{ "openapi": "3.0.1", "info": { "title": "Best Damn PDF Text Extractor", "description": "Extract text, per-page text, metadata and links from any PDF URL as JSON or Markdown, ready for RAG and LLM ingestion. Works with Google Drive and Dropbox links. One flat price per PDF, no per-page fees, failed downloads free.", "version": "0.1", "x-build-id": "OdJevLDLCghFUm1Ro" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/josh99smith~pdf-text-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-josh99smith-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/josh99smith~pdf-text-extractor/runs": { "post": { "operationId": "runs-sync-josh99smith-pdf-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/josh99smith~pdf-text-extractor/run-sync": { "post": { "operationId": "run-sync-josh99smith-pdf-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "One public PDF URL per line (or a JSON array of URLs). Redirects are followed. Duplicates are removed automatically.", "items": { "type": "string" } }, "outputFormat": { "title": "Output format", "enum": [ "text", "markdown", "both" ], "type": "string", "description": "`text` returns the plain text in the `text` field. `markdown` returns a `markdown` field with headings guessed from font sizes and page breaks rendered as horizontal rules (`---`). `both` returns both fields.", "default": "text" }, "perPage": { "title": "Include per-page text", "type": "boolean", "description": "Add a `pages` array with the text and character count of every page. Turn off to keep records smaller when you only need the full text.", "default": true }, "extractLinks": { "title": "Extract links", "type": "boolean", "description": "Collect unique URLs from link annotations and from the text into a `links` array.", "default": true }, "maxPages": { "title": "Max pages per PDF", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Only the first N pages are extracted. `pageCount` always reports the real number of pages.", "default": 500 }, "pageRange": { "title": "Page range", "pattern": "^[0-9,;\\s-]*$", "type": "string", "description": "Only extract these pages (1-based), e.g. `1-5, 8, 12-` (`12-` means to the last page). Leave empty for all pages. Page numbers past the end of a document are ignored; **Max pages per PDF** still caps the total.", "default": "" }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 0, "maximum": 100000, "type": "integer", "description": "When greater than 0, adds a `chunks` array of text pieces of at most this many characters (split on paragraph, line, sentence or word boundaries) ready for embedding in a RAG pipeline. 0 turns chunking off. Typical values: 800-2000. At most 2,000 chunks per PDF.", "default": 0 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 50000, "type": "integer", "description": "How many characters of the previous chunk are repeated at the start of the next one, so that context is not lost at chunk borders. Must be at most half of **Chunk size**. Only used when chunking is on.", "default": 200 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "PDFs larger than this are skipped (reported as `too-large`, not billed). The limit is enforced from the Content-Length header and again while downloading.", "default": 25 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many PDFs to download and parse in parallel. Large PDFs use more memory; lower this if the run hits memory limits.", "default": 5 }, "password": { "title": "PDF password", "type": "string", "description": "User password for password-protected PDFs. Applied to every URL in the run; files that reject it are reported as `encrypted` (not charged). Stored as a secret." }, "timeoutSecs": { "title": "Download timeout (seconds)", "minimum": 5, "maximum": 300, "type": "integer", "description": "Give up on a PDF download after this many seconds.", "default": 60 } } }, "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 } } } } } } } } } }