hardparse 0.2.0

Turn any PDF or image into clean Markdown or LaTeX. Free keyless API.

hardparse

Turn any PDF or image into clean Markdown or LaTeX — tables as real Markdown tables, formulas as LaTeX, handwriting as readable text.

Free, keyless API. 100 requests/day per IP. Zero dependencies.

Install

pip install hardparse

Use

from hardparse import parse

md = parse("invoice.pdf")
print(md)

That's it. No key. No signup.

Want LaTeX instead?

from hardparse import parse_latex

tex = parse_latex("paper.pdf")
open("out.tex", "w").write(tex)
# $ xelatex out.tex  →  out.pdf — ready for your paper or thesis

The returned string is a compilable standalone .tex document — fontspec, amsmath, longtable already in the preamble, xelatex-ready.

More

from hardparse import parse_full

result = parse_full("scan.png")
print(result.markdown)
print(result.page_count, "pages,", result.processing_time_ms, "ms")
print("remaining today:", result.remaining)

Works with paths, bytes, or any file-like object:

parse(Path("doc.pdf"))
parse(open("doc.pdf", "rb"))
parse(b"...raw bytes...")

Rate limits

Anonymous, per-IP: 100 requests / 24h rolling window. On exceed:

from hardparse import parse, RateLimitError

try:
    md = parse("doc.pdf")
except RateLimitError as e:
    print(f"hit limit: used {e.used}/{e.limit}, retry in {e.retry_after}s")

Need more? Email [e-mail].

Self-host / custom endpoint

from hardparse import Client
client = Client(base_url="https://your-host")
md = client.parse("doc.pdf")

Or set HARDPARSE_BASE_URL.

Supported inputs

PDF, PNG, JPG, TIFF, HEIC, WEBP, BMP. 200 MB max.