【工具教程】批量OCR识别PDF中文字，并根据文字对PDF批量重命名和导出表格，基于QT和腾讯API来完成

python复制import sys
import os
import json
from PyQt5.QtWidgets import QApplication, QMainWindow, QPushButton, QFileDialog, QLabel, QVBoxLayout, QWidget
from tencentcloud.common import credential
from tencentcloud.common.profile.client_profile import ClientProfile
from tencentcloud.common.profile.http_profile import HttpProfile
from tencentcloud.ocr.v20181119 import ocr_client, models

class MainWindow(QMainWindow):
    def __init__(self):
        super().__init__()
        self.initUI()

    def initUI(self):
        self.setWindowTitle('PDF OCR Rename')
        self.setGeometry(100, 100, 400, 200)

        self.central_widget = QWidget()
        self.setCentralWidget(self.central_widget)

        self.layout = QVBoxLayout()

        self.select_button = QPushButton('选择PDF文件夹', self)
        self.select_button.clicked.connect(self.select_folder)
        self.layout.addWidget(self.select_button)

        self.rename_button = QPushButton('开始OCR并重命名', self)
        self.rename_button.clicked.connect(self.start_rename)
        self.layout.addWidget(self.rename_button)

        self.status_label = QLabel('', self)
        self.layout.addWidget(self.status_label)

        self.central_widget.setLayout(self.layout)

        self.folder_path = ''
        self.secret_id = 'your_secret_id'
        self.secret_key = 'your_secret_key'

    def select_folder(self):
        self.folder_path = QFileDialog.getExistingDirectory(self, '选择PDF文件夹')
        if self.folder_path:
            self.status_label.setText(f'已选择文件夹: {self.folder_path}')

    def start_rename(self):
        if not self.folder_path:
            self.status_label.setText('请先选择文件夹')
            return

        for filename in os.listdir(self.folder_path):
            if filename.endswith('.pdf'):
                pdf_path = os.path.join(self.folder_path, filename)
                new_name = self.process_pdf(pdf_path)
                if new_name:
                    new_path = os.path.join(self.folder_path, new_name)
                    os.rename(pdf_path, new_path)
                    self.status_label.setText(f'重命名成功: {filename} -> {new_name}')

    def process_pdf(self, pdf_path):
        # 将PDF每一页转换为图片（此处省略具体实现）
        # 假设每一页保存为image_0.jpg, image_1.jpg, ...

        for page_num in range(0, 10):  # 假设PDF有10页
            image_path = f'image_{page_num}.jpg'
            # 调用OCR API
            text_detections = self.ocr_general_basic(image_path, self.secret_id, self.secret_key)
            # 提取关键信息（如文件名）
            for detection in text_detections:
                if '识别结果' in detection:
                    extracted_text = detection['DetectedText']
                    # 假设提取的文本可以作为新文件名
                    new_name = f'{extracted_text}.pdf'
                    return new_name
        return None

    def ocr_general_basic(self, image_path, secret_id, secret_key):
        cred = credential.Credential(secret_id, secret_key)
        httpProfile = HttpProfile()
        httpProfile.endpoint = "ocr.tencentcloudapi.com"

        clientProfile = ClientProfile()
        clientProfile.httpProfile = httpProfile
        client = ocr_client.OcrClient(cred, "ap-guangzhou", clientProfile)

        req = models.GeneralBasicOCRRequest()
        with open(image_path, 'rb') as f:
            img_data = f.read()
        params = {
            "ImageBase64": img_data.encode('base64')
        }
        req.from_json_string(json.dumps(params))

        resp = client.GeneralBasicOCR(req)
        return json.loads(resp.to_json_string())['TextDetections']

if __name__ == '__main__':
    app = QApplication(sys.argv)
    window = MainWindow()
    window.show()
    sys.exit(app.exec_())