{ "openapi": "3.0.1", "info": { "title": "Website URL Crawler & Link Extractor", "description": "Crawl JavaScript-rendered websites and export a URL link map. Get source pages, depth, anchor text, link type, HTTP metadata, and crawl status.", "version": "1.0", "x-build-id": "12OJnonkch4QSqfPj" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/maximedupre~website-url-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-maximedupre-website-url-crawler", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/maximedupre~website-url-crawler/runs": { "post": { "operationId": "runs-sync-maximedupre-website-url-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/maximedupre~website-url-crawler/run-sync": { "post": { "operationId": "run-sync-maximedupre-website-url-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "urls" ], "properties": { "urls": { "title": "Website URLs", "minItems": 1, "type": "array", "description": "Add one or more public websites, domains, or page URLs to crawl.", "items": { "type": "object", "properties": { "url": { "title": "URL", "type": "string", "description": "Website URL or domain to crawl.", "minLength": 1 } }, "required": [ "url" ] } }, "keywords": { "title": "URL keywords", "type": "array", "description": "Keep URLs that contain all listed words or path parts. Leave empty to keep every matching URL.", "items": { "type": "string" }, "default": [] }, "crawlScope": { "title": "Crawl scope", "enum": [ "same-host", "same-domain", "include-external-discovered" ], "type": "string", "description": "Choose which discovered website links can be followed after each page loads.", "default": "same-domain" }, "assetPolicy": { "title": "Asset links", "enum": [ "pages-only", "include-documents", "include-all-links" ], "type": "string", "description": "Choose which document and media URLs should be saved with page URLs.", "default": "include-documents" }, "ignoredExtensions": { "title": "Ignored extensions", "type": "array", "description": "Skip links ending with these file extensions unless Asset links is set to Include all links.", "items": { "type": "string" }, "default": [ "jpg", "jpeg", "png", "gif", "webp", "svg", "zip", "mp4", "mp3" ] }, "maxResults": { "title": "Max URL rows", "minimum": 0, "maximum": 50000, "type": "integer", "description": "Maximum accepted URL rows across the whole run. Use 0 for every URL found within the other limits.", "default": 2000 }, "maxPagesPerStartUrl": { "title": "Max pages per website", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum rendered pages to open per website.", "default": 5 }, "maxDepth": { "title": "Max crawl depth", "minimum": 0, "maximum": 30, "type": "integer", "description": "How many link levels to follow from each website.", "default": 2 }, "maxLinksPerPage": { "title": "Max links per page", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum links to save and consider from each loaded page.", "default": 120 }, "includeHttpStatus": { "title": "Check HTTP status", "type": "boolean", "description": "Add status code, final URL, and content type for loaded pages.", "default": 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 } } }, "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 } } } } } } } } } }