【拆分PDF重命名】将PDF按页拆分多个PDF文件，并用PDF里文字对文件批量重命名，python和腾讯api识别改名的完整代码和详细步骤

pip install PyPDF2 tencentcloud-sdk-python pdf2image

import os
from PyPDF2 import PdfReader, PdfWriter
from pdf2image import convert_from_path
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
import base64

# 腾讯云 API 密钥
SECRET_ID = 'your_secret_id'
SECRET_KEY = 'your_secret_key'

def split_pdf(input_pdf_path):
    """
    将 PDF 按页拆分为多个 PDF 文件
    :param input_pdf_path: 输入的 PDF 文件路径
    :return: 拆分后的 PDF 文件列表
    """
    pdf_reader = PdfReader(input_pdf_path)
    output_pdfs = []
    for page_num in range(len(pdf_reader.pages)):
        pdf_writer = PdfWriter()
        pdf_writer.add_page(pdf_reader.pages[page_num])
        output_pdf_path = f'page_{page_num + 1}.pdf'
        with open(output_pdf_path, 'wb') as output_pdf:
            pdf_writer.write(output_pdf)
        output_pdfs.append(output_pdf_path)
    return output_pdfs

def pdf_page_to_image(pdf_path):
    """
    将 PDF 页面转换为图像
    :param pdf_path: PDF 文件路径
    :return: 图像对象
    """
    images = convert_from_path(pdf_path)
    return images[0]

def ocr_image(image):
    """
    使用腾讯云 OCR 识别图像中的文字
    :param image: 图像对象
    :return: 识别出的文字
    """
    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)

    image.save('temp_image.jpg', 'JPEG')
    with open('temp_image.jpg', 'rb') as f:
        image_data = f.read()
    base64_image = base64.b64encode(image_data).decode('utf-8')

    req = models.GeneralBasicOCRRequest()
    params = {
        "ImageBase64": base64_image
    }
    req.from_json_string(str(params).replace("'", '"'))

    resp = client.GeneralBasicOCR(req)
    result = resp.to_json_string()
    import json
    result_json = json.loads(result)
    text = ''.join([item['DetectedText'] for item in result_json['TextDetections']])
    return text

def rename_pdfs(pdf_paths):
    """
    根据 OCR 识别结果重命名 PDF 文件
    :param pdf_paths: 待重命名的 PDF 文件列表
    """
    for pdf_path in pdf_paths:
        image = pdf_page_to_image(pdf_path)
        text = ocr_image(image)
        # 处理识别结果，去除非法字符
        valid_chars = "-_.() abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789"
        new_name = ''.join(c for c in text if c in valid_chars).strip()
        if new_name:
            new_path = f'{new_name}.pdf'
            os.rename(pdf_path, new_path)
            print(f'Renamed {pdf_path} to {new_path}')
        else:
            print(f'No valid text found for {pdf_path}, keeping original name.')

if __name__ == "__main__":
    input_pdf = 'your_input_pdf.pdf'
    split_pdfs = split_pdf(input_pdf)
    rename_pdfs(split_pdfs)

python pdf_split_and_rename.py