{ "openapi": "3.0.1", "info": { "title": "PDF to Markdown + OCR — Structured Document Extraction", "description": "Convert public PDF URLs into clean structured Markdown. Born-digital pages extract natively; scanned or image-only pages are recovered by a built-in OCR engine — no key or setup required. Per-page mode, confidence and partialFailures for PDF to Markdown and scanned PDF extraction pipelines.", "version": "0.0", "x-build-id": "x2xTjmhesM5nv7an8" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/kaz_kakyo~pdf-structured-ocr/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-kaz_kakyo-pdf-structured-ocr", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/kaz_kakyo~pdf-structured-ocr/runs": { "post": { "operationId": "runs-sync-kaz_kakyo-pdf-structured-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/kaz_kakyo~pdf-structured-ocr/run-sync": { "post": { "operationId": "run-sync-kaz_kakyo-pdf-structured-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Public https links to PDF files. Private/localhost/link-local/RFC1918 targets are rejected (SSRF guard). One document processed per URL.", "items": { "type": "string" } }, "pdfUrl": { "title": "Single PDF URL (optional)", "type": "string", "description": "Optional single public PDF URL. Merged with `pdfUrls` when both are set." }, "maxPages": { "title": "Max pages per PDF", "minimum": 1, "maximum": 500, "type": "integer", "description": "Cap pages processed per document (default 50). Extra pages are skipped and listed in `partialFailures`.", "default": 50 }, "ocr": { "title": "OCR mode", "enum": [ "auto", "never", "always" ], "type": "string", "description": "`auto` (default): OCR only low-text / image-only / rotated pages. `always`: OCR every page via the managed OCR engine. `never`: native extraction only.", "default": "auto" }, "maxOcrPages": { "title": "Max OCR pages per run", "minimum": 1, "maximum": 200, "type": "integer", "description": "Caps how many pages this run may send to OCR. Default 100, hard ceiling 200. Protects shared OCR capacity across users. Native (born-digital) extraction is unaffected.", "default": 100 }, "ocrMaxWaitSecs": { "title": "OCR max wait (seconds)", "minimum": 1, "maximum": 900, "type": "integer", "description": "Maximum time to wait for an OCR job to finish (poll every 5s). Default 300, max 900. On timeout, OCR-routed pages are marked `unavailable` (reason `ocr_timeout`) and not charged.", "default": 300 } } }, "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 } } } } } } } } } }