基于Pyqt5和PaddleOCR实现PDF转DOC

news2024/11/26 19:34:00

在上一篇文章《基于Pyqt5实现笔记本摄像头拍照及PaddleOCR测试》的基础上，继续做了个简单的扩展：
将PDF文档转换为DOC文档。

一、界面增加一个按钮，如下图：
在这里插入图片描述

二、源码修改
1、paddleocr.py文件直接拷贝 Github下载的源码PaddleOCR-release-2.6中的文件，但要注释掉def main():那段代码。

2、修改ui后保存文件，回到PyCharm工程，ocr_camera.ui文件，然后右键，找到"External Tools"，选择PyUIC，更新ocr_camera.py文件。

3、main函数修改：
3.1、新增PDF转DOC按钮点击槽链接：
在这里插入图片描述
3.2、槽函数定义如下，实现打开文件夹选择pdf文件及转换功能。

   def pdfRecognition(self, image_dir):
        fname, _ = QFileDialog.getOpenFileName(self, '选择PDF文件', './', 'Image files(*.PDF *.pdf)')
        self.showtext.append("loadPDF {}".format(fname))
        self.PDFmain(fname)

    def PDFmain(self,image_dir):
        args = paddleocr.parse_args(mMain=True)
        args.use_pdf2docx_api=True
        args.recovery=True
        args.output='pdf'

        print("{}".format(image_dir))
        if paddleocr.is_link(image_dir):
            paddleocr.download_with_progressbar(image_dir, 'tmp.jpg')
            image_file_list = ['tmp.jpg']
        else:
            image_file_list = get_image_file_list(image_dir)
        if len(image_file_list) == 0:
            logger.error('no images find in {}'.format(image_dir))
            self.showtext.append('no images find in {}'.format(image_dir))
            return

        engine = paddleocr.PPStructure()

        for img_path in image_file_list:
            img_name = os.path.basename(img_path).split('.')[0]
            logger.info('{}{}{}'.format('*' * 10, img_path, '*' * 10))

            img, flag_gif, flag_pdf = paddleocr.check_and_read(img_path)
            if not flag_gif and not flag_pdf:
                img = cv2.imread(img_path)

            if args.recovery and args.use_pdf2docx_api and flag_pdf:
                from pdf2docx.converter import Converter
                docx_file = os.path.join(args.output,
                                         '{}.docx'.format(img_name))
                cv = Converter(img_path)
                cv.convert(docx_file)
                cv.close()
                logger.info('docx save to {}'.format(docx_file))
                self.showtext.append('docx save to {}'.format(docx_file))
                continue

            if not flag_pdf:
                if img is None:
                    logger.error("error in loading image:{}".format(img_path))
                    continue
                img_paths = [[img_path, img]]
            else:
                img_paths = []
                for index, pdf_img in enumerate(img):
                    os.makedirs(
                        os.path.join(args.output, img_name), exist_ok=True)
                    pdf_img_path = os.path.join(
                        args.output, img_name,
                        img_name + '_' + str(index) + '.jpg')
                    cv2.imwrite(pdf_img_path, pdf_img)
                    img_paths.append([pdf_img_path, pdf_img])

            all_res = []
            for index, (new_img_path, img) in enumerate(img_paths):
                logger.info('processing {}/{} page:'.format(index + 1,
                                                            len(img_paths)))
                self.showtext.append('processing {}/{} page:'.format(index + 1,
                                                            len(img_paths)))
                new_img_name = os.path.basename(new_img_path).split('.')[0]
                result = engine(new_img_path, img_idx=index)
                paddleocr.save_structure_res(result, args.output, img_name, index)

                if args.recovery and result != []:
                    from copy import deepcopy
                    from ppstructure.recovery.recovery_to_doc import sorted_layout_boxes
                    h, w, _ = img.shape
                    result_cp = deepcopy(result)
                    result_sorted = sorted_layout_boxes(result_cp, w)
                    all_res += result_sorted

            if args.recovery and all_res != []:
                try:
                    from ppstructure.recovery.recovery_to_doc import convert_info_docx
                    convert_info_docx(img, all_res, args.output, img_name)
                except Exception as ex:
                    logger.error(
                        "error in layout recovery image:{}, err msg: {}".format(
                            img_name, ex))
                    continue

            for item in all_res:
                item.pop('img')
                item.pop('res')
                logger.info(item)
            logger.info('result save to {}'.format(args.output))
            self.showtext.append('processing {}/{} page:'.format(index + 1,
                                            len(img_paths)))

三、编译

编译时报错：AttributeError: ‘Document’ object has no attribute ‘pageCount’
网上查说是PyMuPDF版本不对，安装1.18.14版本