import os
import subprocess

from bs4 import BeautifulSoup
import pandas as pd
from datetime import datetime
import random
import string
from selenium import webdriver
from selenium.webdriver.chrome.service import Service


def generate_random_string(length=6):
    return ''.join(random.choices(string.ascii_letters + string.digits, k=length))

try:
    subprocess.run(
        ["taskkill", "/f", "/im", "chrome.exe"],
        stdout=subprocess.DEVNULL,
        stderr=subprocess.DEVNULL,
        check=True
    )
except subprocess.CalledProcessError:
    pass

user_data_dir = os.path.join(os.environ['LOCALAPPDATA'], r"Google\Chrome\User Data")

options = webdriver.ChromeOptions()
options.add_argument(f"user-data-dir={user_data_dir}")
service = Service(executable_path=r'C:\Windows\chromedriver.exe')

driver = webdriver.Chrome(options=options, service=service)

# 打开一个网页
driver.get("https://baidu.com")

while True:
    try:
        # 提示用户按回车开始读取网页内容
        input("请访问web表格所在页面，回车开始执行：")
        div_html = driver.page_source

        # 使用 BeautifulSoup 解析 HTML
        soup = BeautifulSoup(div_html, 'html.parser')

        # 获取 title 标签内容或生成随机字符串
        title_tag = soup.title.string if soup.title else generate_random_string()
        current_date = datetime.now().strftime("%m%d")

        # 找到所有表格
        tables = soup.find_all('table')

        num_tables = len(tables)
        if num_tables == 0:
            print("未找到表格，请检查页面内容。")
            continue

        print(f"*****识别到 {num_tables} 个表格*****")

        dataframes = []
        for i, table in enumerate(tables):
            rows = []
            for row in table.find_all('tr'):
                cols = row.find_all(['td', 'th'])
                cols = [ele.text.strip() for ele in cols]
                rows.append(cols)

            # 使用 pandas 将数据转换为 DataFrame
            df = pd.DataFrame(rows[1:], columns=rows[0])
            dataframes.append(df)

            print(f"\n======================预览数据 (表格 {i + 1})===========================")
            print(df.head())

        # 用户选择需要输出的表格序号
        selection = input(f"\n请输入要输出的表格序号 (1-{num_tables}) 或 'a' 输出所有表格: ").strip().lower()

        if selection == 'a':
            for i, df in enumerate(dataframes):
                excel_path = f'{title_tag}_{current_date}_table{i + 1}.xlsx'
                df.to_excel(excel_path, index=False)
                print(f"数据已保存到 {excel_path}")
        else:
            try:
                selected_table = int(selection) - 1
                if 0 <= selected_table < num_tables:
                    excel_path = f'{title_tag}_{current_date}_table{selected_table + 1}.xlsx'
                    dataframes[selected_table].to_excel(excel_path, index=False)
                    print(f"数据已保存到 {excel_path}")
                else:
                    print("无效的table序号。")
            except ValueError:
                print("请输入有效的序号")

    except Exception as e:
        if 'target window already closed' in str(e):
            print('监听窗口已关闭..')
            exit()
        print(f"发生错误: {e}")

    # 检查是否继续
    cont = input('继续处理？(y/其他退出): ')
    if cont.strip().lower() != 'y':
        driver.quit()
        break