Crawl

curl -X POST "https://api.factagora.com/api/v1/crawl" \
  -H "Authorization: Bearer fa_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://www.reuters.com/business/example-article"}'

{
  "url": "https://www.reuters.com/business/example-article",
  "title": "ECB raises rates by 25 basis points",
  "markdown": "The European Central Bank raised interest rates by 25 basis points on Thursday...",
  "publishedAt": "2026-06-15T08:00:00Z",
  "author": "Jane Editor",
  "description": "The ECB cited persistent core inflation in the eurozone.",
  "fetchedAt": "2026-06-15T09:12:04.221Z"
}

POST

api

crawl

curl -X POST "https://api.factagora.com/api/v1/crawl" \
  -H "Authorization: Bearer fa_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://www.reuters.com/business/example-article"}'

{
  "url": "https://www.reuters.com/business/example-article",
  "title": "ECB raises rates by 25 basis points",
  "markdown": "The European Central Bank raised interest rates by 25 basis points on Thursday...",
  "publishedAt": "2026-06-15T08:00:00Z",
  "author": "Jane Editor",
  "description": "The ECB cited persistent core inflation in the eurozone.",
  "fetchedAt": "2026-06-15T09:12:04.221Z"
}

Fetch a page and get the article body back as Markdown, with the boilerplate stripped out. Useful when you want to run your own processing over a page before sending anything to the other APIs. By default you also get the title, author, published date, and description. Pass a prompt to extract something specific instead.

Request Body

string

required

URL to crawl.

string

Custom extraction instruction. When provided, the response returns plain text matching your instruction and the metadata fields come back as null.

curl -X POST "https://api.factagora.com/api/v1/crawl" \
  -H "Authorization: Bearer fa_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://www.reuters.com/business/example-article"}'

Response

string

The URL that was crawled.

string

Page title. null when prompt was provided.

string

The extracted content. Markdown by default, or plain text matching your instruction when prompt was provided.

string

Published date in ISO 8601. null when prompt was provided, or when the page has no date.

string

Author. null when prompt was provided, or when the page has no author.

string

Page description. null when prompt was provided.

string

When the page was fetched, in ISO 8601.

{
  "url": "https://www.reuters.com/business/example-article",
  "title": "ECB raises rates by 25 basis points",
  "markdown": "The European Central Bank raised interest rates by 25 basis points on Thursday...",
  "publishedAt": "2026-06-15T08:00:00Z",
  "author": "Jane Editor",
  "description": "The ECB cited persistent core inflation in the eurozone.",
  "fetchedAt": "2026-06-15T09:12:04.221Z"
}

Extracting one section

Use prompt when you only want part of the page. The metadata fields come back null and markdown holds plain text.

curl -X POST "https://api.factagora.com/api/v1/crawl" \
  -H "Authorization: Bearer fa_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://example.com/pricing",
    "prompt": "Extract only the FAQ section."
  }'

Overview

Endpoints

Best Practices

Request Body

Response

Extracting one section

​Request Body

​Response

​Extracting one section

Request Body

Response

Extracting one section