如何在python中解析html表

pip install beautifulsoup4 lxml

<table>
    <tr>
        <th>姓名</th>
        <th>年龄</th>
    </tr>
    <tr>
        <td>张三</td>
        <td>28</td>
    </tr>
    <tr>
        <td>李四</td>
        <td>35</td>
    </tr>
</table>

from bs4 import BeautifulSoup

html_doc = """
<table>
    <tr>
        <th>姓名</th>
        <th>年龄</th>
    </tr>
    <tr>
        <td>张三</td>
        <td>28</td>
    </tr>
    <tr>
        <td>李四</td>
        <td>35</td>
    </tr>
</table>
"""

soup = BeautifulSoup(html_doc, 'lxml')

# 找到所有的行
rows = soup.find_all('tr')

# 遍历每一行
for row in rows:
    # 找到当前行的所有单元格
    cells = row.find_all(['td', 'th'])
    # 提取单元格数据
    row_data = [cell.get_text() for cell in cells]
    print(row_data)

pip install lxml

from lxml import etree

html_doc = """
<table>
    <tr>
        <th>姓名</th>
        <th>年龄</th>
    </tr>
    <tr>
        <td>张三</td>
        <td>28</td>
    </tr>
    <tr>
        <td>李四</td>
        <td>35</td>
    </tr>
</table>
"""

# 解析HTML
tree = etree.HTML(html_doc)

# 使用XPath选择所有的行
rows = tree.xpath('//tr')

# 遍历每一行
for row in rows:
    # 使用XPath选择当前行的所有单元格
    cells = row.xpath('.//td | .//th')
    # 提取单元格数据
    row_data = [cell.text for cell in cells]
    print(row_data)