import customtkinter as ctk
import threading
import queue
import os
import time
import urllib.parse
import requests
import re
from datetime import datetime
from playwright.sync_api import sync_playwright


USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"




def sanitize_filename(title, max_length=150):
    title = re.sub(r'[\\/:*?"<>|]', '', title)
    title = re.sub(r'\s+', ' ', title).strip()
    return title[:max_length]




class ScholarPDFBot(ctk.CTk):
    def __init__(self):
        super().__init__()


        ctk.set_appearance_mode("dark")
        ctk.set_default_color_theme("blue")


        self.title("Akademik Makale Botu")
        self.geometry("1000x700")


        self.log_queue = queue.Queue()
        self.is_running = False


        self.create_widgets()
        self.after(100, self.process_logs)


    # ---------------- GUI ---------------- #
    def create_widgets(self):
        ctk.CTkLabel(
            self,
            text="Akademik Makale Botu",
            font=ctk.CTkFont(size=22, weight="bold")
        ).pack(pady=15)


        frame = ctk.CTkFrame(self)
        frame.pack(fill="x", padx=20)


        ctk.CTkLabel(frame, text="Anahtar Kelime").grid(row=0, column=0, padx=5, pady=10, sticky="w")
        self.keyword_entry = ctk.CTkEntry(frame, width=400)
        self.keyword_entry.grid(row=0, column=1, padx=5)


        ctk.CTkLabel(frame, text="Sayfa Sayısı").grid(row=1, column=0, padx=5, pady=10, sticky="w")
        self.page_entry = ctk.CTkEntry(frame, width=100)
        self.page_entry.insert(0, "3")
        self.page_entry.grid(row=1, column=1, padx=5, sticky="w")


        ctk.CTkLabel(frame, text="İndirme Klasörü").grid(row=2, column=0, padx=5, pady=10, sticky="w")
        self.folder_entry = ctk.CTkEntry(frame, width=400)
        self.folder_entry.insert(0, "pdfler")
        self.folder_entry.grid(row=2, column=1, padx=5)


        self.start_btn = ctk.CTkButton(self, text="Botu Başlat", command=self.start_bot)
        self.start_btn.pack(pady=10)


        self.log_box = ctk.CTkTextbox(self, height=400)
        self.log_box.pack(fill="both", expand=True, padx=20, pady=10)


    def log(self, msg):
        timestamp = datetime.now().strftime("%H:%M:%S")
        self.log_queue.put(f"[{timestamp}] {msg}")


    def process_logs(self):
        while not self.log_queue.empty():
            self.log_box.insert("end", self.log_queue.get() + "\n")
            self.log_box.see("end")
        self.after(100, self.process_logs)


    # ---------------- BOT ---------------- #
    def start_bot(self):
        if self.is_running:
            return


        keyword = self.keyword_entry.get().strip()
        pages = int(self.page_entry.get())
        folder = self.folder_entry.get().strip()


        if not keyword:
            self.log("❌ Anahtar kelime boş")
            return


        os.makedirs(folder, exist_ok=True)


        self.is_running = True
        self.start_btn.configure(state="disabled")


        threading.Thread(
            target=self.run_bot,
            args=(keyword, pages, folder),
            daemon=True
        ).start()


    def run_bot(self, keyword, pages, folder):
        encoded_kw = urllib.parse.quote(keyword)
        self.log("🚀 Bot başlatıldı")


        with sync_playwright() as p:
            browser = p.chromium.launch(headless=True)
            context = browser.new_context(user_agent=USER_AGENT)
            page = context.new_page()


            total_downloaded = 0


            for page_index in range(pages):
                start = page_index * 10
                url = f"https://scholar.google.com/scholar?start={start}&q={encoded_kw}&hl=tr&as_sdt=0,5"


                self.log(f"🔍 Derinlemesine araştırılıyor... {page_index + 1}")
                page.goto(url, timeout=60000)
                page.wait_for_timeout(2000)


                results = page.query_selector_all("div.gs_r")


                for result in results:
                    title_text = "makale"
                    title_el = result.query_selector("h3.gs_rt")
                    if title_el:
                        title_text = title_el.inner_text()


                    safe_title = sanitize_filename(title_text)


                    pdf_urls = []


                    # SOL [PDF]
                    left_pdf = result.query_selector(".gs_or_ggsm a")
                    if left_pdf:
                        href = left_pdf.get_attribute("href")
                        if href:
                            pdf_urls.append(href)


                    # MAKALE İÇİ PDF
                    if not pdf_urls:
                        title_link = result.query_selector("h3.gs_rt a")
                        if title_link:
                            article_url = title_link.get_attribute("href")
                            if article_url:
                                try:
                                    tmp = context.new_page()
                                    tmp.goto(article_url, timeout=30000)
                                    tmp.wait_for_timeout(2000)


                                    links = tmp.query_selector_all("a[href]")
                                    for l in links:
                                        href = l.get_attribute("href")
                                        if href and ".pdf" in href.lower():
                                            pdf_urls.append(href)
                                            break


                                    tmp.close()
                                except:
                                    pass


                    for pdf_url in pdf_urls:
                        filename = f"{safe_title}.pdf"
                        path = os.path.join(folder, filename)


                        if os.path.exists(path):
                            self.log(f"⏩ Zaten var: {filename}")
                            continue


                        try:
                            self.log(f"⬇️ Makale indiriliyor: {filename}")
                            self.download_pdf(pdf_url, path)
                            total_downloaded += 1
                            self.log("✅ Kaydedildi")
                        except Exception as e:
                            self.log(f"❌ İndirme hatası: {e}")


                        time.sleep(1)


            browser.close()


        self.log(f"🎉 Tamamlandı – Toplam PDF: {total_downloaded}")
        self.start_btn.configure(state="normal")
        self.is_running = False


    def download_pdf(self, url, path):
        headers = {
            "User-Agent": USER_AGENT,
            "Referer": "https://scholar.google.com/"
        }


        r = requests.get(url, headers=headers, timeout=40, allow_redirects=True)
        r.raise_for_status()


        content_type = r.headers.get("Content-Type", "").lower()
        if not ("pdf" in content_type or "octet-stream" in content_type or url.lower().endswith(".pdf")):
            raise Exception("PDF değil")


        with open(path, "wb") as f:
            f.write(r.content)




if __name__ == "__main__":
    app = ScholarPDFBot()
    app.mainloop()