玖叶教程网

Python抓取图片

import os

import requests

from bs4 import BeautifulSoup

from urllib.parse import urljoin

# 配置请求头，模拟浏览器行为

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'}

# 爬取图片的函数

def download_images(url, output_folder):

response = requests.get(url, headers=headers)

soup = BeautifulSoup(response.text, 'html.parser')

img_tags = soup.find_all('img')

if not os.path.exists(output_folder):

os.makedirs(output_folder)

for img in img_tags:

img_url = img.attrs.get('src')

if not img_url:

continue

img_url = urljoin(url, img_url)

try:

img_data = requests.get(img_url, headers=headers, timeout=5).content

file_name = os.path.join(output_folder, img_url.split("/")[-1])

with open(file_name, 'wb') as handler:

handler.write(img_data)

print(f"Downloaded image: {file_name}")

except Exception as e:

print(f"Error downloading image: {img_url}. Error: {e}")

# 主程序开始执行

if __name__ == '__main__':

target_url = 'https://example.com' # 替换为你要爬取的网站URL

output_folder = 'images' # 图片保存的文件夹名称

download_images(target_url, output_folder)