magnus919_agent-skills/epub/scripts/epub-images

#!/usr/bin/env python3
"""epub-images — Extract or list all images from an EPUB file.

Usage:
  epub-images <file.epub> [--list] [--extract DIR] [--type cover|all] [--json] [--dry-run]

Examples:
  epub-images book.epub --list --json           # list all images
  epub-images book.epub --extract images/       # extract all to directory
  epub-images book.epub --type cover --extract .  # extract only cover image

Dependencies: EbookLib (pip install EbookLib)
"""

import argparse
import json
import os
import sys
import warnings

warnings.filterwarnings("ignore")

DRY_RUN = False
JSON_OUTPUT = False


def die(msg):
    print(f"Error: {msg}", file=sys.stderr)
    sys.exit(1)


def emit(json_data, text=""):
    if JSON_OUTPUT:
        print(json.dumps(json_data, indent=2, default=str))
    else:
        print(text)


def main():
    global DRY_RUN, JSON_OUTPUT

    parser = argparse.ArgumentParser(
        description="Extract or list all images from an EPUB file.",
        epilog="Examples:\n  epub-images book.epub --list --json\n  epub-images book.epub --extract images/")
    parser.add_argument("epub", nargs="?", help="Path to EPUB file")
    parser.add_argument("--list", action="store_true", help="List images only, don't extract")
    parser.add_argument("--extract", "-e", help="Directory to extract images to")
    parser.add_argument("--type", choices=["cover", "all"], default="all", help="Image type filter")
    parser.add_argument("--json", action="store_true")
    parser.add_argument("--dry-run", "-n", action="store_true")
    args = parser.parse_args()

    JSON_OUTPUT = args.json
    DRY_RUN = args.dry_run

    if not args.epub:
        parser.print_help()
        sys.exit(1)

    if DRY_RUN:
        action = "extract to " + args.extract if args.extract else "list"
        emit({"status": "dry_run", "file": args.epub, "action": action},
             f"[dry-run] Would {action} images from: {args.epub}")
        return

    if not os.path.exists(args.epub):
        die(f"File not found: {args.epub}")

    try:
        from ebooklib import epub
        import ebooklib
    except ImportError:
        die("EbookLib required. Install with: pip install EbookLib")

    book = epub.read_epub(args.epub)

    # Find all images
    images = []
    # Read OPF to check for cover-image property (EbookLib's get_properties is unreliable)
    import zipfile
    cover_ids = set()
    try:
        with zipfile.ZipFile(args.epub, 'r') as zf:
            for n in zf.namelist():
                if n.endswith('.opf'):
                    opf = zf.read(n).decode('utf-8', errors='replace')
                    import re
                    for m in re.finditer(r'<item[^>]+properties="([^"]*cover-image[^"]*)"[^>]*>', opf):
                        id_match = re.search(r'id="([^"]+)"', m.group())
                        if id_match:
                            cover_ids.add(id_match.group(1))
                    break
    except Exception:
        pass

    for item in list(book.get_items_of_type(ebooklib.ITEM_IMAGE)) + list(book.get_items_of_type(ebooklib.ITEM_COVER)):
        img = {
            "name": item.get_name(),
            "id": getattr(item, 'id', None),
            "media_type": item.media_type if hasattr(item, "media_type") else "unknown",
            "size_bytes": len(item.get_content()) if hasattr(item, "get_content") else 0,
            "is_cover": getattr(item, 'id', None) in cover_ids,
        }
        images.append(img)

    if args.type == "cover":
        images = [i for i in images if i.get("is_cover")]

    if args.list:
        emit({"file": args.epub, "images": images, "count": len(images)})
    elif args.extract:
        os.makedirs(args.extract, exist_ok=True)
        extracted = []
        for img in images:
            item = None
            for it in book.get_items_of_type(ebooklib.ITEM_IMAGE):
                if it.get_name() == img["name"]:
                    item = it
                    break
            if item and hasattr(item, "get_content"):
                fname = os.path.basename(img["name"])
                out_path = os.path.join(args.extract, fname)
                with open(out_path, "wb") as f:
                    f.write(item.get_content())
                extracted.append(out_path)
        emit({"file": args.epub, "extracted": len(extracted), "directory": args.extract})
    else:
        # Default: list
        emit({"file": args.epub, "images": images, "count": len(images)})


if __name__ == "__main__":
    main()