python爬取指定网址图片代码

代码

import os
import requests
from bs4 import BeautifulSoup

# 指定要爬取的网址
url = 'https://www.baidu.com/'

# 请求网页内容
response = requests.get(url)
response.raise_for_status()  # 如果请求失败，将抛出异常

# 使用BeautifulSoup解析网页内容
soup = BeautifulSoup(response.text, 'html.parser')

# 创建存储图片的文件夹
folder_name = r'F:\jingguan\tu'
if not os.path.exists(folder_name):
    os.makedirs(folder_name)

# 找到网页中的所有<img>标签
img_tags = soup.find_all('img')

# 遍历所有的<img>标签，下载图片
for img in img_tags:
    src = img.get('src')  # 获取图片的src属性
    if src:
        # 完整的图片URL
        img_url = src if src.startswith(('http:', 'https:')) else url + src
        try:
            # 发送请求获取图片内容
            img_response = requests.get(img_url)
            img_response.raise_for_status()

            # 图片文件名
            img_name = os.path.join(folder_name, img_url.split('/')[-1])
            with open(img_name, 'wb') as f:
                f.write(img_response.content)
            print(f"图片已下载：{img_name}")
        except requests.exceptions.RequestException as e:
            print(f"下载图片时出错：{e}")

print("图片下载完成。")