Pricing

$50.00 / 1,000 page processeds

Historical Records Extractor

Turn scans of handwritten and historical records into clean text. One dataset row per page, each with a signed delivery receipt. Pay per delivered page in USD.

Pricing

$50.00 / 1,000 page processeds

Rating

0.0

(0)

Developer

HAL 8

Actor stats

Bookmarked

Total users

Monthly active users

6 days ago

Last modified

Categories

Automation

Document URLs

documentUrls

Optional

Direct links to the scans to extract: PDF, PNG, JPEG or WebP. For local files, upload them to a key-value store (or any file host) first and paste the direct link here. Leave as-is to try the built-in example (a 1940 US census page).

Type:array

Default:

[
  "https://upload.wikimedia.org/wikipedia/commons/thumb/d/d0/1940_Census_Population_Schedules_-_Alabama_-_Jefferson_County_-_ED_68-27_-_DPLA_-_bf9de06eabc448362f928c6bf7afe561_%28page_1%29.jpg/1920px-1940_Census_Population_Schedules_-_Alabama_-_Jefferson_County_-_ED_68-27_-_DPLA_-_bf9de06eabc448362f928c6bf7afe561_%28page_1%29.jpg"
]

Output format

outputFormat

Optional

Shape of the extracted content per page. Markdown returns plain text with tables written out as text; HTML returns richer markup; JSON returns layout blocks.

Type:string

Default:markdown

Options:

markdownhtmljson

Max pages per document

maxPagesPerDocument

Optional

Safety cap for large PDFs. Pages beyond this count are skipped and reported.

Type:integer

Minimum:1

Maximum:200

Default:50

Include delivery receipts

includeReceipts

Optional

Attach the signed per-page delivery receipt to every dataset row. The receipt records which engine handled the page and lets you verify the delivery offline, without an account and without trusting us.

Type:boolean

Default:true

PDF Text Extractor API - URL to Text, Per-Page, Batch

gratifying_graph/pdf-extract-api

Turn any public PDF URL into clean text and metadata. Per-page output, batch processing, and a synchronous API mode for AI agents. Pay per page extracted, cheaper than the alternatives.

Jimmy A

Meteociel Historical Scraper

valentin-b117/meteociel-historical-scraper

Get the historical weather for a specific city and date

Valentin B117

Facebook Page Scraper

khadinakbar/facebook-page-scraper

Scrape public Facebook page/profile URLs into clean page profile records plus optional recent post records. Extracts names, categories, contacts, websites, followers, likes, ratings, ad status, post text, timestamps, engagement counts, media, and links. No login required. MCP-ready.

Khadin Akbar

PDF Text Extractor — text, metadata, per page

x402opklaar/pdf-text-extractor

PDF URLs in, clean text out: full text, per-page text, title/author/page-count metadata. No browser, no OCR overhead — fast digital-PDF extraction. You only pay for PDFs that actually extract; failures are free.

Opklaar

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.

Stas Persiianenko

347

Vision OCR MCP

accelerationengg/vision-ocr-mcp

Extract text from images instantly. Turn receipts, invoices, documents, and handwritten notes into structured data.

Acceleration

5.0

PDF to Text API — Extract PDF Text to Clean JSON for LLM & RAG

omao/pdf-text

Extract clean, structured text from any PDF by URL, page by page. Returns one row per page with de-hyphenated, whitespace-normalized text. Fast, no setup.

Marouane Oulabass

PDF Split — Extract Pages & Ranges

hipersoft/pdf-split

Split one PDF into multiple files by page ranges, every N pages, or one file per page. Break big scans, statements and reports into per-record documents in one run.

hiper soft

PDF Text Extractor — fast PDF to text & JSON, per page

amanatools/pdf-text-extractor

Extract clean plain text from PDF files: whole document plus every page separately, in true reading order — multi-column layouts and RTL (Arabic) handled. No OCR overhead, no API keys. Pay per page delivered; scanned pages are detected, reported and never billed.

Dos

Website Lead Extractor: Emails, Phones & Addresses

f0rty7even/website-lead-extractor

Turn a list of company websites into a clean B2B lead list. Extracts emails, phone numbers in E.164, postal addresses, PO boxes, VAT and company registration numbers and social profiles, verifies every email against DNS, and returns one row per company. Pay per company, never per page.