ffmpeg, python: split video by metadata

gistfile1.txt

#!/usr/bin/env python3

import subprocess
import json
import re
import sys
from pathlib import Path

def extract_chapters(input_file):
    """
    Returns a list of tuples (start_sec, end_sec, title)
    for all chapters in the input video. Uses ffprobe
    with JSON output — this eliminates omissions and parsing errors.
    """
    cmd = [
        "ffprobe",
        "-v", "quiet",
        "-print_format", "json",
        "-show_chapters",
        input_file,
    ]
    result = subprocess.run(cmd, capture_output=True, text=True, check=True)
    data = json.loads(result.stdout)

    chapters = []
    for idx, ch in enumerate(data.get("chapters", []), start=1):
        start_sec = float(ch["start_time"])
        end_sec = float(ch["end_time"])
        title = (
            ch.get("tags", {}).get("title", f"Chapter_{idx}")
            .strip()
            .replace(" ", "_")
        )
        chapters.append((start_sec, end_sec, title))
    return chapters

def split_video(input_file, chapters):
    input_path = Path(input_file)
    for idx, (start, end, title) in enumerate(chapters):
        output_file = f"{input_path.stem}_{idx+1:02d}_{title}.mp4"
        cmd = [
            "ffmpeg", "-y", "-i", input_file,
            "-ss", f"{start:.3f}", "-to", f"{end:.3f}",
            "-vf", "scale=1920:1080",
            "-c:v", "libx264", "-crf", "23", "-preset", "veryfast",
            "-c:a", "aac", "-b:a", "192k",
            output_file
        ]
        print(f"Exporting: {output_file}")
        subprocess.run(cmd)

def main():
    if len(sys.argv) != 2:
        print("Usage: python split_by_chapters.py <video_file>")
        sys.exit(1)

    input_file = sys.argv[1]
    chapters = extract_chapters(input_file)
    if not chapters:
        print("No chapters found.")
        sys.exit(1)
    split_video(input_file, chapters)

if __name__ == "__main__":
    main()