{ "openapi": "3.0.1", "info": { "title": "PDF & Image Text Extractor: Markdown, OCR, RAG Chunks", "description": "Extract text, Markdown and metadata from PDF files and images, with OCR for scanned pages. Paste PDF links, image links or web pages: PDFs linked on a page are found for you. Page-by-page text, AI-ready chunks, page ranges. No browser.", "version": "1.0", "x-build-id": "UCSnzO68e5JzfYl1C" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/hydrocore~pdf-image-text-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-hydrocore-pdf-image-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/hydrocore~pdf-image-text-extractor/runs": { "post": { "operationId": "runs-sync-hydrocore-pdf-image-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/hydrocore~pdf-image-text-extractor/run-sync": { "post": { "operationId": "run-sync-hydrocore-pdf-image-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "Files or pages", "type": "array", "description": "Links to PDF files (.pdf), images (PNG, JPG, WebP, BMP, GIF, TIFF) or web pages. If a link is a web page, the PDFs it links to are collected (see \"Find PDF links on web pages\"). One link per line.", "items": { "type": "string" } }, "datasetId": { "title": "Dataset ID (optional)", "type": "string", "description": "Read links from an Apify dataset, for example the output of another scraper. Use it with \"URL field in dataset\"." }, "datasetUrlField": { "title": "URL field in dataset", "type": "string", "description": "Name of the dataset field that holds the link. The field can also hold a list of links.", "default": "url" }, "findPdfLinks": { "title": "Find PDF links on web pages", "type": "boolean", "description": "When a link is a web page instead of a file, read the page and extract every PDF it links to. Only links in the page's HTML are found; links added later by JavaScript are not.", "default": true }, "pdfLinkKeywords": { "title": "Only PDFs whose link contains", "type": "array", "description": "Optional. Keep only PDF links whose address or link text contains one of these words, e.g. \"annual report\" or \"2025\". Not case-sensitive.", "items": { "type": "string" } }, "maxPdfsPerPage": { "title": "Max PDFs per web page", "minimum": 0, "type": "integer", "description": "Upper limit of PDF links taken from one web page. 0 means no limit.", "default": 25 }, "outputFormat": { "title": "Text format", "enum": [ "markdown", "text", "both" ], "type": "string", "description": "Markdown keeps the document structure and works well with ChatGPT and other AI tools. Plain text keeps the original line breaks.", "default": "markdown" }, "includePages": { "title": "Include text page by page", "type": "boolean", "description": "Add a \"pages\" list with the text of each page, and whether that page was read with OCR.", "default": false }, "chunkSize": { "title": "AI chunk size (characters)", "minimum": 0, "maximum": 20000, "type": "integer", "description": "Split each document into chunks for RAG or vector databases, with page numbers on every chunk. About 1,000-2,000 characters works well. 0 turns chunking off.", "default": 0 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Characters repeated from the end of one chunk at the start of the next, so sentences are not cut off without context.", "default": 200 }, "pageRange": { "title": "Pages to read", "type": "string", "description": "Optional. For example \"1-3, 7, 10-\" (\"10-\" means page 10 to the end). Empty means all pages." }, "maxPages": { "title": "Max pages per document", "minimum": 0, "type": "integer", "description": "Read at most this many pages of each PDF. 0 means no limit. Useful to keep costs down when you only need the first pages of long scanned files.", "default": 0 }, "ocrMode": { "title": "OCR (scanned pages and images)", "enum": [ "auto", "always", "off" ], "type": "string", "description": "Auto reads normal PDFs directly and uses OCR only on pages that have no text (scanned pages). Images always need OCR. OCR pages are billed separately, see Pricing.", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Languages printed in your scanned documents. Pick 1 or 2; more languages make OCR slower and less accurate.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "ita", "por", "nld", "pol", "ces", "slk", "swe", "dan", "nor", "fin", "hun", "ron", "ell", "tur", "rus", "ukr", "ara", "heb", "hin", "ind", "vie", "tha", "jpn", "kor", "chi_sim", "chi_tra" ], "enumTitles": [ "English", "German", "French", "Spanish", "Italian", "Portuguese", "Dutch", "Polish", "Czech", "Slovak", "Swedish", "Danish", "Norwegian", "Finnish", "Hungarian", "Romanian", "Greek", "Turkish", "Russian", "Ukrainian", "Arabic", "Hebrew", "Hindi", "Indonesian", "Vietnamese", "Thai", "Japanese", "Korean", "Chinese (Simplified)", "Chinese (Traditional)" ] }, "default": [ "eng" ] }, "minTextCharsPerPage": { "title": "Scanned page threshold (characters)", "minimum": 0, "type": "integer", "description": "In Auto mode, a page with fewer text characters than this is treated as scanned and read with OCR.", "default": 25 }, "ocrDpi": { "title": "OCR resolution (DPI)", "minimum": 72, "maximum": 400, "type": "integer", "description": "Resolution used to render scanned PDF pages for OCR. 200 is a good balance; use 300 for very small print.", "default": 200 }, "password": { "title": "PDF password", "type": "string", "description": "Password for protected PDFs. The same password is tried on every PDF in the run." }, "maxFileSizeMb": { "title": "Max file size", "minimum": 1, "maximum": 500, "type": "integer", "description": "Larger files are skipped and reported as errors (no charge). For files over 50 MB, give the run 1 GB of memory or more.", "default": 50 }, "maxDocuments": { "title": "Max documents", "minimum": 0, "type": "integer", "description": "Stop after this many files. 0 means no limit.", "default": 0 }, "maxConcurrency": { "title": "Parallel downloads", "minimum": 1, "maximum": 8, "type": "integer", "description": "How many files are downloaded and processed at the same time.", "default": 2 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip links that the website's robots.txt asks bots not to fetch. Turn off only for files you own or have permission to download.", "default": true } } }, "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 } } } } } } } } } }