{ "openapi": "3.0.1", "info": { "title": "PDF Table Extractor", "description": "Extract tables from PDF files into clean JSON, CSV, Markdown and Excel-ready rows. Column structure and empty cells are preserved, so every value stays in the column it came from. Works on financial reports, research papers, government statistics and invoices.", "version": "0.0", "x-build-id": "LtQ01RVOHbQYlTzWx" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/practical_ophthalmologist_iuq~pdf-table-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-practical_ophthalmologist_iuq-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/practical_ophthalmologist_iuq~pdf-table-extractor/runs": { "post": { "operationId": "runs-sync-practical_ophthalmologist_iuq-pdf-table-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/practical_ophthalmologist_iuq~pdf-table-extractor/run-sync": { "post": { "operationId": "run-sync-practical_ophthalmologist_iuq-pdf-table-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "pdfUrls" ], "properties": { "pdfUrls": { "title": "PDF URLs", "type": "array", "description": "Direct links to the PDF files you want tables from.", "items": { "type": "string" } }, "strategy": { "title": "Detection strategy", "enum": [ "auto", "lines", "text", "hybrid" ], "type": "string", "description": "auto runs all three detectors and keeps the best result per table.", "default": "auto" }, "minRows": { "title": "Minimum rows", "minimum": 1, "maximum": 100, "type": "integer", "description": "Ignore tables with fewer rows.", "default": 2 }, "minColumns": { "title": "Minimum columns", "minimum": 1, "maximum": 50, "type": "integer", "description": "Ignore tables with fewer columns.", "default": 2 }, "requireCaption": { "title": "Only captioned tables", "type": "boolean", "description": "Return only tables that have a detected caption such as Table 3. Recommended for research papers, annual reports and government publications, where body text and reference lists can otherwise be mistaken for tables. Leave off for invoices, which rarely label their tables.", "default": false }, "minQualityScore": { "title": "Minimum quality score", "minimum": 0, "maximum": 100, "type": "integer", "description": "0-100. Filters out sparse detections.", "default": 25 }, "maxPagesPerPdf": { "title": "Max pages per PDF", "minimum": 0, "type": "integer", "description": "0 means every page.", "default": 0 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Larger PDFs are skipped.", "default": 50 }, "includeMarkdown": { "title": "Include Markdown output", "type": "boolean", "description": "Adds a Markdown table to every result.", "default": true }, "includeCsv": { "title": "Include CSV output", "type": "boolean", "description": "Adds a CSV string to every result.", "default": true } } }, "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 } } }, "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 } } } } } } } } } }