{ "openapi": "3.0.1", "info": { "title": "PDF Text Extractor – PDF, DOCX & PPTX to Markdown", "description": "Turn PDF, Word (DOCX) and PowerPoint (PPTX) files into clean text and Markdown. Give URLs or uploads and get one row per document, page or RAG-ready chunk, with metadata and a status per file.", "version": "1.0", "x-build-id": "rkpLTBRPnbCXR61h6" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/openfeeds~pdf-to-text-markdown-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-openfeeds-pdf-to-text-markdown-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/openfeeds~pdf-to-text-markdown-extractor/runs": { "post": { "operationId": "runs-sync-openfeeds-pdf-to-text-markdown-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/openfeeds~pdf-to-text-markdown-extractor/run-sync": { "post": { "operationId": "run-sync-openfeeds-pdf-to-text-markdown-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "Document URLs", "maxItems": 10000, "type": "array", "description": "Direct links to PDF, Word (DOCX) or PowerPoint (PPTX) files, one per line, starting with http:// or https://. Each unique URL gets its own result row with a status, so one bad link never stops the run: a malformed link gets status `invalid_url`. A URL listed twice is processed once (the run's SUMMARY counts it under `duplicatesSkipped`). Links to Google Drive and other unsupported platforms are skipped; share pages that return a web page are reported as `unsupported_format`. Exception: once your maximum charge per run is used up, the files not yet started get no row and are listed as `charge_limit_reached` in the SUMMARY record.", "items": { "type": "string" } }, "uploadedFiles": { "title": "Upload files", "maxItems": 1000, "type": "array", "description": "Upload PDF, Word (DOCX) or PowerPoint (PPTX) files from your computer (they are stored in your Apify key-value store), or paste file links. Processed exactly like document URLs.", "default": [] }, "outputMode": { "title": "Output rows", "enum": [ "documents", "pages", "chunks" ], "type": "string", "description": "How results are split into dataset rows: one row per file (`documents`), one row per PDF page or PowerPoint slide (`pages`; a Word file gives one row), or one row per text chunk for RAG and embeddings (`chunks`). Files that fail always produce one status row.", "default": "documents" }, "includeText": { "title": "Include plain text", "type": "boolean", "description": "Adds the `text` field: reading-order plain text with paragraphs separated by blank lines.", "default": true }, "includeMarkdown": { "title": "Include Markdown", "type": "boolean", "description": "Adds the `markdown` field: headings, lists, tables (Word and PowerPoint) and reflowed paragraphs.", "default": true }, "removeHeadersFooters": { "title": "Remove repeated headers and footers", "type": "boolean", "description": "PDF: drops lines that repeat at the top or bottom of most pages (running titles, page numbers). PowerPoint footer, date and slide-number boxes are always skipped, and Word headers and footers are never included.", "default": true }, "pageMarkers": { "title": "Page and slide markers in Markdown", "type": "boolean", "description": "In `documents` mode, inserts `` (PDF) or `` (PowerPoint) before each page or slide so you can cite them.", "default": true }, "includeSpeakerNotes": { "title": "Include PowerPoint speaker notes", "type": "boolean", "description": "Adds each slide's speaker notes under the slide as a 'Speaker notes' block.", "default": true }, "pageRange": { "title": "Pages or slides to extract", "pattern": "^\\s*$|^\\s*\\d+\\s*(-\\s*\\d*)?\\s*(,\\s*\\d+\\s*(-\\s*\\d*)?\\s*)*$", "type": "string", "description": "Page or slide numbers and ranges, for example `1-5, 8, 10-`. Leave empty for all. Applies to every PDF and PowerPoint file; ignored for Word files.", "default": "" }, "maxPagesPerDocument": { "title": "Max pages or slides per file", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Stops after this many pages or slides of each file (after the page selection). Larger files are charged per started 100 pages or slides (see Pricing).", "default": 500 }, "maxFileSizeMb": { "title": "Max file size", "minimum": 1, "maximum": 100, "type": "integer", "description": "Larger files are skipped with status `too_large` and are not charged.", "default": 50 }, "maxCharsPerDocument": { "title": "Max characters per row", "minimum": 1000, "maximum": 2000000, "type": "integer", "description": "In `documents` mode, longer text or Markdown is cut at a paragraph boundary and the full version is saved to the run's key-value store (see `fullTextUrl` / `fullMarkdownUrl`).", "default": 300000 }, "chunkSize": { "title": "Chunk size", "minimum": 200, "maximum": 20000, "type": "integer", "description": "Target length of each chunk in `chunks` mode. About 4 characters ≈ 1 token.", "default": 2000 }, "chunkOverlap": { "title": "Chunk overlap", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Characters repeated from the end of the previous chunk, so context is not lost at boundaries.", "default": 200 }, "pdfPassword": { "title": "PDF password", "type": "string", "description": "Password for encrypted PDFs, if you have it. Tried on every PDF that asks for one; PDFs that open without a password (for example, ones that only restrict printing or editing) are read as they are. Password-protected Word and PowerPoint files are not supported. Stored encrypted; never logged." }, "respectOptOuts": { "title": "Respect publisher opt-outs", "type": "boolean", "description": "Skips files whose publisher reserved text and data mining (TDMRep header, `/.well-known/tdmrep.json` or PDF metadata) or that robots.txt disallows. Skipped files are not charged. Turn off only for files you own or are licensed to process.", "default": true }, "userAgent": { "title": "Custom User-Agent", "maxLength": 300, "type": "string", "description": "Optional. Some publishers require you to identify yourself (for example with your organisation name and a contact address). Leave empty for the default.", "default": "" }, "maxConcurrency": { "title": "Parallel downloads", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many files are downloaded at the same time. At most 2 run against the same website, to stay polite.", "default": 4 }, "timeoutPerDocumentSecs": { "title": "Timeout per file", "minimum": 10, "maximum": 600, "type": "integer", "description": "Limit for downloading and, separately, for parsing each file. Time spent waiting for a turn on the same website (at most 2 parallel downloads per site, plus any robots.txt Crawl-delay) does not count. Files that take longer get status `timeout` and are not charged.", "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 } } } } } } } } } }