Bulk Download Images from a CSV of URLs

#!/usr/bin/env python3
"""Download images in parallel from a CSV list of URLs.

CSV: first column is the URL; optional second column is a file name.

Dependency: pip install requests
"""
import argparse
import csv
import os
import re
from concurrent.futures import ThreadPoolExecutor, as_completed
from urllib.parse import urlparse

import requests


def read_url_rows(path):
    """Yield (url, name_or_None) tuples from the CSV."""
    with open(path, newline="", encoding="utf-8") as f:
        for row in csv.reader(f):
            if not row or not row[0].strip():
                continue
            url = row[0].strip()
            if url.lower() == "url":  # skip a header line
                continue
            name = row[1].strip() if len(row) > 1 and row[1].strip() else None
            yield url, name


def filename_from_url(url, index):
    """Derive a safe file name from the URL path."""
    path = urlparse(url).path
    base = os.path.basename(path) or f"image_{index}"
    base = re.sub(r"[^A-Za-z0-9._-]+", "_", base)
    return base


def download_one(url, name, outdir, index, timeout):
    """Download a single image; return (url, status_string)."""
    try:
        resp = requests.get(url, timeout=timeout, stream=True)
        resp.raise_for_status()
        fname = name or filename_from_url(url, index)
        out_path = os.path.join(outdir, fname)
        with open(out_path, "wb") as f:
            for chunk in resp.iter_content(chunk_size=8192):
                f.write(chunk)
        return url, f"OK -> {out_path}"
    except requests.RequestException as exc:
        return url, f"FAILED ({exc})"


def main():
    parser = argparse.ArgumentParser(description="Bulk image downloader.")
    parser.add_argument("csv_file", help="CSV with image URLs.")
    parser.add_argument("-o", "--outdir", default="images",
                        help="Output directory (default: images).")
    parser.add_argument("-j", "--workers", type=int, default=8,
                        help="Parallel download workers (default: 8).")
    parser.add_argument("-t", "--timeout", type=float, default=20.0,
                        help="Per-request timeout seconds (default: 20).")
    args = parser.parse_args()

    os.makedirs(args.outdir, exist_ok=True)
    rows = list(read_url_rows(args.csv_file))

    ok = 0
    fail = 0
    with ThreadPoolExecutor(max_workers=args.workers) as pool:
        futures = {
            pool.submit(download_one, url, name, args.outdir, i, args.timeout): url
            for i, (url, name) in enumerate(rows, start=1)
        }
        for fut in as_completed(futures):
            url, status = fut.result()
            print(status)
            if status.startswith("OK"):
                ok += 1
            else:
                fail += 1

    print(f"\nDone. {ok} succeeded, {fail} failed, {len(rows)} total.")


if __name__ == "__main__":
    main()