{ "openapi": "3.0.1", "info": { "title": "PDF Table Extractor - PDF to Excel, CSV & JSON (validated rows)", "description": "Extract tables from PDF price lists, invoices and order confirmations into clean rows for Excel, CSV or JSON. Maps your columns, reads EU and US numbers, checks totals and duplicates, returns rejected rows with reasons. Pay only for accepted rows.", "version": "0.0", "x-build-id": "AX4vJMpQbl6RG5B5c" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/first_watch~pdf-table-extraction/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-first_watch-pdf-table-extraction", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/first_watch~pdf-table-extraction/runs": { "post": { "operationId": "runs-sync-first_watch-pdf-table-extraction", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/first_watch~pdf-table-extraction/run-sync": { "post": { "operationId": "run-sync-first_watch-pdf-table-extraction", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "documents", "targetSchema" ], "properties": { "documents": { "title": "Documents", "minItems": 1, "maxItems": 50, "type": "array", "description": "1-50 documents. Each needs a unique 'id' and exactly one source: 'base64Document' (PDF bytes as base64; a data: URL prefix or line breaks are fine), 'url' (public https:// link to a PDF), 'keyValueStoreKey' (PDF record in the run's default key-value store), or inline 'records', 'csv', 'json', 'html' (first table) or 'text' (tab, pipe, semicolon or comma separated). Optional: 'delimiter' for csv/text and 'pageRange' {from: 1, to: 3} for PDFs. Inline and base64 sources are processed offline.", "items": { "type": "object" } }, "targetSchema": { "title": "Target schema", "type": "object", "description": "Canonical columns every row must satisfy. 'columns': list of {name, type (string, number, integer, boolean, or date as YYYY-MM-DD), required, aliases}. Optional: 'uniqueBy' (column names that must be unique together), 'arithmeticChecks' (list of {operands, operator: sum, subtract or multiply, result, tolerance (default 0.01)}) and 'allowUnexpectedColumns' (default false: rows with extra columns are rejected)." }, "options": { "title": "Options", "type": "object", "description": "caseInsensitiveHeaders (default true), trimValues (default true), emptyStringIsNull (default true), failOnAnyRejectedRow (default false; true = all-or-nothing: nothing is delivered or charged if any row is rejected), numberFormat ('auto', 'en' for 1,234.56 or 'eu' for 1.234,56; default auto), dateFormat ('auto', 'DMY', 'MDY' or 'YMD'; default auto) and ocrAllowed (must stay false; there is no OCR).", "default": { "caseInsensitiveHeaders": true, "trimValues": true, "emptyStringIsNull": true, "failOnAnyRejectedRow": false, "numberFormat": "auto", "dateFormat": "auto" } } } }, "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 } } } } } } } } } }