批量识别身份证并导出excel

由于一些行业需要手动录入大量的身份证信息, 因此编写本软件用于减少工作量。

下载地址：

https://pan.xunlei.com/s/VORZO0ORVI_f5-QvI3vutGNgA1?pwd=6jpp#

代码：

• import re
• import threading
• import tkinter as tk
• from tkinter import filedialog, messagebox, ttk
• from openpyxl import Workbook
• from openpyxl.drawing.image import Image as XLImage
• from openpyxl.styles import Alignment
• from paddlenlp import Taskflow
• from paddleocr import PaddleOCR
• # 初始化 OCR 和 NLP 模型
• ocr = PaddleOCR(use_angle_cls=True, lang="ch", use_gpu=False)
• schema = ['地址', '姓名', '时间']
• ie = Taskflow('information_extraction', schema=schema, model='uie-base')
• def extract_info_from_image(image_path):
• try:
• result = ocr.ocr(image_path, cls=True)
• all_text = ""
• for res in result:
• for line in res:
• text = line[1][0]
• if text:
• all_text += text + " "
• # 提取结构化信息
• name = nation = birth = id_number = ""
• # 提取民族和身份证号（通过关键词匹配）
• for res in result:
• for i, line in enumerate(res):
• text = line[1][0]
• if '民族' in text:
• match = re.search(r'民族(.+)', text)
• if match:
• nation = match.group(1).strip()
• if '公民身份号码' in text:
• if i + 1 < len(res):
• next_text = res[i + 1][1][0]
• if re.match(r'\d{17}[\dXx]', next_text):
• id_number = next_text.strip()
• # 使用 IE 模型提取姓名、出生日期
• ie_result = ie(all_text)
• if ie_result and isinstance(ie_result, list):
• info = ie_result[0]
• if '姓名' in info and info['姓名']:
• name = info['姓名'][0]['text']
• if '时间' in info and info['时间']:
• birth = info['时间'][0]['text']
• return {
• "姓名": name,
• "民族": nation,
• "出生日期": birth,
• "身份证号": id_number,
• "图片路径": image_path
• }
• except Exception as e:
• print(f"处理 {image_path} 失败: {e}")
• return None
• class OCRApp:
• def __init__(self, root):
• self.root = root
• self.root.title("身份证批量识别工具")
• self.root.geometry("400x200")
• self.label = tk.Label(root, text="点击下方按钮选择身份证图片", font=("Arial", 14))
• self.label.pack(pady=20)
• self.btn = tk.Button(root, text="选择图片", command=self.start_batch_ocr)
• self.btn.pack(pady=10)
• self.progress = ttk.Progressbar(root, orient="horizontal", length=300, mode="indeterminate")
• self.progress.pack(pady=10)
• def start_batch_ocr(self):
• # 开始文件选择
• file_paths = filedialog.askopenfilenames(
• title="选择身份证图片",
• filetypes=[("Image Files", "*.jpg *.jpeg *.png *.bmp")]
• )
• if not file_paths:
• return
• # 显示进度条
• self.progress.start()
• self.btn.config(state=tk.DISABLED)
• # 在子线程中处理 OCR
• thread = threading.Thread(target=self.process_files, args=(file_paths,))
• thread.start()
• def process_files(self, file_paths):
• wb = Workbook()
• ws = wb.active
• ws.append(["图片", "姓名", "民族", "出生日期", "身份证号"])
• row_idx = 2 # 从第二行开始插入数据
• for path in file_paths:
• info = extract_info_from_image(path)
• if info:
• ws.cell(row=row_idx, column=2, value=info["姓名"])
• ws.cell(row=row_idx, column=3, value=info["民族"])
• ws.cell(row=row_idx, column=4, value=info["出生日期"])
• ws.cell(row=row_idx, column=5, value=info["身份证号"])
• try:
• img = XLImage(path)
• img.width = 500
• img.height = 300
• ws.row_dimensions[row_idx].height = img.height # 设置行高为图片高度
• ws.add_image(img, f"A{row_idx}")
• # 设置 A 列宽度为图片宽度（近似值）
• ws.column_dimensions['A'].width = img.width * 0.14 # 粗略换算像素到 Excel 列宽单位
• except Exception as e:
• print(f"无法插入图片 {path}: {e}")
• # 所有列居中对齐
• for col in range(1, 6): # A~E 列
• cell = ws.cell(row=row_idx, column=col)
• cell.alignment = Alignment(horizontal='center', vertical='center')
• row_idx += 1
• # 设置表头居中
• for col in range(1, 6):
• header_cell = ws.cell(row=1, column=col)
• header_cell.alignment = Alignment(horizontal='center', vertical='center')
• output_path = "身份证识别结果.xlsx"
• wb.save(output_path)
• self.progress.stop()
• self.btn.config(state=tk.NORMAL)
• messagebox.showinfo("完成", f"识别完成，结果已保存至 {output_path}")
• if __name__ == "__main__":
• root = tk.Tk()
• app = OCRApp(root)
• root.mainloop()![](
• )