当前位置：首页 > article >正文

爬虫案例-爬取网页图片

article 2025/1/5 6:06:19

爬虫案例-爬取网页图片

1、安装依赖库
2、爬取图片的代码
3、效果图

1、安装依赖库

#以下是安装http请求的第三方库
pip install requests urllib3  
#以下是安装处理图片的第三方库
pip install image pillow
#以下是安装python解析html的第三方库
pip install beautifulsoup4

2、爬取图片的代码

import requests
import urllib3
import urllib.parse
import os
from io import BytesIO
from PIL import Image
from bs4 import BeautifulSoup

url = "URL"

http = urllib3.PoolManager()
header = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36 Edg/131.0.0.0"}
request = http.request('POST', url, headers=header)

'''以下测试用的
#响应数据
#print(request.data.decode())
#响应头信息
#print(request.headers)
#状态码
#print(request.status)
'''

data = request.data.decode()
#print(data)
soup = BeautifulSoup(data,"html.parser")

# 查找所有<img>标签
i = 0
for img_tag in soup.find_all("img"):
    i += 1
    image_url = img_tag.get("src")
    #print(image_url)
    output_folder = r"C:\Users\zzx\Desktop\图片"+"/"
    if not os.path.exists(output_folder):
        os.makedirs(output_folder)
        #print(image_url)
    if image_url:
        # 将可能的相对 URL 转换为完整的 URL
        image_url_http = urllib.parse.urljoin(url,image_url)
        #print(image_url_http)
        resp = requests.get(image_url_http,stream=True)
      #print(resp)
    try:
        image_data = BytesIO(resp.content)
      #print(image_data)
        image = Image.open(image_data)
        if '.gif' not in  image_url_http.split("/")[-1]:
            image.save(os.path.join(output_folder, f'image_{i}.png'))
            print(f"图像已成功保存到 {os.path.join(output_folder, f'image_{i}.png')}")
        elif '.gif' in image_url_http.split("/")[-1]:
            image.save(os.path.join(output_folder, f'image_{i}.gif'))
            print(f"图像已成功保存到 {os.path.join(output_folder, f'image_{i}.gif')}")
    except Exception as e :
        print(f"保存图像时出错:{e}")
        try:
            # 将图像转换为常见的 JPEG 格式
            if image.mode in ('RGBA', 'LA'):
                image = image.convert('RGB')
            image.save(os.path.join(output_folder, f'image_{i}.jpg'))
            print(f"图像已成功保存到 {os.path.join(output_folder, f'image_{i}.jpg')}")
        except Exception as e:
          print(f"转换并保存图像时出错: {e}")
    print(i,image_url)