I have the data as below
{
"employeealias": "101613177",
"firstname": "Lion",
"lastname": "King",
"date": "2022-04-21",
"type": "Thoughtful Intake",
"subject": "Email: From You Success Coach"
}
{
"employeealias": "101613177",
"firstname": "Lion",
"lastname": "King",
"date": "2022-04-21",
"type": null,
"subject": "Call- CDL options & career assessment"
}
I need to create a dictionary like the below:
You have to create new dictionary with list and use for-loop to check if exists employeealias, firstname, lastname to add other information to sublist. If item doesn't exist then you have to create new item with employeealias, firstname, lastname and other information.
data = [
{"employeealias":"101613177","firstname":"Lion","lastname":"King","date":"2022-04-21","type":"Thoughtful Intake","subject":"Email: From You Success Coach"},
{"employeealias":"101613177","firstname":"Lion","lastname":"King","date":"2022-04-21","type":"null","subject":"Call- CDL options & career assessment"},
]
result = {'interactions': []}
for row in data:
found = False
for item in result['interactions']:
if (row["employeealias"] == item["employeealias"]
and row["firstname"] == item["firstname"]
and row["lastname"] == item["lastname"]):
item["activity"].append({
"date": row["date"],
"subject": row["subject"],
"type": row["type"],
})
found = True
break
if not found:
result['interactions'].append({
"employeealias": row["employeealias"],
"firstname": row["firstname"],
"lastname": row["lastname"],
"activity": [{
"date": row["date"],
"subject": row["subject"],
"type": row["type"],
}]
})
print(result)
EDIT:
You read lines as normal text but you have to convert text to dictonary using module json
import json
data = []
with open("/Users/Downloads/amazon_activity_feed_0005_part_00.json") as a_file:
for line in a_file:
line = line.strip()
dictionary = json.loads(line)
data.append(dictionary)
print(data)
You can create a nested dictionary inside Python like this:
student = {name : "Suman", Age = 20, gender: "male",{class : 11, roll no: 12}}
Related
If I have a heavy json file that have 30m entries like that
{"id":3,"price":"231","type":"Y","location":"NY"}
{"id":4,"price":"321","type":"N","city":"BR"}
{"id":5,"price":"354","type":"Y","city":"XE","location":"CP"}
--snip--
{"id":30373779,"price":"121","type":"N","city":"SR","location":"IU"}
{"id":30373780,"price":"432","type":"Y","location":"TB"}
{"id":30373780,"price":"562","type":"N","city":"CQ"}
how I can only abstract the location and the city and parse it into one json like that in python:
{
"orders":{
3:{
"location":"NY"
},
4:{
"city":"BR"
},
5:{
"city":"XE",
"location":"CP"
},
30373779:{
"city":"SR",
"location":"IU"
},
30373780:{
"location":"TB"
},
30373780:{
"city":"CQ"
}
}
}
P.S: beatufy the syntax is not necessary.
Assuming your input file is actually in jsonlines format, then you can read each line, extract the city and location keys from the dict and then append those to a new dict:
import json
from collections import defaultdict
orders = { 'orders' : defaultdict(dict) }
with open('orders.txt', 'r') as f:
for line in f:
o = json.loads(line)
id = o['id']
if 'location' in o:
orders['orders'][id]['location'] = o['location']
if 'city' in o:
orders['orders'][id]['city'] = o['city']
print(orders)
Output for your sample data (note it has two 30373780 id values, so the values get merged into one dict):
{
"orders": {
"3": {
"location": "NY"
},
"4": {
"city": "BR"
},
"5": {
"location": "CP",
"city": "XE"
},
"30373779": {
"location": "IU",
"city": "SR"
},
"30373780": {
"location": "TB",
"city": "CQ"
}
}
}
As you've said that your file is pretty big and you probably don't want to keep all entries in memory here is the way to consume source file line by line and write output immediately:
import json
with open(r"in.jsonp") as i_f, open(r"out.json", "w") as o_f:
o_f.write('{"orders":{')
for i in i_f:
i_obj = json.loads(i)
o_f.write(f'{i_obj["id"]}:')
o_obj = {}
if location := i_obj.get("location"):
o_obj["location"] = location
if city := i_obj.get("city"):
o_obj["city"] = city
json.dump(o_obj, o_f)
o_f.write(",")
o_f.write('}}')
It will generate semi-valid JSON object in same format you've provided in your question.
I have extracted id, username, and name for 100 followers for 102 politicians using Tweepy. The data is stored in a JSON file named pol_followers. Now I wish to append id and username and save it as a CSV file using the function below. However, when using the function in the last line append_followers_to_csv(pol_followers, "pol_followers.csv") I get the error seen at the bottom.
# Structure of pol_followers. The full pol_followers is much longer...
print(json.dumps(pol_followers, indent=4, sort_keys=True)) # see json data structure
[
{
"data": [
{
"id": "1464206217807601666",
"name": "terry alex",
"username": "terryal51850644"
},
{
"id": "1479032154394968064",
"name": "Charles Williams",
"username": "Charles99924770"
},
{
"id": "2526015770",
"name": "LISA P",
"username": "LISAP0910"
},
{
"id": "2957692520",
"name": "fayaz ahmad",
"username": "ahmadfayaz202"
}
],
"meta": {
"next_token": "F6HS7IU5SRGHEZZZ",
"result_count": 100
}
},
{
"data": [
{
"id": "2482703136",
"name": "HieuVu",
"username": "sachieuhaihanh"
},
{
"id": "580882148",
"name": "Maxine D. Harmon",
"username": "maxxximd"
},
{
"id": "1478867472841334787",
"name": "RBPsych1",
"username": "RBPsych1"
# Create file
csv_follower_file = open("pol_followers.csv", "a", newline="", encoding='utf-8')
csv_follower_writer = csv.writer(csv_follower_file)
# Create headers for the data I want to save. I only want to save these columns in my dataset
csv_follower_writer.writerow(
['id', 'username'])
csv_follower_file.close()\
def append_followers_to_csv(pol_followers, csv_follower_file):
# A counter variable
global follower_id, username
counter = 0
# Open OR create the target CSV file
csv_follower_file = open(csv_follower_file, "a", newline="", encoding='utf-8')
csv_follower_writer = csv.writer(csv_follower_file)
for ids in pol_followers['data']:
# 1. follower ID
follower_id = ids['id']
# 2. follower username
username = ids['username']
# Assemble all data in a list
ress = [follower_id, username]
# Append the result to the CSV file
csv_follower_writer.writerow(ress)
counter += 1
# When done, close the CSV file
csvFile.close()
# Print the number of tweets for this iteration
print("# of Tweets added from this response: ", counter)
append_followers_to_csv(pol_followers, "pol_followers.csv") # Save tweet data in a csv file
File "<input>", line 1, in <module>
File "<input>", line 11, in append_followers_to_csv
TypeError: list indices must be integers or slices, not str
You are just missing additional loop, like so:
for each_dict in pol_followers:
for ids in each_dict['data']:
follower_id = ids['id']
username = ids['username']
You seem to have wrapped your JSON object in a list, so instead of getting the 'data' bit of the JSON, you are getting the 'data'th element of a list when you are iterating in your append_followers_to_csv function, which you can't do in python. Try removing the square brackets around the JSON or making it for ids in pol_followers[0]['data'].
I hope everyone is doing well.
I need a little help where I need to get all the strings from a variable and need to store into a single list in python.
For example -
I have json file from where I am getting ids and all the ids are getting stored into a variable called id as below when I run print(id)
17298626-991c-e490-bae6-47079c6e2202
17298496-19bd-2f89-7b5f-881921abc632
17298698-3e17-7a9b-b337-aacfd9483b1b
172986ac-d91d-c4ea-2e50-d53700480dd0
172986d0-18aa-6f51-9c62-6cb087ad31e5
172986f4-80f0-5c21-3aee-12f22a5f4322
17298712-a4ac-7b36-08e9-8512fa8322dd
17298747-8cc6-d9d0-8d05-50adf228c029
1729875c-050f-9a99-4850-bb0e6ad35fb0
1729875f-0d50-dc94-5515-b4891c40d81c
17298761-c26b-3ce5-e77e-db412c38a5b4
172987c8-2b5d-0d94-c365-e8407b0a8860
1729881a-e583-2b54-3a52-d092020d9c1d
1729881c-64a2-67cf-d561-6e5e38ed14cb
172987ec-7a20-7eb6-3ebe-a9fb621bb566
17298813-7ac4-258b-d6f9-aaf43f9147b1
17298813-f1ef-d28a-0817-5f3b86c3cf23
17298828-b62b-9ee6-248b-521b0663226e
17298825-7449-2fcb-378e-13671cb4688a
I want these all values to be stored into a single list.
Can some please help me out with this.
Below is the code I am using:
import json
with open('requests.json') as f:
data = json.load(f)
print(type(data))
for i in data:
if 'traceId' in i:
id = i['traceId']
newid = id.split()
#print(type(newid))
print(newid)
And below is my json file looks like:
[
{
"id": "376287298-hjd8-jfjb-khkf-6479280283e9",
"submittedTime": 1591692502558,
"traceId": "17298626-991c-e490-bae6-47079c6e2202",
"userName": "ABC",
"onlyChanged": true,
"description": "Not Required",
"startTime": 1591694487929,
"result": "NONE",
"state": "EXECUTING",
"paused": false,
"application": {
"id": "16b22a09-a840-f4d9-f42a-64fd73fece57",
"name": "XYZ"
},
"applicationProcess": {
"id": "dihihdosfj9279278yrie8ue",
"name": "Deploy",
"version": 12
},
"environment": {
"id": "fkjdshkjdshglkjdshgldshldsh03r937837",
"name": "DEV"
},
"snapshot": {
"id": "djnglkfdglki98478yhgjh48yr844h",
"name": "DEV_snapshot"
},
},
{
"id": "17298495-f060-3e9d-7097-1f86d5160789",
"submittedTime": 1591692844597,
"traceId": "17298496-19bd-2f89-7b5f-881921abc632",
"userName": "UYT,
"onlyChanged": true,
"startTime": 1591692845543,
"result": "NONE",
"state": "EXECUTING",
"paused": false,
"application": {
"id": "osfodsho883793hgjbv98r3098w",
"name": "QA"
},
"applicationProcess": {
"id": "owjfoew028r2uoieroiehojehfoef",
"name": "EDC",
"version": 5
},
"environment": {
"id": "16cf69c5-4194-e557-707d-0663afdbceba",
"name": "DTESTU"
},
}
]
From where I am trying to get the traceId.
you could use simple split method like the follwing:
ids = '''17298626-991c-e490-bae6-47079c6e2202 17298496-19bd-2f89-7b5f-881921abc632 17298698-3e17-7a9b-b337-aacfd9483b1b 172986ac-d91d-c4ea-2e50-d53700480dd0 172986d0-18aa-6f51-9c62-6cb087ad31e5 172986f4-80f0-5c21-3aee-12f22a5f4322 17298712-a4ac-7b36-08e9-8512fa8322dd 17298747-8cc6-d9d0-8d05-50adf228c029 1729875c-050f-9a99-4850-bb0e6ad35fb0 1729875f-0d50-dc94-5515-b4891c40d81c 17298761-c26b-3ce5-e77e-db412c38a5b4 172987c8-2b5d-0d94-c365-e8407b0a8860 1729881a-e583-2b54-3a52-d092020d9c1d 1729881c-64a2-67cf-d561-6e5e38ed14cb 172987ec-7a20-7eb6-3ebe-a9fb621bb566 17298813-7ac4-258b-d6f9-aaf43f9147b1 17298813-f1ef-d28a-0817-5f3b86c3cf23 17298828-b62b-9ee6-248b-521b0663226e 17298825-7449-2fcb-378e-13671cb4688a'''
l = ids.split(" ")
print(l)
This will give the following result, I assumed that the separator needed is simple space you can adjust properly:
['17298626-991c-e490-bae6-47079c6e2202', '17298496-19bd-2f89-7b5f-881921abc632', '17298698-3e17-7a9b-b337-aacfd9483b1b', '172986ac-d91d-c4ea-2e50-d53700480dd0', '172986d0-18aa-6f51-9c62-6cb087ad31e5', '172986f4-80f0-5c21-3aee-12f22a5f4322', '17298712-a4ac-7b36-08e9-8512fa8322dd', '17298747-8cc6-d9d0-8d05-50adf228c029', '1729875c-050f-9a99-4850-bb0e6ad35fb0', '1729875f-0d50-dc94-5515-b4891c40d81c', '17298761-c26b-3ce5-e77e-db412c38a5b4', '172987c8-2b5d-0d94-c365-e8407b0a8860', '1729881a-e583-2b54-3a52-d092020d9c1d', '1729881c-64a2-67cf-d561-6e5e38ed14cb', '172987ec-7a20-7eb6-3ebe-a9fb621bb566', '17298813-7ac4-258b-d6f9-aaf43f9147b1', '17298813-f1ef-d28a-0817-5f3b86c3cf23', '17298828-b62b-9ee6-248b-521b0663226e', '17298825-7449-2fcb-378e-13671cb4688a']
Edit
You get list of lists because each iteration you read only 1 id, so what you need to do is to initiate an empty list and append each id to it in the following way:
l = []
for i in data
if 'traceId' in i:
id = i['traceId']
l.append(id)
you can append the ids variable to the list such as,
#list declaration
l1=[]
#this must be in your loop
l1.append(ids)
I'm assuming you get the id as a str type value. Using id.split() will return a list of all ids in one single Python list, as each id is separated by space here in your example.
id = """17298626-991c-e490-bae6-47079c6e2202 17298496-19bd-2f89-7b5f-881921abc632
17298698-3e17-7a9b-b337-aacfd9483b1b 172986ac-d91d-c4ea-2e50-d53700480dd0
172986d0-18aa-6f51-9c62-6cb087ad31e5 172986f4-80f0-5c21-3aee-12f22a5f4322
17298712-a4ac-7b36-08e9-8512fa8322dd 17298747-8cc6-d9d0-8d05-50adf228c029
1729875c-050f-9a99-4850-bb0e6ad35fb0 1729875f-0d50-dc94-5515-b4891c40d81c
17298761-c26b-3ce5-e77e-db412c38a5b4 172987c8-2b5d-0d94-c365-e8407b0a8860
1729881a-e583-2b54-3a52-d092020d9c1d 1729881c-64a2-67cf-d561-6e5e38ed14cb
172987ec-7a20-7eb6-3ebe-a9fb621bb566 17298813-7ac4-258b-d6f9-aaf43f9147b1
17298813-f1ef-d28a-0817-5f3b86c3cf23 17298828-b62b-9ee6-248b-521b0663226e
17298825-7449-2fcb-378e-13671cb4688a"""
id_list = id.split()
print(id_list)
Output:
['17298626-991c-e490-bae6-47079c6e2202', '17298496-19bd-2f89-7b5f-881921abc632',
'17298698-3e17-7a9b-b337-aacfd9483b1b', '172986ac-d91d-c4ea-2e50-d53700480dd0',
'172986d0-18aa-6f51-9c62-6cb087ad31e5', '172986f4-80f0-5c21-3aee-12f22a5f4322',
'17298712-a4ac-7b36-08e9-8512fa8322dd', '17298747-8cc6-d9d0-8d05-50adf228c029',
'1729875c-050f-9a99-4850-bb0e6ad35fb0', '1729875f-0d50-dc94-5515-b4891c40d81c',
'17298761-c26b-3ce5-e77e-db412c38a5b4', '172987c8-2b5d-0d94-c365-e8407b0a8860',
'1729881a-e583-2b54-3a52-d092020d9c1d', '1729881c-64a2-67cf-d561-6e5e38ed14cb',
'172987ec-7a20-7eb6-3ebe-a9fb621bb566', '17298813-7ac4-258b-d6f9-aaf43f9147b1',
'17298813-f1ef-d28a-0817-5f3b86c3cf23', '17298828-b62b-9ee6-248b-521b0663226e',
'17298825-7449-2fcb-378e-13671cb4688a']
split() splits by default with space as a separator. You can use the sep argument to use any other separator if needed.
I have done my research but I couldn't find any answers that worked.
I have the following JSON file:
{
"Cars": [{
"Manufacturer": "Audi",
"model": "R8",
"price": 50000,
"a": {
"n": "1",
"street": "ABC Street",
"city": "London",
"postcode": "TW1 1AA"
}
},
{
"Manufacturer": "Ford",
"model": "Fiesta",
"price": 10000,
"a": {
"n": 2,
"street": "DEF street",
"town": "London",
"PostCode": "TW2 2AB"
}
},
{
"Manufacturer": "VW",
"model": "Polo",
"price": 5000,
"a": {
"n": "3",
"Street": "GHI Street",
"town": "London",
"postcode": "TW3 3CD"
}
}
]
}
In my python file, to remove the JSON elements, I am using the following:
deletecar = int(input("Enter price of car to delete: "))
for item in data["Cars"]:
if deletecar == item["price"]:
item.pop("Manufacturer")
item.pop("model")
item.pop("price")
item.pop("a")
with open("testjson.json", 'w') as f:
json.dump(data, f)
When I run this, if I delete the first car in the JSON file, I find this:
{"Cars": [{}, {"Manufacturer": "Ford", ...
If I now run my program again, but I try to search for cars, the program won't work due to these empty braces.
So how can I remove them using Python?
Thanks in advance.
You need to remove the item itself, which means you need two steps:
find the index at which the item you want to remove is
remove the item from the list (with del)
And you don't need to "empty" the dict as that's not what you're looking for.
Alternatively, you could create a brand new list without the offending item using a list comprehension or a filter call e.g.
deletecar = int(input("Enter price of car to delete: "))
data['Cars'] = [
item for item in data['Cars']
if item['price'] != deletecar
]
with open("testjson.json", 'w') as f:
json.dump(data, f)
(note: this "removes" all items which match, rather than just the first as your code does).
Also you probably want to save after you're done processing, not during processing.
Since it's a list, you can find the index values in your list that match your price input. Then remove those elements from values in the 'Cars' list
deletecar = int(input("Enter price of car to delete: "))
# Get the index values of where the item is located
index_to_delete = []
for item in data["Cars"]:
if deletecar == item["price"]:
index_to_delete.append(data["Cars"].index(item))
# Since the index values will change as you delete them,
# you will have to remove them in reverse order (in case there's more than 1
# item being removed
for i in reversed(index_to_delete):
del data["Cars"][i]
# write to file
with open("testjson.json", 'w') as f:
json.dump(data, f)
I extracted the following script from html using beautiful-soup:
<script>
dataLayer =[{
"pageTitle": "PRODUCT: Macculloch Parka Print( 9512MP )",
"pageCategory": "shop-mens-parkas",
"visitorLoginState": "Guest",
"EmployeeLoginState": false,
"customerEmail": "null",
"customerOrders": "null",
"customerValue": "0",
"Country": "CA",
"State": "ON",
"ecommerce": {
"currencyCode": "CAD",
"detail": {
"actionField": {
"list": "Product Category / Search Results"
},
"products": [
{
"name": "Macculloch Parka Print",
"id": "9512MP",
"price": 1295,
"brand": "Canada Goose",
"category": "shop-mens-parkas"}]}}}];</script>
I want to extract the information related to the product (name, id, price and brand) as a dataframe. Is there a way to do it without using regex?
You can use regex to get json and parse:
import json
import re
data = json.loads(re.search(r"dataLayer =(.*);", d, re.DOTALL).group(1))
products = data[0]["ecommerce"]["detail"]["products"]
product_name = products[0]["name"]
product_id = products[0]["id"]
product_price = products[0]["price"]
product_brand = products[0]["brand"]
product_category = products[0]["category"]
Here is a temporary solution, contingent on receiving more information on the format of the data.
import re
import json
def get_datalayer_json(raw_script_tag: str):
parser_re = r"<script>\s*dataLayer =(.*);\s*</script>"
parser_result = re.match(parser_re, raw_script_tag.strip(), re.DOTALL)
if parser_result is None:
return None
else:
return json.loads(parser_result.group(1))