{ "openapi": "3.0.1", "info": { "title": "Government PDF Table Extractor – PDF to JSON", "description": "PDF table extractor for government reports and annual accounts: extract tables from PDF to JSON with headers, typed records, page and position, confidence and sum checks. Joins multi-page tables, handles merged headers and Dutch number formats; Claude can read scanned pages, validated in code.", "version": "0.1", "x-build-id": "9hxFahbRaeXY0c0Wp" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/lwsdjfls~govt-pdf-table-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-lwsdjfls-govt-pdf-table-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/lwsdjfls~govt-pdf-table-extractor/runs": { "post": { "operationId": "runs-sync-lwsdjfls-govt-pdf-table-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/lwsdjfls~govt-pdf-table-extractor/run-sync": { "post": { "operationId": "run-sync-lwsdjfls-govt-pdf-table-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "maxItems": 500, "type": "array", "description": "Direct http(s) links to PDF files (one per line, each up to 2,048 characters). Links to key-value store records work too. The same link listed twice is read once.", "items": { "type": "string", "maxLength": 2048 }, "default": [] }, "pdfFiles": { "title": "PDF files (base64)", "maxItems": 100, "type": "array", "description": "For API callers: [{ \"fileName\": \"report.pdf\", \"data\": \"\" }]. Up to 100 files; the total input must stay under Apify's 9 MB input limit, so use URLs for large files.", "items": { "type": "object", "properties": { "fileName": { "title": "File name", "type": "string", "editor": "textfield", "description": "The name this document is reported under, for example report.pdf.", "minLength": 1, "maxLength": 200 }, "data": { "title": "File contents (base64)", "type": "string", "editor": "textarea", "description": "The PDF itself, base64 encoded, without a data: prefix.", "minLength": 1 } }, "required": [ "fileName", "data" ] }, "default": [] }, "pages": { "title": "Pages", "pattern": "^\\s*(\\d+\\s*(-\\s*(\\d+\\s*)?)?|-\\s*(\\d+\\s*)?)(,\\s*(\\d+\\s*(-\\s*(\\d+\\s*)?)?|-\\s*(\\d+\\s*)?))*$", "maxLength": 1000, "type": "string", "description": "Page numbers and ranges to read, for every document: 1-5,8 or 14-17 (up to 1,000 characters). Empty means all pages (up to the per-document cap)." }, "mode": { "title": "Mode", "enum": [ "fast", "llm-fallback", "llm" ], "type": "string", "description": "fast: deterministic only (text-layer PDFs, cheapest). llm-fallback: deterministic, plus Claude for pages without a text layer (scans) and pages whose tables came out with low confidence. llm: Claude reads every page.", "default": "fast" }, "llmModel": { "title": "LLM model", "enum": [ "haiku", "sonnet" ], "type": "string", "description": "Claude Haiku 4.5 reads most pages well and is the cheaper event; Claude Sonnet 5 for dense or hard layouts.", "default": "haiku" }, "flavor": { "title": "Detection", "enum": [ "auto", "stream", "lattice" ], "type": "string", "description": "auto tries whitespace-aligned and ruled-line detection and keeps the best reading per table. stream: whitespace only (reports, statistics). lattice: ruled lines only (forms, invoices).", "default": "auto" }, "expectedColumns": { "title": "Expected columns", "maxItems": 100, "type": "array", "description": "Optional. The column names you expect, in order. Tables with that many columns get these names as record keys; others are flagged in checks.", "items": { "type": "string", "minLength": 1, "maxLength": 200 }, "default": [] }, "minRows": { "title": "Minimum rows", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Tables with fewer body rows are ignored (layout boxes, legends).", "default": 2 }, "minColumns": { "title": "Minimum columns", "minimum": 1, "maximum": 100, "type": "integer", "description": "Tables with fewer columns are ignored.", "default": 2 }, "mergeAcrossPages": { "title": "Join tables that continue on the next page", "type": "boolean", "description": "A table with the same columns that continues on the next page (with or without a repeated header) is delivered once, with all its rows and pages.", "default": true }, "includeCells": { "title": "Include cell coordinates", "type": "boolean", "description": "Adds every cell with its page and bounding box (PDF points, origin top-left) to each table. Makes records larger.", "default": false }, "maxPagesPerDocument": { "title": "Maximum pages per document", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Pages beyond this are not read (or charged).", "default": 200 }, "maxFileMb": { "title": "Maximum file size (MB)", "minimum": 1, "maximum": 100, "type": "integer", "description": "Larger files are reported as failed and cost nothing. At most 100 MB.", "default": 50 }, "maxLlmPagesPerRun": { "title": "Maximum LLM pages per run", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Caps the pages sent to Claude in one run; the rest is delivered from the deterministic pass.", "default": 200 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Only for downloading PDFs from sites that block data-centre addresses.", "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 } } }, "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 } } } } } } } } } }