{ "openapi": "3.0.1", "info": { "title": "Fix Broken Text in Scraped Data - Mojibake, Entities, Language", "description": "Scraped text full of Café, don’t, & and invisible characters breaks LLMs and CRMs. Pick the dataset and get repaired text in every field plus a detected-language column, with a per-field report of what changed. Offline.", "version": "1.0", "x-build-id": "Bm3Jf2qic4aPwt6nk" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/that_red_bird~scraped-text-fixer/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-that_red_bird-scraped-text-fixer", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/that_red_bird~scraped-text-fixer/runs": { "post": { "operationId": "runs-sync-that_red_bird-scraped-text-fixer", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/that_red_bird~scraped-text-fixer/run-sync": { "post": { "operationId": "run-sync-that_red_bird-scraped-text-fixer", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "datasets": { "title": "Dataset(s) to fix", "type": "array", "description": "Pick the dataset of any scraper run. Every text field, including nested ones, is cleaned. Use the picker rather than typing an ID: it gives this Actor permission to read your dataset. Leave empty to use the pasted rows below, or the built-in demo." }, "rows": { "title": "Rows (JSON)", "type": "array", "description": "Optional. Paste rows as JSON objects, e.g. {\"title\":\"Café de Paris\",\"text\":\"don’t miss it\"}. Plain strings are treated as a text field.", "default": [] }, "rowsCsv": { "title": "Rows (CSV or JSON text)", "type": "string", "description": "Optional. Paste a CSV (first row = column names) or a JSON array.", "default": "" }, "fixMojibake": { "title": "Repair mojibake", "type": "boolean", "description": "Repair text where UTF-8 was read with the wrong encoding (Café becomes Café, don’t becomes don’t, Cyrillic and emoji too), including double-encoded text.", "default": true }, "decodeHtmlEntities": { "title": "Decode HTML entities", "type": "boolean", "description": "Turn &, ', é,   and similar into real characters. Turn off if your text legitimately talks about HTML.", "default": true }, "unicodeNormalization": { "title": "Unicode normalization", "enum": [ "NFC", "NFKC", "none" ], "type": "string", "description": "NFC joins combining accents into single characters (safe for everything). NFKC also folds compatibility characters such as full-width letters and ligatures. none leaves characters alone.", "default": "NFC" }, "keepNewlines": { "title": "Keep line breaks", "type": "boolean", "description": "When on, line breaks are kept (3 or more in a row become 2). When off, all whitespace including line breaks becomes a single space.", "default": true }, "straightenQuotes": { "title": "Straighten curly quotes", "type": "boolean", "description": "Replace curly quotes with plain ' and \" characters. Off by default.", "default": false }, "detectLanguage": { "title": "Detect language", "type": "boolean", "description": "Add language (ISO 639-1 code), languageName and languageConfidence columns, detected offline from the text fields. Needs about 20 characters of text; shorter text is reported as und.", "default": true }, "languageFields": { "title": "Fields used for language detection", "type": "array", "description": "Optional list of field names (for example description, reviewText) to detect the language from. Empty = all text fields of 20 or more characters.", "default": [], "items": { "type": "string" } }, "skipFields": { "title": "Fields to leave untouched", "type": "array", "description": "Optional list of field names that must not be changed, for example rawHtml or code. Nested fields are skipped with their parent.", "default": [], "items": { "type": "string" } }, "keepOriginals": { "title": "Keep original text", "type": "boolean", "description": "When on, the text before fixing is stored in an originalText object for every field that was changed. Makes rows bigger.", "default": false }, "maxRows": { "title": "Maximum rows", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Safety limit on the number of rows processed in one run.", "default": 100000 } } }, "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 } } } } } } } } } }