{ "openapi": "3.0.1", "info": { "title": "PDF Table Extractor: PDF to Excel & CSV Converter with OCR", "description": "Use this to extract every table from PDF files into Excel and CSV (PDF to Excel converter, OCR for scans). Input: PDF URLs or uploads plus optional page ranges. Output: one row per table with pages, header, row and column counts and cell data, plus Excel and CSV files.", "version": "0.1", "x-build-id": "zlPKebbvs0Ulx2sUb" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/pandadad0214~pdf-table-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-pandadad0214-pdf-table-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/pandadad0214~pdf-table-extractor/runs": { "post": { "operationId": "runs-sync-pandadad0214-pdf-table-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/pandadad0214~pdf-table-extractor/run-sync": { "post": { "operationId": "run-sync-pandadad0214-pdf-table-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "pdfUrls": { "title": "PDF URLs", "type": "array", "description": "Direct links to PDF files. Google Drive and Dropbox share links are converted to direct downloads automatically. Up to 150 MB per file.", "items": { "type": "string" } }, "pdfFiles": { "title": "Upload PDFs", "type": "array", "description": "Or upload PDFs from your computer. They are stored in a key-value store in your Apify account." }, "pdfStore": { "title": "Key-value store with PDFs", "type": "string", "description": "Optional. Pick a key-value store in your account that holds PDFs. The Actor gets read access to this store only." }, "pdfStoreKeys": { "title": "Record keys in that store", "type": "array", "description": "Optional. Keys of the PDFs to process (e.g. REPORT.pdf). Leave empty to process every PDF record in the store (up to 50).", "items": { "type": "string" } }, "pages": { "title": "Pages", "type": "string", "description": "Optional. Only these pages, e.g. 1-5, 8, 12-end. Leave empty for all pages (up to the page limit below)." }, "maxPagesPerPdf": { "title": "Maximum pages per PDF", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Caps cost and run time on very long documents. You pay per page analysed. Whole number, 1 to 2,000 pages; default 100.", "default": 100 }, "detection": { "title": "Table detection", "enum": [ "auto", "lattice", "stream" ], "type": "string", "description": "Auto tries ruled-grid detection first and switches to whitespace (column alignment) detection when that recovers more of the table. Pick one mode if you know your PDF's style.", "default": "auto" }, "headerDetection": { "title": "Header row", "enum": [ "auto", "firstRow", "none" ], "type": "string", "description": "Auto finds header rows above the first data row (multi-line headers are joined). First row = always use row 1. None = generic Column 1, Column 2… names.", "default": "auto" }, "mergeWrappedRows": { "title": "Merge wrapped rows", "type": "boolean", "description": "Join labels that wrap onto a second line back into one row, so numbers stay on the right line. Default: on.", "default": true }, "mergeAcrossPages": { "title": "Join tables that continue on the next page", "type": "boolean", "description": "When a table carries on over a page break with the same columns, output it as one table with a page range. Default: on.", "default": true }, "numbersAsNumbers": { "title": "Numbers as numbers in Excel", "type": "boolean", "description": "Write 1,234 / (56) / 4.2% as real Excel numbers (parentheses = negative) so you can sum and chart them. CSV and dataset keep the text exactly as printed. Default: on.", "default": true }, "ocrScannedPages": { "title": "OCR scanned pages (beta)", "type": "boolean", "description": "Pages with no text layer (scans, photos) are always detected. Off (default): they are skipped, listed in SUMMARY and on the Index sheet, and cost nothing. On: they are read with Tesseract OCR (English) and their tables are marked 'verify'. OCR is slow (about a minute per page) and can misread digits and dot leaders, so use it for clean scans and check the numbers.", "default": false }, "maxOcrPagesPerPdf": { "title": "Maximum OCR pages per PDF", "minimum": 0, "maximum": 100, "type": "integer", "description": "OCR has its own cap because it is slow and priced per page. Extra scanned pages are flagged, not charged. Whole number, 0 to 100 pages; default 10.", "default": 10 }, "pdfPassword": { "title": "PDF password", "type": "string", "description": "Optional. Only for password-protected PDFs you are allowed to open." } } }, "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 } } } } } } } } } }