python爬虫百度图片代码

Python爬取百度图片通常会用到`requests`库来发送HTTP请求获取网页内容，然后利用如BeautifulSoup、Pandas等库解析HTML，提取出图片链接。以下是一个简单的示例，展示如何使用`beautifulsoup4`库从搜索结果页抓取图片：

import requests
from bs4 import BeautifulSoup
import os

def get_baidu_image_links(keyword):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'
    }
    url = f'http://image.baidu.com/search/index?tn=baiduimage&ie=utf-8&word={keyword}'
    
    response = requests.get(url, headers=headers)
    soup = BeautifulSoup(response.text, 'lxml')
    
    # 图片链接通常在class为"i-bdimg"的元素中
    img_tags = soup.find_all('a', class_='i-bdimg')

    image_links = [img['href'] for img in img_tags]
    return image_links

# 下载并保存图片
def download_images(image_urls, save_dir='images'):
    if not os.path.exists(save_dir):
        os.makedirs(save_dir)

    for i, link in enumerate(image_urls[:10]):  # 通常只下载部分图片
        img_response = requests.get(link, headers=headers)
        with open(os.path.join(save_dir, f'image_{i+1}.jpg'), 'wb') as f:
            f.write(img_response.content)

# 使用示例
keyword = '猫'
image_links = get_baidu_image_links(keyword)
download_images(image_links)