[core] Do not alter default format selection when simulated (#9862)

Closes #9843
Authored by: seproDev

README.md

@@ -2219,6 +2219,7 @@ ### Differences in default behavior
 * yt-dlp versions between 2021.11.10 and 2023.06.21 estimated `filesize_approx` values for fragmented/manifest formats. This was added for convenience in [f2fe69](https://github.com/yt-dlp/yt-dlp/commit/f2fe69c7b0d208bdb1f6292b4ae92bc1e1a7444a), but was reverted in [0dff8e](https://github.com/yt-dlp/yt-dlp/commit/0dff8e4d1e6e9fb938f4256ea9af7d81f42fd54f) due to the potentially extreme inaccuracy of the estimated values. Use `--compat-options manifest-filesize-approx` to keep extracting the estimated values
 * yt-dlp uses modern http client backends such as `requests`. Use `--compat-options prefer-legacy-http-handler` to prefer the legacy http handler (`urllib`) to be used for standard http requests.
 * The sub-modules `swfinterp`, `casefold` are removed.
+* Passing `--simulate` (or calling `extract_info` with `download=False`) no longer alters the default format selection. See [#9843](https://github.com/yt-dlp/yt-dlp/issues/9843) for details.
 
 For ease of use, a few more compat options are available:
 

test/test_YoutubeDL.py

@@ -4,6 +4,7 @@
 import os
 import sys
 import unittest
+from unittest.mock import patch
 
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
@@ -520,7 +521,33 @@ def test_format_filtering(self):
             ydl.process_ie_result(info_dict)
         self.assertEqual(ydl.downloaded_info_dicts, [])
 
-    def test_default_format_spec(self):
+    @patch('yt_dlp.postprocessor.ffmpeg.FFmpegMergerPP.available', False)
+    def test_default_format_spec_without_ffmpeg(self):
+        ydl = YDL({})
+        self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio')
+
+        ydl = YDL({'simulate': True})
+        self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio')
+
+        ydl = YDL({})
+        self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
+
+        ydl = YDL({'simulate': True})
+        self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
+
+        ydl = YDL({'outtmpl': '-'})
+        self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio')
+
+        ydl = YDL({})
+        self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio')
+        self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
+
+    @patch('yt_dlp.postprocessor.ffmpeg.FFmpegMergerPP.available', True)
+    @patch('yt_dlp.postprocessor.ffmpeg.FFmpegMergerPP.can_merge', lambda _: True)
+    def test_default_format_spec_with_ffmpeg(self):
+        ydl = YDL({})
+        self.assertEqual(ydl._default_format_spec({}), 'bestvideo*+bestaudio/best')
+
         ydl = YDL({'simulate': True})
         self.assertEqual(ydl._default_format_spec({}), 'bestvideo*+bestaudio/best')
 
@@ -528,13 +555,13 @@ def test_default_format_spec(self):
         self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
 
         ydl = YDL({'simulate': True})
-        self.assertEqual(ydl._default_format_spec({'is_live': True}), 'bestvideo*+bestaudio/best')
+        self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
 
         ydl = YDL({'outtmpl': '-'})
         self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio')
 
         ydl = YDL({})
-        self.assertEqual(ydl._default_format_spec({}, download=False), 'bestvideo*+bestaudio/best')
+        self.assertEqual(ydl._default_format_spec({}), 'bestvideo*+bestaudio/best')
         self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
 
 

yt_dlp/YoutubeDL.py

@@ -2190,9 +2190,8 @@ def _select_formats(self, formats, selector):
                                    or all(f.get('acodec') == 'none' for f in formats)),  # OR, No formats with audio
         }))
 
-    def _default_format_spec(self, info_dict, download=True):
-        download = download and not self.params.get('simulate')
-        prefer_best = download and (
+    def _default_format_spec(self, info_dict):
+        prefer_best = (
             self.params['outtmpl']['default'] == '-'
             or info_dict.get('is_live') and not self.params.get('live_from_start'))
 
@@ -2200,7 +2199,7 @@ def can_merge():
             merger = FFmpegMergerPP(self)
             return merger.available and merger.can_merge()
 
-        if not prefer_best and download and not can_merge():
+        if not prefer_best and not can_merge():
             prefer_best = True
             formats = self._get_formats(info_dict)
             evaluate_formats = lambda spec: self._select_formats(formats, self.build_format_selector(spec))
@@ -2959,7 +2958,7 @@ def is_wellformed(f):
                     continue
 
             if format_selector is None:
-                req_format = self._default_format_spec(info_dict, download=download)
+                req_format = self._default_format_spec(info_dict)
                 self.write_debug(f'Default format spec: {req_format}')
                 format_selector = self.build_format_selector(req_format)