{
"openapi": "3.0.1",
"info": {
"title": "Broken Link Checker — Crawl Sites & Find 404s",
"description": "Crawl each website (same domain, respects robots.txt), check every internal and external link, and get the broken ones (404, 5xx, timeouts, DNS errors) with the page where they were found, anchor text, plus one summary row per site.",
"version": "0.1",
"x-build-id": "yYeQ7sx7hBpysaKjE"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/hoanglongteam~broken-link-checker/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-hoanglongteam-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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/hoanglongteam~broken-link-checker/runs": {
"post": {
"operationId": "runs-sync-hoanglongteam-broken-link-checker",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/hoanglongteam~broken-link-checker/run-sync": {
"post": {
"operationId": "run-sync-hoanglongteam-broken-link-checker",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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 crawl",
"type": "array",
"description": "Start URLs or domains, e.g. example.com or https://example.com/blog/. The crawler stays on the same domain (www and non-www count as the same site).",
"items": {
"type": "string"
}
},
"maxPagesPerSite": {
"title": "Max pages per site",
"minimum": 1,
"maximum": 2000,
"type": "integer",
"description": "Maximum number of HTML pages to crawl on each site. Every link found on these pages is checked.",
"default": 50
},
"checkExternalLinks": {
"title": "Check external links",
"type": "boolean",
"description": "Also check links pointing to other domains (one HEAD/GET request each). Turn off to check internal links only.",
"default": true
},
"checkImages": {
"title": "Check images",
"type": "boolean",
"description": "Also check ![]()
URLs, not just links.",
"default": false
},
"maxLinksPerSite": {
"title": "Max unique links to check per site",
"minimum": 10,
"maximum": 20000,
"type": "integer",
"description": "Safety cap on unique link URLs checked per site (internal + external). Also caps cost, since each unique link checked is one charged event.",
"default": 2000
},
"maxConcurrency": {
"title": "Max concurrency",
"minimum": 1,
"maximum": 30,
"type": "integer",
"description": "Maximum number of HTTP requests in flight at once across all sites. Requests to the same host are additionally limited to 2 at a time.",
"default": 10
},
"delayMs": {
"title": "Delay between requests to the same host (ms)",
"minimum": 0,
"maximum": 10000,
"type": "integer",
"description": "Polite pause between two requests to the same host. A robots.txt Crawl-delay (up to 10 s) overrides this when larger, and the delay is raised automatically if a host answers 429 Too Many Requests.",
"default": 200
},
"timeoutSecs": {
"title": "Request timeout (seconds)",
"minimum": 3,
"maximum": 60,
"type": "integer",
"description": "Max seconds to wait for each request before reporting the link as a timeout.",
"default": 15
}
}
},
"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
}
}
}
}
}
}
}
}
}
}