{ "openapi": "3.0.1", "info": { "title": "PDF to Text & Markdown – Bulk PDF Extractor with OCR", "description": "Extract text or clean Markdown (headings, lists, tables) from PDF URLs in bulk, or from every PDF linked on a web page. Metadata, page ranges, per-page or per-document output, OCR for scanned pages, RAG chunks. Full .md/.txt files saved to the key-value store.", "version": "0.1", "x-build-id": "iutxKdyGxnJ6gEAa7" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/gazidev~pdf-text-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-gazidev-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/gazidev~pdf-text-extractor/runs": { "post": { "operationId": "runs-sync-gazidev-pdf-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/gazidev~pdf-text-extractor/run-sync": { "post": { "operationId": "run-sync-gazidev-pdf-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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, one per line. Google Drive / Dropbox share links, GitHub `blob` links and arXiv `/abs/` pages are converted to direct downloads automatically.", "default": [ "https://arxiv.org/pdf/1706.03762", "https://www.irs.gov/pub/irs-pdf/fw9.pdf" ], "items": { "type": "string" } }, "pageUrls": { "title": "Web pages to scan for PDF links", "type": "array", "description": "Optional. The Actor loads each page (plain HTTP, no browser) and extracts every PDF it links to (links ending in `.pdf`, or matching `PDF link regex`). Great for report archives, documentation, investor-relations or government form pages.", "default": [], "items": { "type": "string" } }, "maxPdfs": { "title": "Max PDFs", "minimum": 0, "type": "integer", "description": "Stop after this many PDFs in total (direct URLs + PDFs found on pages). 0 = no limit.", "default": 50 }, "sameDomainOnly": { "title": "Only PDFs on the same domain as the page", "type": "boolean", "description": "When scanning web pages, skip PDF links that point to other domains.", "default": false }, "pdfLinkRegex": { "title": "PDF link regex", "type": "string", "description": "Optional. When set, a link found on a scanned page is taken if its URL matches this regex (case-insensitive), even without a `.pdf` extension, e.g. `/download/|annual-report`." }, "outputFormat": { "title": "Output format", "enum": [ "markdown", "text" ], "type": "string", "description": "`markdown`: headings (`#`), lists, ruled tables as Markdown tables, paragraphs re-flowed - best for LLMs and RAG. `text`: plain text with the original line breaks, faster.", "default": "markdown" }, "outputMode": { "title": "One dataset row per", "enum": [ "document", "page", "chunk" ], "type": "string", "description": "`document`: one row per PDF with metadata and the full content. `page`: one row per page. `chunk`: one row per RAG chunk (uses `Chunk size`, default 1,500 characters). The price is the same in every mode (per page).", "default": "document" }, "pageRange": { "title": "Page range", "type": "string", "description": "Optional. Pages to extract, e.g. `1-5`, `1,3,10-`, or `-3--1` for the last three pages. Empty = all pages (up to `Max pages per PDF`). Only extracted pages are charged." }, "maxPagesPerPdf": { "title": "Max pages per PDF", "minimum": 0, "type": "integer", "description": "Safety cap on pages extracted from one PDF (after the page range). 0 = no limit.", "default": 500 }, "removeHeadersFooters": { "title": "Remove running headers, footers and page numbers", "type": "boolean", "description": "Drops lines repeated at the top or bottom of many pages (journal names, 'Confidential', 'Page 3 of 10') and bare page numbers. Needs 3+ pages for repeated lines.", "default": true }, "extractTables": { "title": "Markdown tables", "type": "boolean", "description": "Markdown format only: detect ruled tables (with drawn lines) and output them as Markdown tables. Tables without lines stay as text lines.", "default": true }, "pageMarkers": { "title": "Insert page markers", "type": "boolean", "description": "Adds `` (Markdown) or `--- page N ---` (text) before each page in the document content and saved file.", "default": false }, "maxCharsPerItem": { "title": "Max characters in the dataset content field", "minimum": 1000, "type": "integer", "description": "Longer content is cut in the dataset (`contentTruncated: true`). The complete text is always in the saved .md/.txt file (`contentFileUrl`).", "default": 100000 }, "saveToKeyValueStore": { "title": "Save full .md / .txt files", "type": "boolean", "description": "Save each PDF's full Markdown or text as a file in the run's key-value store, linked from every row (`contentFileUrl`).", "default": true }, "ocrMode": { "title": "OCR mode", "enum": [ "auto", "off", "force" ], "type": "string", "description": "`auto`: pages without a usable text layer (scans, photos, broken font encodings) are read with Tesseract OCR and charged as `ocr-page`; normal pages are not OCR'd. `off`: never OCR (scanned pages are reported, not charged). `force`: OCR every page.", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Languages of the scanned text. Pick 1-3: more languages are slower.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "ita", "por", "nld", "tur", "pol", "rus", "ukr", "ces", "swe", "ron", "ara", "hin", "chi_sim", "jpn", "kor", "ind", "vie" ], "enumTitles": [ "English", "German", "French", "Spanish", "Italian", "Portuguese", "Dutch", "Turkish", "Polish", "Russian", "Ukrainian", "Czech", "Swedish", "Romanian", "Arabic", "Hindi", "Chinese (simplified)", "Japanese", "Korean", "Indonesian", "Vietnamese" ] }, "default": [ "eng" ] }, "ocrDpi": { "title": "OCR resolution (DPI)", "minimum": 100, "maximum": 400, "type": "integer", "description": "Rendering resolution for OCR. 300 is best for normal print; 200 is a little faster; 400 helps with very small text.", "default": 300 }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Split each PDF into RAG-ready chunks of about this many characters, cut at paragraph, sentence or word boundaries, with page numbers and the section heading. 0 = no chunks (in `chunk` mode the default is 1,500). Chunks are free.", "default": 0 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "type": "integer", "description": "Characters of the previous chunk repeated at the start of the next one (at most half the chunk size).", "default": 200 }, "pdfPassword": { "title": "PDF password", "type": "string", "description": "Optional. Password for encrypted PDFs (used for all PDFs of the run). PDFs that only restrict printing/copying open without it." }, "maxFileSizeMb": { "title": "Max PDF size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Larger files are skipped with an error row (free).", "default": 50 }, "requestTimeoutSecs": { "title": "Download timeout (seconds)", "minimum": 10, "maximum": 600, "type": "integer", "description": "Timeout for one download. Failed downloads (timeouts, HTTP 429/5xx) are retried 3 times with backoff.", "default": 120 }, "maxConcurrentDownloads": { "title": "Parallel downloads", "minimum": 1, "maximum": 10, "type": "integer", "description": "PDFs downloaded in parallel while the previous ones are being extracted.", "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 } } } } } } } } } }