用Python抓取Naver图片：官方API、分页与CSV导出

python3 -m venv .venv
source .venv/bin/activate
python -m pip install requests
export NAVER_CLIENT_ID='你的 Client ID'
export NAVER_CLIENT_SECRET='你的 Client Secret'

py -m venv .venv
.\.venv\Scripts\python.exe -m pip install requests
$env:NAVER_CLIENT_ID = '你的 Client ID'
$env:NAVER_CLIENT_SECRET = '你的 Client Secret'

"""将 Naver 图片搜索 API 元数据导出为 CSV。"""
import argparse
import csv
import os
import re
from html import unescape

import requests

API_URL = "https://openapi.naver.com/v1/search/image"
FIELDNAMES = ["query", "title", "image_url", "thumbnail_url", "width", "height"]


def clean_title(value):
    return unescape(re.sub(r"<[^>]+>", "", value or ""))


def fetch_images(query, limit, client_id, client_secret, session=None):
    if not 1 <= limit <= 1000:
        raise ValueError("limit must be between 1 and 1000")
    http = session or requests.Session()
    headers = {
        "X-Naver-Client-Id": client_id,
        "X-Naver-Client-Secret": client_secret,
    }
    rows = []
    for start in range(1, limit + 1, 100):
        display = min(100, limit - len(rows))
        response = http.get(
            API_URL,
            headers=headers,
            params={"query": query, "display": display, "start": start, "sort": "sim"},
            timeout=20,
        )
        response.raise_for_status()
        payload = response.json()
        if not isinstance(payload, dict) or not isinstance(payload.get("items"), list):
            raise ValueError("API 响应缺少 items 列表")
        items = payload["items"]
        for item in items:
            rows.append({
                "query": query,
                "title": clean_title(item.get("title")),
                "image_url": item.get("link", ""),
                "thumbnail_url": item.get("thumbnail", ""),
                "width": item.get("sizewidth", ""),
                "height": item.get("sizeheight", ""),
            })
        if len(items) < display:
            break
    return rows


def main():
    parser = argparse.ArgumentParser()
    parser.add_argument("query", help="搜索词，例如 seoul skyline")
    parser.add_argument("--limit", type=int, default=100)
    parser.add_argument("--output", default="naver_images.csv")
    args = parser.parse_args()
    client_id = os.environ.get("NAVER_CLIENT_ID")
    client_secret = os.environ.get("NAVER_CLIENT_SECRET")
    if not client_id or not client_secret:
        parser.error("请先设置 NAVER_CLIENT_ID 和 NAVER_CLIENT_SECRET")
    if not args.query.strip() or not 1 <= args.limit <= 1000:
        parser.error("query 不能为空，limit 必须为 1–1000")
    try:
        rows = fetch_images(args.query, args.limit, client_id, client_secret)
    except requests.HTTPError as exc:
        response = exc.response
        status = response.status_code if response is not None else None
        advice = {
            400: "检查 query、display、start 和 sort 参数。",
            401: "检查 Client ID 和 Client Secret。",
            403: "检查应用权限及 Search API 是否已启用。",
            429: "检查速率限制和每日配额；更换代理不会增加配额。",
        }.get(status, "核对 API 状态及官方错误文档。")
        if status == 429 and response is not None:
            retry_after = response.headers.get("Retry-After")
            if retry_after:
                advice += f" 服务端建议的 Retry-After：{retry_after}。"
        parser.exit(1, f"API 请求失败（HTTP {status}）：{advice}\n本次未写入 CSV。\n")
    except requests.Timeout:
        parser.exit(1, "请求超时：检查网络连接。本次未写入 CSV。\n")
    except (requests.RequestException, ValueError, TypeError):
        parser.exit(1, "请求或响应解析失败：检查网络和 API 响应格式。本次未写入 CSV。\n")
    with open(args.output, "w", encoding="utf-8-sig", newline="") as file:
        writer = csv.DictWriter(file, fieldnames=FIELDNAMES)
        writer.writeheader()
        writer.writerows(rows)
    print(f"已保存 {len(rows)} 条记录到 {args.output}")


if __name__ == "__main__":
    main()

python naver_image_api.py 'seoul skyline' --limit 120 --output naver_images.csv

.\.venv\Scripts\python.exe naver_image_api.py 'seoul skyline' --limit 120 --output naver_images.csv

已保存 1 条记录到 demo.csv
query,title,image_url,thumbnail_url,width,height
首尔风景,서울 & 中国,https://example.org/a,https://example.org/t,100,80