{
  "data": {
    "id": "XqaBiFj9F6jDYAaVP",
    "userId": "HIMU0xktu1JeZb4Xl",
    "name": "website-content-crawler-lite",
    "username": "fetch_cat",
    "description": "Crawl public website pages and extract clean text, Markdown, metadata, and links for AI, SEO, and monitoring workflows.",
    "isPublic": true,
    "createdAt": "2026-06-20T06:07:08.086Z",
    "modifiedAt": "2026-07-09T11:09:29.331Z",
    "taggedBuilds": {
      "latest": {
        "buildId": "dwGxFaRSH7efPVUzL",
        "finishedAt": "2026-07-09T11:09:29.331Z",
        "buildNumberInt": 100009,
        "buildNumber": "0.1.9"
      }
    },
    "stats": {
      "totalBuilds": 9,
      "totalRuns": 36,
      "totalUsers": 2,
      "totalUsers7Days": 1,
      "totalUsers30Days": 1,
      "totalUsers90Days": 1,
      "lastRunStartedAt": "2026-07-09T12:12:34.913Z",
      "actorReviewCount": 0,
      "actorReviewRating": 0,
      "bookmarkCount": 0,
      "publicActorRunStats30Days": {
        "ABORTED": 0,
        "FAILED": 0,
        "SUCCEEDED": 18,
        "TIMED-OUT": 0,
        "TOTAL": 18
      }
    },
    "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": "Website Content Crawler Lite for AI and SEO",
    "seoDescription": "Crawl public websites into clean text, Markdown, HTML, metadata, and links for AI, RAG, SEO audits, content monitoring, and automation workflows.",
    "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\nWebsite Content Crawler Lite is a lightweight public website crawler that starts from one or more seed URLs and produces structured page records for AI, RAG, SEO, research, monitoring, and documentation workflows. It follows links within a configurable scope with domain scoping by default, supports depth limits and include/exclude URL patterns, and can optionally honor robots rules. The Actor extracts cleaned plain text, converts pages to Markdown, or returns cleaned HTML, and collects page metadata such as title, meta description, first H1, discovered links, HTTP status and content type, crawl depth and parent-link relationships, timestamps, and skip/error reasons for filtered or failed pages. Outputs are optimized for content pipelines, metadata audits, link-mapping, and downstream indexing or analysis.\n\n## Use cases\n\n- Build a RAG content feed by crawling documentation or public content and exporting Markdown for embedding/indexing workflows.  \n- Audit SEO metadata by crawling sections to review titles, meta descriptions, H1 tags, internal links, and status codes.  \n- Monitor public website copy by running recurring crawls and comparing cleaned page text snapshots over time.  \n- Extract documentation pages from a specific folder or section using URL include patterns.  \n- Collect link maps and site structure using discovered links, crawl depth, and parent-link relationships.",
    "deploymentKey": "ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABAQDVo+uh6cYbP40QCZ6BwhHNFNCXNmKU5MsfJY5pvrZo7/TnmPbHpr4CWUaD6pqHRGO0++HlG6VtjLT4f/fSQlAHxN1YyBicR6Yf1APFTT+yeLkGK9YeeqctdSrkSTBM+RBm3UPH6bIZNIfrCycx9Bjfff29DvYuUSk2mu1eccIS3MB9adeBe11pKCksQ1dYmIRF/hsHN8DflefTYIz52M6D91c3Nhq1UAO2Gh1Cxo+iAZTmG4375eeoBB+gm3Od1lYQ04AFbOJ6c+RwuplAuiI6rnnCTsndBsYemkWIGY2Kz4ggPRD3tyGzYJiTEi0vqNpY2/JEPYoZA1JzGz233rcd \n"
  }
}