{ "openapi": "3.0.1", "info": { "title": "PDF Text Extractor with OCR, Tables & Markdown", "description": "Extract text, tables and metadata from any PDF, digital or scanned. Built-in OCR in 124 languages reads scanned pages automatically. Get Markdown for AI and RAG, tables as CSV, filled form fields and per-page results. USD 0.30 per 1,000 text pages, USD 3 per 1,000 OCR pages.", "version": "0.1", "x-build-id": "bA7jfjjZLjCUdKAzc" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/usefulapi~pdf-text-ocr/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-usefulapi-pdf-text-ocr", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/usefulapi~pdf-text-ocr/runs": { "post": { "operationId": "runs-sync-usefulapi-pdf-text-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/usefulapi~pdf-text-ocr/run-sync": { "post": { "operationId": "run-sync-usefulapi-pdf-text-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "PDF or image URLs", "type": "array", "description": "Direct links to PDF files or images (PNG, JPEG, TIFF, WebP, GIF, BMP). Google Drive and Dropbox share links work when the file is public. You can also give a text file of links (one per line).", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "files": { "title": "Upload files", "type": "array", "description": "Upload PDFs or images from your computer (they go to a key-value store on your account)." }, "ocrMode": { "title": "OCR mode", "enum": [ "auto", "always", "never" ], "type": "string", "description": "Auto reads scanned pages with OCR and every other page from its exact text layer. Always reads every page with OCR (also text in pictures; every page is then billed as an OCR page). Never skips OCR. Images are always read with OCR.", "default": "auto" }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Languages printed on the scans, up to 3 (first = main language). 124 languages; pick only the ones you need, more languages make OCR slower and less accurate. Chinese, Japanese and Korean pages count as 2 OCR pages; for vertical print pick the \"vertical\" models.", "items": { "type": "string", "enum": [ "eng", "afr", "sqi", "amh", "ara", "hye", "asm", "aze", "aze_cyrl", "eus", "bel", "ben", "bos", "bre", "bul", "mya", "cat", "ceb", "chr", "chi_sim", "chi_sim_vert", "chi_tra", "chi_tra_vert", "cos", "hrv", "ces", "dan", "div", "nld", "dzo", "enm", "epo", "est", "fao", "fil", "fin", "frk", "fra", "frm", "fry", "glg", "kat", "kat_old", "deu", "deu_latf", "ell", "grc", "guj", "hat", "heb", "hin", "hun", "isl", "ind", "iku", "gle", "ita", "ita_old", "jpn", "jpn_vert", "jav", "kan", "kaz", "khm", "kor", "kor_vert", "kmr", "kir", "lao", "lat", "lav", "lit", "ltz", "mkd", "msa", "mal", "mlt", "mri", "mar", "mon", "nep", "nor", "oci", "ori", "pus", "fas", "pol", "por", "pan", "que", "ron", "rus", "san", "gla", "srp", "srp_latn", "snd", "sin", "slk", "slv", "spa", "spa_old", "sun", "swa", "swe", "syr", "tgk", "tam", "tat", "tel", "tha", "bod", "tir", "ton", "tur", "ukr", "urd", "uig", "uzb", "uzb_cyrl", "vie", "cym", "yid", "yor" ], "enumTitles": [ "English (eng)", "Afrikaans (afr)", "Albanian (sqi)", "Amharic (amh)", "Arabic (ara)", "Armenian (hye)", "Assamese (asm)", "Azerbaijani (aze)", "Azerbaijani (Cyrillic) (aze_cyrl)", "Basque (eus)", "Belarusian (bel)", "Bengali (ben)", "Bosnian (bos)", "Breton (bre)", "Bulgarian (bul)", "Burmese (mya)", "Catalan (cat)", "Cebuano (ceb)", "Cherokee (chr)", "Chinese (Simplified) (chi_sim)", "Chinese (Simplified, vertical) (chi_sim_vert)", "Chinese (Traditional) (chi_tra)", "Chinese (Traditional, vertical) (chi_tra_vert)", "Corsican (cos)", "Croatian (hrv)", "Czech (ces)", "Danish (dan)", "Dhivehi (div)", "Dutch (nld)", "Dzongkha (dzo)", "English (Middle, 1100-1500) (enm)", "Esperanto (epo)", "Estonian (est)", "Faroese (fao)", "Filipino (fil)", "Finnish (fin)", "Frankish (frk)", "French (fra)", "French (Middle, 1400-1600) (frm)", "Frisian (Western) (fry)", "Galician (glg)", "Georgian (kat)", "Georgian (Old) (kat_old)", "German (deu)", "German (Fraktur) (deu_latf)", "Greek (ell)", "Greek (Ancient) (grc)", "Gujarati (guj)", "Haitian Creole (hat)", "Hebrew (heb)", "Hindi (hin)", "Hungarian (hun)", "Icelandic (isl)", "Indonesian (ind)", "Inuktitut (iku)", "Irish (gle)", "Italian (ita)", "Italian (Old) (ita_old)", "Japanese (jpn)", "Japanese (vertical) (jpn_vert)", "Javanese (jav)", "Kannada (kan)", "Kazakh (kaz)", "Khmer (khm)", "Korean (kor)", "Korean (vertical) (kor_vert)", "Kurdish (Kurmanji) (kmr)", "Kyrgyz (kir)", "Lao (lao)", "Latin (lat)", "Latvian (lav)", "Lithuanian (lit)", "Luxembourgish (ltz)", "Macedonian (mkd)", "Malay (msa)", "Malayalam (mal)", "Maltese (mlt)", "Maori (mri)", "Marathi (mar)", "Mongolian (mon)", "Nepali (nep)", "Norwegian (nor)", "Occitan (oci)", "Odia (ori)", "Pashto (pus)", "Persian (fas)", "Polish (pol)", "Portuguese (por)", "Punjabi (pan)", "Quechua (que)", "Romanian (ron)", "Russian (rus)", "Sanskrit (san)", "Scottish Gaelic (gla)", "Serbian (Cyrillic) (srp)", "Serbian (Latin) (srp_latn)", "Sindhi (snd)", "Sinhala (sin)", "Slovak (slk)", "Slovenian (slv)", "Spanish (spa)", "Spanish (Old) (spa_old)", "Sundanese (sun)", "Swahili (swa)", "Swedish (swe)", "Syriac (syr)", "Tajik (tgk)", "Tamil (tam)", "Tatar (tat)", "Telugu (tel)", "Thai (tha)", "Tibetan (bod)", "Tigrinya (tir)", "Tongan (ton)", "Turkish (tur)", "Ukrainian (ukr)", "Urdu (urd)", "Uyghur (uig)", "Uzbek (uzb)", "Uzbek (Cyrillic) (uzb_cyrl)", "Vietnamese (vie)", "Welsh (cym)", "Yiddish (yid)", "Yoruba (yor)" ] }, "default": [ "eng" ] }, "ocrDpi": { "title": "OCR resolution (DPI)", "minimum": 150, "maximum": 400, "type": "integer", "description": "300 suits normal print. Use 400 for very small print (US Legal pages then count as 2 OCR pages); 200 for large print (faster).", "default": 300 }, "tables": { "title": "Tables", "enum": [ "lines", "text", "off" ], "type": "string", "description": "Ruled tables finds tables with drawn cell borders. Ruled and aligned (experimental) also looks for tables lined up by spaces only; it skips anything that looks like a paragraph but can still miss or split such tables.", "default": "lines" }, "markdown": { "title": "Markdown", "type": "boolean", "description": "Also return Markdown: headings from font sizes, lists, tables as Markdown tables. Good for AI and RAG pipelines.", "default": true }, "layoutText": { "title": "Text with the page layout kept", "type": "boolean", "description": "Also return text placed as on the page (columns side by side, padded with spaces). Useful for forms and reports.", "default": false }, "outputMode": { "title": "One row per", "enum": [ "document", "page" ], "type": "string", "description": "Document: one row per file with all its pages. Page: one row per page.", "default": "document" }, "pageRange": { "title": "Pages to read", "type": "string", "description": "For example \"1-5, 8, 10-\". Empty = every page." }, "maxPagesPerFile": { "title": "Max pages per file", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Pages read per file at most (after \"Pages to read\"). Up to 5,000.", "default": 1000 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Larger files are skipped with a clear message. Up to 500 MB.", "default": 100 }, "pdfPassword": { "title": "PDF password", "type": "string", "description": "For password-protected PDFs (used for every file in this run)." } } }, "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 } } } } } } } } } }