PDF Tables to CSV and JSON
Pricing
from $10.00 / 1,000 page processeds
Go to Apify Store
PDF Tables to CSV and JSON
Extract tables from batches of PDF URLs with page references and downloadable CSV and JSON files.
PDF Tables to CSV and JSON
Pricing
from $10.00 / 1,000 page processeds
Extract tables from batches of PDF URLs with page references and downloadable CSV and JSON files.
You can access the PDF Tables to CSV and JSON programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "zSwo7f8rZThKjsbh3" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/kiwitools~pdf-tables-to-csv-json/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-kiwitools-pdf-tables-to-csv-json", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/kiwitools~pdf-tables-to-csv-json/runs": { "post": { "operationId": "runs-sync-kiwitools-pdf-tables-to-csv-json", "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/kiwitools~pdf-tables-to-csv-json/run-sync": { "post": { "operationId": "run-sync-kiwitools-pdf-tables-to-csv-json", "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", "required": [ "pdfUrls" ], "properties": { "pdfUrls": { "title": "PDF URLs", "minItems": 1, "maxItems": 100, "type": "array", "description": "Direct links to public PDF files (HTTP/HTTPS), up to 100 per run. Duplicates are processed once. Only submit PDFs you have the right to process.", "items": { "type": "string" } }, "maxPages": { "title": "Maximum pages per PDF", "minimum": 1, "maximum": 200, "type": "integer", "description": "Process the first N pages of each PDF. You are charged per processed page, so keep this as low as you need.", "default": 20 }, "enableOcr": { "title": "Enable English OCR", "type": "boolean", "description": "Read scanned pages (no text layer) with English OCR. Scanned pages are charged at the OCR page price. OCR can misread digits and decimal points; check suspiciousValues and verify important numbers.", "default": false }, "tableMode": { "title": "Table extraction mode", "enum": [ "fast", "accurate" ], "type": "string", "description": "Accurate is recommended for complex tables.", "default": "accurate" }, "headerStyle": { "title": "Multi-level header style", "enum": [ "joined", "leaf", "dotted" ], "type": "string", "description": "How stacked column headers are named. joined: 'Parent / Child'. leaf: only the lowest header. dotted: 'Parent.Child' (Docling's original format).", "default": "joined" }, "mergedCells": { "title": "Merged cells", "enum": [ "first", "repeat" ], "type": "string", "description": "first: a merged cell's text appears once, in its first cell (section labels are not repeated across columns). repeat: copy the text into every cell it covers.", "default": "first" }, "includeNonDataTables": { "title": "Include contents pages and lists of figures", "type": "boolean", "description": "By default, tables that look like a table of contents or list of figures (dot leaders, page-number columns) are skipped. Turn on to keep them, marked tableType 'contents'.", "default": false }, "safeCsv": { "title": "Escape spreadsheet formulas", "type": "boolean", "description": "Prefix formula-like CSV cells with an apostrophe. JSON retains original text.", "default": true }, "maxFileSizeMb": { "title": "Maximum download size (MiB)", "minimum": 1, "maximum": 100, "type": "integer", "description": "Reject larger PDF downloads.", "default": 25 }, "documentTimeoutSeconds": { "title": "Conversion timeout per PDF", "minimum": 30, "maximum": 1800, "type": "integer", "description": "Stop a conversion taking longer than this limit. Download time is separate.", "default": 180 } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for PDF Tables to CSV and JSON from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: