Improve sitemap, RSS, and SEO guardrails

2026-07-11 13:09:57 +09:00
parent e0945f46a6
commit bcc3d6e680
12 changed files with 215 additions and 104 deletions
@@ -27,6 +27,9 @@ jobs:
          set -e
          python3 scripts/validate_locked_db_connection.py

+      - name: Validate SEO search guardrails
+        run: python3 scripts/validate_seo.py
+
      - name: Build solution
        run: dotnet build src/TaxBaik.sln -c Release --no-restore -p:ContinuousIntegrationBuild=true

@@ -339,6 +342,22 @@ jobs:
              fi
              echo "✓ [6/6] 관리자 페이지 로드 완료"

+              # 검색 엔진은 Content-Type뿐 아니라 유효한 XML 본문을 요구한다.
+              # 공통 Razor 레이아웃이 다시 섞이는 회귀를 배포 직후 차단한다.
+              SITEMAP_BODY=\$(curl -fsS http://127.0.0.1:5001/sitemap.xml 2>/dev/null || true)
+              RSS_BODY=\$(curl -fsS http://127.0.0.1:5001/rss.xml 2>/dev/null || true)
+              if ! printf '%s' "\$SITEMAP_BODY" | grep -q '<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">' \
+                || printf '%s' "\$SITEMAP_BODY" | grep -q '<!DOCTYPE html>'; then
+                echo "❌ sitemap.xml XML 응답 검증 실패" >&2
+                exit 1
+              fi
+              if ! printf '%s' "\$RSS_BODY" | grep -q '<rss version="2.0"' \
+                || printf '%s' "\$RSS_BODY" | grep -q '<!DOCTYPE html>'; then
+                echo "❌ rss.xml XML 응답 검증 실패" >&2
+                exit 1
+              fi
+              echo "✓ [7/7] 사이트맵 및 RSS XML 응답 검증 완료"
+
              echo "✓ 서비스 정상 (시도 \$i/\$ATTEMPTS)"
              # 구 배포 디렉토리 정리 (최근 5개 보존)
              ls -1dt \$DEPLOY_HOME/deployments/taxbaik_* 2>/dev/null \
@@ -0,0 +1,17 @@
+# SEO Search Guardrails
+
+These rules protect search discovery and must remain enforced by `scripts/validate_seo.py` in CI.
+
+- `sitemap.xml` and `rss.xml` are XML-only responses. They must not render the shared HTML layout.
+- `sitemap.xml` includes canonical, indexable URLs only. Redirect-only URLs and authenticated routes are excluded.
+- Blog URLs use the post's actual `UpdatedAt` value for `lastmod`; the homepage uses the most recent active FAQ, announcement, or displayed blog update.
+- Sitemap collection must page through every published blog post. Do not introduce a fixed total-content limit.
+- `/rss.xml` is the one canonical feed. `/feed.xml` permanently redirects to it.
+- `robots.txt` declares one canonical sitemap and never blocks XML resources.
+- Canonical URLs always use `https://www.taxbaik.com` and include the current indexable path. Paginated and category-filtered blog pages set an explicit canonical URL.
+
+Run locally with:
+
+```powershell
+python scripts/validate_seo.py
+```
@@ -0,0 +1,53 @@
+#!/usr/bin/env python3
+"""Static SEO guardrails run in CI before deployment."""
+
+from pathlib import Path
+import re
+import sys
+
+
+ROOT = Path(__file__).resolve().parents[1]
+WEB = ROOT / "src" / "TaxBaik.Web"
+errors: list[str] = []
+
+
+def read(relative: str) -> str:
+    return (ROOT / relative).read_text(encoding="utf-8")
+
+
+def require(condition: bool, message: str) -> None:
+    if not condition:
+        errors.append(message)
+
+
+sitemap_view = read("src/TaxBaik.Web/Pages/Sitemap.cshtml")
+rss_view = read("src/TaxBaik.Web/Pages/Rss.cshtml")
+feed_view = read("src/TaxBaik.Web/Pages/Feed.cshtml")
+sitemap_model = read("src/TaxBaik.Web/Pages/Sitemap.cshtml.cs")
+layout = read("src/TaxBaik.Web/Pages/_Layout.cshtml")
+robots = read("src/TaxBaik.Web/wwwroot/robots.txt")
+
+require("Layout = null" in sitemap_view, "sitemap.xml must render without the HTML layout")
+require("Layout = null" in rss_view, "rss.xml must render without the HTML layout")
+require("Html.Raw(rssContent.ToString())" in rss_view, "RSS XML must not be HTML-encoded")
+require("StatusCodes.Status308PermanentRedirect" in feed_view, "feed.xml must permanently redirect to rss.xml")
+require("DateTime.UtcNow:yyyy-MM-dd" not in sitemap_view, "sitemap lastmod must not use the current request date")
+require("GetAllPublishedPostsAsync" in sitemap_model, "sitemap must page through all published blog posts")
+require("/faq" not in sitemap_model and "/announcement" not in sitemap_model and "/inquiry" not in sitemap_model,
+        "redirect-only URLs must not be included in the sitemap")
+require("var canonicalUrl" in layout and "Context.Request.Path" in layout,
+        "default canonical URL must use the current path")
+
+sitemap_directives = re.findall(r"^Sitemap:\s*(\S+)\s*$", robots, flags=re.MULTILINE)
+require(sitemap_directives == ["https://www.taxbaik.com/sitemap.xml"],
+        "robots.txt must declare exactly one canonical sitemap URL")
+require(not re.search(r"^Disallow:\s*.*\.xml", robots, flags=re.MULTILINE),
+        "robots.txt must not block XML feeds or the sitemap")
+
+if errors:
+    print("SEO guardrail validation failed:", file=sys.stderr)
+    for error in errors:
+        print(f"- {error}", file=sys.stderr)
+    sys.exit(1)
+
+print("SEO guardrail validation passed")
@@ -2,6 +2,12 @@
@model TaxBaik.Web.Pages.Blog.BlogIndexModel
@{
    ViewData["Title"] = "블로그 | 백원숙 세무회계";
+    ViewData["Description"] = "세금 신고, 부동산 세금, 증여·상속 관련 최신 세무 정보와 절세 팁을 확인하세요.";
+    var canonicalQuery = Model.SelectedCategoryId.HasValue
+        ? $"?categoryId={Model.SelectedCategoryId.Value}" + (Model.CurrentPage > 1 ? $"&page={Model.CurrentPage}" : string.Empty)
+        : Model.CurrentPage > 1 ? $"?page={Model.CurrentPage}" : string.Empty;
+    ViewData["CanonicalUrl"] = $"https://www.taxbaik.com/blog{canonicalQuery}";
+    ViewData["OgUrl"] = ViewData["CanonicalUrl"];
 }

 <div class="container py-5">
@@ -4,7 +4,7 @@
    ViewData["Title"] = Model.Post?.SeoTitle ?? Model.Post?.Title;
    ViewData["Description"] = Model.Post?.SeoDescription ?? "";
    ViewData["OgImage"] = Model.Post?.ThumbnailUrl ?? "";
-    var canonicalUrl = $"{Request.Scheme}://{Request.Host}{Request.PathBase}/blog/{Model.Post?.Slug}";
+    var canonicalUrl = $"https://www.taxbaik.com/blog/{Uri.EscapeDataString(Model.Post?.Slug ?? string.Empty)}";
    ViewData["CanonicalUrl"] = canonicalUrl;
    ViewData["OgUrl"] = canonicalUrl;
 }
@@ -1,35 +1,6 @@
@page "/feed.xml"
-@model TaxBaik.Web.Pages.RssModel
@{
-    Response.ContentType = "application/rss+xml; charset=utf-8";
-}@{
-    var rssContent = new System.Text.StringBuilder();
-    rssContent.AppendLine("<?xml version=\"1.0\" encoding=\"utf-8\"?>");
-    rssContent.AppendLine("<rss version=\"2.0\" xmlns:content=\"http://purl.org/rss/1.0/modules/content/\">");
-    rssContent.AppendLine("  <channel>");
-    rssContent.AppendLine("    <title>백원숙 세무회계 - 블로그</title>");
-    rssContent.AppendLine("    <link>https://www.taxbaik.com</link>");
-    rssContent.AppendLine("    <description>세무사 백원숙의 세금, 부동산, 가족자산 전문 블로그</description>");
-    rssContent.AppendLine("    <language>ko-kr</language>");
-    rssContent.AppendLine($"    <lastBuildDate>{Model.LastBuildDate}</lastBuildDate>");
-    rssContent.AppendLine("    <ttl>60</ttl>");
-
-    foreach (var post in Model.Posts)
-    {
-        rssContent.AppendLine("    <item>");
-        rssContent.AppendLine($"      <title>{System.Net.WebUtility.HtmlEncode(post.Title)}</title>");
-        rssContent.AppendLine($"      <link>https://www.taxbaik.com/blog/{post.Slug}</link>");
-        rssContent.AppendLine($"      <guid isPermaLink=\"true\">https://www.taxbaik.com/blog/{post.Slug}</guid>");
-        rssContent.AppendLine($"      <pubDate>{post.PublishedAt?.ToString("R")}</pubDate>");
-        var desc = post.Content?.Substring(0, Math.Min(200, post.Content?.Length ?? 0)) ?? "";
-        rssContent.AppendLine($"      <description>{System.Net.WebUtility.HtmlEncode(desc)}</description>");
-        if (!string.IsNullOrEmpty(post.Content))
-        {
-            rssContent.AppendLine($"      <content:encoded><![CDATA[{post.Content}]]></content:encoded>");
+    Layout = null;
+    Response.StatusCode = StatusCodes.Status308PermanentRedirect;
+    Response.Headers.Location = "/rss.xml";
 }
-        rssContent.AppendLine("    </item>");
-    }
-
-    rssContent.AppendLine("  </channel>");
-    rssContent.AppendLine("</rss>");
-}@rssContent.ToString()
@@ -1,17 +1,19 @@
@page "/rss.xml"
@model TaxBaik.Web.Pages.RssModel
@{
+    Layout = null;
    Response.ContentType = "application/rss+xml; charset=utf-8";
 }@{
    var rssContent = new System.Text.StringBuilder();
    rssContent.AppendLine("<?xml version=\"1.0\" encoding=\"utf-8\"?>");
-    rssContent.AppendLine("<rss version=\"2.0\" xmlns:content=\"http://purl.org/rss/1.0/modules/content/\">");
+    rssContent.AppendLine("<rss version=\"2.0\" xmlns:atom=\"http://www.w3.org/2005/Atom\" xmlns:content=\"http://purl.org/rss/1.0/modules/content/\">");
    rssContent.AppendLine("  <channel>");
    rssContent.AppendLine("    <title>백원숙 세무회계 - 블로그</title>");
    rssContent.AppendLine("    <link>https://www.taxbaik.com</link>");
    rssContent.AppendLine("    <description>세무사 백원숙의 세금, 부동산, 가족자산 전문 블로그</description>");
    rssContent.AppendLine("    <language>ko-kr</language>");
    rssContent.AppendLine($"    <lastBuildDate>{Model.LastBuildDate}</lastBuildDate>");
+    rssContent.AppendLine("    <atom:link href=\"https://www.taxbaik.com/rss.xml\" rel=\"self\" type=\"application/rss+xml\" />");
    rssContent.AppendLine("    <ttl>60</ttl>");

    foreach (var post in Model.Posts)
@@ -25,11 +27,11 @@
        rssContent.AppendLine($"      <description>{System.Net.WebUtility.HtmlEncode(desc)}</description>");
        if (!string.IsNullOrEmpty(post.Content))
        {
-            rssContent.AppendLine($"      <content:encoded><![CDATA[{post.Content}]]></content:encoded>");
+            rssContent.AppendLine($"      <content:encoded><![CDATA[{post.Content.Replace("]]>", "]]]]><![CDATA[>")}]]></content:encoded>");
        }
        rssContent.AppendLine("    </item>");
    }

    rssContent.AppendLine("  </channel>");
    rssContent.AppendLine("</rss>");
-}@rssContent.ToString()
+}@Html.Raw(rssContent.ToString())
@@ -1,14 +1,18 @@
@page "/sitemap.xml"
@model TaxBaik.Web.Pages.SitemapModel
@{
+    Layout = null;
    Response.ContentType = "application/xml; charset=utf-8";
 }<?xml version="1.0" encoding="utf-8"?>
 <urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
    @foreach (var url in Model.Urls)
    {
        <url>
-            <loc>@System.Net.WebUtility.HtmlEncode(url)</loc>
-            <lastmod>@DateTime.UtcNow:yyyy-MM-dd</lastmod>
+            <loc>@url.Location</loc>
+            @if (url.LastModified.HasValue)
+            {
+                <lastmod>@url.LastModified.Value.ToUniversalTime().ToString("yyyy-MM-dd")</lastmod>
+            }
        </url>
    }
 </urlset>
@@ -5,48 +5,91 @@ namespace TaxBaik.Web.Pages;

 public class SitemapModel : PageModel
 {
+    private const string BaseUrl = "https://www.taxbaik.com";
+    private const int BlogPageSize = 100;
+
    private readonly BlogService _blogService;
+    private readonly FaqService _faqService;
+    private readonly AnnouncementService _announcementService;
+    private readonly ILogger<SitemapModel> _logger;

-    public List<string> Urls { get; set; } = [];
+    public List<SitemapUrl> Urls { get; } = [];

-    public SitemapModel(BlogService blogService)
+    public SitemapModel(
+        BlogService blogService,
+        FaqService faqService,
+        AnnouncementService announcementService,
+        ILogger<SitemapModel> logger)
    {
        _blogService = blogService;
+        _faqService = faqService;
+        _announcementService = announcementService;
+        _logger = logger;
    }

    public async Task OnGetAsync()
    {
-        var baseUrl = "https://www.taxbaik.com";
+        // FAQ와 공지사항은 홈에만 표시되고 각각의 URL은 리다이렉트된다.
+        // 따라서 홈의 변경일에 합산하고 리다이렉트 URL은 sitemap에서 제외한다.
+        var homeLastModified = default(DateTime);
+        var posts = new List<TaxBaik.Domain.Entities.BlogPost>();

-        // 정적 페이지 (항상 포함)
-        Urls.AddRange(new[]
-        {
-            $"{baseUrl}",
-            $"{baseUrl}/about",
-            $"{baseUrl}/services",
-            $"{baseUrl}/contact",
-            $"{baseUrl}/privacy",
-            $"{baseUrl}/terms",
-            $"{baseUrl}/blog",
-            $"{baseUrl}/faq",
-            $"{baseUrl}/announcement",
-            $"{baseUrl}/inquiry"
-        });
-
-        // 동적 블로그 포스트 (DB 오류 처리)
        try
        {
-            var (posts, _) = await _blogService.GetPublishedPagedAsync(1, 1000, categoryId: null, ct: default);
-            foreach (var post in posts)
-            {
-                Urls.Add($"{baseUrl}/blog/{post.Slug}");
-            }
+            var faqTask = _faqService.GetActiveAsync(HttpContext.RequestAborted);
+            var announcementTask = _announcementService.GetActiveAsync(HttpContext.RequestAborted);
+            var postsTask = GetAllPublishedPostsAsync(HttpContext.RequestAborted);
+
+            await Task.WhenAll(faqTask, announcementTask, postsTask);
+            posts = await postsTask;
+            homeLastModified = (await faqTask)
+                .Select(faq => faq.UpdatedAt)
+                .Concat((await announcementTask).Select(announcement => announcement.UpdatedAt))
+                .Concat(posts.Take(3).Select(post => post.UpdatedAt))
+                .DefaultIfEmpty()
+                .Max();
        }
        catch (Exception ex)
        {
-            // DB 연결 실패 등의 경우, 정적 페이지만으로도 sitemap 제공
-            // 프로덕션에서는 DB가 있으므로 이 경로는 사용되지 않음
-            System.Diagnostics.Debug.WriteLine($"Sitemap: Blog posts load failed: {ex.Message}");
+            // DB 문제 중에도 검색 엔진이 기존 핵심 페이지를 계속 발견할 수 있게 한다.
+            _logger.LogError(ex, "Failed to load dynamic sitemap content");
+        }
+
+        Urls.AddRange(new[]
+        {
+            new SitemapUrl($"{BaseUrl}/", homeLastModified == default ? null : homeLastModified),
+            new SitemapUrl($"{BaseUrl}/about"),
+            new SitemapUrl($"{BaseUrl}/services"),
+            new SitemapUrl($"{BaseUrl}/contact"),
+            new SitemapUrl($"{BaseUrl}/privacy"),
+            new SitemapUrl($"{BaseUrl}/terms"),
+            new SitemapUrl($"{BaseUrl}/blog")
+        });
+
+        foreach (var post in posts)
+        {
+            Urls.Add(new SitemapUrl(
+                $"{BaseUrl}/blog/{Uri.EscapeDataString(post.Slug)}",
+                post.UpdatedAt == default ? post.PublishedAt : post.UpdatedAt));
        }
    }
+
+    private async Task<List<TaxBaik.Domain.Entities.BlogPost>> GetAllPublishedPostsAsync(CancellationToken ct)
+    {
+        var posts = new List<TaxBaik.Domain.Entities.BlogPost>();
+        var page = 1;
+
+        while (true)
+        {
+            var (items, total) = await _blogService.GetPublishedPagedAsync(page, BlogPageSize, ct: ct);
+            posts.AddRange(items);
+
+            if (posts.Count >= total || !items.Any())
+                return posts;
+
+            page++;
+        }
+    }
+
+    public sealed record SitemapUrl(string Location, DateTime? LastModified = null);
 }
@@ -1,3 +1,9 @@
+@{
+    const string SiteUrl = "https://www.taxbaik.com";
+    var canonicalUrl = ViewData["CanonicalUrl"] as string ?? $"{SiteUrl}{Context.Request.PathBase}{Context.Request.Path}";
+    var ogUrl = ViewData["OgUrl"] as string ?? canonicalUrl;
+    var robots = ViewData["Robots"] as string ?? "index, follow";
+}
 <!DOCTYPE html>
 <html lang="ko">
 <head>
@@ -12,30 +18,29 @@
    <meta property="og:title" content="@(ViewData["Title"] ?? "백원숙 세무회계 - 세무사 전문 상담")" />
    <meta property="og:description" content="@(ViewData["Description"] ?? "백원숙 세무회계 - 사업자 기장, 부동산 양도세·증여세, 종합소득세 전문 상담. 맞춤형 세무 절세 컨설팅 제공.")" />
    <meta property="og:image" content="@(ViewData["OgImage"] ?? "https://www.taxbaik.com/images/og-image.jpg")" />
-    <meta property="og:url" content="@(ViewData["OgUrl"] ?? "https://www.taxbaik.com/")" />
+    <meta property="og:url" content="@ogUrl" />
    
    <!-- Twitter -->
-    <meta property="twitter:card" content="summary_large_image" />
-    <meta property="twitter:title" content="@(ViewData["Title"] ?? "백원숙 세무회계 - 세무사 전문 상담")" />
-    <meta property="twitter:description" content="@(ViewData["Description"] ?? "백원숙 세무회계 - 사업자 기장, 부동산 양도세·증여세, 종합소득세 전문 상담. 맞춤형 세무 절세 컨설팅 제공.")" />
-    <meta property="twitter:image" content="@(ViewData["OgImage"] ?? "https://www.taxbaik.com/images/og-image.jpg")" />
+    <meta name="twitter:card" content="summary_large_image" />
+    <meta name="twitter:title" content="@(ViewData["Title"] ?? "백원숙 세무회계 - 세무사 전문 상담")" />
+    <meta name="twitter:description" content="@(ViewData["Description"] ?? "백원숙 세무회계 - 사업자 기장, 부동산 양도세·증여세, 종합소득세 전문 상담. 맞춤형 세무 절세 컨설팅 제공.")" />
+    <meta name="twitter:image" content="@(ViewData["OgImage"] ?? "https://www.taxbaik.com/images/og-image.jpg")" />

    <!-- 검색엔진 등록용 소유권 인증 메타 태그 (발급받으신 토큰이 있으면 아래 content에 넣어 주시면 됩니다) -->
    <!-- <meta name="naver-site-verification" content="네이버_서치어드바이저_토큰_입력" /> -->
    <!-- <meta name="google-site-verification" content="구글_서치콘솔_토큰_입력" /> -->

-    <meta name="robots" content="index, follow" />
+    <meta name="robots" content="@robots" />
    <meta name="theme-color" content="#C89D6E" />
    <link rel="icon" type="image/svg+xml" href="/favicon.svg" />

    <!-- RSS Feed -->
    <link rel="alternate" type="application/rss+xml" title="백원숙 세무회계 블로그" href="/rss.xml" />
-    <link rel="alternate" type="application/rss+xml" title="TaxBaik Blog Feed" href="/feed.xml" />
    <link rel="preconnect" href="https://fonts.googleapis.com" />
    <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
    <link rel="dns-prefetch" href="https://cdn.jsdelivr.net" />
    <link href="https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700;800&family=Noto+Sans+KR:wght@400;500;700&family=Outfit:wght@400;500;600;700;800&display=swap" rel="stylesheet" />
-    <link rel="canonical" href="@(ViewData["CanonicalUrl"] ?? "https://www.taxbaik.com/")" />
+    <link rel="canonical" href="@canonicalUrl" />
    <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/css/bootstrap.min.css" rel="stylesheet" />
    <link rel="stylesheet" href="~/css/site.css" asp-append-version="true" />

@@ -46,8 +46,8 @@ public class SitemapValidationService
            result.TotalUrls = staticUrls.Count;

            // 2. 동적 블로그 포스트 검증
-            var (posts, _) = await _blogService.GetPublishedPagedAsync(1, 1000, categoryId: null, ct: default);
-            var blogUrls = posts.Select(p => $"https://www.taxbaik.com/blog/{p.Slug}").ToList();
+            var posts = await GetAllPublishedPostsAsync();
+            var blogUrls = posts.Select(p => $"https://www.taxbaik.com/blog/{Uri.EscapeDataString(p.Slug)}").ToList();

            ValidateUrls(blogUrls, result);

@@ -251,10 +251,25 @@ public class SitemapValidationService
            $"{baseUrl}/contact",
            $"{baseUrl}/privacy",
            $"{baseUrl}/terms",
-            $"{baseUrl}/blog",
-            $"{baseUrl}/faq",
-            $"{baseUrl}/announcement",
-            $"{baseUrl}/inquiry"
+            $"{baseUrl}/blog"
        };
    }
+
+    private async Task<List<TaxBaik.Domain.Entities.BlogPost>> GetAllPublishedPostsAsync()
+    {
+        const int pageSize = 100;
+        var posts = new List<TaxBaik.Domain.Entities.BlogPost>();
+        var page = 1;
+
+        while (true)
+        {
+            var (items, total) = await _blogService.GetPublishedPagedAsync(page, pageSize);
+            posts.AddRange(items);
+
+            if (posts.Count >= total || !items.Any())
+                return posts;
+
+            page++;
+        }
+    }
 }
@@ -7,30 +7,6 @@ Allow: /
 Disallow: /admin/
 Disallow: /portal/
 Disallow: /manage/
-Disallow: *.json$
-Disallow: *.xml$ (sitemap 제외)
-
-# 검색 엔진별 크롤링 속도 제한
-User-agent: Googlebot
-Crawl-delay: 1
-
-User-agent: Bingbot
-Crawl-delay: 2
-
-User-agent: Yeti
-Crawl-delay: 1
-
-# Naver, Kakao 검색 엔진
-User-agent: Naver
-Allow: /
-
-User-agent: Kakaobot
-Allow: /

 # Sitemap 위치
 Sitemap: https://www.taxbaik.com/sitemap.xml
-Sitemap: https://www.taxbaik.com/sitemap.xml
-
-# RSS 피드
-Sitemap: https://www.taxbaik.com/rss.xml
-Sitemap: https://www.taxbaik.com/feed.xml