{ "openapi": "3.0.1", "info": { "title": "PDF Text and Table Extractor with OCR", "description": "Extract text, tables and Markdown from PDF files in bulk. Automatic OCR fallback for scanned pages, page ranges and URL lists. Clean output for RAG, search and data pipelines.", "version": "0.0", "x-build-id": "cvqbq4VHwZEgdOtw0" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/tiger19935~pdf-text-table-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-tiger19935-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/tiger19935~pdf-text-table-extractor/runs": { "post": { "operationId": "runs-sync-tiger19935-pdf-text-table-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/tiger19935~pdf-text-table-extractor/run-sync": { "post": { "operationId": "run-sync-tiger19935-pdf-text-table-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "PDF URLs", "type": "array", "description": "Direct links to PDF files, one per row. Public URLs only (the link must return the PDF itself, not a web page).", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "pageRange": { "title": "Page range", "type": "string", "description": "Which pages to read, for example 1-5 or 1,3,10-20 or 5- (page 5 to the end). Leave empty for all pages. Applied to every PDF." }, "outputMode": { "title": "Output format", "enum": [ "perPage", "perDocument" ], "type": "string", "description": "One dataset row per page (best for RAG chunking and search) or one row per document (full text, all tables and page list in one record).", "default": "perPage" }, "extractTables": { "title": "Detect tables", "type": "boolean", "description": "Find tables in the page layout and return them as arrays of rows. Works on PDFs with real text columns; for scanned pages tables are best-effort.", "default": true }, "includeMarkdown": { "title": "Return Markdown", "type": "boolean", "description": "Add a cleaned Markdown version of each page: paragraphs joined, headings marked, tables as Markdown tables.", "default": true }, "ocrFallback": { "title": "OCR for scanned pages", "type": "boolean", "description": "Run OCR on pages that have no text layer (scanned documents, photos of paper). OCR pages are billed at the OCR page price.", "default": true }, "forceOcr": { "title": "Force OCR on every page", "type": "boolean", "description": "Ignore the text layer and OCR all pages. Use it when the embedded text is garbled. Slower and billed at the OCR page price.", "default": false }, "ocrLanguages": { "title": "OCR languages", "type": "string", "description": "Tesseract language codes joined with a plus sign, for example eng or eng+deu. Available: eng, deu, fra, spa, ita, por, rus, ukr, pol, nld, tur, ara, chi_sim, chi_tra, jpn, kor, hin, ces, swe, heb, vie, tha, ron.", "default": "eng" }, "ocrDpi": { "title": "OCR resolution (DPI)", "minimum": 100, "maximum": 400, "type": "integer", "description": "Rendering resolution for OCR. 200 is a good balance, 300 helps with small print.", "default": 200 }, "maxOcrPagesPerPdf": { "title": "Max OCR pages per PDF", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Safety limit for OCR pages in one PDF.", "default": 100 }, "maxPagesPerPdf": { "title": "Max pages per PDF", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Only the first N selected pages of each PDF are processed.", "default": 200 }, "maxConcurrency": { "title": "Parallel PDFs", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many PDFs to process at the same time. Raise the actor memory for values above 3.", "default": 3 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 300, "type": "integer", "description": "PDFs larger than this are skipped.", "default": 100 } } }, "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 } } } } } } } } } }