{ "openapi": "3.0.1", "info": { "title": "PDF to JSON Parser", "description": "Convert PDF documents into structured JSON. Extracts text, tables, and fields from any PDF URL, and can optionally run an AI structuring pass that turns raw text into clean, organized JSON ready for automation or analysis. No API key needed.", "version": "0.1", "x-build-id": "1W30bNMdp7Crb0aPi" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/jungle_synthesizer~pdf-to-json-parser/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-jungle_synthesizer-pdf-to-json-parser", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/jungle_synthesizer~pdf-to-json-parser/runs": { "post": { "operationId": "runs-sync-jungle_synthesizer-pdf-to-json-parser", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/jungle_synthesizer~pdf-to-json-parser/run-sync": { "post": { "operationId": "run-sync-jungle_synthesizer-pdf-to-json-parser", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "sp_intended_usage", "sp_improvement_suggestions", "pdfUrls" ], "properties": { "sp_intended_usage": { "title": "What is the intended usage of this data?", "minLength": 1, "type": "string", "description": "What will this data feed? E.g. lead lists, KYB checks, price tracking." }, "sp_improvement_suggestions": { "title": "How can we improve this crawler for you?", "minLength": 1, "type": "string", "description": "Provide any feedback or suggestions for improvements." }, "sp_contact": { "title": "Contact email (optional)", "minLength": 1, "type": "string", "description": "We'll personally help with your use case. No spam." }, "pdfUrls": { "title": "PDF URLs", "type": "array", "description": "List of public PDF URLs to process. Each URL must be directly downloadable (no login required). Max file size: 50 MB per PDF.", "items": { "type": "string" } }, "aiStructuring": { "title": "AI Structuring", "type": "boolean", "description": "Turn raw text into structured JSON using AI. Costs more per PDF.", "default": false }, "extractionPrompt": { "title": "Extraction Prompt", "type": "string", "description": "Custom prompt for the AI structuring pass. Tells the model what fields to extract and how to structure the output JSON. Leave blank to use the default prompt (general-purpose document extraction: title, author, summary, key_fields, tables).", "default": "" }, "ocr": { "title": "OCR (scanned PDFs)", "type": "boolean", "description": "Read scanned or photographed PDFs that have no usable text layer. Charged per page converted, on top of the per-PDF rate. Leave off for normal PDFs — they already extract for free.", "default": false }, "ocrMaxPages": { "title": "OCR Page Limit", "minimum": 0, "type": "integer", "description": "Maximum pages to OCR per PDF. Scanned documents are often long while the details you want sit on the first page or two, and every page is charged, so this caps the cost. Set to 0 to convert the whole document.", "default": 5 }, "maxItems": { "title": "Max Items", "type": "integer", "description": "Maximum number of PDFs to process per run.", "default": 15 } } }, "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 } } } } } } } } } }