from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.action_chains import ActionChains
import pandas as pd
import time, random

chrome_driver_path = "D:\\lecturertask\\chromedriver.exe"
chrome_options = Options()

user_agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, seperti Gecko) Chrome/120.0.0.0 Safari/537.36"
chrome_options.add_argument(f"user-agent={user_agent}")
chrome_options.add_experimental_option("excludeSwitches", ["enable-automation"])
chrome_options.add_experimental_option("useAutomationExtension", False)

chrome_options.add_argument("--disable-gpu")
chrome_options.add_argument("--no-sandbox")
chrome_options.add_argument("--window-size=1920x1080")

service = Service(chrome_driver_path)
browser = webdriver.Chrome(service=service, options=chrome_options)

browser.get("https://sinta.kemdikbud.go.id/logins")
input("Login secara manual, lalu tekan ENTER untuk melanjutkan...")

browser.get("https://sinta.kemdikbud.go.id/affiliations/profile/447/?view=researches")
time.sleep(random.uniform(2, 6))

all_research = []
page = 1
action = ActionChains(browser)

while True:
    print(f"📄 Scraping halaman {page}...")

    research_items = browser.find_elements(By.CSS_SELECTOR, "div.ar-list-item.mb-5")
    if not research_items:
        print("❌ Tidak ada data di halaman ini, berhenti.")
        break

    for item in research_items:
        try:
            action.move_to_element(item).perform()
            time.sleep(random.uniform(0.5, 2))

            title = item.find_element(By.CSS_SELECTOR, "div.ar-title").text.strip()

            leader_element = item.find_elements(By.CSS_SELECTOR, "div.ar-meta a")
            leader = leader_element[0].text.strip() if leader_element else "Tidak Ada Leader"

            personil_elements = item.find_elements(By.CSS_SELECTOR, "div.ar-meta a[href*='authors/profile']")
            personil_list = "; ".join([p.text.strip() for p in personil_elements]) if personil_elements else "Tidak Ada Personil"

            research_type_element = item.find_elements(By.CSS_SELECTOR, "a.ar-pub")
            research_type = research_type_element[0].text.strip() if research_type_element else "Tidak Diketahui"

            year_element = item.find_elements(By.CSS_SELECTOR, "a.ar-year")
            year = year_element[0].text.strip().replace("📅 ", "") if year_element else "Tidak Ada Tahun"

            fund_element = item.find_elements(By.CSS_SELECTOR, "a.ar-quartile")
            fund = fund_element[0].text.strip().replace("📊 ", "") if fund_element else "Tidak Ada Dana"

            all_research.append([title, leader, personil_list, research_type, year, fund])
        except Exception as e:
            print(f"⚠️ Error mengambil data: {e}")

    try:
        next_button = WebDriverWait(browser, random.uniform(3, 7)).until(
            EC.presence_of_element_located((By.LINK_TEXT, str(page + 1)))
        )
        next_button.click()
        time.sleep(random.uniform(3, 7))
        page += 1
    except:
        print("✅ Tidak ada halaman berikutnya, selesai scraping.")
        break

df = pd.DataFrame(all_research, columns=["Judul", "Leader", "Personil", "Tipe Penelitian", "Tahun", "Dana"])
df.to_excel("data_penelitian.xlsx", index=False, engine="openpyxl")

print(f"🎉 Scraping selesai! {len(all_research)} data disimpan di 'data_penelitian.xlsx'")

browser.quit()