{ "openapi": "3.0.1", "info": { "title": "PDF to Text & Markdown Converter (Metadata, Tables)", "description": "Convert PDF URLs to clean Markdown or plain text for LLMs, RAG and search: headings, paragraphs, lists, best-effort tables, title/author/date metadata, page count and word count. Fast, no OCR. Pay only for PDFs with extracted text.", "version": "0.1", "x-build-id": "IFjPNdzcZtYLcwzib" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/blond_terrarium~pdf-to-text-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-blond_terrarium-pdf-to-text-markdown", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/blond_terrarium~pdf-to-text-markdown/runs": { "post": { "operationId": "runs-sync-blond_terrarium-pdf-to-text-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/blond_terrarium~pdf-to-text-markdown/run-sync": { "post": { "operationId": "run-sync-blond_terrarium-pdf-to-text-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "PDF URLs", "type": "array", "description": "Direct links to PDF files (any URL that returns a PDF, also without .pdf in the name). One row per document.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "outputFormat": { "title": "Output format", "enum": [ "markdown", "text", "both" ], "type": "string", "description": "Markdown keeps structure (good for LLMs/RAG). Plain text is paragraphs only.", "default": "markdown" }, "pageRange": { "title": "Page range", "pattern": "^\\s*$|^\\s*\\d*\\s*-?\\s*\\d*\\s*(,\\s*\\d*\\s*-?\\s*\\d*\\s*)*$", "type": "string", "description": "Optional, e.g. '1-5', '1,3,10-12' or '20-' (from page 20 to the end). Empty = all pages." }, "maxPagesPerDoc": { "title": "Max pages per document", "minimum": 0, "maximum": 100000, "type": "integer", "description": "0 = no limit. Applied after the page range. Price is per document, not per page.", "default": 0 }, "includePages": { "title": "Include per-page text array", "type": "boolean", "description": "Adds a 'pages' array with the text (and Markdown) of every page, e.g. for page-level citations.", "default": false }, "removeHeadersFooters": { "title": "Remove repeated headers, footers and page numbers", "type": "boolean", "description": "Drops lines that repeat at the top/bottom of most pages (documents with 3+ pages) and bare page numbers.", "default": true }, "findPdfLinks": { "title": "Find PDF links on HTML pages", "type": "boolean", "description": "If an input URL is a web page instead of a PDF, convert the .pdf files it links to (one level deep). The HTML page itself is free.", "default": false }, "maxPdfLinksPerPage": { "title": "Max PDF links per HTML page", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Only used with 'Find PDF links on HTML pages'.", "default": 50 }, "maxChargedDocuments": { "title": "Max charged documents", "minimum": 0, "type": "integer", "description": "Stop after this many converted (charged) documents. 0 = no limit (the run's Max total charge still applies).", "default": 0 }, "maxFileSizeMb": { "title": "Max PDF size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Larger files are skipped (free row with status TOO_LARGE). Very large PDFs may need more memory.", "default": 100 }, "includeFailedDocuments": { "title": "Include failed documents (free rows)", "type": "boolean", "description": "Adds a free row with the reason (404, not a PDF, encrypted, scanned/no text layer...) so you can see every input.", "default": true }, "maxConcurrency": { "title": "Downloads in parallel", "minimum": 1, "maximum": 20, "type": "integer", "description": "Parsing is CPU-bound, so more than 4-8 rarely helps.", "default": 4 }, "requestTimeoutSecs": { "title": "Download timeout (s)", "minimum": 10, "maximum": 600, "type": "integer", "description": "Per file, including the download.", "default": 120 }, "maxRetries": { "title": "Retries", "minimum": 0, "maximum": 5, "type": "integer", "description": "For timeouts, resets, 429 and 5xx.", "default": 1 }, "userAgent": { "title": "User-Agent", "type": "string", "description": "Leave empty for the default browser-compatible UA." }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional. Apify datacenter proxy or your own proxy URLs. Residential proxy isn't supported (it would raise the price for everyone)." } } }, "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 } } } } } } } } } }