Files
Brancheneinstufung2/company-explorer/backend/scripts/import_job_titles.py
2026-02-20 13:25:21 +00:00

96 lines
3.1 KiB
Python
Raw Blame History

This file contains invisible Unicode characters
This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
import sys
import os
import csv
import argparse
from datetime import datetime
# Setup Environment
sys.path.append(os.path.join(os.path.dirname(__file__), "../../"))
from backend.database import SessionLocal, RawJobTitle, init_db, engine, Base
def import_titles(file_path: str, delimiter: str = ';'):
print(f"🚀 Starting Import from {file_path}...")
# Ensure Table Exists
RawJobTitle.__table__.create(bind=engine, checkfirst=True)
db = SessionLocal()
total_rows = 0
new_titles = 0
updated_titles = 0
try:
with open(file_path, 'r', encoding='utf-8-sig') as f: # utf-8-sig handles BOM from Excel
# Try to detect header
sample = f.read(1024)
has_header = csv.Sniffer().has_header(sample)
f.seek(0)
reader = csv.reader(f, delimiter=delimiter)
if has_header:
headers = next(reader)
print(f" Header detected: {headers}")
# Try to find the right column index
col_idx = 0
for i, h in enumerate(headers):
if h.lower() in ['funktion', 'jobtitle', 'title', 'position', 'rolle']:
col_idx = i
print(f" -> Using column '{h}' (Index {i})")
break
else:
col_idx = 0
print(" No header detected, using first column.")
# Process Rows
for row in reader:
if not row: continue
if len(row) <= col_idx: continue
raw_title = row[col_idx].strip()
if not raw_title: continue # Skip empty
total_rows += 1
# Check existance
existing = db.query(RawJobTitle).filter(RawJobTitle.title == raw_title).first()
if existing:
existing.count += 1
existing.updated_at = datetime.utcnow()
updated_titles += 1
else:
db.add(RawJobTitle(title=raw_title, count=1))
new_titles += 1
if total_rows % 100 == 0:
db.commit()
print(f" Processed {total_rows} rows...", end='\r')
db.commit()
except Exception as e:
print(f"\n❌ Error: {e}")
db.rollback()
finally:
db.close()
print(f"\n✅ Import Complete.")
print(f" Total Processed: {total_rows}")
print(f" New Unique Titles: {new_titles}")
print(f" Updated Frequencies: {updated_titles}")
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="Import Job Titles from CSV")
parser.add_argument("file", help="Path to CSV file")
parser.add_argument("--delimiter", default=";", help="CSV Delimiter (default: ';')")
args = parser.parse_args()
if not os.path.exists(args.file):
print(f"❌ File not found: {args.file}")
sys.exit(1)
import_titles(args.file, args.delimiter)