"simplejson.errors.JSONDecodeError: Expecting value: line 1 column 1 (char 0)"卡住此错误

Question

import pandas as pd
import csv
import re
import json
import requests
def Table():
table = pd.read_json("https://www.nmc.org.in/MCIRest/open/getPaginatedData?service=getPaginatedDoctor&draw=1&columns%5B0%5D%5Bdata%5D=0&columns%5B0%5D%5Bname%5D=&columns%5B0%5D%5Bsearchable%5D=true&columns%5B0%5D%5Borderable%5D=true&columns%5B0%5D%5Bsearch%5D%5Bvalue%5D=&columns%5B0%5D%5Bsearch%5D%5Bregex%5D=false&columns%5B1%5D%5Bdata%5D=1&columns%5B1%5D%5Bname%5D=&columns%5B1%5D%5Bsearchable%5D=true&columns%5B1%5D%5Borderable%5D=true&columns%5B1%5D%5Bsearch%5D%5Bvalue%5D=&columns%5B1%5D%5Bsearch%5D%5Bregex%5D=false&columns%5B2%5D%5Bdata%5D=2&columns%5B2%5D%5Bname%5D=&columns%5B2%5D%5Bsearchable%5D=true&columns%5B2%5D%5Borderable%5D=true&columns%5B2%5D%5Bsearch%5D%5Bvalue%5D=&columns%5B2%5D%5Bsearch%5D%5Bregex%5D=false&columns%5B3%5D%5Bdata%5D=3&columns%5B3%5D%5Bname%5D=&columns%5B3%5D%5Bsearchable%5D=true&columns%5B3%5D%5Borderable%5D=true&columns%5B3%5D%5Bsearch%5D%5Bvalue%5D=&columns%5B3%5D%5Bsearch%5D%5Bregex%5D=false&columns%5B4%5D%5Bdata%5D=4&columns%5B4%5D%5Bname%5D=&columns%5B4%5D%5Bsearchable%5D=true&columns%5B4%5D%5Borderable%5D=true&columns%5B4%5D%5Bsearch%5D%5Bvalue%5D=&columns%5B4%5D%5Bsearch%5D%5Bregex%5D=false&columns%5B5%5D%5Bdata%5D=5&columns%5B5%5D%5Bname%5D=&columns%5B5%5D%5Bsearchable%5D=true&columns%5B5%5D%5Borderable%5D=true&columns%5B5%5D%5Bsearch%5D%5Bvalue%5D=&columns%5B5%5D%5Bsearch%5D%5Bregex%5D=false&columns%5B6%5D%5Bdata%5D=6&columns%5B6%5D%5Bname%5D=&columns%5B6%5D%5Bsearchable%5D=true&columns%5B6%5D%5Borderable%5D=true&columns%5B6%5D%5Bsearch%5D%5Bvalue%5D=&columns%5B6%5D%5Bsearch%5D%5Bregex%5D=false&order%5B0%5D%5Bcolumn%5D=0&order%5B0%5D%5Bdir%5D=asc&start=20000&length=8751&search%5Bvalue%5D=&search%5Bregex%5D=false&name=&registrationNo=&smcId=&year=2020&_=1611587198138")['data']
with open('C:\Users\SmartDB\Desktop\2020_out_2.csv', 'w', newline="") as f:
writer = csv.writer(f)
writer.writerow(
['Year Of The Info', 'Registration#', 'State Medical Councils', 'Name', 'FatherName'])
data = []
for item in table:
writer.writerow(item[1:6])
required = item[6]
match = re.search(
r"openDoctorDetailsnew('([^']*)', '([^']*)'", required)
data.append(match.group().split("'")[1:4:2])
print("Data Saved Into out.csv")
return data
def Details():
names = []
items = []
for doc, val in Table():
print(f"Extracting DoctorID# {doc}, RegValue# {val}")
json = {'doctorId': doc, 'regdNoValue': val}
r = requests.post("https://www.nmc.org.in/MCIRest/open/getDataFromService? 
service=getDoctorDetailsByIdImr",json=json).json()
try:
if r.keys() not in names:
names.append(r.keys())
items.append(r.values())
except:
pass 
print("Done")
return names, items

def Save():
with open('C:\Users\SmartDB\Desktop\2020_data_2.csv','w', newline="") as d:
writer = csv.writer(d)
n, i = Details()
writer.writerows(n)
writer.writerows(i)

Save()

在提取过程中进行网页抓取时，我得到了这个错误"simplejson.errors。JSONDecodeError:期望值:第1行第1列(字符0)"所以请帮我解决这个错误，数据出现在。csv文件中，而不是在data.csv文件中。

Answer 1

我猜你用pd.read_json()请求的URL是错误的，因为这是你代码中读取json的唯一地方。

simplejson.errors.JSONDecodeError: Expecting value: line 1 column 1 (char 0)意味着它无法解码json，在json测试的第1行第1列(不是源代码的第1行第1列)。

很可能URL是错误的，返回的是空响应而不是json。

Answer 2

编辑:

如前所述，pandas.read_json()也接受一个URL。我运行了你的代码，它一直运行成功。

问题可能是您从端点获得非200响应，并且响应体不是JSON。

这可能是因为您有打字错误(可能)或您的授权无效(不太可能因为我刚刚运行它并且它有效)，或者您发出了太多请求并且API服务器暂时阻止了您的IP:)

也可能有许多其他原因。也许你可以在转换为JSON之前发布你的请求结果，我们可以更好地帮助你，即

r = requests.post("https://www.nmc.org.in/MCIRest/open/getDataFromService?service=getDoctorDetailsByIdImr", json=json)
j = r.json()

告诉我们r是什么

确保你的请求的所有部分都正确输入。

---

您的第一行似乎试图使用pandas读取json文件，除非您刚刚传递了一个URL字符串。

table = pd.read_json("https://www.nmc.org.in/MCIRest/open/getPaginatedData?service=getPaginatedDoctor&draw=1&columns%5B0%...")['data']

这不是JSON。你必须使用GET请求从网页下载JSON，然后尝试将其作为JSON读取。

这个错误意味着pd.read_json()试图读取一些URL字符串作为JSON，当然，它不是一个。