@tushar-br/desktop 1.0.282 → 1.0.283

package/staging_area/micro projects/SD -Advanced Media Processing Toolkit Automated Downloader, Segmenter & Neural Dubber/.venv/Lib/site-packages/yt_dlp/extractor/rtlnl.py

@@ -0,0 +1,294 @@
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_duration,
+)
+
+
+class RtlNlIE(InfoExtractor):
+    IE_NAME = 'rtl.nl'
+    IE_DESC = 'rtl.nl and rtlxl.nl'
+    _EMBED_REGEX = [r'<iframe[^>]+?\bsrc=(?P<q1>[\'"])(?P<url>(?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)(?P=q1)']
+    _VALID_URL = r'''(?x)
+        https?://(?:(?:www|static)\.)?
+        (?:
+            rtlxl\.nl/(?:[^\#]*\#!|programma)/[^/]+/|
+            rtl\.nl/(?:(?:system/videoplayer/(?:[^/]+/)+(?:video_)?embed\.html|embed)\b.+?\buuid=|video/)|
+            embed\.rtl\.nl/\#uuid=
+        )
+        (?P<id>[0-9a-f-]+)'''
+
+    _TESTS = [{
+        # new URL schema
+        'url': 'https://www.rtlxl.nl/programma/rtl-nieuws/0bd1384d-d970-3086-98bb-5c104e10c26f',
+        'md5': '490428f1187b60d714f34e1f2e3af0b6',
+        'info_dict': {
+            'id': '0bd1384d-d970-3086-98bb-5c104e10c26f',
+            'ext': 'mp4',
+            'title': 'RTL Nieuws',
+            'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
+            'timestamp': 1593293400,
+            'upload_date': '20200627',
+            'duration': 661.08,
+        },
+    }, {
+        # old URL schema
+        'url': 'http://www.rtlxl.nl/#!/rtl-nieuws-132237/82b1aad1-4a14-3d7b-b554-b0aed1b2c416',
+        'md5': '473d1946c1fdd050b2c0161a4b13c373',
+        'info_dict': {
+            'id': '82b1aad1-4a14-3d7b-b554-b0aed1b2c416',
+            'ext': 'mp4',
+            'title': 'RTL Nieuws',
+            'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
+            'timestamp': 1461951000,
+            'upload_date': '20160429',
+            'duration': 1167.96,
+        },
+        'skip': '404',
+    }, {
+        # best format available a3t
+        'url': 'http://www.rtl.nl/system/videoplayer/derden/rtlnieuws/video_embed.html#uuid=84ae5571-ac25-4225-ae0c-ef8d9efb2aed/autoplay=false',
+        'md5': 'dea7474214af1271d91ef332fb8be7ea',
+        'info_dict': {
+            'id': '84ae5571-ac25-4225-ae0c-ef8d9efb2aed',
+            'ext': 'mp4',
+            'timestamp': 1424039400,
+            'title': 'RTL Nieuws - Nieuwe beelden Kopenhagen: chaos direct na aanslag',
+            'thumbnail': r're:^https?://screenshots\.rtl\.nl/(?:[^/]+/)*sz=[0-9]+x[0-9]+/uuid=84ae5571-ac25-4225-ae0c-ef8d9efb2aed$',
+            'upload_date': '20150215',
+            'description': 'Er zijn nieuwe beelden vrijgegeven die vlak na de aanslag in Kopenhagen zijn gemaakt. Op de video is goed te zien hoe omstanders zich bekommeren om één van de slachtoffers, terwijl de eerste agenten ter plaatse komen.',
+        }
+    }, {
+        # empty synopsis and missing episodes (see https://github.com/ytdl-org/youtube-dl/issues/6275)
+        # best format available nettv
+        'url': 'http://www.rtl.nl/system/videoplayer/derden/rtlnieuws/video_embed.html#uuid=f536aac0-1dc3-4314-920e-3bd1c5b3811a/autoplay=false',
+        'info_dict': {
+            'id': 'f536aac0-1dc3-4314-920e-3bd1c5b3811a',
+            'ext': 'mp4',
+            'title': 'RTL Nieuws - Meer beelden van overval juwelier',
+            'thumbnail': r're:^https?://screenshots\.rtl\.nl/(?:[^/]+/)*sz=[0-9]+x[0-9]+/uuid=f536aac0-1dc3-4314-920e-3bd1c5b3811a$',
+            'timestamp': 1437233400,
+            'upload_date': '20150718',
+            'duration': 30.474,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # encrypted m3u8 streams, georestricted
+        'url': 'http://www.rtlxl.nl/#!/afl-2-257632/52a74543-c504-4cde-8aa8-ec66fe8d68a7',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.rtl.nl/system/videoplayer/derden/embed.html#!/uuid=bb0353b0-d6a4-1dad-90e9-18fe75b8d1f0',
+        'only_matching': True,
+    }, {
+        'url': 'http://rtlxl.nl/?_ga=1.204735956.572365465.1466978370#!/rtl-nieuws-132237/3c487912-023b-49ac-903e-2c5d79f8410f',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.rtl.nl/video/c603c9c2-601d-4b5e-8175-64f1e942dc7d/',
+        'only_matching': True,
+    }, {
+        'url': 'https://static.rtl.nl/embed/?uuid=1a2970fc-5c0b-43ff-9fdc-927e39e6d1bc&autoplay=false&publicatiepunt=rtlnieuwsnl',
+        'only_matching': True,
+    }, {
+        # new embed URL schema
+        'url': 'https://embed.rtl.nl/#uuid=84ae5571-ac25-4225-ae0c-ef8d9efb2aed/autoplay=false',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        uuid = self._match_id(url)
+        info = self._download_json(
+            'http://www.rtl.nl/system/s4m/vfd/version=2/uuid=%s/fmt=adaptive/' % uuid,
+            uuid)
+
+        material = info['material'][0]
+        title = info['abstracts'][0]['name']
+        subtitle = material.get('title')
+        if subtitle:
+            title += ' - %s' % subtitle
+        description = material.get('synopsis')
+
+        meta = info.get('meta', {})
+
+        videopath = material['videopath']
+        m3u8_url = meta.get('videohost', 'http://manifest.us.rtl.nl') + videopath
+
+        formats = self._extract_m3u8_formats(
+            m3u8_url, uuid, 'mp4', m3u8_id='hls', fatal=False)
+
+        thumbnails = []
+
+        for p in ('poster_base_url', '"thumb_base_url"'):
+            if not meta.get(p):
+                continue
+
+            thumbnails.append({
+                'url': self._proto_relative_url(meta[p] + uuid),
+                'width': int_or_none(self._search_regex(
+                    r'/sz=([0-9]+)', meta[p], 'thumbnail width', fatal=False)),
+                'height': int_or_none(self._search_regex(
+                    r'/sz=[0-9]+x([0-9]+)',
+                    meta[p], 'thumbnail height', fatal=False))
+            })
+
+        return {
+            'id': uuid,
+            'title': title,
+            'formats': formats,
+            'timestamp': material['original_date'],
+            'description': description,
+            'duration': parse_duration(material.get('duration')),
+            'thumbnails': thumbnails,
+        }
+
+
+class RTLLuBaseIE(InfoExtractor):
+    _MEDIA_REGEX = {
+        'video': r'<rtl-player\s[^>]*\bhls\s*=\s*"([^"]+)',
+        'audio': r'<rtl-audioplayer\s[^>]*\bsrc\s*=\s*"([^"]+)',
+        'thumbnail': r'<rtl-player\s[^>]*\bposter\s*=\s*"([^"]+)',
+    }
+
+    def get_media_url(self, webpage, video_id, media_type):
+        return self._search_regex(self._MEDIA_REGEX[media_type], webpage, f'{media_type} url', default=None)
+
+    def get_formats_and_subtitles(self, webpage, video_id):
+        video_url, audio_url = self.get_media_url(webpage, video_id, 'video'), self.get_media_url(webpage, video_id, 'audio')
+
+        formats, subtitles = [], {}
+        if video_url is not None:
+            formats, subtitles = self._extract_m3u8_formats_and_subtitles(video_url, video_id)
+        if audio_url is not None:
+            formats.append({'url': audio_url, 'ext': 'mp3', 'vcodec': 'none'})
+
+        return formats, subtitles
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        is_live = video_id in ('live', 'live-2', 'lauschteren')
+
+        # TODO: extract comment from https://www.rtl.lu/comments?status=1&order=desc&context=news|article|<video_id>
+        # we can context from <rtl-comments context=<context> in webpage
+        webpage = self._download_webpage(url, video_id)
+
+        formats, subtitles = self.get_formats_and_subtitles(webpage, video_id)
+
+        return {
+            'id': video_id,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage, default=None),
+            'formats': formats,
+            'subtitles': subtitles,
+            'thumbnail': self.get_media_url(webpage, video_id, 'thumbnail') or self._og_search_thumbnail(webpage, default=None),
+            'is_live': is_live,
+        }
+
+
+class RTLLuTeleVODIE(RTLLuBaseIE):
+    IE_NAME = 'rtl.lu:tele-vod'
+    _VALID_URL = r'https?://(?:www\.)?rtl\.lu/(tele/(?P<slug>[\w-]+)/v/|video/)(?P<id>\d+)(\.html)?'
+    _TESTS = [{
+        'url': 'https://www.rtl.lu/tele/de-journal-vun-der-tele/v/3266757.html',
+        'info_dict': {
+            'id': '3266757',
+            'title': 'Informatiounsversammlung Héichwaasser',
+            'ext': 'mp4',
+            'thumbnail': 'https://replay-assets.rtl.lu/2021/11/16/d3647fc4-470d-11ec-adc2-3a00abd6e90f_00008.jpg',
+            'description': 'md5:b1db974408cc858c9fd241812e4a2a14',
+        }
+    }, {
+        'url': 'https://www.rtl.lu/video/3295215',
+        'info_dict': {
+            'id': '3295215',
+            'title': 'Kulturassisen iwwer d\'Bestandsopnam vum Lëtzebuerger Konscht',
+            'ext': 'mp4',
+            'thumbnail': 'https://replay-assets.rtl.lu/2022/06/28/0000_3295215_0000.jpg',
+            'description': 'md5:85bcd4e0490aa6ec969d9bf16927437b',
+        }
+    }]
+
+
+class RTLLuArticleIE(RTLLuBaseIE):
+    IE_NAME = 'rtl.lu:article'
+    _VALID_URL = r'https?://(?:(www|5minutes|today)\.)rtl\.lu/(?:[\w-]+)/(?:[\w-]+)/a/(?P<id>\d+)\.html'
+    _TESTS = [{
+        # Audio-only
+        'url': 'https://www.rtl.lu/sport/news/a/1934360.html',
+        'info_dict': {
+            'id': '1934360',
+            'ext': 'mp3',
+            'thumbnail': 'https://static.rtl.lu/rtl2008.lu/nt/p/2022/06/28/19/e4b37d66ddf00bab4c45617b91a5bb9b.jpeg',
+            'description': 'md5:5eab4a2a911c1fff7efc1682a38f9ef7',
+            'title': 'md5:40aa85f135578fbd549d3c9370321f99',
+        }
+    }, {
+        # 5minutes
+        'url': 'https://5minutes.rtl.lu/espace-frontaliers/frontaliers-en-questions/a/1853173.html',
+        'info_dict': {
+            'id': '1853173',
+            'ext': 'mp4',
+            'description': 'md5:ac031da0740e997a5cf4633173634fee',
+            'title': 'md5:87e17722ed21af0f24be3243f4ec0c46',
+            'thumbnail': 'https://replay-assets.rtl.lu/2022/01/26/screenshot_20220126104933_3274749_12b249833469b0d6e4440a1dec83cdfa.jpg',
+        }
+    }, {
+        # today.lu
+        'url': 'https://today.rtl.lu/entertainment/news/a/1936203.html',
+        'info_dict': {
+            'id': '1936203',
+            'ext': 'mp4',
+            'title': 'Once Upon A Time...zu Lëtzebuerg: The Three Witches\' Tower',
+            'description': 'The witchy theme continues in the latest episode of Once Upon A Time...',
+            'thumbnail': 'https://replay-assets.rtl.lu/2022/07/02/screenshot_20220702122859_3290019_412dc5185951b7f6545a4039c8be9235.jpg',
+        }
+    }]
+
+
+class RTLLuLiveIE(RTLLuBaseIE):
+    _VALID_URL = r'https?://www\.rtl\.lu/(?:tele|radio)/(?P<id>live(?:-\d+)?|lauschteren)'
+    _TESTS = [{
+        # Tele:live
+        'url': 'https://www.rtl.lu/tele/live',
+        'info_dict': {
+            'id': 'live',
+            'ext': 'mp4',
+            'live_status': 'is_live',
+            'title': r're:RTL - Télé LIVE \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
+            'thumbnail': 'https://static.rtl.lu/livestream/channel1.jpg',
+        }
+    }, {
+        # Tele:live-2
+        'url': 'https://www.rtl.lu/tele/live-2',
+        'info_dict': {
+            'id': 'live-2',
+            'ext': 'mp4',
+            'live_status': 'is_live',
+            'title': r're:RTL - Télé LIVE \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
+            'thumbnail': 'https://static.rtl.lu/livestream/channel2.jpg',
+        }
+    }, {
+        # Radio:lauschteren
+        'url': 'https://www.rtl.lu/radio/lauschteren',
+        'info_dict': {
+            'id': 'lauschteren',
+            'ext': 'mp4',
+            'live_status': 'is_live',
+            'title': r're:RTL - Radio LIVE \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
+            'thumbnail': 'https://static.rtl.lu/livestream/rtlradiowebtv.jpg',
+        }
+    }]
+
+
+class RTLLuRadioIE(RTLLuBaseIE):
+    _VALID_URL = r'https?://www\.rtl\.lu/radio/(?:[\w-]+)/s/(?P<id>\d+)(\.html)?'
+    _TESTS = [{
+        'url': 'https://www.rtl.lu/radio/5-vir-12/s/4033058.html',
+        'info_dict': {
+            'id': '4033058',
+            'ext': 'mp3',
+            'description': 'md5:f855a4f3e3235393ae47ed1db5d934b9',
+            'title': '5 vir 12 - Stau um Stau',
+            'thumbnail': 'https://static.rtl.lu/rtlg//2022/06/24/c9c19e5694a14be46a3647a3760e1f62.jpg',
+        }
+    }]

package/staging_area/micro projects/SD -Advanced Media Processing Toolkit Automated Downloader, Segmenter & Neural Dubber/.venv/Lib/site-packages/yt_dlp/extractor/rtnews.py

@@ -0,0 +1,196 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import js_to_json
+
+
+class RTNewsIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?rt\.com/[^/]+/(?:[^/]+/)?(?P<id>\d+)'
+
+    _TESTS = [{
+        'url': 'https://www.rt.com/sport/546301-djokovic-arrives-belgrade-crowds/',
+        'playlist_mincount': 2,
+        'info_dict': {
+            'id': '546301',
+            'title': 'Crowds gather to greet deported Djokovic as he returns to Serbia (VIDEO)',
+            'description': 'md5:1d5bfe1a988d81fd74227cfdf93d314d',
+            'thumbnail': 'https://cdni.rt.com/files/2022.01/article/61e587a085f540102c3386c1.png'
+        },
+    }, {
+        'url': 'https://www.rt.com/shows/in-question/535980-plot-to-assassinate-julian-assange/',
+        'playlist_mincount': 1,
+        'info_dict': {
+            'id': '535980',
+            'title': 'The plot to assassinate Julian Assange',
+            'description': 'md5:55279ce5e4441dc1d16e2e4a730152cd',
+            'thumbnail': 'https://cdni.rt.com/files/2021.09/article/615226f42030274e8879b53d.png'
+        },
+        'playlist': [{
+            'info_dict': {
+                'id': '6152271d85f5400464496162',
+                'ext': 'mp4',
+                'title': '6152271d85f5400464496162',
+            },
+        }]
+    }]
+
+    def _entries(self, webpage):
+        video_urls = set(re.findall(r'https://cdnv\.rt\.com/.*[a-f0-9]+\.mp4', webpage))
+        for v_url in video_urls:
+            v_id = re.search(r'([a-f0-9]+)\.mp4', v_url).group(1)
+            if v_id:
+                yield {
+                    'id': v_id,
+                    'title': v_id,
+                    'url': v_url,
+                }
+
+    def _real_extract(self, url):
+        id = self._match_id(url)
+        webpage = self._download_webpage(url, id)
+
+        return {
+            '_type': 'playlist',
+            'id': id,
+            'entries': self._entries(webpage),
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+        }
+
+
+class RTDocumentryIE(InfoExtractor):
+    _VALID_URL = r'https?://rtd\.rt\.com/(?:(?:series|shows)/[^/]+|films)/(?P<id>[^/?$&#]+)'
+
+    _TESTS = [{
+        'url': 'https://rtd.rt.com/films/escobars-hitman/',
+        'info_dict': {
+            'id': 'escobars-hitman',
+            'ext': 'mp4',
+            'title': "Escobar's Hitman. Former drug-gang killer, now loved and loathed in Colombia",
+            'description': 'md5:647c76984b7cb9a8b52a567e87448d88',
+            'thumbnail': 'https://cdni.rt.com/rtd-files/films/escobars-hitman/escobars-hitman_11.jpg',
+            'average_rating': 8.53,
+            'duration': 3134.0
+        },
+        'params': {'skip_download': True}
+    }, {
+        'url': 'https://rtd.rt.com/shows/the-kalashnikova-show-military-secrets-anna-knishenko/iskander-tactical-system-natos-headache/',
+        'info_dict': {
+            'id': 'iskander-tactical-system-natos-headache',
+            'ext': 'mp4',
+            'title': "Iskander tactical system. NATO's headache | The Kalashnikova Show. Episode 10",
+            'description': 'md5:da7c24a0aa67bc2bb88c86658508ca87',
+            'thumbnail': 'md5:89de8ce38c710b7c501ff02d47e2aa89',
+            'average_rating': 9.27,
+            'duration': 274.0,
+            'timestamp': 1605726000,
+            'view_count': int,
+            'upload_date': '20201118'
+        },
+        'params': {'skip_download': True}
+    }, {
+        'url': 'https://rtd.rt.com/series/i-am-hacked-trailer/introduction-to-safe-digital-life-ep2/',
+        'info_dict': {
+            'id': 'introduction-to-safe-digital-life-ep2',
+            'ext': 'mp4',
+            'title': 'How to Keep your Money away from Hackers | I am Hacked. Episode 2',
+            'description': 'md5:c46fa9a5af86c0008c45a3940a8cce87',
+            'thumbnail': 'md5:a5e81b9bf5aed8f5e23d9c053601b825',
+            'average_rating': 10.0,
+            'duration': 1524.0,
+            'timestamp': 1636977600,
+            'view_count': int,
+            'upload_date': '20211115'
+        },
+        'params': {'skip_download': True}
+    }]
+
+    def _real_extract(self, url):
+        id = self._match_id(url)
+        webpage = self._download_webpage(url, id)
+        ld_json = self._search_json_ld(webpage, None, fatal=False)
+        if not ld_json:
+            self.raise_no_formats('No video/audio found at the provided url.', expected=True)
+        media_json = self._parse_json(
+            self._search_regex(r'(?s)\'Med\'\s*:\s*\[\s*({.+})\s*\]\s*};', webpage, 'media info'),
+            id, transform_source=js_to_json)
+        if 'title' not in ld_json and 'title' in media_json:
+            ld_json['title'] = media_json['title']
+        formats = [{'url': src['file']} for src in media_json.get('sources') or [] if src.get('file')]
+
+        return {
+            'id': id,
+            'thumbnail': media_json.get('image'),
+            'formats': formats,
+            **ld_json
+        }
+
+
+class RTDocumentryPlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://rtd\.rt\.com/(?:series|shows)/(?P<id>[^/]+)/$'
+
+    _TESTS = [{
+        'url': 'https://rtd.rt.com/series/i-am-hacked-trailer/',
+        'playlist_mincount': 6,
+        'info_dict': {
+            'id': 'i-am-hacked-trailer',
+        },
+    }, {
+        'url': 'https://rtd.rt.com/shows/the-kalashnikova-show-military-secrets-anna-knishenko/',
+        'playlist_mincount': 34,
+        'info_dict': {
+            'id': 'the-kalashnikova-show-military-secrets-anna-knishenko',
+        },
+    }]
+
+    def _entries(self, webpage, id):
+        video_urls = set(re.findall(r'list-2__link\s*"\s*href="([^"]+)"', webpage))
+        for v_url in video_urls:
+            if id not in v_url:
+                continue
+            yield self.url_result(
+                'https://rtd.rt.com%s' % v_url,
+                ie=RTDocumentryIE.ie_key())
+
+    def _real_extract(self, url):
+        id = self._match_id(url)
+        webpage = self._download_webpage(url, id)
+
+        return {
+            '_type': 'playlist',
+            'id': id,
+            'entries': self._entries(webpage, id),
+        }
+
+
+class RuptlyIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?ruptly\.tv/[a-z]{2}/videos/(?P<id>\d+-\d+)'
+
+    _TESTS = [{
+        'url': 'https://www.ruptly.tv/en/videos/20220112-020-Japan-Double-trouble-Tokyo-zoo-presents-adorable-panda-twins',
+        'info_dict': {
+            'id': '20220112-020',
+            'ext': 'mp4',
+            'title': 'Japan: Double trouble! Tokyo zoo presents adorable panda twins | Video Ruptly',
+            'description': 'md5:85a8da5fdb31486f0562daf4360ce75a',
+            'thumbnail': 'https://storage.ruptly.tv/thumbnails/20220112-020/i6JQKnTNpYuqaXsR/i6JQKnTNpYuqaXsR.jpg'
+        },
+        'params': {'skip_download': True}
+    }]
+
+    def _real_extract(self, url):
+        id = self._match_id(url)
+        webpage = self._download_webpage(url, id)
+        m3u8_url = self._search_regex(r'preview_url"\s?:\s?"(https?://storage\.ruptly\.tv/video_projects/.+\.m3u8)"', webpage, 'm3u8 url', fatal=False)
+        if not m3u8_url:
+            self.raise_no_formats('No video/audio found at the provided url.', expected=True)
+        formats, subs = self._extract_m3u8_formats_and_subtitles(m3u8_url, id, ext='mp4')
+        return {
+            'id': id,
+            'formats': formats,
+            'subtitles': subs,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+        }

package/staging_area/micro projects/SD -Advanced Media Processing Toolkit Automated Downloader, Segmenter & Neural Dubber/.venv/Lib/site-packages/yt_dlp/extractor/rtp.py

@@ -0,0 +1,97 @@
+from .common import InfoExtractor
+from ..utils import js_to_json
+import re
+import json
+import urllib.parse
+import base64
+
+
+class RTPIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?rtp\.pt/play/p(?P<program_id>[0-9]+)/(?P<id>[^/?#]+)/?'
+    _TESTS = [{
+        'url': 'http://www.rtp.pt/play/p405/e174042/paixoes-cruzadas',
+        'md5': 'e736ce0c665e459ddb818546220b4ef8',
+        'info_dict': {
+            'id': 'e174042',
+            'ext': 'mp3',
+            'title': 'Paixões Cruzadas',
+            'description': 'As paixões musicais de António Cartaxo e António Macedo',
+            'thumbnail': r're:^https?://.*\.jpg',
+        },
+    }, {
+        'url': 'http://www.rtp.pt/play/p831/a-quimica-das-coisas',
+        'only_matching': True,
+    }]
+
+    _RX_OBFUSCATION = re.compile(r'''(?xs)
+        atob\s*\(\s*decodeURIComponent\s*\(\s*
+            (\[[0-9A-Za-z%,'"]*\])
+        \s*\.\s*join\(\s*(?:""|'')\s*\)\s*\)\s*\)
+    ''')
+
+    def __unobfuscate(self, data, *, video_id):
+        if data.startswith('{'):
+            data = self._RX_OBFUSCATION.sub(
+                lambda m: json.dumps(
+                    base64.b64decode(urllib.parse.unquote(
+                        ''.join(self._parse_json(m.group(1), video_id))
+                    )).decode('iso-8859-1')),
+                data)
+        return js_to_json(data)
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+        title = self._html_search_meta(
+            'twitter:title', webpage, display_name='title', fatal=True)
+
+        f, config = self._search_regex(
+            r'''(?sx)
+                var\s+f\s*=\s*(?P<f>".*?"|{[^;]+?});\s*
+                var\s+player1\s+=\s+new\s+RTPPlayer\s*\((?P<config>{(?:(?!\*/).)+?})\);(?!\s*\*/)
+            ''', webpage,
+            'player config', group=('f', 'config'))
+
+        f = self._parse_json(
+            f, video_id,
+            lambda data: self.__unobfuscate(data, video_id=video_id))
+        config = self._parse_json(
+            config, video_id,
+            lambda data: self.__unobfuscate(data, video_id=video_id))
+
+        formats = []
+        if isinstance(f, dict):
+            f_hls = f.get('hls')
+            if f_hls is not None:
+                formats.extend(self._extract_m3u8_formats(
+                    f_hls, video_id, 'mp4', 'm3u8_native', m3u8_id='hls'))
+
+            f_dash = f.get('dash')
+            if f_dash is not None:
+                formats.extend(self._extract_mpd_formats(f_dash, video_id, mpd_id='dash'))
+        else:
+            formats.append({
+                'format_id': 'f',
+                'url': f,
+                'vcodec': 'none' if config.get('mediaType') == 'audio' else None,
+            })
+
+        subtitles = {}
+
+        vtt = config.get('vtt')
+        if vtt is not None:
+            for lcode, lname, url in vtt:
+                subtitles.setdefault(lcode, []).append({
+                    'name': lname,
+                    'url': url,
+                })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'description': self._html_search_meta(['description', 'twitter:description'], webpage),
+            'thumbnail': config.get('poster') or self._og_search_thumbnail(webpage),
+            'subtitles': subtitles,
+        }

package/staging_area/micro projects/SD -Advanced Media Processing Toolkit Automated Downloader, Segmenter & Neural Dubber/.venv/Lib/site-packages/yt_dlp/extractor/rtrfm.py

@@ -0,0 +1,65 @@
+from .common import InfoExtractor
+
+
+class RTRFMIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?rtrfm\.com\.au/(?:shows|show-episode)/(?P<id>[^/?\#&]+)'
+    _TESTS = [
+        {
+            'url': 'https://rtrfm.com.au/shows/breakfast/',
+            'md5': '46168394d3a5ce237cf47e85d0745413',
+            'info_dict': {
+                'id': 'breakfast-2021-11-16',
+                'ext': 'mp3',
+                'series': 'Breakfast with Taylah',
+                'title': r're:^Breakfast with Taylah \d{4}-\d{2}-\d{2}$',
+                'description': 'md5:0979c3ab1febfbec3f1ccb743633c611',
+            },
+            'skip': 'ID and md5 changes daily',
+        },
+        {
+            'url': 'https://rtrfm.com.au/show-episode/breakfast-2021-11-11/',
+            'md5': '396bedf1e40f96c62b30d4999202a790',
+            'info_dict': {
+                'id': 'breakfast-2021-11-11',
+                'ext': 'mp3',
+                'series': 'Breakfast with Taylah',
+                'title': 'Breakfast with Taylah 2021-11-11',
+                'description': 'md5:0979c3ab1febfbec3f1ccb743633c611',
+            },
+        },
+        {
+            'url': 'https://rtrfm.com.au/show-episode/breakfast-2020-06-01/',
+            'md5': '594027f513ec36a24b15d65007a24dff',
+            'info_dict': {
+                'id': 'breakfast-2020-06-01',
+                'ext': 'mp3',
+                'series': 'Breakfast with Taylah',
+                'title': 'Breakfast with Taylah 2020-06-01',
+                'description': r're:^Breakfast with Taylah ',
+            },
+            'skip': 'This audio has expired',
+        },
+    ]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        show, date, title = self._search_regex(
+            r'''\.playShow(?:From)?\(['"](?P<show>[^'"]+)['"],\s*['"](?P<date>[0-9]{4}-[0-9]{2}-[0-9]{2})['"],\s*['"](?P<title>[^'"]+)['"]''',
+            webpage, 'details', group=('show', 'date', 'title'))
+        url = self._download_json(
+            'https://restreams.rtrfm.com.au/rzz',
+            show, 'Downloading MP3 URL', query={'n': show, 'd': date})['u']
+        # This is the only indicator of an error until trying to download the URL and
+        # downloads of mp4 URLs always fail (403 for current episodes, 404 for missing).
+        if '.mp4' in url:
+            url = None
+            self.raise_no_formats('Expired or no episode on this date', expected=True)
+        return {
+            'id': '%s-%s' % (show, date),
+            'title': '%s %s' % (title, date),
+            'series': title,
+            'url': url,
+            'release_date': date,
+            'description': self._og_search_description(webpage),
+        }