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

import functools
import re

from .common import InfoExtractor
from ..utils import (
    clean_html,
    determine_ext,
    float_or_none,
    HEADRequest,
    InAdvancePagedList,
    int_or_none,
    join_nonempty,
    orderedSet,
    remove_end,
    make_archive_id,
    smuggle_url,
    strip_jsonp,
    try_call,
    unescapeHTML,
    unified_strdate,
    unsmuggle_url,
    url_or_none,
)


class ORFTVthekIE(InfoExtractor):
    IE_NAME = 'orf:tvthek'
    IE_DESC = 'ORF TVthek'
    _VALID_URL = r'(?P<url>https?://tvthek\.orf\.at/(?:(?:[^/]+/){2}){1,2}(?P<id>\d+))(/[^/]+/(?P<vid>\d+))?(?:$|[?#])'

    _TESTS = [{
        'url': 'https://tvthek.orf.at/profile/ZIB-2/1211/ZIB-2/14121079',
        'info_dict': {
            'id': '14121079',
        },
        'playlist_count': 11,
        'params': {'noplaylist': True}
    }, {
        'url': 'https://tvthek.orf.at/profile/ZIB-2/1211/ZIB-2/14121079/Umfrage-Welches-Tier-ist-Sebastian-Kurz/15083150',
        'info_dict': {
            'id': '14121079',
        },
        'playlist_count': 1,
        'params': {'playlist_items': '5'}
    }, {
        'url': 'https://tvthek.orf.at/profile/ZIB-2/1211/ZIB-2/14121079/Umfrage-Welches-Tier-ist-Sebastian-Kurz/15083150',
        'info_dict': {
            'id': '14121079',
            'playlist_count': 1
        },
        'playlist': [{
            'info_dict': {
                'id': '15083150',
                'ext': 'mp4',
                'description': 'md5:7be1c485425f5f255a5e4e4815e77d04',
                'thumbnail': 'https://api-tvthek.orf.at/uploads/media/segments/0130/59/824271ea35cd8931a0fb08ab316a5b0a1562342c.jpeg',
                'title': 'Umfrage: Welches Tier ist Sebastian Kurz?',
            }
        }],
        'playlist_count': 1,
        'params': {'noplaylist': True, 'skip_download': 'm3u8'}
    }, {
        '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 _pagefunc(self, url, data_jsb, n, *, image=None):
        sd = data_jsb[n]
        video_id, title = str(sd['id']), sd['title']
        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, note=f'Downloading {format_id} m3u8 manifest')
                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, note=f'Downloading {format_id} mpd manifest'))
            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')
        http_url = next(
            (f['url'] for f in formats if re.match(r'^https?://.*\.mp4$', f['url'])),
            None) if geo_str else None
        if http_url:
            self._request_webpage(
                HEADRequest(http_url), video_id, fatal=False, note='Testing for geoblocking',
                errnote=f'This video seems to be blocked outside of {geo_str}. You may want to try the streaming-* formats')

        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') or image
        if image:
            thumbnails.append({
                'id': 'full',
                'url': image,
                'preference': 1,
            })

        yield {
            'id': video_id,
            'title': title,
            'webpage_url': smuggle_url(f'{url}/part/{video_id}', {'force_noplaylist': True}),
            'formats': formats,
            'subtitles': subtitles,
            'description': sd.get('description'),
            'duration': int_or_none(sd.get('duration_in_seconds')),
            'upload_date': upload_date,
            'thumbnails': thumbnails,
        }

    def _real_extract(self, url):
        url, smuggled_data = unsmuggle_url(url)
        playlist_id, video_id, base_url = self._match_valid_url(url).group('id', 'vid', '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']

        if not self._yes_playlist(playlist_id, video_id, smuggled_data):
            data_jsb = [sd for sd in data_jsb if str(sd.get('id')) == video_id]

        playlist_count = len(data_jsb)
        image = self._og_search_thumbnail(webpage) if playlist_count == 1 else None

        page_func = functools.partial(self._pagefunc, base_url, data_jsb, image=image)
        return {
            '_type': 'playlist',
            'entries': InAdvancePagedList(page_func, playlist_count, 1),
            'id': playlist_id,
        }


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 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
b695e3f9	1	import functools
5d73273f	2	import re
54543467 JMF	3
	4	from .common import InfoExtractor
	5	from ..utils import (
aca2fd22	6	clean_html,
0732a905 PH	7	determine_ext,
0732a905 PH	8	float_or_none,
5d73273f	9	HEADRequest,
b695e3f9	10	InAdvancePagedList,
14137b57	11	int_or_none,
34921b43	12	join_nonempty,
0732a905	13	orderedSet,
14137b57	14	remove_end,
5770293d	15	make_archive_id,
b695e3f9	16	smuggle_url,
0732a905	17	strip_jsonp,
5770293d	18	try_call,
73c801d6	19	unescapeHTML,
0732a905	20	unified_strdate,
b695e3f9	21	unsmuggle_url,
4b6aca17	22	url_or_none,
54543467 JMF	23	)
54543467 JMF	24
5d73273f	25
eb368012 S	26	class ORFTVthekIE(InfoExtractor):
	27	IE_NAME = 'orf:tvthek'
	28	IE_DESC = 'ORF TVthek'
b695e3f9	29	_VALID_URL = r'(?P<url>https?://tvthek\.orf\.at/(?:(?:[^/]+/){2}){1,2}(?P<id>\d+))(/[^/]+/(?P<vid>\d+))?(?:$\|[?#])'
5d73273f	30
13d27a42	31	_TESTS = [{
b695e3f9	32	'url': 'https://tvthek.orf.at/profile/ZIB-2/1211/ZIB-2/14121079',
	33	'info_dict': {
	34	'id': '14121079',
	35	},
	36	'playlist_count': 11,
	37	'params': {'noplaylist': True}
	38	}, {
	39	'url': 'https://tvthek.orf.at/profile/ZIB-2/1211/ZIB-2/14121079/Umfrage-Welches-Tier-ist-Sebastian-Kurz/15083150',
	40	'info_dict': {
	41	'id': '14121079',
	42	},
	43	'playlist_count': 1,
	44	'params': {'playlist_items': '5'}
	45	}, {
	46	'url': 'https://tvthek.orf.at/profile/ZIB-2/1211/ZIB-2/14121079/Umfrage-Welches-Tier-ist-Sebastian-Kurz/15083150',
	47	'info_dict': {
	48	'id': '14121079',
	49	'playlist_count': 1
	50	},
	51	'playlist': [{
	52	'info_dict': {
	53	'id': '15083150',
	54	'ext': 'mp4',
	55	'description': 'md5:7be1c485425f5f255a5e4e4815e77d04',
	56	'thumbnail': 'https://api-tvthek.orf.at/uploads/media/segments/0130/59/824271ea35cd8931a0fb08ab316a5b0a1562342c.jpeg',
	57	'title': 'Umfrage: Welches Tier ist Sebastian Kurz?',
	58	}
	59	}],
	60	'playlist_count': 1,
	61	'params': {'noplaylist': True, 'skip_download': 'm3u8'}
	62	}, {
a6620ac2 PH	63	'url': 'http://tvthek.orf.at/program/Aufgetischt/2745173/Aufgetischt-Mit-der-Steirischen-Tafelrunde/8891389',
	64	'playlist': [{
	65	'md5': '2942210346ed779588f428a92db88712',
	66	'info_dict': {
	67	'id': '8896777',
	68	'ext': 'mp4',
	69	'title': 'Aufgetischt: Mit der Steirischen Tafelrunde',
	70	'description': 'md5:c1272f0245537812d4e36419c207b67d',
	71	'duration': 2668,
	72	'upload_date': '20141208',
	73	},
	74	}],
13d27a42 PH	75	'skip': 'Blocked outside of Austria / Germany',
	76	}, {
	77	'url': 'http://tvthek.orf.at/topic/Im-Wandel-der-Zeit/8002126/Best-of-Ingrid-Thurnher/7982256',
7b0d333a NP	78	'info_dict': {
	79	'id': '7982259',
	80	'ext': 'mp4',
	81	'title': 'Best of Ingrid Thurnher',
	82	'upload_date': '20140527',
	83	'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".',
	84	},
	85	'params': {
	86	'skip_download': True, # rtsp downloads
	87	},
7512aa98	88	'skip': 'Blocked outside of Austria / Germany',
73c801d6 S	89	}, {
73c801d6 S	90	'url': 'http://tvthek.orf.at/topic/Fluechtlingskrise/10463081/Heimat-Fremde-Heimat/13879132/Senioren-betreuen-Migrantenkinder/13879141',
7512aa98	91	'only_matching': True,
73c801d6 S	92	}, {
73c801d6 S	93	'url': 'http://tvthek.orf.at/profile/Universum/35429',
7512aa98	94	'only_matching': True,
13d27a42	95	}]
54543467	96
b695e3f9	97	def _pagefunc(self, url, data_jsb, n, *, image=None):
	98	sd = data_jsb[n]
	99	video_id, title = str(sd['id']), sd['title']
	100	formats = []
	101	for fd in sd['sources']:
	102	src = url_or_none(fd.get('src'))
	103	if not src:
	104	continue
	105	format_id = join_nonempty('delivery', 'quality', 'quality_string', from_dict=fd)
	106	ext = determine_ext(src)
	107	if ext == 'm3u8':
	108	m3u8_formats = self._extract_m3u8_formats(
	109	src, video_id, 'mp4', m3u8_id=format_id, fatal=False, note=f'Downloading {format_id} m3u8 manifest')
	110	if any('/geoprotection' in f['url'] for f in m3u8_formats):
	111	self.raise_geo_restricted()
	112	formats.extend(m3u8_formats)
	113	elif ext == 'f4m':
	114	formats.extend(self._extract_f4m_formats(
	115	src, video_id, f4m_id=format_id, fatal=False))
	116	elif ext == 'mpd':
	117	formats.extend(self._extract_mpd_formats(
	118	src, video_id, mpd_id=format_id, fatal=False, note=f'Downloading {format_id} mpd manifest'))
	119	else:
	120	formats.append({
	121	'format_id': format_id,
	122	'url': src,
	123	'protocol': fd.get('protocol'),
	124	})
	125
	126	# Check for geoblocking.
	127	# There is a property is_geoprotection, but that's always false
	128	geo_str = sd.get('geoprotection_string')
	129	http_url = next(
	130	(f['url'] for f in formats if re.match(r'^https?://.*\.mp4$', f['url'])),
	131	None) if geo_str else None
	132	if http_url:
	133	self._request_webpage(
	134	HEADRequest(http_url), video_id, fatal=False, note='Testing for geoblocking',
	135	errnote=f'This video seems to be blocked outside of {geo_str}. You may want to try the streaming-* formats')
	136
	137	self._sort_formats(formats)
	138
	139	subtitles = {}
	140	for sub in sd.get('subtitles', []):
	141	sub_src = sub.get('src')
	142	if not sub_src:
	143	continue
	144	subtitles.setdefault(sub.get('lang', 'de-AT'), []).append({
	145	'url': sub_src,
	146	})
	147
	148	upload_date = unified_strdate(sd.get('created_date'))
	149
	150	thumbnails = []
	151	preview = sd.get('preview_image_url')
	152	if preview:
	153	thumbnails.append({
	154	'id': 'preview',
	155	'url': preview,
	156	'preference': 0,
	157	})
	158	image = sd.get('image_full_url') or image
	159	if image:
	160	thumbnails.append({
161	'id': 'full',
162	'url': image,
163	'preference': 1,
164	})
165
166	yield {
167	'id': video_id,
168	'title': title,
169	'webpage_url': smuggle_url(f'{url}/part/{video_id}', {'force_noplaylist': True}),
170	'formats': formats,
171	'subtitles': subtitles,
172	'description': sd.get('description'),
173	'duration': int_or_none(sd.get('duration_in_seconds')),
174	'upload_date': upload_date,
175	'thumbnails': thumbnails,
176	}
177
54543467	178	def _real_extract(self, url):
b695e3f9	179	url, smuggled_data = unsmuggle_url(url)
b695e3f9	180	playlist_id, video_id, base_url = self._match_valid_url(url).group('id', 'vid', 'url')
54543467 JMF	181	webpage = self._download_webpage(url, playlist_id)
54543467 JMF	182
73c801d6 S	183	data_jsb = self._parse_json(
	184	self._search_regex(
	185	r'<div[^>]+class=(["\']).?VideoPlaylist.?\1[^>]+data-jsb=(["\'])(?P<json>.+?)\2',
	186	webpage, 'playlist', group='json'),
	187	playlist_id, transform_source=unescapeHTML)['playlist']['videos']
5d73273f	188
b695e3f9	189	if not self._yes_playlist(playlist_id, video_id, smuggled_data):
b695e3f9	190	data_jsb = [sd for sd in data_jsb if str(sd.get('id')) == video_id]
46358f64	191
b695e3f9	192	playlist_count = len(data_jsb)
b695e3f9	193	image = self._og_search_thumbnail(webpage) if playlist_count == 1 else None
5d73273f	194
b695e3f9	195	page_func = functools.partial(self._pagefunc, base_url, data_jsb, image=image)
5d73273f PH	196	return {
5d73273f PH	197	'_type': 'playlist',
b695e3f9	198	'entries': InAdvancePagedList(page_func, playlist_count, 1),
5d73273f PH	199	'id': playlist_id,
5d73273f PH	200	}
eb368012 S	201
eb368012 S	202
efe93167	203	class ORFRadioIE(InfoExtractor):
5770293d	204	IE_NAME = 'orf:radio'
	205
	206	STATION_INFO = {
	207	'fm4': ('fm4', 'fm4', 'orffm4'),
	208	'noe': ('noe', 'oe2n', 'orfnoe'),
	209	'wien': ('wie', 'oe2w', 'orfwie'),
	210	'burgenland': ('bgl', 'oe2b', 'orfbgl'),
	211	'ooe': ('ooe', 'oe2o', 'orfooe'),
	212	'steiermark': ('stm', 'oe2st', 'orfstm'),
	213	'kaernten': ('ktn', 'oe2k', 'orfktn'),
	214	'salzburg': ('sbg', 'oe2s', 'orfsbg'),
	215	'tirol': ('tir', 'oe2t', 'orftir'),
	216	'vorarlberg': ('vbg', 'oe2v', 'orfvbg'),
	217	'oe3': ('oe3', 'oe3', 'orfoe3'),
	218	'oe1': ('oe1', 'oe1', 'orfoe1'),
	219	}
	220	_STATION_RE = '\|'.join(map(re.escape, STATION_INFO.keys()))
eb368012	221
5770293d	222	_VALID_URL = rf'''(?x)
	223	https?://(?:
	224	(?P<station>{_STATION_RE})\.orf\.at/player\|
	225	radiothek\.orf\.at/(?P<station2>{_STATION_RE})
	226	)/(?P<date>[0-9]+)/(?P<show>\w+)'''
aca2fd22	227
5770293d	228	_TESTS = [{
	229	'url': 'https://radiothek.orf.at/ooe/20220801/OGMO',
	230	'info_dict': {
	231	'id': 'OGMO',
	232	'title': 'Guten Morgen OÖ',
	233	'description': 'md5:a3f6083399ef92b8cbe2d421b180835a',
	234	},
	235	'playlist': [{
	236	'md5': 'f33147d954a326e338ea52572c2810e8',
	237	'info_dict': {
	238	'id': '2022-08-01_0459_tl_66_7DaysMon1_319062',
0146c6cd	239	'ext': 'mp3',
5770293d	240	'title': 'Guten Morgen OÖ',
	241	'upload_date': '20220801',
	242	'duration': 18000,
	243	'timestamp': 1659322789,
	244	'description': 'md5:a3f6083399ef92b8cbe2d421b180835a',
	245	}
	246	}]
	247	}, {
	248	'url': 'https://ooe.orf.at/player/20220801/OGMO',
1339ecb2	249	'info_dict': {
5770293d	250	'id': 'OGMO',
	251	'title': 'Guten Morgen OÖ',
	252	'description': 'md5:a3f6083399ef92b8cbe2d421b180835a',
1339ecb2	253	},
5770293d	254	'playlist': [{
	255	'md5': 'f33147d954a326e338ea52572c2810e8',
	256	'info_dict': {
	257	'id': '2022-08-01_0459_tl_66_7DaysMon1_319062',
	258	'ext': 'mp3',
	259	'title': 'Guten Morgen OÖ',
	260	'upload_date': '20220801',
	261	'duration': 18000,
	262	'timestamp': 1659322789,
	263	'description': 'md5:a3f6083399ef92b8cbe2d421b180835a',
	264	}
	265	}]
	266	}, {
	267	'url': 'http://fm4.orf.at/player/20170107/4CC',
aca2fd22	268	'only_matching': True,
5770293d	269	}, {
13283058	270	'url': 'https://noe.orf.at/player/20200423/NGM',
13283058	271	'only_matching': True,
5770293d	272	}, {
13283058	273	'url': 'https://wien.orf.at/player/20200423/WGUM',
13283058	274	'only_matching': True,
5770293d	275	}, {
13283058	276	'url': 'https://burgenland.orf.at/player/20200423/BGM',
13283058	277	'only_matching': True,
5770293d	278	}, {
13283058	279	'url': 'https://steiermark.orf.at/player/20200423/STGMS',
13283058	280	'only_matching': True,
5770293d	281	}, {
13283058	282	'url': 'https://kaernten.orf.at/player/20200423/KGUMO',
13283058	283	'only_matching': True,
5770293d	284	}, {
13283058	285	'url': 'https://salzburg.orf.at/player/20200423/SGUM',
13283058	286	'only_matching': True,
5770293d	287	}, {
13283058	288	'url': 'https://tirol.orf.at/player/20200423/TGUMO',
13283058	289	'only_matching': True,
5770293d	290	}, {
13283058	291	'url': 'https://vorarlberg.orf.at/player/20200423/VGUM',
13283058	292	'only_matching': True,
5770293d	293	}, {
13283058	294	'url': 'https://oe3.orf.at/player/20200424/3WEK',
13283058	295	'only_matching': True,
5770293d	296	}, {
1339ecb2 S	297	'url': 'http://oe1.orf.at/player/20170108/456544',
	298	'md5': '34d8a6e67ea888293741c86a099b745b',
	299	'info_dict': {
	300	'id': '2017-01-08_0759_tl_51_7DaysSun6_256141',
	301	'ext': 'mp3',
	302	'title': 'Morgenjournal',
	303	'duration': 609,
	304	'timestamp': 1483858796,
	305	'upload_date': '20170108',
	306	},
	307	'skip': 'Shows from ORF radios are only available for 7 days.'
5770293d	308	}]
	309
	310	def _entries(self, data, station):
	311	_, loop_station, old_ie = self.STATION_INFO[station]
	312	for info in data['streams']:
	313	item_id = info.get('loopStreamId')
	314	if not item_id:
	315	continue
	316	video_id = item_id.replace('.mp3', '')
	317	yield {
	318	'id': video_id,
	319	'ext': 'mp3',
	320	'url': f'https://loopstream01.apa.at/?channel={loop_station}&id={item_id}',
	321	'_old_archive_ids': [make_archive_id(old_ie, video_id)],
	322	'title': data.get('title'),
	323	'description': clean_html(data.get('subtitle')),
	324	'duration': try_call(lambda: (info['end'] - info['start']) / 1000),
	325	'timestamp': int_or_none(info.get('start'), scale=1000),
	326	'series': data.get('programTitle'),
	327	}
	328
	329	def _real_extract(self, url):
	330	station, station2, show_date, show_id = self._match_valid_url(url).group('station', 'station2', 'date', 'show')
	331	api_station, _, _ = self.STATION_INFO[station or station2]
	332	data = self._download_json(
	333	f'http://audioapi.orf.at/{api_station}/api/json/current/broadcast/{show_id}/{show_date}', show_id)
	334
	335	return self.playlist_result(
	336	self._entries(data, station or station2), show_id, data.get('title'), clean_html(data.get('subtitle')))
efe93167	337
efe93167	338
14137b57 S	339	class ORFIPTVIE(InfoExtractor):
	340	IE_NAME = 'orf:iptv'
	341	IE_DESC = 'iptv.ORF.at'
5886b38d	342	_VALID_URL = r'https?://iptv\.orf\.at/(?:#/)?stories/(?P<id>\d+)'
14137b57 S	343
14137b57 S	344	_TEST = {
529d26c3 S	345	'url': 'http://iptv.orf.at/stories/2275236/',
529d26c3 S	346	'md5': 'c8b22af4718a4b4af58342529453e3e5',
14137b57	347	'info_dict': {
529d26c3	348	'id': '350612',
14137b57	349	'ext': 'flv',
529d26c3 S	350	'title': 'Weitere Evakuierungen um Vulkan Calbuco',
	351	'description': 'md5:d689c959bdbcf04efeddedbf2299d633',
	352	'duration': 68.197,
ec85ded8	353	'thumbnail': r're:^https?://.*\.jpg$',
529d26c3	354	'upload_date': '20150425',
14137b57 S	355	},
	356	}
	357
	358	def _real_extract(self, url):
	359	story_id = self._match_id(url)
	360
	361	webpage = self._download_webpage(
	362	'http://iptv.orf.at/stories/%s' % story_id, story_id)
	363
	364	video_id = self._search_regex(
	365	r'data-video(?:id)?="(\d+)"', webpage, 'video id')
	366
	367	data = self._download_json(
	368	'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id,
	369	video_id)[0]
	370
	371	duration = float_or_none(data['duration'], 1000)
	372
	373	video = data['sources']['default']
	374	load_balancer_url = video['loadBalancerUrl']
	375	abr = int_or_none(video.get('audioBitrate'))
	376	vbr = int_or_none(video.get('bitrate'))
	377	fps = int_or_none(video.get('videoFps'))
	378	width = int_or_none(video.get('videoWidth'))
	379	height = int_or_none(video.get('videoHeight'))
	380	thumbnail = video.get('preview')
	381
	382	rendition = self._download_json(
	383	load_balancer_url, video_id, transform_source=strip_jsonp)
	384
	385	f = {
	386	'abr': abr,
	387	'vbr': vbr,
	388	'fps': fps,
	389	'width': width,
	390	'height': height,
	391	}
	392
	393	formats = []
	394	for format_id, format_url in rendition['redirect'].items():
	395	if format_id == 'rtmp':
	396	ff = f.copy()
	397	ff.update({
	398	'url': format_url,
	399	'format_id': format_id,
	400	})
	401	formats.append(ff)
	402	elif determine_ext(format_url) == 'f4m':
	403	formats.extend(self._extract_f4m_formats(
	404	format_url, video_id, f4m_id=format_id))
	405	elif determine_ext(format_url) == 'm3u8':
	406	formats.extend(self._extract_m3u8_formats(
	407	format_url, video_id, 'mp4', m3u8_id=format_id))
	408	else:
	409	continue
	410	self._sort_formats(formats)
	411
	412	title = remove_end(self._og_search_title(webpage), ' - iptv.ORF.at')
	413	description = self._og_search_description(webpage)
	414	upload_date = unified_strdate(self._html_search_meta(
	415	'dc.date', webpage, 'upload date'))
	416
	417	return {
	418	'id': video_id,
419	'title': title,
420	'description': description,
421	'duration': duration,
422	'thumbnail': thumbnail,
423	'upload_date': upload_date,
424	'formats': formats,
425	}
0732a905 PH	426
	427
	428	class ORFFM4StoryIE(InfoExtractor):
	429	IE_NAME = 'orf:fm4:story'
	430	IE_DESC = 'fm4.orf.at stories'
	431	_VALID_URL = r'https?://fm4\.orf\.at/stories/(?P<id>\d+)'
	432
	433	_TEST = {
	434	'url': 'http://fm4.orf.at/stories/2865738/',
	435	'playlist': [{
	436	'md5': 'e1c2c706c45c7b34cf478bbf409907ca',
	437	'info_dict': {
	438	'id': '547792',
	439	'ext': 'flv',
	440	'title': 'Manu Delago und Inner Tongue live',
	441	'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.',
	442	'duration': 1748.52,
	443	'thumbnail': r're:^https?://.*\.jpg$',
	444	'upload_date': '20170913',
	445	},
	446	}, {
	447	'md5': 'c6dd2179731f86f4f55a7b49899d515f',
	448	'info_dict': {
	449	'id': '547798',
	450	'ext': 'flv',
	451	'title': 'Manu Delago und Inner Tongue live (2)',
	452	'duration': 1504.08,
	453	'thumbnail': r're:^https?://.*\.jpg$',
	454	'upload_date': '20170913',
	455	'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.',
	456	},
	457	}],
	458	}
	459
	460	def _real_extract(self, url):
	461	story_id = self._match_id(url)
	462	webpage = self._download_webpage(url, story_id)
	463
	464	entries = []
	465	all_ids = orderedSet(re.findall(r'data-video(?:id)?="(\d+)"', webpage))
	466	for idx, video_id in enumerate(all_ids):
	467	data = self._download_json(
	468	'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id,
	469	video_id)[0]
	470
	471	duration = float_or_none(data['duration'], 1000)
	472
	473	video = data['sources']['q8c']
	474	load_balancer_url = video['loadBalancerUrl']
	475	abr = int_or_none(video.get('audioBitrate'))
	476	vbr = int_or_none(video.get('bitrate'))
	477	fps = int_or_none(video.get('videoFps'))
	478	width = int_or_none(video.get('videoWidth'))
	479	height = int_or_none(video.get('videoHeight'))
	480	thumbnail = video.get('preview')
	481
	482	rendition = self._download_json(
	483	load_balancer_url, video_id, transform_source=strip_jsonp)
	484
	485	f = {
	486	'abr': abr,
	487	'vbr': vbr,
	488	'fps': fps,
	489	'width': width,
490	'height': height,
491	}
492
493	formats = []
494	for format_id, format_url in rendition['redirect'].items():
495	if format_id == 'rtmp':
496	ff = f.copy()
497	ff.update({
498	'url': format_url,
499	'format_id': format_id,
500	})
501	formats.append(ff)
502	elif determine_ext(format_url) == 'f4m':
503	formats.extend(self._extract_f4m_formats(
504	format_url, video_id, f4m_id=format_id))
505	elif determine_ext(format_url) == 'm3u8':
506	formats.extend(self._extract_m3u8_formats(
507	format_url, video_id, 'mp4', m3u8_id=format_id))
508	else:
509	continue
510	self._sort_formats(formats)
511
512	title = remove_end(self._og_search_title(webpage), ' - fm4.ORF.at')
513	if idx >= 1:
514	# Titles are duplicates, make them unique
515	title += ' (' + str(idx + 1) + ')'
516	description = self._og_search_description(webpage)
517	upload_date = unified_strdate(self._html_search_meta(
518	'dc.date', webpage, 'upload date'))
519
520	entries.append({
521	'id': video_id,
522	'title': title,
523	'description': description,
524	'duration': duration,
525	'thumbnail': thumbnail,
526	'upload_date': upload_date,
527	'formats': formats,
528	})
529
530	return self.playlist_result(entries)