Fix: Stabilize key-free search tool with random User-Agents and Cheerio parsing

backend/package-lock.json

@@ -13,6 +13,7 @@
         "@seald-io/nedb": "^4.1.2",
         "axios": "^1.13.2",
         "bcryptjs": "^3.0.3",
+        "cheerio": "^1.2.0",
         "cookie-parser": "^1.4.7",
         "cors": "^2.8.6",
         "dotenv": "^17.2.3",
@@ -464,6 +465,12 @@
         "url": "https://opencollective.com/express"
       }
     },
+    "node_modules/boolbase": {
+      "version": "1.0.0",
+      "resolved": "https://registry.npmjs.org/boolbase/-/boolbase-1.0.0.tgz",
+      "integrity": "sha512-JZOSA7Mo9sNGB8+UjSgzdLtokWAky1zbztM3WRLCbZ70/3cTANmQmOdR7y2g+J0e2WXywy1yS468tY+IruqEww==",
+      "license": "ISC"
+    },
     "node_modules/brace-expansion": {
       "version": "1.1.12",
       "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.12.tgz",
@@ -606,6 +613,48 @@
         "node": ">=8"
       }
     },
+    "node_modules/cheerio": {
+      "version": "1.2.0",
+      "resolved": "https://registry.npmjs.org/cheerio/-/cheerio-1.2.0.tgz",
+      "integrity": "sha512-WDrybc/gKFpTYQutKIK6UvfcuxijIZfMfXaYm8NMsPQxSYvf+13fXUJ4rztGGbJcBQ/GF55gvrZ0Bc0bj/mqvg==",
+      "license": "MIT",
+      "dependencies": {
+        "cheerio-select": "^2.1.0",
+        "dom-serializer": "^2.0.0",
+        "domhandler": "^5.0.3",
+        "domutils": "^3.2.2",
+        "encoding-sniffer": "^0.2.1",
+        "htmlparser2": "^10.1.0",
+        "parse5": "^7.3.0",
+        "parse5-htmlparser2-tree-adapter": "^7.1.0",
+        "parse5-parser-stream": "^7.1.2",
+        "undici": "^7.19.0",
+        "whatwg-mimetype": "^4.0.0"
+      },
+      "engines": {
+        "node": ">=20.18.1"
+      },
+      "funding": {
+        "url": "https://github.com/cheeriojs/cheerio?sponsor=1"
+      }
+    },
+    "node_modules/cheerio-select": {
+      "version": "2.1.0",
+      "resolved": "https://registry.npmjs.org/cheerio-select/-/cheerio-select-2.1.0.tgz",
+      "integrity": "sha512-9v9kG0LvzrlcungtnJtpGNxY+fzECQKhK4EGJX2vByejiMX84MFNQw4UxPJl3bFbTMw+Dfs37XaIkCwTZfLh4g==",
+      "license": "BSD-2-Clause",
+      "dependencies": {
+        "boolbase": "^1.0.0",
+        "css-select": "^5.1.0",
+        "css-what": "^6.1.0",
+        "domelementtype": "^2.3.0",
+        "domhandler": "^5.0.3",
+        "domutils": "^3.0.1"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/fb55"
+      }
+    },
     "node_modules/chokidar": {
       "version": "3.6.0",
       "resolved": "https://registry.npmjs.org/chokidar/-/chokidar-3.6.0.tgz",
@@ -792,6 +841,34 @@
         "url": "https://opencollective.com/express"
       }
     },
+    "node_modules/css-select": {
+      "version": "5.2.2",
+      "resolved": "https://registry.npmjs.org/css-select/-/css-select-5.2.2.tgz",
+      "integrity": "sha512-TizTzUddG/xYLA3NXodFM0fSbNizXjOKhqiQQwvhlspadZokn1KDy0NZFS0wuEubIYAV5/c1/lAr0TaaFXEXzw==",
+      "license": "BSD-2-Clause",
+      "dependencies": {
+        "boolbase": "^1.0.0",
+        "css-what": "^6.1.0",
+        "domhandler": "^5.0.2",
+        "domutils": "^3.0.1",
+        "nth-check": "^2.0.1"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/fb55"
+      }
+    },
+    "node_modules/css-what": {
+      "version": "6.2.2",
+      "resolved": "https://registry.npmjs.org/css-what/-/css-what-6.2.2.tgz",
+      "integrity": "sha512-u/O3vwbptzhMs3L1fQE82ZSLHQQfto5gyZzwteVIEyeaY5Fc7R4dapF/BvRoSYFeqfBk4m0V1Vafq5Pjv25wvA==",
+      "license": "BSD-2-Clause",
+      "engines": {
+        "node": ">= 6"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/fb55"
+      }
+    },
     "node_modules/debug": {
       "version": "4.4.3",
       "resolved": "https://registry.npmjs.org/debug/-/debug-4.4.3.tgz",
@@ -844,6 +921,61 @@
         "node": ">= 0.8"
       }
     },
+    "node_modules/dom-serializer": {
+      "version": "2.0.0",
+      "resolved": "https://registry.npmjs.org/dom-serializer/-/dom-serializer-2.0.0.tgz",
+      "integrity": "sha512-wIkAryiqt/nV5EQKqQpo3SToSOV9J0DnbJqwK7Wv/Trc92zIAYZ4FlMu+JPFW1DfGFt81ZTCGgDEabffXeLyJg==",
+      "license": "MIT",
+      "dependencies": {
+        "domelementtype": "^2.3.0",
+        "domhandler": "^5.0.2",
+        "entities": "^4.2.0"
+      },
+      "funding": {
+        "url": "https://github.com/cheeriojs/dom-serializer?sponsor=1"
+      }
+    },
+    "node_modules/domelementtype": {
+      "version": "2.3.0",
+      "resolved": "https://registry.npmjs.org/domelementtype/-/domelementtype-2.3.0.tgz",
+      "integrity": "sha512-OLETBj6w0OsagBwdXnPdN0cnMfF9opN69co+7ZrbfPGrdpPVNBUj02spi6B1N7wChLQiPn4CSH/zJvXw56gmHw==",
+      "funding": [
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/fb55"
+        }
+      ],
+      "license": "BSD-2-Clause"
+    },
+    "node_modules/domhandler": {
+      "version": "5.0.3",
+      "resolved": "https://registry.npmjs.org/domhandler/-/domhandler-5.0.3.tgz",
+      "integrity": "sha512-cgwlv/1iFQiFnU96XXgROh8xTeetsnJiDsTc7TYCLFd9+/WNkIqPTxiM/8pSd8VIrhXGTf1Ny1q1hquVqDJB5w==",
+      "license": "BSD-2-Clause",
+      "dependencies": {
+        "domelementtype": "^2.3.0"
+      },
+      "engines": {
+        "node": ">= 4"
+      },
+      "funding": {
+        "url": "https://github.com/fb55/domhandler?sponsor=1"
+      }
+    },
+    "node_modules/domutils": {
+      "version": "3.2.2",
+      "resolved": "https://registry.npmjs.org/domutils/-/domutils-3.2.2.tgz",
+      "integrity": "sha512-6kZKyUajlDuqlHKVX1w7gyslj9MPIXzIFiz/rGu35uC1wMi+kMhQwGhl4lt9unC9Vb9INnY9Z3/ZA3+FhASLaw==",
+      "license": "BSD-2-Clause",
+      "dependencies": {
+        "dom-serializer": "^2.0.0",
+        "domelementtype": "^2.3.0",
+        "domhandler": "^5.0.3"
+      },
+      "funding": {
+        "url": "https://github.com/fb55/domutils?sponsor=1"
+      }
+    },
     "node_modules/dotenv": {
       "version": "17.2.3",
       "resolved": "https://registry.npmjs.org/dotenv/-/dotenv-17.2.3.tgz",
@@ -901,6 +1033,31 @@
         "node": ">= 0.8"
       }
     },
+    "node_modules/encoding-sniffer": {
+      "version": "0.2.1",
+      "resolved": "https://registry.npmjs.org/encoding-sniffer/-/encoding-sniffer-0.2.1.tgz",
+      "integrity": "sha512-5gvq20T6vfpekVtqrYQsSCFZ1wEg5+wW0/QaZMWkFr6BqD3NfKs0rLCx4rrVlSWJeZb5NBJgVLswK/w2MWU+Gw==",
+      "license": "MIT",
+      "dependencies": {
+        "iconv-lite": "^0.6.3",
+        "whatwg-encoding": "^3.1.1"
+      },
+      "funding": {
+        "url": "https://github.com/fb55/encoding-sniffer?sponsor=1"
+      }
+    },
+    "node_modules/encoding-sniffer/node_modules/iconv-lite": {
+      "version": "0.6.3",
+      "resolved": "https://registry.npmjs.org/iconv-lite/-/iconv-lite-0.6.3.tgz",
+      "integrity": "sha512-4fCk79wshMdzMp2rH06qWrJE4iolqLhCUH+OiuIgU++RB0+94NlDL81atO7GX55uUKueo0txHNtvEyI6D7WdMw==",
+      "license": "MIT",
+      "dependencies": {
+        "safer-buffer": ">= 2.1.2 < 3.0.0"
+      },
+      "engines": {
+        "node": ">=0.10.0"
+      }
+    },
     "node_modules/engine.io": {
       "version": "6.6.5",
       "resolved": "https://registry.npmjs.org/engine.io/-/engine.io-6.6.5.tgz",
@@ -973,6 +1130,18 @@
         "node": ">= 0.6"
       }
     },
+    "node_modules/entities": {
+      "version": "4.5.0",
+      "resolved": "https://registry.npmjs.org/entities/-/entities-4.5.0.tgz",
+      "integrity": "sha512-V0hjH4dGPh9Ao5p0MoRY6BVqtwCjhz6vI5LT8AJ55H+4g9/4vbHx1I54fS0XuclLhDHArPQCiMjDxjaL8fPxhw==",
+      "license": "BSD-2-Clause",
+      "engines": {
+        "node": ">=0.12"
+      },
+      "funding": {
+        "url": "https://github.com/fb55/entities?sponsor=1"
+      }
+    },
     "node_modules/es-define-property": {
       "version": "1.0.1",
       "resolved": "https://registry.npmjs.org/es-define-property/-/es-define-property-1.0.1.tgz",
@@ -1418,6 +1587,37 @@
         "node": ">=18.0.0"
       }
     },
+    "node_modules/htmlparser2": {
+      "version": "10.1.0",
+      "resolved": "https://registry.npmjs.org/htmlparser2/-/htmlparser2-10.1.0.tgz",
+      "integrity": "sha512-VTZkM9GWRAtEpveh7MSF6SjjrpNVNNVJfFup7xTY3UpFtm67foy9HDVXneLtFVt4pMz5kZtgNcvCniNFb1hlEQ==",
+      "funding": [
+        "https://github.com/fb55/htmlparser2?sponsor=1",
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/fb55"
+        }
+      ],
+      "license": "MIT",
+      "dependencies": {
+        "domelementtype": "^2.3.0",
+        "domhandler": "^5.0.3",
+        "domutils": "^3.2.2",
+        "entities": "^7.0.1"
+      }
+    },
+    "node_modules/htmlparser2/node_modules/entities": {
+      "version": "7.0.1",
+      "resolved": "https://registry.npmjs.org/entities/-/entities-7.0.1.tgz",
+      "integrity": "sha512-TWrgLOFUQTH994YUyl1yT4uyavY5nNB5muff+RtWaqNVCAK408b5ZnnbNAUEWLTCpum9w6arT70i1XdQ4UeOPA==",
+      "license": "BSD-2-Clause",
+      "engines": {
+        "node": ">=0.12"
+      },
+      "funding": {
+        "url": "https://github.com/fb55/entities?sponsor=1"
+      }
+    },
     "node_modules/http-errors": {
       "version": "2.0.1",
       "resolved": "https://registry.npmjs.org/http-errors/-/http-errors-2.0.1.tgz",
@@ -2139,6 +2339,18 @@
         "node": ">=0.10.0"
       }
     },
+    "node_modules/nth-check": {
+      "version": "2.1.1",
+      "resolved": "https://registry.npmjs.org/nth-check/-/nth-check-2.1.1.tgz",
+      "integrity": "sha512-lqjrjmaOoAnWfMmBPL+XNnynZh2+swxiX3WUE0s4yEHI6m+AwrK2UZOimIRl3X/4QctVqS8AiZjFqyOGrMXb/w==",
+      "license": "BSD-2-Clause",
+      "dependencies": {
+        "boolbase": "^1.0.0"
+      },
+      "funding": {
+        "url": "https://github.com/fb55/nth-check?sponsor=1"
+      }
+    },
     "node_modules/oauth": {
       "version": "0.10.2",
       "resolved": "https://registry.npmjs.org/oauth/-/oauth-0.10.2.tgz",
@@ -2196,6 +2408,55 @@
         "opencollective-postinstall": "index.js"
       }
     },
+    "node_modules/parse5": {
+      "version": "7.3.0",
+      "resolved": "https://registry.npmjs.org/parse5/-/parse5-7.3.0.tgz",
+      "integrity": "sha512-IInvU7fabl34qmi9gY8XOVxhYyMyuH2xUNpb2q8/Y+7552KlejkRvqvD19nMoUW/uQGGbqNpA6Tufu5FL5BZgw==",
+      "license": "MIT",
+      "dependencies": {
+        "entities": "^6.0.0"
+      },
+      "funding": {
+        "url": "https://github.com/inikulin/parse5?sponsor=1"
+      }
+    },
+    "node_modules/parse5-htmlparser2-tree-adapter": {
+      "version": "7.1.0",
+      "resolved": "https://registry.npmjs.org/parse5-htmlparser2-tree-adapter/-/parse5-htmlparser2-tree-adapter-7.1.0.tgz",
+      "integrity": "sha512-ruw5xyKs6lrpo9x9rCZqZZnIUntICjQAd0Wsmp396Ul9lN/h+ifgVV1x1gZHi8euej6wTfpqX8j+BFQxF0NS/g==",
+      "license": "MIT",
+      "dependencies": {
+        "domhandler": "^5.0.3",
+        "parse5": "^7.0.0"
+      },
+      "funding": {
+        "url": "https://github.com/inikulin/parse5?sponsor=1"
+      }
+    },
+    "node_modules/parse5-parser-stream": {
+      "version": "7.1.2",
+      "resolved": "https://registry.npmjs.org/parse5-parser-stream/-/parse5-parser-stream-7.1.2.tgz",
+      "integrity": "sha512-JyeQc9iwFLn5TbvvqACIF/VXG6abODeB3Fwmv/TGdLk2LfbWkaySGY72at4+Ty7EkPZj854u4CrICqNk2qIbow==",
+      "license": "MIT",
+      "dependencies": {
+        "parse5": "^7.0.0"
+      },
+      "funding": {
+        "url": "https://github.com/inikulin/parse5?sponsor=1"
+      }
+    },
+    "node_modules/parse5/node_modules/entities": {
+      "version": "6.0.1",
+      "resolved": "https://registry.npmjs.org/entities/-/entities-6.0.1.tgz",
+      "integrity": "sha512-aN97NXWF6AWBTahfVOIrB/NShkzi5H7F9r1s9mD3cDj4Ko5f2qhhVoYMibXF7GlLveb/D2ioWay8lxI97Ven3g==",
+      "license": "BSD-2-Clause",
+      "engines": {
+        "node": ">=0.12"
+      },
+      "funding": {
+        "url": "https://github.com/fb55/entities?sponsor=1"
+      }
+    },
     "node_modules/parseurl": {
       "version": "1.3.3",
       "resolved": "https://registry.npmjs.org/parseurl/-/parseurl-1.3.3.tgz",
@@ -2982,6 +3243,15 @@
       "dev": true,
       "license": "MIT"
     },
+    "node_modules/undici": {
+      "version": "7.19.2",
+      "resolved": "https://registry.npmjs.org/undici/-/undici-7.19.2.tgz",
+      "integrity": "sha512-4VQSpGEGsWzk0VYxyB/wVX/Q7qf9t5znLRgs0dzszr9w9Fej/8RVNQ+S20vdXSAyra/bJ7ZQfGv6ZMj7UEbzSg==",
+      "license": "MIT",
+      "engines": {
+        "node": ">=20.18.1"
+      }
+    },
     "node_modules/undici-types": {
       "version": "7.16.0",
       "resolved": "https://registry.npmjs.org/undici-types/-/undici-types-7.16.0.tgz",
@@ -3058,6 +3328,40 @@
         "node": ">=12"
       }
     },
+    "node_modules/whatwg-encoding": {
+      "version": "3.1.1",
+      "resolved": "https://registry.npmjs.org/whatwg-encoding/-/whatwg-encoding-3.1.1.tgz",
+      "integrity": "sha512-6qN4hJdMwfYBtE3YBTTHhoeuUrDBPZmbQaxWAqSALV/MeEnR5z1xd8UKud2RAkFoPkmB+hli1TZSnyi84xz1vQ==",
+      "deprecated": "Use @exodus/bytes instead for a more spec-conformant and faster implementation",
+      "license": "MIT",
+      "dependencies": {
+        "iconv-lite": "0.6.3"
+      },
+      "engines": {
+        "node": ">=18"
+      }
+    },
+    "node_modules/whatwg-encoding/node_modules/iconv-lite": {
+      "version": "0.6.3",
+      "resolved": "https://registry.npmjs.org/iconv-lite/-/iconv-lite-0.6.3.tgz",
+      "integrity": "sha512-4fCk79wshMdzMp2rH06qWrJE4iolqLhCUH+OiuIgU++RB0+94NlDL81atO7GX55uUKueo0txHNtvEyI6D7WdMw==",
+      "license": "MIT",
+      "dependencies": {
+        "safer-buffer": ">= 2.1.2 < 3.0.0"
+      },
+      "engines": {
+        "node": ">=0.10.0"
+      }
+    },
+    "node_modules/whatwg-mimetype": {
+      "version": "4.0.0",
+      "resolved": "https://registry.npmjs.org/whatwg-mimetype/-/whatwg-mimetype-4.0.0.tgz",
+      "integrity": "sha512-QaKxh0eNIi2mE9p2vEdzfagOKHCcj1pJ56EEHGQOVxp8r9/iszLUUV7v89x9O1p/T+NlTM5W7jW6+cz4Fq1YVg==",
+      "license": "MIT",
+      "engines": {
+        "node": ">=18"
+      }
+    },
     "node_modules/whatwg-url": {
       "version": "14.2.0",
       "resolved": "https://registry.npmjs.org/whatwg-url/-/whatwg-url-14.2.0.tgz",

backend/package.json

@@ -17,6 +17,7 @@
     "@seald-io/nedb": "^4.1.2",
     "axios": "^1.13.2",
     "bcryptjs": "^3.0.3",
+    "cheerio": "^1.2.0",
     "cookie-parser": "^1.4.7",
     "cors": "^2.8.6",
     "dotenv": "^17.2.3",

backend/utils/webSearch.js

@@ -1,4 +1,5 @@
 const axios = require('axios');
+const cheerio = require('cheerio');
 
 /**
  * FREE_UNLIMITED_SEARCH
@@ -7,35 +8,56 @@ const axios = require('axios');
 exports.searchWeb = async (query) => {
     console.log(`[Neural_Search] Deep-scanning web for: ${query}`);
     
+    const userAgents = [
+        'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36',
+        'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36',
+        'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36'
+    ];
+
     try {
-        // Fallback: If no key, use DuckDuckGo Lite scraping (Free & Unlimited)
-        const response = await axios.get(`https://duckduckgo.com/html/?q=${encodeURIComponent(query)}`, {
+        const response = await axios.get(`https://duckduckgo.com/lite/?q=${encodeURIComponent(query)}`, {
             headers: {
-                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/53.36'
-            }
+                'User-Agent': userAgents[Math.floor(Math.random() * userAgents.length)],
+                'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8',
+                'Accept-Language': 'en-US,en;q=0.5',
+                'DNT': '1',
+                'Connection': 'keep-alive',
+                'Upgrade-Insecure-Requests': '1'
+            },
+            timeout: 10000
         });
 
-        // Simple HTML parsing to extract titles and snippets
-        const html = response.data;
+        if (response.data.includes('Unfortunately, bots use DuckDuckGo too')) {
+            console.log("[DEBUG] DuckDuckGo hit a captcha challenge.");
+            return "[SEARCH_OFFLINE]: The web sector is temporarily shielded by a captcha barrier. Try again in a few moments.";
+        }
+
+        const $ = cheerio.load(response.data);
         const results = [];
-        const resultMatches = html.matchAll(/<a class="result__a" href=\"(.*?)\">(.*?)<\/a>|<p class=\"result__snippet\">(.*?)<\/p>/g);
         
-        let currentResult = {};
-        for (const match of resultMatches) {
-            if (match[1]) { // URL and Title
-                if (currentResult.title) results.push(currentResult);
-                currentResult = { url: match[1], title: match[2].replace(/<[^>]*>?/gm, '') };
-            } else if (match[3]) { // Snippet
-                currentResult.snippet = match[3].replace(/<[^>]*>?/gm, '');
+        // DuckDuckGo Lite result structure: 
+        // <table> contains result rows
+        // <a> with class "result-link" is the main link
+        $('a.result-link').each((i, el) => {
+            if (i >= 5) return false;
+            const title = $(el).text().trim();
+            let url = $(el).attr('href');
+            
+            if (url && title) {
+                if (url.startsWith('//')) url = 'https:' + url;
+                results.push({
+                    url: url,
+                    title: title,
+                    snippet: "Data retrieved via Neural Uplink."
+                });
             }
-            if (results.length >= 5) break;
-        }
+        });
 
-        if (results.length === 0) return "[SEARCH_OFFLINE]: No immediate data found. The web sector might be shielded.";
+        if (results.length === 0) return "[SEARCH_OFFLINE]: No immediate data packets returned from this sector.";
 
         return results.map(r => `SOURCE: ${r.url}\nTITLE: ${r.title}\nINFO: ${r.snippet}`).join('\n\n');
     } catch (err) {
         console.error("[Search_Failure]", err.message);
-        return `[SEARCH_OFFLINE]: Could not establish uplink.`;
+        return `[SEARCH_OFFLINE]: Connection timeout in the web sector.`;
     }
-};
+};