如何整合Python代码遍历Excel UPC列表拼接URL实现循环请求产品数据

import requests
import json
import pandas as pd
import time

def get_upc_info(upc_code):
    headers = {
        'Content-Type': 'application/json',
        'Accept': 'application/json',
        'Accept-Encoding': 'gzip,deflate',
    }
    try:
        resp = requests.get(f'https://api.upcitemdb.com/prod/trial/lookup?upc={upc_code}', headers=headers, timeout=10)
        resp.raise_for_status()
        data = json.loads(resp.text)
        if 'items' not in data or len(data['items']) == 0:
            print(f"UPC:{upc_code} 未查询到对应商品信息")
            return
        for item in data['items']:
            print("{}\t{}\t{}\t{}-{}".format(item['ean'], item['title'], item['brand'], item['lowest_recorded_price'], item['highest_recorded_price']))
            for offer in item['offers']:
                print("{}\t{}\t{}".format(offer['domain'], offer['title'], offer['price']))
        print("-"*50)
    except Exception as e:
        print(f"UPC:{upc_code} 处理失败，错误信息：{str(e)}")

if __name__ == '__main__':
    xl = pd.ExcelFile("C:/Users/Cody Sparrow/Desktop/Collection.xlsx")
    df = xl.parse("Sheet1")
    for i in df.index:
        current_upc = str(df.loc[i, 'Barcode'])
        print(f"正在处理第{i+1}条UPC：{current_upc}")
        get_upc_info(current_upc)
        # 可根据接口限流要求调整休眠时间，避免请求被拦截
        time.sleep(1)

• 补充了原Excel读取代码缺失的import pandas as pd导入语句，同时修正了循环取值逻辑：原代码print(df['Barcode'])会每次打印整列UPC，改为取当前行的单个UPC值df.loc[i, 'Barcode']
• 将UPC爬取逻辑封装为独立函数，适配循环调用场景
• 增加了基础异常处理，避免请求超时、UPC无效、返回数据结构异常时程序直接崩溃
• 新增了请求间隔控制，避免短时间请求过多触发接口限流规则

内容的提问来源于stack exchange，提问作者Cody Arnold