{
  "data": {
    "id": "XqaBiFj9F6jDYAaVP",
    "userId": "HIMU0xktu1JeZb4Xl",
    "name": "website-content-crawler-lite",
    "username": "fetch_cat",
    "description": "Fast, reliable HTTP website crawler for clean text, Markdown, HTML, metadata, and links. Built for AI/RAG, SEO audits, monitoring, and automation with robots.txt, retries, proxy support, and bounded exports.",
    "isPublic": true,
    "createdAt": "2026-06-20T06:07:08.086Z",
    "modifiedAt": "2026-08-08T09:13:55.351Z",
    "taggedBuilds": {
      "latest": {
        "buildId": "TPNFxzkOXYlh8oVQa",
        "finishedAt": "2026-08-08T09:13:55.351Z",
        "buildNumberInt": 100014,
        "buildNumber": "0.1.14"
      }
    },
    "stats": {
      "totalBuilds": 14,
      "totalRuns": 191,
      "totalUsers": 4,
      "totalUsers7Days": 1,
      "totalUsers30Days": 3,
      "totalUsers90Days": 3,
      "lastRunStartedAt": "2026-08-26T14:10:34.469Z",
      "actorReviewCount": 0,
      "actorReviewRating": 0,
      "bookmarkCount": 0,
      "publicActorRunStats30Days": {
        "ABORTED": 0,
        "FAILED": 3,
        "SUCCEEDED": 35,
        "TIMED-OUT": 0,
        "TOTAL": 38
      }
    },
    "versions": [
      {
        "versionNumber": "0.1",
        "sourceType": "SOURCE_FILES",
        "buildTag": "latest"
      }
    ],
    "defaultRunOptions": {
      "build": "latest",
      "timeoutSecs": 300,
      "memoryMbytes": 512
    },
    "exampleRunInput": {
      "body": "{\"startUrls\":[{\"url\":\"https://docs.apify.com/academy\"}],\"maxPages\":5,\"maxDepth\":1,\"sameDomainOnly\":true,\"includeGlobs\":[\"https://docs.apify.com/**\"],\"excludeGlobs\":[\"**/login**\",\"**/signup**\"],\"outputFormat\":\"markdown\",\"respectRobotsTxt\":true,\"requestTimeoutSecs\":20}",
      "contentType": "application/json"
    },
    "categories": [
      "AI",
      "SEO_TOOLS",
      "DEVELOPER_TOOLS"
    ],
    "isDeprecated": false,
    "title": "Website Content Crawler Lite",
    "pictureUrl": "https://apify-image-uploads-prod.s3.us-east-1.amazonaws.com/HIMU0xktu1JeZb4Xl-actor-XqaBiFj9F6jDYAaVP-lejYR3RJQv-website-content-crawler-lite-actor-icon.png",
    "seoTitle": "Fast Website Content Crawler for Markdown, AI and SEO",
    "seoDescription": "Crawl public websites into clean Markdown, text or HTML for RAG, AI agents, SEO audits and monitoring, with retries, robots.txt and optional proxies.",
    "pricingInfos": [
      {
        "pricingModel": "PAY_PER_EVENT",
        "createdAt": "2026-06-20T06:09:17.151Z",
        "startedAt": "2026-06-20T06:09:17.081Z",
        "apifyMarginPercentage": 0.2,
        "pricingPerEvent": {
          "actorChargeEvents": {
            "start": {
              "eventTitle": "Start",
              "eventDescription": "One-time fee per run",
              "eventPriceUsd": 0.005,
              "isOneTimeEvent": true
            },
            "page": {
              "eventTitle": "Page extracted",
              "eventDescription": "Charged for each successfully extracted HTML page. Skipped and blocked pages are not charged.",
              "eventTieredPricingUsd": {
                "FREE": {
                  "tieredEventPriceUsd": 0.000575
                },
                "BRONZE": {
                  "tieredEventPriceUsd": 0.0005
                },
                "SILVER": {
                  "tieredEventPriceUsd": 0.00039
                },
                "GOLD": {
                  "tieredEventPriceUsd": 0.0003
                },
                "PLATINUM": {
                  "tieredEventPriceUsd": 0.0002
                },
                "DIAMOND": {
                  "tieredEventPriceUsd": 0.00014
                }
              },
              "isPrimaryEvent": true
            }
          }
        }
      },
      {
        "pricingModel": "PAY_PER_EVENT",
        "startedAt": "2026-06-20T06:18:27.687Z",
        "pricingPerEvent": {
          "actorChargeEvents": {
            "start": {
              "eventTitle": "Run started",
              "eventDescription": "One-time fee charged when a run starts. Covers fixed startup cost (init, proxy warmup, first HTTP setup).",
              "eventPriceUsd": 0.005,
              "isOneTimeEvent": true
            },
            "page": {
              "eventTitle": "Page extracted",
              "eventDescription": "Charged per page extracted.",
              "eventTieredPricingUsd": {
                "FREE": {
                  "tieredEventPriceUsd": 0.00019876
                },
                "BRONZE": {
                  "tieredEventPriceUsd": 0.00017284
                },
                "SILVER": {
                  "tieredEventPriceUsd": 0.00013481
                },
                "GOLD": {
                  "tieredEventPriceUsd": 0.0001037
                },
                "PLATINUM": {
                  "tieredEventPriceUsd": 0.000069135
                },
                "DIAMOND": {
                  "tieredEventPriceUsd": 0.000048395
                }
              },
              "isPrimaryEvent": true
            }
          }
        },
        "createdAt": "2026-06-20T06:18:27.760Z",
        "apifyMarginPercentage": 0.2
      }
    ],
    "notice": "NONE",
    "isCritical": false,
    "isGeneric": false,
    "hasNoDataset": false,
    "isSourceCodeHidden": true,
    "standbyUrl": null,
    "actorPermissionLevel": "LIMITED_PERMISSIONS",
    "readmeSummary": "## Website Content Crawler Lite\n\nA lightweight HTTP website crawler and content extractor that quickly fetches public HTML pages, follows in-scope links, and exports cleaned page content (plain text, Markdown, or cleaned HTML) plus page metadata and discovered links. Technical capabilities include bounded concurrency, configurable crawl depth and page limits, robots.txt awareness, optional proxy support with validation and session identifiers, automatic retries for transient errors and rate limits, memory- and size-safety caps (response size, exported content, links per page), and a machine-readable run summary with diagnostic error/skip records and checkpointed pending work. The Actor extracts readable page text and converts content to Markdown or HTML, captures page metadata (title, meta description, first H1), records HTTP status and content type, discovers absolute links and parent relationships, and provides timestamps and failure/skipped diagnostics useful for downstream AI ingestion, SEO, monitoring, research, and automation workflows.\n\n## Use cases\n\n- Export website pages to Markdown or text for AI/RAG ingestion and embedding pipelines.  \n- Perform SEO audits by collecting titles, meta descriptions, H1s, status codes, and internal link data.  \n- Content monitoring and scheduled runs to detect page text or metadata changes.  \n- Documentation indexing by crawling docs sites and saving cleaned Markdown.  \n- Research and lead-generation pipelines that require cleaned website text for extraction or classification.  \n- Lightweight website-to-Markdown exports and content archiving for automation workflows.",
    "deploymentKey": "ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABAQDVo+uh6cYbP40QCZ6BwhHNFNCXNmKU5MsfJY5pvrZo7/TnmPbHpr4CWUaD6pqHRGO0++HlG6VtjLT4f/fSQlAHxN1YyBicR6Yf1APFTT+yeLkGK9YeeqctdSrkSTBM+RBm3UPH6bIZNIfrCycx9Bjfff29DvYuUSk2mu1eccIS3MB9adeBe11pKCksQ1dYmIRF/hsHN8DflefTYIz52M6D91c3Nhq1UAO2Gh1Cxo+iAZTmG4375eeoBB+gm3Od1lYQ04AFbOJ6c+RwuplAuiI6rnnCTsndBsYemkWIGY2Kz4ggPRD3tyGzYJiTEi0vqNpY2/JEPYoZA1JzGz233rcd \n"
  }
}