1

2

3

4

5

6

7

8

from selenium import webdriver

import time

# 设置Selenium WebDriver

driver_path = 'path/to/chromedriver'

driver = webdriver.Chrome(executable_path=driver_path)

driver.get("商品详情页面URL")

# 等待页面加载完成

time.sleep(10)  # 根据实际情况调整等待时间

1

2

3

4

5

6

7

8

9

10

from bs4 import BeautifulSoup

# 获取页面源码

html = driver.page_source

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

# 根据页面结构提取商品信息

product_name = soup.find('div', {'class': 'product-name'}).text.strip()

product_price = soup.find('span', {'class': 'product-price'}).text.strip()

# 打印商品信息

print(f"商品名称: {product_name}")

print(f"商品价格: {product_price}")

1

2

3

4

5

import requests

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'

}

response = requests.get('目标URL', headers=headers)

1

2

3

4

5

6

7

8

import json

# 将商品信息存储为JSON格式

data = {

    'product_name': product_name,

    'product_price': product_price

}

with open('product_details.json', 'w', encoding='utf-8') as f:

    json.dump(data, f, ensure_ascii=False, indent=4)