{ "openapi": "3.0.1", "info": { "title": "CSV & Excel Data Cleaner | Dedupe & Fix", "description": "Clean CSV, Excel & JSON in bulk: fix encoding, dates, numbers & currency, flag bad emails, remove duplicates (fuzzy too). Full change log. No AI.", "version": "0.1", "x-build-id": "UwIYQGqMb5duU6OXq" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/makentest~csv-excel-data-cleaner-dedupe-fix/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-makentest-csv-excel-data-cleaner-dedupe-fix", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/makentest~csv-excel-data-cleaner-dedupe-fix/runs": { "post": { "operationId": "runs-sync-makentest-csv-excel-data-cleaner-dedupe-fix", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/makentest~csv-excel-data-cleaner-dedupe-fix/run-sync": { "post": { "operationId": "run-sync-makentest-csv-excel-data-cleaner-dedupe-fix", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "sourceType": { "title": "Source type", "enum": [ "text", "url", "dataset", "keyValueStore" ], "type": "string", "description": "Where the data comes from. Fill in the matching field below.", "default": "text" }, "pastedText": { "title": "Pasted text", "type": "string", "description": "CSV or JSON text (max 5 MB). Used when Source type is 'Pasted text'.", "default": "" }, "fileUrl": { "title": "Data file (upload or URL)", "type": "string", "description": "Upload your .csv, .xlsx or .json file here (Console: pick 'Upload' to store it in a key-value store), or paste a public http(s) link. The file is read once; only the location you give is contacted.", "default": "" }, "datasetId": { "title": "Apify dataset ID", "type": "string", "description": "ID of the dataset to clean (e.g. output of another Actor). Nested values are converted to JSON text.", "default": "" }, "kvStoreId": { "title": "Key-value store ID", "type": "string", "description": "Leave empty to use this run's default store. Used with 'Record key'.", "default": "" }, "kvRecordKey": { "title": "Record key", "type": "string", "description": "Key of the CSV, XLSX or JSON record to clean.", "default": "" }, "inputFormat": { "title": "File format", "enum": [ "auto", "csv", "xlsx", "json" ], "type": "string", "description": "Auto-detect from the content, or force a format.", "default": "auto" }, "sheetName": { "title": "Excel sheet name", "type": "string", "description": "Sheet to read. Empty = first sheet.", "default": "" }, "hasHeader": { "title": "First row is a header", "type": "boolean", "description": "Untick if the file has no header row; columns are then named column_1, column_2, ...", "default": true }, "encoding": { "title": "Text encoding", "enum": [ "auto", "utf-8", "cp1252", "latin-1", "utf-16" ], "type": "string", "description": "Auto tries UTF-8 first, then Windows-1252. Pick one explicitly if accents look wrong.", "default": "auto" }, "delimiter": { "title": "CSV delimiter", "enum": [ "auto", ",", ";", "\t", "|" ], "type": "string", "description": "Field separator of the CSV input.", "default": "auto" }, "trimWhitespace": { "title": "Trim whitespace", "type": "boolean", "description": "Remove leading/trailing spaces from every cell.", "default": true }, "collapseInternalSpaces": { "title": "Collapse repeated spaces", "type": "boolean", "description": "Turn runs of spaces/tabs inside a cell into one space ('Ana García' → 'Ana García').", "default": false }, "repairEncoding": { "title": "Repair encoding problems", "type": "boolean", "description": "Fix mojibake (e.g. 'Café' → 'Café'), smart quotes, invisible characters and non-breaking spaces.", "default": true }, "headerCase": { "title": "Normalize headers", "enum": [ "none", "snake_case", "lower", "upper", "title" ], "type": "string", "description": "Headers are always trimmed, de-duplicated and never empty. Choose a casing style, or keep the originals.", "default": "none" }, "normalizeBlanks": { "title": "Normalize blanks / nulls", "type": "boolean", "description": "Treat empty cells and the null tokens below as one consistent empty value.", "default": true }, "nullTokens": { "title": "Null tokens", "type": "array", "description": "Cell texts treated as empty (exact match after trimming). Note '-' and '0' are never treated as null unless you add them.", "items": { "type": "string" }, "default": [ "null", "NULL", "N/A", "n/a", "NA", "#N/A", "nan", "NaN", "none", "None" ] }, "blankFill": { "title": "Fill empty cells with", "type": "string", "description": "Text written into empty cells of CSV/XLSX output (JSON and dataset keep null). Empty = leave blank.", "default": "" }, "caseRules": { "title": "Value casing rules", "type": "array", "description": "List of {\"column\": \"Name\", \"case\": \"title\"} (case: lower, upper, title). Use \"*\" for all columns.", "items": { "type": "object" }, "default": [] }, "findReplaceRules": { "title": "Find / replace rules", "type": "array", "description": "List of {\"column\": \"*\", \"find\": \"St.\", \"replace\": \"Street\", \"mode\": \"literal|regex\", \"caseSensitive\": true, \"wholeCell\": false}. Applied in order.", "items": { "type": "object" }, "default": [] }, "numericColumns": { "title": "Numeric columns", "type": "array", "description": "Columns to convert into true numbers: strips currency symbols/codes, % and thousands separators; (1,234) becomes -1234.", "items": { "type": "string" }, "default": [] }, "decimalSeparator": { "title": "Decimal separator", "enum": [ "auto", ".", "," ], "type": "string", "description": "'Auto' treats '1,234' as 1234 and '1,5' as 1.5. Pick one when your data is consistently European or US.", "default": "auto" }, "percentMode": { "title": "Percent handling", "enum": [ "number", "fraction" ], "type": "string", "description": "'10%' becomes 10 (number) or 0.1 (fraction).", "default": "number" }, "dateColumns": { "title": "Date columns", "type": "array", "description": "Columns to convert into one consistent date format.", "items": { "type": "string" }, "default": [] }, "dayFirst": { "title": "Day before month (31/12/2024)", "type": "boolean", "description": "How to read ambiguous dates like 03/04/2024. Ambiguous values are flagged in the output.", "default": false }, "dateOutputFormat": { "title": "Date output format", "enum": [ "iso", "iso_date", "us", "eu" ], "type": "string", "description": "ISO keeps a time part when the input had one; 'ISO date only' removes it.", "default": "iso" }, "emailColumns": { "title": "Email columns", "type": "array", "description": "Columns checked for a valid email format (flags only; no emails are verified or sent).", "items": { "type": "string" }, "default": [] }, "lowercaseEmails": { "title": "Lowercase emails", "type": "boolean", "description": "Lowercase values in the email columns.", "default": true }, "phoneColumns": { "title": "Phone columns", "type": "array", "description": "Columns checked for a plausible phone format (7–15 digits).", "items": { "type": "string" }, "default": [] }, "phoneFormat": { "title": "Phone output", "enum": [ "none", "e164" ], "type": "string", "description": "'E.164' only rewrites numbers that already start with + or 00; other numbers are left unchanged and flagged.", "default": "none" }, "includeColumns": { "title": "Keep only these columns", "type": "array", "description": "Empty = keep all columns.", "items": { "type": "string" }, "default": [] }, "excludeColumns": { "title": "Drop these columns", "type": "array", "description": "Columns removed from the output.", "items": { "type": "string" }, "default": [] }, "requiredColumns": { "title": "Required columns", "type": "array", "description": "Rows with an empty value here are handled by the error policy.", "items": { "type": "string" }, "default": [] }, "errorPolicy": { "title": "Error policy", "enum": [ "quarantine", "keep", "skip", "fail" ], "type": "string", "description": "What to do with a row that has an unparseable number/date, a missing required value or too many cells.", "default": "quarantine" }, "preserveOriginals": { "title": "Preserve originals", "type": "boolean", "description": "Adds an '_original' column with the original values of every cell that was changed in that row.", "default": false }, "dedupeMode": { "title": "Duplicate detection", "enum": [ "none", "exact", "key", "fuzzy" ], "type": "string", "description": "How duplicates are found.", "default": "none" }, "dedupeKeyColumns": { "title": "Key columns", "type": "array", "description": "Required for key and fuzzy modes.", "items": { "type": "string" }, "default": [] }, "dedupeCaseInsensitive": { "title": "Ignore case in key", "type": "boolean", "description": "Key mode only: compare keys case-insensitively and trimmed.", "default": true }, "fuzzyThreshold": { "title": "Fuzzy similarity threshold", "minimum": 0.5, "maximum": 1, "type": "number", "description": "0.5–1.0. Higher = stricter. Keys are lowercased, accent-stripped and punctuation-free before comparing.", "default": 0.9 }, "duplicatePrecedence": { "title": "Which duplicate wins", "enum": [ "first", "last", "mostComplete" ], "type": "string", "description": "The row that stays in the clean output.", "default": "first" }, "quarantineDuplicates": { "title": "Send removed duplicates to Rejected export", "type": "boolean", "description": "Keeps an audit trail of every removed row.", "default": true }, "outputFormats": { "title": "Export formats", "type": "array", "description": "Files saved to the key-value store (CLEAN.csv / CLEAN.json / CLEAN.xlsx). Excel has Clean, Rejected and Summary tabs.", "items": { "type": "string", "enum": [ "csv", "json", "xlsx" ], "enumTitles": [ "CSV", "JSON", "Excel (.xlsx)" ] }, "default": [ "csv" ] }, "outputCsvDelimiter": { "title": "CSV output delimiter", "enum": [ ",", ";", "\t", "|" ], "type": "string", "description": "Field separator used in CLEAN.csv and REJECTED.csv.", "default": "," }, "csvUtf8Bom": { "title": "Add UTF-8 BOM to CSV", "type": "boolean", "description": "Helps older Excel versions open accents correctly.", "default": false }, "escapeFormulaCells": { "title": "Neutralize spreadsheet formulas in CSV", "type": "boolean", "description": "Prefix text cells starting with = + - @ with an apostrophe (numbers untouched). Changes data, so off by default. XLSX output never stores text as formulas.", "default": false }, "includeFlagsColumn": { "title": "Add '_flags' column", "type": "boolean", "description": "Shows validation flags per row when email/phone checks or the 'keep' policy are used.", "default": true }, "changeLog": { "title": "Write row-level change log", "type": "boolean", "description": "CHANGE_LOG.csv: every changed cell with the rules that changed it.", "default": true }, "changeLogIncludeValues": { "title": "Include values in change log", "type": "boolean", "description": "Untick to log only row/column/rule (no before/after values) if the log is shared.", "default": true }, "maxChangeLogEntries": { "title": "Max change log entries", "minimum": 0, "maximum": 200000, "type": "integer", "description": "Counts stay exact; entries beyond the cap are not written.", "default": 10000 }, "profileColumns": { "title": "Column profiling report", "enum": [ "off", "after", "both" ], "type": "string", "description": "Type, % null, unique count and top values per column (COLUMN_PROFILE.json).", "default": "after" }, "settingsFileUrl": { "title": "Settings file (JSON, optional)", "type": "string", "description": "Upload or link a JSON file with settings, e.g. {\"headerCase\":\"snake_case\",\"numericColumns\":[\"Price\"]}. Values in the file replace the same fields in this form. Source fields cannot be set in it. Same format as the local 'clean_local.py --settings' file.", "default": "" }, "profileName": { "title": "Load saved profile", "type": "string", "description": "Name of a profile saved earlier. Its cleaning settings (sections 2–5) replace the ones in this form.", "default": "" }, "profileJson": { "title": "Inline profile (JSON)", "type": "object", "description": "Paste a profile document {\"profileVersion\":1,\"settings\":{...}} instead of loading by name. Do not set both." }, "saveProfileAs": { "title": "Save these settings as profile", "type": "string", "description": "Letters, digits, . _ - only (max 60). Saved after a successful run.", "default": "" }, "dryRun": { "title": "Dry run (preview)", "type": "boolean", "description": "Process only a small sample, never charge, and mark the result as a preview.", "default": false }, "dryRunSampleSize": { "title": "Dry run sample size", "minimum": 10, "maximum": 1000, "type": "integer", "description": "Rows processed in dry run.", "default": 100 }, "chunkSize": { "title": "Chunk size", "minimum": 100, "maximum": 10000, "type": "integer", "description": "Rows processed per chunk. Keeps memory bounded.", "default": 1000 }, "maxRows": { "title": "Max rows", "minimum": 1, "maximum": 5000000, "type": "integer", "description": "Rows beyond this are not processed.", "default": 500000 }, "maxFileSizeMb": { "title": "Max input size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Larger inputs fail before processing.", "default": 100 }, "maxOutputSizeMb": { "title": "Max output size (MB, per file)", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Processing stops cleanly when exceeded.", "default": 200 }, "timeoutSeconds": { "title": "Timeout (seconds)", "minimum": 30, "maximum": 86400, "type": "integer", "description": "Processing stops cleanly when exceeded.", "default": 3000 }, "memoryLimitMb": { "title": "Memory guard (MB)", "minimum": 0, "maximum": 32768, "type": "integer", "description": "0 = 85% of the run's memory. Processing stops cleanly if exceeded.", "default": 0 } } }, "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 } } } } } } } } } }