{ "openapi": "3.0.1", "info": { "title": "PDF Text Extractor - PDF to Text & Markdown for LLM/RAG", "description": "Extract text from PDF files by URL, or from all PDFs linked on a web page. Get full text, Markdown per page, title, dates, page count, table of contents and RAG chunks with page numbers. Detects scanned pages. Fast, no browser. Export JSON/CSV or call via API/MCP.", "version": "1.0", "x-build-id": "3ohRm03at4QjnfvJN" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/teddythebuilder~pdf-text-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-teddythebuilder-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/teddythebuilder~pdf-text-extractor/runs": { "post": { "operationId": "runs-sync-teddythebuilder-pdf-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/teddythebuilder~pdf-text-extractor/run-sync": { "post": { "operationId": "run-sync-teddythebuilder-pdf-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "pdfUrls": { "title": "PDF URLs", "type": "array", "description": "Direct links to PDF files, e.g. https://www.irs.gov/pub/irs-pdf/fw9.pdf. Leave empty if you use 'Web pages with PDF links'.", "default": [ "https://www.irs.gov/pub/irs-pdf/fw9.pdf", "https://www.irs.gov/pub/irs-pdf/fw4.pdf" ], "items": { "type": "string" } }, "pageUrls": { "title": "Web pages with PDF links", "type": "array", "description": "Web pages to scan for links to PDF files (one level), e.g. an investor-relations or downloads page. Every PDF linked there is extracted.", "default": [], "items": { "type": "string" } }, "pdfLinkContains": { "title": "Only PDF links containing", "type": "array", "description": "When scanning web pages, keep only PDF links whose URL or link text contains one of these words, e.g. annual-report or 2025.", "default": [], "items": { "type": "string" } }, "maxPdfs": { "title": "Max PDFs", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop after this many PDFs.", "default": 100 }, "chunkSize": { "title": "RAG chunk size (characters)", "minimum": 0, "maximum": 100000, "type": "integer", "description": "If > 0, adds a 'chunks' array (each chunk with its page number), e.g. 1500 for embeddings. 0 = no chunks.", "default": 0 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 50000, "type": "integer", "description": "Characters repeated from the previous chunk, e.g. 150. At most half the chunk size.", "default": 0 }, "includePlainText": { "title": "Return full plain text", "type": "boolean", "description": "Add a 'text' field with the whole document as plain text (the Markdown field is always returned).", "default": true }, "includePageTexts": { "title": "Return text per page", "type": "boolean", "description": "Add a 'pageTexts' array with one entry per page.", "default": false }, "layoutMode": { "title": "Keep layout (columns, tables)", "type": "boolean", "description": "Preserve the horizontal layout of each page with spaces, which keeps table columns aligned. Slower; off = natural reading order.", "default": false }, "maxPagesPerPdf": { "title": "Max pages per PDF", "minimum": 0, "type": "integer", "description": "Extract only the first N pages of each PDF, e.g. 10 to read summaries cheaply. 0 = all pages.", "default": 0 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Larger files are skipped (free row).", "default": 50 }, "pdfPassword": { "title": "PDF password", "type": "string", "description": "Password for encrypted PDFs, if you have it (the same password is tried on every PDF)." }, "maxConcurrency": { "title": "Parallel downloads", "minimum": 1, "maximum": 10, "type": "integer", "description": "PDFs downloaded and parsed at the same time.", "default": 3 } } }, "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 } } } } } } } } } }