文本数据格式转换备份

概述

一些文本格式转换代码，个人做一下备份。

ipynb转py格式

import nbformat
from nbconvert import PythonExporter# 读取 Jupyter notebook 文件
notebook_filename = 'Builddata.ipynb'  # 替换为你的 .ipynb 文件路径
with open(notebook_filename, 'r', encoding='utf-8') as notebook_file:notebook_content = nbformat.read(notebook_file, as_version=4)# 使用 PythonExporter 将 notebook 转换为 Python 脚本
python_exporter = PythonExporter()
python_code, _ = python_exporter.from_notebook_node(notebook_content)# 将 Python 代码写入 .py 文件
python_filename = notebook_filename.replace('.ipynb', '.py')
with open(python_filename, 'w', encoding='utf-8') as python_file:python_file.write(python_code)print(f'Notebook converted to Python script: {python_filename}')

CSV格式转数据库db格式

import sqlite3
import csv# 你的CSV文件路径
csv_file = '202103_LD.csv'# 转成SQLite数据库文件路径
db_file = '202103_LD.db'# 连接SQLite数据库（如果数据库文件不存在，它会被自动创建）
conn = sqlite3.connect(db_file)
cursor = conn.cursor()# 读取CSV文件并获取列名
with open(csv_file, mode='r', newline='', encoding='utf-8') as file:reader = csv.reader(file)headers = next(reader)  # 获取第一行（标签行）# 动态创建SQL表语句 data为表名columns = ', '.join([f"{header} TEXT" for header in headers])create_table_sql = f"CREATE TABLE IF NOT EXISTS data ({columns})"cursor.execute(create_table_sql)# 插入数据for row in reader:placeholders = ', '.join(['?' for _ in headers])insert_sql = f"INSERT INTO data ({', '.join(headers)}) VALUES ({placeholders})"cursor.execute(insert_sql, row)# 提交事务并关闭连接
conn.commit()
conn.close()print(f"数据成功从CSV文件导入到数据库 {db_file} 中！")

CSV格式转json格式

import csv
import jsoncsv_file = 'data.csv'
json_file = 'data.json'# 读取CSV文件
with open(csv_file, mode='r', newline='', encoding='utf-8') as csvf:reader = csv.DictReader(csvf)data = [row for row in reader]# 写入JSON文件
with open(json_file, 'w', encoding='utf-8') as jsonf:json.dump(data, jsonf, ensure_ascii=False, indent=4)

json格式转CSV格式

import json
import csvjson_file = 'data.json'
csv_file = 'data.csv'# 读取JSON文件
with open(json_file, 'r', encoding='utf-8') as jf:data = json.load(jf)# 写入CSV文件
with open(csv_file, mode='w', newline='', encoding='utf-8') as cf:writer = csv.DictWriter(cf, fieldnames=data[0].keys())writer.writeheader()writer.writerows(data)