Upload 3 files

Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.11-slim
+
+RUN apt-get update && apt-get install -y \
+    wget curl gnupg ca-certificates \
+    libnss3 libxss1 libasound2 libatk-bridge2.0-0 \
+    libgtk-3-0 libgbm1 libxshmfence1 \
+    --no-install-recommends && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+RUN playwright install chromium --with-deps
+
+COPY . .
+EXPOSE 7860
+CMD ["python", "app.py"]

app.py

@@ -0,0 +1,296 @@
+# ============================================================
+# 🔱 Emperor Fetch Space — app.py
+# نفس كود السحب من main.py حرفياً + Gradio wrapper فوقيه
+# ============================================================
+
+import os, asyncio, base64, json, subprocess, io
+from playwright.async_api import async_playwright
+import cloudscraper, requests
+from bs4 import BeautifulSoup
+from PIL import Image
+import gradio as gr
+
+# ── تنزيل Chromium تلقائياً ───────────────────────────────
+chromium_path = os.path.expanduser(
+    "~/.cache/ms-playwright/chromium_headless_shell-1223"
+    "/chrome-headless-shell-linux64/chrome-headless-shell"
+)
+if not os.path.exists(chromium_path):
+    print("⬇️ جاري تنزيل Chromium...", flush=True)
+    subprocess.run(["playwright", "install", "chromium", "--with-deps"], check=True)
+    print("✅ Chromium جاهز", flush=True)
+
+# ── الإعدادات ─────────────────────────────────────────────
+API_SECRET = os.getenv("FETCH_SECRET", "emperor_secret_key")
+browser_semaphore = asyncio.Semaphore(1)
+
+
+# ============================================================
+# ✅ نفس fetch_manhwa من main.py حرفياً
+# ============================================================
+async def fetch_manhwa(url):
+    print(f"⏳ طلب سحب جديد لـ {url} - في انتظار دور المتصفح...", flush=True)
+
+    async with browser_semaphore:
+        print(f"🚀 المتصفح متاح الآن! بدء السحب لـ {url}...", flush=True)
+
+        async with async_playwright() as p:
+            browser = await p.chromium.launch(
+                headless=True,
+                args=[
+                    "--no-sandbox",
+                    "--disable-setuid-sandbox",
+                    "--disable-dev-shm-usage",
+                    "--disable-gpu",
+                    "--no-first-run",
+                    "--no-zygote",
+                    "--single-process",
+                    "--js-flags=--max-old-space-size=256",
+                ]
+            )
+
+            context = await browser.new_context(
+                user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36",
+                viewport={"width": 1280, "height": 1000},
+                extra_http_headers={"Cache-Control": "no-cache", "Pragma": "no-cache"}
+            )
+            page = await context.new_page()
+
+            captured = []
+            captured_urls = set()
+            skip_kw = ["logo", "icon", "avatar", "banner", "ads", "pixel", "1x1", ".gif", "loader", "thumb", "widgets"]
+
+            async def on_response(response):
+                try:
+                    if response.request.resource_type != "image":
+                        return
+                    rurl = response.url
+                    if any(kw in rurl.lower() for kw in skip_kw):
+                        return
+                    if rurl in captured_urls:
+                        return
+                    body = await response.body()
+                    if len(body) > 4000:
+                        captured.append(body)
+                        captured_urls.add(rurl)
+                        print(f"  📸 [{len(captured)}] {rurl[-50:]}")
+                        del body
+                except:
+                    pass
+
+            page.on("response", on_response)
+
+            try:
+                print(f"🚀 جاري فتح الصفحة: {url}")
+                await page.goto(url, wait_until="domcontentloaded", timeout=60000)
+                await page.wait_for_timeout(3000)
+
+                print("🔄 جاري تتبع الصور واستهدافها عنصراً عنصراً...")
+
+                current_idx = 0
+                no_new_imgs_streak = 0
+                max_images_to_check = 200
+
+                while current_idx < max_images_to_check:
+                    imgs = page.locator("img")
+                    count = await imgs.count()
+
+                    if current_idx >= count:
+                        await page.evaluate("window.scrollBy(0, 1200)")
+                        await page.wait_for_timeout(600)
+
+                        new_count = await imgs.count()
+                        if new_count == count:
+                            no_new_imgs_streak += 1
+                            if no_new_imgs_streak > 10:
+                                break
+                        else:
+                            no_new_imgs_streak = 0
+                        continue
+
+                    try:
+                        img = imgs.nth(current_idx)
+                        current_idx += 1
+
+                        src = await img.get_attribute("src") or ""
+                        data_src = await img.get_attribute("data-src") or ""
+                        combined = (src + data_src).lower()
+                        if any(kw in combined for kw in skip_kw):
+                            continue
+
+                        await img.scroll_into_view_if_needed(timeout=1500)
+                        await page.wait_for_timeout(150)
+
+                    except Exception:
+                        continue
+
+                print(f"📊 إجمالي الصور الممسوكة حياً من الشبكة: {len(captured)}")
+
+                # ── Fallback الشامل ──
+                if len(captured) < 5:
+                    print("⚠️ التقاط الشبكة ضعيف، جاري قراءة الـ DOM...")
+                    dom_urls = await page.evaluate("""
+                        () => Array.from(document.querySelectorAll('img'))
+                            .map(img => img.dataset.src || img.dataset.lazy || img.dataset.original || img.dataset.url || img.getAttribute('data-cfsrc') || img.src)
+                            .filter(src => src && src.startsWith('http') && !src.includes('logo') && !src.includes('avatar'))
+                    """)
+
+                    unique_urls = [u for u in set(dom_urls) if u not in captured_urls]
+                    print(f"📄 تم العثور على {len(unique_urls)} رابط بالـ DOM.")
+
+                    async def fetch_single_img(img_url):
+                        try:
+                            res = await context.request.get(img_url, headers={"Referer": url}, timeout=12000)
+                            if res.ok:
+                                b = await res.body()
+                                if len(b) > 4000:
+                                    captured.append(b)
+                                    captured_urls.add(img_url)
+                        except:
+                            pass
+
+                    if unique_urls:
+                        await asyncio.gather(*[fetch_single_img(u) for u in unique_urls])
+
+                await browser.close()
+                print(f"✅ انتهى السحب بنجاح! إجمالي الصور: {len(captured)}")
+                return captured
+
+            except Exception as e:
+                await browser.close()
+                print(f"❌ خطأ أثناء السحب: {e}")
+                return []
+
+
+# ============================================================
+# ✅ نفس fetch_fast من main.py حرفياً
+# ============================================================
+async def fetch_fast(url):
+    try:
+        print(f"🚀 fetch_fast بدأ: {url}", flush=True)
+        loop = asyncio.get_event_loop()
+        headers = {
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36",
+            "Referer": "https://www.google.com/",
+            "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8",
+            "Accept-Language": "en-US,en;q=0.9",
+            "Accept-Encoding": "gzip, deflate, br",
+            "Connection": "keep-alive",
+            "Upgrade-Insecure-Requests": "1",
+            "Sec-Fetch-Dest": "document",
+            "Sec-Fetch-Mode": "navigate",
+            "Sec-Fetch-Site": "none",
+            "Cache-Control": "max-age=0",
+        }
+
+        scraper = cloudscraper.create_scraper()
+        res = await loop.run_in_executor(
+            None,
+            lambda: scraper.get(url, timeout=15)
+        )
+
+        print(f"🔍 Status: {res.status_code}", flush=True)
+
+        soup = BeautifulSoup(res.text, "html.parser")
+
+        img_urls = []
+        for img in soup.find_all("img"):
+            src = img.get("data-src") or img.get("src") or ""
+            if src.startswith("http") and all(x not in src.lower() for x in ["logo", "wp-content/themes", "dflazy", "avatar"]):
+                img_urls.append(src)
+
+        print(f"🔍 لاقى {len(img_urls)} رابط", flush=True)
+
+        if len(img_urls) < 3:
+            return None
+
+        async def download_img(img_url):
+            try:
+                r = await loop.run_in_executor(
+                    None,
+                    lambda: requests.get(img_url, headers={"Referer": url, "User-Agent": headers["User-Agent"]}, timeout=15)
+                )
+                if r.ok and len(r.content) > 5000:
+                    return r.content
+            except:
+                pass
+            return None
+
+        tasks = [download_img(u) for u in img_urls]
+        results = await asyncio.gather(*tasks)
+        images_bytes = [r for r in results if r]
+
+        print(f"✅ fetch_fast حمّل {len(images_bytes)} صورة", flush=True)
+        return images_bytes if len(images_bytes) >= 3 else None
+
+    except Exception as e:
+        print(f"⚠️ fetch_fast فشل: {type(e).__name__}: {e}", flush=True)
+        return None
+
+
+# ============================================================
+# 🎮 Gradio Wrapper — الـ endpoint اللي البوت بيناديه
+# ============================================================
+def fetch_chapter(url: str, secret: str):
+    """
+    Input:  url, secret
+    Output: images_json (base64 list as JSON string), count, status
+    """
+    if secret != API_SECRET:
+        return "[]", 0, "error:unauthorized"
+
+    url = url.strip()
+    if not url.startswith("http"):
+        return "[]", 0, "error:invalid_url"
+
+    print(f"📥 طلب سحب: {url}", flush=True)
+
+    loop = asyncio.new_event_loop()
+    asyncio.set_event_loop(loop)
+
+    try:
+        # نفس المنطق الأصلي: fast أول، لو فشل deep
+        images = loop.run_until_complete(fetch_fast(url))
+        method = "fast"
+
+        if not images:
+            print("🔄 fetch_fast فشل → fetch_manhwa", flush=True)
+            images = loop.run_until_complete(fetch_manhwa(url))
+            method = "deep"
+
+        if not images:
+            return "[]", 0, "error:fetch_failed"
+
+        encoded = [base64.b64encode(img).decode() for img in images]
+        print(f"✅ [{method}] {len(encoded)} صورة جاهزة", flush=True)
+        return json.dumps(encoded), len(encoded), f"ok:{method}"
+
+    except Exception as e:
+        print(f"❌ Exception: {e}", flush=True)
+        return "[]", 0, f"error:{str(e)[:100]}"
+    finally:
+        loop.close()
+
+
+# ── Gradio Interface ──────────────────────────────────────
+with gr.Blocks(title="Emperor Fetch API") as demo:
+    gr.Markdown("## 🔱 Emperor Fetch Space\nInternal API — not for public use.")
+
+    with gr.Row():
+        url_in     = gr.Textbox(label="URL",    placeholder="https://...")
+        secret_in  = gr.Textbox(label="Secret", type="password")
+
+    btn = gr.Button("Fetch", variant="primary")
+
+    images_out = gr.Textbox(label="images_json")
+    count_out  = gr.Number(label="count")
+    status_out = gr.Textbox(label="status")
+
+    btn.click(
+        fn=fetch_chapter,
+        inputs=[url_in, secret_in],
+        outputs=[images_out, count_out, status_out],
+        api_name="fetch_chapter"   # ← الاسم اللي بيناديه البوت
+    )
+
+demo.launch(server_name="0.0.0.0", server_port=7860)

requirements.txt

@@ -0,0 +1,6 @@
+gradio>=4.0.0
+playwright
+requests
+cloudscraper
+beautifulsoup4
+Pillow