# Crawl blog content and get LLM-ready Markdown

**Use case:** 

Crawl all blog posts on a website.  Get the content as Markdown ready-to-use for AI or RAG pipeline.

## Input

```json
{
  "startUrls": [
    {
      "url": "https://crawlee.dev/"
    }
  ],
  "crawlerType": "playwright:adaptive",
  "includeUrlGlobs": [
    {
      "glob": "https://crawlee.dev/blog/**"
    }
  ],
  "excludeUrlGlobs": [],
  "maxCrawlDepth": 4,
  "maxCrawlPages": 9999999,
  "useSitemaps": true,
  "useLlmsTxt": false,
  "respectRobotsTxtFile": false,
  "keepUrlFragments": false,
  "ignoreCanonicalUrl": false,
  "proxyConfiguration": {
    "useApifyProxy": true
  },
  "initialCookies": "***",
  "customHttpHeaders": {},
  "signHttpRequests": false,
  "initialConcurrency": 0,
  "maxConcurrency": 200,
  "requestTimeoutSecs": 60,
  "minFileDownloadSpeedKBps": 128,
  "maxRequestRetries": 3,
  "maxSessionRotations": 10,
  "ignoreHttpsErrors": false,
  "dynamicContentWaitSecs": 10,
  "waitForSelector": "",
  "softWaitForSelector": "",
  "maxScrollHeightPixels": 5000,
  "removeCookieWarnings": true,
  "blockMedia": true,
  "expandIframes": true,
  "clickElementsCssSelector": "[aria-expanded=\"false\"]",
  "pageFunction": "",
  "keepElementsCssSelector": "",
  "removeElementsCssSelector": "nav, footer, script, style, noscript, svg, img[src^='data:'],\n[role=\"alert\"],\n[role=\"banner\"],\n[role=\"dialog\"],\n[role=\"alertdialog\"],\n[role=\"region\"][aria-label*=\"skip\" i],\n[aria-modal=\"true\"]",
  "htmlTransformer": "readableText",
  "readableTextCharThreshold": 100,
  "aggressivePrune": false,
  "debugMode": false,
  "debugLog": false,
  "storeSkippedUrls": false,
  "saveHtml": false,
  "saveHtmlAsFile": false,
  "saveMarkdown": true,
  "saveFiles": false,
  "saveScreenshots": false,
  "maxResults": 9999999,
  "clientSideMinChangePercentage": 15,
  "renderingTypeDetectionPercentage": 10,
  "reuseStoredDetectionResults": false
}
```

## Output

```json
{
  "url": {
    "label": "URL",
    "format": "string"
  },
  "markdown": {
    "label": "Markdown",
    "format": "string"
  }
}
```

## About this Actor

This example demonstrates how to use [Website Content Crawler](https://apify.com/apify/website-content-crawler) with a specific input configuration. Visit the [Actor detail page](https://apify.com/apify/website-content-crawler) to learn more, explore other use cases, and run it yourself.