{ "openapi": "3.0.1", "info": { "title": "PDF Tools (Merge / Split / Compress / OCR / Watermark)", "description": "All-in-one PDF processor: merge multiple PDFs, split by page ranges, compress file size, extract text, OCR scanned documents (Tesseract), add text watermarks, rotate pages, and read metadata. Accepts PDF URLs or Key-Value Store keys.", "version": "0.1", "x-build-id": "djimrF61TQiGFKcMz" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/mrkrokko~pdf-tools/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-mrkrokko-pdf-tools", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/mrkrokko~pdf-tools/runs": { "post": { "operationId": "runs-sync-mrkrokko-pdf-tools", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/mrkrokko~pdf-tools/run-sync": { "post": { "operationId": "run-sync-mrkrokko-pdf-tools", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "operation" ], "properties": { "operation": { "title": "Operation", "enum": [ "merge", "split", "compress", "extractText", "ocr", "watermark", "rotate", "metadata", "pageCount" ], "type": "string", "description": "Which PDF operation to perform.", "default": "pageCount" }, "pdfUrls": { "title": "PDF file URLs", "minItems": 1, "type": "array", "description": "Direct-download URLs to PDF files. For merge, order matters. API callers may also send a single 'pdfUrl' or Apify-style 'startUrls'.", "items": { "type": "string" } }, "pdfKeys": { "title": "PDF Key-Value Store keys", "type": "array", "description": "Optional keys of PDF records stored in the run's default Key-Value Store. Useful for API workflows that upload files before running the Actor.", "items": { "type": "string" } }, "pageRanges": { "title": "Page ranges (split/extract)", "type": "string", "description": "Comma-separated page ranges, e.g. '1-3,5,8-10'. 1-indexed. Used by split and extractText." }, "watermarkText": { "title": "Watermark text", "type": "string", "description": "Text to overlay as watermark (operation=watermark)." }, "watermarkOpacity": { "title": "Watermark opacity", "minimum": 0.01, "maximum": 1, "type": "number", "description": "Opacity of the watermark (0.0 = invisible, 1.0 = fully opaque).", "default": 0.15 }, "watermarkFontSize": { "title": "Watermark font size", "minimum": 10, "maximum": 200, "type": "integer", "description": "Font size in points for the watermark text.", "default": 60 }, "watermarkAngle": { "title": "Watermark rotation angle (degrees)", "minimum": 0, "maximum": 360, "type": "integer", "description": "Angle in degrees to rotate the watermark text.", "default": 45 }, "rotateAngle": { "title": "Rotation angle (degrees)", "enum": [ "90", "180", "270" ], "type": "string", "description": "Clockwise rotation angle for pages. Must be a multiple of 90.", "default": "90" }, "ocrLanguages": { "title": "OCR languages", "type": "string", "description": "Tesseract language codes, e.g. 'eng', 'deu', 'eng+deu'. Pre-installed: eng, deu, fra, spa, ita, por.", "default": "eng" }, "compressionLevel": { "title": "Compression level", "enum": [ "low", "medium", "high" ], "type": "string", "description": "How aggressively to compress.", "default": "medium" }, "outputFileName": { "title": "Output file name", "type": "string", "description": "Base name for the output file in Key-Value Store (without .pdf extension). Auto-generated if empty." } } }, "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 } } } } } } } } } }