{ "openapi": "3.0.1", "info": { "title": "PDF Text Extractor: Markdown, Tables & OCR", "description": "Turn PDF files at public URLs into clean text or Markdown with headings, lists and tables, plus metadata. Scanned pages are read with OCR. Pay per page that gave text, with a lower price for text-layer pages and nothing for files that fail.", "version": "1.0", "x-build-id": "b8q4k7MMaixZKlNC6" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/private_image_hg9~pdf-text-table-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-private_image_hg9-pdf-text-table-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/private_image_hg9~pdf-text-table-extractor/runs": { "post": { "operationId": "runs-sync-private_image_hg9-pdf-text-table-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/private_image_hg9~pdf-text-table-extractor/run-sync": { "post": { "operationId": "run-sync-private_image_hg9-pdf-text-table-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "fileUrls" ], "properties": { "fileUrls": { "title": "PDF addresses", "type": "array", "description": "One public http(s) address of a PDF file per line. Each file gets one row (or one row per page with \"One row per page\"). Repeats are read once. Addresses that answer with a PDF under another content type, or after redirects, are fine.", "items": { "type": "string" } }, "outputFormat": { "title": "Output format", "enum": [ "markdown", "text", "both" ], "type": "string", "description": "Markdown keeps headings, lists and tables (good for AI and search tools). Text is the plain text layer in reading order. Both gives you both fields.", "default": "markdown" }, "extractTables": { "title": "Extract tables", "type": "boolean", "description": "Find ruled tables (tables drawn with lines) and return their cells in the tables field, and as Markdown tables in the Markdown. Turn off for speed if you only need the text.", "default": true }, "ocr": { "title": "OCR for scanned pages", "enum": [ "auto", "always", "off" ], "type": "string", "description": "Auto reads with OCR only pages that are a picture with no usable text layer. Always reads every page with OCR (for PDFs whose text layer is broken). Off never uses OCR. OCR pages cost more than text-layer pages.", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "string", "description": "Languages of the scanned text, as Tesseract codes joined with +: eng (English), deu (German), fra (French), spa (Spanish), ita (Italian), por (Portuguese), nld (Dutch). For example deu+eng.", "default": "eng" }, "pageRange": { "title": "Pages to read", "type": "string", "description": "Optional. Page numbers and ranges for every file, like 1-5,9 or 10- (to the end). Leave empty to read every page." }, "maxPagesPerFile": { "title": "Max pages per file", "minimum": 1, "maximum": 5000, "type": "integer", "description": "The most pages read from one file (after the page range). Pages past this are not read or charged.", "default": 500 }, "splitPages": { "title": "One row per page", "type": "boolean", "description": "Save one row for each page instead of one row for each file. Handy for chunking documents for AI and search.", "default": false }, "maxConcurrency": { "title": "Files at once", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many files are downloaded and read in parallel. Requests to the same website still go one at a time.", "default": 4 } } }, "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 } } } } } } } } } }