FFprobe не отражает изменения размеров MP4

Я пытаюсь редактировать ширину и высоту MP4 без масштабирования.

Я делаю это, редактируя поля tkhd и stsd заголовка MP4.

• exiftool покажет новую ширину и высоту, а ffprobe — нет.

Перед редактированием:

Exif:
$ exiftool $f | egrep -i 'width|height'

Image Width                     : 100
Image Height                    : 100
Source Image Width              : 100
Source Image Height             : 100

FFprobe:
$ ffprobe -v quiet -show_streams $f | egrep 'width|height'

width=100
height=100
coded_width=100
coded_height=100

После редактирования вышеуказанных размеров я получаю следующий вывод файла Python:

[ftyp] size:32
[mdat] size:196933
[moov] size:2057
- [mvhd] size:108
- [trak] size:1941
- - [tkhd] size:92
     Updated tkhd box: Width: 100 -> 300, Height: 100 -> 400
- - [mdia] size:1841
- - - [mdhd] size:32
- - - [hdlr] size:44
- - - [minf] size:1757
- - - - [vmhd] size:20
- - - - [dinf] size:36
- - - - - [dref] size:28
- - - - [stbl] size:1693
- - - - - [stsd] size:145
           Updated stsd box #1: Width: 100 -> 300, Height: 100 -> 400
- - - - - [stts] size:512
- - - - - [stss] size:56
- - - - - [stsc] size:28
- - - - - [stsz] size:924
- - - - - [stco] size:20

Затем снова запустите EXIFtool и FFprobe:

$ exiftool $f egrep -i 'width|height'

Image Width                     : 300
Image Height                    : 400
Source Image Width              : 300
Source Image Height             : 400

$ ffprobe -v quiet -show_streams $f | egrep 'width|height'

width=100
height=100
coded_width=100
coded_height=100

Это мой код Python:

import sys, struct

def read_box(f):
    offset = f.tell()
    header = f.read(8)
    if len(header) < 8:
        return None, offset
    size, box_type = struct.unpack(">I4s", header)
    box_type = box_type.decode("ascii")
    if size == 1:
        size = struct.unpack(">Q", f.read(8))[0]
    elif size == 0:
        size = None
    return {"type": box_type, "size": size, "start_offset": offset}, offset

def edit_tkhd_box(f, box_start, new_width, new_height, depth):
    f.seek(box_start + 84, 0)  # Go to the width/height part in tkhd box
    try:
        old_width = struct.unpack('>I', f.read(4))[0] >> 16
        old_height = struct.unpack('>I', f.read(4))[0] >> 16
        f.seek(box_start + 84, 0)  # Go back to write
        f.write(struct.pack('>I', new_width << 16))
        f.write(struct.pack('>I', new_height << 16))
        print(f"{'  ' * depth} Updated tkhd box: Width: {old_width} -> {new_width}, Height: {old_height} -> {new_height}")
    except struct.error:
        print(f"  Error reading or writing width/height to tkhd box")

def edit_stsd_box(f, box_start, new_width, new_height, depth):
    f.seek(box_start + 12, 0)  # Skip to the entry count in stsd box
    try:
        entry_count = struct.unpack('>I', f.read(4))[0]
        for i in range(entry_count):
            entry_start = f.tell()
            f.seek(entry_start + 4, 0)  # Skip the entry size
            format_type = f.read(4).decode("ascii", "ignore")
            if format_type == "avc1":
                f.seek(entry_start + 32, 0)  # Adjust this based on format specifics
                try:
                    old_width = struct.unpack('>H', f.read(2))[0]
                    old_height = struct.unpack('>H', f.read(2))[0]
                    f.seek(entry_start + 32, 0)  # Go back to write
                    f.write(struct.pack('>H', new_width))
                    f.write(struct.pack('>H', new_height))
                    print(f"{'  ' * depth} Updated stsd box #{i + 1}: Width: {old_width} -> {new_width}, Height: {old_height} -> {new_height}")
                except struct.error:
                    print(f"  Error reading or writing dimensions to avc1 format in entry {i + 1}")
            else:
                f.seek(entry_start + 8, 0)  # Skip to the next entry
    except struct.error:
        print(f"  Error reading or writing entries in stsd box")

def parse_and_edit_boxes(f, new_width, new_height, depth=0, parent_size=None):
    while True:
        current_pos = f.tell()
        if parent_size is not None and current_pos >= parent_size:
            break
        box, box_start = read_box(f)
        if not box:
            break
        box_type, box_size = box["type"], box["size"]
        print(f'{"- " * depth}[{box_type}] size:{box_size}')
        
        if box_type == "tkhd":
            edit_tkhd_box(f, box_start, new_width, new_height, depth)
        elif box_type == "stsd":
            edit_stsd_box(f, box_start, new_width, new_height, depth)
        
        # Recursively parse children if it's a container box
        if box_type in ["moov", "trak", "mdia", "minf", "stbl", "dinf", "edts"]:
            parse_and_edit_boxes(f, new_width, new_height, depth + 1, box_start + box_size)
        
        if box_size is None:
            f.seek(0, 2)  # Move to the end of file
        else:
            f.seek(box_start + box_size, 0)

if __name__ == '__main__':
    if len(sys.argv) != 4:
        print("Usage: python script.py <input_file> <new_width> <new_height>")
    else:
        with open(sys.argv[1], 'r+b') as f:
            parse_and_edit_boxes(f, int(sys.argv[2]), int(sys.argv[3]))

Кажется, это связано с ff_h264_decode_seq_parameter_set

🤔 А знаете ли вы, что...
В Python есть множество библиотек и фреймворков для разработки веб-приложений.