Python script to extract Apple Dictionary entries from AppleDict source XML format.

extract_appledict_entries.py

"""
Script to extract Apple Dictionary entries from AppleDict source XML format to HTML files.
You will need to use pyglossary to extract the dictionary's Body.data to XML first.

Usage:
    python extractentries.py input.xml output_folder/
"""

import os
import re
import sys
from tqdm import tqdm


def sanitize_filename(title: str) -> str:
    """Make `<d:title>` safe for filenames"""
    return re.sub(r"[^\w\-_.]", "_", title.strip())


def extract_entries(xml_path: str, output_dir: str):
    """Extract Apple Dictionary entries from AppleDict source XML format"""
    os.makedirs(output_dir, exist_ok=True)

    with open(xml_path, "r", encoding="utf-8") as f:
        xml = f.read()

    chunks = xml.split("<d:entry")
    entry_count = 0

    for chunk in tqdm(chunks[1:], desc="Extracting entries", unit="entry"):
        full_entry = "<d:entry" + chunk
        closing_tag_index = full_entry.find("</d:entry>")

        if closing_tag_index == -1:
            continue  # skip malformed entry

        full_entry = full_entry[: closing_tag_index + len("</d:entry>")]

        title_match = re.search(r'd:title="(.*?)"', full_entry)
        title = title_match.group(1) if title_match else f"entry{entry_count}"

        safe_title = sanitize_filename(title)
        filename = f"{entry_count+1:05d}_{safe_title}.html"

        with open(
            os.path.join(output_dir, filename), "w", encoding="utf-8"
        ) as out_file:
            out_file.write(full_entry)

        entry_count += 1

    print(f"✅ Extracted {entry_count} entries to: {output_dir}")


if __name__ == "__main__":
    if len(sys.argv) != 3:
        print("Usage: python extract_appledict_entries.py input.xml output_folder/")
        sys.exit(1)

    input_xml = sys.argv[1]
    output_folder = sys.argv[2]

    extract_entries(input_xml, output_folder)