{ "openapi": "3.0.1", "info": { "title": "PDF Text Extractor: tables, OCR, Markdown, JSON per page", "description": "Turn PDF URLs into clean data: per-page text, tables as real rows (CSV/Excel-ready, with page numbers and Markdown), document metadata, and OCR for scanned pages with confidence scores. Chain from any dataset of URLs. Pay per page, no per-file fee.", "version": "0.1", "x-build-id": "FXDCXPxNLcPe17J5Z" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/brenton8907~pdf-text-table-ocr-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-brenton8907-pdf-text-table-ocr-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/brenton8907~pdf-text-table-ocr-extractor/runs": { "post": { "operationId": "runs-sync-brenton8907-pdf-text-table-ocr-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/brenton8907~pdf-text-table-ocr-extractor/run-sync": { "post": { "operationId": "run-sync-brenton8907-pdf-text-table-ocr-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "type": "array", "description": "Direct links to PDF files (one per line, or upload a text file of URLs). Apify key-value store record URLs work too.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "inputDatasetId": { "title": "URLs from dataset", "type": "string", "description": "Optional: read PDF URLs from an existing Apify dataset (ID or name), e.g. the output of a crawler. Combined with the URLs above." }, "urlField": { "title": "URL field in dataset", "type": "string", "description": "Field holding the PDF URL in each dataset item. Dot paths like `file.url` are allowed.", "default": "url" }, "outputMode": { "title": "Output", "enum": [ "pages", "documents", "tableRows" ], "type": "string", "description": "Pages: one dataset row per PDF page. Documents: one row per file with the whole text and all tables. Table rows: only tables, one row per table row, with page number, header and cells.", "default": "pages" }, "pageRange": { "title": "Page range", "type": "string", "description": "Which pages to process, 1-based, e.g. `1-3,7,10-`. Empty = all pages." }, "maxPagesPerDocument": { "title": "Max pages per document", "minimum": 0, "type": "integer", "description": "Stop after this many pages of each PDF (after the page range is applied). 0 = no limit.", "default": 0 }, "extractText": { "title": "Extract text", "type": "boolean", "description": "Per-page text from the PDF text layer.", "default": true }, "extractTables": { "title": "Extract tables", "type": "boolean", "description": "Detect tables on each page and return them as rows (plus a Markdown rendering).", "default": true }, "tableStrategy": { "title": "Table detection", "enum": [ "auto", "lines", "text" ], "type": "string", "description": "`lines` finds tables drawn with borders (most reliable). `text` infers tables from column alignment (for borderless tables, more false positives). `auto` tries lines first and falls back to text when a page has none.", "default": "auto" }, "keepLayout": { "title": "Keep text layout", "type": "boolean", "description": "Preserve horizontal positioning with spaces (useful for columns and forms). Off = reading-order text.", "default": false }, "ocr": { "title": "OCR", "enum": [ "auto", "always", "never" ], "type": "string", "description": "Scanned pages have no text layer. `auto` runs Tesseract OCR only on pages whose text layer has fewer than `ocrMinChars` characters. OCR pages are billed at the OCR rate.", "default": "auto" }, "ocrMinChars": { "title": "OCR threshold (chars)", "minimum": 0, "type": "integer", "description": "In `auto` mode, a page with fewer extracted characters than this is treated as scanned and sent to OCR.", "default": 25 }, "ocrLanguages": { "title": "OCR languages", "type": "string", "description": "Tesseract language codes joined with `+`, e.g. `eng+deu`. Installed: eng, deu, fra, spa, ita, por, nld.", "default": "eng" }, "ocrDpi": { "title": "OCR resolution (DPI)", "minimum": 72, "maximum": 400, "type": "integer", "description": "Render resolution for OCR. 200 is a good default; 300 for small print (slower).", "default": 200 }, "password": { "title": "PDF password", "type": "string", "description": "Password for encrypted PDFs (applied to every file)." }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Files larger than this are skipped with an error row instead of being downloaded.", "default": 50 }, "downloadTimeoutSecs": { "title": "Download timeout (s)", "minimum": 5, "maximum": 600, "type": "integer", "description": "Per-file download timeout in seconds.", "default": 60 }, "concurrency": { "title": "Parallel documents", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many PDFs to download and process at once. Raise memory for large files when increasing this.", "default": 3 }, "includeRaw": { "title": "Include raw metadata", "type": "boolean", "description": "Attach the untouched PDF metadata dictionary to each row.", "default": 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 } } }, "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 } } } } } } } } } }