在Python中将HTML表格转换为Pandas数据框

pip install beautifulsoup4
pip install pandas

import pandas as pd
from bs4 import BeautifulSoup

# 假设HTML表格保存在一个名为table.html的文件中
with open('table.html') as file:
    soup = BeautifulSoup(file, 'html.parser')

# 找到HTML表格
table = soup.find('table')

# 提取表头
headers = []
for th in table.find_all('th'):
    headers.append(th.text.strip())

# 提取表格数据
data = []
for row in table.find_all('tr'):
    row_data = []
    for td in row.find_all('td'):
        row_data.append(td.text.strip())
    if row_data:
        data.append(row_data)

# 创建Pandas数据框
df = pd.DataFrame(data, columns=headers)

# 打印数据框
print(df)