364d2c69ff
New standalone Python/FastAPI service for automatic compliance document scanning, LLM-based classification, IPFS archival, and gap analysis. Includes extractors (PDF, DOCX, XLSX, PPTX), keyword fallback classifier, compliance matrix, and full REST API on port 8098. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
16 lines
343 B
Python
16 lines
343 B
Python
"""PDF text extraction using PyMuPDF (fitz)."""
|
|
|
|
import fitz
|
|
|
|
|
|
def extract_pdf(file_path: str) -> str:
|
|
"""Extract text from a PDF file."""
|
|
doc = fitz.open(file_path)
|
|
pages = []
|
|
for page in doc:
|
|
text = page.get_text()
|
|
if text.strip():
|
|
pages.append(text)
|
|
doc.close()
|
|
return "\n\n".join(pages)
|