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>
23 lines
638 B
Python
23 lines
638 B
Python
"""XLSX text extraction using openpyxl."""
|
|
|
|
from openpyxl import load_workbook
|
|
|
|
|
|
def extract_xlsx(file_path: str) -> str:
|
|
"""Extract text from an XLSX file."""
|
|
wb = load_workbook(file_path, read_only=True, data_only=True)
|
|
sheets = []
|
|
|
|
for sheet_name in wb.sheetnames:
|
|
ws = wb[sheet_name]
|
|
rows = []
|
|
for row in ws.iter_rows(values_only=True):
|
|
cells = [str(c) for c in row if c is not None]
|
|
if cells:
|
|
rows.append(" | ".join(cells))
|
|
if rows:
|
|
sheets.append(f"[{sheet_name}]\n" + "\n".join(rows))
|
|
|
|
wb.close()
|
|
return "\n\n".join(sheets)
|