puppeteer api

Dockers/puppeteer-api/main.py

@@ -0,0 +1,56 @@
+from fastapi import FastAPI, HTTPException, Header
+from pyppeteer import launch
+import os
+import asyncio
+from typing import Optional
+from urllib.parse import unquote
+
+app = FastAPI()
+
+# Get API key from environment variable
+API_KEY = os.getenv('API_KEY')
+if not API_KEY:
+    raise ValueError("API_KEY environment variable must be set")
+
+async def wait_for_network_idle(page):
+    """Wait until no network requests are in flight"""
+    await page.waitForNetworkIdle(idleTime=500, timeout=30000)
+
+@app.get("/")
+async def visit_url(url: str, x_api_key: Optional[str] = Header(None)):
+    # Validate API key
+    if not x_api_key or x_api_key != API_KEY:
+        raise HTTPException(status_code=401, detail="Invalid API key")
+
+    try:
+        # Decode URL if it's encoded
+        decoded_url = unquote(url)
+        print(decoded_url)
+
+        # Launch browser using installed Chrome
+        browser = await launch(
+            headless=True,
+            executablePath='/usr/bin/google-chrome',
+            args=['--no-sandbox', '--disable-setuid-sandbox']
+        )
+
+        # Create new page
+        page = await browser.newPage()
+
+        # Navigate to URL and wait for network idle
+        await page.goto(decoded_url, waitUntil='networkidle2')
+
+        # Get page content
+        content = await page.content()
+
+        # Close browser
+        await browser.close()
+
+        return {"status": "success", "content": content}
+
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8000)