PDF 文件转换为 Word 文件

代码功能概述

这段 Python 代码定义了一个名为 pdf_to_word 的函数，其主要功能是将 PDF 文件转换为 Word 文件。它支持转换整个 PDF 文件，也可以根据指定的页码范围进行转换。函数会对输入的参数进行检查，确保 PDF 文件存在且路径为字符串类型，转换完成后会返回包含转换结果信息（如文件大小、转换耗时、错误码和错误信息等）的字典。

if __name__ == "__main__":
    pdf_path = "example.pdf"
    result = pdf_to_word(pdf_path)
    print(result)

import os
import time
import logging
from pdf2docx import Converter

# 配置日志记录
logging.basicConfig(level=logging.ERROR, format='%(asctime)s - %(levelname)s - %(message)s')

def get_file_info(pdf_path):
    """
    提取PDF文件的目录和文件名（不含扩展名）
    :param pdf_path: PDF文件路径
    :return: 文件目录和文件名（不含扩展名）
    """
    file_dir = os.path.dirname(pdf_path)
    file_name = os.path.splitext(os.path.basename(pdf_path))[0]
    return file_dir, file_name

def validate_page_nums(page_nums):
    """
    验证页码参数的有效性
    :param page_nums: 页码参数，如 '1,3-5'
    :return: 有效的页码列表，如果无效则返回 None
    """
    try:
        pages = []
        for part in page_nums.split(','):
            if '-' in part:
                start, end = map(int, part.split('-'))
                if start <= 0 or end < start:
                    return None
                pages.extend(range(start - 1, end))
            else:
                page = int(part)
                if page <= 0:
                    return None
                pages.append(page - 1)
        return pages
    except ValueError:
        return None

def pdf_to_word(pdf_path, word_path=None, page_nums=None):
    """
    @方法名称: pdf转word
    @中文注释: pdf转word
    @入参:
        @param pdf_path str pdf文件路径
        @param page_nums str 页码序号
    @出参:
        @返回状态:
            @return 0 失败或异常
            @return 1 成功
        @返回错误码
        @返回错误信息
        @param doc_file str word文件名
    @使用范例: pdf_to_word('test.pdf')
    """
    result_dict = {
        "status": 0,
        "error_code": "",
        "error_msg": "",
        "file_size_mb": 0,
        "recognize_time": 0,
        "filename": ""
    }
    try:
        if not isinstance(pdf_path, str):
            result_dict["error_code"] = "111111"
            result_dict["error_msg"] = "pdf文件路径参数类型错误,不为字符串"
            return result_dict
        if not os.path.isfile(pdf_path):
            result_dict["error_code"] = "999999"
            result_dict["error_msg"] = f"PDF文件未找到: {pdf_path}"
            return result_dict

        start_time = time.time()

        if not word_path:
            file_dir, file_name = get_file_info(pdf_path)
            word_path = os.path.join(file_dir, f'{file_name}.docx')

        if page_nums:
            pages = validate_page_nums(page_nums)
            if pages is None:
                result_dict["error_code"] = "222222"
                result_dict["error_msg"] = "页码参数格式错误"
                return result_dict
        else:
            pages = None

        with Converter(pdf_path) as cv:
            if pages:
                cv.convert(docx_filename=word_path, pages=pages)
            else:
                cv.convert(docx_filename=word_path, start=0)

        file_size = os.path.getsize(word_path)
        file_size_mb = round(file_size / (1024 * 1024), 2)
        result_dict["file_size_mb"] = file_size_mb

        end_time = time.time()
        recognize_time = (end_time - start_time) * 1000
        recognize_time = round(recognize_time, 2)
        result_dict["recognize_time"] = recognize_time
        result_dict["error_code"] = "000000"
        result_dict["error_msg"] = "pdf转word成功"
        result_dict["filename"] = os.path.basename(word_path)
        result_dict["status"] = 1

        return result_dict

    except Exception as e:
        logging.error(f"pdf转word异常: {e}")
        result_dict["error_code"] = "999999"
        result_dict["error_msg"] = "PDF到Word转换过程中发生错误," + str(e)
        return result_dict

测试代码示例

if __name__ == "__main__":
    pdf_path = "example.pdf"
    result = pdf_to_word(pdf_path)
    print(result)