JSON Extraction

Extract, query, and transform data from JSON documents.

Quick Start

import json

# Load JSON
with open('data.json') as f:
    data = json.load(f)

# Access nested data
value = data['key']['nested']['value']
items = data.get('items', [])

JSONPath Queries

Use jsonpath-ng for complex queries:

pip install jsonpath-ng

from jsonpath_ng import parse

# Find all prices
jsonpath_expr = parse('$.products[*].price')
prices = [match.value for match in jsonpath_expr.find(data)]

# Find nested items
jsonpath_expr = parse('$..items[*].name')
names = [match.value for match in jsonpath_expr.find(data)]

Common JSONPath Patterns

Flattening Nested JSON

def flatten_json(nested: dict, prefix: str = '') -> dict:
    """Flatten nested JSON into single-level dictionary."""
    flat = {}
    for key, value in nested.items():
        new_key = f"{prefix}.{key}" if prefix else key
        if isinstance(value, dict):
            flat.update(flatten_json(value, new_key))
        elif isinstance(value, list):
            for i, item in enumerate(value):
                if isinstance(item, dict):
                    flat.update(flatten_json(item, f"{new_key}[{i}]"))
                else:
                    flat[f"{new_key}[{i}]"] = item
        else:
            flat[new_key] = value
    return flat

Extracting from API Responses

def extract_paginated(response_json: dict) -> list:
    """Extract data from paginated API response."""
    data = response_json.get('data', response_json.get('results', []))
    return data

def safe_get(data: dict, *keys, default=None):
    """Safely navigate nested dictionary."""
    for key in keys:
        if isinstance(data, dict):
            data = data.get(key, default)
        elif isinstance(data, list) and isinstance(key, int):
            data = data[key] if key < len(data) else default
        else:
            return default
    return data

Helper Script

Use extract_json.py for command-line extraction:

python extract_json.py data.json --path "$.items[*].name" --output names.json
python extract_json.py data.json --flatten --output flat.json