I have a JSON which is in nested form. I would like to extract specific data from json and put into csv using pandas python.
data = {
"class":"hudson.model.Hudson",
"jobs":[
{
"_class":"hudson.model.FreeStyleProject",
"name":"git_checkout",
"url":"http://localhost:8080/job/git_checkout/",
"builds":[
{
"_class":"hudson.model.FreeStyleBuild",
"duration":1201,
"number":6,
"result":"FAILURE",
"url":"http://localhost:8080/job/git_checkout/6/"
}
]
},
{
"_class":"hudson.model.FreeStyleProject",
"name":"output",
"url":"http://localhost:8080/job/output/",
"builds":[
]
},
{
"_class":"org.jenkinsci.plugins.workflow.job.WorkflowJob",
"name":"pipeline_test",
"url":"http://localhost:8080/job/pipeline_test/",
"builds":[
{
"_class":"org.jenkinsci.plugins.workflow.job.WorkflowRun",
"duration":9274,
"number":85,
"result":"SUCCESS",
"url":"http://localhost:8080/job/pipeline_test/85/"
},
{
"_class":"org.jenkinsci.plugins.workflow.job.WorkflowRun",
"duration":4251,
"number":84,
"result":"SUCCESS",
"url":"http://localhost:8080/job/pipeline_test/84/"
}
]
}
]
}
From the above JSON i want to fetch jobs name value and builds result value . I am new to python any help will be appreciated .
Till now i have tried
main_data = data['jobs]
json_normalize(main_data,['builds'],
record_prefix='jobs_', errors='ignore')
which gives information only build key values and not the name of job .
Can anyone help ?
Expected Output:
Considering only first build result value you can need to be in csv column you can achieve this using pandas.
data = {
"class": "hudson.model.Hudson",
"jobs": [
{
"_class": "hudson.model.FreeStyleProject",
"name": "git_checkout",
"url": "http://localhost:8080/job/git_checkout/",
"builds": [
{
"_class": "hudson.model.FreeStyleBuild",
"duration": 1201,
"number": 6,
"result": "FAILURE",
"url": "http://localhost:8080/job/git_checkout/6/"
}
]
},
{
"_class": "hudson.model.FreeStyleProject",
"name": "output",
"url": "http://localhost:8080/job/output/",
"builds": []
},
{
"_class": "org.jenkinsci.plugins.workflow.job.WorkflowJob",
"name": "pipeline_test",
"url": "http://localhost:8080/job/pipeline_test/",
"builds": [
{
"_class": "org.jenkinsci.plugins.workflow.job.WorkflowRun",
"duration": 9274,
"number": 85,
"result": "SUCCESS",
"url": "http://localhost:8080/job/pipeline_test/85/"
},
{
"_class": "org.jenkinsci.plugins.workflow.job.WorkflowRun",
"duration": 4251,
"number": 84,
"result": "SUCCESS",
"url": "http://localhost:8080/job/pipeline_test/84/"
}
]
}
]
}
main_data = data.get('jobs')
res = {'name':[], 'result':[]}
for name_dict in main_data:
res['name'].append(name_dict.get('name','NA'))
resultval = name_dict['builds'][0].get('result') if len(name_dict['builds'])>0 else 'NA'
res['result'].append(resultval)
print(res)
import pandas as pd
df = pd.DataFrame(res)
df.to_csv("/home/file_timer/jobs.csv", index=False)
Check the csv file output
name,result
git_checkout,FAILURE
output,NA
pipeline_test,SUCCESS
If 'NA' result want to skip then
main_data = data.get('jobs')
res = {'name':[], 'result':[]}
for name_dict in main_data:
if len(name_dict['builds'])==0:
continue
res['name'].append(name_dict.get('name', 'NA'))
resultval = name_dict['builds'][0].get('result')
res['result'].append(resultval)
print(res)
import pandas as pd
df = pd.DataFrame(res)
df.to_csv("/home/akash.pagar/shell_learning/file_timer/jobs.csv", index=False)
Output will bw like
name,result
git_checkout,FAILURE
pipeline_test,SUCCESS
Simply with build number,
for job in data.get('jobs'):
for build in job.get('builds'):
print(job.get('name'), build.get('number'), build.get('result'))
gives the result
git_checkout 6 FAILURE
pipeline_test 85 SUCCESS
pipeline_test 84 SUCCESS
If you want to get the result of latest build, and pretty sure about the build number always in decending order,
for job in data.get('jobs'):
if job.get('builds'):
print(job.get('name'), job.get('builds')[0].get('result'))
and if you are not sure the order,
for job in data.get('jobs'):
if job.get('builds'):
print(job.get('name'), sorted(job.get('builds'), key=lambda k: k.get('number'))[-1].get('result'))
then the result will be:
git_checkout FAILURE
pipeline_test SUCCESS
Assuming last build is the last element of its list and you don't care about jobs with no builds, this does:
import pandas as pd
#data = ... #same format as in the question
z = [(job["name"], job["builds"][-1]["result"]) for job in data["jobs"] if len(job["builds"])]
df = pd.DataFrame(data=z, columns=["name", "result"])
#df.to_csv #TODO
Also we don't necessarily need pandas to create the csv file.
You could do:
import csv
#z = ... #see previous code block
with open("f.csv", 'w') as fp:
csv.writer(fp).writerows([("name", "result")] + z)
Related
I am using Github's GraphQL API to fetch some issue details.
I used Python Requests to fetch the data locally.
This is how the output.json looks like
{
"data": {
"viewer": {
"login": "some_user"
},
"repository": {
"issues": {
"edges": [
{
"node": {
"id": "I_kwDOHQ63-s5auKbD",
"title": "test issue 1",
"number": 146,
"createdAt": "2023-01-06T06:39:54Z",
"closedAt": null,
"state": "OPEN",
"updatedAt": "2023-01-06T06:42:00Z",
"comments": {
"edges": [
{
"node": {
"id": "IC_kwDOHQ63-s5R2XCV",
"body": "comment 01"
}
},
{
"node": {
"id": "IC_kwDOHQ63-s5R2XC9",
"body": "comment 02"
}
}
]
},
"labels": {
"edges": []
}
},
"cursor": "Y3Vyc29yOnYyOpHOWrimww=="
},
{
"node": {
"id": "I_kwDOHQ63-s5auKm8",
"title": "test issue 2",
"number": 147,
"createdAt": "2023-01-06T06:40:34Z",
"closedAt": null,
"state": "OPEN",
"updatedAt": "2023-01-06T06:40:34Z",
"comments": {
"edges": []
},
"labels": {
"edges": [
{
"node": {
"name": "food"
}
},
{
"node": {
"name": "healthy"
}
}
]
}
},
"cursor": "Y3Vyc29yOnYyOpHOWripvA=="
}
]
}
}
}
}
The json was put inside a list using
result = response.json()["data"]["repository"]["issues"]["edges"]
And then this list was put inside a DataFrame
import pandas as pd
df = pd.DataFrame (result, columns = ['node', 'cursor'])
df
These are the contents of the data frame
id
title
number
createdAt
closedAt
state
updatedAt
comments
labels
I_kwDOHQ63-s5auKbD
test issue 1
146
2023-01-06T06:39:54Z
None
OPEN
2023-01-06T06:42:00Z
{'edges': [{'node': {'id': 'IC_kwDOHQ63-s5R2XCV","body": "comment 01"}},{'node': {'id': 'IC_kwDOHQ63-s5R2XC9","body": "comment 02"}}]}
{'edges': []}
I_kwDOHQ63-s5auKm8
test issue 2
147
2023-01-06T06:40:34Z
None
OPEN
2023-01-06T06:40:34Z
{'edges': []}
{'edges': [{'node': {'name': 'food"}},{'node': {'name': 'healthy"}}]}
I would like to split/explode the comments and labels columns.
The values in these columns are nested dictionaries
I would like there to be as many rows for a single issue, as there are comments & labels.
I would like to flatten out the data frame.
So this involves split/explode and concat.
There are several stackoverflow answers that delve on this topic. And I have tried the code from several of them.
I can not paste the links to those questions, because stackoverflow marks my question as spam due to many links.
But these are the steps I have tried
df3 = df2['comments'].apply(pd.Series)
Drill down further
df4 = df3['edges'].apply(pd.Series)
df4
Drill down further
df5 = df4['node'].apply(pd.Series)
df5
The last statement above gives me the KeyError: 'node'
I understand, this is because node is not a key in the DataFrame.
But how else can i split this dictionary and concatenate all columns back to my issues row?
This is how I would like the output to look like
id
title
number
createdAt
closedAt
state
updatedAt
comments
labels
I_kwDOHQ63-s5auKbD
test issue 1
146
2023-01-06T06:39:54Z
None
OPEN
2023-01-06T06:42:00Z
comment 01
Null
I_kwDOHQ63-s5auKbD
test issue 1
146
2023-01-06T06:39:54Z
None
OPEN
2023-01-06T06:42:00Z
comment 02
Null
I_kwDOHQ63-s5auKm8
test issue 2
147
2023-01-06T06:40:34Z
None
OPEN
2023-01-06T06:40:34Z
Null
food
I_kwDOHQ63-s5auKm8
test issue 2
147
2023-01-06T06:40:34Z
None
OPEN
2023-01-06T06:40:34Z
Null
healthy
If dct is your dictionary from the question you can try:
df = pd.DataFrame(d['node'] for d in dct['data']['repository']['issues']['edges'])
df['comments'] = df['comments'].str['edges']
df = df.explode('comments')
df['comments'] = df['comments'].str['node'].str['body']
df['labels'] = df['labels'].str['edges']
df = df.explode('labels')
df['labels'] = df['labels'].str['node'].str['name']
print(df.to_markdown(index=False))
Prints:
id
title
number
createdAt
closedAt
state
updatedAt
comments
labels
I_kwDOHQ63-s5auKbD
test issue 1
146
2023-01-06T06:39:54Z
OPEN
2023-01-06T06:42:00Z
comment 01
nan
I_kwDOHQ63-s5auKbD
test issue 1
146
2023-01-06T06:39:54Z
OPEN
2023-01-06T06:42:00Z
comment 02
nan
I_kwDOHQ63-s5auKm8
test issue 2
147
2023-01-06T06:40:34Z
OPEN
2023-01-06T06:40:34Z
nan
food
I_kwDOHQ63-s5auKm8
test issue 2
147
2023-01-06T06:40:34Z
OPEN
2023-01-06T06:40:34Z
nan
healthy
#andrej-kesely has answered my question.
I have selected his response as the answer for this question.
I am now posting a consolidated script that includes my poor code and andrej's great code.
In this script i want to fetch details from Github's GraphQL API Server.
And put it inside pandas.
Primary source for this script is this gist.
And a major chunk of remaining code is an answer by #andrej-kesely.
Now onto the consolidated script.
First import the necessary packages and set headers
import requests
import json
import pandas as pd
headers = {"Authorization": "token <your_github_personal_access_token>"}
Now define the query that will fetch data from github.
In my particular case, I am fetching issue details form a particular repo
it can be something else for you.
query = """
{
viewer {
login
}
repository(name: "your_github_repo", owner: "your_github_user_name") {
issues(states: OPEN, last: 2) {
edges {
node {
id
title
number
createdAt
closedAt
state
updatedAt
comments(first: 10) {
edges {
node {
id
body
}
}
}
labels(orderBy: {field: NAME, direction: ASC}, first: 10) {
edges {
node {
name
}
}
}
comments(first: 10) {
edges {
node {
id
body
}
}
}
}
cursor
}
}
}
}
"""
Execute the query and save the response
def run_query(query):
request = requests.post('https://api.github.com/graphql', json={'query': query}, headers=headers)
if request.status_code == 200:
return request.json()
else:
raise Exception("Query failed to run by returning code of {}. {}".format(request.status_code, query))
result = run_query(query)
And now is the trickiest part.
In my query response, there are several nested dictionaries.
I would like to split them - more details in my question above.
This magic code from #andrej-kesely does that for you.
df = pd.DataFrame(d['node'] for d in result['data']['repository']['issues']['edges'])
df['comments'] = df['comments'].str['edges']
df = df.explode('comments')
df['comments'] = df['comments'].str['node'].str['body']
df['labels'] = df['labels'].str['edges']
df = df.explode('labels')
df['labels'] = df['labels'].str['node'].str['name']
print(df)
I read csv file into a dataframe named df
Each rows contains str below.
'{"id":2140043003,"name":"Olallo Rubio",...}'
I would like to extract "name" and "id" from each row and make a new dataframe to store the str.
I use the following codes to extract but it shows an error. Please let me know if there is any suggestions on how to solve this problem. Thanks
JSONDecodeError: Expecting ',' delimiter: line 1 column 32 (char 31)
text={
"id": 2140043003,
"name": "Olallo Rubio",
"is_registered": True,
"chosen_currency": 'Null',
"avatar": {
"thumb": "https://ksr-ugc.imgix.net/assets/019/223/259/16513215a3869caaea2d35d43f3c0c5f_original.jpg?w=40&h=40&fit=crop&v=1510685152&auto=format&q=92&s=653706657ccc49f68a27445ea37ad39a",
"small": "https://ksr-ugc.imgix.net/assets/019/223/259/16513215a3869caaea2d35d43f3c0c5f_original.jpg?w=160&h=160&fit=crop&v=1510685152&auto=format&q=92&s=0bd2f3cec5f12553e679153ba2b5d7fa",
"medium": "https://ksr-ugc.imgix.net/assets/019/223/259/16513215a3869caaea2d35d43f3c0c5f_original.jpg?w=160&h=160&fit=crop&v=1510685152&auto=format&q=92&s=0bd2f3cec5f12553e679153ba2b5d7fa"
},
"urls": {
"web": {
"user": "https://www.kickstarter.com/profile/2140043003"
},
"api": {
"user": "https://api.kickstarter.com/v1/users/2140043003?signature=1531480520.09df9a36f649d71a3a81eb14684ad0d3afc83e03"
}
}
}
def extract(text,*args):
list1=[]
for i in args:
list1.append(text[i])
return list1
print(extract(text,'name','id'))
# ['Olallo Rubio', 2140043003]
Here's what I came up with using pandas.json_normalize():
import pandas as pd
sample = [{
"id": 2140043003,
"name":"Olallo Rubio",
"is_registered": True,
"chosen_currency": None,
"avatar":{
"thumb":"https://ksr-ugc.imgix.net/assets/019/223/259/16513215a3869caaea2d35d43f3c0c5f_original.jpg?w=40&h=40&fit=crop&v=1510685152&auto=format&q=92&s=653706657ccc49f68a27445ea37ad39a",
"small":"https://ksr-ugc.imgix.net/assets/019/223/259/16513215a3869caaea2d35d43f3c0c5f_original.jpg?w=160&h=160&fit=crop&v=1510685152&auto=format&q=92&s=0bd2f3cec5f12553e679153ba2b5d7fa",
"medium":"https://ksr-ugc.imgix.net/assets/019/223/259/16513215a3869caaea2d35d43f3c0c5f_original.jpg?w=160&h=160&fit=crop&v=1510685152&auto=format&q=92&s=0bd2f3cec5f12553e679153ba2b5d7fa"
},
"urls":{
"web":{
"user":"https://www.kickstarter.com/profile/2140043003"
},
"api":{
"user":"https://api.kickstarter.com/v1/users/2140043003?signature=1531480520.09df9a36f649d71a3a81eb14684ad0d3afc83e03"
}
}
}]
# Create datafrane
df = pd.json_normalize(sample)
# Select columns into new dataframe.
df1 = df.loc[:, ["name", "id",]]
Check df1:
Input:
print(df1)
Output:
name id
0 Olallo Rubio 2140043003
I am trying to read some json with the following format. A simple pd.read_json() returns ValueError: Trailing data. Adding lines=True returns ValueError: Expected object or value. I've tried various combinations of readlines() and load()/loads() so far without success.
Any ideas how I could get this into a dataframe?
{
"content": "kdjfsfkjlffsdkj",
"source": {
"name": "jfkldsjf"
},
"title": "dsldkjfslj",
"url": "vkljfklgjkdlgj"
}
{
"content": "djlskgfdklgjkfgj",
"source": {
"name": "ldfjkdfjs"
},
"title": "lfsjdfklfldsjf",
"url": "lkjlfggdflkjgdlf"
}
The sample you have above isn't valid JSON. To be valid JSON these objects need to be within a JS array ([]) and be comma separated, as follows:
[{
"content": "kdjfsfkjlffsdkj",
"source": {
"name": "jfkldsjf"
},
"title": "dsldkjfslj",
"url": "vkljfklgjkdlgj"
},
{
"content": "djlskgfdklgjkfgj",
"source": {
"name": "ldfjkdfjs"
},
"title": "lfsjdfklfldsjf",
"url": "lkjlfggdflkjgdlf"
}]
I just tried on my machine. When formatted correctly, it works
>>> pd.read_json('data.json')
content source title url
0 kdjfsfkjlffsdkj {'name': 'jfkldsjf'} dsldkjfslj vkljfklgjkdlgj
1 djlskgfdklgjkfgj {'name': 'ldfjkdfjs'} lfsjdfklfldsjf lkjlfggdflkjgdlf
Another solution if you do not want to reformat your files.
Assuming your JSON is in a string called my_json you could do:
import json
import pandas as pd
splitted = my_json.split('\n\n')
my_list = [json.loads(e) for e in splitted]
df = pd.DataFrame(my_list)
Thanks for the ideas internet. None quite solved the problem in the way I needed (I had lots of newline characters in the strings themselves which meant I couldn't split on them) but they helped point the way. In case anyone has a similar problem, this is what worked for me:
with open('path/to/original.json', 'r') as f:
data = f.read()
data = data.split("}\n")
data = [d.strip() + "}" for d in data]
data = list(filter(("}").__ne__, data))
data = [json.loads(d) for d in data]
with open('path/to/reformatted.json', 'w') as f:
json.dump(data, f)
df = pd.read_json('path/to/reformatted.json')
If you can use jq then solution is simpler:
jq -s '.' path/to/original.json > path/to/reformatted.json
Is there any way to pull the key from JSON if the only thing I know is the value? (In groovy or python)
An example:
I know the "_number" value and I need a key.
So let's say, known _number is 2 and as an output, I should get dsf34f43f34f34f
{
"id": "8e37ecadf4908f79d58080e6ddbc",
"project": "some_project",
"branch": "master",
"current_revision": "3rtgfgdfg2fdsf",
"revisions": {
"43g5g534534rf34f43f": {
"_number": 3,
"created": "2019-04-16 09:03:07.459000000",
"uploader": {
"_account_id": 4
},
"description": "Rebase"
},
"dsf34f43f34f34f": {
"_number": 2,
"created": "2019-04-02 10:54:14.682000000",
"uploader": {
"_account_id": 2
},
"description": "Rebase"
}
}
}
With Groovy:
def json = new groovy.json.JsonSlurper().parse("x.json" as File)
println(json.revisions.findResult{ it.value._number==2 ? it.key : null })
// => dsf34f43f34f34f
Python 3: (assuming that data is saved in data.json):
import json
with open('data.json') as f:
json_data = json.load(f)
for rev, revdata in json_data['revisions'].items():
if revdata['_number'] == 2:
print(rev)
Prints all revs where _number equals 2.
using dict-comprehension:
print({k for k,v in d['revisions'].items() if v.get('_number') == 2})
OUTPUT:
{'dsf34f43f34f34f'}
i have json file that containd the metadata of 900 articles and i want to extract the Urls from it. my file start like this
[
{
"title": "The histologic phenotypes of …",
"authors": [
{
"name": "JE Armes"
},
],
"publisher": "Wiley Online Library",
"article_url": "https://onlinelibrary.wiley.com/doi/abs/10.1002/(SICI)1097-0142(19981201)83:11%3C2335::AID-CNCR13%3E3.0.CO;2-N",
"cites": 261,
"use": true
},
{
"title": "Comparative epidemiology of pemphigus in ...",
"authors": [
{
"name": "S Bastuji-Garin"
},
{
"name": "R Souissi"
}
],
"year": 1995,
"publisher": "search.ebscohost.com",
"article_url": "http://search.ebscohost.com/login.aspx?direct=true&profile=ehost&scope=site&authtype=crawler&jrnl=0022202X&AN=12612836&h=B9CC58JNdE8SYy4M4RyVS%2FrPdlkoZF%2FM5hifWcv%2FwFvGxUCbEaBxwQghRKlK2vLtwY2WrNNl%2B3z%2BiQawA%2BocoA%3D%3D&crl=c",
"use": true
},
.........
I want to inspect the file with objectpath to create json.tree for the extraxtion of the url. this is the code i want to execute
1. import json
2. import objectpath
3. with open("Data_sample.json") as datafile: data = json.load(datafile)
4. jsonnn_tree = objectpath.Tree(data['name of data'])
5. result_tuple = tuple(jsonnn_tree.execute('$..article_url'))
But in the step 4 for the creation of the tree, I have to insert the name of the data whitch i think that i haven't in my file. How can i replace this line?
You can get all the article urls using a list comprehension.
import json
with open("Data_sample.json") as fh:
articles = json.load(fh)
article_urls = [article['article_url'] for article in articles]
You can instantiate the tree like this:
tobj = op.Tree(your_data)
results = tobj.execute("$.article_url")
And in the end:
results = [x for x in results]
will yield:
["url1", "url2", ...]
Did you try removing the reference and just using:
jsonnn_tree = objectpath.Tree(data)