[extractor] Deprecate `_sort_formats`

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

diff --git a/yt_dlp/extractor/generic.py b/yt_dlp/extractor/generic.py
index b0b26b61ad4f08d8d127b83f6337668c1580c2df..85581e62280738fd87a5ecb0469e90b7633d82d3 100644 (file)
--- a/yt_dlp/extractor/generic.py
+++ b/yt_dlp/extractor/generic.py
@@ -2399,40 +2399,6 @@ class GenericIE(InfoExtractor):
                 'upload_date': '20210111',
             }
         },
-        {
-            'note': 'Rumble embed',
-            'url': 'https://rumble.com/vdmum1-moose-the-dog-helps-girls-dig-a-snow-fort.html',
-            'md5': '53af34098a7f92c4e51cf0bd1c33f009',
-            'info_dict': {
-                'id': 'vb0ofn',
-                'ext': 'mp4',
-                'timestamp': 1612662578,
-                'uploader': 'LovingMontana',
-                'channel': 'LovingMontana',
-                'upload_date': '20210207',
-                'title': 'Winter-loving dog helps girls dig a snow fort ',
-                'channel_url': 'https://rumble.com/c/c-546523',
-                'thumbnail': 'https://sp.rmbl.ws/s8/1/5/f/x/x/5fxxb.OvCc.1-small-Moose-The-Dog-Helps-Girls-D.jpg',
-                'duration': 103,
-            }
-        },
-        {
-            'note': 'Rumble JS embed',
-            'url': 'https://therightscoop.com/what-does-9-plus-1-plus-1-equal-listen-to-this-audio-of-attempted-kavanaugh-assassins-call-and-youll-get-it',
-            'md5': '4701209ac99095592e73dbba21889690',
-            'info_dict': {
-                'id': 'v15eqxl',
-                'ext': 'mp4',
-                'channel': 'Mr Producer Media',
-                'duration': 92,
-                'title': '911 Audio From The Man Who Wanted To Kill Supreme Court Justice Kavanaugh',
-                'channel_url': 'https://rumble.com/c/RichSementa',
-                'thumbnail': 'https://sp.rmbl.ws/s8/1/P/j/f/A/PjfAe.OvCc-small-911-Audio-From-The-Man-Who-.jpg',
-                'timestamp': 1654892716,
-                'uploader': 'Mr Producer Media',
-                'upload_date': '20220610',
-            }
-        },
         {
             'note': 'JSON LD with multiple @type',
             'url': 'https://www.nu.nl/280161/video/hoe-een-bladvlo-dit-verwoestende-japanse-onkruid-moet-vernietigen.html',
@@ -2618,7 +2584,9 @@ def _real_extract(self, url):
             **smuggled_data.get('http_headers', {})
         })
         new_url = full_response.geturl()
-        if url != new_url:
+        if new_url == urllib.parse.urlparse(url)._replace(scheme='https').geturl():
+            url = new_url
+        elif url != new_url:
             self.report_following_redirect(new_url)
             if force_videoid:
                 new_url = smuggle_url(new_url, {'force_videoid': force_videoid})
@@ -2651,7 +2619,6 @@ def _real_extract(self, url):
                     'vcodec': 'none' if m.group('type') == 'audio' else None
                 }]
                 info_dict['direct'] = True
-            self._sort_formats(formats)
             info_dict.update({
                 'formats': formats,
                 'subtitles': subtitles,
@@ -2669,7 +2636,6 @@ def _real_extract(self, url):
         if first_bytes.startswith(b'#EXTM3U'):
             self.report_detected('M3U playlist')
             info_dict['formats'], info_dict['subtitles'] = self._extract_m3u8_formats_and_subtitles(url, video_id, 'mp4')
-            self._sort_formats(info_dict['formats'])
             return info_dict
 
         # Maybe it's a direct link to a video?
@@ -2703,12 +2669,10 @@ def _real_extract(self, url):
             elif doc.tag == 'SmoothStreamingMedia':
                 info_dict['formats'], info_dict['subtitles'] = self._parse_ism_formats_and_subtitles(doc, url)
                 self.report_detected('ISM manifest')
-                self._sort_formats(info_dict['formats'])
                 return info_dict
             elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
                 smil = self._parse_smil(doc, url, video_id)
                 self.report_detected('SMIL file')
-                self._sort_formats(smil['formats'])
                 return smil
             elif doc.tag == '{http://xspf.org/ns/0/}playlist':
                 self.report_detected('XSPF playlist')
@@ -2723,12 +2687,10 @@ def _real_extract(self, url):
                     mpd_base_url=full_response.geturl().rpartition('/')[0],
                     mpd_url=url)
                 self.report_detected('DASH manifest')
-                self._sort_formats(info_dict['formats'])
                 return info_dict
             elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
                 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
                 self.report_detected('F4M manifest')
-                self._sort_formats(info_dict['formats'])
                 return info_dict
         except xml.etree.ElementTree.ParseError:
             pass
@@ -2872,7 +2834,6 @@ def _extract_embeds(self, url, webpage, *, urlh=None, info_dict={}):
                 })
             if formats or subtitles:
                 self.report_detected('video.js embed')
-                self._sort_formats(formats)
                 return [{'formats': formats, 'subtitles': subtitles}]
 
         # Looking for http://schema.org/VideoObject
@@ -2955,8 +2916,6 @@ def filter_video(urls):
                     if not formats[-1].get('height'):
                         formats[-1]['quality'] = 1
 
-                self._sort_formats(formats)
-
                 return [{
                     'id': flashvars['video_id'],
                     'display_id': display_id,
@@ -3105,9 +3064,6 @@ def filter_video(urls):
             else:
                 entry_info_dict['url'] = video_url
 
-            if entry_info_dict.get('formats'):
-                self._sort_formats(entry_info_dict['formats'])
-
             entries.append(entry_info_dict)
 
         if len(entries) > 1: