deno / app.py
megatrump's picture
Update app.py
bc3acf5 verified
raw
history blame
3.39 kB
import re
import logging
from flask import Flask, request, Response
import requests
from urllib.parse import urlparse
# --- 设置日志 ---
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
app = Flask(__name__)
# --- 白名单过滤规则 ---
ALLOWED_PATTERNS = [
re.compile(r'^https://github\.com/[^/]+/[^/]+/(?:releases|archive)/.*$', re.IGNORECASE),
re.compile(r'^https://github\.com/[^/]+/[^/]+/(?:blob|raw)/.*$', re.IGNORECASE),
# --- 这里是修正后的一行 ---
re.compile(r'^https://github\.com/[^/]+/[^/]+/(?:info|git-).*$', re.IGNORECASE),
re.compile(r'^https://raw\.(?:githubusercontent|github)\.com/[^/]+/[^/]+/.*/.*$', re.IGNORECASE),
re.compile(r'^https://gist\.(?:githubusercontent|github)\.com/[^/]+/[^/]+/.*/.*$', re.IGNORECASE),
re.compile(r'^https://github\.com/[^/]+/[^/]+/tags.*$', re.IGNORECASE),
re.compile(r'^https://avatars\.githubusercontent\.com/.*$', re.IGNORECASE),
re.compile(r'^https://github\.githubassets\.com/.*$', re.IGNORECASE),
re.compile(r'^https://github\.com/[^/]+/?$', re.IGNORECASE),
re.compile(r'^https://github\.com/[^/]+/[^/]+/?$', re.IGNORECASE),
]
def is_url_allowed(url):
"""检查给定的URL是否匹配白名单中的任何一个模式。"""
for pattern in ALLOWED_PATTERNS:
if pattern.match(url):
return True
return False
# --- 核心代理逻辑 ---
@app.route('/', defaults={'path': ''}, methods=['GET', 'POST', 'PUT', 'DELETE'])
@app.route('/<path:path>', methods=['GET', 'POST', 'PUT', 'DELETE'])
def proxy(path):
target_path = request.full_path
if target_path.startswith('/'):
target_path = target_path[1:]
if not target_path:
return ("<p>GitHub reverse proxy is active.</p>"), 200
if not target_path.startswith(('http://', 'https://')):
target_url = 'https://' + target_path
else:
target_url = target_path
if not is_url_allowed(target_url):
logging.warning(f"URL Denied! No pattern matched: {target_url}")
error_message = "<h1>403 Forbidden</h1><p>Request blocked by proxy security policy.</p>"
return error_message, 403
try:
target_host = urlparse(target_url).hostname
if not target_host:
raise ValueError("Could not parse hostname")
except Exception as e:
return f"Invalid target URL in path: {e}", 400
headers = {key: value for (key, value) in request.headers if key.lower() != 'host'}
headers['Host'] = target_host
try:
resp = requests.request(
method=request.method,
url=target_url,
headers=headers,
data=request.get_data(),
cookies=request.cookies,
allow_redirects=False,
stream=True,
timeout=30
)
excluded_headers = ['content-encoding', 'content-length', 'transfer-encoding', 'connection']
response_headers = [(name, value) for (name, value) in resp.raw.headers.items() if name.lower() not in excluded_headers]
return Response(resp.iter_content(chunk_size=8192), status=resp.status_code, headers=response_headers)
except requests.exceptions.RequestException as e:
return f"An error occurred while proxying: {e}", 502
if __name__ == '__main__':
app.run(host='0.0.0.0', port=7860)