Create app.py
Browse files
app.py
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import asyncio
|
| 2 |
+
from playwright.async_api import async_playwright
|
| 3 |
+
|
| 4 |
+
# Your list of 100+ sites
|
| 5 |
+
SITES = [
|
| 6 |
+
"https://example.com",
|
| 7 |
+
"https://example.com",
|
| 8 |
+
# ... add up to 100+ URLs here ...
|
| 9 |
+
]
|
| 10 |
+
|
| 11 |
+
async def browse_sites():
|
| 12 |
+
async with async_playwright() as p:
|
| 13 |
+
# Launch browser in headless mode
|
| 14 |
+
browser = await p.chromium.launch(headless=True)
|
| 15 |
+
context = await browser.new_context()
|
| 16 |
+
page = await context.new_page()
|
| 17 |
+
|
| 18 |
+
for url in SITES:
|
| 19 |
+
try:
|
| 20 |
+
print(f"Navigating to: {url}")
|
| 21 |
+
await page.goto(url, timeout=15000) # 15 sec timeout
|
| 22 |
+
title = await page.title()
|
| 23 |
+
print(f"Successfully loaded: {title}")
|
| 24 |
+
|
| 25 |
+
# Perform your scraping/interaction here
|
| 26 |
+
|
| 27 |
+
except Exception as e:
|
| 28 |
+
print(f"Failed to load {url}: {e}")
|
| 29 |
+
|
| 30 |
+
await browser.close()
|
| 31 |
+
|
| 32 |
+
if __name__ == "__main__":
|
| 33 |
+
asyncio.run(browse_sites())
|