{ "openapi": "3.0.1", "info": { "title": "URL Canonicalizer", "description": "Canonicalize URLs by stripping tracking parameters, normalizing hosts, paths, query strings, and grouping equivalent URL variants.", "version": "1.0", "x-build-id": "SRomf7GMG3CW3zg7w" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/junipr~url-canonicalizer/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-junipr-url-canonicalizer", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/junipr~url-canonicalizer/runs": { "post": { "operationId": "runs-sync-junipr-url-canonicalizer", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/junipr~url-canonicalizer/run-sync": { "post": { "operationId": "run-sync-junipr-url-canonicalizer", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "URL List", "type": "array", "description": "URLs or URL-like strings to canonicalize.", "items": { "type": "string" } }, "records": { "title": "Record Objects", "type": "array", "description": "Optional row objects that contain URL fields or text fields.", "items": { "type": "object" } }, "urlFields": { "title": "URL Fields", "type": "array", "description": "Record fields that should be read as direct URLs.", "items": { "type": "string" }, "default": [ "url", "sourceUrl", "landingPage" ] }, "textFields": { "title": "Text Fields", "type": "array", "description": "Record fields to scan for URLs when extractUrlsFromText is enabled.", "items": { "type": "string" }, "default": [ "text", "description", "notes" ] }, "mixedText": { "title": "Mixed Text", "type": "string", "description": "Optional free text containing URLs to extract and canonicalize." }, "extractUrlsFromText": { "title": "Extract URLs From Text", "type": "boolean", "description": "Extract URL-like strings from mixedText and configured text fields.", "default": true }, "allowSchemalessUrls": { "title": "Allow Schemaless URLs", "type": "boolean", "description": "Treat strings like example.com/path as HTTPS URLs.", "default": true }, "forceHttps": { "title": "Force HTTPS", "type": "boolean", "description": "Convert http:// URLs to https:// in canonical output.", "default": true }, "stripWww": { "title": "Strip WWW", "type": "boolean", "description": "Remove leading www. from hostnames.", "default": true }, "stripHash": { "title": "Strip Hash", "type": "boolean", "description": "Remove URL fragments.", "default": true }, "stripTrailingSlash": { "title": "Strip Trailing Slash", "type": "boolean", "description": "Remove trailing slash from non-root paths.", "default": true }, "stripIndexFiles": { "title": "Strip Index Files", "type": "boolean", "description": "Normalize /index.html and similar index files to the containing path.", "default": true }, "sortQueryParams": { "title": "Sort Query Params", "type": "boolean", "description": "Sort kept query parameters by name and value.", "default": true }, "dropEmptyQueryParams": { "title": "Drop Empty Query Params", "type": "boolean", "description": "Drop query parameters with empty values.", "default": true }, "stripParams": { "title": "Params To Strip", "type": "array", "description": "Query parameters to remove. Defaults include common tracking parameters.", "items": { "type": "string" }, "default": [ "utm_source", "utm_medium", "utm_campaign", "utm_term", "utm_content", "fbclid", "gclid", "msclkid" ] }, "keepParams": { "title": "Params To Keep", "type": "array", "description": "Important parameters to preserve even if they look like tracking parameters.", "items": { "type": "string" }, "default": [] }, "includeInvalid": { "title": "Include Invalid Rows", "type": "boolean", "description": "Include invalid URL inputs in the dataset with issues.", "default": true }, "includeReport": { "title": "Include Report Artifacts", "type": "boolean", "description": "Write canonical URL CSV, group JSON, and report artifacts to the key-value store.", "default": true }, "maxItems": { "title": "Max Items", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Maximum extracted URL items to process. Default is small and safe for Apify quality checks.", "default": 100 }, "dryRun": { "title": "Dry Run", "type": "boolean", "description": "Validate input and write a dry-run summary without PPE charges or dataset output.", "default": false }, "debug": { "title": "Debug Logs", "type": "boolean", "description": "Enable debug-level logs.", "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 } } } } } } } } } }