My code is as follows:

import json
import pandas as pd
from difflib import SequenceMatcher




description_file = open("description.json", encoding="utf-8")


nodescription_file = open("nodescription.json",  encoding="utf-8")


desc = json.load(description_file)
nodesc = json.load(nodescription_file)


stack = []
def get_values():
    data = []
    for pages in nodesc:
        for rows in pages["dataRows"]:
            skip = False
            if skip:
                break
            email = ""
            companyname = rows["columnValues"]["companyName"][0]["name"]
            fullname = ""
            firmName = rows["columnValues"]["firm"][0]["name"]
            pbid = rows["columnValues"]["companyName"][0]["pbId"]
            managementposition = rows["columnValues"]["managementPosition"][0]["value"]
            
            if len(rows["columnValues"]["email"]):
                email = rows["columnValues"]["email"][0]["value"]
            else:
                email = "No email"
            
            if len(rows["columnValues"]["fullName"]):
                 fullname = rows["columnValues"]["fullName"][0]["name"]
         
            for desc_rows in desc["dataRows"]:
                pbid_desc = desc_rows["columnValues"]["investorName"][0]["pbId"]
                
                description = ""
                if len(desc_rows["columnValues"]["description"]):
                    description = desc_rows["columnValues"]["description"][0]["value"]
                else:
                    description = "No description"
                
                if pbid == pbid_desc:
                    data.append({"Full Name": fullname, "Email": email, "Company Name": companyname, "Position":managementposition, "Description": description})
                
    save_data(data, "file7.csv")
                       
                        

def similar(a, b): #Dont use this anymore, pbid was relational
    
    return SequenceMatcher(None, a, b).ratio()

def instack(string):
    for i in stack:
        if string == i:
            return True
    return False

def save_data(data, name):
    pd.read_json(json.dumps(data, ensure_ascii=False).encode('utf8'), encoding='utf-8').to_csv(name, encoding="utf-8")
get_values()
description_file.close()
nodescription_file.close()

I am getting an error of:

Traceback (most recent call last):
  File "/Users/dan/Desktop/Upwork/main.py", line 69, in <module>
    get_values()
  File "/Users/dan/Desktop/Upwork/main.py", line 53, in get_values
    save_data(data, "file7.csv")
  File "/Users/dan/Desktop/Upwork/main.py", line 68, in save_data
    pd.read_json(json.dumps(data, ensure_ascii=False).encode('utf8'), encoding='utf-8').to_csv(name, encoding="utf-8")
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pandas/util/_decorators.py", line 207, in wrapper
    return func(*args, **kwargs)
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pandas/util/_decorators.py", line 311, in wrapper
    return func(*args, **kwargs)
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pandas/io/json/_json.py", line 588, in read_json
    json_reader = JsonReader(
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pandas/io/json/_json.py", line 673, in __init__
    data = self._get_data_from_filepath(filepath_or_buffer)
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pandas/io/json/_json.py", line 710, in _get_data_from_filepath
    self.handles = get_handle(
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/pandas/io/common.py", line 826, in get_handle
    raise TypeError(
TypeError: Expected file path name or file-like object, got <class 'bytes'> type

Please help - I am a total noob. Thank you so much. The above is not code it is an error and the stackoverflow autobot is making be write more of a questions because it cannot discern the code text from the result text - or I am just a noob. Please help. Thank you so much in advance. I am on PC using Visual Studio and have already installed pip pandas and pip cdifflib is not installing for some reason with exit code 1120 legacy install failure.

CodePudding user response：

The error you get is because read_json expects as a fisrt argument either a path to a file or a file-like object, but you're giving it a bytes string.

I think what should work is to convert your bytes string into a bytes buffer that is a file-like object, with io.BytesIO :

pd.read_json(io.BytesIO(json.dumps(data, ensure_ascii=False).encode('utf8')), encoding='utf-8').to_csv(name, encoding="utf-8")