{
  "openapi": "3.0.1",
  "info": {
    "title": "Website Metadata API — Schema.org, Open Graph & JSON-LD",
    "description": "Read any list of URLs over plain HTTP and get one row per page: title, meta tags, Open Graph, Twitter cards, canonical, hreflang, feeds, icons, JSON-LD and microdata with person names removed, plus normalised Article, Product, Organization, Event, JobPosting and FAQ data. No browser, no API key.",
    "version": "0.1",
    "x-build-id": "g6K1i2FEyTejQEE4i"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2"
    }
  ],
  "paths": {
    "/acts/insight.solutions~website-metadata-api/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run-sync-get-dataset-items-insight.solutions-website-metadata-api",
        "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": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    },
    "/acts/insight.solutions~website-metadata-api/runs": {
      "post": {
        "operationId": "runs-sync-insight.solutions-website-metadata-api",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor and returns information about the initiated run in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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": {
                  "$ref": "#/components/schemas/runsResponseSchema"
                }
              }
            }
          }
        }
      }
    },
    "/acts/insight.solutions~website-metadata-api/run-sync": {
      "post": {
        "operationId": "run-sync-insight.solutions-website-metadata-api",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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",
        "properties": {
          "urls": {
            "title": "URLs",
            "type": "array",
            "description": "The pages to read, one row each. Full URLs or bare domains (`apify.com` means its home page over https). The `#fragment` is dropped and duplicates are read, and billed, once. Email addresses, IP addresses and non-http schemes come back as free `invalid-url` rows.",
            "items": {
              "type": "string"
            }
          },
          "website": {
            "title": "Website (sitemap seed)",
            "type": "string",
            "description": "Optional. A site whose sitemap adds URLs to the list: the `Sitemap:` lines in its robots.txt, else `/sitemap.xml` and the other usual locations. Sitemap indexes and `.xml.gz` files are followed. A site with no readable sitemap is a free `no-sitemap` row.",
            "default": ""
          },
          "maxUrlsFromSitemap": {
            "title": "URLs taken from the sitemap",
            "minimum": 1,
            "maximum": 5000,
            "type": "integer",
            "description": "How many page URLs the `website` sitemap may add, in sitemap order. Reading stops as soon as this many are found, so a 50,000-URL sitemap costs one file, not fifty.",
            "default": 100
          },
          "includeJsonLd": {
            "title": "Include JSON-LD",
            "type": "boolean",
            "description": "Every `<script type=\"application/ld+json\">` block, parsed leniently, `@graph` flattened, person names removed (see README). Off: `jsonLd` is null; `schemaTypes` and the entities are still filled.",
            "default": true
          },
          "includeMicrodata": {
            "title": "Include microdata",
            "type": "boolean",
            "description": "`itemscope` / `itemprop` items as JSON-LD-shaped objects, nested by element nesting, person names removed. RDFa is not read.",
            "default": true
          },
          "includeOpenGraph": {
            "title": "Include Open Graph",
            "type": "boolean",
            "description": "`og:*` tags as an object, with `og:image` / `og:video` as arrays carrying their width, height and alt, plus `article:*` and `product:*` tags.",
            "default": true
          },
          "includeTwitter": {
            "title": "Include Twitter cards",
            "type": "boolean",
            "description": "`twitter:*` tags as a flat object.",
            "default": true
          },
          "includeMetaTags": {
            "title": "Include every meta tag",
            "type": "boolean",
            "description": "Every `<meta name|property|http-equiv>` as a `{name, property, httpEquiv, content}` list, in page order. Author-like tags keep their name with a null content when the content is a person's name.",
            "default": true
          },
          "includeLinks": {
            "title": "Include links",
            "type": "boolean",
            "description": "Canonical, hreflang alternates, RSS/Atom/JSON feeds, icons with sizes, manifest, AMP, prev/next, `rel=me` and license, from the page's `<link>` elements.",
            "default": true
          },
          "includeHeadings": {
            "title": "Include headings",
            "type": "boolean",
            "description": "The text of the page's `<h1>` and `<h2>` elements, the first 50 of each.",
            "default": true
          },
          "includeEntities": {
            "title": "Include normalised entities",
            "type": "boolean",
            "description": "Article, Product, Organization, LocalBusiness, Event, JobPosting, FAQ, breadcrumbs, VideoObject, Recipe, WebSite and SoftwareApplication in one fixed shape each, from JSON-LD, then microdata, then Open Graph.",
            "default": true
          },
          "followRedirects": {
            "title": "Follow redirects",
            "type": "boolean",
            "description": "Follow redirects (up to 10) and read the page they end on; `finalUrl` and `redirectCount` say where that was. Off: a redirect is a free `redirected` row naming its target.",
            "default": true
          },
          "respectRobots": {
            "title": "Respect robots.txt",
            "type": "boolean",
            "description": "Read each site's robots.txt once and skip URLs its `User-agent: *` rules disallow (free `robots-disallowed` rows), honouring its `Crawl-delay` up to 30 seconds. Turn off only for sites you are entitled to read regardless.",
            "default": true
          },
          "requestTimeoutSecs": {
            "title": "Request timeout (seconds)",
            "minimum": 5,
            "maximum": 60,
            "type": "integer",
            "description": "How long one page request may take before it is a free `timeout` row. A timeout is not retried.",
            "default": 20
          },
          "maxConcurrency": {
            "title": "Pages in parallel",
            "minimum": 1,
            "maximum": 20,
            "type": "integer",
            "description": "How many URLs are fetched at once. Requests to one host are spaced at least 300 ms apart whatever this says, so this speeds up a list of many sites, not one site.",
            "default": 8
          },
          "maxRunSecs": {
            "title": "Maximum run time (seconds)",
            "minimum": 30,
            "maximum": 3600,
            "type": "integer",
            "description": "Wall-clock budget for the whole run. When it is reached the Actor stops, keeps and bills every page already returned, and files a free `timeout` row for each URL it never reached.",
            "default": 240
          },
          "proxyConfiguration": {
            "title": "Proxy configuration",
            "type": "object",
            "description": "Apify's datacenter proxy by default — most sites answer it and its cost is inside the per-page price. A site whose bot wall refuses datacenter addresses comes back as a free `blocked` row; switching to the RESIDENTIAL group is the fix. Each worker keeps its own session and a refused session is rotated once.",
            "default": {
              "useApifyProxy": true
            }
          }
        }
      },
      "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
                  },
                  "PROXY_UNBLOCKER_UNITS": {
                    "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
                  },
                  "PROXY_UNBLOCKER_UNITS": {
                    "type": "integer",
                    "example": 0
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}