从HTML表中提取数据以将值存储在变量中

from bs4 import BeautifulSoup

# 假设HTML表格内容如下：
html = """
<table>
  <tr>
    <th>姓名</th>
    <th>年龄</th>
    <th>性别</th>
  </tr>
  <tr>
    <td>张三</td>
    <td>25</td>
    <td>男</td>
  </tr>
  <tr>
    <td>李四</td>
    <td>30</td>
    <td>女</td>
  </tr>
</table>
"""

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

# 定位到表格元素
table = soup.find('table')

# 初始化存储数据的变量
data = []

# 遍历表格的行和列
for row in table.find_all('tr'):
    row_data = []
    for cell in row.find_all('td'):
        row_data.append(cell.text)
    data.append(row_data)

# 打印提取的数据
for row in data:
    print(row)

['张三', '25', '男']
['李四', '30', '女']