jpg$',
529d26c3	214	'upload_date': '20150425',
14137b57 S	215	},
	216	}
	217
	218	def _real_extract(self, url):
	219	story_id = self._match_id(url)
	220
	221	webpage = self._download_webpage(
	222	'http://iptv.orf.at/stories/%s' % story_id, story_id)
	223
	224	video_id = self._search_regex(
	225	r'data-video(?:id)?="(\d+)"', webpage, 'video id')
	226
	227	data = self._download_json(
	228	'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id,
	229	video_id)[0]
	230
	231	duration = float_or_none(data['duration'], 1000)
	232
	233	video = data['sources']['default']
	234	load_balancer_url = video['loadBalancerUrl']
	235	abr = int_or_none(video.get('audioBitrate'))
	236	vbr = int_or_none(video.get('bitrate'))
	237	fps = int_or_none(video.get('videoFps'))
	238	width = int_or_none(video.get('videoWidth'))
	239	height = int_or_none(video.get('videoHeight'))
	240	thumbnail = video.get('preview')
	241
	242	rendition = self._download_json(
	243	load_balancer_url, video_id, transform_source=strip_jsonp)
	244
	245	f = {
	246	'abr': abr,
	247	'vbr': vbr,
	248	'fps': fps,
	249	'width': width,
	250	'height': height,
	251	}
	252
	253	formats = []
	254	for format_id, format_url in rendition['redirect'].items():
	255	if format_id == 'rtmp':
	256	ff = f.copy()
	257	ff.update({
	258	'url': format_url,
	259	'format_id': format_id,
	260	})
	261	formats.append(ff)
	262	elif determine_ext(format_url) == 'f4m':
	263	formats.extend(self._extract_f4m_formats(
	264	format_url, video_id, f4m_id=format_id))
	265	elif determine_ext(format_url) == 'm3u8':
	266	formats.extend(self._extract_m3u8_formats(
	267	format_url, video_id, 'mp4', m3u8_id=format_id))
	268	else:
	269	continue
14137b57 S	270
	271	title = remove_end(self._og_search_title(webpage), ' - iptv.ORF.at')
	272	description = self._og_search_description(webpage)
	273	upload_date = unified_strdate(self._html_search_meta(
	274	'dc.date', webpage, 'upload date'))
	275
	276	return {
	277	'id': video_id,
	278	'title': title,
	279	'description': description,
	280	'duration': duration,
	281	'thumbnail': thumbnail,
	282	'upload_date': upload_date,
	283	'formats': formats,
	284	}
0732a905 PH	285
	286
	287	class ORFFM4StoryIE(InfoExtractor):
	288	IE_NAME = 'orf:fm4:story'
	289	IE_DESC = 'fm4.orf.at stories'
	290	_VALID_URL = r'https?://fm4\.orf\.at/stories/(?P<id>\d+)'
	291
	292	_TEST = {
	293	'url': 'http://fm4.orf.at/stories/2865738/',
	294	'playlist': [{
	295	'md5': 'e1c2c706c45c7b34cf478bbf409907ca',
	296	'info_dict': {
	297	'id': '547792',
	298	'ext': 'flv',
	299	'title': 'Manu Delago und Inner Tongue live',
	300	'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.',
	301	'duration': 1748.52,
	302	'thumbnail': r're:^https?://.*\.jpg$',
	303	'upload_date': '20170913',
	304	},
	305	}, {
	306	'md5': 'c6dd2179731f86f4f55a7b49899d515f',
	307	'info_dict': {
	308	'id': '547798',
	309	'ext': 'flv',
	310	'title': 'Manu Delago und Inner Tongue live (2)',
	311	'duration': 1504.08,
	312	'thumbnail': r're:^https?://.*\.jpg$',
	313	'upload_date': '20170913',
	314	'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.',
	315	},
	316	}],
	317	}
	318
	319	def _real_extract(self, url):
	320	story_id = self._match_id(url)
	321	webpage = self._download_webpage(url, story_id)
	322
	323	entries = []
	324	all_ids = orderedSet(re.findall(r'data-video(?:id)?="(\d+)"', webpage))
	325	for idx, video_id in enumerate(all_ids):
	326	data = self._download_json(
	327	'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id,
	328	video_id)[0]
	329
	330	duration = float_or_none(data['duration'], 1000)
	331
	332	video = data['sources']['q8c']
	333	load_balancer_url = video['loadBalancerUrl']
	334	abr = int_or_none(video.get('audioBitrate'))
	335	vbr = int_or_none(video.get('bitrate'))
	336	fps = int_or_none(video.get('videoFps'))
	337	width = int_or_none(video.get('videoWidth'))
	338	height = int_or_none(video.get('videoHeight'))
	339	thumbnail = video.get('preview')
	340
	341	rendition = self._download_json(
	342	load_balancer_url, video_id, transform_source=strip_jsonp)
	343
	344	f = {
	345	'abr': abr,
	346	'vbr': vbr,
	347	'fps': fps,
	348	'width': width,
349	'height': height,
350	}
351
352	formats = []
353	for format_id, format_url in rendition['redirect'].items():
354	if format_id == 'rtmp':
355	ff = f.copy()
356	ff.update({
357	'url': format_url,
358	'format_id': format_id,
359	})
360	formats.append(ff)
361	elif determine_ext(format_url) == 'f4m':
362	formats.extend(self._extract_f4m_formats(
363	format_url, video_id, f4m_id=format_id))
364	elif determine_ext(format_url) == 'm3u8':
365	formats.extend(self._extract_m3u8_formats(
366	format_url, video_id, 'mp4', m3u8_id=format_id))
367	else:
368	continue
0732a905 PH	369
	370	title = remove_end(self._og_search_title(webpage), ' - fm4.ORF.at')
	371	if idx >= 1:
	372	# Titles are duplicates, make them unique
	373	title += ' (' + str(idx + 1) + ')'
	374	description = self._og_search_description(webpage)
	375	upload_date = unified_strdate(self._html_search_meta(
	376	'dc.date', webpage, 'upload date'))
	377
	378	entries.append({
	379	'id': video_id,
	380	'title': title,
	381	'description': description,
	382	'duration': duration,
	383	'thumbnail': thumbnail,
	384	'upload_date': upload_date,
	385	'formats': formats,
	386	})
	387
	388	return self.playlist_result(entries)
a0d50aab H	389
	390
	391	class ORFONIE(InfoExtractor):
	392	IE_NAME = 'orf:on'
0dd53fae	393	_VALID_URL = r'https?://on\.orf\.at/video/(?P<id>\d+)'
a0d50aab H	394	_TESTS = [{
	395	'url': 'https://on.orf.at/video/14210000/school-of-champions-48',
	396	'info_dict': {
	397	'id': '14210000',
	398	'ext': 'mp4',
	399	'duration': 2651.08,
	400	'thumbnail': 'https://api-tvthek.orf.at/assets/segments/0167/98/thumb_16697671_segments_highlight_teaser.jpeg',
	401	'title': 'School of Champions (4/8)',
	402	'description': 'md5:d09ad279fc2e8502611e7648484b6afd',
	403	'media_type': 'episode',
	404	'timestamp': 1706472362,
	405	'upload_date': '20240128',
3779f2a3	406	'_old_archive_ids': ['orftvthek 14210000'],
a0d50aab	407	}
0dd53fae T	408	}, {
	409	'url': 'https://on.orf.at/video/3220355',
	410	'md5': 'f94d98e667cf9a3851317efb4e136662',
	411	'info_dict': {
	412	'id': '3220355',
	413	'ext': 'mp4',
	414	'duration': 445.04,
	415	'thumbnail': 'https://api-tvthek.orf.at/assets/segments/0002/60/thumb_159573_segments_highlight_teaser.png',
	416	'title': '50 Jahre Burgenland: Der Festumzug',
	417	'description': 'md5:1560bf855119544ee8c4fa5376a2a6b0',
	418	'media_type': 'episode',
	419	'timestamp': 52916400,
	420	'upload_date': '19710905',
3779f2a3	421	'_old_archive_ids': ['orftvthek 3220355'],
0dd53fae	422	}
a0d50aab H	423	}]
a0d50aab H	424
0dd53fae	425	def _extract_video(self, video_id):
a0d50aab H	426	encrypted_id = base64.b64encode(f'3dSlfek03nsLKdj4Jsd{video_id}'.encode()).decode()
a0d50aab H	427	api_json = self._download_json(
0dd53fae T	428	f'https://api-tvthek.orf.at/api/v4.3/public/episode/encrypted/{encrypted_id}', video_id)
	429
	430	if traverse_obj(api_json, 'is_drm_protected'):
	431	self.report_drm(video_id)
a0d50aab H	432
	433	formats, subtitles = [], {}
	434	for manifest_type in traverse_obj(api_json, ('sources', {dict.keys}, ...)):
	435	for manifest_url in traverse_obj(api_json, ('sources', manifest_type, ..., 'src', {url_or_none})):
	436	if manifest_type == 'hls':
	437	fmts, subs = self._extract_m3u8_formats_and_subtitles(
0dd53fae	438	manifest_url, video_id, fatal=False, m3u8_id='hls')
a0d50aab H	439	elif manifest_type == 'dash':
a0d50aab H	440	fmts, subs = self._extract_mpd_formats_and_subtitles(
0dd53fae	441	manifest_url, video_id, fatal=False, mpd_id='dash')
a0d50aab H	442	else:
	443	continue
	444	formats.extend(fmts)
	445	self._merge_subtitles(subs, target=subtitles)
	446
0dd53fae T	447	for sub_url in traverse_obj(api_json, (
	448	'_embedded', 'subtitle',
	449	('xml_url', 'sami_url', 'stl_url', 'ttml_url', 'srt_url', 'vtt_url'), {url_or_none})):
	450	self._merge_subtitles({'de': [{'url': sub_url}]}, target=subtitles)
	451
a0d50aab H	452	return {
	453	'id': video_id,
	454	'formats': formats,
	455	'subtitles': subtitles,
3779f2a3	456	'_old_archive_ids': [make_archive_id('ORFTVthek', video_id)],
a0d50aab	457	**traverse_obj(api_json, {
0dd53fae	458	'age_limit': ('age_classification', {parse_age_limit}),
a0d50aab H	459	'duration': ('duration_second', {float_or_none}),
	460	'title': (('title', 'headline'), {str}),
	461	'description': (('description', 'teaser_text'), {str}),
	462	'media_type': ('video_type', {str}),
	463	}, get_all=False),
	464	}
	465
	466	def _real_extract(self, url):
0dd53fae T	467	video_id = self._match_id(url)
0dd53fae T	468	webpage = self._download_webpage(url, video_id)
a0d50aab H	469
	470	return {
	471	'id': video_id,
	472	'title': self._html_search_meta(['og:title', 'twitter:title'], webpage, default=None),
	473	'description': self._html_search_meta(
	474	['description', 'og:description', 'twitter:description'], webpage, default=None),
0dd53fae T	475	**self._search_json_ld(webpage, video_id, fatal=False),
0dd53fae T	476	**self._extract_video(video_id),
a0d50aab	477	}