Create fetch.py

app/fetch.py

@@ -0,0 +1,59 @@
+import asyncio
+from playwright.async_api import async_playwright
+
+class Fetcher:
+    def __init__(self):
+        self.playwright = None
+        self.browser = None
+        self.context = None
+        self.sem = asyncio.Semaphore(2)  # <= 2 core thì đừng quá tay
+
+    async def start(self):
+        self.playwright = await async_playwright().start()
+        self.browser = await self.playwright.chromium.launch(
+            headless=True,
+            args=[
+                "--disable-blink-features=AutomationControlled",
+                "--no-sandbox",
+                "--disable-dev-shm-usage",
+            ],
+        )
+        self.context = await self.browser.new_context(
+            user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/121.0",
+            viewport={"width": 1280, "height": 720},
+        )
+
+        # block nặng
+        await self.context.route(
+            "**/*",
+            lambda route: route.abort()
+            if route.request.resource_type in ["image", "font", "media"]
+            else route.continue_(),
+        )
+
+    async def stop(self):
+        if self.context:
+            await self.context.close()
+        if self.browser:
+            await self.browser.close()
+        if self.playwright:
+            await self.playwright.stop()
+
+    async def fetch(self, url: str):
+        async with self.sem:
+            page = await self.context.new_page()
+            try:
+                await page.goto(url, timeout=30000, wait_until="domcontentloaded")
+                content = await page.content()
+                return {
+                    "ok": True,
+                    "length": len(content),
+                    "html": content,
+                }
+            except Exception as e:
+                return {
+                    "ok": False,
+                    "error": str(e),
+                }
+            finally:
+                await page.close()