Skip to main content
Before you begin!
Visit the Wetrocloud console to get your API key. If you have trouble obtaining it, refer to this guide.

​
Introduction

This quickstart guide will show you how to extract structured data from any website using the Wetrocloud API. In just a few minutes, you’ll be able to:
  • Extract data from any URL
  • Define your own JSON schema for structured output
  • Use AI-powered prompts to specify what data to extract
Prerequisites:

​
Your First Data Extraction

Let’s extract billionaire names and net worth from a news article.
1

Make Your First Request

Extract structured data from a website by providing a link, prompt, and JSON schema.
import requests
import json

url = "https://api.wetrocloud.com/v1/extract/"

headers = {
    "Content-Type": "application/json",
    "Authorization": "Token <api_key>"
}

payload = {
    "link": "https://theweek.com/news/people/954994/billionaires-richest-person-in-the-world",
    "prompt": "Extract the names and networth of Billionares in the article",
    "json_schema": [
        {"name": "string"},
        {"networth": "number"}
    ],
    "delay": 2
}

response = requests.post(url, headers=headers, data=json.dumps(payload))
print(response.json())
2

Understanding the Response

The API returns a structured JSON response matching your schema:
{
  "response": [
    {
      "name": "Elon Musk",
      "networth": "$462 billion"
    },
    {
      "name": "Larry Ellison",
      "networth": "$340 billion"
    },
    {
      "name": "Mark Zuckerberg",
      "networth": "$258 billion"
    },
    {
      "name": "Jeff Bezos",
      "networth": "$244 billion"
    },
    {
      "name": "Larry Page",
      "networth": "$221 billion"
    },
    {
      "name": "Sergey Brin",
      "networth": "$207 billion"
    },
    {
      "name": "Bernard Arnault",
      "networth": "$197 billion"
    },
    {
      "name": "Steve Ballmer",
      "networth": "$179 billion"
    },
    {
      "name": "Jensen Huang",
      "networth": "$158 billion"
    },
    {
      "name": "Michael Dell",
      "networth": "$156 billion"
    }
  ],
  "success": true
}
FieldDescription
responseArray of extracted data matching your JSON schema
successBoolean indicating if the extraction was successful
3

Try Different Schemas or Plain Text

You can customize the JSON schema to extract different types of data, or omit it entirely for plain text responses.
Pro tip: The json_schema parameter is optional. Omit it to get a plain text response instead of structured JSON.
Here are some examples:Extract product information:
import requests
import json

url = "https://api.wetrocloud.com/v1/extract/"

headers = {
    "Content-Type": "application/json",
    "Authorization": "Token <api_key>"
}

payload = {
    "link": "https://example.com/products",
    "prompt": "Extract all product details",
    "json_schema": [
        {"product_name": "string"},
        {"price": "number"},
        {"rating": "number"}
    ]
}

response = requests.post(url, headers=headers, data=json.dumps(payload))
print(response.json())
Extract contact information:
import requests
import json

url = "https://api.wetrocloud.com/v1/extract/"

headers = {
    "Content-Type": "application/json",
    "Authorization": "Token <api_key>"
}

payload = {
    "link": "https://example.com/contact",
    "prompt": "Extract contact details",
    "json_schema": [
        {"name": "string"},
        {"email": "string"},
        {"phone": "string"}
    ]
}

response = requests.post(url, headers=headers, data=json.dumps(payload))
print(response.json())
Get plain text response (without json_schema):
import requests
import json

url = "https://api.wetrocloud.com/v1/extract/"

headers = {
    "Content-Type": "application/json",
    "Authorization": "Token <api_key>"
}

payload = {
    "link": "https://theweek.com/news/people/954994/billionaires-richest-person-in-the-world",
    "prompt": "Extract the names and networth of Billionares in the article"
}

response = requests.post(url, headers=headers, data=json.dumps(payload))
print(response.json())
Response:
{
  "response": "Here are the names and net worths of the billionaires...\n\n1. **Elon Musk:** $462 billion\n2. **Larry Ellison:** $340 billion...",
  "success": true
}

​
Next Steps

Great! You’ve successfully extracted structured data from a website. Now you can:
  • Learn more about the Data Extraction API and all available parameters
  • Explore the complete API Reference
  • Check out advanced features like custom delays and complex schemas
Need help? Email us at [email protected]