[ie/LRTRadio] Add extractor (#12801)

Closes #12745
Authored by: subrat-lima

test/test_utils.py

@@ -659,6 +659,8 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(url_or_none('mms://foo.de'), 'mms://foo.de')
         self.assertEqual(url_or_none('rtspu://foo.de'), 'rtspu://foo.de')
         self.assertEqual(url_or_none('ftps://foo.de'), 'ftps://foo.de')
+        self.assertEqual(url_or_none('ws://foo.de'), 'ws://foo.de')
+        self.assertEqual(url_or_none('wss://foo.de'), 'wss://foo.de')
 
     def test_parse_age_limit(self):
         self.assertEqual(parse_age_limit(None), None)

yt_dlp/downloader/niconico.py

@@ -85,6 +85,7 @@ class NiconicoLiveFD(FileDownloader):
                             'quality': live_quality,
                             'protocol': 'hls+fmp4',
                             'latency': live_latency,
+                            'accessRightMethod': 'single_cookie',
                             'chasePlay': False,
                         },
                         'room': {

yt_dlp/extractor/_extractors.py

@@ -903,6 +903,7 @@ from .ivi import (
     IviIE,
 )
 from .ivideon import IvideonIE
+from .ivoox import IvooxIE
 from .iwara import (
     IwaraIE,
     IwaraPlaylistIE,
@@ -960,7 +961,10 @@ from .kick import (
 )
 from .kicker import KickerIE
 from .kickstarter import KickStarterIE
-from .kika import KikaIE
+from .kika import (
+    KikaIE,
+    KikaPlaylistIE,
+)
 from .kinja import KinjaEmbedIE
 from .kinopoisk import KinoPoiskIE
 from .kommunetv import KommunetvIE
@@ -1061,6 +1065,7 @@ from .loom import (
 from .lovehomeporn import LoveHomePornIE
 from .lrt import (
     LRTVODIE,
+    LRTRadioIE,
     LRTStreamIE,
 )
 from .lsm import (

yt_dlp/extractor/common.py

@@ -1570,6 +1570,8 @@ class InfoExtractor:
         """Yield all json ld objects in the html"""
         if default is not NO_DEFAULT:
             fatal = False
+        if not fatal and not isinstance(html, str):
+            return
         for mobj in re.finditer(JSON_LD_RE, html):
             json_ld_item = self._parse_json(
                 mobj.group('json_ld'), video_id, fatal=fatal,

yt_dlp/extractor/ivoox.py

@@ -0,0 +1,78 @@
+from .common import InfoExtractor
+from ..utils import int_or_none, parse_iso8601, url_or_none, urljoin
+from ..utils.traversal import traverse_obj
+
+
+class IvooxIE(InfoExtractor):
+    _VALID_URL = (
+        r'https?://(?:www\.)?ivoox\.com/(?:\w{2}/)?[^/?#]+_rf_(?P<id>[0-9]+)_1\.html',
+        r'https?://go\.ivoox\.com/rf/(?P<id>[0-9]+)',
+    )
+    _TESTS = [{
+        'url': 'https://www.ivoox.com/dex-08x30-rostros-del-mal-los-asesinos-en-audios-mp3_rf_143594959_1.html',
+        'md5': '993f712de5b7d552459fc66aa3726885',
+        'info_dict': {
+            'id': '143594959',
+            'ext': 'mp3',
+            'timestamp': 1742731200,
+            'channel': 'DIAS EXTRAÑOS con Santiago Camacho',
+            'title': 'DEx 08x30 Rostros del mal: Los asesinos en serie que aterrorizaron España',
+            'description': 'md5:eae8b4b9740d0216d3871390b056bb08',
+            'uploader': 'Santiago Camacho',
+            'thumbnail': 'https://static-1.ivoox.com/audios/c/d/5/2/cd52f46783fe735000c33a803dce2554_XXL.jpg',
+            'upload_date': '20250323',
+            'episode': 'DEx 08x30 Rostros del mal: Los asesinos en serie que aterrorizaron España',
+            'duration': 11837,
+            'tags': ['españa', 'asesinos en serie', 'arropiero', 'historia criminal', 'mataviejas'],
+        },
+    }, {
+        'url': 'https://go.ivoox.com/rf/143594959',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.ivoox.com/en/campodelgas-28-03-2025-audios-mp3_rf_144036942_1.html',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        media_id = self._match_id(url)
+        webpage = self._download_webpage(url, media_id, fatal=False)
+
+        data = self._search_nuxt_data(
+            webpage, media_id, fatal=False, traverse=('data', 0, 'data', 'audio'))
+
+        direct_download = self._download_json(
+            f'https://vcore-web.ivoox.com/v1/public/audios/{media_id}/download-url', media_id, fatal=False,
+            note='Fetching direct download link', headers={'Referer': url})
+
+        download_paths = {
+            *traverse_obj(direct_download, ('data', 'downloadUrl', {str}, filter, all)),
+            *traverse_obj(data, (('downloadUrl', 'mediaUrl'), {str}, filter)),
+        }
+
+        formats = []
+        for path in download_paths:
+            formats.append({
+                'url': urljoin('https://ivoox.com', path),
+                'http_headers': {'Referer': url},
+            })
+
+        return {
+            'id': media_id,
+            'formats': formats,
+            'uploader': self._html_search_regex(r'data-prm-author="([^"]+)"', webpage, 'author', default=None),
+            'timestamp': parse_iso8601(
+                self._html_search_regex(r'data-prm-pubdate="([^"]+)"', webpage, 'timestamp', default=None)),
+            'channel': self._html_search_regex(r'data-prm-podname="([^"]+)"', webpage, 'channel', default=None),
+            'title': self._html_search_regex(r'data-prm-title="([^"]+)"', webpage, 'title', default=None),
+            'thumbnail': self._og_search_thumbnail(webpage, default=None),
+            'description': self._og_search_description(webpage, default=None),
+            **self._search_json_ld(webpage, media_id, default={}),
+            **traverse_obj(data, {
+                'title': ('title', {str}),
+                'description': ('description', {str}),
+                'thumbnail': ('image', {url_or_none}),
+                'timestamp': ('uploadDate', {parse_iso8601(delimiter=' ')}),
+                'duration': ('duration', {int_or_none}),
+                'tags': ('tags', ..., 'name', {str}),
+            }),
+        }

yt_dlp/extractor/kika.py

@@ -1,3 +1,5 @@
+import itertools
+
 from .common import InfoExtractor
 from ..utils import (
     determine_ext,
@@ -124,3 +126,43 @@ class KikaIE(InfoExtractor):
                         'vbr': ('bitrateVideo', {int_or_none}, {lambda x: None if x == -1 else x}),
                     }),
                 }
+
+
+class KikaPlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?kika\.de/[\w-]+/(?P<id>[a-z-]+\d+)'
+
+    _TESTS = [{
+        'url': 'https://www.kika.de/logo/logo-die-welt-und-ich-562',
+        'info_dict': {
+            'id': 'logo-die-welt-und-ich-562',
+            'title': 'logo!',
+            'description': 'md5:7b9d7f65561b82fa512f2cfb553c397d',
+        },
+        'playlist_count': 100,
+    }]
+
+    def _entries(self, playlist_url, playlist_id):
+        for page in itertools.count(1):
+            data = self._download_json(playlist_url, playlist_id, note=f'Downloading page {page}')
+            for item in traverse_obj(data, ('content', lambda _, v: url_or_none(v['api']['url']))):
+                yield self.url_result(
+                    item['api']['url'], ie=KikaIE,
+                    **traverse_obj(item, {
+                        'id': ('id', {str}),
+                        'title': ('title', {str}),
+                        'duration': ('duration', {int_or_none}),
+                        'timestamp': ('date', {parse_iso8601}),
+                    }))
+
+            playlist_url = traverse_obj(data, ('links', 'next', {url_or_none}))
+            if not playlist_url:
+                break
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        brand_data = self._download_json(
+            f'https://www.kika.de/_next-api/proxy/v1/brands/{playlist_id}', playlist_id)
+
+        return self.playlist_result(
+            self._entries(brand_data['videoSubchannel']['videosPageUrl'], playlist_id),
+            playlist_id, title=brand_data.get('title'), description=brand_data.get('description'))

yt_dlp/extractor/lrt.py

@@ -2,8 +2,11 @@ from .common import InfoExtractor
 from ..utils import (
     clean_html,
     merge_dicts,
+    str_or_none,
     traverse_obj,
+    unified_timestamp,
     url_or_none,
+    urljoin,
 )
 
 
@@ -80,7 +83,7 @@ class LRTVODIE(LRTBaseIE):
     }]
 
     def _real_extract(self, url):
-        path, video_id = self._match_valid_url(url).groups()
+        path, video_id = self._match_valid_url(url).group('path', 'id')
         webpage = self._download_webpage(url, video_id)
 
         media_url = self._extract_js_var(webpage, 'main_url', path)
@@ -106,3 +109,42 @@ class LRTVODIE(LRTBaseIE):
         }
 
         return merge_dicts(clean_info, jw_data, json_ld_data)
+
+
+class LRTRadioIE(LRTBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?lrt\.lt/radioteka/irasas/(?P<id>\d+)/(?P<path>[^?#/]+)'
+    _TESTS = [{
+        # m3u8 download
+        'url': 'https://www.lrt.lt/radioteka/irasas/2000359728/nemarios-eiles-apie-pragarus-ir-skaistyklas-su-aiste-kiltinaviciute',
+        'info_dict': {
+            'id': '2000359728',
+            'ext': 'm4a',
+            'title': 'Nemarios eilės: apie pragarus ir skaistyklas su Aiste Kiltinavičiūte',
+            'description': 'md5:5eee9a0e86a55bf547bd67596204625d',
+            'timestamp': 1726143120,
+            'upload_date': '20240912',
+            'tags': 'count:5',
+            'thumbnail': r're:https?://.+/.+\.jpe?g',
+            'categories': ['Daiktiniai įrodymai'],
+        },
+    }, {
+        'url': 'https://www.lrt.lt/radioteka/irasas/2000304654/vakaras-su-knyga-svetlana-aleksijevic-cernobylio-malda-v-dalis?season=%2Fmediateka%2Faudio%2Fvakaras-su-knyga%2F2023',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id, path = self._match_valid_url(url).group('id', 'path')
+        media = self._download_json(
+            'https://www.lrt.lt/radioteka/api/media', video_id,
+            query={'url': f'/mediateka/irasas/{video_id}/{path}'})
+
+        return traverse_obj(media, {
+            'id': ('id', {int}, {str_or_none}),
+            'title': ('title', {str}),
+            'tags': ('tags', ..., 'name', {str}),
+            'categories': ('playlist_item', 'category', {str}, filter, all, filter),
+            'description': ('content', {clean_html}, {str}),
+            'timestamp': ('date', {lambda x: x.replace('.', '/')}, {unified_timestamp}),
+            'thumbnail': ('playlist_item', 'image', {urljoin('https://www.lrt.lt')}),
+            'formats': ('playlist_item', 'file', {lambda x: self._extract_m3u8_formats(x, video_id)}),
+        })

yt_dlp/extractor/niconico.py

@@ -27,6 +27,7 @@ from ..utils import (
     traverse_obj,
     try_get,
     unescapeHTML,
+    unified_timestamp,
     update_url_query,
     url_basename,
     url_or_none,
@@ -985,6 +986,7 @@ class NiconicoLiveIE(InfoExtractor):
                     'quality': 'abr',
                     'protocol': 'hls+fmp4',
                     'latency': latency,
+                    'accessRightMethod': 'single_cookie',
                     'chasePlay': False,
                 },
                 'room': {
@@ -1005,6 +1007,7 @@ class NiconicoLiveIE(InfoExtractor):
             if data.get('type') == 'stream':
                 m3u8_url = data['data']['uri']
                 qualities = data['data']['availableQualities']
+                cookies = data['data']['cookies']
                 break
             elif data.get('type') == 'disconnect':
                 self.write_debug(recv)
@@ -1043,6 +1046,11 @@ class NiconicoLiveIE(InfoExtractor):
                     **res,
                 })
 
+        for cookie in cookies:
+            self._set_cookie(
+                cookie['domain'], cookie['name'], cookie['value'],
+                expire_time=unified_timestamp(cookie['expires']), path=cookie['path'], secure=cookie['secure'])
+
         formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', live=True)
         for fmt, q in zip(formats, reversed(qualities[1:])):
             fmt.update({

yt_dlp/utils/_utils.py

@@ -2044,7 +2044,7 @@ def url_or_none(url):
     if not url or not isinstance(url, str):
         return None
     url = url.strip()
-    return url if re.match(r'(?:(?:https?|rt(?:m(?:pt?[es]?|fp)|sp[su]?)|mms|ftps?):)?//', url) else None
+    return url if re.match(r'(?:(?:https?|rt(?:m(?:pt?[es]?|fp)|sp[su]?)|mms|ftps?|wss?):)?//', url) else None
 
 
 def strftime_or_none(timestamp, date_format='%Y%m%d', default=None):