Develop Reference

python load json data error - python

I want to load this JSON data in python :
JSON data:
{"status":"success","result":{"users":{"5543295":{"status":{"payment_verified":false,"identity_verified":false,"email_verified":true,"deposit_made":false,"phone_verified":false,"facebook_connected":false,"profile_complete":true},"avatar_large":"/img/unknown.png","avatar_cdn":"//cdn6.f-cdn.com/img/unknown.png","spam_profile":null,"search_languages":null,"corporate_users":null,"support_status":null,"last_name":null,"suspended":null,"primary_language":"en","timezone":{"country":"US","offset":-7.0,"id":105,"timezone":"America/Los_Angeles"},"membership_package":null,"qualifications":[{"description":"Foundation vWorker Member","level":null,"icon_url":"/img/insignia/vworker.png","icon_name":"vworker","score_percentage":null,"user_percentile":null,"type":null,"id":null,"name":null}],"id":5543295,"badges":null,"hourly_rate":null,"responsiveness":null,"first_name":null,"display_name":"vw693015vw","tagline":null,"account_balances":null,"public_name":"vw693015vw","role":"employer","location":{"administrative_area":null,"city":null,"country":{"highres_flag_url":"/img/flags/highres_png/unknown.png","code":null,"name":"","flag_url_cdn":"//cdn5.f-cdn.com/img/flags/png/unknown.png","highres_flag_url_cdn":"//cdn5.f-cdn.com/img/flags/highres_png/unknown.png","flag_url":"/img/flags/png/unknown.png"},"vicinity":null,"longitude":null,"full_address":null,"latitude":null},"closed":false,"email":null,"username":"vw693015vw","is_local":null,"endorsements":null,"jobs":[],"employer_reputation":{"user_id":5543295,"last3months":{"completion_rate":null,"all":null,"incomplete_reviews":null,"complete":null,"on_time":null,"on_budget":null,"positive":0.0,"overall":0.0,"reviews":null,"category_ratings":{"communication":0.0,"clarity_spec":0.0,"payment_prom":0.0,"work_for_again":0.0,"professionalism":0.0},"earnings":null,"rehire_rate":null,"incomplete":null},"entire_history":{"completion_rate":null,"all":null,"incomplete_reviews":null,"complete":null,"on_time":null,"on_budget":null,"positive":0.0,"overall":0.0,"reviews":null,"category_ratings":{"communication":0.0,"clarity_spec":0.0,"payment_prom":0.0,"work_for_again":0.0,"professionalism":0.0},"earnings":null,"rehire_rate":null,"incomplete":null},"earnings_score":0.0,"role":"employer","job_history":{"job_counts":[],"count_other":0},"last12months":{"completion_rate":null,"all":null,"incomplete_reviews":null,"complete":null,"on_time":null,"on_budget":null,"positive":0.0,"overall":0.0,"reviews":null,"category_ratings":{"communication":0.0,"clarity_spec":0.0,"payment_prom":0.0,"work_for_again":0.0,"professionalism":0.0},"earnings":null,"rehire_rate":null,"incomplete":null},"project_stats":{"draft":0,"open":0,"complete":0,"pending":0,"work_in_progress":0}},"company":"","registration_date":1041968572,"is_active":null,"avatar_large_cdn":"//cdn6.f-cdn.com/img/unknown.png","profile_description":"","address":null,"limited_account":false,"portfolio_count":0,"preferred_freelancer":false,"true_location":null,"primary_currency":{"code":"USD","name":"US Dollar","country":"US","sign":"$","exchange_rate":1.0,"id":1},"mobile_tracking":null,"test_user":false,"chosen_role":"both","reputation":{"user_id":5543295,"last3months":{"completion_rate":0.0,"all":0,"incomplete_reviews":0,"complete":0,"on_time":0.0,"on_budget":0.0,"positive":0.0,"overall":0.0,"reviews":0,"category_ratings":{"communication":0.0,"expertise":0.0,"hire_again":0.0,"quality":0.0,"professionalism":0.0},"earnings":null,"rehire_rate":null,"incomplete":0},"entire_history":{"completion_rate":0.0,"all":0,"incomplete_reviews":0,"complete":0,"on_time":0.0,"on_budget":0.0,"positive":0.0,"overall":0.0,"reviews":0,"category_ratings":{"communication":0.0,"expertise":0.0,"hire_again":0.0,"quality":0.0,"professionalism":0.0},"earnings":null,"rehire_rate":null,"incomplete":0},"earnings_score":0.0,"role":"freelancer","job_history":{"job_counts":[],"count_other":0},"last12months":{"completion_rate":0.0,"all":0,"incomplete_reviews":0,"complete":0,"on_time":0.0,"on_budget":0.0,"positive":0.0,"overall":0.0,"reviews":0,"category_ratings":{"communication":0.0,"expertise":0.0,"hire_{"status":"success","result":{"users":{"5543296":{"status":{"payment_verified":false,"identity_verified":false,"email_verified":true,"deposit_made":false,"phone_verified":false,"facebook_connected":false,"profile_complete":true},"avatar_large":"/img/unknown.png","avatar_cdn":"//cdn6.f-cdn.com/img/unknown.png","spam_profile":null,"search_languages":null,"corporate_users":null,"support_status":null,"last_name":null,"suspended":null,"primary_language":"en","timezone":{"country":"IN","offset":5.5,"id":164,"timezone":"Asia/Calcutta"},"membership_package":null,"qualifications":[{"description":"Foundation vWorker Member","level":null,"icon_url":"/img/insignia/vworker.png","icon_name":"vworker","score_percentage":null,"user_percentile":null,"type":null,"id":null,"name":null}],"id":5543296,"badges":null,"hourly_rate":null,"responsiveness":null,"first_name":null,"display_name":"vw1619364vw","tagline":null,"account_balances":null,"public_name":"vw1619364vw","role":"employer","location":{"administrative_area":null,"city":null,"country":{"highres_flag_url":"/img/flags/highres_png/unknown.png","code":null,"name":"","flag_url_cdn":"//cdn5.f-cdn.com/img/flags/png/unknown.png","highres_flag_url_cdn":"//cdn5.f-cdn.com/img/flags/highres_png/unknown.png","flag_url":"/img/flags/png/unknown.png"},"vicinity":null,"longitude":null,"full_address":null,"latitude":null},"closed":false,"email":null,"username":"vw1619364vw","is_local":null,"endorsements":null,"jobs":[],"employer_reputation":{"user_id":5543296,"last3months":{"completion_rate":null,"all":null,"incomplete_reviews":null,"complete":null,"on_time":null,"on_budget":null,"positive":0.0,"overall":0.0,"reviews":null,"category_ratings":{"communication":0.0,"clarity_spec":0.0,"payment_prom":0.0,"work_for_again":0.0,"professionalism":0.0},"earnings":null,"rehire_rate":null,"incomplete":null},"entire_history":{"completion_rate":null,"all":null,"incomplete_reviews":null,"complete":null,"on_time":null,"on_budget":null,"positive":0.0,"overall":0.0,"reviews":null,"category_ratings":{"communication":0.0,"clarity_spec":0.0,"payment_prom":0.0,"work_for_again":0.0,"professionalism":0.0},"earnings":null,"rehire_rate":null,"incomplete":null},"earnings_score":0.0,"role":"employer","job_history":{"job_counts":[],"count_other":0},"last12months":{"completion_rate":null,"all":null,"incomplete_reviews":null,"complete":null,"on_time":null,"on_budget":null,"positive":0.0,"overall":0.0,"reviews":null,"category_ratings":{"communication":0.0,"clarity_spec":0.0,"payment_prom":0.0,"work_for_again":0.0,"professionalism":0.0},"earnings":null,"rehire_rate":null,"incomplete":null},"project_stats":{"draft":0,"open":0,"complete":0,"pending":0,"work_in_progress":0}},"company":"","registration_date":1124680669,"is_active":null,"avatar_large_cdn":"//cdn6.f-cdn.com/img/unknown.png","profile_description":"","address":null,"limited_account":false,"portfolio_count":0,"preferred_freelancer":false,"true_location":null,"primary_currency":{"code":"USD","name":"US Dollar","country":"US","sign":"$","exchange_rate":1.0,"id":1},"mobile_tracking":null,"test_user":false,"chosen_role":"both","reputation":{"user_id":5543296,"last3months":{"completion_rate":0.0,"all":0,"incomplete_reviews":0,"complete":0,"on_time":0.0,"on_budget":0.0,"positive":0.0,"overall":0.0,"reviews":0,"category_ratings":{"communication":0.0,"expertise":0.0,"hire_again":0.0,"quality":0.0,"professionalism":0.0},"earnings":null,"rehire_rate":null,"incomplete":0},"entire_history":{"completion_rate":0.0,"all":0,"incomplete_reviews":0,"complete":0,"on_time":0.0,"on_budget":0.0,"positive":0.0,"overall":0.0,"reviews":0,"category_ratings":{"communication":0.0,"expertise":0.0,"hire_again":0.0,"quality":0.0,"professionalism":0.0},"earnings":null,"rehire_rate":null,"incomplete":0},"earnings_score":0.0,"role":"freelancer","job_history":{"job_counts":[],"count_other":0},"last12months":{"completion_rate":0.0,"all":0,"incomplete_reviews":0,"complete":0,"on_time":0.0,"on_budget":0.0,"positive":0.0,"overall":0.0,"reviews":0,"category_ratings":{"communication":0.0,"expertise":0.0,"hire_agaiagain":0.0,"quality":0.0,"professionalism":0.0},"earnings":null,"rehire_rate":null,"incomplete":0},"project_stats":null},"avatar":"/img/unknown.png","cover_image":{"current_image":{"url":"//cdn2.f-cdn.com/static/img/profiles/cover-product.jpg","width":1920,"height":550,"id":null,"description":""},"past_images":null},"corporate":null,"force_verify":null}}},"request_id":"2520481ca4d6b8130bdc20f6114d8037"}
My Python code :
import json
json_data = open('test.txt', 'r').read()
data = json.loads(json_data)
I'm sure JSON data is valid, because is result of one website, I need to load this in python and get username value.
Actual error :
MacBook-Pro-di-admin:freelancer11 admin$ python load.py
Traceback (most recent call last):
File "load.py", line 6, in <module>
data = json.loads(json_data)
File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/json/__init__.py", line 338, in loads
return _default_decoder.decode(s)
File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/json/decoder.py", line 366, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/json/decoder.py", line 382, in raw_decode
obj, end = self.scan_once(s, idx)
ValueError: Expecting : delimiter: line 1 column 4099 (char 4098)

So if you head over to your favorite JSON validator, like JSONlint, you will see the JSON is not valid, and that is precisely what the error in python means.

Related

I want to get information from a forum, Dcard.
I have also built a function to arrange the data I receive.
import json
import pandas as pd
import requests
from requests_html import HTML
import re
import openpyxl
def Crawl(ID):
link='https://www.dcard.tw/_api/posts/'+str(ID)
requ=requests.get(link)
rejs=requ.json()
return(pd.DataFrame(
data=
[{'ID':rejs['id'],
'title':rejs['title'],
'content':rejs['content'],
'excerpt':rejs['excerpt'],
'createdAt':rejs['createdAt'],
'updatedAt':rejs['updatedAt'],
'commentCount':rejs['commentCount'],
'forumName':rejs['forumName'],
'forumAlias':rejs['forumAlias'],
'gender':rejs['gender'],
'likeCount':rejs['likeCount'],
'reactions':rejs['reactions'],
'topics':rejs['topics']}],
columns=['ID',"title","content","excerpt","createdAt","updateAt","commentCount",
"forumName","forumAlias","gender","likeCount","reactionns","topics"])
)
test3=open('D:/Quinna/爬蟲/test4.txt','w',encoding='UTF-8')
p=requests.Session()
url=requests.get("https://www.dcard.tw/search?query=%E5%88%86%E6%89%8B&forum=relationship")
soup=BeautifulSoup(url.text,"html.parser")
a_tags=soup.find_all('h2')
for tag in a_tags:
a=tag.select_one('a').get('href')[18:27] #get the ID from the API
print(Crawl(a))
However, whenever I tried, the error message still comes up.
Is the json not a valid format? How to amend it?
Traceback (most recent call last):
File "D:\Quinna\爬蟲\test4.py", line 38, in <module>
print(Crawl(a))
File "D:\Quinna\爬蟲\test4.py", line 12, in Crawl
rejs=requ.json()
File "C:\Users\user\AppData\Roaming\Python\Python38\site-packages\requests\models.py", line 900, in json
return complexjson.loads(self.text, **kwargs)
File "C:\Program Files (x86)\Python38-32\lib\json\__init__.py", line 357, in loads
return _default_decoder.decode(s)
File "C:\Program Files (x86)\Python38-32\lib\json\decoder.py", line 337, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "C:\Program Files (x86)\Python38-32\lib\json\decoder.py", line 355, in raw_decode
raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

This this. You aren't getting the IDs in a proper way.
Replace this line:
a = tag.select_one('a').get('href')[18:27]
to this line:
a = tag.select_one('a').get('href').split('/')[-1]

I am trying to make a code in python that imports a JSON file from a folder into my program in order for it to access the data inside. However, I am facing errors
global bees
with open('data/bees.json') as f:
bees = json.load(f)["bees"]
Where in the data/bees.json I have this:
{
"bees": []
}
The error I get
Traceback (most recent call last):
File "d:/Entertainment/Coding/Python/Pygame/BUG WORLD/main.py", line 70, in <module>
bees = json.load(f)
File "C:\Users\ernes\AppData\Local\Programs\Python\Python37-32\lib\json\__init__.py", line 296, in load
parse_constant=parse_constant, object_pairs_hook=object_pairs_hook, **kw)
File "C:\Users\ernes\AppData\Local\Programs\Python\Python37-32\lib\json\__init__.py", line 348, in loads
return _default_decoder.decode(s)
File "C:\Users\ernes\AppData\Local\Programs\Python\Python37-32\lib\json\decoder.py", line 337, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "C:\Users\ernes\AppData\Local\Programs\Python\Python37-32\lib\json\decoder.py", line 355, in raw_decode
raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)
Is there a way I am able to import JSON files from another folder without causing any errors?? Please help

Looks like you're on Windows, so:
with open(r'c:\path\to\file\bees.json') as json_file:
bees_js = json.load(json_file)

The relative path should be open("data/bees.json") without the /, starting a path with / means absolute path from the root.

You might want to try the following:
import json
with open('path_to_file/bees.json') as json_file:
bees_js = json.load(json_file)

I am receiving the following error when running the below python script.
ValueError: Invalid control character at: line 7591 column 220620 (char 385678)
I did some research on this and it appeared that it would be resolved by passing 'strict=false' within json.dumps(), but I'm still receiving the same error. This is the only REST service that I have attempted to query that returns this error.
import arcgis
import json
from arcgis import ArcGIS
service = ArcGIS("http://mapping.dekalbcountyga.gov/arcgis/rest/services/LandUse/MapServer")
query = service.get(0, count_only=False)
json_query = json.dumps(query, strict=False)
f = open("dekalb_parcels.geojson", "w")
f.write(json_query)
f.close()
Any help that can be provided would be very appreciated. Thank you.
UPDATE - This is the full error that I am receiving.
Traceback (most recent call last):
File "G:\Python\Scripts\dekalb_parcel_query.py", line 8, in <module>
query = service.get(0, count_only=False)
File "C:\Python27\lib\site-packages\arcgis\arcgis.py", line 146, in get
jsobj = self.get_json(layer, where, fields, count_only, srid)
File "C:\Python27\lib\site-packages\arcgis\arcgis.py", line 90, in get_json
return response.json()
File "C:\Python27\lib\site-packages\requests\models.py", line 802, in json
return json.loads(self.text, **kwargs)
File "C:\Python27\lib\json\__init__.py", line 338, in loads
return _default_decoder.decode(s)
File "C:\Python27\lib\json\decoder.py", line 366, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "C:\Python27\lib\json\decoder.py", line 382, in raw_decode
obj, end = self.scan_once(s, idx)
ValueError: Invalid control character at: line 7591 column 220620 (char 385678)

I was able to fix this issue by passing strict=False within return response.json()

I'm trying to take the JSON from a twitter get_user query and turn it into a Python object that I can extract data from (twitter handle, location, screen name, etc.)
Here is what I created. I am not sure why it doesn't work.
api = tweepy.API(auth,parser=tweepy.parsers.JSONParser())
user = api.search_users('google.com')
t_dict = json.loads(user)
pprint(t_dict)
Error:
Traceback (most recent call last):
File "Get_User_By_URL.py", line 23, in <module>
t_dict = json.loads(user)
File "/usr/lib/python2.7/json/__init__.py", line 338, in loads
return _default_decoder.decode(s)
File "/usr/lib/python2.7/json/decoder.py", line 366, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
TypeError: expected string or buffer

api.search_users is already returning a python object. It isn't a json string that needs to be parsed. According to tweetpy documentation search_users actually returns a list of users. So the following is possible:
for user in api.search_users('google.com'):
print user.screen_name

Why do I get
ValueError: No JSON object could be decoded
from this code:
import urllib.request,json
n = urllib.request.urlopen("http://graph.facebook.com/55")
d = json.loads(str(n.readall()))
The full error:
Traceback (most recent call last):
File "<pyshell#41>", line 1, in <module>
d= json.loads(str(n.readall()))
File "C:\Python33\lib\json\__init__.py", line 309, in loads
return _default_decoder.decode(s)
File "C:\Python33\lib\json\decoder.py", line 352, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "C:\Python33\lib\json\decoder.py", line 370, in raw_decode
raise ValueError("No JSON object could be decoded")
ValueError: No JSON object could be decoded
The output of str(n.readall()):
'b\'{"id":"55","name":"Jillian Copeland","first_name":"Jillian","last_name":"Copeland","username":"JCoMD","gender":"female","locale":"en_US"}\''
Maybe the b is throwing it off?
If that is the issue, how do I convert the binary stream from the readall to a string and not have that b?
I am trying to learn a little python so please keep that in mind.
I am using Python 3.3 in Windows.

I believe that this is an exact duplicate of this question, but sadly there's no accepted answer.
On my end, this works:
import urllib.request,json
n = urllib.request.urlopen("http://graph.facebook.com/55")
d= json.loads(n.readall().decode('utf-8'))