问题描述
我有两个不同的JSON对象,它们的一个属性略有不同:
import pandas as pd
from pathlib import Path
def get_sheet_details(filename):
import os
import xmltodict
import shutil
import zipfile
sheets = []
# Make a temporary directory with the file name
directory_to_extract_to = (filename.with_suffix(''))
os.mkdir(directory_to_extract_to)
# Extract the xlsx file as it is just a zip file
zip_ref = zipfile.ZipFile(filename,'r')
zip_ref.extractall(directory_to_extract_to)
zip_ref.close()
# Open the workbook.xml which is very light and only has meta data,get sheets from it
path_to_workbook = directory_to_extract_to / 'xl' / 'workbook.xml'
with open(path_to_workbook,'r') as f:
xml = f.read()
dictionary = xmltodict.parse(xml)
for sheet in dictionary['workbook']['sheets']['sheet']:
sheet_details = {
'id': sheet['@sheetId'],# can be sheetId for some versions
'name': sheet['@name'] # can be name
}
sheets.append(sheet_details)
# Delete the extracted files directory
shutil.rmtree(directory_to_extract_to)
return sheets
def csvfrmxlsx(xlsxfl,df): # create csv files in csv folder on parent directory
from xlsx2csv import Xlsx2csv
for index,row in df.iterrows():
shnum = row['id']
shnph = xlsxfl.parent / 'csv' / Path(row['name'] + '.csv') # path for converted csv file
Xlsx2csv(str(xlsxfl),outputencoding="utf-8").convert(str(shnph),sheetid=int(shnum))
return
pthfnc = 'c:/xlsx/'
wrkfl = 'my.xlsx'
xls_file = Path(pthfnc + wrkfl)
sheetsdic = get_sheet_details(xls_file) # dictionary with sheet names and ids without opening xlsx file
df = pd.DataFrame.from_dict(sheetsdic)
csvfrmxlsx(xls_file,df) # df with sheets to be converted
如何在不添加新类或对MyObject进行修改的情况下反序列化JSONObject2?
解决方法
更新我的答案以提供针对此问题的更动态和更可靠的答案。 在使用此解决方案时,对我来说,关于OP问题提到的问题变得显而易见,但是假设考虑到以下项目列表,则可以使用动态json解决此问题。
- 提供的json无效
- 提供的类不是可公开的,因此不能序列化
- 属性也不可序列化,因为它们也不公开
using Newtonsoft.Json;
using System;
using System.Collections.Generic;
using System.Linq;
using System.Reflection;
using System.Runtime.Remoting;
using System.Text;
using System.Threading.Tasks;
namespace commandexample
{
class Program
{
static void Main(string[] args)
{
string JSONObject1 = @"
{
prop1: ""val1"",prop2: {
prop3: ""val3"",prop4: ""val4""
}
}";
string JSONObject2 = @"
{
prop1: ""val1"",prop2:[{
prop3: ""val3"",prop4: ""val4""
}]
}";
var dyn = JsonConvert.DeserializeObject<dynamic>(JSONObject2);
if (dyn.prop2.GetType().Name == "JArray")
{
dyn.prop2 = dyn.prop2[0];
}
string updatedJson = JsonConvert.SerializeObject(dyn);
MyObject result1 = JsonConvert.DeserializeObject<MyObject>(JSONObject1);
MyObject result2 = JsonConvert.DeserializeObject<MyObject>(updatedJson);
}
public class MyObject
{
public string prop1 { get; set; }
public MyInnerObject prop2 { get; set; }
}
public class MyInnerObject
{
public string prop3;
public string prop4;
}
}
}
原始帖子
如果您知道该数组将始终仅包含一个项目,并且您的json文档中只有一个数组,则可以在方括号的json字符串上执行字符串替换。这将满足您特定问题的条件,但是如果将来文档更改以添加其他阵列属性,则可能会导致问题。确实取决于您的用例。
我认为这是一个数据问题,一个人试图读取由两个独立系统生成的json文档,而其中一个系统未正确创建该文档。
JSONObject2 = JSONObject2.Replace("[","").Replace("]","");
//then continue with the Deserialization
JsonConvert.DeserializeObject<MyObject>(JSONObject2);