{ "openapi": "3.0.1", "info": { "title": "URL Hygiene & Dedup API", "description": "Normalize and deduplicate URL lists before crawling, enrichment, analytics, or RAG. Remove tracking parameters, sort queries, flag invalid URLs, and group duplicate links without fetching target websites.", "version": "0.1", "x-build-id": "GU1oeC9b8YHMyA7LG" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/craigtechservicesllc~url-hygiene-dedup-api/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-craigtechservicesllc-url-hygiene-dedup-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/craigtechservicesllc~url-hygiene-dedup-api/runs": { "post": { "operationId": "runs-sync-craigtechservicesllc-url-hygiene-dedup-api", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/craigtechservicesllc~url-hygiene-dedup-api/run-sync": { "post": { "operationId": "run-sync-craigtechservicesllc-url-hygiene-dedup-api", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Absolute HTTP(S) URLs to normalize.", "items": { "type": "string" } }, "items": { "title": "JSON items", "type": "array", "description": "Objects containing a URL field." }, "datasetId": { "title": "Source dataset ID", "type": "string", "description": "Dataset in the current Apify account. Do not include a token in this field." }, "urlField": { "title": "URL field", "type": "string", "description": "Dot path used for JSON items or dataset rows.", "default": "url" }, "maxItems": { "title": "Maximum URLs", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum number of input URLs to process in one run.", "default": 100000 }, "removeTrackingParameters": { "title": "Remove known tracking parameters", "type": "boolean", "description": "Removes UTM, ad-click, and common email-campaign parameters.", "default": true }, "removeParameters": { "title": "Additional parameters to remove", "type": "array", "description": "Extra query-parameter names to remove from every URL.", "default": [], "items": { "type": "string" } }, "keepParameters": { "title": "Parameters that must be kept", "type": "array", "description": "Overrides the tracking and removal lists.", "default": [], "items": { "type": "string" } }, "stripFragment": { "title": "Remove URL fragments", "type": "boolean", "description": "Removes the #fragment portion because it is not sent to web servers.", "default": true }, "sortQueryParameters": { "title": "Sort query parameters", "type": "boolean", "description": "Sorts query parameters into a stable order for deterministic comparison.", "default": true }, "removeTrailingSlash": { "title": "Remove trailing slash from non-root paths", "type": "boolean", "description": "Treats non-root paths with and without a final slash as equivalent.", "default": true }, "collapsePathSlashes": { "title": "Collapse repeated path slashes", "type": "boolean", "description": "Replaces repeated slashes in URL paths with a single slash.", "default": true }, "dropWww": { "title": "Treat www and apex hostnames as equal", "type": "boolean", "description": "Off by default because some sites serve different content on www.", "default": false }, "forceHttps": { "title": "Treat HTTP and HTTPS as equal", "type": "boolean", "description": "Off by default because changing scheme can merge distinct resources.", "default": false }, "includeUniqueOnly": { "title": "Emit first occurrence only", "type": "boolean", "description": "Outputs only the first item in each duplicate group.", "default": 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 } } }, "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 } } } } } } } } } }