from fastapi import FastAPI, UploadFile
import markpdf

app = FastAPI()
client = markpdf.AsyncClient(api_key="YOUR_API_KEY")

@app.post("/upload")
async def upload(file: UploadFile):
    content = await file.read()
    markdown = await client.convert_raw_bytes(
        content,
        filename=file.filename,
        mode="fast",
    )
    return {"markdown": markdown}

markdown = client.convert_from_url(
    "https://bucket.example.com/manual-800-papages.pdf?sig=...",
    pages="120-145",
    mode="fast",
)

result = client.convert_from_url(
    pdf_url,
    output_url=presigned_put_url,       # pre-signed PUT to your bucket
    output_head_url=presigned_head_url,  # optional: detect cache hits
)

print(result.cached)      # True si ya existía y no se reprocesó
print(result.output_url)  # URL final del Markdown subido

import markpdf

client = markpdf.Client(api_key="YOUR_API_KEY")
PDF = "https://bucket.example.com/informe-anual.pdf?sig=..."

# 1. Index without converting the entire document
spine = client.pdf_index(PDF)
print(f"{spine.page_count} pápages, ~{spine.estimated_tokens_full} full tokens")

# 2. The agent decides which section he is interested in
target = next(s for s in spine.sections if "Resultados" in s.text)
following = next((s for s in spine.sections if s.page > target.page), None)
end_page = (following.page - 1) if following else spine.page_count

# 3. Bring Markdown only from that section
markdown = client.convert_from_url(PDF, pages=f"{target.page}-{end_page}", mode="fast")

result = client.convert_file(
    "documents.zip",
    input_format="zip",
    response_format="json",
)

print(result.markdown)  # Markdown concatenated from the supported documents inside the ZIP

import asyncio
import markpdf

async def convert_all(paths: list[str]) -> list[str]:
    async with markpdf.AsyncClient(api_key="YOUR_API_KEY", max_retries=3) as client:
        tasks = [client.convert_file(p, mode="fast") for p in paths]
        return await asyncio.gather(*tasks, return_exceptions=True)

results = asyncio.run(convert_all(["a.pdf", "b.docx", "c.pdf"]))
for path, result in zip(["a.pdf", "b.docx", "c.pdf"], results):
    if isinstance(result, Exception):
        print(f"{path} falló: {result}")
    else:
        print(f"{path}: {len(result)} caracteres")