chachong/docx_extract.py

import os
import docx
import mysql_pool
from pymysql.converters import escape_string
import xlsxwriter
import uuid


def read_docx(file_path):
    mysql = mysql_pool.ConnMysql()
    # print(os.path.abspath('丽水市本级信息化项目建设方案模板.docx'))
    # url = "http://jobapi.ningdatech.com/prometheus-yw_file_service/files/20240919/669f323c5c824f89a34bf04a66105902.doc"
    # file_name = "丽水市本级信息化项目建设方案模板.docx"
    # file_path = os.path.join("temp", file_name)
    excel_path = f"/Users/kebobo/fsdownload/dup_check/temp/{uuid.uuid4()}.xls"
    try:
        # r = requests.get(url)
        # with open(file_path, "wb") as code:
        #     code.write(r.content)

        # # 转化文件格式
        # convert_doc_to_docx(file_path, file_path.replace('.doc', '.docx'))
        # file_path = file_path.replace('.doc', '.docx')
        # 读取文件
        # doc = docx.Document(os.path.abspath(file_path))
        doc = docx.Document(file_path)
        # 是否开始获取文本
        is_acquire = 0
        is_project_name = 0
        content = []
        # 功能模块
        feature_map = {}
        # 功能名
        feature_name = ""
        # 项目名
        xmmc = ""
        for para in doc.paragraphs:
            style = para.style.name
            print(f"style: {para.style.name}, value: {para.text}")
            if str(style).find('toc') == 1:
                continue
            # 获取文档项目名称
            if para.text.find('项目名称') != -1:
                is_project_name = 1
            elif para.text.find('项目类型') != -1:
                is_project_name = 0
            if is_project_name == 1:
                if str(style).find('Heading') == -1 and str(style).find('toc') == -1:
                    xmmc = para.text

            if para.text == '3.1.2 建设内容':
                is_acquire = 1
            elif para.text == '3.2 整体架构设计':
                is_acquire = 0
            if is_acquire == 1:
                if str(style).find('Heading') == -1:
                    # print(f"content: {para.text}, style: {para.style.name}")
                    feature_map[feature_name] = para.text
                    # 重置功能名
                    feature_name = ""
                    content.append(para.text)
                else:
                    feature_map[para.text] = ""
                    feature_name = para.text

        # 使用next函数逐个获取元素
        # for key, value in feature_map.items():
        #     if key != "3.1.2 建设内容" and key != "":
        #         print(f"Key: {key}, Value: {value}")
        #         # 将功能描述入库
        #         mysql.sql_change_msg(
        #             """insert into user_history_module_data(xmmc,gnmc,gnms,line, remark) value("%s", "%s", "%s", "%s", "%s")""" % (
        #                 escape_string(xmmc), escape_string(key), escape_string(value), "", "自动拆解导入"))

        # 生成excel文件(兼容老版本, 减少改动量)
        workbook = xlsxwriter.Workbook(excel_path)
        worksheet = workbook.add_worksheet("Sheet1")
        worksheet.write('A1', '项目名称')
        worksheet.write('B1', escape_string(xmmc))

        i = 0
        for key, value in feature_map.items():
            if key != "3.1.2 建设内容" and key != "":
                i = i + 1
                worksheet.write(f"A{i + 1}", '功能模块')
                worksheet.write(f"B{i + 1}", escape_string(key))
                worksheet.write(f"C{i + 1}", '功能描述')
                worksheet.write(f"D{i + 1}", escape_string(value))
        workbook.close()
        return excel_path


    finally:
        # os.remove(file_path)
        # print("删除文件")
        print("转换完成")

    return "\n".join(content)


def convert_doc_to_docx(doc_file, docx_file):
    try:
        if doc_file.endswith('.doc'):
            # 创建一个新的.docx文件
            docx_document = docx.Document()

            # 读取.doc文件的内容
            with open(doc_file, 'rb') as doc:
                content = doc.read()

            # 将.doc文件的内容写入.docx文件
            docx_document.add_paragraph(content)

            # 保存.docx文件
            docx_document.save(docx_file)
    finally:
        os.remove(doc_file)


# file_path = "丽水市本级信息化项目建设方案模板.docx"
# doc_content = read_docx()
# print(doc_content)