lambda_학사일정,샘물알림

lambda_tem/lambda_schedule.py

@@ -0,0 +1,144 @@
+import json
+import re
+import pymysql
+import os
+from datetime import datetime
+from bs4 import BeautifulSoup
+from selenium import webdriver
+from selenium.webdriver.chrome.options import Options
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+
+# ✅ 환경변수 기반 RDS 설정
+DB_HOST = os.environ.get("DB_HOST", "oneteam.cfog0q0ku1kn.ap-northeast-2.rds.amazonaws.com")
+DB_USER = os.environ.get("DB_USER", "admin")
+DB_PASSWORD = os.environ.get("DB_PASSWORD", "Oneteam2025!")
+DB_NAME = os.environ.get("DB_NAME", "oneteam_DB")
+DB_PORT = int(os.environ.get("DB_PORT", 3306))
+TABLE_NAME = "smu_schedule"
+
+def crawl_schedule(driver, wait, year):
+    url = f"https://www.smu.ac.kr/kor/life/academicCalendar.do?mode=list&srYear={year}&srMonth=1"
+    driver.get(url)
+    try:
+        wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, "div.schedule-list table")))
+    except:
+        return []
+
+    soup = BeautifulSoup(driver.page_source, "html.parser")
+    table = soup.select_one("div.year-schedule div.schedule-list table")
+    data = []
+
+    current_year, current_month = None, None
+
+    for row in table.select("tbody tr"):
+        tds = row.find_all("td")
+        if tds[0].has_attr("rowspan"):
+            m = re.match(r"(\d{4})년\s*(\d{1,2})월", tds[0].text.strip())
+            if m:
+                current_year = int(m.group(1))
+                current_month = int(m.group(2))
+            date_range = tds[1].get_text(strip=True)
+            content = tds[2].get_text(strip=True)
+        else:
+            date_range = tds[0].get_text(strip=True)
+            content = tds[1].get_text(strip=True)
+
+        date_match = re.match(r"(\d{1,2})\.(\d{1,2})\([^\)]*\) ~ (\d{1,2})\.(\d{1,2})\([^\)]*\)", date_range)
+        if date_match and current_year and current_month:
+            sm, sd, em, ed = map(int, date_match.groups())
+            start_year = current_year - 1 if sm > current_month else current_year
+            end_year = start_year if em >= sm else start_year + 1
+            start_date = f"{start_year}.{sm:02d}.{sd:02d}"
+            end_date = f"{end_year}.{em:02d}.{ed:02d}"
+        else:
+            start_date, end_date = None, None
+
+        data.append({
+            "start_date": start_date,
+            "end_date": end_date,
+            "content": content.strip()
+        })
+
+    return data
+
+
+def lambda_handler(event, context):
+    options = Options()
+    options.add_argument("--headless")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    driver = webdriver.Chrome(options=options)
+    wait = WebDriverWait(driver, 10)
+
+    conn = None
+    cursor = None
+
+    try:
+        # ✅ DB 연결
+        conn = pymysql.connect(
+            host=DB_HOST,
+            user=DB_USER,
+            password=DB_PASSWORD,
+            database=DB_NAME,
+            port=DB_PORT,
+            charset='utf8mb4',
+            cursorclass=pymysql.cursors.DictCursor
+        )
+        cursor = conn.cursor()
+
+        # ✅ 테이블 생성
+        create_sql = f"""
+        CREATE TABLE IF NOT EXISTS {TABLE_NAME} (
+            id INT AUTO_INCREMENT PRIMARY KEY,
+            start_date VARCHAR(10),
+            end_date VARCHAR(10),
+            content TEXT,
+            created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
+        )
+        """
+        cursor.execute(create_sql) 
+
+        # ✅ 기존 데이터 조회
+        cursor.execute(f"SELECT start_date, end_date, content FROM {TABLE_NAME}")
+        existing = set((row["start_date"], row["end_date"], row["content"]) for row in cursor.fetchall())
+
+        # ✅ 수집 연도
+        current_year = datetime.now().year
+        target_years = range(current_year, current_year + 2)
+
+        total_saved = 0
+        for year in target_years:
+            data = crawl_schedule(driver, wait, year)
+            new_data = [
+                (d["start_date"], d["end_date"], d["content"])
+                for d in data if None not in (d["start_date"], d["end_date"], d["content"])
+                and (d["start_date"], d["end_date"], d["content"]) not in existing
+            ]
+            if new_data:
+                cursor.executemany(
+                    f"INSERT INTO {TABLE_NAME} (start_date, end_date, content) VALUES (%s, %s, %s)",
+                    new_data
+                )
+                conn.commit()
+                total_saved += len(new_data)
+
+    except Exception as e:
+        return {
+            "statusCode": 500,
+            "body": json.dumps({"error": str(e)})
+        }
+
+    finally:
+        if cursor: cursor.close()
+        if conn: conn.close()
+        driver.quit()
+
+    return {
+        "statusCode": 200,
+        "body": json.dumps({
+            "message": f"총 저장된 일정: {total_saved}개",
+            "saved_count": total_saved
+        })
+    }

lambda_tem/lambda_smu_alarm.py

@@ -0,0 +1,134 @@
+import json
+import re
+import time
+import os
+import pymysql
+from datetime import datetime, timedelta
+from bs4 import BeautifulSoup
+from selenium import webdriver
+from selenium.webdriver.chrome.options import Options
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+
+# ✅ 날짜 파싱 함수
+def parse_date(text):
+    today = datetime.today()
+    text = text.strip()
+    if "방금 전" in text or "초 전" in text or "분 전" in text or "시간 전" in text:
+        return today.strftime("%Y-%m-%d")
+    match = re.search(r"(\d+)\s*일\s*전", text)
+    if match:
+        return (today - timedelta(days=int(match.group(1)))).strftime("%Y-%m-%d")
+    match = re.search(r"(\d{4}-\d{2}-\d{2})", text)
+    return match.group(1) if match else today.strftime("%Y-%m-%d")
+
+def lambda_handler(event, context):
+    # ✅ 환경설정 (필요시 os.environ.get(...)로 수정)
+    USER_ID = "202210852"  # os.environ.get("SMU_ID")
+    USER_PASSWORD = "manse1223~!"  # os.environ.get("SMU_PW")
+
+    DB_HOST = "oneteam.cfog0q0ku1kn.ap-northeast-2.rds.amazonaws.com"
+    DB_USER = "admin"
+    DB_PASSWORD = "Oneteam2025!"  # os.environ.get("DB_PASSWORD")
+    DB_NAME = "oneteam_DB"
+    DB_PORT = 3306
+    TABLE_NAME = "notifications_cleaned"
+
+    # ✅ Selenium 설정
+    options = Options()
+    options.add_argument("--headless")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    driver = webdriver.Chrome(options=options)
+    wait = WebDriverWait(driver, 10)
+
+    try:
+        # ✅ 로그인
+        driver.get("https://smsso.smu.ac.kr/svc/tk/Auth.do?ac=Y&ifa=N&id=portal&")
+        wait.until(EC.presence_of_element_located((By.ID, "user_id"))).send_keys(USER_ID)
+        wait.until(EC.presence_of_element_located((By.ID, "user_password"))).send_keys(USER_PASSWORD)
+        wait.until(EC.element_to_be_clickable((By.XPATH, "//button[contains(text(), '로그인')]"))).click()
+        wait.until(EC.url_contains("portal.smu.ac.kr/p/S00"))
+
+        # ✅ 알림 아이콘 클릭
+        wait.until(EC.element_to_be_clickable((By.ID, "countTag"))).click()
+        time.sleep(2)
+
+        # ✅ 알림 HTML 추출
+        html = driver.find_element(By.ID, "_notiList").get_attribute("innerHTML")
+        soup = BeautifulSoup(html, "html.parser")
+        all_lis = soup.select("li")
+
+        # ✅ DB에서 기존 데이터 가져오기
+        conn = pymysql.connect(
+            host=DB_HOST,
+            user=DB_USER,
+            password=DB_PASSWORD,
+            database=DB_NAME,
+            port=DB_PORT,
+            charset='utf8mb4'
+        )
+        cursor = conn.cursor()
+        cursor.execute(f"CREATE TABLE IF NOT EXISTS {TABLE_NAME} ("
+                       "id INT AUTO_INCREMENT PRIMARY KEY,"
+                       "date VARCHAR(10),"
+                       "content TEXT,"
+                       "link VARCHAR(500),"
+                       "created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP)")
+        cursor.execute(f"SELECT date, content FROM {TABLE_NAME}")
+        existing = set((row[0], row[1]) for row in cursor.fetchall())
+
+        # ✅ 알림 파싱 및 중복 제거
+        results = []
+        i = 0
+        max_count = 30
+        while i < len(all_lis) - 1 and len(results) < max_count:
+            content_li = all_lis[i]
+            time_li = all_lis[i + 1]
+
+            if "time" not in time_li.get("class", []):
+                i += 1
+                continue
+
+            date = parse_date(time_li.get_text(strip=True))
+            onclick = content_li.get("onclick", "")
+            link_match = re.search(r"location\.href='([^']+)'", onclick) if onclick else None
+            link = "https://www.smu.ac.kr" + link_match.group(1) if link_match else ""
+            content = content_li.get_text(" ", strip=True)
+
+            if (date, content) in existing:
+                i += 2
+                continue
+
+            results.append((date, content, link))
+            i += 2
+
+        # ✅ 새 데이터 저장
+        saved_count = 0
+        if results:
+            insert_sql = f"INSERT INTO {TABLE_NAME} (date, content, link) VALUES (%s, %s, %s)"
+            cursor.executemany(insert_sql, results)
+            conn.commit()
+            saved_count = cursor.rowcount
+
+        cursor.close()
+        conn.close()
+        driver.quit()
+
+        return {
+            "statusCode": 200,
+            "body": json.dumps({
+                "message": f"✅ 새 알림 저장: {saved_count}개",
+                "saved_count": saved_count
+            })
+        }
+
+    except Exception as e:
+        driver.quit()
+        return {
+            "statusCode": 500,
+            "body": json.dumps({
+                "error": str(e)
+            })
+        }