Python如何爬取觅知网素材图片

# Python如何爬取觅知网素材图片

在当今数字化时代，图片素材的需求日益增长，觅知网作为国内知名的素材平台，提供了大量高质量的图片资源。本文将详细介绍如何使用Python爬取觅知网素材图片，涵盖技术实现、注意事项及完整代码示例。

## 一、准备工作

### 1.1 环境配置
- Python 3.6+
- 第三方库：`requests`、`BeautifulSoup4`、`os`
- 安装命令：
  ```bash
  pip install requests beautifulsoup4

import requests

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'
}
url = 'https://www.51miz.com/shipin/'
response = requests.get(url, headers=headers)

from bs4 import BeautifulSoup

soup = BeautifulSoup(response.text, 'html.parser')
img_tags = soup.find_all('img', class_='lazy')  # 根据实际class调整
img_urls = [img['data-original'] for img in img_tags if 'data-original' in img.attrs]

   api_url = 'https://www.51miz.com/api/search'
   params = {'keyword': '风景', 'page': 1}
   api_response = requests.get(api_url, params=params, headers=headers)
   data = api_response.json()
   img_urls = [item['thumb_url'] for item in data['list']]

import os

save_dir = 'downloaded_images'
os.makedirs(save_dir, exist_ok=True)

for idx, url in enumerate(img_urls):
    try:
        img_data = requests.get(url, headers=headers).content
        with open(f'{save_dir}/image_{idx}.jpg', 'wb') as f:
            f.write(img_data)
        print(f'下载完成: {url}')
    except Exception as e:
        print(f'下载失败: {url}, 错误: {e}')

proxies = {'http': 'http://123.45.67.89:8080'}
response = requests.get(url, headers=headers, proxies=proxies)

import random

user_agents = [
    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) ...',
    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) ...'
]
headers['User-Agent'] = random.choice(user_agents)

import os
import time
import random
import requests
from bs4 import BeautifulSoup

# 配置
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'
}
save_dir = 'mizhi_images'
os.makedirs(save_dir, exist_ok=True)

def download_images(keyword, max_pages=3):
    for page in range(1, max_pages + 1):
        url = f'https://www.51miz.com/s?q={keyword}&page={page}'
        try:
            response = requests.get(url, headers=headers)
            soup = BeautifulSoup(response.text, 'html.parser')
            img_tags = soup.select('.image-item img[data-src]')
            
            for idx, img in enumerate(img_tags):
                img_url = img['data-src']
                if not img_url.startswith('http'):
                    img_url = 'https:' + img_url
                try:
                    img_data = requests.get(img_url, headers=headers).content
                    with open(f'{save_dir}/{keyword}_p{page}_{idx}.jpg', 'wb') as f:
                        f.write(img_data)
                    print(f'Page {page}: 下载成功 {img_url}')
                except Exception as e:
                    print(f'下载失败: {e}')
            time.sleep(random.uniform(1, 3))
        except Exception as e:
            print(f'请求失败: {e}')

if __name__ == '__main__':
    download_images('风景', max_pages=2)