URL to Markdown API - Web Pages to Clean Text for LLMs

{
  "url": "https://www.nasa.gov/humans-in-space/",
  "finalUrl": "https://www.nasa.gov/humans-in-space/",
  "statusCode": 200,
  "contentType": "text/html",
  "title": "Humans In Space - NASA",
  "description": "In this original series, NASA astronauts take viewers on a journey to the International Space Station, exploring the life-changing experience of an orbital perspective.",
  "language": "en-US",
  "canonical": "https://www.nasa.gov/humans-in-space/",
  "author": "Dacia Massengill",
  "publishedAt": "2022-12-02T21:06:45.000Z",
  "modifiedAt": "2026-10-05T15:20:09.000Z",
  "siteName": "NASA",
  "mainImage": "https://www.nasa.gov/wp-content/uploads/2022/12/iss072e595426orig.jpg",
  "wordCount": 302,
  "tokenEstimate": 893,
  "markdown": "# Humans In Space - NASA\n\nBuilding on 60 years of exploration experience and more than two decades of continuous human presence on the International Space Station, NASA will expand humanity’s reach deeper into space than ever before.\n\n### NASA+ Series\n\n## Down to Earth\n\nIn this original series, N…",
  "text": "Building on 60 years of exploration experience and more than two decades of continuous human presence on the International Space Station, NASA will expand humanity’s reach deeper into space than ever before.\n\nNASA+ Series\n\nDown to Earth\n\nIn this original series, NASA astronauts take viewers on a…",
  "headings": [
    {
      "level": 1,
      "text": "Humans In Space - NASA"
    },
    {
      "level": 3,
      "text": "NASA+ Series"
    },
    {
      "level": 2,
      "text": "Down to Earth"
    },
    {
      "level": 2,
      "text": "Artemis II Lunar Flyby"
    },
    {
      "level": 3,
      "text": "Humans in Space"
    },
    {
      "level": 2,
      "text": "Human Spaceflight"
    }
  ],
  "links": [
    {
      "url": "https://www.nasa.gov/",
      "text": "",
      "internal": true
    },
    {
      "url": "https://www.nasa.gov/news/",
      "text": "News & Events",
      "internal": true
    },
    {
      "url": "https://www.nasa.gov/2026-news-releases/",
      "text": "News Releases",
      "internal": true
    }
  ],
  "images": [
    {
      "src": "https://images-assets.nasa.gov/image/iss075e0070083/iss075e0070083~large.jpg?w=1920&h=1280&fit=clip&crop=faces%2Cfocalpoint",
      "alt": "NASA astronaut and Expedition 75 flight engineer Anil Menon is attached to the Canadarm2 robotic arm’s latching end effector during a spacewalk to install a high-speed space-to-ground antenna on the International Space Station’s Z1 truss segment above the Unity module. Menon and ESA (European Space Agency) astronaut and Expedition 75 flight engineer Sophie Adenot (out of frame) spent six hours and 30 minutes replacing a failed antenna with a spare and making the precise connections needed to activate it for high-speed transmissions with mission control."
    },
    {
      "src": "https://images-assets.nasa.gov/image/jsc2026e391565/jsc2026e391565~large.jpg?w=1920&h=1280&fit=clip&crop=faces%2Cfocalpoint",
      "alt": "Four astronauts are pictured in orange Orion Crew Survival System suits. The astronauts on the far left and far right of the image are standing, holding their helmets. In between them, are the other two astronauts, who are seated and holding their gloves."
    }
  ],
  "contentHash": "sha256:b084d35db91f86024ac4f634e5a7f917c794a7d59ba24d873f6b69d6692dd797",
  "scrapedAt": "2026-11-07T07:01:38.852Z"
}

curl -s -X POST "https://api.apify.com/v2/acts/rocketyard~web-page-to-markdown/run-sync-get-dataset-items" \
  -H "Authorization: Bearer $APIFY_TOKEN" \
  -H 'content-type: application/json' \
  -d '{"startUrls":[{"url":"https://en.wikipedia.org/wiki/Web_scraping"}],"outputFormats":["markdown"],"maxItems":10}'

import { ApifyClient } from 'apify-client';
const client = new ApifyClient({ token: process.env.APIFY_TOKEN });
const run = await client.actor('rocketyard/web-page-to-markdown').call({"startUrls":[{"url":"https://en.wikipedia.org/wiki/Web_scraping"}],"outputFormats":["markdown"],"maxItems":10});
const { items } = await client.dataset(run.defaultDatasetId).listItems();

from apify_client import ApifyClient
client = ApifyClient("<APIFY_TOKEN>")
run = client.actor("rocketyard/web-page-to-markdown").call(run_input={"startUrls":[{"url":"https://en.wikipedia.org/wiki/Web_scraping"}],"outputFormats":["markdown"],"maxItems":10})
items = client.dataset(run["defaultDatasetId"]).list_items().items

https://mcp.apify.com?tools=rocketyard/web-page-to-markdown

claude mcp add --transport http apify "https://mcp.apify.com?tools=rocketyard/web-page-to-markdown"

{
  "mcpServers": {
    "apify": { "url": "https://mcp.apify.com?tools=rocketyard/web-page-to-markdown" }
  }
}

{
  "startUrls": [
    {
      "url": "https://en.wikipedia.org/wiki/Web_scraping"
    }
  ],
  "outputFormats": [
    "markdown"
  ],
  "maxItems": 10
}

{
  "name": "URL to Markdown API daily",
  "nodes": [
    {
      "parameters": {
        "rule": {
          "interval": [
            {
              "field": "days",
              "daysInterval": 1,
              "triggerAtHour": 7
            }
          ]
        }
      },
      "id": "c1f6a2d0-4a57-4b5e-9d7a-0a1b2c3d4e01",
      "name": "Every day at 07:00",
      "type": "n8n-nodes-base.scheduleTrigger",
      "typeVersion": 1.2,
      "position": [
        0,
        0
      ]
    },
    {
      "parameters": {
        "method": "POST",
        "url": "https://api.apify.com/v2/acts/rocketyard~web-page-to-markdown/run-sync-get-dataset-items",
        "authentication": "genericCredentialType",
        "genericAuthType": "httpBearerAuth",
        "sendBody": true,
        "specifyBody": "json",
        "jsonBody": "{\n  \"startUrls\": [\n    {\n      \"url\": \"https://en.wikipedia.org/wiki/Web_scraping\"\n    }\n  ],\n  \"outputFormats\": [\n    \"markdown\"\n  ],\n  \"maxItems\": 10\n}",
        "options": {
          "timeout": 300000
        }
      },
      "id": "c1f6a2d0-4a57-4b5e-9d7a-0a1b2c3d4e02",
      "name": "Run URL to Markdown API",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        260,
        0
      ],
      "credentials": {
        "httpBearerAuth": {
          "name": "Apify API token"
        }
      }
    }
  ],
  "connections": {
    "Every day at 07:00": {
      "main": [
        [
          {
            "node": "Run URL to Markdown API",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "settings": {}
}

curl -X POST "https://api.apify.com/v2/acts/rocketyard~web-page-to-markdown/run-sync-get-dataset-items" -H "Authorization: Bearer $APIFY_TOKEN" -H "Content-Type: application/json" -d '{"startUrls":[{"url":"https://en.wikipedia.org/wiki/Web_scraping"}],"outputFormats":["markdown"],"maxItems":10}'