dsh-free-search 0.4.34 → 0.4.35

package/lib/client.js

@@ -222,7 +222,7 @@ window.__ModuleLoader__.load({
     };
     const tt = (lang) => I18N[lang === "en" ? "en" : "zh"];
     // 当前插件版本（与 lib/index.js 的 PLUGIN_VERSION 保持一致）
-    const PLUGIN_VERSION = "0.4.34";
+    const PLUGIN_VERSION = "0.4.35";
     const ENGINES = [
       { id: "ddg", label: "DuckDuckGo · HTML", badge: "FREE", link: "https://duckduckgo.com" },
       { id: "ddg-lite", label: "DuckDuckGo · Lite", badge: "FREE", link: "https://duckduckgo.com" },

package/lib/index.js

@@ -52,7 +52,7 @@ const FREE_ENGINES = ["ddg", "ddg-lite", "bing", "searxng", "anysearch"];
 const ALL_ENGINES = ["ddg", "ddg-lite", "bing", "searxng", "anysearch", "exa", "tavily", "keenable", "firecrawl", "parallel", "perplexity", "serpbase", "deepseek-official"];
 
 // 当前插件版本（发布时与 package.json 同步）
-const PLUGIN_VERSION = "0.4.34";
+const PLUGIN_VERSION = "0.4.35";
 // 检查更新的 npm registry 元数据地址（dsh-free-search 是 npmjs 上的公开包）
 const NPM_REGISTRY_URL = "https://registry.npmjs.org/dsh-free-search/latest";
 const PLUGIN_NPM_URL = "https://www.npmjs.com/package/dsh-free-search";
@@ -347,6 +347,31 @@ async function searchDdgLite(query, maxResults, options, signal) {
   return { sources: uniqueSources(sources, maxResults ?? 10), truncated: false };
 }
 
+// Bing 在「查询无结果」时会返回一张完全无关的缓存 SERP（<li class="b_algo"> 照常存在，
+// 但内容是别的查询/热门页的内容），直接返回等于把垃圾结果喂给模型（issue #38：YouTube、
+// 法语微软文档、瑞士基金等都复现过）。这里用「查询 token 与结果文本是否重叠」识别这种页面。
+// token 规则：CJK 取 1-2 字组合（二元组），拉丁/数字取长度 >=2 的词。
+function queryOverlapTokens(query) {
+  const tokens = new Set();
+  for (const run of String(query).match(/[\u4e00-\u9fff]+/g) ?? []) {
+    if (run.length <= 2) tokens.add(run);
+    for (let i = 0; i + 1 < run.length; i++) tokens.add(run.slice(i, i + 2));
+  }
+  for (const word of String(query).toLowerCase().split(/[^a-z0-9]+/)) {
+    if (word.length >= 2) tokens.add(word);
+  }
+  return [...tokens];
+}
+
+function looksRelevant(query, sources) {
+  const tokens = queryOverlapTokens(query);
+  if (tokens.length === 0) return true; // 纯符号查询无法判定，不拦截
+  return sources.some((s) => {
+    const hay = `${s.title ?? ""} ${s.snippet ?? ""} ${s.url ?? ""}`.toLowerCase();
+    return tokens.some((t) => hay.includes(t.toLowerCase()));
+  });
+}
+
 async function searchBing(query, maxResults, options, signal) {
   // mkt：显式 bingMarket 优先；否则按 lang 映射（zh→zh-CN, ru→ru-RU ...）
   const profile = LANG_PROFILES[options?.lang] ?? LANG_PROFILES.zh;
@@ -374,6 +399,10 @@ async function searchBing(query, maxResults, options, signal) {
       ...(snippetMatch ? { snippet: stripTags(snippetMatch[1]) } : {}),
     });
   }
+  // Bing 无结果时会返回无关的缓存页：判为 0 结果，交给统一回退链换下一个引擎
+  if (sources.length > 0 && !looksRelevant(query, sources)) {
+    return { sources: [], truncated: false };
+  }
   return { sources: uniqueSources(sources, maxResults ?? 10), truncated: false };
 }
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "dsh-free-search",
-  "version": "0.4.34",
+  "version": "0.4.35",
   "description": "Free web search for DeepSeek Harness: 13 engines (Bing/DuckDuckGo/AnySearch/SearXNG/Exa/Tavily/Keenable/Firecrawl/Parallel keyless; Perplexity/SerpBase/DeepSeek with key) + time filtering + platform search + web_fetch, with web settings UI.",
   "type": "module",
   "main": "lib/index.js",