{ "openapi": "3.0.1", "info": { "title": "PDF Text Extractor: Markdown & Metadata | $1.00 per 1,000 PDFs", "description": "Extract the text of PDF files page by page, as plain text or as Markdown with headings, bold, lists and paragraphs, ready for LLM and search pipelines. Each PDF also gives its page count, title, author, dates and other metadata. Links or uploads. Batch mode: process up to 1000 items per run.", "version": "0.1", "x-build-id": "SWTWUy0cpWs3BcOnx" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/v0iddo~mint-pdf-text-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-v0iddo-mint-pdf-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/v0iddo~mint-pdf-text-extractor/runs": { "post": { "operationId": "runs-sync-v0iddo-mint-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/v0iddo~mint-pdf-text-extractor/run-sync": { "post": { "operationId": "run-sync-v0iddo-mint-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", "properties": { "file_url": { "title": "File URL", "type": "string", "description": "Public http(s) URL of the file. The PDF: base64 string (or data: URI) or {\"url\": \"https://...\"}. Up to 10 MB." }, "file_urls": { "title": "File URLs (bulk)", "type": "array", "description": "Many files in one run: one public http(s) URL per line, up to 1000. Each file is processed on its own with the options below and gives its own row.", "items": { "type": "string" } }, "file_text": { "title": "File (text)", "type": "string", "description": "The file content pasted as text. Use this or file_url." }, "file_base64": { "title": "File (base64)", "type": "string", "description": "The file content as base64 (or a data: URI). Use this or file_url." }, "pages": { "title": "Pages", "maxLength": 1000, "type": "string", "description": "Pages to extract, e.g. '1-3,7' or '5-' (default: all pages)." }, "layout": { "title": "Layout", "type": "boolean", "description": "Preserve the visual layout (columns, spacing) instead of reading order.", "default": false }, "format": { "title": "Output format", "enum": [ "text", "markdown" ], "type": "string", "description": "text: the plain text of each page. markdown: headings, bold and italic, lists and paragraphs as Markdown, page headers and footers that repeat on most pages left out (layout does not apply).", "default": "text" }, "items": { "title": "Batch items", "type": "array", "description": "Optional. A list of input objects with the same fields as above; every object is processed in its own right and the top-level fields act as shared defaults. Leave empty to process the single input above (up to 1000 items per run)." } } }, "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 } } } } } } } } } }