Create app.py
Browse files
app.py
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from flask import Flask, request, Response
|
| 2 |
+
import requests
|
| 3 |
+
|
| 4 |
+
app = Flask(__name__)
|
| 5 |
+
|
| 6 |
+
# Replace 'socio_secret_2026' with a strong, random password
|
| 7 |
+
SECRET_KEY = "socio_secret_2026"
|
| 8 |
+
|
| 9 |
+
@app.route('/api/proxy')
|
| 10 |
+
def proxy():
|
| 11 |
+
target_url = request.args.get('url')
|
| 12 |
+
key = request.args.get('key')
|
| 13 |
+
|
| 14 |
+
# 1. Security Check
|
| 15 |
+
if key != SECRET_KEY:
|
| 16 |
+
return "Unauthorized", 401
|
| 17 |
+
|
| 18 |
+
if not target_url:
|
| 19 |
+
return "Missing URL", 400
|
| 20 |
+
|
| 21 |
+
# 2. Browser-like Headers to minimize block probability
|
| 22 |
+
headers = {
|
| 23 |
+
"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"
|
| 24 |
+
}
|
| 25 |
+
|
| 26 |
+
try:
|
| 27 |
+
# 3. Fetch with allow_redirects=True to ensure you get the final page content
|
| 28 |
+
resp = requests.get(target_url, headers=headers, timeout=20, allow_redirects=True)
|
| 29 |
+
|
| 30 |
+
# 4. Return the content back to your Airflow scraper
|
| 31 |
+
return Response(
|
| 32 |
+
resp.text,
|
| 33 |
+
status=resp.status_code,
|
| 34 |
+
content_type=resp.headers.get('content-type', 'text/html')
|
| 35 |
+
)
|
| 36 |
+
except Exception as e:
|
| 37 |
+
return str(e), 500
|
| 38 |
+
|
| 39 |
+
if __name__ == '__main__':
|
| 40 |
+
app.run()
|