{ "openapi": "3.0.1", "info": { "title": "PDF Text Extractor: OCR, Markdown, Page Checks", "description": "Extract text from PDF URLs or your own files, with OCR for scanned pages and a verdict on every page. Each row carries the full text or Markdown, page count, word count, PDF type, and flags for wrong or hidden text layers. Page ranges and passwords work. Failed files are free.", "version": "0.1", "x-build-id": "cSKK7wGYpThA4zVn2" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/pradio~pdf-text-verifier/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-pradio-pdf-text-verifier", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/pradio~pdf-text-verifier/runs": { "post": { "operationId": "runs-sync-pradio-pdf-text-verifier", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/pradio~pdf-text-verifier/run-sync": { "post": { "operationId": "run-sync-pradio-pdf-text-verifier", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "URLs", "type": "array", "description": "PDF document URLs to verify and extract; one data row per document. Give URLs here, files in base64Pdfs, or both", "items": { "type": "string" } }, "base64Pdfs": { "title": "PDF files as base64", "type": "array", "description": "your own PDF files sent inline, for files that are not at a public URL: a list of objects such as {\"name\": \"invoice-17.pdf\", \"data\": \"\"}, with an optional \"password\" per file. Each file gets one row carrying its name in file_name; an entry that is not valid base64 or not a PDF is an uncharged miss row naming it. Suited to small files, since the whole run input has a size limit" }, "outputFormat": { "title": "Output format", "enum": [ "text", "markdown", "both" ], "type": "string", "description": "which whole-document text columns each row carries: text (plain text, the default), markdown (headings, paragraphs and list items inferred from the layout) or both. Per-page text in page_verdicts is the same in every format", "default": "text" }, "pageRange": { "title": "Page range", "type": "string", "description": "the pages to read in every document, such as 1-5,8 or 10- (page 10 to the end); leave empty to read every page. A value that is not a page range makes every entry an uncharged bad_input miss that says why" }, "pdfPassword": { "title": "PDF password", "type": "string", "description": "the password that opens your password-protected PDFs; used for every document in the run unless an entry carries its own password. A file that needs a password and gets none, or the wrong one, is an uncharged miss row that says so" }, "ocrLanguage": { "title": "OCR Language", "type": "string", "description": "the language OCR reads where a page's text layer fails or hides text; a Tesseract code such as eng, deu or fra" }, "verifyPages": { "title": "Verify every page", "type": "boolean", "description": "render each page and check its embedded text against what the page actually shows; catches wrong and hidden layers the statistics check cannot see; a second charge, page-verified, applies per verified page", "default": false }, "maxItems": { "title": "Maximum items", "minimum": 1, "type": "integer", "description": "the most rows one run returns, a failed entry's status row included; rows come back in input order; entries past the cap are not fetched or read, so nothing is charged for them, not even a verified page, and the run log says the run was capped", "default": 100 }, "maxPagesPerDocument": { "title": "Maximum pages per document", "minimum": 1, "type": "integer", "description": "the most pages one document contributes; the document is marked pages_truncated when it has more, and under verifyPages the cap also bounds page-verified charges per document", "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 } } } } } } } } } }