【全自动改PDF名】批量OCR识别提取PDF自定义指定区域内容保存到 Excel 以及根据PDF文件内容的标题来批量重命名

from aliyunsdkcore.client import AcsClient
from aliyunsdkocr.request.v20191230.RecognizePDFRequest import RecognizePDFRequest
import json
# 初始化AcsClient
client = AcsClient('<your_access_key>', '<your_secret_key>', 'cn-hangzhou')  # 替换为你的AccessKey和密钥，以及地域
# 创建OCR请求
request = RecognizePDFRequest()
request.set_accept_format('json')
# 设置PDF文件在OSS中的路径
request.set_OSSFileURL('oss://<your-bucket>/<your-pdf-file>')
# 设置识别区域参数（根据实际需求调整）
request.set_Regions(json.dumps([{"left": 100, "top": 100, "width": 200, "height": 200}]))
# 发送请求并获取识别结果
response = client.do_action_with_exception(request)
result = json.loads(response)
# 处理识别结果，提取所需内容
extracted_data = result['Data']['Blocks']

from openpyxl import Workbook
# 创建新的Excel工作簿
wb = Workbook()
ws = wb.active
# 写入表头
headers = ['Column1', 'Column2', 'Column3']  # 根据实际需求修改表头
ws.append(headers)
# 写入识别数据
for data in extracted_data:
    row_data = [data['Content'], data['Confidence']]  # 根据实际提取内容修改
    ws.append(row_data)
# 保存Excel文件到OSS
wb.save('result.xlsx')
# 使用OSS Python SDK将Excel文件上传到OSS
import oss2
auth = oss2.Auth('<your_access_key>', '<your_secret_key>')
bucket = oss2.Bucket(auth, 'oss-cn-hangzhou.aliyuncs.com', '<your-bucket>')
bucket.put_object('result.xlsx', open('result.xlsx', 'rb'))

import oss2
# 初始化OSS认证
auth = oss2.Auth('<your_access_key>', '<your_secret_key>')
bucket = oss2.Bucket(auth, 'oss-cn-hangzhou.aliyuncs.com', '<your-bucket>')
# 获取原始PDF文件名
original_filename = '<your-pdf-file>'
# 假设已经提取到标题
new_title = 'new_title.pdf'
# 重命名文件
bucket.copy_object(bucket.bucket_name, original_filename, bucket.bucket_name, new_title)
bucket.delete_object(bucket.bucket_name, original_filename)