{ "openapi": "3.0.1", "info": { "title": "Text Cleanup and URL De-tracking", "description": "Cleans a list of texts in one pass: strips HTML, repairs mojibake, tidies Unicode and removes URL trackers. $0.0005 per text.", "version": "1.0", "x-build-id": "q8rYt1gfAAImcPq4K" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/comradecoding~text-cleanup/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-comradecoding-text-cleanup", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/comradecoding~text-cleanup/runs": { "post": { "operationId": "runs-sync-comradecoding-text-cleanup", "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/comradecoding~text-cleanup/run-sync": { "post": { "operationId": "run-sync-comradecoding-text-cleanup", "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": [ "texts" ], "properties": { "texts": { "title": "Texts", "type": "array", "description": "The texts to clean. Each entry is a string, or an object with a text field and an optional id field that is copied to the output row so you can match it back. Up to 500,000 characters per text. Returns one row per text: text (cleaned) plus counts of what changed." }, "htmlMode": { "title": "HTML handling", "enum": [ "auto", "strip", "keep" ], "type": "string", "description": "auto: strip tags when the text contains HTML tags, otherwise only decode references such as & so plain text keeps its line breaks. strip: always treat the text as HTML. keep: leave tags and references as they are.", "default": "auto" }, "fixMojibake": { "title": "Repair mojibake", "type": "boolean", "description": "Repair UTF-8 text that was read as Windows-1252 or Latin-1, such as Café to Café or ’ to a curly apostrophe. Also repairs text that was read wrongly twice.", "default": true }, "unicodeForm": { "title": "Unicode normalization form", "enum": [ "NFC", "NFKC", "NFD", "NFKD", "none" ], "type": "string", "description": "NFC (the usual choice) joins accents to their letters. NFKC also turns ligatures and full-width letters into plain ones. NFD and NFKD split accents off. none skips normalization. Invisible characters (zero width space, soft hyphen, byte order mark, control codes) are removed in every mode.", "default": "NFC" }, "whitespace": { "title": "Whitespace", "enum": [ "lines", "collapse", "keep" ], "type": "string", "description": "lines: collapse spaces and tabs inside each line, trim lines, keep at most one blank line in a row. collapse: the whole text becomes one line with single spaces. keep: no whitespace changes.", "default": "lines" }, "cleanUrls": { "title": "Remove tracking parameters from URLs", "type": "boolean", "description": "Remove utm_ parameters and 30 known click and email trackers (fbclid, gclid, msclkid, mc_eid and others) from every http and https URL in the text. Other parameters stay exactly as they were.", "default": true }, "maxItems": { "title": "Max rows", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Stop after this many output rows. Each row is one billable result. Texts past the cap are not processed and not charged.", "default": 1000 } } }, "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 } } } } } } } } } }