在终端输出上读取pdf 2列到1列

pip install PyPDF2
pip install tabulate

import PyPDF2
from tabulate import tabulate

def read_pdf_columns_to_single_column(file_path):
    pdf_file = open(file_path, 'rb')
    pdf_reader = PyPDF2.PdfReader(pdf_file)

    # 读取PDF文件的每一页内容，并将两列合并为一列
    merged_column = []
    for page in pdf_reader.pages:
        text = page.extract_text()
        lines = text.split('\n')
        for i in range(0, len(lines), 2):
            if i+1 < len(lines):
                merged_column.append([lines[i], lines[i+1]])

    # 使用tabulate库将合并后的内容输出到终端
    print(tabulate(merged_column, headers=['Column 1', 'Column 2'], tablefmt='grid'))

    pdf_file.close()

# 调用函数并传入PDF文件的路径
read_pdf_columns_to_single_column('path/to/pdf_file.pdf')