Pricing

Pay per usage

PDF & Invoice Data Extractor — Text, Metadata, Amounts, Dates

Extract text, metadata, page count, emails, dates, and financial amounts from PDFs in bulk — with automatic OCR fallback for scanned pages. No paid AI APIs required.

Pricing

Pay per usage

Rating

0.0

(0)

Developer

Harsh

Actor stats

Bookmarked

Total users

Monthly active users

11 hours ago

Last modified

Categories

Automation

Upload PDF or ZIP File

pdfFile

Optional

Upload a single PDF, or a ZIP file containing many PDFs.

Type:string

Bulk PDF URLs List

urls

Optional

Paste public PDF links here (you can add more than one).

Type:array

AI provider (optional)

aiProvider

Optional

Only used for bank/account statement PDFs. Choose which AI to use, based on the API key you provide below.

Type:string

Default:gemini

Options:

geminiopenaiclaude

AI API Key (optional)

aiApiKey

Optional

Optional. If you provide your own API key for the selected provider, bank/account statement transactions will be organized into clean structured JSON. Your key is stored encrypted, we never save or see it, and we never charge for its use — any AI usage is billed directly to your own provider account. Without a key, everything still works exactly as before (free, local extraction only).

Type:string

AI model (advanced, optional)

aiModel

Optional

Leave blank to use a sensible default for the selected provider. Only change this if that default model becomes unavailable, or you want to use a specific model.

Type:string

PDF Text Extractor - Bulk PDF to Text & Metadata

santamaria-automations/pdf-extractor

Extract text and metadata from any PDF URL in bulk. Get page content, author, title, creation date, and more. Detects scanned PDFs that need OCR. Perfect for document analysis, research, and compliance.

NanoScrape

PDF Extract — Text, Tables & Metadata (OCR-ready)

sathvic_kollu/techtenstein-pdf-extract

Extract clean text, structured tables, and metadata from any PDF URL. Supports OCR for scanned documents. Ideal for building document pipelines, financial data extraction, invoice processing, and research automation.

Techtenstein Services Private Limited

PDF Toolkit — Extract Text, Metadata & Page Count

accurate_pouch/pdf-toolkit

Extract text from PDFs, read metadata (title, author, dates), count pages. Bulk processing from URLs. $0.003 per PDF.

Manchitt Sanan

PDF OCR Tool — Scanned PDF Text Extraction

junipr/pdf-ocr-tool

Run OCR on scanned PDFs and image-based documents. Extract text by page with language options, confidence scores, and searchable text exports.

junipr

PDF Text Extractor — Text & Metadata from URLs

darknezz/pdf-text-extractor

Extract clean text and metadata from any PDF by URL: full text, page count, title, author, dates as JSON. Perfect for AI pipelines, RAG ingestion, document search and content analysis. No API key needed.

Oaida Adrian

PDF Text Extractor — Markdown, OCR & Metadata

memo23/pdf-text-extractor

Turn any PDF URL into clean data: full text, LLM-ready Markdown, per-page content, and metadata. Reads scanned PDFs via OCR (23 languages), supports page ranges, and processes files in parallel. Export JSON, CSV, or Excel. Ideal for RAG pipelines, invoices, and research.

Muhamed Didovic

PDF to Text Extractor — Native Text & Metadata

junipr/pdf-to-text-extractor

Extract text, page metadata, outlines, links, and document info from PDFs with page-level output and automation-friendly exports.

junipr

PDF to Structured Data (Excel/JSON) with OCR

nibble/pdf-to-structured-data

Convert PDF invoices, forms, statements and reports into clean structured JSON (text, tables, key/values) with an OCR fallback for scanned pages.

Simon Fletcher

PDF Text Extractor

automation-lab/pdf-text-extractor

Extract text, metadata, and page-by-page content from PDF files. Provide PDF URLs and get structured JSON with full text, per-page text, page count, author, title, creation date, and more. Export as JSON, CSV, or Excel. No browser or proxy needed.