{
 "schema_version": 1,
 "generated": "2026-10-31",
 "id": "ocrmypdf-ocrmypdf--make-scanned-pdfs-searchable",
 "repo": "ocrmypdf/OCRmyPDF",
 "repo_url": "https://github.com/ocrmypdf/OCRmyPDF",
 "repo_slug": "ocrmypdf-ocrmypdf",
 "title": "Make your scanned PDFs searchable",
 "page_title": "How to make your scanned PDFs searchable with OC Rmy PDF",
 "summary": "Install OC Rmy PDF and add a hidden text layer to scans so you can search and copy text.",
 "who": "Someone with a drawer of scanned bills, letters and manuals saved as image-only PDFs.",
 "problem": "Scanned PDFs are just pictures, so search, copy and paste do not work.",
 "outcome": "Searchable PDF/A files that look the same as the originals and are often smaller.",
 "steps": [
  "Install it, for example `apt install ocrmypdf` on Debian or Ubuntu, or `brew install ocrmypdf` on macOS",
  "Add an OCR layer with `ocrmypdf --output-type pdfa input.pdf output.pdf`",
  "Straighten crooked scans with `ocrmypdf --deskew input.pdf output.pdf`",
  "Turn a photo into a one page PDF with `ocrmypdf input.jpg output.pdf`",
  "See every option with `ocrmypdf --help`"
 ],
 "agent_prompt": "Install ocrmypdf/OCRmyPDF and run it on every PDF in <folder> with `--output-type pdfa` and `--deskew`, writing results to <output folder>. Skip files that already have text and report the size before and after.",
 "agents": [
  "claude-code",
  "codex",
  "cursor"
 ],
 "difficulty": "Beginner",
 "time": "15 minutes",
 "basis": "readme",
 "caveat": "OCR accuracy depends on scan quality; Tesseract struggles with handwriting and very low resolution images.",
 "category": "Life admin",
 "tags": [
  "Life admin"
 ],
 "lang": "python",
 "requirements": [
  "Linux, Windows (or WSL), macOS or FreeBSD, or the Docker image",
  "Ghostscript and Tesseract OCR installed",
  "Tesseract language packs for non-English documents"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": true,
 "score": 1.0,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/ocrmypdf-ocrmypdf/make-scanned-pdfs-searchable/",
 "md": "https://dedupedai.com/use-cases/ocrmypdf-ocrmypdf/make-scanned-pdfs-searchable/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/ocrmypdf-ocrmypdf--make-scanned-pdfs-searchable.json",
 "api_version": "v1"
}