{
  "data": {
    "id": "kwHS2PKHK4gyKjVZ8",
    "userId": "HIMU0xktu1JeZb4Xl",
    "name": "hugging-face-datasets-scraper",
    "username": "fetch_cat",
    "description": "Scrape public Hugging Face dataset metadata, tags, access flags, downloads, likes, and recency signals.",
    "isPublic": true,
    "createdAt": "2026-07-17T08:38:27.535Z",
    "modifiedAt": "2026-09-25T19:19:23.394Z",
    "taggedBuilds": {
      "latest": {
        "buildId": "XLpfdeXHHuU9nHADq",
        "finishedAt": "2026-09-25T19:19:23.110Z",
        "buildNumberInt": 100005,
        "buildNumber": "0.1.5"
      },
      "input-ux-20260925": {
        "buildId": "XLpfdeXHHuU9nHADq",
        "finishedAt": "2026-09-25T19:19:23.110Z",
        "buildNumberInt": 100005,
        "buildNumber": "0.1.5"
      }
    },
    "stats": {
      "totalBuilds": 5,
      "totalRuns": 110,
      "totalUsers": 3,
      "totalUsers7Days": 2,
      "totalUsers30Days": 2,
      "totalUsers90Days": 2,
      "lastRunStartedAt": "2026-10-14T10:56:43.446Z",
      "actorReviewCount": 0,
      "actorReviewRating": 0,
      "bookmarkCount": 0,
      "publicActorRunStats30Days": {
        "ABORTED": 0,
        "FAILED": 0,
        "SUCCEEDED": 26,
        "TIMED-OUT": 0,
        "TOTAL": 26
      }
    },
    "versions": [
      {
        "versionNumber": "0.1",
        "sourceType": "SOURCE_FILES",
        "buildTag": "latest"
      }
    ],
    "defaultRunOptions": {
      "build": "latest",
      "timeoutSecs": 300,
      "memoryMbytes": 512
    },
    "exampleRunInput": {
      "body": "{\n  \"searchQueries\": [\"finance\"],\n  \"maxItems\": 10,\n  \"sort\": \"downloads\",\n  \"dedupe\": true\n}",
      "contentType": "application/json; charset=utf-8"
    },
    "categories": [
      "AI",
      "DEVELOPER_TOOLS",
      "AUTOMATION"
    ],
    "isDeprecated": false,
    "title": "Hugging Face Datasets Scraper",
    "pictureUrl": "https://apify-image-uploads-prod.s3.us-east-1.amazonaws.com/HIMU0xktu1JeZb4Xl-actor-kwHS2PKHK4gyKjVZ8-jlxFZJjBUm-actor-icon.png",
    "seoTitle": "Hugging Face Datasets Scraper - CSV, JSON, API",
    "seoDescription": "Export public Hugging Face dataset metadata, tags, licenses, downloads, likes, access flags, and recency signals to CSV, JSON, Excel, or API fast.",
    "pricingInfos": [
      {
        "pricingModel": "PAY_PER_EVENT",
        "startedAt": "2026-07-17T08:42:13.681Z",
        "pricingPerEvent": {
          "actorChargeEvents": {
            "start": {
              "eventTitle": "Start",
              "eventDescription": "One-time fee per run",
              "eventPriceUsd": 0.005,
              "isOneTimeEvent": true
            },
            "item": {
              "eventTitle": "Dataset metadata record",
              "eventDescription": "Per Hugging Face dataset metadata record produced",
              "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
            }
          }
        },
        "createdAt": "2026-07-17T08:42:14.115Z",
        "apifyMarginPercentage": 0.2
      }
    ],
    "notice": "NONE",
    "isCritical": false,
    "isGeneric": false,
    "hasNoDataset": false,
    "isSourceCodeHidden": true,
    "standbyUrl": null,
    "actorPermissionLevel": "LIMITED_PERMISSIONS",
    "readmeSummary": "## Hugging Face Datasets Scraper\n\nA crawler for the Hugging Face dataset catalog that discovers and extracts structured metadata for each public dataset entry: it performs keyword searches and exact-ID lookups across paginated catalog results, ranks and filters results by popularity and recency, deduplicates matches, parses raw tags into convenient fields (license, task, language, size, formats, libraries, modalities, region), and optionally captures truncated README card text and run provenance/diagnostics. Outputs are one metadata record per dataset containing identifiers and URLs, owner and repository names, public descriptions, popularity and trending metrics, timestamps and revision info, access flags, raw tags plus parsed license/task/language/format fields, size/format/library indicators, and per-run provenance details useful for dataset comparison, monitoring, and audit.\n\n## Use cases\n\n- Discover training and retrieval-augmented-generation (RAG) datasets by topic or popularity for dataset selection and benchmarking.\n- Export and compare dataset licenses, tags, tasks, languages, formats, and size categories for compliance or license review.\n- Enrich a list of known Hugging Face dataset IDs with current public metadata and metrics.\n- Monitor catalog changes over time by sorting and scheduling runs by recency or trending score.\n- Find popular NLP, vision, or domain-specific datasets (examples: finance, medical imaging, instruction tuning) for fine-tuning, R&D, or dataset curation.",
    "deploymentKey": "ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABAQCe62XezMBq94Ns5tzkZdWTp19xHT8PK0X8YhCqZoDcpEOK/y5KdflStn+23r067V2Y8JTK9KpE5XeRSsWg/PhORIE5QrJSY7+QMU4UsQBPPbr+lijwKvuth/zx7Xj11oS6i6frkg29WTJYIKmagDewKgxqssvIqlLz3EAYGvlXn55z3MmXNjiUQ3+JBLvSg73sYtqQywNZtaAGjX7vXUSizguBR40foowslAsMhwPrxXYZwAW7cDzks3hzQzhXrIK4QSSLEK5mkFndcHCIOku/TYXOTqVnwmWy0esAdkNxeNRFs3G6Kv7J24WlSvXnQnl5J7jwn6AxePiSOs5aBTTN \n"
  }
}