尚硅谷Python爬虫教程小白零基础速通（含python基础+爬虫案例）

P76 爬取星巴克图片源码：

# 下载星巴克所有产品图片


import urllib.request as ur
import os
from lxml import etree
import threading

url = 'https://www.starbucks.com.cn/menu/'

response = ur.urlopen(url)
content = response.read().decode('utf-8')

tree = etree.HTML(content)

# 提取图片地址属性
src_list = tree.xpath("//div[@class='preview circle']/@style")
name_list = tree.xpath("//strong/text()")

# 拼接图片地址
images_url_list = [url[:-6] + src[23:-2] for src in src_list]

# 创建目录用于保存图片
os.makedirs('../starbucks_images', exist_ok=True)


# 下载图片的线程函数
def download_image(image_url, filename, index):
    try:
        ur.urlretrieve(image_url, filename)
        print(f"下载图片{index}: {filename} 完成")
    except Exception as e:
        print(f"下载图片{index}: {filename} 时出错: {str(e)}")


# 多线程下载图片
threads = []
for i, (image_url, name) in enumerate(zip(images_url_list, name_list)):
    filename = f'../starbucks_images/{name.replace("/", " or ")}.jpg'
    thread = threading.Thread(target=download_image, args=(image_url, filename, i + 1))
    threads.append(thread)
    thread.start()

# 等待所有线程完成
for thread in threads:
    thread.join()

print("图片下载完成")