{ "openapi": "3.0.1", "info": { "title": "PDF Text Extractor — PDF to Text & Markdown API | $3/1k PDFs", "description": "Extract text and Markdown from PDF URLs in bulk, with document info (title, dates, page count, producer) and per-page text. Pure JavaScript, no OCR, no API key. Broken links, non-PDFs and scanned files are free rows. $3 per 1,000 PDFs.", "version": "0.1", "x-build-id": "2PUWyoPxwQ3D0Xmch" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/glasswing~pdf-text-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-glasswing-pdf-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/glasswing~pdf-text-extractor/runs": { "post": { "operationId": "runs-sync-glasswing-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/glasswing~pdf-text-extractor/run-sync": { "post": { "operationId": "run-sync-glasswing-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": { "startUrls": { "title": "PDF URLs", "uniqueItems": true, "type": "array", "description": "Direct links to PDF files, one per line. Google Drive, Dropbox and GitHub share links and arXiv abstract pages are turned into their download links automatically. A link that does not return a PDF gives a free row with the reason.", "default": [ "https://nvlpubs.nist.gov/nistpubs/CSWP/NIST.CSWP.29.pdf", "https://www.irs.gov/pub/irs-pdf/p1.pdf" ], "items": { "type": "string" } }, "fileUploads": { "title": "Upload PDFs or key-value store records", "type": "array", "description": "Upload PDF files from your computer, or give records already in an Apify key-value store: the record's API URL or `storeId/key` (`username~store-name/key`). Records are read with your run's own token, so private stores work. Each file is one row (or chunk rows), billed like a URL." }, "base64Files": { "title": "PDFs as base64 (API)", "type": "array", "description": "For API calls and automations: PDFs sent inside the input, each a base64 string (a `data:application/pdf;base64,...` URL works too) or an object `{ \"fileName\": \"invoice.pdf\", \"base64\": \"JVBERi0...\", \"password\": \"optional\" }`. The whole input must stay under Apify's input size limit; for bigger files use a key-value store record above." }, "password": { "title": "PDF password", "type": "string", "description": "Opens password-protected PDFs: tried on every file that needs a password (a password in a base64Files entry wins for that file). Stored encrypted, never logged or written to the dataset. A wrong password gives a free `wrong_password` row." }, "outputFormat": { "title": "Output format", "enum": [ "both", "text", "markdown" ], "type": "string", "description": "Plain text keeps the PDF's lines; Markdown rebuilds headings, lists and paragraphs (and tables with 'Extract tables'), good for LLMs and RAG. Both is the default.", "default": "both" }, "ragChunks": { "title": "RAG chunks (one row per chunk)", "type": "boolean", "description": "For vector databases and RAG: write one row per token-sized chunk with `text`, page numbers (`pageStart`, `pageEnd`, `pageNumbers`), the section heading above it, an estimated `tokenCount`, a stable `chunkId` and overlap with the previous chunk. Chunks are Markdown unless Output format is plain text. Billing: one result per PDF per started 50 chunks (up to 50 chunks costs the same as one PDF).", "default": false }, "chunkSizeTokens": { "title": "Chunk size", "minimum": 100, "maximum": 2000, "type": "integer", "description": "Target chunk size in estimated tokens (about 4 characters of English text per token; 1 per CJK character). Chunks break at paragraphs, then sentences, then words, and never exceed this size.", "default": 500 }, "chunkOverlapTokens": { "title": "Chunk overlap", "minimum": 0, "maximum": 500, "type": "integer", "description": "Tokens repeated from the end of one chunk at the start of the next, so a sentence cut at a boundary is still found. At most half the chunk size.", "default": 50 }, "extractTables": { "title": "Extract tables", "type": "boolean", "description": "Find tables in the PDF's text layer (columns separated by white space; no OCR) and return them as rows of cells in a `tables` array, and as Markdown tables in `markdown` and in RAG chunks. Tables that are images, or drawn column by column, stay as plain text lines.", "default": false }, "splitByPage": { "title": "One row per page", "type": "boolean", "description": "Write one row per page instead of one row per PDF. Each page row with text is one billed result, so a 20-page PDF costs 20 results. For page-level text at the per-PDF price, leave this off and turn on 'Include per-page text' instead.", "default": false }, "includePageText": { "title": "Include per-page text", "type": "boolean", "description": "Add a `pages` array to each PDF row with the text (and Markdown) of every page, so you can cite page numbers. Still one result per PDF.", "default": false }, "pageRange": { "title": "Page range", "pattern": "^\\s*$|^\\s*(\\d+\\s*(-\\s*\\d*)?|-\\s*\\d+)(\\s*[,;]\\s*(\\d+\\s*(-\\s*\\d*)?|-\\s*\\d+))*\\s*$", "type": "string", "description": "Read only these pages of every PDF, e.g. `1-5, 8, 12-` (`12-` = page 12 to the end, `-3` = the first 3 pages). Leave empty for all pages (up to Max pages)." }, "maxPages": { "title": "Max pages per PDF", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Stop after this many pages of each PDF; the row then says `truncated: true` and how far it got. Up to 1,000.", "default": 100 }, "includeMetadata": { "title": "Include document info", "type": "boolean", "description": "Add the PDF's own document info: title, subject, keywords, creator and producer software, creation and modification dates, PDF version, language, whether it has form fields or is encrypted. The author field is never returned (it usually holds a person's name).", "default": true }, "maxFileSizeMb": { "title": "Max file size", "minimum": 1, "maximum": 100, "type": "integer", "description": "Larger PDFs are skipped with a free `error` row (checked from the Content-Length header before downloading, and again after). Up to 100 MB.", "default": 50 }, "timeoutSecs": { "title": "Timeout per PDF", "minimum": 10, "maximum": 600, "type": "integer", "description": "Maximum time for downloading one PDF, and again for reading it. A PDF that runs out of time while being read returns the pages read so far with `truncated: true`.", "default": 120 }, "maxItems": { "title": "Maximum rows", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Safety cap on rows written: PDFs, or pages with 'One row per page'. Rows with status `ok` are the billable results; `not_found` and `error` rows are free.", "default": 1000 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. Downloads go direct, which works for nearly every file host. Enable Apify Proxy (datacenter) only if a host blocks direct downloads.", "default": { "useApifyProxy": false } } } }, "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 } } } } } } } } } }