LLM Web Scraper

LLM Web Scraper API Documentation

Introduction

The LLM Web Scraper API combines web scraping with Large Language Model processing to extract specific information from web pages using natural language prompts. This version provides structured, intelligent data extraction.

Authentication

All API requests require authentication using an API key. Include your key in the x-api-key header:

x-api-key: YOUR_API_KEY_HERE

Base URL

https://api.yetanotherapi.com/v1/llm-web-scrapper

Pricing

Each API call costs 1 credit.

Endpoint Details

LLM-Enhanced Web Scraping

Extract structured information from a webpage using natural language prompts.

HTTP Method: POST Endpoint: /

Request Headers

Header	Value	Description
x-api-key	YOUR_API_KEY_HERE	Your unique API authentication key
Content-Type	application/json	Specify JSON request body

Request Body Parameters

Parameter	Type	Required	Description
url	string	Yes	URL of the web page to scrape
prompt	string	Yes	Natural language prompt describing what to extract
use_llm	boolean	Yes	Must be set to true for LLM processing
webhook	string	No	Optional webhook URL for receiving response

Example Request

curl --location 'https://api.yetanotherapi.com/v1/llm-web-scrapper' \
--header 'x-api-key: $API_KEY_HERE' \
--header 'Content-Type: application/json' \
--data '{
    "url": "https://www.amazon.in/AMVR-Controller-Compatible-Accessories-Adjustable/dp/B0CJRK7B8J",
    "prompt": "Extract the product name, price, rating, and top 3 features",
    "use_llm": true,
    "webhook": "https://your-webhook.com/endpoint"
}'

Response Structure

{
    "request_id": "c03995eb-e117-4eca-85c8-e6d398a968d9",
    "llm_json_structure": {
        "product_name": "AMVR VR Controller Grip Cover",
        "price": 1499.00,
        "rating": 4.5,
        "top_features": [
            "Anti-slip surface",
            "Adjustable fit",
            "Compatible with Meta Quest 2"
        ]
    }
}

Prompt Guidelines

• Be specific about what information you want to extract

• Specify the desired format for numerical data

• Mention if you want specific sorting or filtering

• Include any required unit conversions

Example prompts:

• "Extract product specifications in a structured format"

• "Find all prices and convert them to USD"

• "List main article headings and their first paragraphs"

Error Handling

{
    "error": "Invalid prompt format",
    "status_code": 400
}

Common Error Codes:

• 400: Bad Request (invalid parameters)

• 401: Unauthorized (invalid API key)

• 422: Unprocessable Content (LLM processing failed)

• 429: Too Many Requests

Limitations

• Maximum processing time: 20 seconds

• Complex prompts may require status checking

• Some websites may block automated access

• LLM processing may not be 100% accurate

Support

For technical support or to report issues, contact: [email protected]