Add HDR information to formats

2021-10-18 18:34:21 +05:30 · 2021-10-18 18:34:21 +05:30 · 176f1866cb
commit 176f1866cb
parent 17bddf3e95
6 changed files with 47 additions and 6 deletions
--- a/README.md
+++ b/README.md
@ -1060,6 +1060,7 @@ The available fields are:
 - `asr` (numeric): Audio sampling rate in Hertz
 - `vbr` (numeric): Average video bitrate in KBit/s
 - `fps` (numeric): Frame rate
+ - `dynamic_range` (string): The dynamic range of the video
 - `vcodec` (string): Name of the video codec in use
 - `container` (string): Name of the container format
 - `filesize` (numeric): The number of bytes, if known in advance
@ -1283,6 +1284,7 @@ The available fields are:
 - `width`: Width of video
 - `res`: Video resolution, calculated as the smallest dimension.
 - `fps`: Framerate of video
+ - `hdr`: The dynamic range of the video (`DV` > `HDR12` > `HDR10+` > `HDR10` > `SDR`)
 - `tbr`: Total average bitrate in KBit/s
 - `vbr`: Average video bitrate in KBit/s
 - `abr`: Average audio bitrate in KBit/s
@ -1293,9 +1295,9 @@ The available fields are:

 All fields, unless specified otherwise, are sorted in descending order. To reverse this, prefix the field with a `+`. Eg: `+res` prefers format with the smallest resolution. Additionally, you can suffix a preferred value for the fields, separated by a `:`. Eg: `res:720` prefers larger videos, but no larger than 720p and the smallest video if there are no videos less than 720p. For `codec` and `ext`, you can provide two preferred values, the first for video and the second for audio. Eg: `+codec:avc:m4a` (equivalent to `+vcodec:avc,+acodec:m4a`) sets the video codec preference to `h264` > `h265` > `vp9` > `vp9.2` > `av01` > `vp8` > `h263` > `theora` and audio codec preference to `mp4a` > `aac` > `vorbis` > `opus` > `mp3` > `ac3` > `dts`. You can also make the sorting prefer the nearest values to the provided by using `~` as the delimiter. Eg: `filesize~1G` prefers the format with filesize closest to 1 GiB.

-The fields `hasvid` and `ie_pref` are always given highest priority in sorting, irrespective of the user-defined order. This behaviour can be changed by using `--format-sort-force`. Apart from these, the default order used is: `lang,quality,res,fps,codec:vp9.2,size,br,asr,proto,ext,hasaud,source,id`. The extractors may override this default order, but they cannot override the user-provided order.
+The fields `hasvid` and `ie_pref` are always given highest priority in sorting, irrespective of the user-defined order. This behaviour can be changed by using `--format-sort-force`. Apart from these, the default order used is: `lang,quality,res,fps,hdr:12,codec:vp9.2,size,br,asr,proto,ext,hasaud,source,id`. The extractors may override this default order, but they cannot override the user-provided order.

-Note that the default has `codec:vp9.2`; i.e. `av1` is not prefered
+Note that the default has `codec:vp9.2`; i.e. `av1` is not prefered. Similarly, the default for hdr is `hdr:12`; i.e. dolby vision is not prefered. These choices are made since DV and AV1 formats are not yet fully compatible with most devices. This may be changed in the future as more devices become capable of smoothly playing back these formats.

 If your format selector is `worst`, the last item is selected after sorting. This means it will select the format that is worst in all respects. Most of the time, what you actually want is the video with the smallest filesize instead. So it is generally better to use `-f best -S +size,+br,+res,+fps`.

--- a/test/test_utils.py
+++ b/test/test_utils.py
@ -848,30 +848,52 @@ class TestUtil(unittest.TestCase):
        self.assertEqual(parse_codecs('avc1.77.30, mp4a.40.2'), {
            'vcodec': 'avc1.77.30',
            'acodec': 'mp4a.40.2',
+            'dynamic_range': None,
        })
        self.assertEqual(parse_codecs('mp4a.40.2'), {
            'vcodec': 'none',
            'acodec': 'mp4a.40.2',
+            'dynamic_range': None,
        })
        self.assertEqual(parse_codecs('mp4a.40.5,avc1.42001e'), {
            'vcodec': 'avc1.42001e',
            'acodec': 'mp4a.40.5',
+            'dynamic_range': None,
        })
        self.assertEqual(parse_codecs('avc3.640028'), {
            'vcodec': 'avc3.640028',
            'acodec': 'none',
+            'dynamic_range': None,
        })
        self.assertEqual(parse_codecs(', h264,,newcodec,aac'), {
            'vcodec': 'h264',
            'acodec': 'aac',
+            'dynamic_range': None,
        })
        self.assertEqual(parse_codecs('av01.0.05M.08'), {
            'vcodec': 'av01.0.05M.08',
            'acodec': 'none',
+            'dynamic_range': None,
+        })
+        self.assertEqual(parse_codecs('vp9.2'), {
+            'vcodec': 'vp9.2',
+            'acodec': 'none',
+            'dynamic_range': 'HDR10',
+        })
+        self.assertEqual(parse_codecs('av01.0.12M.10.0.110.09.16.09.0'), {
+            'vcodec': 'av01.0.12M.10',
+            'acodec': 'none',
+            'dynamic_range': 'HDR10',
+        })
+        self.assertEqual(parse_codecs('dvhe'), {
+            'vcodec': 'dvhe',
+            'acodec': 'none',
+            'dynamic_range': 'DV',
        })
        self.assertEqual(parse_codecs('theora, vorbis'), {
            'vcodec': 'theora',
            'acodec': 'vorbis',
+            'dynamic_range': None,
        })
        self.assertEqual(parse_codecs('unknownvcodec, unknownacodec'), {
            'vcodec': 'unknownvcodec',
--- a/yt_dlp/YoutubeDL.py
+++ b/yt_dlp/YoutubeDL.py
@ -2291,6 +2291,8 @@ class YoutubeDL(object):
                format['protocol'] = determine_protocol(format)
            if format.get('resolution') is None:
                format['resolution'] = self.format_resolution(format, default=None)
+            if format.get('dynamic_range') is None and format.get('vcodec') != 'none':
+                format['dynamic_range'] = 'SDR'
            # Add HTTP headers, so that external programs can use them from the
            # json output
            full_format_info = info_dict.copy()
@ -3176,6 +3178,7 @@ class YoutubeDL(object):
                    format_field(f, 'ext'),
                    self.format_resolution(f),
                    format_field(f, 'fps', '%d'),
+                    format_field(f, 'dynamic_range', '%s', ignore=(None, 'SDR')).replace('HDR', ''),
                    '|',
                    format_field(f, 'filesize', ' %s', func=format_bytes) + format_field(f, 'filesize_approx', '~%s', func=format_bytes),
                    format_field(f, 'tbr', '%4dk'),
@ -3193,7 +3196,7 @@ class YoutubeDL(object):
                        format_field(f, 'container', ignore=(None, f.get('ext'))),
                    ))),
                ] for f in formats if f.get('preference') is None or f['preference'] >= -1000]
-            header_line = ['ID', 'EXT', 'RESOLUTION', 'FPS', '|', ' FILESIZE', '  TBR', 'PROTO',
+            header_line = ['ID', 'EXT', 'RESOLUTION', 'FPS', 'HDR', '|', ' FILESIZE', '  TBR', 'PROTO',
                           '|', 'VCODEC', '  VBR', 'ACODEC', ' ABR', ' ASR', 'MORE INFO']
        else:
            table = [
--- a/yt_dlp/extractor/common.py
+++ b/yt_dlp/extractor/common.py
@ -147,6 +147,8 @@ class InfoExtractor(object):
                    * width      Width of the video, if known
                    * height     Height of the video, if known
                    * resolution Textual description of width and height
+                    * dynamic_range The dynamic range of the video. One of:
+                                 "SDR" (None), "HDR10", "HDR10+, "HDR12", "HLG, "DV"
                    * tbr        Average bitrate of audio and video in KBit/s
                    * abr        Average audio bitrate in KBit/s
                    * acodec     Name of the audio codec in use
@ -1507,7 +1509,7 @@ class InfoExtractor(object):
        regex = r' *((?P<reverse>\+)?(?P<field>[a-zA-Z0-9_]+)((?P<separator>[~:])(?P<limit>.*?))?)? *$'

        default = ('hidden', 'aud_or_vid', 'hasvid', 'ie_pref', 'lang', 'quality',
-                   'res', 'fps', 'codec:vp9.2', 'size', 'br', 'asr',
+                   'res', 'fps', 'hdr:12', 'codec:vp9.2', 'size', 'br', 'asr',
                   'proto', 'ext', 'hasaud', 'source', 'format_id')  # These must not be aliases
        ytdl_default = ('hasaud', 'lang', 'quality', 'tbr', 'filesize', 'vbr',
                        'height', 'width', 'proto', 'vext', 'abr', 'aext',
@ -1518,6 +1520,8 @@ class InfoExtractor(object):
                       'order': ['av0?1', 'vp0?9.2', 'vp0?9', '[hx]265|he?vc?', '[hx]264|avc', 'vp0?8', 'mp4v|h263', 'theora', '', None, 'none']},
            'acodec': {'type': 'ordered', 'regex': True,
                       'order': ['opus', 'vorbis', 'aac', 'mp?4a?', 'mp3', 'e?a?c-?3', 'dts', '', None, 'none']},
+            'hdr': {'type': 'ordered', 'regex': True, 'field': 'dynamic_range',
+                    'order': ['dv', '(hdr)?12', r'(hdr)?10\+', '(hdr)?10', 'hlg', '', 'sdr', None]},
            'proto': {'type': 'ordered', 'regex': True, 'field': 'protocol',
                      'order': ['(ht|f)tps', '(ht|f)tp$', 'm3u8.+', '.*dash', 'ws|websocket', '', 'mms|rtsp', 'none', 'f4']},
            'vext': {'type': 'ordered', 'field': 'video_ext',
--- a/yt_dlp/extractor/youtube.py
+++ b/yt_dlp/extractor/youtube.py
@ -2653,7 +2653,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):

        # Source is given priority since formats that throttle are given lower source_preference
        # When throttling issue is fully fixed, remove this
-        self._sort_formats(formats, ('quality', 'res', 'fps', 'source', 'codec:vp9.2', 'lang'))
+        self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang'))

        keywords = get_first(video_details, 'keywords', expected_type=list) or []
        if not keywords and webpage:
--- a/yt_dlp/utils.py
+++ b/yt_dlp/utils.py
@ -4618,12 +4618,21 @@ def parse_codecs(codecs_str):
        return {}
    split_codecs = list(filter(None, map(
        str.strip, codecs_str.strip().strip(',').split(','))))
-    vcodec, acodec = None, None
+    vcodec, acodec, hdr = None, None, None
    for full_codec in split_codecs:
        codec = full_codec.split('.')[0]
        if codec in ('avc1', 'avc2', 'avc3', 'avc4', 'vp9', 'vp8', 'hev1', 'hev2', 'h263', 'h264', 'mp4v', 'hvc1', 'av01', 'theora', 'dvh1', 'dvhe'):
            if not vcodec:
                vcodec = full_codec
+                if codec in ('dvh1', 'dvhe'):
+                    hdr = 'DV'
+                elif codec == 'vp9' and vcodec.startswith('vp9.2'):
+                    hdr = 'HDR10'
+                elif codec == 'av01':
+                    parts = full_codec.split('.')
+                    if len(parts) > 3 and parts[3] == '10':
+                        hdr = 'HDR10'
+                        vcodec = '.'.join(parts[:4])
        elif codec in ('mp4a', 'opus', 'vorbis', 'mp3', 'aac', 'ac-3', 'ec-3', 'eac3', 'dtsc', 'dtse', 'dtsh', 'dtsl'):
            if not acodec:
                acodec = full_codec
@ -4639,6 +4648,7 @@ def parse_codecs(codecs_str):
        return {
            'vcodec': vcodec or 'none',
            'acodec': acodec or 'none',
+            'dynamic_range': hdr,
        }
    return {}