Getting Started with sieve

1. Create your free account

Sign up at scrape.usesieve.com with Google or an email + password (you'll verify your email at first login).

The free plan includes 100 credits per month — enough to try real extractions before you ever talk to us. Paid plans start at $25/month.

2. Create an API key

In the app, open Settings → API keys and click Generate key. The key (it starts with dc_sk_) is shown once — copy it somewhere safe. Send it on every request:

import requests

BASE_URL = "https://scrape.usesieve.com"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
}

3. Start your first scrape

Describe what you want and (optionally) which pages to visit. The request returns immediately with a session id:

start = requests.post(f"{BASE_URL}/api/scrapes", headers=headers, json={
    "instruction": "Extract store name, address, phone, and hours",
    "target_urls": ["https://example.com/stores"],
})
start.raise_for_status()
session_id = start.json()["session_id"]

4. Poll for results

Poll the session until status is "done", then read the summary and download the output files:

import time

while True:
    result = requests.get(f"{BASE_URL}/api/scrapes/{session_id}", headers=headers).json()
    if result["status"] == "done":
        break
    time.sleep(5)

print(result["summary"])
for f in result["files"]:  # each: { name, size, ext, url }
    print(f["name"], BASE_URL + f["url"])