kma-data-api/extract_continuous_data.py

105 lines
3.6 KiB
Python

import os
import requests
import csv
from datetime import datetime, timedelta
import time
# 1. API 인증키 설정
def get_env_variable(var_name):
if os.path.exists(".env"):
with open(".env", "r") as f:
for line in f:
if "=" in line:
k, v = line.split("=", 1)
if k.strip() == var_name:
return v.strip()
return os.getenv(var_name)
API_KEY = get_env_variable("WEATHER_KEY") or get_env_variable("KMA_API_KEY")
# 2. 정밀 좌표 설정 (NetCDF 추출값)
TARGET_LAT = 34.925323
TARGET_LON = 127.710838
# 3. 추출 기간 설정
start_dt = datetime(2026, 4, 1, 0, 0)
end_dt = datetime(2026, 5, 7, 23, 55)
# 4. API 설정
BASE_URL = "https://apihub.kma.go.kr/api/typ01/url/sfc_nc_var.php"
OBS_ELEMENTS = "ta,hm,td,wd_10m,ws_10m,uu,vv,rn_ox,vs"
INTERVAL = 5
def extract_all():
current_dt = start_dt
all_data = []
total_hours = int((end_dt - start_dt).total_seconds() / 3600) + 1
count = 0
print(f"--- 연속 데이터 추출 시작 (총 {total_hours}개 구간) ---")
output_filename = "weather_data_continuous_20260401_20260507.csv"
keys = ["tm", "ta", "hm", "td", "wd_10m", "ws_10m", "uu", "vv", "rn_ox", "vs"]
with open(output_filename, 'w', newline='', encoding='utf-8-sig') as f:
writer = csv.DictWriter(f, fieldnames=keys)
writer.writeheader()
while current_dt <= end_dt:
# 1시간 단위 요청
tm1 = current_dt
tm2 = current_dt + timedelta(minutes=55) # 12개 데이터 (5분 간격)
if tm2 > end_dt: tm2 = end_dt
params = {
"tm1": tm1.strftime("%Y%m%d%H%M"),
"tm2": tm2.strftime("%Y%m%d%H%M"),
"obs": OBS_ELEMENTS,
"itv": INTERVAL,
"lon": TARGET_LON,
"lat": TARGET_LAT,
"help": 0,
"authKey": API_KEY
}
try:
response = requests.get(BASE_URL, params=params, timeout=30)
response.raise_for_status()
rows = []
for line in response.text.strip().split('\n'):
if line.startswith('#') or not line.strip(): continue
parts = [p.strip() for p in line.replace(',', ' ').split()]
if len(parts) >= 10:
rows.append({
"tm": parts[0],
"ta": parts[1],
"hm": parts[2],
"td": parts[3],
"wd_10m": parts[4],
"ws_10m": parts[5],
"uu": parts[6],
"vv": parts[7],
"rn_ox": parts[8],
"vs": parts[9]
})
if rows:
writer.writerows(rows)
count += 1
if count % 50 == 0:
print(f" 진행률: {count}/{total_hours} 구간 완료 ({current_dt.strftime('%Y-%m-%d %H:%M')})")
except Exception as e:
print(f" Error at {tm1}: {e}")
current_dt += timedelta(hours=1)
# API 부하 방지를 위한 미세 지연 (필요 시)
# time.sleep(0.05)
print(f"\n--- 추출 완료: {output_filename} ---")
if __name__ == "__main__":
extract_all()