From 2228ac170f85ca151fdc7526edba3e7f4ca0e8d2 Mon Sep 17 00:00:00 2001
From: rain <rain>
Date: Mon, 20 Jul 2026 10:55:20 +0800
Subject: [PATCH] fix: correct baidu crawl configuration

---
 robots.txt               | 32 ++++++++++----
 sitemap.xml              | 12 +-----
 tmp/seo-indexing-test.js | 92 ++++++++++++++++++++++++++++++++++++++++
 3 files changed, 116 insertions(+), 20 deletions(-)
 create mode 100644 tmp/seo-indexing-test.js

diff --git a/robots.txt b/robots.txt
index 098cbf2..35105c8 100644
--- a/robots.txt
+++ b/robots.txt
@@ -1,26 +1,40 @@
-# 对所有搜索引擎生效
 User-agent: *
-
-# 允许抓取网站所有公开页面
 Allow: /
 
-# 屏蔽登录/注册/用户中心页面
+# 登录、注册和用户中心
 Disallow: /login.html
 Disallow: /reg.html
 Disallow: /repwd.html
 Disallow: /usercenter.html
+Disallow: /html/login.html
+Disallow: /html/reg.html
+Disallow: /html/repwd.html
+Disallow: /html/usercenter.html
 
-# 屏蔽财务相关页面
+# 财务页面
 Disallow: /chongzhi.html
 Disallow: /tixian.html
 Disallow: /tixianlist.html
+Disallow: /jine.html
+Disallow: /html/chongzhi.html
+Disallow: /html/tixian.html
+Disallow: /html/tixianlist.html
+Disallow: /html/jine.html
 
-# 屏蔽收藏/分销/推广相关页面
+# 用户收藏、分销、推广和发布页面
 Disallow: /mianfeishoucang.html
-Disallow: /zhuanjiashoucang.html
 Disallow: /wodefenxiao.html
 Disallow: /fenxiao.html
 Disallow: /tuiguang.html
+Disallow: /fabumianfeiwenzhang.html
+Disallow: /fufei.html
+Disallow: /apply.html
+Disallow: /html/mianfeishoucang.html
+Disallow: /html/wodefenxiao.html
+Disallow: /html/fenxiao.html
+Disallow: /html/tuiguang.html
+Disallow: /html/fabumianfeiwenzhang.html
+Disallow: /html/fufei.html
+Disallow: /html/apply.html
 
-# 提交 sitemap，搜索引擎根据 sitemap 快速抓取
-Sitemap: https://3d.3dyjs.cn/sitemap.xml
\ No newline at end of file
+Sitemap: https://www.scs8888.cn/sitemap.xml
diff --git a/sitemap.xml b/sitemap.xml
index 9ad7f2b..af7d8b9 100644
--- a/sitemap.xml
+++ b/sitemap.xml
@@ -1,18 +1,8 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
   <url>
-    <loc>https://3d.3dyjs.cn/</loc>
+    <loc>https://www.scs8888.cn/</loc>
     <changefreq>daily</changefreq>
     <priority>1.0</priority>
   </url>
-  <url>
-    <loc>https://3d.3dyjs.cn/zhuanjia.html</loc>
-    <changefreq>daily</changefreq>
-    <priority>0.9</priority>
-  </url>
-  <url>
-    <loc>https://3d.3dyjs.cn/kaijiang.html</loc>
-    <changefreq>daily</changefreq>
-    <priority>0.8</priority>
-  </url>
 </urlset>
diff --git a/tmp/seo-indexing-test.js b/tmp/seo-indexing-test.js
new file mode 100644
index 0000000..c573d6a
--- /dev/null
+++ b/tmp/seo-indexing-test.js
@@ -0,0 +1,92 @@
+const fs = require("fs");
+
+function read(path) {
+  return fs.readFileSync(path, "utf8");
+}
+
+function assert(condition, message) {
+  if (!condition) throw new Error(message);
+}
+
+const robots = read("robots.txt");
+const sitemap = read("sitemap.xml");
+const index = read("html/index.html");
+const article = read("html/mianfei.html");
+const commonUtil = read("utils/CommonUtil.js");
+
+assert(!robots.includes("3d.3dyjs.cn"), "robots should not reference the old domain");
+assert(!sitemap.includes("3d.3dyjs.cn"), "sitemap should not reference the old domain");
+assert(
+  robots.includes("Sitemap: https://www.scs8888.cn/sitemap.xml"),
+  "robots should advertise the production sitemap",
+);
+
+const sitemapLocations = Array.from(sitemap.matchAll(/<loc>([^<]+)<\/loc>/g), (match) => match[1]);
+assert(sitemapLocations.length === 1, "static sitemap should contain only the confirmed homepage");
+assert(
+  sitemapLocations[0] === "https://www.scs8888.cn/",
+  "static sitemap homepage should use the canonical production origin",
+);
+
+[
+  "login",
+  "reg",
+  "usercenter",
+  "chongzhi",
+  "tixian",
+  "fabumianfeiwenzhang",
+  "fufei",
+].forEach((privateRoute) => {
+  assert(!sitemap.includes(privateRoute), `private route must not appear in sitemap: ${privateRoute}`);
+});
+
+assert(/<meta\s+name="description"/i.test(index), "homepage description metadata missing");
+assert(
+  /<link\s+rel="canonical"\s+href="https:\/\/www\.scs8888\.cn\/"/i.test(index),
+  "homepage canonical metadata missing",
+);
+assert(
+  index.includes('<h1 class="seo-heading">神彩算彩票数据分析与免费预测文章</h1>'),
+  "homepage crawlable H1 missing",
+);
+assert(
+  index.includes("开奖数据、走势分析和免费文章"),
+  "homepage crawlable site description missing",
+);
+
+assert(/<meta\s+name="description"/i.test(article), "article default description metadata missing");
+assert(
+  /<meta\s+name="robots"\s+content="index, follow"/i.test(article),
+  "article robots metadata missing",
+);
+assert(
+  /<link\s+id="canonicalUrl"\s+rel="canonical"/i.test(article),
+  "article canonical hook missing",
+);
+assert(article.includes("function updateArticleSeo(data)"), "article SEO updater missing");
+assert(article.includes("updateArticleSeo(data);"), "article renderer should update SEO metadata");
+assert(
+  article.includes("https://www.scs8888.cn/mianfei/"),
+  "article canonical should use the public pretty URL",
+);
+
+assert(
+  /return `\/mianfei\/\$\{id\}\.html`/.test(commonUtil),
+  "CommonUtil.freeArticleHref should own the public article URL",
+);
+
+const deploymentDocPath = "docs/baidu-indexing-deployment.md";
+assert(fs.existsSync(deploymentDocPath), "backend deployment handoff missing");
+const deploymentDoc = read(deploymentDocPath);
+[
+  "/mianfei/{id}.html",
+  "404",
+  "301",
+  "动态 sitemap",
+  "Baiduspider",
+  "预渲染",
+].forEach((requiredText) => {
+  assert(deploymentDoc.includes(requiredText), `deployment handoff missing: ${requiredText}`);
+});
+
+console.log("SEO indexing checks passed");