{ "openapi": "3.0.1", "info": { "title": "PDF Text Extractor with OCR", "description": "PDF to text: extract clean text from PDF files by URL or upload. Reads the PDF's own text layer and runs OCR only on scanned pages. Per-page output for RAG and AI pipelines. Blank and failed pages are free.", "version": "0.0", "x-build-id": "tunXdae60b1fOfduo" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ridgeline_apps~pdf-text-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ridgeline_apps-pdf-text-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ridgeline_apps~pdf-text-extractor/runs": { "post": { "operationId": "runs-sync-ridgeline_apps-pdf-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ridgeline_apps~pdf-text-extractor/run-sync": { "post": { "operationId": "run-sync-ridgeline_apps-pdf-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "files" ], "properties": { "files": { "title": "PDF files", "type": "array", "description": "Paste PDF URLs (one per line) or upload PDF files. Each PDF becomes one result, or one result per page if you choose page output." }, "ocrMode": { "title": "OCR for scanned pages", "enum": [ "auto", "never", "always" ], "type": "string", "description": "Auto reads the PDF's own text and runs OCR only on pages that are scanned images. Never skips OCR entirely (cheapest). Always runs OCR on every page.", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Languages used when a page needs OCR. Pick every language that appears in your documents.", "items": { "type": "string", "enum": [ "eng", "spa", "fra", "deu", "por", "ita", "nld" ], "enumTitles": [ "English", "Spanish", "French", "German", "Portuguese", "Italian", "Dutch" ] }, "default": [ "eng" ] }, "outputMode": { "title": "Output", "enum": [ "document", "page" ], "type": "string", "description": "One result per PDF (with page details inside), or one result per page (best for RAG, embeddings and spreadsheets).", "default": "document" }, "includePageDetails": { "title": "Include per-page details", "type": "boolean", "description": "In 'one result per PDF' mode, also include a list of pages with their text, method (text or OCR) and OCR confidence.", "default": true }, "pageFrom": { "title": "First page", "minimum": 1, "type": "integer", "description": "Start at this page (1 = first page).", "default": 1 }, "pageTo": { "title": "Last page", "minimum": 1, "type": "integer", "description": "Stop at this page. Leave empty to read to the end." }, "maxPagesPerPdf": { "title": "Max pages per PDF", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Safety limit on pages read from each PDF.", "default": 500 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Larger files are skipped and not charged.", "default": 50 }, "ocrDpi": { "title": "OCR resolution (DPI)", "minimum": 150, "maximum": 400, "type": "integer", "description": "Higher values read small print better but run slower. 300 suits most scans.", "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 }, "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 } } } } } } } } } }