from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

# 初始化 WebDriver
driver = webdriver.Chrome()
driver.get("你的目标网页链接")

# 定义等待对象
wait = WebDriverWait(driver, 20)

# 提取表头数据
def extract_header_data():
    headers = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '.el-table__header-wrapper thead')))
    header_cols = headers.find_elements(By.TAG_NAME, 'th')
    columns = [col.text.strip() for col in header_cols if col.text.strip()]
    return columns

# 提取表体数据（包括隐藏元素的内容）
def extract_table_data():
    body = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '.el-table__body-wrapper tbody')))
    rows = body.find_elements(By.TAG_NAME, 'tr')

    data = []  # 存储表格数据
    for row in rows:
        row_data = []
        cols = row.find_elements(By.TAG_NAME, 'td')
        for col in cols:
            # 检查是否为隐藏内容
            try:
                # 尝试提取隐藏内容
                hidden_text = driver.execute_script("return arguments[0].textContent", col.find_element(By.XPATH, './/div'))
                row_data.append(hidden_text.strip())
            except Exception:
                # 如果无法提取隐藏内容，则使用可见内容
                row_data.append(col.text.strip())
        data.append(row_data)
    return data

# 提取并打印表头和表体数据
try:
    headers = extract_header_data()
    print("表头:", headers)

    table_data = extract_table_data()
    for row in table_data:
        print("表体行:", row)
finally:
    # 关闭浏览器
    driver.quit()