{ "openapi": "3.0.1", "info": { "title": "Business PDF Field Extractor", "description": "Give PDF addresses and get fixed fields back: invoice and purchase order numbers, dates, parties, totals, and line items, plus contract parties, dates, term, renewal, notice, and governing law. Reads scans with OCR. No AI and no API key.", "version": "0.1", "x-build-id": "hw5ICwThSvgIhTn8q" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/mambalabs~business-pdf-field-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-mambalabs-business-pdf-field-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/mambalabs~business-pdf-field-extractor/runs": { "post": { "operationId": "runs-sync-mambalabs-business-pdf-field-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/mambalabs~business-pdf-field-extractor/run-sync": { "post": { "operationId": "run-sync-mambalabs-business-pdf-field-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "pdf_urls": { "title": "PDF addresses", "type": "array", "description": "Web addresses of PDF files, up to 1,000. Each file up to 40 MB. The address must answer without a login. In Clay, put the column in a one item list.", "items": { "type": "string" } }, "pdf_file": { "title": "Or upload one PDF", "type": "string", "description": "Optional. One PDF file from your computer, stored in your Apify account." }, "document_type": { "title": "Document type", "type": "string", "description": "auto (default) works it out per file. Set invoice, purchase_order, or contract to read every file as that type.", "default": "auto" }, "date_order": { "title": "Date order", "type": "string", "description": "How to read a date such as 03/04/2025 when both readings are valid. mdy (default) reads March 4, dmy reads 3 April. Unambiguous dates ignore this.", "default": "mdy" }, "read_scans": { "title": "Read scanned pages", "type": "string", "description": "yes (default): a page with no text layer goes through OCR, charged per page. no: those pages are skipped and the row says so.", "default": "yes" }, "ocr_language": { "title": "OCR language", "type": "string", "description": "Language of scanned pages: eng (default), deu, fra, spa, nld, ita, or por.", "default": "eng" }, "max_pages": { "title": "Maximum pages per file", "type": "string", "description": "Pages to read per file, up to 500. Default 50.", "default": "50" }, "max_ocr_pages": { "title": "Maximum OCR pages per file", "type": "string", "description": "Scanned pages to read per file, up to 100. Default 10. This caps the OCR charge per file.", "default": "10" }, "max_documents": { "title": "Maximum documents", "type": "string", "description": "Files to read in this run, up to 1,000. Default 100.", "default": "100" }, "line_item_rows": { "title": "Line items as rows", "type": "string", "description": "yes (default): each line item is also its own free row, which suits CSV and Clay. no: line items stay in the line_items field only.", "default": "yes" }, "include_text": { "title": "Include full text", "type": "string", "description": "yes: add the document text to the row, up to 200,000 characters. Default no.", "default": "no" }, "max_charge_usd": { "title": "Maximum charge for this run (USD)", "type": "string", "description": "Optional. The run stops before a charge that would pass this amount. Summary rows are always returned." }, "source_tag": { "title": "Source tag", "type": "string", "description": "Internal attribution tag. Leave empty." } } }, "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 } } } } } } } } } }