获取HTML表标签<table><tbody><th><tr><td>之间的所有文本(单行和多行)并生成json

from bs4 import BeautifulSoup
import json

html = '''
<table>
  <tbody>
    <tr>
      <th>Header 1</th>
      <th>Header 2</th>
    </tr>
    <tr>
      <td>Row 1, Column 1</td>
      <td>Row 1, Column 2</td>
    </tr>
    <tr>
      <td>Row 2, Column 1</td>
      <td>Row 2, Column 2</td>
    </tr>
  </tbody>
</table>
'''

soup = BeautifulSoup(html, 'html.parser')
table = soup.find('table')
rows = table.find_all('tr')

data = []
for row in rows:
    columns = row.find_all('td')
    row_data = [column.get_text(strip=True) for column in columns]
    data.append(row_data)

json_data = json.dumps(data)
print(json_data)

[["Row 1, Column 1", "Row 1, Column 2"], ["Row 2, Column 1", "Row 2, Column 2"]]