mini_code/test111.py

import time
from loguru import *
from urllib.parse import urlparse, parse_qs

import pandas as pd
from DrissionPage import *

if __name__ == '__main__':

    co = ChromiumOptions()
    co.set_local_port(9999)

    page = ChromiumPage(addr_or_opts=co)

    # 读取 Excel 文件
    excel_file = pd.ExcelFile('sample_items_1000_api.xlsx')

    # 获取指定工作表中的数据
    df = excel_file.parse('in')

    # 读取第一列数据
    first_column = df.iloc[:, 0]

    # 逐行遍历第一列数据
    n = 0
    n1 = 0
    for value in first_column:
        print(value)

        # 解析 URL
        parsed_url = urlparse(value)

        # 提取查询参数部分
        query_params = parsed_url.query

        # 解析查询参数为字典
        param_dict = parse_qs(query_params)

        a = time.time()
        tab = page.new_tab()
        tab.listen.start("shopee.tw/api/v4/pdp/get_pc")
        tab.get(f"https://shopee.tw/product/{param_dict['shop_id'][0]}/{param_dict['item_id'][0]}")
        res = tab.listen.wait(timeout=15)
        print(res.response.body)
        if res.response.body.get("data", {}).get("item", {}):
            n += 1
            n1 += time.time() - a

            logger.info(f"成功第{n}个，耗时{time.time() - a}秒")
            logger.success(f"成功第{n}个，一共耗时{n1}秒")

        tab.close()