Spaces:

LPX55
/

flask

Paused

App Files Files Community

lazyfling commited on May 18, 2025

Commit

32c9c25

verified ·

1 Parent(s): 4496a6a

Update app.py

Browse files

Files changed (1) hide show

app.py +178 -218

app.py CHANGED Viewed

@@ -1,272 +1,232 @@
-from flask import Flask, request, jsonify, make_response, render_template_string
 import requests
-import logging
 import re
-from urllib.parse import urljoin, urlparse, quote
-import base64
 logging.basicConfig(level=logging.INFO)
 app = Flask(__name__)
-HTML_TEMPLATE = '''
 <!DOCTYPE html>
 <html>
 <head>
-    <title>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>高级网页代理</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>使用说明: 输入任何网站的完整URL（包含https://），即可通过代理访问</p>
         </div>
     </div>
 </body>
 </html>
-'''
-def create_proxy_url(original_url, base_url):
-    """创建代理URL"""
-    if not original_url:
-        return ""
-    # 处理相对URL
-    if not original_url.startswith('http'):
-        original_url = urljoin(base_url, original_url)
-    return f"/proxy?url={quote(original_url)}"
-def rewrite_html(content, base_url):
-    """全面重写HTML内容中的资源引用"""
     try:
-        content_str = content.decode('utf-8', errors='replace')
-        # 1. 替换基本的src和href属性
-        patterns = [
-            # 标准src和href属性
-            (r'(src|href)=["\'](.*?)["\']',
-             lambda m: f'{m.group(1)}="{create_proxy_url(m.group(2), base_url)}"'),
-            # data-src属性 (延迟加载)
-            (r'data-src=["\'](.*?)["\']',
-             lambda m: f'data-src="{create_proxy_url(m.group(1), base_url)}"'),
-            # srcset属性 (响应式图片)
-            (r'srcset=["\'](.*?)["\']',
-             lambda m: f'srcset="{" ".join([" ".join([create_proxy_url(p.strip().split(" ")[0], base_url)] + p.strip().split(" ")[1:]) for p in m.group(1).split(",")])}'),
-            # CSS中的url()
-            (r'url\([\'"]?(.*?)[\'"]?\)',
-             lambda m: f'url({create_proxy_url(m.group(1), base_url)})'),
-            # action属性 (表单)
-            (r'action=["\'](.*?)["\']',
-             lambda m: f'action="{create_proxy_url(m.group(1), base_url)}"'),
-            # meta刷新
-            (r'<meta[^>]*?http-equiv=["\'](refresh)["\'][^>]*?content=["\'](.*?)["\'][^>]*?>',
-             lambda m: re.sub(r'url=(.*)', lambda u: f'url={create_proxy_url(u.group(1), base_url)}', m.group(0))),
-        ]
-        for pattern, replacement in patterns:
-            content_str = re.sub(pattern, replacement, content_str)
-        # 2. 注入代理处理脚本到HTML头部
-        proxy_script = '''
         <script>
-        // 重写XHR和Fetch请求，使其通过代理
         (function() {
-            // 保存原始方法
-            const originalXhrOpen = XMLHttpRequest.prototype.open;
-            const originalFetch = window.fetch;
             // 重写XHR
             XMLHttpRequest.prototype.open = function(method, url, async, user, password) {
-                // 转换URL到代理URL
-                if (url && !url.startsWith('/proxy') && !url.startsWith('data:')) {
-                    const absoluteUrl = new URL(url, window.location).href;
-                    url = '/proxy?url=' + encodeURIComponent(absoluteUrl);
                 }
-                return originalXhrOpen.call(this, method, url, async, user, password);
             };
             // 重写Fetch
             window.fetch = function(resource, init) {
-                if (typeof resource === 'string' && !resource.startsWith('/proxy') && !resource.startsWith('data:')) {
-                    const absoluteUrl = new URL(resource, window.location).href;
-                    resource = '/proxy?url=' + encodeURIComponent(absoluteUrl);
                 }
-                return originalFetch.call(this, resource, init);
             };
-            // 监听所有DOM变化，重写新添加元素的URL
-            const observer = new MutationObserver(function(mutations) {
-                mutations.forEach(function(mutation) {
-                    if (mutation.type === 'childList') {
-                        mutation.addedNodes.forEach(function(node) {
-                            if (node.nodeType === 1) { // 元素节点
-                                rewireElement(node);
-                                const elements = node.querySelectorAll('*');
-                                elements.forEach(rewireElement);
-                            }
-                        });
-                    }
-                });
-            });
-            function rewireElement(el) {
-                // 处理src和href属性
-                ['src', 'href', 'action', 'data-src'].forEach(attr => {
-                    if (el.hasAttribute && el.hasAttribute(attr)) {
-                        let val = el.getAttribute(attr);
-                        if (val && !val.startsWith('/proxy') && !val.startsWith('data:') && !val.startsWith('javascript:')) {
-                            const absoluteUrl = new URL(val, window.location).href;
-                            el.setAttribute(attr, '/proxy?url=' + encodeURIComponent(absoluteUrl));
-                        }
-                    }
-                });
-                // 处理样式表中的url()
-                if (el.style && el.style.cssText) {
-                    el.style.cssText = el.style.cssText.replace(/url\(['"]?(.*?)['"]?\)/g, function(match, url) {
-                        if (!url.startsWith('/proxy') && !url.startsWith('data:')) {
-                            const absoluteUrl = new URL(url, window.location).href;
-                            return `url('/proxy?url=${encodeURIComponent(absoluteUrl)}')`;
-                        }
-                        return match;
-                    });
                 }
-            }
-            // 启动观察器
-            observer.observe(document, { childList: true, subtree: true });
-            // 初始处理所有元素
-            document.addEventListener('DOMContentLoaded', function() {
-                document.querySelectorAll('*').forEach(rewireElement);
-            });
         })();
         </script>
-        '''
-        # 在head标签结束前注入脚本
-        if '<head>' in content_str:
-            content_str = content_str.replace('</head>', f'{proxy_script}</head>')
         else:
-            content_str = f'{proxy_script}\n{content_str}'
-        # 3. 添加base标签，帮助处理相对URL
-        base_tag = f'<base href="{base_url}">'
-        if '<head>' in content_str:
-            content_str = content_str.replace('<head>', f'<head>{base_tag}')
-        return content_str.encode('utf-8', errors='replace')
-    except Exception as e:
-        logging.error(f"重写HTML出错: {e}")
-        return content
-def rewrite_css(content, base_url):
-    """重写CSS中的URL引用"""
-    try:
-        content_str = content.decode('utf-8', errors='replace')
-        # 处理CSS中的url()引用
-        content_str = re.sub(
-            r'url\([\'"]?(.*?)[\'"]?\)',
-            lambda m: f'url({create_proxy_url(m.group(1), base_url)})',
-            content_str
-        )
         return content_str.encode('utf-8', errors='replace')
     except Exception as e:
-        logging.error(f"重写CSS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:
-        logging.info(f"代理请求: {url}")
-        # 构建请求头
-        headers = {
-            'User-Agent': request.headers.get('User-Agent', 'Mozilla/5.0 (compatible; SpacesProxy/1.0)'),
-            'Accept': request.headers.get('Accept', '*/*'),
-            'Accept-Language': request.headers.get('Accept-Language', 'en-US,en;q=0.9'),
-            'Accept-Encoding': 'identity',  # 禁用压缩以简化处理
-            'Connection': 'keep-alive',
-            'Referer': url  # 使用目标URL作为Referer
-        }
-        # 发送请求获取响应
-        response = requests.get(
-            url=url,
-            headers=headers,
-            timeout=30,
-            allow_redirects=True,
-            verify=False  # 禁用SSL验证
-        )
-        # 获取内容类型
-        content_type = response.headers.get('Content-Type', '').lower()
-        content = response.content
-        # 根据内容类型进行不同处理
-        if 'text/html' in content_type:
-            content = rewrite_html(content, url)
-        elif 'text/css' in content_type:
-            content = rewrite_css(content, url)
-        # 其他类型保持原样
-        # 创建响应
-        resp = make_response(content)
-        resp.status_code = response.status_code
-        # 设置响应头
-        for key, value in response.headers.items():
-            if key.lower() not in ['content-encoding', 'content-length', 'transfer-encoding',
-                                   'connection', 'host', 'access-control-allow-origin',
-                                   'content-security-policy', 'x-frame-options']:
-                resp.headers[key] = value
-        # 设置正确的内容类型
-        if 'Content-Type' in response.headers:
-            resp.headers['Content-Type'] = response.headers['Content-Type']
-        # 添加允许跨域的头
-        resp.headers['Access-Control-Allow-Origin'] = '*'
-        return resp
-    except Exception as e:
-        logging.error(f"代理请求错误: {e}")
-        return jsonify({
-            "error": str(e),
-            "url": url,
-            "提示": "请检查URL是否正确，或者该网站是否可以正常访问"
-        }), 500
 if __name__ == '__main__':
     app.run(host='0.0.0.0', port=7860, debug=True)

+from flask import Flask, request, Response
 import requests
 import re
+import urllib.parse
+import logging
 logging.basicConfig(level=logging.INFO)
 app = Flask(__name__)
+# 首页HTML
+HOME_PAGE = """
 <!DOCTYPE html>
 <html>
 <head>
+    <title>简易Web代理</title>
     <style>
+        body { font-family: Arial, sans-serif; text-align: center; margin-top: 50px; }
+        .container { max-width: 600px; margin: 0 auto; }
+        input[type="text"] { width: 70%; padding: 10px; margin: 10px 0; }
+        button { padding: 10px 20px; background: #4285f4; color: white; border: none; cursor: pointer; }
+        .note { margin-top: 20px; color: #666; font-size: 0.9em; }
     </style>
 </head>
 <body>
     <div class="container">
+        <h1>Web代理</h1>
+        <form id="proxyForm">
+            <input type="text" id="urlInput" placeholder="输入要访问的URL (例如: https://github.com)" required>
+            <button type="submit">访问</button>
         </form>
         <div class="note">
+            <p>输入完整URL，包括https://前缀</p>
         </div>
     </div>
+    <script>
+        document.getElementById('proxyForm').addEventListener('submit', function(e) {
+            e.preventDefault();
+            const url = document.getElementById('urlInput').value;
+            if(url) {
+                window.location.href = '/proxy/' + encodeURIComponent(btoa(url));
+            }
+        });
+    </script>
 </body>
 </html>
+"""
+@app.route('/')
+def index():
+    return HOME_PAGE
+@app.route('/proxy/<path:encoded_url>')
+def proxy_path(encoded_url):
     try:
+        # Base64解码URL
+        url = urllib.parse.unquote(encoded_url)
+        url = str(base64_decode(url))
+        return proxy_request(url)
+    except Exception as e:
+        logging.error(f"代理路径出错: {e}")
+        return f"代理错误: {str(e)}", 500
+def base64_decode(encoded):
+    # 添加填充以确保正确解码
+    padding = 4 - (len(encoded) % 4)
+    if padding < 4:
+        encoded += "=" * padding
+    try:
+        return bytes.decode(base64.b64decode(encoded))
+    except:
+        try:
+            # 尝试URL安全的Base64解码
+            return bytes.decode(base64.urlsafe_b64decode(encoded))
+        except:
+            # 如果解码失败，返回原始值
+            return encoded
+def proxy_request(url):
+    try:
+        # 如果URL不是完整的HTTP URL，添加协议
+        if not url.startswith('http'):
+            url = 'https://' + url
+        logging.info(f"代理请求: {url}")
+        # 创建会话以便保留cookies等状态
+        session = requests.Session()
+        # 构建请求头
+        headers = {
+            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
+            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
+            'Accept-Language': 'en-US,en;q=0.5',
+            'Accept-Encoding': 'identity',  # 禁用压缩
+            'Connection': 'keep-alive',
+            'Upgrade-Insecure-Requests': '1',
+        }
+        # 发送请求
+        resp = session.get(url, headers=headers, stream=True, verify=False, timeout=30)
+        # 获取响应内容
+        content = resp.content
+        content_type = resp.headers.get('Content-Type', 'text/html')
+        # 如果是HTML内容，修改所有链接
+        if 'text/html' in content_type:
+            content = rewrite_links(content, url)
+        # 创建响应对象
+        response = Response(content)
+        # 复制原始响应的头信息
+        for key, value in resp.headers.items():
+            if key.lower() not in ['content-encoding', 'content-length', 'transfer-encoding',
+                                  'connection', 'content-security-policy']:
+                response.headers[key] = value
+        return response
+    except Exception as e:
+        logging.error(f"代理请求失败: {e}")
+        return f"访问 {url} 失败: {str(e)}", 500
+def rewrite_links(content, base_url):
+    try:
+        # 解码内容
+        content_str = content.decode('utf-8', errors='replace')
+        # 解析基础URL信息
+        parsed_base = urllib.parse.urlparse(base_url)
+        base_domain = f"{parsed_base.scheme}://{parsed_base.netloc}"
+        # 替换所有链接
+        def encode_url(url):
+            # 将相对URL转为绝对URL
+            if url.startswith('/'):
+                absolute_url = base_domain + url
+            elif not url.startswith('http') and not url.startswith('data:') and not url.startswith('#'):
+                absolute_url = urllib.parse.urljoin(base_url, url)
+            else:
+                absolute_url = url
+            # 将URL编码为Base64并添加代理前缀
+            if absolute_url.startswith('http'):
+                encoded = base64.b64encode(absolute_url.encode()).decode()
+                return f"/proxy/{urllib.parse.quote(encoded)}"
+            return url
+        # 1. 替换href属性
+        content_str = re.sub(r'href=["\'](.*?)["\']',
+                           lambda m: f'href="{encode_url(m.group(1))}"', content_str)
+        # 2. 替换src属性
+        content_str = re.sub(r'src=["\'](.*?)["\']',
+                           lambda m: f'src="{encode_url(m.group(1))}"', content_str)
+        # 3. 替换action属性(表单)
+        content_str = re.sub(r'action=["\'](.*?)["\']',
+                           lambda m: f'action="{encode_url(m.group(1))}"', content_str)
+        # 4. 替换CSS中的URL
+        content_str = re.sub(r'url\([\'"]?(.*?)[\'"]?\)',
+                           lambda m: f'url({encode_url(m.group(1))})', content_str)
+        # 5. 注入处理JavaScript的脚本
+        script = """
         <script>
         (function() {
+            // 创建Base64编码函数
+            function encodeURL(url) {
+                if(url && url.startsWith('http')) {
+                    return '/proxy/' + encodeURIComponent(btoa(url));
+                }
+                return url;
+            }
             // 重写XHR
+            const originalOpen = XMLHttpRequest.prototype.open;
             XMLHttpRequest.prototype.open = function(method, url, async, user, password) {
+                if(url && url.startsWith('http')) {
+                    arguments[1] = encodeURL(url);
                 }
+                return originalOpen.apply(this, arguments);
             };
             // 重写Fetch
+            const originalFetch = window.fetch;
             window.fetch = function(resource, init) {
+                if(typeof resource === 'string' && resource.startsWith('http')) {
+                    arguments[0] = encodeURL(resource);
                 }
+                return originalFetch.apply(this, arguments);
             };
+            // 监听所有点击事件，处理链接
+            document.addEventListener('click', function(e) {
+                const target = e.target.closest('a');
+                if(target && target.href && target.href.startsWith('http') &&
+                   !target.href.includes('/proxy/')) {
+                    e.preventDefault();
+                    location.href = encodeURL(target.href);
                 }
+            }, true);
         })();
         </script>
+        """
+        # 在body结束前插入脚本
+        if '</body>' in content_str:
+            content_str = content_str.replace('</body>', script + '</body>')
         else:
+            content_str += script
         return content_str.encode('utf-8', errors='replace')
     except Exception as e:
+        logging.error(f"���写链接出错: {e}")
         return content
+import base64
+@app.route('/proxy', methods=['GET'])
+def proxy_get():
     url = request.args.get('url', '')
     if not url:
+        return HOME_PAGE
+    # 对URL进行Base64编码并重定向
+    encoded_url = base64.b64encode(url.encode()).decode()
+    return proxy_request(url)
 if __name__ == '__main__':
     app.run(host='0.0.0.0', port=7860, debug=True)