I am trying to combine multiple lists in selected format. Simply, trying to create
elapsed + "' " + player + ' (A: ' + assist + ') - ' + detail (for example: 51' H. Onyekuru (A: R. Babel) - Normal Goal ). I also added the json file i took the data. Maybe it can be created directly without creating lists.
Code:
elapsed = []
player = []
assist = []
detail = []
for item in data['response']:
player.append(item['player']['name'])
for item in data['response']:
elapsed.append(item['time']['elapsed'])
for item in data['response']:
assist.append(item['assist']['name'])
for item in data['response']:
detail.append(item['detail'])
JSON file:
{
"get": "fixtures/events",
"parameters": { "fixture": "599120", "type": "goal" },
"errors": [],
"results": 3,
"paging": { "current": 1, "total": 1 },
"response": [
{
"time": { "elapsed": 51, "extra": null },
"team": {
"id": 645,
"name": "Galatasaray",
"logo": "https://media.api-sports.io/football/teams/645.png"
},
"player": { "id": 456, "name": "H. Onyekuru" },
"assist": { "id": 19034, "name": "R. Babel" },
"type": "Goal",
"detail": "Normal Goal",
"comments": null
},
{
"time": { "elapsed": 79, "extra": null },
"team": {
"id": 645,
"name": "Galatasaray",
"logo": "https://media.api-sports.io/football/teams/645.png"
},
"player": { "id": 456, "name": "H. Onyekuru" },
"assist": { "id": 142959, "name": "K. Akturkoglu" },
"type": "Goal",
"detail": "Normal Goal",
"comments": null
},
{
"time": { "elapsed": 90, "extra": 7 },
"team": {
"id": 3573,
"name": "Gazi\u015fehir Gaziantep",
"logo": "https://media.api-sports.io/football/teams/3573.png"
},
"player": { "id": 25921, "name": "A. Maxim" },
"assist": { "id": null, "name": null },
"type": "Goal",
"detail": "Penalty",
"comments": null
}
]
}
Output:
['H. Onyekuru', 'H. Onyekuru', 'A. Maxim']
[51, 79, 90]
['R. Babel', 'K. Akturkoglu', None]
['Normal Goal', 'Normal Goal', 'Penalty']
Sure you can – just iterate over the events and print out those lines (or gather them into a list if you like, for example). The f-string syntax below requires Python 3.6 or newer.
data = {
# ... elided for brevity, see OP's post
}
for event in data["response"]:
print(f"{event['time']['elapsed']}' {event['player']['name']} (A: {event['assist']['name']}) {event['detail']}")
This prints out
51' H. Onyekuru (A: R. Babel) Normal Goal
79' H. Onyekuru (A: K. Akturkoglu) Normal Goal
90' A. Maxim (A: None) Penalty
This creates a list of strings in the format that you want. As a bonus, python is quite nice for iterables so it can be done in one line.
list_of_all = [f"{item['time']['elapsed']}' {item['player']['name']} ({item['assist']['name']}) {item['detail']}" for item in data['response']]
Related
Goal: To create a script that will take in nested JSON object as input and output a CSV file with all keys as rows in the CSV?
Example:
{
"Document": {
"DocumentType": 945,
"Version": "V007",
"ClientCode": "WI",
"Shipment": [
{
"ShipmentHeader": {
"ShipmentID": 123456789,
"OrderChannel": "Shopify",
"CustomerNumber": 234234,
"VendorID": "2343SDF",
"ShipViaCode": "FEDX2D",
"AsnDate": "2018-01-27",
"AsnTime": "09:30:47-08:00",
"ShipmentDate": "2018-01-23",
"ShipmentTime": "09:30:47-08:00",
"MBOL": 12345678901234568,
"BOL": 12345678901234566,
"ShippingNumber": "1ZTESTTEST",
"LoadID": 321456987,
"ShipmentWeight": 10,
"ShipmentCost": 2.3,
"CartonsTotal": 2,
"CartonPackagingCode": "CTN25",
"OrdersTotal": 2
},
"References": [
{
"Reference": {
"ReferenceQualifier": "TST",
"ReferenceText": "Testing text"
}
}
],
"Addresses": {
"Address": [
{
"AddressLocationQualifier": "ST",
"LocationNumber": 23234234,
"Name": "John Smith",
"Address1": "123 Main St",
"Address2": "Suite 12",
"City": "Hometown",
"State": "WA",
"Zip": 92345,
"Country": "USA"
},
{
"AddressLocationQualifier": "BT",
"LocationNumber": 2342342,
"Name": "Jane Smith",
"Address1": "345 Second Ave",
"Address2": "Building 32",
"City": "Sometown",
"State": "CA",
"Zip": "23665-0987",
"Country": "USA"
}
]
},
"Orders": {
"Order": [
{
"OrderHeader": {
"PurchaseOrderNumber": 23456342,
"RetailerPurchaseOrderNumber": 234234234,
"RetailerOrderNumber": 23423423,
"CustomerOrderNumber": 234234234,
"Department": 3333,
"Division": 23423,
"OrderWeight": 10.23,
"CartonsTotal": 2,
"QTYOrdered": 12,
"QTYShipped": 23
},
"Cartons": {
"Carton": [
{
"SSCC18": 12345678901234567000,
"TrackingNumber": "1ZTESTTESTTEST",
"CartonContentsQty": 10,
"CartonWeight": 10.23,
"LineItems": {
"LineItem": [
{
"LineNumber": 1,
"ItemNumber": 1234567890,
"UPC": 9876543212,
"QTYOrdered": 34,
"QTYShipped": 32,
"QTYUOM": "EA",
"Description": "Shoes",
"Style": "Tall",
"Size": 9.5,
"Color": "Bllack",
"RetailerItemNumber": 2342333,
"OuterPack": 10
},
{
"LineNumber": 2,
"ItemNumber": 987654321,
"UPC": 7654324567,
"QTYOrdered": 12,
"QTYShipped": 23,
"QTYUOM": "EA",
"Description": "Sunglasses",
"Style": "Short",
"Size": 10,
"Color": "White",
"RetailerItemNumber": 565465456,
"OuterPack": 12
}
]
}
}
]
}
}
]
}
}
]
}
}
In the above JSON Object, I want all the keys (nested included) in a List (Duplicates can be removed by using a set Data Structure). If Nested Key Occurs like in actual JSON they can be keys multiple times in the CSV !
I personally feel that recursion is a perfect application for this type of problem if the amount of nests you will encounter is unpredictable. Here I have written an example in Python of how you can utilise recursion to extract all keys. Cheers.
import json
row = ""
def extract_keys(data):
global row
if isinstance(data, dict):
for key, value in data.items():
row += key + "\n"
extract_keys(value)
elif isinstance(data, list):
for element in data:
extract_keys(element)
# MAIN
with open("input.json", "r") as rfile:
dicts = json.load(rfile)
extract_keys(dicts)
with open("output.csv", "w") as wfile:
wfile.write(row)
I've never heard of or found an option for what I'm looking for, but maybe someone knows a way:
To collect the data from a JSON I need to map manually it like this:
events = response['events']
for event in events:
tournament_name = event['tournament']['name']
tournament_slug = event['tournament']['slug']
tournament_category_name = event['tournament']['category']['name']
tournament_category_slug = event['tournament']['category']['slug']
tournament_category_sport_name = event['tournament']['category']['sport']['name']
tournament_category_sport_slug = event['tournament']['category']['sport']['slug']
tournament_category_sport_id = event['tournament']['category']['sport']['id']
The complete model is this:
{
"events": [
{
"tournament": {
"name": "Serie A",
"slug": "serie-a",
"category": {
"name": "Italy",
"slug": "italy",
"sport": {
"name": "Football",
"slug": "football",
"id": 1
},
"id": 31,
"flag": "italy",
"alpha2": "IT"
},
"uniqueTournament": {
"name": "Serie A",
"slug": "serie-a",
"category": {
"name": "Italy",
"slug": "italy",
"sport": {
"name": "Football",
"slug": "football",
"id": 1
},
"id": 31,
"flag": "italy",
"alpha2": "IT"
},
"userCount": 586563,
"id": 23,
"hasEventPlayerStatistics": true
},
"priority": 254,
"id": 33
},
"roundInfo": {
"round": 24
},
"customId": "Kdbsfeb",
"status": {
"code": 7,
"description": "2nd half",
"type": "inprogress"
},
"winnerCode": 0,
"homeTeam": {
"name": "Bologna",
"slug": "bologna",
"shortName": "Bologna",
"gender": "M",
"userCount": 39429,
"nameCode": "BOL",
"national": false,
"type": 0,
"id": 2685,
"subTeams": [
],
"teamColors": {
"primary": "#003366",
"secondary": "#cc0000",
"text": "#cc0000"
}
},
"awayTeam": {
"name": "Empoli",
"slug": "empoli",
"shortName": "Empoli",
"gender": "M",
"userCount": 31469,
"nameCode": "EMP",
"national": false,
"type": 0,
"id": 2705,
"subTeams": [
],
"teamColors": {
"primary": "#0d5696",
"secondary": "#ffffff",
"text": "#ffffff"
}
},
"homeScore": {
"current": 0,
"display": 0,
"period1": 0
},
"awayScore": {
"current": 0,
"display": 0,
"period1": 0
},
"coverage": 1,
"time": {
"initial": 2700,
"max": 5400,
"extra": 540,
"currentPeriodStartTimestamp": 1644159735
},
"changes": {
"changes": [
"status.code",
"status.description",
"time.currentPeriodStart"
],
"changeTimestamp": 1644159743
},
"hasGlobalHighlights": false,
"hasEventPlayerStatistics": true,
"hasEventPlayerHeatMap": true,
"id": 9645399,
"statusTime": {
"prefix": "",
"initial": 2700,
"max": 5400,
"timestamp": 1644159735,
"extra": 540
},
"startTimestamp": 1644156000,
"slug": "empoli-bologna",
"lastPeriod": "period2",
"finalResultOnly": false
}
]
}
In my example I am collecting 7 values.
But there are 83 possible values to be collected.
In case I want to get all the values options that exist in this JSON, is there any way to make this map sequence automatically to print so I can copy it to the code?
Because manually it takes too long to do and it's very tiring.
And the results of texts like print() in terminal would be something like:
tournament_name = event['tournament']['name']
tournament_slug = event['tournament']['slug']
...
...
...
And so on until delivering the 83 object paths with values to collect...
Then I could copy all the prints and paste into my Python file to retrieve the values or any other way to make the work easier.
If the elements in the events arrays are the same, this code works without errors.
def get_prints(recode: dict):
for key in recode.keys():
if type(recode[key]) == dict:
for sub_print in get_prints(recode[key]):
yield [key] + sub_print
else:
yield [key]
class Automater:
def __init__(self,name: str):
"""
Params:
name: name of json
"""
self.name = name
def get_print(self,*args):
"""
Params:
*args: keys json
"""
return '_'.join(args) + ' = ' + self.name + ''.join([f"['{arg}']" for arg in args])
For example, this code:
dicts = {
'tournament':{
'name':"any name",
'slug':'somthing else',
'sport':{
'name':'sport',
'anotherdict':{
'yes':True
}
}
}
}
list_names = get_prints(dicts)
for name in list_names:
print(auto.get_print(*name))
Gives this output:
tournament_name = event['tournament']['name']
tournament_slug = event['tournament']['slug']
tournament_sport_name = event['tournament']['sport']['name']
tournament_sport_anotherdict_yes = event['tournament']['sport']['anotherdict']['yes']
I am trying to access the team name key value and the american key value
print(bv_json['outcomes'][0]['description'])
the parts of the json table that I need are denoted with the ########### trailing near the end of the table posted, I get an error about needing an integer to iterate rather than string, I am also struggling with navigating through the keys
thanks
[
{
"path": [
{
"id": "2958468",
"link": "/basketball/nba",
"description": "NBA",
"type": "LEAGUE",
"sportCode": "BASK",
"order": 1,
"leaf": true,
"current": true
},
{
"id": "227",
"link": "/basketball",
"description": "Basketball",
"type": "SPORT",
"sportCode": "BASK",
"order": 1,
"leaf": false,
"current": false
}
],
"events": [
{
"id": "8801181",
"description": "L.A. Clippers # Utah Jazz",
"type": "GAMEEVENT",
"link": "/basketball/nba/l-a-clippers-utah-jazz-202106082215",
"status": "O",
"sport": "BASK",
"startTime": 1623204900000,
"live": true,
"awayTeamFirst": true,
"denySameGame": "NO",
"teaserAllowed": true,
"competitionId": "2958468",
"notes": "Best of 7 - Game 1",
"numMarkets": 34,
"lastModified": 1623212024024,
"competitors": [
{
"id": "8801181-285",
"name": "Utah Jazz",
"home": true
},
{
"id": "8801181-310",
"name": "L.A. Clippers",
"home": false
}
],
"displayGroups": [
{
"id": "100-97",
"description": "Game Lines",
"defaultType": true,
"alternateType": false,
"markets": [
{
"id": "157658380",
"descriptionKey": "Head To Head",
"description": "Moneyline",
"key": "2W-12",
"marketTypeId": "3059",
"status": "O",
"singleOnly": false,
"notes": "",
"period": {
"id": "341",
"description": "Live Game",
"abbreviation": "G",
"live": true,
"main": true
},
"outcomes": [
{
"id": "849253180",
"description": "L.A. Clippers",##############
"status": "O",
"type": "A",
"competitorId": "8801181-310",
"price": {
"id": "7927852247",
"american": "+125",#########################
"decimal": "2.250",
"fractional": "5/4",
"malay": "-0.80",
"indonesian": "1.25",
"hongkong": "1.25"
It looks like your data structure is
[{[{[{[{{}}]}]}]}]
Which is a list containing a dictionary of a list of dictionaries of lists of dictionaries, which is to say it's nested and confusing.
To make it easy on yourself, I think defining some variables will help.
Let's access the first level list item, the dictionary that contains 'path'- this dict contains all the other lists of dictionaries.
full_dict = bvjson[0] # step into a list
Looking at the data, we know that outcomes is in the 'events' list of dicts, so let's define that variable to make it easier to step into for our when we get to our ultimate answer.
events = full_dict['events'] # access dictionary value by key
Now we have access to events, which is a list of dictionaries of lists of dictionaries.
In events, we see that 'outcomes' actually lives two steps into the 'displayGroups' value, so let's get 'displayGroups' into something useable.
display = events['displayGroups'][0]
# 'displayGroups' is a key in the dictionary in the event list,
# and it holds a list of dictionaries, so we use [0] to step
# into the list to access the dicts.
# Note - if there are multiple lists this will only access the first one.
Stepping in further:
markets = display['markets'][0]
outcomes = markets['outcomes'][0]
You finally have easy access to the outcomes list of dict!
description = outcomes['description']
price = outcomes['price']['american']
So remember, anytime you get a confusing nested json like this, stepping in to each value can help you figure out how to get what you want and if you need to access via index (if it's a list) or via key (if it's a dictionary).
Think of all of this as just a way to diagnose and figure out why you aren't getting the values you are requesting - it will be different for each case, and different logic will be required for handling getting multiple values out of each list or dict - but this is a good start and way to get your mind around it.
Here is your data properly enclosed:
bvjson =
[
{
"path": [
{
"id": "2958468",
"link": "/basketball/nba",
"description": "NBA",
"type": "LEAGUE",
"sportCode": "BASK",
"order": 1,
"leaf": True,
"current": True
},
{
"id": "227",
"link": "/basketball",
"description": "Basketball",
"type": "SPORT",
"sportCode": "BASK",
"order": 1,
"leaf": False,
"current": False
}
],
"events": [
{
"id": "8801181",
"description": "L.A. Clippers # Utah Jazz",
"type": "GAMEEVENT",
"link": "/basketball/nba/l-a-clippers-utah-jazz-202106082215",
"status": "O",
"sport": "BASK",
"startTime": 1623204900000,
"live": True,
"awayTeamFirst": True,
"denySameGame": "NO",
"teaserAllowed": True,
"competitionId": "2958468",
"notes": "Best of 7 - Game 1",
"numMarkets": 34,
"lastModified": 1623212024024,
"competitors": [
{
"id": "8801181-285",
"name": "Utah Jazz",
"home": True
},
{
"id": "8801181-310",
"name": "L.A. Clippers",
"home": False
}
],
"displayGroups": [
{
"id": "100-97",
"description": "Game Lines",
"defaultType": True,
"alternateType": False,
"markets": [
{
"id": "157658380",
"descriptionKey": "Head To Head",
"description": "Moneyline",
"key": "2W-12",
"marketTypeId": "3059",
"status": "O",
"singleOnly": False,
"notes": "",
"period": {
"id": "341",
"description": "Live Game",
"abbreviation": "G",
"live": True,
"main": True
},
"outcomes": [
{
"id": "849253180",
"description": "L.A. Clippers",##############
"status": "O",
"type": "A",
"competitorId": "8801181-310",
"price": {
"id": "7927852247",
"american": "+125",#########################
"decimal": "2.250",
"fractional": "5/4",
"malay": "-0.80",
"indonesian": "1.25",
"hongkong": "1.25"}
}
]
}
]
}
]
}
]
}
]
I have a json file where I need to read it in a structured way to insert in a database each value in its respective column, but in the tag "customFields" the fields change index, example: "Tribe / Customer" can be index 0 (row['customFields'][0]) in a json block, and in the other one be index 3 (row['customFields'][3]), so I tried to read the data using the name of the row field ['customFields'] ['Tribe / Customer'], but I got the error below:
TypeError: list indices must be integers or slices, not str
Script:
def getCustomField(ModelData):
for row in ModelData["data"]["squads"][0]["cards"]:
print(row['identifier'],
row['customFields']['Tribe / Customer'],
row['customFields']['Stopped with'],
row['customFields']['Sub-Activity'],
row['customFields']['Activity'],
row['customFields']['Complexity'],
row['customFields']['Effort'])
if __name__ == "__main__":
f = open('test.json')
json_file = json.load(f)
getCustomField(json_file)
JSON:
{
"data": {
"squads": [
{
"name": "TESTE",
"cards": [
{
"identifier": "0102",
"title": "TESTE",
"description": " TESTE ",
"status": "on_track",
"priority": null,
"assignees": [
{
"fullname": "TESTE",
"email": "TESTE"
}
],
"createdAt": "2020-04-16T15:00:31-03:00",
"secondaryLabel": null,
"primaryLabels": [
"TESTE",
"TESTE"
],
"swimlane": "TESTE",
"workstate": "Active",
"customFields": [
{
"name": "Tribe / Customer",
"value": "TESTE 1"
},
{
"name": "Checkpoint",
"value": "GNN"
},
{
"name": "Stopped with",
"value": null
},
{
"name": "Sub-Activity",
"value": "DEPLOY"
},
{
"name": "Activity",
"value": "TOOL"
},
{
"name": "Complexity",
"value": "HIGH"
},
{
"name": "Effort",
"value": "20"
}
]
},
{
"identifier": "0103",
"title": "TESTE",
"description": " TESTE ",
"status": "on_track",
"priority": null,
"assignees": [
{
"fullname": "TESTE",
"email": "TESTE"
}
],
"createdAt": "2020-04-16T15:00:31-03:00",
"secondaryLabel": null,
"primaryLabels": [
"TESTE",
"TESTE"
],
"swimlane": "TESTE",
"workstate": "Active",
"customFields": [
{
"name": "Tribe / Customer",
"value": "TESTE 1"
},
{
"name": "Stopped with",
"value": null
},
{
"name": "Checkpoint",
"value": "GNN"
},
{
"name": "Sub-Activity",
"value": "DEPLOY"
},
{
"name": "Activity",
"value": "TOOL"
},
{
"name": "Complexity",
"value": "HIGH"
},
{
"name": "Effort",
"value": "20"
}
]
}
]
}
]
}
}
You'll have to parse the list of custom fields into something you can access by name. Since you're accessing multiple entries from the same list, a dictionary is the most appropriate choice.
for row in ModelData["data"]["squads"][0]["cards"]:
custom_fields_dict = {field['name']: field['value'] for field in row['customFields']}
print(row['identifier'],
custom_fields_dict['Tribe / Customer'],
...
)
If you only wanted a single field you could traverse the list looking for a match, but it would be less efficient to do that repeatedly.
I'm skipping over dealing with missing fields - you'd probably want to use get('Tribe / Customer', some_reasonable_default) if there's any possibility of the field not being present in the json list.
Hi im am trying to parse json data and gets this error every time the element
if ['fields']['assignee'] in each:
TypeError: list indices must be integers or slices, not str
>>>
My json is this
{
"expand": "schema,names",
"startAt": 1,
"maxResults": 50,
"total": 7363,
"issues": [
{
"expand": "operations,versionedRepresentations,editmeta,changelog,renderedFields",
"id": "591838",
"self": "https://jira.mynet.com/rest/api/2/issue/591838",
"key": "TEST-8564",
"fields": {
"summary": "delete tables 31-03-2020 ",
"customfield_10006": 2.0,
"created": "2020-02-27T10:29:12.000+0100",
"description": "A LOT OF TEXT",
"assignee": null,
"labels": [
"DATA",
"Refined"
],
"status": {
"self": "https://jira.mynet.com/rest/api/2/status/10000",
"description": "",
"iconUrl": "https://jira.mynet.com/",
"name": "To Do",
"id": "10000",
"statusCategory": {
"self": "https://jira.mynet.com/rest/api/2/statuscategory/2",
"id": 2,
"key": "new",
"colorName": "blue-gray",
"name": "To Do"
}
}
}
}
]
}
The element in ['fields']['assignee'] is NULL in this example
sometimes it is like this
"assignee": : {
"self": "https://mynet.com/rest/api/2/user?username=xxxxxx",
"name": "sij",
"key": "x",
"emailAddress": xx#mynet.com",
"avatarUrls": {
"48x48": "https://mynet.com/secure/useravatar?ownerId=bdysdh&avatarId=16743",
"24x24": "https://mynet.com/secure/useravatar?size=small&ownerId=bdysdh&avatarId=16743",
"16x16": "https://mynet.com/secure/useravatar?size=xsmall&ownerId=bdysdh&avatarId=16743",
"32x32": "https://mynet.com/secure/useravatar?size=medium&ownerId=bdysdh&avatarId=16743"
},
"displayName": "Bruce Springsteen",
"active": true,
"timeZone": "Arctic/Longyearbyen"
},
I am trying to check of assignee is null and if so print null
my code looks like this
with open('C:\\TEMP\\testdata.json') as json_file:
data = json.load(json_file)
for each in data['issues']:
if ['fields']['assignee'] in each:
print (['fields']['assignee']['name'])
else:
print ('null')
I have tried to put in [0] between ['fields']['assignee']['name'] but nothing seems to help.
Try with
if 'fields' in each and 'assignee' in each['fields']:
Note that you need the name of the key, not surrounded by square brackets.
Perhaps better:
for each in data['issues']:
print(each.get('fields', {}).get('assignee', {}).get('name', 'null'))
and if you can't guarantee that 'issues' exists in data either:
for each in data.get('issues', []):
<as before>
data.get('issues', []) returns an empty list if data['issuess'] doesn't exist.