{ "openapi": "3.0.1", "info": { "title": "Harbor Registry Extractor", "description": "Point at any self-hosted Harbor container registry and extract its public projects, repositories, image artifacts (with vulnerability-scan severity) and instance fingerprint via the open /api/v2.0 REST API. One actor, any Harbor — no per-host scraper.", "version": "0.1", "x-build-id": "Q6PS2goKb2v4ksflU" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datamule~harbor-registry-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datamule-harbor-registry-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/datamule~harbor-registry-extractor/runs": { "post": { "operationId": "runs-sync-datamule-harbor-registry-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/datamule~harbor-registry-extractor/run-sync": { "post": { "operationId": "run-sync-datamule-harbor-registry-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "sources" ], "properties": { "sources": { "title": "Harbor instance URL(s)", "type": "array", "description": "One or more Harbor container-registry base URLs. Harbor exposes an /api/v2.0 REST API; public projects are anonymous-browsable by design and /systeminfo + /health are unauthenticated on every install, so ONE actor works against any instance: https://registry.cern.ch (CERN's public registry), https://demo.goharbor.io (the vendor demo), or any self-hosted install on your Kubernetes clusters. Paste the server root as given (the /api/v2.0/... path is appended for you). When several are listed, each is queried in turn and a source that is unreachable, behind an anti-bot wall, or fully auth-gated is skipped with a warning.", "items": { "type": "string" } }, "mode": { "title": "Mode", "enum": [ "projects", "repositories", "artifacts", "discovery" ], "type": "string", "description": "What to extract. projects (default): the public-project census from /api/v2.0/projects — one row per project (owner, repo count, public flag, auto-scan, severity, timestamps). repositories: the repos inside one Project — one row per repo (artifact count, pull count, timestamps). artifacts: the images inside a Project (and optionally one Repository) — one row per artifact (digest, tags, size, push time, vulnerability scan severity + counts). discovery: one fingerprint row per instance from /systeminfo + /health (Harbor version, auth mode, self-registration, component health).", "default": "projects" }, "project": { "title": "Project (repositories / artifacts mode)", "type": "string", "description": "REQUIRED for repositories and artifacts modes: the Harbor project name to drill into (e.g. \"acc\" on registry.cern.ch). Ignored in projects and discovery modes." }, "repository": { "title": "Repository (artifacts mode, optional)", "type": "string", "description": "ARTIFACTS MODE only. A single repository name RELATIVE to the project (the part after \"project/\"), e.g. \"gcr.io/knative-releases/.../webhook\". Leave empty to walk EVERY repository in the project (bounded by Max records)." }, "q": { "title": "Query filter (projects / repositories mode)", "type": "string", "description": "Optional Harbor-native fuzzy filter passed as ?q= — e.g. \"name=~acc\" to match project/repo names containing \"acc\". Leave empty to list everything. See Harbor's API docs for the q syntax." }, "name": { "title": "Exact project name (projects mode)", "type": "string", "description": "PROJECTS MODE only. Restrict to projects whose name exactly matches (passed as ?name=). Leave empty for no name filter." }, "page": { "title": "Start page", "minimum": 1, "type": "integer", "description": "The Harbor page number to start from (1-based). Pagination then continues via Harbor's Link: rel=next header until the cap or the last page. Leave at 1 to start from the beginning.", "default": 1 }, "pageSize": { "title": "Page size", "minimum": 1, "maximum": 100, "type": "integer", "description": "Rows requested per Harbor API page (1-100; Harbor caps these collections at 100). This is a fetch-batch tuning knob, not a total cap — use Max records for that. Leave empty for 100.", "default": 100 }, "maxRecords": { "title": "Max records (global cap)", "minimum": 1, "type": "integer", "description": "A GLOBAL cap on the number of rows to emit across ALL sources (each row is one project/repo/artifact/instance and one billable event). Pagination — and, in artifacts mode, the per-repo fan-out — stops as soon as the cap is reached, so a small value is a cheap, deterministic sample. Leave empty to fetch every matching record — a broad artifacts run on a large registry can return very many rows." }, "bearer": { "title": "Bearer token / robot account", "type": "string", "description": "Optional Harbor bearer token or robot-account credential for reading a private instance (sent as Authorization: Bearer ***). NOT required for anonymous/public projects. Never logged." }, "extraHeaders": { "title": "Extra request headers", "type": "object", "description": "Optional extra HTTP headers as a JSON object, e.g. {\"X-Harbor-CSRF-Token\": \"...\"} for a gateway-fronted instance. Not required for the public servers. Header values are never logged." } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }