用Python实现亚马逊Amazon高性能爬虫采集销量信息

import requests
from bs4 import BeautifulSoup
import pandas as pd

# 设置用户代理，以模拟真实的浏览器访问
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'}

# 获取ASIN对应的销量信息
def get_product_ranking(asin):
    url = f'https://www.amazon.com/dp/{asin}/ref=cm_cr_arp_d_paging_btm_2?ie=UTF8'
    try:
        response = requests.get(url, headers=headers)
        response.raise_for_status()
        soup = BeautifulSoup(response.text, 'html.parser')

        # 解析销量信息
        ranking_data = soup.find('li', {'id': 'SalesRank'})
        if ranking_data:
            ranking = ranking_data.text.strip()
        else:
            ranking = 'N/A'

        return ranking
    except requests.RequestException as e:
        print(f'Error: {e}')
        return 'Error'

# 示例：获取ASIN为B01M8YGI1Y的产品销量信息
ranking = get_product_ranking('B01M8YGI1Y')
print(ranking)