URL Wrangler
Pricing
from $0.01 / actor run
Go to Apify Store
URL Wrangler
Join relative URLs, decompose URLs into a node/edge tree, replace/remove query params, and extract fields — batch URL wrangling toolkit.
URL Wrangler
Pricing
from $0.01 / actor run
Join relative URLs, decompose URLs into a node/edge tree, replace/remove query params, and extract fields — batch URL wrangling toolkit.
You can access the URL Wrangler programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "IbGR0hTZMXNqnMtgO" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/rl1987~url-wrangler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-rl1987-url-wrangler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/rl1987~url-wrangler/runs": { "post": { "operationId": "runs-sync-rl1987-url-wrangler", "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/rl1987~url-wrangler/run-sync": { "post": { "operationId": "run-sync-rl1987-url-wrangler", "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": [ "operation", "urls" ], "properties": { "operation": { "title": "Operation", "enum": [ "urljoin", "unfurl", "replace_params", "extract" ], "type": "string", "description": "Which URL-wrangling operation to run over the URL list.", "default": "urljoin" }, "urls": { "title": "URLs", "type": "array", "description": "The URLs to process. For 'urljoin', these are the relative URLs resolved against Base URL. For the other operations, these are the URLs operated on directly.", "items": { "type": "string" } }, "baseUrl": { "title": "Base URL (urljoin only)", "type": "string", "description": "Reference URL every entry in URLs is resolved against." }, "params": { "title": "Params to upsert (replace_params only)", "type": "array", "description": "Query-string key/value pairs to add or overwrite on every URL.", "items": { "type": "object", "properties": { "key": { "title": "Param name", "type": "string", "description": "Query-string key" }, "value": { "title": "Param value", "type": "string", "description": "New value for this key" } }, "required": [ "key", "value" ] } }, "remove": { "title": "Params to remove (replace_params only)", "type": "array", "description": "Query-string keys to strip from every URL. Supports fnmatch wildcards, e.g. \"utm_*\".", "items": { "type": "string" } }, "field": { "title": "Field (extract only)", "enum": [ "domain", "apex", "subdomain", "tld", "path", "keys", "values", "keypairs", "format" ], "type": "string", "description": "Which field to extract from every URL.", "default": "domain" }, "format": { "title": "Custom format (extract only, field=format)", "type": "string", "description": "Printf-style directive string, e.g. \"%s://%d%p?%q\". Directives: %s scheme, %u userinfo, %d domain, %S subdomain, %r root, %t tld, %P port, %p path, %e extension, %q query, %f fragment, %@ %: %? %# conditional separators, %a authority, %% literal percent." }, "unfurlDetail": { "title": "Detail level (unfurl only)", "enum": [ "summary", "full" ], "type": "string", "description": "'summary' returns the node/edge tree; 'full' also includes a node/edge count summary.", "default": "summary" }, "outputFormat": { "title": "Include ASCII tree (unfurl only)", "type": "boolean", "description": "Also render a human-readable ASCII tree alongside the JSON node/edge graph.", "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for URL Wrangler from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: