One page, or every page.

cloud.ts

const cloud = new CloudApi({ apiKey: process.env.WRIT_API_KEY }); // wt_…
const page = await cloud.scrape("https://example.com");
const site = await cloud.map("https://example.com", { search: "pricing", limit: 20 });
console.log(cloud.tier); // "metered" | "keyless"

cloud.py

cloud = Cloud(api_key=os.environ["WRIT_API_KEY"])  # wt_… — no daemon needed
page = cloud.scrape("https://example.com")
site = cloud.map("https://example.com", search="pricing", limit=20)
print(cloud.tier)  # "metered" | "keyless"

metered.sh

# Metered — wt_ API key, billed from your credit pool
curl -X POST https://api.usewrit.app/api/crawl/scrape \
  -H "Authorization: Bearer $WRIT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com"}'

keyless.sh

# Keyless — no account, no key: a stable device id is the only identity.
# 429 keyless_rate_limited when the allowance is spent.
curl -X POST https://api.usewrit.app/v1/keyless/scrape \
  -H "X-Writ-Client-Id: $WRIT_CLIENT_ID" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://example.com"}'
curl https://api.usewrit.app/v1/keyless/quota -H "X-Writ-Client-Id: $WRIT_CLIENT_ID"

crawl.ts

const job = await client.crawl.start({
  url: "https://example.com",
  max_depth: 3,
  page_budget: 500,
});
const status = await client.crawl.get(job.id);
const table = await client.data.workflowData(job.data_workflow_id);

crawl.py

job = client.crawl.start("https://example.com", max_depth=3, page_budget=500)
job = client.crawl.get(job["id"])
table = client.data.workflow_data(job["data_workflow_id"])

crawl.go

job, _ := client.Crawl.Start(ctx, writ.CrawlStartParams{URL: "https://example.com"})
st, _ := client.Crawl.Get(ctx, job.ID)

crawl.rs

use writ_client::CrawlStartParams;

let job = agent.crawl().start(CrawlStartParams {
    url: "https://example.com".into(),
    ..Default::default()
}).await?;
let job = agent.crawl().get(job.id).await?;

save-and-run.sh

# 1. Save the crawl — name + slug + the config it should always run.
curl -X POST https://api.usewrit.app/api/crawl/definitions \
  -H "Authorization: Bearer $WRIT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Docs index",
    "slug": "docs-index",
    "default_max_age_seconds": 86400,
    "config": {
      "url": "https://example.com/docs",
      "include_paths": ["^/docs/"],
      "max_depth": 3,
      "page_budget": 500
    }
  }'

# 2. Call it. Fresh enough? You get the data. Stale? It re-crawls.
curl -X POST https://api.usewrit.app/api/crawl/definitions/docs-index/run \
  -H "Authorization: Bearer $WRIT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"max_age": 86400, "wait": true, "timeout": 120, "limit": 50}'

200 — the window held

{
  "cached": true,
  "_cache": { "hit": true, "age_seconds": 3512, "source_crawl_id": 8811 },
  "definition": { "name": "Docs index", "slug": "docs-index" },
  "crawl": { "id": 8811, "status": "completed", "pages_done": 412 },
  "status_url": "/api/crawl/8811",
  "data": [ { "url": "https://example.com/docs/intro", "title": "Intro" } ]
}

// A miss answers 202 with the new crawl and its status_url instead.
// wait:true that overruns answers 504 — still carrying crawl_id and
// status_url, so the pages already paid for stay collectable.

read-only.sh

# What the last completed run collected — any age, never crawls, never bills.
curl "https://api.usewrit.app/api/crawl/definitions/docs-index/data?limit=50" \
  -H "Authorization: Bearer $WRIT_API_KEY"

# Force a fresh pass, whatever the definition's default window says.
curl -X POST https://api.usewrit.app/api/crawl/definitions/docs-index/run \
  -H "Authorization: Bearer $WRIT_API_KEY" \
  -H "Cache-Control: no-cache"

usage.sh

curl https://api.usewrit.app/api/crawl/meta/usage \
  -H "Authorization: Bearer $WRIT_API_KEY"

200

{
  "pages_included_per_month": 75000,
  "pages_used_this_period": 12480,
  "pages_remaining": 62520,
  "per_job_page_cap": 25000,
  "max_concurrent_crawls": 3,
  "overage_price_micros_per_page": 500,
  "browser_page_units": 2,
  "ocr_page_units": 2
}

// -1 anywhere in this body means unlimited.

crawl tools

// Crawl a site and save it under a callable name in one turn.
writ_crawl_site {
  "url": "https://example.com/docs",
  "extract": "markdown",
  "max_pages": 500,
  "max_depth": 3,
  "include": ["^/docs/"],
  "exclude": ["^/docs/legacy/"],
  "same_domain": true,
  "allow_subdomains": false,
  "content": { "preset": "article", "exclude_selectors": ["nav", "footer"] },
  "save_as": "docs-index"
}

// Re-using a save_as name UPDATES that saved crawl — it does not duplicate it.
// max_age only matters together with save_as.
writ_run_saved_crawl { "crawl": "docs-index", "max_age": 86400, "limit": 50 }
writ_saved_crawl_data { "crawl": "docs-index" }
writ_saved_crawls {}
writ_crawl_status { "crawl_id": 8811 }
writ_map  { "url": "https://example.com" }
writ_scrape { "url": "https://example.com/pricing" }