Python Example

This example demonstrates how to use the WebClassifAI API with Python using the requests library.

Installation


pip install requests

Basic Example


import requests
import json
 
def classify_urls(urls, api_key, taxonomy="iab-1.0"):
    """
    Classify a list of URLs using the WebClassifAI API.
 
    Args:
        urls (list): List of URLs to classify
        api_key (str): Your API key
        taxonomy (str): Classification taxonomy to use (default: "iab-1.0")
 
    Returns:
        dict: API response containing classification results
    """
    endpoint = "https://api.classifai.com/v1"
 
    payload = {
        "urls": urls,
        "api_key": api_key,
        "taxonomy": taxonomy
    }
 
    headers = {
        "Content-Type": "application/json"
    }
 
    try:
        response = requests.post(endpoint, json=payload, headers=headers)
        response.raise_for_status()  # Raise an exception for bad status codes
        return response.json()
    except requests.exceptions.RequestException as e:
        print(f"Error making request: {e}")
        return None
 
# Example usage
if __name__ == "__main__":
    # Your API key
    API_KEY = "your_api_key_here"
 
    # List of URLs to classify
    urls = [
        "https://www.example.com/",
        "https://www.tech-blog.com/"
    ]
 
    # Get classifications
    results = classify_urls(urls, API_KEY)
 
    if results:
        # Process results
        for result in results["results"]:
            url = result["url"]
            print(f"\nURL: {url}")
            print(f"Scraped successfully: {result['scraped_successfully']}")
 
            for prediction in result["predictions"]:
                print("\nPrediction:")
                if "tier1" in prediction:
                    tier1 = prediction["tier1"]
                    print(f"Tier 1: {tier1['name']} ({tier1['code']}) - Confidence: {tier1['confidence']:.2f}")
 
                if "tier2" in prediction:
                    tier2 = prediction["tier2"]
                    print(f"Tier 2: {tier2['name']} ({tier2['code']}) - Confidence: {tier2['confidence']:.2f}")

Error Handling

The example includes basic error handling for network issues and invalid responses. For production use, you might want to add:

Rate limiting
Retry logic
More detailed error handling
Logging

Batch Processing

For optimal performance, send multiple URLs in a single request:


# Process up to 500 URLs in a single request
urls = ["https://example.com"] * 500
results = classify_urls(urls, API_KEY)

Async Example

Important: We strongly recommend batching URLs in a single request (up to the 500 URL limit) for optimal performance. Only use async execution when your limits exceed 500 URLs or your architecture specifically requires it.


import aiohttp
import asyncio
 
async def classify_urls_async(urls, api_key, taxonomy="iab-1.0"):
    endpoint = "https://api.classifai.com/v1"
 
    payload = {
        "urls": urls,
        "api_key": api_key,
        "taxonomy": taxonomy
    }
 
    headers = {
        "Content-Type": "application/json"
    }
 
    async with aiohttp.ClientSession() as session:
        async with session.post(endpoint, json=payload, headers=headers) as response:
            return await response.json()
 
# Example usage
async def main():
    API_KEY = "your_api_key_here"
 
    # For best performance, process URLs in batches of up to 500
    # Only split into multiple async requests if absolutely necessary
    batch_size = 500
    all_urls = ["https://www.example.com/"] * 1000
 
    batches = [all_urls[i:i+batch_size] for i in range(0, len(all_urls), batch_size)]
    tasks = [classify_urls_async(batch, API_KEY) for batch in batches]
 
    results = await asyncio.gather(*tasks)
    for batch_result in results:
        print(f"Processed batch with {len(batch_result['results'])} URLs")
 
if __name__ == "__main__":
    asyncio.run(main())