ghibili/discard_media.py

import os
import sys

def find_small_media_files(root_dir, max_size_mb=50, output_file="small_media_files.txt"):
    import re
    max_size_bytes = max_size_mb * 1024 * 1024
    media_exts = ('.mkv', '.mp4', '.mht', '.txt', '.url', '.gif', '.mp4', '.mkv', '.avi', '.mov', '.flv', '.wmv', '.webm')
    found = []
    for dirpath, _, filenames in os.walk(root_dir):
        for fname in filenames:
            fpath = os.path.join(dirpath, fname)
            # Check for extension, size, or pattern match
            matches_ext_and_size = (
                fname.lower().endswith(media_exts) and
                os.path.getsize(fpath) < max_size_bytes
            )
            matches_pattern = (
                fname.endswith("__") or
                "padding" in fname.lower()
            )
            try:
                if matches_ext_and_size or matches_pattern:
                    found.append(fpath)
            except Exception:
                continue
    with open(output_file, "w", encoding="utf-8") as f:
        for path in found:
            f.write(path + "\n")
    print(f"Found {len(found)} files matching criteria. Results saved to {output_file}")

if __name__ == "__main__":
    if len(sys.argv) < 2:
        print("Usage: python find_small_media.py <directory> [max_size_mb] [output_file]")
    else:
        root = sys.argv[1]
        max_mb = int(sys.argv[2]) if len(sys.argv) > 2 else 1
        out_file = sys.argv[3] if len(sys.argv) > 3 else "small_media_files.txt"
        find_small_media_files(root, max_mb, out_file)