Merge 87c8703f90 into ccf0a6b86b

2024-12-02 16:32:51 +01:00 · 2024-11-24 00:52:31 +05:30 · 2024-11-24 00:52:31 +05:30 · 618a6c2a01
commit 618a6c2a01
parent ccf0a6b86b 87c8703f90
3 changed files with 56 additions and 52 deletions
--- a/yt_dlp/extractor/_extractors.py
+++ b/yt_dlp/extractor/_extractors.py
@ -1659,10 +1659,8 @@
    RaiIE,
    RaiNewsIE,
    RaiPlayIE,
-    RaiPlayLiveIE,
    RaiPlayPlaylistIE,
    RaiPlaySoundIE,
-    RaiPlaySoundLiveIE,
    RaiPlaySoundPlaylistIE,
    RaiSudtirolIE,
 )
--- a/yt_dlp/extractor/la7.py
+++ b/yt_dlp/extractor/la7.py
@ -7,10 +7,11 @@

 class LA7IE(InfoExtractor):
    IE_NAME = 'la7.it'
-    _VALID_URL = r'''(?x)https?://(?:
-        (?:www\.)?la7\.it/([^/]+)/(?:rivedila7|video|news)/|
-        tg\.la7\.it/repliche-tgla7\?id=
-    )(?P<id>.+)'''
+    _VALID_URL = [
+        r'https?://(?:www\.)?la7\.it/[^/]+/(?:rivedila7|video|news)/.+-(?P<id>\d{5,})',
+        r'https?://tg\.la7\.it/repliche-tgla7\?id=(?P<id>\d{5,})',
+        r'https?://tg\.la7\.it(?:/[^/]+)+-(?P<id>\d{5,})'
+    ]

    _TESTS = [{
        # single quality video
@ -39,7 +40,7 @@ class LA7IE(InfoExtractor):
            'formats': 'count:8',
        },
    }, {
-        'url': 'http://www.la7.it/omnibus/rivedila7/omnibus-news-02-07-2016-189077',
+        'url': 'https://tg.la7.it/repliche-tgla7?id=464601',
        'only_matching': True,
    }]
    _HOST = 'https://awsvodpkg.iltrovatore.it'
--- a/yt_dlp/extractor/rai.py
+++ b/yt_dlp/extractor/rai.py
@ -10,6 +10,7 @@
    filter_dict,
    int_or_none,
    join_nonempty,
+    make_archive_id,
    parse_duration,
    remove_start,
    strip_or_none,
@ -250,7 +251,10 @@ def _extract_subtitles(url, video_data):


 class RaiPlayIE(RaiBaseIE):
-    _VALID_URL = rf'(?P<base>https?://(?:www\.)?raiplay\.it/.+?-(?P<id>{RaiBaseIE._UUID_RE}))\.(?:html|json)'
+    _VALID_URL = [
+        rf'(?P<base>https?://(?:www\.)?raiplay\.it/.+?-(?P<id>{RaiBaseIE._UUID_RE}))\.(?:html|json)',
+        r'(?P<base>https?://(?:www\.)?raiplay\.it/dirette/(?P<id>[^/?#&]+))',
+    ]
    _TESTS = [{
        'url': 'https://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
        'md5': '8970abf8caf8aef4696e7b1f2adfc696',
@ -321,6 +325,25 @@ class RaiPlayIE(RaiBaseIE):
            'timestamp': 1348495020,
            'upload_date': '20120924',
        },
+    }, {
+        # 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,
@ -354,6 +377,7 @@ 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': media.get('name'),
            'alt_title': strip_or_none(alt_title or None),
            'description': media.get('description'),
@ -377,28 +401,6 @@ def _real_extract(self, url):
        }


-class RaiPlayLiveIE(RaiPlayIE):  # XXX: Do not subclass from concrete IE
-    _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/dirette/(?P<id>[^/?#&]+))'
-    _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,
-            'formats': 'count:3',
-        },
-        'params': {'skip_download': True},
-    }]
-
-
 class RaiPlayPlaylistIE(InfoExtractor):
    _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/programmi/(?P<id>[^/?#&]+))(?:/(?P<extra_id>[^?#&]+))?'
    _TESTS = [{
@ -463,7 +465,10 @@ def _real_extract(self, url):


 class RaiPlaySoundIE(RaiBaseIE):
-    _VALID_URL = rf'(?P<base>https?://(?:www\.)?raiplaysound\.it/.+?-(?P<id>{RaiBaseIE._UUID_RE}))\.(?:html|json)'
+    _VALID_URL = [
+        rf'(?P<base>https?://(?:www\.)?raiplaysound\.it/.+?-(?P<id>{RaiBaseIE._UUID_RE}))\.(?:html|json)',
+        r'(?P<base>https?://(?:www\.)?raiplaysound\.it/(?P<id>[^/?#&]+)$)',
+    ]
    _TESTS = [{
        'url': 'https://www.raiplaysound.it/audio/2021/12/IL-RUGGITO-DEL-CONIGLIO-1ebae2a7-7cdb-42bb-842e-fe0d193e9707.html',
        'md5': '8970abf8caf8aef4696e7b1f2adfc696',
@ -482,7 +487,26 @@ class RaiPlaySoundIE(RaiBaseIE):
            'timestamp': 1638346620,
            'upload_date': '20211201',
        },
-        'params': {'skip_download': True},
+        '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):
@ -506,6 +530,7 @@ 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'),
@ -521,26 +546,6 @@ def _real_extract(self, url):
        }


-class RaiPlaySoundLiveIE(RaiPlaySoundIE):  # XXX: Do not subclass from concrete IE
-    _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplaysound\.it/(?P<id>[^/?#&]+)$)'
-    _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': True},
-    }]
-
-
 class RaiPlaySoundPlaylistIE(InfoExtractor):
    _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplaysound\.it/(?:programmi|playlist|audiolibri)/(?P<id>[^/?#&]+))(?:/(?P<extra_id>[^?#&]+))?'
    _TESTS = [{