{ "openapi": "3.0.1", "info": { "title": "Bulk URL Status Checker – HTTP Codes & Redirect Chains", "description": "Check thousands of URLs at once: HTTP status code, every redirect hop (301/302/307/308), final URL, loops, broken links (404/410/5xx), DNS/SSL/timeout errors, plus optional title, canonical and noindex. Verify migration redirect maps. $0.30 per 1,000 URLs.", "version": "0.1", "x-build-id": "4L9IQaaaXYcOGi0YK" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/gazidev~bulk-url-status-checker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-gazidev-bulk-url-status-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/gazidev~bulk-url-status-checker/runs": { "post": { "operationId": "runs-sync-gazidev-bulk-url-status-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/gazidev~bulk-url-status-checker/run-sync": { "post": { "operationId": "run-sync-gazidev-bulk-url-status-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", "properties": { "urls": { "title": "URLs to check", "type": "array", "description": "Full URLs (`https://example.com/page`) or bare domains (`example.com`, checked as https). Paste as many as you like; duplicates are removed and invalid values are reported for free.", "items": { "type": "string" } }, "bulkText": { "title": "Bulk list (paste text or CSV)", "type": "string", "description": "Paste a long list: one URL per line, a CSV export with a `url` / `link` / `address` column (e.g. from Screaming Frog, Ahrefs, Search Console), or any text - every URL in it is picked up." }, "redirectMap": { "title": "Redirect map to verify (old URL → expected URL)", "type": "string", "description": "For site migrations: one pair per line, `old-url new-url` (separated by a space, tab, comma or `->`). Each old URL is checked and the row gets `expectedUrl` and `matchesExpected` (true only when the final URL equals the expected one and returns 2xx)." }, "sourceFileUrl": { "title": "Load URLs from a file (URL)", "type": "string", "description": "Optional: a public link to a .txt or .csv file with URLs (Google Sheets 'Publish to web → CSV' links work)." }, "datasetId": { "title": "Read URLs from an Apify dataset (ID or name)", "type": "string", "description": "Optional: chain this Actor after a crawler or sitemap extractor. Every value of the field below is checked." }, "datasetField": { "title": "Dataset field with the URL", "type": "string", "description": "Field name in that dataset (arrays of URLs are also accepted).", "default": "url" }, "outputFilter": { "title": "Output", "enum": [ "all", "problems", "broken" ], "type": "string", "description": "`all` = one row per URL. `problems` = only URLs that are not 2xx, redirect, have an SSL problem or do not match the expected URL. `broken` = only 4xx/5xx/network errors. Every checked URL is charged either way.", "default": "all" }, "extractPageInfo": { "title": "Also read title, canonical, meta robots", "type": "boolean", "description": "Download the first 96 KB of each final HTML page (GET instead of HEAD) to add `title`, `canonical`, `canonicalIsSelf`, `metaRobots`, `noindex` and `metaRefreshUrl`. Slightly slower; same price.", "default": false }, "method": { "title": "Request method", "enum": [ "auto", "GET" ], "type": "string", "description": "`auto` sends HEAD first (fast, no body) and re-checks with GET when a server mishandles HEAD (405, 403, 404, 5xx…). `GET` always uses GET (only headers are read).", "default": "auto" }, "maxRedirects": { "title": "Max redirects to follow", "minimum": 1, "maximum": 30, "type": "integer", "description": "Longer chains are reported as `TOO_MANY_REDIRECTS`. Loops are detected automatically.", "default": 10 }, "checkInvalidSsl": { "title": "Still check URLs with invalid SSL", "type": "boolean", "description": "When a certificate is invalid/expired, retry without verification so you still get the status code; the problem is reported in `sslError`. Off = report `SSL_ERROR` and stop.", "default": true }, "maxUrls": { "title": "Max URLs", "minimum": 0, "type": "integer", "description": "Check at most this many URLs (0 = no limit).", "default": 0 }, "dedupe": { "title": "Remove duplicate URLs", "type": "boolean", "description": "Check each normalized URL once.", "default": true }, "maxConcurrency": { "title": "Parallel requests", "minimum": 1, "maximum": 100, "type": "integer", "description": "Total parallel checks.", "default": 20 }, "maxRequestsPerHost": { "title": "Parallel requests per host", "minimum": 1, "maximum": 20, "type": "integer", "description": "Keeps the load on any single website low.", "default": 4 }, "timeoutSecs": { "title": "Timeout per request (seconds)", "minimum": 3, "maximum": 120, "type": "integer", "description": "Per hop. Timed-out URLs are reported as `TIMEOUT`.", "default": 15 }, "retries": { "title": "Retries", "minimum": 0, "maximum": 3, "type": "integer", "description": "Retries for timeouts, connection errors, 429 and 503 (with backoff).", "default": 1 }, "userAgent": { "title": "Custom User-Agent", "type": "string", "description": "Optional. By default an honest bot User-Agent with a contact address is sent." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. Only needed for sites that block datacenter IPs.", "default": { "useApifyProxy": false } } } }, "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 } } } } } } } } } }