Python实战：用代码爬取拼多多网页商品数据

import requests from bs4 import BeautifulSoup def scrape_pinduoduo(url): # 发送GET请求获取网页内容 response = requests.get(url) if response.status_code == 200: # 使用BeautifulSoup解析网页内容 soup = BeautifulSoup(response.content, 'html.parser') # 找到所有商品信息的标签 products = soup.find_all('div', class_='goods-item') results = [] # 遍历每个商品信息标签，提取所需数据 for product in products: # 提取商品名称 name = product.find('div', class_='goods-name').text.strip() # 提取商品价格 price = product.find('div', class_='price').text.strip() # 提取商品销量 sales = product.find('div', class_='sales').text.strip() # 将提取的数据添加到结果列表中 results.append({'name': name, 'price': price, 'sales': sales}) return results else: print('Failed to load page:', response.status_code) # 调用函数进行爬取 url = 'https://www.pinduoduo.com/' data = scrape_pinduoduo(url) # 打印爬取的数据 for item in data: print('Name:', item['name']) print('Price:', item['price']) print('Sales:', item['sales']) print('------------------') ######[AI写代码神器 | 882点数解答 | 2024-12-09 16:25:32]