Spaces:

LPX55
/

flask

Paused

App Files Files Community

lazyfling commited on May 18, 2025

Commit

4390011

verified ·

1 Parent(s): c0ae781

Update app.py

Browse files

Files changed (1) hide show

app.py +109 -46

app.py CHANGED Viewed

@@ -1,53 +1,116 @@
-from flask import Flask, request, jsonify, make_response
-import requests
-import logging
-logging.basicConfig(level=logging.INFO)
-app = Flask(__name__)
-def proxy_request(full_url):
-    try:
-        headers = {key: value for key, value in request.headers.items() if key.lower() != 'host'}
-        headers['User-Agent'] = request.headers.get('User-Agent', 'Mozilla/5.0 (compatible; SpacesProxy/1.0)')
-        response = requests.request(
-            method=request.method,
-            url=full_url,
-            headers=headers,
-            data=request.get_data(),
-            params=request.args,
-            timeout=60,
-            stream=True  # 启用流式以处理大响应，如HTML页面
-        )
-        return response.iter_content(chunk_size=1024), response.status_code, response.headers  # 返回迭代器以流式输出
-    except requests.exceptions.RequestException as e:
-        logging.error(f"代理请求错误: {e}")
-        return jsonify({"error": str(e)}), 500
-@app.route('/proxy/<path:url>')
-def handle_proxy(url):
-    if not url.startswith('http'):
-        full_url = f"https://{url}"
-    else:
-        full_url = url  # 使用传入的完整URL
-    content_iter, status_code, headers = proxy_request(full_url)  # 获取迭代器
-    resp = make_response('')  # 初始化响应
-    resp.status_code = status_code
-    for key, value in headers.items():
-        if key.lower() not in ['content-encoding', 'content-length', 'transfer-encoding', 'connection', 'host']:  # 更严格过滤可能冲突的头部
-            resp.headers[key] = value
-    resp.mimetype = headers.get('Content-Type', 'text/html')  # 设置正确的MIME类型
-    # 流式写入内容
-    def generate():
-        for chunk in content_iter:  # 逐块输出内容
-            yield chunk
-    resp.response = generate()  # 将生成器设置为响应体
-    resp.headers['Content-Length'] = headers.get('Content-Length', '0')  # 如果可用，设置内容长度
-    return resp
-if __name__ == '__main__':
-    app.run(host='0.0.0.0', port=7860, debug=True)

+from flask import Flask, request, jsonify, make_response, render_template_string, url_for
+import requests
+import logging
+import re
+from urllib.parse import urljoin, urlparse
+logging.basicConfig(level=logging.INFO)
+app = Flask(__name__)
+HTML_TEMPLATE = '''
+<!DOCTYPE html>
+<html>
+<head>
+    <title>简易网页代理</title>
+    <style>
+        body { font-family: Arial, sans-serif; margin: 0; padding: 20px; }
+        .container { max-width: 800px; margin: 0 auto; }
+        .form-group { margin-bottom: 15px; }
+        input[type="text"] { width: 80%; padding: 8px; }
+        button { padding: 8px 15px; background: #4285f4; color: white; border: none; cursor: pointer; }
+        .note { margin-top: 20px; font-size: 0.9em; color: #666; }
+    </style>
+</head>
+<body>
+    <div class="container">
+        <h1>网页代理</h1>
+        <form action="/proxy" method="get">
+            <div class="form-group">
+                <input type="text" name="url" placeholder="输入完整URL (例如: https://github.com)" required>
+                <button type="submit">访问</button>
+            </div>
+        </form>
+        <div class="note">
+            <p>使用方法: 输入完整URL，包括https://前缀</p>
+        </div>
+    </div>
+</body>
+</html>
+'''
+def rewrite_html(content, original_url):
+    """重写HTML中的链接，使它们通过代理访问"""
+    try:
+        content_str = content.decode('utf-8')
+        base_url = urlparse(original_url)
+        base_domain = f"{base_url.scheme}://{base_url.netloc}"
+        # 重写相对URL为绝对URL然后添加代理前缀
+        content_str = re.sub(r'(src|href)=["\'](?!http)([^"\']+)["\']',
+                          lambda m: f'{m.group(1)}="/proxy?url={urljoin(base_domain, m.group(2))}"',
+                          content_str)
+        # 重写绝对URL添加代理前缀
+        content_str = re.sub(r'(src|href)=["\'](https?://[^"\']+)["\']',
+                          lambda m: f'{m.group(1)}="/proxy?url={m.group(2)}"',
+                          content_str)
+        return content_str.encode('utf-8')
+    except Exception as e:
+        logging.error(f"重写HTML出错: {e}")
+        return content
+@app.route('/')
+def index():
+    return render_template_string(HTML_TEMPLATE)
+@app.route('/proxy')
+def proxy():
+    url = request.args.get('url', '')
+    if not url:
+        return render_template_string(HTML_TEMPLATE)
+    if not url.startswith('http'):
+        url = f"https://{url}"
+    try:
+        headers = {key: value for key, value in request.headers.items()
+                   if key.lower() not in ['host', 'cookie', 'referer']}
+        headers['User-Agent'] = request.headers.get('User-Agent', 'Mozilla/5.0 (compatible; SpacesProxy/1.0)')
+        response = requests.get(
+            url=url,
+            headers=headers,
+            timeout=30,
+            allow_redirects=True
+        )
+        content_type = response.headers.get('Content-Type', '')
+        content = response.content
+        # 对HTML内容进行链接重写
+        if 'text/html' in content_type:
+            content = rewrite_html(content, url)
+        # 创建响应
+        resp = make_response(content)
+        resp.status_code = response.status_code
+        # 复制必要的头部信息
+        for key, value in response.headers.items():
+            if key.lower() not in ['content-encoding', 'content-length', 'transfer-encoding',
+                                   'connection', 'host', 'access-control-allow-origin']:
+                resp.headers[key] = value
+        # 设置正确的MIME类型
+        if 'Content-Type' in response.headers:
+            resp.mimetype = response.headers['Content-Type'].split(';')[0]
+        return resp
+    except Exception as e:
+        logging.error(f"代理请求错误: {e}")
+        return jsonify({"error": str(e), "url": url}), 500
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=7860, debug=True)