You can access the PDF Text and Tables Extractor 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.

Python

JavaScript

CLI

OpenAPI

HTTP

MCP

{
  "openapi": "3.0.1",
  "info": {
    "version": "0.1",
    "x-build-id": "dqxT488QK1X2Dy6fa"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2"
    }
  ],
  "paths": {
    "/acts/timbered_oak~pdf-text-and-tables/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run-sync-get-dataset-items-timbered_oak-pdf-text-and-tables",
        "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": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    },
    "/acts/timbered_oak~pdf-text-and-tables/runs": {
      "post": {
        "operationId": "runs-sync-timbered_oak-pdf-text-and-tables",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor and returns information about the initiated run in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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": {
                  "$ref": "#/components/schemas/runsResponseSchema"
                }
              }
            }
          }
        }
      }
    },
    "/acts/timbered_oak~pdf-text-and-tables/run-sync": {
      "post": {
        "operationId": "run-sync-timbered_oak-pdf-text-and-tables",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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",
            "type": "array",
            "description": "URLs of PDF documents to fetch and extract.",
            "items": {
              "type": "string"
            }
          },
          "maxPages": {
            "title": "Max pages per PDF",
            "type": "integer",
            "description": "Stop extracting after this many pages (protects memory on huge files).",
            "default": 200
          },
          "extractTables": {
            "title": "Extract tables",
            "type": "boolean",
            "description": "Heuristically detect and extract tables (lines sharing a y-coordinate with 3+ column gaps). Off = text only.",
            "default": true
          },
          "pagesAsRows": {
            "title": "One row per page",
            "type": "boolean",
            "description": "false (default): one dataset row per PDF with full text + a pages array. true: one dataset row per page.",
            "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
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}

PDF Text and Tables Extractor — by URL, $17 per 1,000 OpenAPI definition

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 Text and Tables Extractor from the options below:

OpenAPI.json

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:

PDF Text and Tables Extractor API in Python

PDF Text and Tables Extractor API in JavaScript

PDF Text and Tables Extractor API through CLI

PDF Text and Tables Extractor API

PDF Text & Table Extractor (pdfplumber, batch URLs)

gochujang/pdf-text-extractor

Download any PDF by URL and extract clean per-page text + detected tables (as 2D arrays) + document metadata (title/author/created/modified). Powered by pdfplumber. Batch up to 50 PDFs. $0.01 per PDF + $0.0005 per page.

Hojun Lee

177

PDF Text & Table Extractor: OCR, DOCX, PPTX, XLSX to Data + RAG

ntriqpro/pdf-text-extractor

Extract text from PDF, DOCX, PPTX, HTML, TXT, MD and EML by URL. One document in, hundreds of rows out: typed elements (titles, paragraphs, lists, tables), RAG-ready chunks and a per-document summary. Unofficial wrapper around unstructured (Apache-2.0).

daehwan kim

PDF Text & Table Extractor with CSV Tables + OCR

inn_corp/pdf-text-table-extractor

Extract text, RAG-ready markdown, and tables from PDF URLs. Every detected table becomes its own CSV-ready dataset record. No OCR; scanned pages are flagged, never guessed.

Inn Corp

PDF Text & Table Extractor — PDF URL to Structured JSON

toolkitlabs/pdf-text-tables

Extract text and tables from PDF files. Send PDF URLs; get JSON with per-page text, detected tables as row arrays, page count and metadata. Deterministic parsing, no model inference.

Toolkit Labs

PDF Text Extractor — Structured Tables, Markdown & Metadata

nuhemugames/pdf-text-table-extractor

Extract text from PDF URLs at scale: full text, per-page text, real structured tables (rows and columns as JSON, not text lines), document metadata and clean Markdown for LLM/RAG. The table extraction generic PDF text extractors don't have. No credentials needed.

kuon

Image OCR Extractor

gochujang/image-ocr-extractor

Extract text from images (PNG, JPG, WebP, TIFF) using Tesseract OCR. Batch up to 50 images, multi-language, confidence scores.

Hojun Lee

PDF → RAG Chunks (Token-Aware, Vector-Ready)

gochujang/pdf-rag-chunker

Download any PDF and chunk into semantically coherent segments ready for embedding/RAG. Configurable chunk size + overlap. Returns one row per chunk with page, char count, token estimate. Feed directly into OpenAI text-embedding-3 / Voyage / Cohere. $0.005 per PDF + $0.0002 per chunk.

Hojun Lee

PPTX Text Extractor — PowerPoint, Google Drive, Notes

gochujang/pptx-text-extractor

Extract text, speaker notes, and slide structure from PowerPoint (.pptx) files at any URL — including Google Drive and Dropbox links. Batch up to 50 files. Perfect for LLM/RAG pipelines. No API key. $0.02/file + $0.001/slide.

Hojun Lee

PDF Text Extractor — Markdown, Tables, OCR & RAG Chunks

nanare-sudo/pdf-text-extractor-rag

Extract text, GFM Markdown, tables (2D arrays + CSV) and heading-aware RAG chunks with page anchors from PDFs. URLs, base64 upload, key-value store, password-protected PDFs, page ranges, OCR fallback (eng/deu/fra/spa) only for pages without a text layer. Failed PDFs are never charged.

Leonardo Berisha

PDF Text Extractor - Markdown, Tables & RAG Chunks

readable_slash/pdf-text-extractor-structured

Extract text from PDF to clean Markdown with real tables, headings and lists. Bulk PDF to text conversion for RAG, LLM and vector database ingestion, with optional context-aware chunking. Detects scanned PDFs, handles encrypted files and broken URLs. Pay only for documents extracted.