Update scripts/scraper_pddikti.py

scripts/scraper_pddikti.py

@@ -2,12 +2,30 @@ import requests
 import pandas as pd
 
 def run_scraping_logic():
-    # Contoh scraping
-    url = "http://universities.hipolabs.com/search?country=Indonesia"
-    res = requests.get(url)
-    df = pd.DataFrame(res.json())
+    print("--- MEMULAI PROSES PENARIKAN DATA DUMMY ---")
     
-    # Logika cleaning atau upload ke BigQuery ditaruh di sini
-    output_path = "/opt/airflow/logs/data_akademik.csv"
-    df.to_csv(output_path, index=False)
-    return f"Berhasil menarik {len(df)} data."
+    # URL API Publik (Data Universitas)
+    url = "http://universities.hipolabs.com/search?country=Indonesia"
+    
+    try:
+        # 1. Extract
+        response = requests.get(url, timeout=10)
+        data = response.json()
+        
+        # 2. Transform (Gunakan Pandas)
+        df = pd.DataFrame(data)
+        
+        # Kita ambil 5 data teratas saja untuk ditampilkan di log
+        preview_data = df[['name', 'web_pages']].head(5)
+        
+        # 3. Load (Simulasi: Tampilkan ke Log Airflow)
+        print("HASIL PENARIKAN DATA (5 Teratas):")
+        print("====================================================")
+        print(preview_data.to_string(index=False))
+        print("====================================================")
+        print(f"Total data yang berhasil ditarik: {len(df)} baris.")
+        
+        return True
+    except Exception as e:
+        print(f"TERJADI KESALAHAN: {str(e)}")
+        return False