【实战教程】CodeBuddy智能爬虫：一键批量下载高清美图

将该http://www.netbian.com/mei/ 网址中的图片使用py脚本下载到本地，具体要求如下:
1. 通过我提供的xpath获取图片的地址以及图片名称  
img_urls = xp.xpath('//ul/li/a/img/@src')
img_names = xp.xpath('//ul/li/a/img/@alt')

import os
import requests
from lxml import html
from urllib.parse import urljoin
import time
import random


def download_images_with_xpath(url, save_folder='downloaded_images', max_images=20):
    """
    使用XPath从指定网址下载图片到本地

    参数:
        url: 要抓取的网页URL
        save_folder: 图片保存目录
        max_images: 最多下载图片数量
    """
    # 创建保存目录
    if not os.path.exists(save_folder):
        os.makedirs(save_folder)

    # 设置请求头模拟浏览器访问
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
        'Referer': 'http://www.netbian.com/'
    }

    try:
        # 获取网页内容
        response = requests.get(url, headers=headers, timeout=10)
        response.raise_for_status()

        # 解析HTML
        tree = html.fromstring(response.content)

        # 使用提供的XPath获取图片URL和名称
        img_urls = tree.xpath('//ul/li/a/img/@src')
        img_names = tree.xpath('//ul/li/a/img/@alt')

        # 确保获取到的数据长度一致
        min_length = min(len(img_urls), len(img_names), max_images)
        img_urls = img_urls[:min_length]
        img_names = img_names[:min_length]

        downloaded_count = 0

        for img_url, img_name in zip(img_urls, img_names):
            if downloaded_count >= max_images:
                break

            try:
                # 处理相对URL
                full_img_url = urljoin(url, img_url)

                # 过滤非图片的URL
                if not full_img_url.lower().endswith(('.jpg', '.jpeg', '.png', '.gif', '.webp')):
                    continue

                # 清理图片名称（移除非法字符）
                clean_name = ''.join(c for c in img_name if c.isalnum() or c in (' ', '_', '-')).strip()
                if not clean_name:
                    clean_name = f"image_{downloaded_count + 1}"

                # 下载图片
                img_data = requests.get(full_img_url, headers=headers, timeout=15).content

                # 获取文件扩展名
                ext = os.path.splitext(full_img_url)[1].lower()
                if not ext:
                    ext = '.jpg'  # 默认扩展名

                # 生成保存路径
                filename = os.path.join(save_folder, f"{clean_name}{ext}")

                # 处理文件名冲突
                counter = 1
                while os.path.exists(filename):
                    filename = os.path.join(save_folder, f"{clean_name}_{counter}{ext}")
                    counter += 1

                # 保存图片
                with open(filename, 'wb') as f:
                    f.write(img_data)

                print(f"已下载: {filename} (原名: {img_name})")
                downloaded_count += 1

                # 随机延迟，避免请求过于频繁
                time.sleep(random.uniform(1.0, 2.5))

            except requests.exceptions.RequestException as e:
                print(f"下载图片失败: {img_url} - 错误: {e}")
                continue
            except Exception as e:
                print(f"处理图片时出错: {img_name} - 错误: {e}")
                continue

        print(f"\n下载完成! 共下载了 {downloaded_count} 张图片到 {save_folder} 目录")

    except requests.exceptions.RequestException as e:
        print(f"访问网页失败: {e}")
    except Exception as e:
        print(f"解析网页时出错: {e}")


if __name__ == "__main__":
    # 目标网址
    target_url = "http://www.netbian.com/mei/"

    # 下载图片
    download_images_with_xpath(
        target_url,
        save_folder='美女图片',
        max_images=30
    )