Can it extract pages behind a login?

No. The extractor fetches public pages only.

How many pages can a crawl cover?

Up to 200 pages and 5 levels deep, with scope rules to stay within a section of the site.

Pro and API plans

Web Extractor

Turn a public web page, a batch of URLs or a whole section of a site into clean, citable text your AI can use.

Extract a web page See pricing and plans

Published 24 September 2026 · Reviewed 24 September 2026

Who it is for

Researchers and analysts
Marketers
Developers building datasets
Journalists

The problem

Saving a web page keeps the navigation, the cookie banner and the ads, and loses the article. JavaScript-rendered pages save as nothing at all.

How GistCite solves it

Fetch a page, or render it in a real browser when it needs JavaScript, and get the main content as Markdown, text, HTML or JSON. Define fields with CSS selectors for structured output, batch up to 25 URLs, or crawl a site with scope and depth limits into one download.

Capabilities

Clean Markdown from any page

Main content only, with headings and links kept.

Benefit: Cite the page, not the chrome.

Extract a web page to Markdown

Browser rendering

A Playwright sidecar renders pages that need JavaScript, scrolls for lazy content and can click a load-more control.

Benefit: Modern sites extract like static ones.

Extract a JavaScript-rendered page

Structured fields

Describe fields with CSS selectors and get JSON objects back.

Benefit: A product list becomes a table.

Extract structured fields with selectors

Batches and crawls

25 URLs per batch; crawls up to 200 pages and 5 levels deep with scope rules.

Benefit: A documentation site becomes one corpus.

Crawl a site into one download

Benefits

Every page lands in your history for summary, Ask and Create.
Public pages only; the extractor respects the limits documented in the spec.

How it works

Step 1
Paste a URL
Or a list, or a start page for a crawl.
Step 2
Extract
Plain fetch, or browser rendering when needed; optional selectors.
Step 3
Download
Markdown, text, HTML, JSON, or a ZIP for batches and crawls.

Integrations and formats

Playwright browser rendering
REST API
JSON / Markdown / HTML export
AI Summary, Ask and Create

Security and data handling

Read the full picture on the security and compliance page.

Only public pages are fetched; no credentials are stored or used.
Uploads are processed in memory and never written to disk or object storage; only the extracted text is kept.
Every extraction endpoint is rate-limited per IP; signed-in use is metered against the plan's monthly quota.
TLS in transit; passwords bcrypt-hashed; API keys stored only as SHA-256 digests.

Evidence

Browser rendering runs in a separate Playwright sidecar (decision record 0009). Check this

Pricing

Plans: Pro and API
Cost per action: 1 unit per page extracted, including each batch item and crawled page.
How it is priced: Included in Pro and API plans.

Compare the Free, Pro and API plans

Web Extractor questions

Can it extract pages behind a login?: No. The extractor fetches public pages only.
How many pages can a crawl cover?: Up to 200 pages and 5 levels deep, with scope rules to stay within a section of the site.

Try Web Extractor now

Extract a web page

Prefer to talk first? Contact the team · Read the API documentation