{ "openapi": "3.0.1", "info": { "title": "PDF Text Extractor: PDF URL to Text and Markdown per Page", "description": "Convert PDF links to clean text and Markdown in reading order, per document or per page, with title, author, dates and page count. Headings and lists kept for LLM and RAG pipelines. $2 per 1,000 PDFs, failed files free, no OCR needed for digital PDFs.", "version": "1.0", "x-build-id": "WkHW7gJGTXeQcvxDp" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/pistachio_implementation~pdf-text-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-pistachio_implementation-pdf-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/pistachio_implementation~pdf-text-extractor/runs": { "post": { "operationId": "runs-sync-pistachio_implementation-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/pistachio_implementation~pdf-text-extractor/run-sync": { "post": { "operationId": "run-sync-pistachio_implementation-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": [ "urls" ], "properties": { "urls": { "title": "PDF URLs", "type": "array", "description": "Direct links to PDF files. Any public link works, including files you uploaded to an Apify key value store.", "items": { "type": "string" } }, "outputMode": { "title": "One row per", "enum": [ "document", "pages" ], "type": "string", "description": "\"document\" returns one row per PDF with the whole text. \"pages\" returns one row per page (handy for citations and chunking). The price is per PDF either way.", "default": "document" }, "includeText": { "title": "Include plain text", "type": "boolean", "description": "Plain text in reading order with paragraph breaks.", "default": true }, "includeMarkdown": { "title": "Include Markdown", "type": "boolean", "description": "Markdown with headings detected from font size, bullet lists, and pages separated by a rule.", "default": true }, "maxPagesPerPdf": { "title": "Maximum pages per PDF", "minimum": 1, "maximum": 3000, "type": "integer", "description": "Read at most this many pages from each file. Rows say when a file was cut.", "default": 300 }, "maxFileSizeMb": { "title": "Maximum file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Files larger than this are skipped for free. For files over 50 MB give the run 1 GB of memory or more.", "default": 50 }, "maxTextLength": { "title": "Maximum text length", "minimum": 0, "type": "integer", "description": "Cut text and Markdown in each row to this many characters. 0 means no limit.", "default": 0 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip files that the site's robots.txt closes to automated tools. Skipped files are free.", "default": true }, "maxConcurrency": { "title": "Parallel downloads", "minimum": 1, "maximum": 5, "type": "integer", "description": "How many PDFs to work on at once. Downloads from one host are always spaced one second apart.", "default": 2 } } }, "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 } } } } } } } } } }