47 lines
1.8 KiB
Python
Executable File
47 lines
1.8 KiB
Python
Executable File
import os
|
|
import json
|
|
from openpyxl import load_workbook
|
|
from tqdm import tqdm
|
|
def update_excel_with_data(excel_path, data_root):
|
|
# 加载工作簿并获取活动工作表
|
|
workbook = load_workbook(excel_path)
|
|
sheet = workbook.active
|
|
|
|
# 确定开始行
|
|
last_row = sheet.max_row + 1
|
|
|
|
# 遍历目录和文件
|
|
for root, dirs, files in tqdm(os.walk(data_root)):
|
|
for file in files:
|
|
if file.endswith('.json'):
|
|
json_path = os.path.join(root, file)
|
|
image_path = os.path.splitext(json_path)[0] + '.jpg' # 假设图像文件是jpg格式
|
|
|
|
# 读取JSON文件
|
|
with open(json_path, 'r', encoding='utf-8') as json_file:
|
|
data = json.load(json_file)
|
|
content = data.get('content', '')
|
|
|
|
# 提取文件夹名称作为关键字
|
|
keyword = os.path.basename(root)
|
|
|
|
# 填充Excel表格
|
|
sheet.cell(row=last_row, column=1, value=last_row - 1) # 序号
|
|
sheet.cell(row=last_row, column=2, value=keyword) # 关键字
|
|
sheet.cell(row=last_row, column=3, value=content) # 文本内容
|
|
sheet.cell(row=last_row, column=4, value=1) # 数据功能类型
|
|
sheet.cell(row=last_row, column=5, value=image_path) # 对应图片路径
|
|
|
|
# 为下一条记录增加行索引
|
|
last_row += 1
|
|
|
|
# 保存更新后的工作簿
|
|
workbook.save(excel_path)
|
|
|
|
# 路径需要根据您的实际情况调整
|
|
excel_path = '/data1/Hatcher/model/project/MPKFNet/大规模数据库-文本.xlsx'
|
|
data_root = '/data5/Hatcher/data/llma/result'
|
|
|
|
# 调用此函数以运行
|
|
update_excel_with_data(excel_path, data_root)
|