CKAN API Testing Prompts

Note: These prompts are from Day 7 (6/11/24) of the logbook.

System Instructions:

Same as the instructions for Example 1 in practice.

Helping set up the CKAN API and Creating a Dataset

Prompt:

Create a python script that sets up the CKAN API and creates a dataset in CKAN in a specific organization. Make sure to include comments in the script to explain what each part of the code does.

Response:

# Import the necessary libraries
import requests
import json

# Set the URL for the CKAN API
ckan_url = 'https://data.yourorganization.org'

# Set the API key for the CKAN API
api_key = 'YOUR_API_KEY'

# Function to create a new dataset in a specific organization
def create_dataset_in_org(name, title, description, owner_org):
    # Set the URL for the CKAN API endpoint to create a new dataset
    url = f'{ckan_url}/api/3/action/package_create'

    # Set the headers for the request
    headers = {
        'Authorization': api_key,
        'Content-Type': 'application/json'
    }
    # Prepare the data to be sent in the request
    data = {
        'name': name,
        'title': title,
        'notes': description,
        'owner_org': owner_org
    }
    # Make the request to create the dataset
    response = requests.post(url, headers=headers, data=json.dumps(data))
    return response.json()

Creating a Function to Get the Dataset ID

Prompt:

Create a Python function that takes a dataset name as input and returns the dataset ID from CKAN. The function should handle cases where the dataset is not found and return None in such cases.

Response:

def get_dataset_id(dataset_name):
    url = f'{ckan_url}/api/3/action/package_show'
    headers = {'Authorization': api_key}
    params = {'id': dataset_name}

    response = requests.get(url, headers=headers, params=params)

    if response.status_code == 200:
        # The dataset exists and the response contains the dataset metadata
        dataset_metadata = response.json()
        if dataset_metadata['success']:
            return dataset_metadata['result']['id']
        else:
            print(f"Error: {dataset_metadata['error']['message']}")
            return None
    elif response.status_code == 404:
        print(f"Dataset '{dataset_name}' not found.")
        return None
    else:
        print(f"An error occurred: {response.status_code} - {response.text}")
        return None

Debugging the get_dataset_id Function

Prompt:

Can you tell me why this function call is saying that the dataset is not found even though I know that the dataset name is correct and the dataset exists in the organization?

(Same function as above)

Response:

If the function call is saying that the dataset is not found even though the dataset name is correct and it exists, there might be several potential issues to investigate:

1. Dataset Name: Ensure that the dataset_name provided is exactly as it appears in CKAN, including case sensitivity and any special characters.
2. Authorization: Verify that the API key has the necessary permissions to access the dataset.
3. CKAN Instance URL: Ensure that the ckan_url is correct and points to the right CKAN instance.
4. API Endpoint: Ensure that the CKAN instance's API endpoint is working correctly.

Adding Comments to the Functions

Prompt:

Add comments to the below functions to explain what each function does, what parameters it takes, and what it returns. Make sure to include a brief description of the purpose of the function and any important details that the user should be aware of when using it.

Functions (Not Shown Here)

Response:

(Not Shown Here)

Can be found in the CKAN API Testing Scripts.

💬

x