如何使用Python从LaTeX表中提取数据

import re

def extract_data_from_latex_table(latex_table):
    # 匹配表格行
    row_pattern = r"\\hline\n(.+?)\\\\"
    rows = re.findall(row_pattern, latex_table, re.DOTALL)

    data = []
    for row in rows:
        # 匹配表格列
        col_pattern = r"(.+?) &"
        cols = re.findall(col_pattern, row)

        # 提取每列的数据
        row_data = []
        for col in cols:
            # 去除空格和换行符
            col = col.strip()
            row_data.append(col)

        data.append(row_data)

    return data

# 示例LaTeX表格
latex_table = r"""
\begin{tabular}{|c|c|c|}
\hline
Header 1 & Header 2 & Header 3 \\
\hline
Data 1 & Data 2 & Data 3 \\
\hline
Data 4 & Data 5 & Data 6 \\
\hline
\end{tabular}
"""

# 提取数据
table_data = extract_data_from_latex_table(latex_table)

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

['Header 1', 'Header 2', 'Header 3']
['Data 1', 'Data 2', 'Data 3']
['Data 4', 'Data 5', 'Data 6']