csv 格式化 json文件

csv转json

csv 文件示例

dishes_id,dish_name,早餐,中餐,晚餐,加餐,米饭,面食或面点,粗粮,热菜,凉菜,汤,点心,蒸,炒,烧,炖,烩,煨,煎,烤,卤,焖,炸,灼,鲁菜,川菜,粤菜,江苏菜,闽菜,浙江菜,湘菜,徽菜,东北菜,新疆菜,淮扬菜,晋菜,云南菜,西北菜,潮州菜,其他地区特色,酸,甜,苦,辣,咸,水果,乳制品,主食,坚果,面片与挂面,馄饨,蒸或煮的鸡蛋,可煮烂的肉菜,可滤渣的蔬菜汁,白色意大利面,精面做的面包和谷物,牛奶,豆浆,含蔗糖的食物,粥
969855,猪脚姜,0.0,1.0,1.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,1.0,0.0,0.0,1.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0
2350698,苹果醋泡藕片,1.0,1.0,1.0,1.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0
2396213,豉油鸡,0.0,1.0,1.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,1.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0
777765,橙蜜莲藕,1.0,1.0,1.0,1.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,1.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0

json文件示例

{
    "total_count": 1000,
    "dishes_list": [{
        "dish_id": 3000281,
        "dish_name": "米饭",
        "早餐": 0,
        "中餐": 1,
        "晚餐": 1,
        "加餐": 0,
        "米饭": 1,
        "面食或面点": 0,
        "粗粮": 0,
        "热菜": 0,
        "凉菜": 0,
        "汤": 0,
        "点心": 0,
        "蒸": 0,
        ......
    }]
}

工程结构

完整代码

import json

data_file = "douguo_labels.csv"
target_file = "test.txt"
with open(data_file, 'r', encoding='utf8') as file:
    file_list = file.readlines()
    row_count = len(file_list)
    header = file_list[0].split(",")
    col_count = len(header)
    sub_dict = {}
    dishes_list = []
    for i in range(row_count):
        if i > 0:
            line_list = file_list[i].split(",")
            for j in range(col_count):
                if j == 1:
                    sub_dict.update({header[j]: str(line_list[j])})
                else:
                    sub_dict.update({header[j]: int(float(line_list[j]))})
        dishes_list.append(sub_dict)
    result_dict = {
        "total_count": row_count,
        "dishes_list": dishes_list
    }
with open(target_file, 'w', encoding='utf8') as target_file:
	# ensure_ascii=False 正常显示中文
	# indent 缩进为4个空格
	# separators 分隔符为','和':'(默认是', '和': ',有空格)
    result = json.dumps(result_dict, ensure_ascii=False, indent=4, separators=(',', ':'))
    target_file.write(result)

json转CSV

json文件示例

{
  "pdtBeginTime": "2022-09-15 05:37:42",
  "data": [
    {
      "machine_code": "Blower",
      "machine_name": "吹瓶机",
      "realPdtList": [
        {
          "beginTime": "2022-09-15 05:37:42",
          "endTime": "2022-09-15 05:38:08",
          "status": "self",
          "timeLen": "00:00:26"
        },
        {
          "beginTime": "2022-09-15 05:38:08",
          "endTime": "2022-09-15 05:38:49",
          "status": "normal",
          "timeLen": "00:00:41"
        }
      ]
    }
  ],
  "pdtEndTime": "2022-09-15 05:38:49",
  "realLineCode": "BJP8",
  "status": "success"
}

csv 文件示例

pdtBeginTime,pdtEndTime,realLineCode,machine_code,machine_name,beginTime,endTime,status,timeLen
2022-09-15 05:37:42,2022-09-15 05:38:49,BJP8,Blower,吹瓶机,2022-09-15 05:38:08,2022-09-15 05:38:49,normal,00:00:41
2022-09-15 05:37:42,2022-09-15 05:38:49,BJP8,Blower,吹瓶机,2022-09-15 05:38:08,2022-09-15 05:38:49,normal,00:00:41

工程目录

完整代码

import json
import pandas

table_list = []
with open('test.txt', 'r', encoding='utf8') as file:
    context = file.read()
    context_dict = json.loads(context)
    # key_list = ['pdtBeginTime', 'pdtEndTime', 'realLineCode', 'data', 'machine_code', 'machine_name', 'realPdtList',
    #             'beginTime', 'endTime', 'status', 'timeLen']
    row_dict = {}
    # 按json层级获取字段值，插入row字典
    row_dict.update({'pdtBeginTime': context_dict['pdtBeginTime']})
    row_dict.update({'pdtEndTime': context_dict['pdtEndTime']})
    row_dict.update({'realLineCode': context_dict['realLineCode']})
    data_list = context_dict['data']
    for machine in data_list:
        row_dict.update({'machine_code': machine['machine_code']})
        row_dict.update({'machine_name': machine['machine_name']})
        realPdtList = machine['realPdtList']
        for realPdt in realPdtList:
            row_dict.update({'beginTime': realPdt['beginTime']})
            row_dict.update({'endTime': realPdt['endTime']})
            row_dict.update({'status': realPdt['status']})
            row_dict.update({'timeLen': realPdt['timeLen']})
            table_list.append(row_dict)

df = pandas.DataFrame(table_list)
df.to_csv('test.csv', index=None)