{ "openapi": "3.0.1", "info": { "title": "PDF Text & Table Extractor with CSV Tables + OCR", "description": "Extract text, RAG-ready markdown, and tables from PDF URLs. Every detected table becomes its own CSV-ready dataset record. No OCR; scanned pages are flagged, never guessed.", "version": "0.1", "x-build-id": "kS9cco9lNEAUCuB5U" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/inn_corp~pdf-text-table-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-inn_corp-pdf-text-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/inn_corp~pdf-text-table-extractor/runs": { "post": { "operationId": "runs-sync-inn_corp-pdf-text-table-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/inn_corp~pdf-text-table-extractor/run-sync": { "post": { "operationId": "run-sync-inn_corp-pdf-text-table-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 PDFs to process. Supply only documents you have the right to access: each is fetched with a plain HTTP GET, and the Actor never bypasses logins, paywalls, or DRM.", "items": { "type": "string" } }, "pageRange": { "title": "Page range", "type": "string", "description": "Pages to process, 1-based, like \"1-5,8,12-\" (\"12-\" means page 12 to the end). Leave empty for all pages." }, "outputMode": { "title": "Output mode", "enum": [ "text", "tables", "both", "markdown-only" ], "type": "string", "description": "\"Text and tables\" (default) writes page records with text, markdown, and tables. \"Text only\" skips table detection. \"Tables only\" writes just table records. \"Markdown only\" writes page records whose markdown embeds the detected tables, without the raw text field.", "default": "both" }, "tablesAsRecords": { "title": "Each table as its own record", "type": "boolean", "description": "When on, every detected table also becomes its own dataset record with rows, rowCount, columnCount, and a ready-to-save CSV string.", "default": true }, "maxPages": { "title": "Max pages per PDF", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Processing stops after this many pages per document.", "default": 200 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 100, "type": "integer", "description": "Documents over this size are rejected with a \"too-large\" summary record, checked with a HEAD request before any download, and are never charged.", "default": 50 }, "timeoutPerPdfSecs": { "title": "Timeout per PDF (seconds)", "minimum": 5, "maximum": 600, "type": "integer", "description": "Wall-clock budget per document, download included. When it runs out, the pages already extracted are kept and the summary record says \"timeout\".", "default": 120 }, "tableStrategy": { "title": "Table detection strategy", "enum": [ "lines", "text" ], "type": "string", "description": "Table detection is heuristic and imperfect. \"Ruled lines\" finds tables drawn with visible lines; \"Text alignment\" infers cells from how the text lines up. If results look wrong, try the other strategy.", "default": "lines" }, "enableOcr": { "title": "Enable OCR for scanned pages", "type": "boolean", "description": "Off by default: nothing changes unless you turn this on. When on, any page whose native text is empty or near-empty is rendered to an image and read with Tesseract OCR; the result lands in a separate ocrText field (never blended into text or markdown) and is billed as an additional page-ocr event on top of the normal page-extracted charge. OCR quality varies with scan quality and is English-only by default; it is not as reliable as native text extraction.", "default": false } } }, "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 } } } } } } } } } }