From 7b93fb5ddccfaed77b986f3f0aa6b60f7c25245b Mon Sep 17 00:00:00 2001 From: nixxo Date: Fri, 16 Dec 2022 11:20:03 +0100 Subject: [PATCH] [extractor/rai] using new _VALID_URLS property - implemented _VALID_URLS property - deleted a couple of subclasses - added '_old_archive_ids' to manage back-compatibility with removed subclasses (by @pukkandan) --- yt_dlp/extractor/_extractors.py | 2 - yt_dlp/extractor/rai.py | 94 ++++++++++++++++----------------- 2 files changed, 47 insertions(+), 49 deletions(-) diff --git a/yt_dlp/extractor/_extractors.py b/yt_dlp/extractor/_extractors.py index a12328f04..1677d38e2 100644 --- a/yt_dlp/extractor/_extractors.py +++ b/yt_dlp/extractor/_extractors.py @@ -1479,10 +1479,8 @@ ) from .rai import ( RaiPlayIE, - RaiPlayLiveIE, RaiPlayPlaylistIE, RaiPlaySoundIE, - RaiPlaySoundLiveIE, RaiPlaySoundPlaylistIE, RaiNewsIE, RaiSudtirolIE, diff --git a/yt_dlp/extractor/rai.py b/yt_dlp/extractor/rai.py index cab12cc21..a84d63fa0 100644 --- a/yt_dlp/extractor/rai.py +++ b/yt_dlp/extractor/rai.py @@ -16,6 +16,7 @@ HEADRequest, int_or_none, join_nonempty, + make_archive_id, parse_duration, remove_start, strip_or_none, @@ -234,7 +235,10 @@ def _extract_subtitles(url, video_data): class RaiPlayIE(RaiBaseIE): - _VALID_URL = rf'(?Phttps?://(?:www\.)?raiplay\.it/.+?-(?P{RaiBaseIE._UUID_RE}))\.(?:html|json)' + _VALID_URLS = [ + rf'(?Phttps?://(?:www\.)?raiplay\.it/.+?-(?P{RaiBaseIE._UUID_RE}))\.(?:html|json)', + r'(?Phttps?://(?:www\.)?raiplay\.it/dirette/(?P[^/?#&]+))', + ] _TESTS = [{ 'url': 'http://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html', 'md5': '8970abf8caf8aef4696e7b1f2adfc696', @@ -282,6 +286,25 @@ class RaiPlayIE(RaiBaseIE): 'timestamp': 1637318940, 'upload_date': '20211119', }, + }, { + # live stream + 'url': 'https://www.raiplay.it/dirette/rainews24', + 'info_dict': { + 'id': 'd784ad40-e0ae-4a69-aa76-37519d238a9c', + 'display_id': 'rainews24', + 'ext': 'mp4', + 'title': r're:^Diretta di Rai News 24 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + 'description': 'md5:4d00bcf6dc98b27c6ec480de329d1497', + 'uploader': 'Rai News 24', + 'creator': 'Rai News 24', + 'is_live': True, + 'live_status': 'is_live', + 'upload_date': '20090502', + 'timestamp': 1241276220, + }, + 'params': { + 'skip_download': True, + }, }, { 'url': 'http://www.raiplay.it/video/2016/11/gazebotraindesi-efebe701-969c-4593-92f3-285f0d1ce750.html?', 'only_matching': True, @@ -336,6 +359,7 @@ def _real_extract(self, url): return { 'id': remove_start(media.get('id'), 'ContentItem-') or video_id, 'display_id': video_id, + '_old_archive_ids': [make_archive_id('RaiPlayLive', video_id)] if not re.match(RaiBaseIE._UUID_RE, video_id) else None, 'title': title, 'alt_title': strip_or_none(alt_title or None), 'description': media.get('description'), @@ -355,29 +379,6 @@ def _real_extract(self, url): } -class RaiPlayLiveIE(RaiPlayIE): # XXX: Do not subclass from concrete IE - _VALID_URL = r'(?Phttps?://(?:www\.)?raiplay\.it/dirette/(?P[^/?#&]+))' - _TESTS = [{ - 'url': 'http://www.raiplay.it/dirette/rainews24', - 'info_dict': { - 'id': 'd784ad40-e0ae-4a69-aa76-37519d238a9c', - 'display_id': 'rainews24', - 'ext': 'mp4', - 'title': 're:^Diretta di Rai News 24 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', - 'description': 'md5:4d00bcf6dc98b27c6ec480de329d1497', - 'uploader': 'Rai News 24', - 'creator': 'Rai News 24', - 'is_live': True, - 'live_status': 'is_live', - 'upload_date': '20090502', - 'timestamp': 1241276220, - }, - 'params': { - 'skip_download': True, - }, - }] - - class RaiPlayPlaylistIE(InfoExtractor): _VALID_URL = r'(?Phttps?://(?:www\.)?raiplay\.it/programmi/(?P[^/?#&]+))(?:/(?P[^?#&]+))?' _TESTS = [{ @@ -440,7 +441,10 @@ def _real_extract(self, url): class RaiPlaySoundIE(RaiBaseIE): - _VALID_URL = rf'(?Phttps?://(?:www\.)?raiplaysound\.it/.+?-(?P{RaiBaseIE._UUID_RE}))\.(?:html|json)' + _VALID_URLS = [ + rf'(?Phttps?://(?:www\.)?raiplaysound\.it/.+?-(?P{RaiBaseIE._UUID_RE}))\.(?:html|json)', + r'(?Phttps?://(?:www\.)?raiplaysound\.it/(?P[^/?#&]+)$)', + ] _TESTS = [{ 'url': 'https://www.raiplaysound.it/audio/2021/12/IL-RUGGITO-DEL-CONIGLIO-1ebae2a7-7cdb-42bb-842e-fe0d193e9707.html', 'md5': '8970abf8caf8aef4696e7b1f2adfc696', @@ -462,6 +466,23 @@ class RaiPlaySoundIE(RaiBaseIE): 'params': { 'skip_download': True, }, + }, { + 'url': 'https://www.raiplaysound.it/radio2', + 'info_dict': { + 'id': 'b00a50e6-f404-4af6-8f8c-ff3b9af73a44', + 'display_id': 'radio2', + 'ext': 'mp4', + 'title': r're:Rai Radio 2 \d+-\d+-\d+ \d+:\d+', + 'thumbnail': r're:https://www\.raiplaysound\.it/dl/img/.+png', + 'uploader': 'rai radio 2', + 'series': 'Rai Radio 2', + 'creator': 'raiplaysound', + 'is_live': True, + 'live_status': 'is_live', + }, + 'params': { + 'skip_download': 'live', + }, }] def _real_extract(self, url): @@ -488,6 +509,7 @@ def _real_extract(self, url): **info, 'id': uid or audio_id, 'display_id': audio_id, + '_old_archive_ids': [make_archive_id('RaiPlaySoundLive', audio_id)] if not re.match(RaiBaseIE._UUID_RE, audio_id) else None, 'title': traverse_obj(media, 'title', 'episode_title'), 'alt_title': traverse_obj(media, ('track_info', 'media_name'), expected_type=strip_or_none), 'description': media.get('description'), @@ -503,28 +525,6 @@ def _real_extract(self, url): } -class RaiPlaySoundLiveIE(RaiPlaySoundIE): # XXX: Do not subclass from concrete IE - _VALID_URL = r'(?Phttps?://(?:www\.)?raiplaysound\.it/(?P[^/?#&]+)$)' - _TESTS = [{ - 'url': 'https://www.raiplaysound.it/radio2', - 'info_dict': { - 'id': 'b00a50e6-f404-4af6-8f8c-ff3b9af73a44', - 'display_id': 'radio2', - 'ext': 'mp4', - 'title': r're:Rai Radio 2 \d+-\d+-\d+ \d+:\d+', - 'thumbnail': r're:https://www.raiplaysound.it/dl/img/.+?png', - 'uploader': 'rai radio 2', - 'series': 'Rai Radio 2', - 'creator': 'raiplaysound', - 'is_live': True, - 'live_status': 'is_live', - }, - 'params': { - 'skip_download': 'live', - }, - }] - - class RaiPlaySoundPlaylistIE(InfoExtractor): _VALID_URL = r'(?Phttps?://(?:www\.)?raiplaysound\.it/(?:programmi|playlist|audiolibri)/(?P[^/?#&]+))(?:/(?P[^?#&]+))?' _TESTS = [{