Erweiterte Techniken zur Handhabung von verschachteltem JSON
Nachdem wir grundlegende Ansätze zur Handhabung von KeyError in verschachtelten JSON-Objekten untersucht haben, wollen wir uns einige fortgeschrittenere Techniken ansehen, die Ihren Code noch robuster und wartungsfreundlicher machen können.
-
Erstellen Sie eine neue Datei namens advanced_techniques.py in der WebIDE.
-
Fügen Sie den folgenden Code hinzu, um mehrere erweiterte Techniken zu implementieren:
## Exploring advanced techniques for handling nested JSON objects
import json
from functools import reduce
import operator
## Sample JSON data with various nested structures
json_str = """
{
"user": {
"id": 12345,
"name": "Jane Smith",
"profile": {
"bio": "Software developer with 5 years of experience",
"social_media": {
"twitter": "@janesmith",
"linkedin": "jane-smith"
}
},
"skills": ["Python", "JavaScript", "SQL"],
"employment": {
"current": {
"company": "Tech Solutions Inc.",
"position": "Senior Developer"
},
"previous": [
{
"company": "WebDev Co",
"position": "Junior Developer",
"duration": "2 years"
}
]
}
}
}
"""
## Parse the JSON string into a Python dictionary
data = json.loads(json_str)
print("Loaded JSON data structure:")
print(json.dumps(data, indent=2)) ## Pretty-print the JSON data
print("\n----- Technique 1: Using a path string with split -----")
def get_by_path(data, path_string, default=None, separator='.'):
"""
Access a nested value using a dot-separated path string.
Example:
get_by_path(data, "user.profile.social_media.twitter")
"""
keys = path_string.split(separator)
## Start with the root data
current = data
## Try to traverse the path
for key in keys:
## Handle array indices in the path (e.g., "employment.previous.0.company")
if key.isdigit() and isinstance(current, list):
index = int(key)
if 0 <= index < len(current):
current = current[index]
else:
return default
elif isinstance(current, dict) and key in current:
current = current[key]
else:
return default
return current
## Test the function
paths_to_check = [
"user.name",
"user.profile.social_media.twitter",
"user.skills.1",
"user.employment.current.position",
"user.employment.previous.0.company",
"user.contact.email", ## This path doesn't exist
]
for path in paths_to_check:
value = get_by_path(data, path, "Not available")
print(f"{path}: {value}")
print("\n----- Technique 2: Using functools.reduce -----")
def get_by_path_reduce(data, path_list, default=None):
"""
Access a nested value using reduce and operator.getitem.
This approach is more concise but less flexible with error handling.
"""
try:
return reduce(operator.getitem, path_list, data)
except (KeyError, IndexError, TypeError):
return default
## Test the reduce-based function
path_lists = [
["user", "name"],
["user", "profile", "social_media", "twitter"],
["user", "skills", 1],
["user", "employment", "current", "position"],
["user", "employment", "previous", 0, "company"],
["user", "contact", "email"], ## This path doesn't exist
]
for path in path_lists:
value = get_by_path_reduce(data, path, "Not available")
path_str = "->".join([str(p) for p in path])
print(f"{path_str}: {value}")
print("\n----- Technique 3: Class-based approach -----")
class SafeDict:
"""
A wrapper class for dictionaries that provides safe access to nested keys.
"""
def __init__(self, data):
self.data = data
def get(self, *keys, default=None):
"""
Access nested keys safely, returning default if any key is missing.
"""
current = self.data
for key in keys:
if isinstance(current, dict) and key in current:
current = current[key]
elif isinstance(current, list) and isinstance(key, int) and 0 <= key < len(current):
current = current[key]
else:
return default
return current
def __str__(self):
return str(self.data)
## Create a SafeDict instance
safe_data = SafeDict(data)
## Test the class-based approach
print(f"User name: {safe_data.get('user', 'name', default='Unknown')}")
print(f"Twitter handle: {safe_data.get('user', 'profile', 'social_media', 'twitter', default='None')}")
print(f"Second skill: {safe_data.get('user', 'skills', 1, default='None')}")
print(f"Current position: {safe_data.get('user', 'employment', 'current', 'position', default='None')}")
print(f"Previous company: {safe_data.get('user', 'employment', 'previous', 0, 'company', default='None')}")
print(f"Email (missing): {safe_data.get('user', 'contact', 'email', default='Not provided')}")
- Speichern Sie die Datei und führen Sie sie aus, indem Sie ein Terminal öffnen und Folgendes eingeben:
python3 advanced_techniques.py
Sie sollten eine Ausgabe sehen, die verschiedene Möglichkeiten zur sicheren Zugriff auf verschachtelte Werte in JSON-Objekten demonstriert. Jede Technik hat ihre eigenen Vorteile:
- Pfad-String mit Split: Einfach zu verwenden, wenn Ihr Pfad als String definiert ist (z. B. in Konfigurationsdateien)
- Reduce mit operator.getitem: Ein präziserer Ansatz, nützlich in der funktionalen Programmierung
- Klassenbasierter Ansatz: Bietet einen wiederverwendbaren Wrapper, der Ihren Code sauberer und wartungsfreundlicher macht
Erstellen wir nun eine praktische Anwendung, die diese Techniken verwendet, um eine komplexere JSON-Datenstruktur zu verarbeiten:
## Create a new file called practical_example.py
- Erstellen Sie eine neue Datei namens
practical_example.py und fügen Sie den folgenden Code hinzu:
import json
## Sample JSON data representing a customer order system
json_str = """
{
"orders": [
{
"order_id": "ORD-001",
"customer": {
"id": "CUST-101",
"name": "Alice Johnson",
"contact": {
"email": "alice@example.com",
"phone": "555-1234"
}
},
"items": [
{
"product_id": "PROD-A1",
"name": "Wireless Headphones",
"price": 79.99,
"quantity": 1
},
{
"product_id": "PROD-B2",
"name": "Smartphone Case",
"price": 19.99,
"quantity": 2
}
],
"shipping_address": {
"street": "123 Maple Ave",
"city": "Springfield",
"state": "IL",
"zip": "62704"
},
"payment": {
"method": "credit_card",
"status": "completed"
}
},
{
"order_id": "ORD-002",
"customer": {
"id": "CUST-102",
"name": "Bob Smith",
"contact": {
"email": "bob@example.com"
// phone missing
}
},
"items": [
{
"product_id": "PROD-C3",
"name": "Bluetooth Speaker",
"price": 49.99,
"quantity": 1
}
],
"shipping_address": {
"street": "456 Oak St",
"city": "Rivertown",
"state": "CA"
// zip missing
}
// payment information missing
}
]
}
"""
## Parse the JSON data
try:
data = json.loads(json_str)
except json.JSONDecodeError as e:
print(f"Invalid JSON: {e}")
exit(1)
## Import our SafeDict class from the previous example
class SafeDict:
def __init__(self, data):
self.data = data
def get(self, *keys, default=None):
current = self.data
for key in keys:
if isinstance(current, dict) and key in current:
current = current[key]
elif isinstance(current, list) and isinstance(key, int) and 0 <= key < len(current):
current = current[key]
else:
return default
return current
def __str__(self):
return str(self.data)
## Create a SafeDict instance
safe_data = SafeDict(data)
print("Processing order information safely...")
## Process each order
for i in range(10): ## Try to process up to 10 orders
## Use SafeDict to avoid KeyError
order = safe_data.get('orders', i)
if order is None:
print(f"No order found at index {i}")
break
## Create a SafeDict for this specific order
order_dict = SafeDict(order)
## Safely extract order information
order_id = order_dict.get('order_id', default='Unknown')
customer_name = order_dict.get('customer', 'name', default='Unknown Customer')
customer_email = order_dict.get('customer', 'contact', 'email', default='No email provided')
customer_phone = order_dict.get('customer', 'contact', 'phone', default='No phone provided')
## Process shipping information
shipping = order_dict.get('shipping_address', default={})
shipping_dict = SafeDict(shipping)
shipping_address = f"{shipping_dict.get('street', default='')}, " \
f"{shipping_dict.get('city', default='')}, " \
f"{shipping_dict.get('state', default='')} " \
f"{shipping_dict.get('zip', default='')}"
## Process payment information
payment_status = order_dict.get('payment', 'status', default='Unknown')
## Calculate order total
items = order_dict.get('items', default=[])
order_total = 0
for item in items:
item_dict = SafeDict(item)
price = item_dict.get('price', default=0)
quantity = item_dict.get('quantity', default=0)
order_total += price * quantity
## Print order summary
print(f"\nOrder ID: {order_id}")
print(f"Customer: {customer_name}")
print(f"Contact: {customer_email} | {customer_phone}")
print(f"Shipping Address: {shipping_address}")
print(f"Payment Status: {payment_status}")
print(f"Order Total: ${order_total:.2f}")
print(f"Items: {len(items)}")
## Print item details
for j, item in enumerate(items):
item_dict = SafeDict(item)
name = item_dict.get('name', default='Unknown Product')
price = item_dict.get('price', default=0)
quantity = item_dict.get('quantity', default=0)
print(f" {j+1}. {name} (${price:.2f} × {quantity}) = ${price*quantity:.2f}")
- Speichern Sie die Datei und führen Sie sie aus:
python3 practical_example.py
Sie sollten eine Ausgabe sehen, die zeigt, wie Sie eine komplexe JSON-Datenstruktur sicher verarbeiten und fehlende oder unvollständige Daten auf elegante Weise behandeln können. Dies ist besonders wichtig, wenn Sie mit Daten aus externen Quellen arbeiten, deren Struktur möglicherweise nicht immer Ihren Erwartungen entspricht.
Das praktische Beispiel zeigt, wie man:
- Sicher durch verschachtelte JSON-Strukturen navigiert
- Fehlende Daten mit geeigneten Standardwerten behandelt
- Sammlungen von Objekten innerhalb des JSON verarbeitet
- Verschachtelte Informationen extrahiert und formatiert
Diese Techniken helfen Ihnen dabei, robustere Anwendungen zu erstellen, die reale JSON-Daten verarbeiten können, ohne aufgrund von KeyError-Ausnahmen abzustürzen.