{ "openapi": "3.0.1", "info": { "title": "Broken Link Checker: 404s, Redirects & Dead Links", "description": "Crawl a website and check every link on its pages: internal, external and, if you like, images, scripts and stylesheets. Finds 404s, server errors, timeouts, DNS and SSL failures and redirect loops, with the page, link text and redirect chain. Pay per page checked.", "version": "1.0", "x-build-id": "zeJAruUgDRJx8qLdL" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/private_image_hg9~broken-link-checker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-private_image_hg9-broken-link-checker", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/private_image_hg9~broken-link-checker/runs": { "post": { "operationId": "runs-sync-private_image_hg9-broken-link-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/private_image_hg9~broken-link-checker/run-sync": { "post": { "operationId": "run-sync-private_image_hg9-broken-link-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "Websites to check", "type": "array", "description": "One start page per line, like https://example.com/ or example.com/docs/. The crawl starts there and visits pages of the same site (www. and the bare domain count as one site). Links on those pages are checked wherever they point. Start URLs on the same site share its page limit.", "items": { "type": "string" } }, "maxPagesPerSite": { "title": "Max pages per site", "minimum": 1, "maximum": 10000, "type": "integer", "description": "How many pages of each site are crawled and have their links checked. You pay per page, so this also caps the cost per site.", "default": 100 }, "maxDepth": { "title": "Max clicks from the start page", "minimum": 0, "maximum": 100, "type": "integer", "description": "0 checks only the start page. 1 also crawls the pages it links to, and so on. Links on the last level are still checked, just not crawled.", "default": 10 }, "checkAssets": { "title": "Also check images, scripts and stylesheets", "type": "boolean", "description": "Check the files each page loads: images (src and srcset), scripts, stylesheets, icons, video, audio and iframes. They get linkType \"asset\".", "default": false }, "reportAllLinks": { "title": "List working links too", "type": "boolean", "description": "Save a row for every link, including the ones that work and the ones robots.txt kept the checker away from. Off: only broken and problem links are saved.", "default": false }, "maxRequestsPerSecondPerHost": { "title": "Requests per second per host of your site", "minimum": 1, "maximum": 10, "type": "integer", "description": "The most requests sent each second to any one host of the site being crawled, page fetches and link checks together. Page fetches are also kept to at most 2 per second and to the Crawl-delay its robots.txt asks for (up to 10 seconds); link checks there wait at least that delay, up to 1 second.", "default": 3 }, "maxRequestsPerSecondPerExternalHost": { "title": "Link checks per second per other host", "minimum": 1, "maximum": 20, "type": "integer", "description": "The most link checks sent each second to any one host your pages link to but that is not crawled (github.com, a partner site, a CDN...). Each link is checked once per run with one HEAD request (plus a GET when needed).", "default": 10 } } }, "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 } } } } } } } } } }