From e1c9354512ade1854da9cc2750883b146ce23fc6 Mon Sep 17 00:00:00 2001 From: uduki Date: Mon, 31 Aug 2026 21:52:26 +0900 Subject: [PATCH] =?UTF-8?q?=E3=81=A8=E3=82=8A=E3=81=82=E3=81=88=E3=81=9A?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .gitignore | 7 + WebImageViewer.slnx | 3 + WebImageViewer/Class/Common/BaseScraper.cs | 65 + WebImageViewer/Class/Common/HttpHelper.cs | 72 + WebImageViewer/Class/Common/IScraper.cs | 30 + WebImageViewer/Class/Models/GalleryItem.cs | 67 + WebImageViewer/Class/Models/ImageInfo.cs | 37 + .../Class/Renderers/HtmlRenderer.cs | 1314 +++++++++++++++++ .../Class/Scrapers/MomongaScraper.cs | 233 +++ .../Class/Services/GalleryService.cs | 77 + WebImageViewer/Program.cs | 141 ++ .../PublishProfiles/FolderProfile.pubxml | 15 + WebImageViewer/Properties/launchSettings.json | 14 + WebImageViewer/WebImageViewer.csproj | 13 + WebImageViewer/WebImageViewer.http | 6 + WebImageViewer/appsettings.Development.json | 8 + WebImageViewer/appsettings.json | 9 + 17 files changed, 2111 insertions(+) create mode 100644 .gitignore create mode 100644 WebImageViewer.slnx create mode 100644 WebImageViewer/Class/Common/BaseScraper.cs create mode 100644 WebImageViewer/Class/Common/HttpHelper.cs create mode 100644 WebImageViewer/Class/Common/IScraper.cs create mode 100644 WebImageViewer/Class/Models/GalleryItem.cs create mode 100644 WebImageViewer/Class/Models/ImageInfo.cs create mode 100644 WebImageViewer/Class/Renderers/HtmlRenderer.cs create mode 100644 WebImageViewer/Class/Scrapers/MomongaScraper.cs create mode 100644 WebImageViewer/Class/Services/GalleryService.cs create mode 100644 WebImageViewer/Program.cs create mode 100644 WebImageViewer/Properties/PublishProfiles/FolderProfile.pubxml create mode 100644 WebImageViewer/Properties/launchSettings.json create mode 100644 WebImageViewer/WebImageViewer.csproj create mode 100644 WebImageViewer/WebImageViewer.http create mode 100644 WebImageViewer/appsettings.Development.json create mode 100644 WebImageViewer/appsettings.json diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..aa1a8a8 --- /dev/null +++ b/.gitignore @@ -0,0 +1,7 @@ +################################################################################ +# この .gitignore ファイルは Microsoft(R) Visual Studio によって自動的に作成されました。 +################################################################################ + +/.vs +/WebImageViewer/bin +/WebImageViewer/obj diff --git a/WebImageViewer.slnx b/WebImageViewer.slnx new file mode 100644 index 0000000..9783aad --- /dev/null +++ b/WebImageViewer.slnx @@ -0,0 +1,3 @@ + + + diff --git a/WebImageViewer/Class/Common/BaseScraper.cs b/WebImageViewer/Class/Common/BaseScraper.cs new file mode 100644 index 0000000..7c0ae6f --- /dev/null +++ b/WebImageViewer/Class/Common/BaseScraper.cs @@ -0,0 +1,65 @@ +using HtmlAgilityPack; +using Microsoft.Extensions.Logging; +using WebImageViewer.Class.Models; + +namespace WebImageViewer.Class.Common; + +/// +/// 各種Webサイトスクレイパーの共通基底クラス +/// +public abstract class BaseScraper : IScraper +{ + protected readonly HttpHelper HttpHelper; + protected readonly ILogger Logger; + + public abstract string SiteName { get; } + + protected BaseScraper(HttpHelper httpHelper, ILogger logger) + { + HttpHelper = httpHelper; + Logger = logger; + } + + /// + public abstract bool CanHandle(string urlOrPath); + + /// + public abstract Task ScrapeAsync(string idOrUrl, string? category = null, CancellationToken cancellationToken = default); + + /// + /// 指定されたURLからHTMLを取得し、HtmlDocumentとしてパースします。 + /// + /// 対象URL + /// キャンセレーショントークン + /// パースされたHtmlDocument + protected async Task LoadHtmlDocumentAsync(string url, CancellationToken cancellationToken = default) + { + try + { + Logger.LogInformation("[{SiteName}] HTMLを取得中: {Url}", SiteName, url); + var html = await HttpHelper.GetHtmlAsync(url, cancellationToken); + + var doc = new HtmlDocument(); + doc.LoadHtml(html); + return doc; + } + catch (Exception ex) + { + Logger.LogError(ex, "[{SiteName}] HTMLの取得またはパースに失敗しました: {Url}", SiteName, url); + return null; + } + } + + /// + /// HTML文字列のエンティティデコードおよび前後の空白をトリムします。 + /// + protected static string CleanText(string? input) + { + if (string.IsNullOrWhiteSpace(input)) + { + return string.Empty; + } + + return HtmlEntity.DeEntitize(input).Trim(); + } +} diff --git a/WebImageViewer/Class/Common/HttpHelper.cs b/WebImageViewer/Class/Common/HttpHelper.cs new file mode 100644 index 0000000..bde8f0c --- /dev/null +++ b/WebImageViewer/Class/Common/HttpHelper.cs @@ -0,0 +1,72 @@ +using System.Net.Http.Headers; + +namespace WebImageViewer.Class.Common; + +/// +/// HTTPリクエスト処理を行う共通ヘルパークラス +/// +public class HttpHelper +{ + private readonly HttpClient _httpClient; + + public HttpHelper(HttpClient httpClient) + { + _httpClient = httpClient; + ConfigureDefaultHeaders(_httpClient); + } + + /// + /// デフォルトのブラウザ模倣ヘッダーを設定します。 + /// + private static void ConfigureDefaultHeaders(HttpClient client) + { + client.DefaultRequestHeaders.Clear(); + client.DefaultRequestHeaders.UserAgent.ParseAdd( + "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36"); + client.DefaultRequestHeaders.Accept.ParseAdd( + "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8"); + client.DefaultRequestHeaders.AcceptLanguage.ParseAdd("ja,en-US;q=0.9,en;q=0.8"); + client.Timeout = TimeSpan.FromSeconds(30); + } + + /// + /// 指定URLからHTML文字列を取得します。 + /// + /// 対象URL + /// キャンセレーショントークン + /// HTML文字列 + public async Task GetHtmlAsync(string url, CancellationToken cancellationToken = default) + { + using var request = new HttpRequestMessage(HttpMethod.Get, url); + request.Headers.Add("Referer", url); + + using var response = await _httpClient.SendAsync(request, HttpCompletionOption.ResponseHeadersRead, cancellationToken); + response.EnsureSuccessStatusCode(); + + return await response.Content.ReadAsStringAsync(cancellationToken); + } + + /// + /// 指定URLのバイト配列(画像等)を取得します。 + /// + /// 画像URL + /// リファラー(省略可能) + /// キャンセレーショントークン + /// バイトデータとコンテンツタイプ + public async Task<(byte[] Data, string ContentType)> GetBinaryAsync(string url, string? referer = null, CancellationToken cancellationToken = default) + { + using var request = new HttpRequestMessage(HttpMethod.Get, url); + if (!string.IsNullOrEmpty(referer)) + { + request.Headers.Add("Referer", referer); + } + + using var response = await _httpClient.SendAsync(request, cancellationToken); + response.EnsureSuccessStatusCode(); + + var data = await response.Content.ReadAsByteArrayAsync(cancellationToken); + var contentType = response.Content.Headers.ContentType?.MediaType ?? "image/jpeg"; + + return (data, contentType); + } +} diff --git a/WebImageViewer/Class/Common/IScraper.cs b/WebImageViewer/Class/Common/IScraper.cs new file mode 100644 index 0000000..0b8a697 --- /dev/null +++ b/WebImageViewer/Class/Common/IScraper.cs @@ -0,0 +1,30 @@ +using WebImageViewer.Class.Models; + +namespace WebImageViewer.Class.Common; + +/// +/// 各スクレイパーが実装すべき共通インターフェース +/// +public interface IScraper +{ + /// + /// 対象サイトの名称 + /// + string SiteName { get; } + + /// + /// 指定されたURLやパス、IDをこのスクレイパーで処理可能かどうかを判定します。 + /// + /// 対象のURLまたはパス + /// 処理可能な場合はtrue + bool CanHandle(string urlOrPath); + + /// + /// 作品IDまたはURLからギャラリー情報および画像一覧を取得します。 + /// + /// 作品IDまたはURL + /// カテゴリ(fanzine, magazineなど。省略時は自動判定) + /// キャンセレーショントークン + /// 取得したGalleryItem(失敗時はnull) + Task ScrapeAsync(string idOrUrl, string? category = null, CancellationToken cancellationToken = default); +} diff --git a/WebImageViewer/Class/Models/GalleryItem.cs b/WebImageViewer/Class/Models/GalleryItem.cs new file mode 100644 index 0000000..f3c7af2 --- /dev/null +++ b/WebImageViewer/Class/Models/GalleryItem.cs @@ -0,0 +1,67 @@ +namespace WebImageViewer.Class.Models; + +/// +/// ギャラリー全体の情報(タイトル、メタデータ、画像一覧)を保持するモデル +/// +public class GalleryItem +{ + /// + /// 作品ID(例: mo3469109) + /// + public string Id { get; set; } = string.Empty; + + /// + /// 作品タイトル + /// + public string Title { get; set; } = string.Empty; + + /// + /// カテゴリ(例: 同人誌, fanzine, 商業誌, magazine 等) + /// + public string Category { get; set; } = string.Empty; + + /// + /// サークル名 + /// + public string? Circle { get; set; } + + /// + /// 作者名 + /// + public string? Author { get; set; } + + /// + /// タグ一覧 + /// + public List Tags { get; set; } = new(); + + /// + /// 総ページ数 + /// + public int TotalPages => Images.Count; + + /// + /// 表紙・サムネイル画像のURL + /// + public string? ThumbnailUrl { get; set; } + + /// + /// 取得元サイト名(例: momon-ga) + /// + public string SourceSite { get; set; } = string.Empty; + + /// + /// 取得元の元ページURL + /// + public string SourceUrl { get; set; } = string.Empty; + + /// + /// 画像リスト + /// + public List Images { get; set; } = new(); + + /// + /// データ取得日時 + /// + public DateTime FetchedAt { get; set; } = DateTime.UtcNow; +} diff --git a/WebImageViewer/Class/Models/ImageInfo.cs b/WebImageViewer/Class/Models/ImageInfo.cs new file mode 100644 index 0000000..e98ff5a --- /dev/null +++ b/WebImageViewer/Class/Models/ImageInfo.cs @@ -0,0 +1,37 @@ +namespace WebImageViewer.Class.Models; + +/// +/// ギャラリー内の各画像情報を保持するモデル +/// +public class ImageInfo +{ + /// + /// ページ番号(1始まり) + /// + public int PageNumber { get; set; } + + /// + /// 画像のURL + /// + public string ImageUrl { get; set; } = string.Empty; + + /// + /// サムネイル画像のURL(未設定の場合はImageUrlと同じ) + /// + public string? ThumbnailUrl { get; set; } + + /// + /// 画像の代替テキスト + /// + public string? AltText { get; set; } + + /// + /// 画像の横幅(取得できた場合) + /// + public int? Width { get; set; } + + /// + /// 画像の高さ(取得できた場合) + /// + public int? Height { get; set; } +} diff --git a/WebImageViewer/Class/Renderers/HtmlRenderer.cs b/WebImageViewer/Class/Renderers/HtmlRenderer.cs new file mode 100644 index 0000000..53a7ca9 --- /dev/null +++ b/WebImageViewer/Class/Renderers/HtmlRenderer.cs @@ -0,0 +1,1314 @@ +using System.Text.Encodings.Web; +using System.Text.Json; +using WebImageViewer.Class.Models; + +namespace WebImageViewer.Class.Renderers; + +/// +/// WebImageViewerの洗練されたモダンUI HTMLを生成するレンダークラス +/// +public static class HtmlRenderer +{ + private static readonly HtmlEncoder Encoder = HtmlEncoder.Default; + + /// + /// ギャラリー閲覧画面のHTMLを生成します。 + /// + public static string RenderGalleryViewer(GalleryItem gallery) + { + var title = Encoder.Encode(gallery.Title); + var category = Encoder.Encode(gallery.Category); + var circle = !string.IsNullOrEmpty(gallery.Circle) ? Encoder.Encode(gallery.Circle) : null; + var author = !string.IsNullOrEmpty(gallery.Author) ? Encoder.Encode(gallery.Author) : null; + var sourceSite = Encoder.Encode(gallery.SourceSite); + var sourceUrl = Encoder.Encode(gallery.SourceUrl); + var totalPages = gallery.TotalPages; + + var galleryJson = JsonSerializer.Serialize(gallery, new JsonSerializerOptions + { + PropertyNamingPolicy = JsonNamingPolicy.CamelCase, + Encoder = System.Text.Encodings.Web.JavaScriptEncoder.UnsafeRelaxedJsonEscaping + }); + + // タグバッジHTMLの生成 + var tagsHtml = string.Empty; + if (gallery.Tags.Count > 0) + { + var tagItems = string.Join("\n", gallery.Tags.Select(t => $"#{Encoder.Encode(t)}")); + tagsHtml = $""" +
+ {tagItems} +
+ """; + } + + // スクロール用画像リストHTMLの生成 + var imagesHtml = string.Join("\n", gallery.Images.Select(img => + { + var imgUrl = Encoder.Encode(img.ImageUrl); + var altText = Encoder.Encode(img.AltText ?? $"{gallery.Title} {img.PageNumber}ページ"); + return $""" +
+ {altText} +
{img.PageNumber} / {totalPages}
+
+ """; + })); + + // サムネイル一覧HTMLの生成 + var thumbsHtml = string.Join("\n", gallery.Images.Select(img => + { + var thumbUrl = Encoder.Encode(img.ThumbnailUrl ?? img.ImageUrl); + return $""" +
+ {img.PageNumber} +
{img.PageNumber}
+
+ """; + })); + + var circleHeaderHtml = circle != null ? $"サークル: {circle}" : ""; + var authorHeaderHtml = author != null ? $"作者: {author}" : ""; + var circleInfoHtml = circle != null ? $"🏢 サークル: {circle}" : ""; + var authorInfoHtml = author != null ? $"✍️ 作者: {author}" : ""; + + return $$""" + + + + + + {{title}} - WebImageViewer + + + + + + + + +
+
+ + + + +
+
+ + + + +
+
+ + +
+ + +
+ + +
+

{{title}}

+
+ 📁 カテゴリ: {{category}} + {{circleInfoHtml}} + {{authorInfoHtml}} + 📄 総ページ数: {{totalPages}} ページ + 🔗 元サイト: {{sourceSite}} +
+ {{tagsHtml}} +
+ + + {{imagesHtml}} + + +
+

🎉 最後のページに到達しました(全 {{totalPages}} ページ)

+

閲覧ありがとうございます!

+ +
+ +
+ + +
+
+ Slide Image + +
+ +
+ +
+ +
+
+
+ +
+ + +
+
+ 1 + / + {{totalPages}} +
+ +
+
+
+ +
+ + +
+
+ + +
+
+
+

📖 サムネイル一覧 ({{totalPages}} ページ)

+ +
+
+ {{thumbsHtml}} +
+
+ + + + + + + +"""; + } + + /// + /// ホーム画面(URL・ID入力フォーム)のHTMLを生成します。 + /// + public static string RenderHomePage() + { + return """ + + + + + + WebImageViewer - プレミアム画像ビューアー + + + + + + +
+
+

WebImageViewer

+

高速スクレイピングと洗練されたモダンUIで快適な画像閲覧体験を

+
+ +
+
+ +
+ + +
+
+ + +
+ +
+
+
⚡
+
超高速キャッシュ
+
メモリキャッシュによるストレスフリーな即時表示
+
+
+
📱
+
2つの閲覧モード
+
快適な縦スクロール&コミックスライド表示に対応
+
+
+
⌨️
+
キーボード操作
+
矢印キー、全画面、サムネイル一覧ジャンプ
+
+
+
+ + + + +"""; + } + + /// + /// エラー画面(ギャラリーが見つからない場合等)のHTMLを生成します。 + /// + public static string RenderErrorPage(string message, int statusCode = 404) + { + return $$""" + + + + + + エラー {{statusCode}} - WebImageViewer + + + + + +
+
{{statusCode}}
+

ギャラリーを取得できませんでした

+

{{Encoder.Encode(message)}}

+ ホームへ戻る +
+ + +"""; + } +} diff --git a/WebImageViewer/Class/Scrapers/MomongaScraper.cs b/WebImageViewer/Class/Scrapers/MomongaScraper.cs new file mode 100644 index 0000000..241eac6 --- /dev/null +++ b/WebImageViewer/Class/Scrapers/MomongaScraper.cs @@ -0,0 +1,233 @@ +using System.Text.RegularExpressions; +using HtmlAgilityPack; +using Microsoft.Extensions.Logging; +using WebImageViewer.Class.Common; +using WebImageViewer.Class.Models; + +namespace WebImageViewer.Class.Scrapers; + +/// +/// momon-ga.com 固有のスクレイパークラス +/// +public partial class MomongaScraper : BaseScraper +{ + private const string BaseDomain = "momon-ga.com"; + private const string BaseUrl = "https://momon-ga.com"; + + public override string SiteName => "momon-ga"; + + public MomongaScraper(HttpHelper httpHelper, ILogger logger) + : base(httpHelper, logger) + { + } + + /// + public override bool CanHandle(string urlOrPath) + { + if (string.IsNullOrWhiteSpace(urlOrPath)) + { + return false; + } + + // momon-ga のドメインが含まれているか、または典型的なID形式(moから始まる等)かパス形式 + return urlOrPath.Contains(BaseDomain, StringComparison.OrdinalIgnoreCase) || + urlOrPath.StartsWith("mo", StringComparison.OrdinalIgnoreCase) || + urlOrPath.Contains("fanzine", StringComparison.OrdinalIgnoreCase) || + urlOrPath.Contains("magazine", StringComparison.OrdinalIgnoreCase); + } + + /// + public override async Task ScrapeAsync(string idOrUrl, string? category = null, CancellationToken cancellationToken = default) + { + var (targetUrl, normalizedId, resolvedCategory) = ResolveUrlAndId(idOrUrl, category); + + Logger.LogInformation("[{SiteName}] スクレイピング開始 - ID: {Id}, Category: {Category}, URL: {Url}", + SiteName, normalizedId, resolvedCategory, targetUrl); + + var doc = await LoadHtmlDocumentAsync(targetUrl, cancellationToken); + if (doc == null || doc.DocumentNode == null) + { + Logger.LogWarning("[{SiteName}] ドキュメントの読み込みに失敗しました: {Url}", SiteName, targetUrl); + return null; + } + + // タイトルの抽出(h1タグ、またはpost-data内のh1、またはtitleタグ) + var titleNode = doc.DocumentNode.SelectSingleNode("//div[@id='post-data']//h1") ?? + doc.DocumentNode.SelectSingleNode("//h1") ?? + doc.DocumentNode.SelectSingleNode("//title"); + var title = CleanText(titleNode?.InnerText) ?? normalizedId; + + // 余分なサイト名表記を除去(例: "新妻契約 - 同人誌 - エロ漫画 momon:GA(モモンガッ!!)" -> "新妻契約") + if (title.Contains(" - ")) + { + title = title.Split(" - ")[0].Trim(); + } + + var galleryItem = new GalleryItem + { + Id = normalizedId, + Title = string.IsNullOrEmpty(title) ? normalizedId : title, + Category = resolvedCategory, + SourceSite = SiteName, + SourceUrl = targetUrl, + FetchedAt = DateTime.UtcNow + }; + + // サークル、作者、タグの抽出 + ExtractTagsAndMetadata(doc, galleryItem); + + // 画像一覧の抽出(#post-hentai img) + ExtractImages(doc, galleryItem); + + // サムネイルの決定(data-thumb属性、または1枚目の画像) + var historyNode = doc.DocumentNode.SelectSingleNode("//div[contains(@class, 'history')]"); + var dataThumb = historyNode?.GetAttributeValue("data-thumb", null); + if (!string.IsNullOrWhiteSpace(dataThumb)) + { + galleryItem.ThumbnailUrl = dataThumb; + } + else if (galleryItem.Images.Count > 0) + { + galleryItem.ThumbnailUrl = galleryItem.Images[0].ImageUrl; + } + + Logger.LogInformation("[{SiteName}] スクレイピング完了: 『{Title}』, 画像数: {Count}枚", + SiteName, galleryItem.Title, galleryItem.Images.Count); + + return galleryItem; + } + + /// + /// IDまたはURLから完全なリクエストURL、正規化されたID、カテゴリを解決します。 + /// + private static (string TargetUrl, string NormalizedId, string ResolvedCategory) ResolveUrlAndId(string idOrUrl, string? category) + { + var trimmed = idOrUrl.Trim(); + string resolvedCategory = string.IsNullOrWhiteSpace(category) ? "fanzine" : category.Trim().ToLowerInvariant(); + string normalizedId; + + if (trimmed.StartsWith("http://", StringComparison.OrdinalIgnoreCase) || + trimmed.StartsWith("https://", StringComparison.OrdinalIgnoreCase)) + { + // URL形式の場合 + var uri = new Uri(trimmed); + var segments = uri.AbsolutePath.Split('/', StringSplitOptions.RemoveEmptyEntries); + if (segments.Length >= 2) + { + resolvedCategory = segments[0]; + normalizedId = segments[1]; + } + else if (segments.Length == 1) + { + normalizedId = segments[0]; + } + else + { + normalizedId = trimmed; + } + + return ($"{BaseUrl}/{resolvedCategory}/{normalizedId}/", normalizedId, resolvedCategory); + } + + // パスまたはIDのみの場合(例: "fanzine/mo3469109" や "mo3469109") + if (trimmed.Contains('/')) + { + var parts = trimmed.Split('/', StringSplitOptions.RemoveEmptyEntries); + if (parts.Length >= 2) + { + resolvedCategory = parts[0]; + normalizedId = parts[1]; + } + else + { + normalizedId = parts[0]; + } + } + else + { + normalizedId = trimmed; + } + + var fullUrl = $"{BaseUrl}/{resolvedCategory}/{normalizedId}/"; + return (fullUrl, normalizedId, resolvedCategory); + } + + /// + /// タグテーブルからサークル、作者、内容タグを抽出します。 + /// + private static void ExtractTagsAndMetadata(HtmlDocument doc, GalleryItem item) + { + var tagTables = doc.DocumentNode.SelectNodes("//div[@id='post-tag']//div[contains(@class, 'post-tag-table')]"); + if (tagTables == null) return; + + foreach (var table in tagTables) + { + var titleNode = table.SelectSingleNode(".//div[contains(@class, 'post-tag-title')]"); + var titleText = CleanText(titleNode?.InnerText); + + var linkNodes = table.SelectNodes(".//div[contains(@class, 'post-tags')]//a"); + if (linkNodes == null) continue; + + var tagValues = linkNodes.Select(n => CleanText(n.InnerText)).Where(s => !string.IsNullOrEmpty(s)).ToList(); + + if (titleText.Contains("サークル", StringComparison.OrdinalIgnoreCase) || titleText.Contains("グループ", StringComparison.OrdinalIgnoreCase)) + { + item.Circle = string.Join(", ", tagValues); + } + else if (titleText.Contains("作者", StringComparison.OrdinalIgnoreCase) || titleText.Contains("漫画家", StringComparison.OrdinalIgnoreCase)) + { + item.Author = string.Join(", ", tagValues); + } + else if (titleText.Contains("内容", StringComparison.OrdinalIgnoreCase) || titleText.Contains("タグ", StringComparison.OrdinalIgnoreCase) || titleText.Contains("キャラクター", StringComparison.OrdinalIgnoreCase)) + { + item.Tags.AddRange(tagValues); + } + } + } + + /// + /// 本文領域から画像一覧を抽出します。 + /// + private static void ExtractImages(HtmlDocument doc, GalleryItem item) + { + var imgNodes = doc.DocumentNode.SelectNodes("//div[@id='post-hentai']//img") ?? + doc.DocumentNode.SelectNodes("//div[contains(@class, 'entry-content')]//img") ?? + doc.DocumentNode.SelectNodes("//article//img"); + + if (imgNodes == null) return; + + int pageNum = 1; + foreach (var img in imgNodes) + { + // src または data-src, data-lazy-src 属性から画像URLを取得 + var src = img.GetAttributeValue("src", null) ?? + img.GetAttributeValue("data-src", null) ?? + img.GetAttributeValue("data-lazy-src", null); + + if (string.IsNullOrWhiteSpace(src)) continue; + + // 広告画像やアイコン等を除外 + if (src.Contains("themes", StringComparison.OrdinalIgnoreCase) || + src.Contains("plugins", StringComparison.OrdinalIgnoreCase) || + src.Contains("banner", StringComparison.OrdinalIgnoreCase) || + src.Contains("ad_", StringComparison.OrdinalIgnoreCase)) + { + continue; + } + + var alt = img.GetAttributeValue("alt", null); + int? width = int.TryParse(img.GetAttributeValue("width", null), out var w) ? w : null; + int? height = int.TryParse(img.GetAttributeValue("height", null), out var h) ? h : null; + + item.Images.Add(new ImageInfo + { + PageNumber = pageNum++, + ImageUrl = src, + ThumbnailUrl = src, + AltText = CleanText(alt), + Width = width, + Height = height + }); + } + } +} diff --git a/WebImageViewer/Class/Services/GalleryService.cs b/WebImageViewer/Class/Services/GalleryService.cs new file mode 100644 index 0000000..3f4dd1e --- /dev/null +++ b/WebImageViewer/Class/Services/GalleryService.cs @@ -0,0 +1,77 @@ +using Microsoft.Extensions.Caching.Memory; +using Microsoft.Extensions.Logging; +using WebImageViewer.Class.Common; +using WebImageViewer.Class.Models; + +namespace WebImageViewer.Class.Services; + +/// +/// 各種スクレイパーを管理し、ギャラリーの取得とキャッシュ制御を行うサービスクラス +/// +public class GalleryService +{ + private readonly IEnumerable _scrapers; + private readonly IMemoryCache _cache; + private readonly ILogger _logger; + + // キャッシュ有効期間(デフォルト: 1時間) + private static readonly TimeSpan DefaultCacheDuration = TimeSpan.FromHours(1); + + public GalleryService( + IEnumerable scrapers, + IMemoryCache cache, + ILogger logger) + { + _scrapers = scrapers; + _cache = cache; + _logger = logger; + } + + /// + /// 指定されたIDまたはURL、カテゴリからギャラリー情報を取得します(キャッシュ付き)。 + /// + /// 作品IDまたはURL + /// カテゴリ(fanzine, magazineなど) + /// キャッシュを無視して再取得するかどうか + /// キャンセレーショントークン + /// 取得したGalleryItem + public async Task GetGalleryAsync( + string idOrUrl, + string? category = null, + bool bypassCache = false, + CancellationToken cancellationToken = default) + { + if (string.IsNullOrWhiteSpace(idOrUrl)) + { + return null; + } + + var cacheKey = $"gallery_{category ?? "default"}_{idOrUrl.Trim().ToLowerInvariant()}"; + + if (!bypassCache && _cache.TryGetValue(cacheKey, out GalleryItem? cachedItem) && cachedItem != null) + { + _logger.LogInformation("キャッシュからギャラリー情報を取得しました: {Key}", cacheKey); + return cachedItem; + } + + // 処理可能なスクレイパーを探索 + var scraper = _scrapers.FirstOrDefault(s => s.CanHandle(idOrUrl)); + if (scraper == null) + { + _logger.LogWarning("対象のURL/IDを処理できるスクレイパーが見つかりませんでした: {Input}", idOrUrl); + return null; + } + + _logger.LogInformation("スクレイパー [{SiteName}] を使用して取得を開始します: {Input}", scraper.SiteName, idOrUrl); + + var result = await scraper.ScrapeAsync(idOrUrl, category, cancellationToken); + if (result != null && result.Images.Count > 0) + { + // キャッシュに保存 + _cache.Set(cacheKey, result, DefaultCacheDuration); + _logger.LogInformation("ギャラリー情報をキャッシュに保存しました: {Key} (画像 {Count} 枚)", cacheKey, result.Images.Count); + } + + return result; + } +} diff --git a/WebImageViewer/Program.cs b/WebImageViewer/Program.cs new file mode 100644 index 0000000..0311b95 --- /dev/null +++ b/WebImageViewer/Program.cs @@ -0,0 +1,141 @@ +using Microsoft.AspNetCore.HttpOverrides; +using WebImageViewer.Class.Common; +using WebImageViewer.Class.Renderers; +using WebImageViewer.Class.Scrapers; +using WebImageViewer.Class.Services; + +var builder = WebApplication.CreateBuilder(args); + +// ========================================== +// サービスの登録 (DIコンテナ) +// ========================================== + +// メモリキャッシュ機能の追加(VPSのトラフィック削減・高速化) +builder.Services.AddMemoryCache(); + +// HTTP通信用ヘルパーの登録 +builder.Services.AddHttpClient(); + +// 各種スクレイパークラスの登録(Class/Scrapers フォルダより) +builder.Services.AddScoped(); +builder.Services.AddScoped(); + +// ギャラリー統括管理サービスの登録(Class/Services フォルダより) +builder.Services.AddScoped(); + +// VPS(リバースプロキシ環境: https://udukipc-web.armonica-vps.work/)対応のフォワードヘッダー設定 +builder.Services.Configure(options => +{ + options.ForwardedHeaders = ForwardedHeaders.XForwardedFor | ForwardedHeaders.XForwardedProto | ForwardedHeaders.XForwardedHost; + // リバースプロキシ背後での動作を許可 + options.KnownIPNetworks.Clear(); + options.KnownProxies.Clear(); +}); + +var app = builder.Build(); + +// ========================================== +// ミドルウェアパイプラインの設定 +// ========================================== + +app.UseForwardedHeaders(); + +// ========================================== +// ルーティング・エンドポイントの定義 +// ========================================== + +// トップページ(URL入力・ギャラリー検索UI) +app.MapGet("/", () => Results.Content(HtmlRenderer.RenderHomePage(), "text/html; charset=utf-8")); + +// 同人誌ビューアー画面(例: /fanzine/mo3469109/) +app.MapGet("/fanzine/{id}", async (string id, GalleryService galleryService, CancellationToken ct) => +{ + var gallery = await galleryService.GetGalleryAsync(id, "fanzine", false, ct); + if (gallery == null || gallery.Images.Count == 0) + { + return Results.Content( + HtmlRenderer.RenderErrorPage($"指定された作品(ID: {id})の画像一覧を取得できませんでした。URLまたはIDをご確認ください。", 404), + "text/html; charset=utf-8", + statusCode: 404); + } + + return Results.Content(HtmlRenderer.RenderGalleryViewer(gallery), "text/html; charset=utf-8"); +}); + +// 商業誌・雑誌ビューアー画面(例: /magazine/{id}/) +app.MapGet("/magazine/{id}", async (string id, GalleryService galleryService, CancellationToken ct) => +{ + var gallery = await galleryService.GetGalleryAsync(id, "magazine", false, ct); + if (gallery == null || gallery.Images.Count == 0) + { + return Results.Content( + HtmlRenderer.RenderErrorPage($"指定された雑誌・商業誌(ID: {id})の画像一覧を取得できませんでした。", 404), + "text/html; charset=utf-8", + statusCode: 404); + } + + return Results.Content(HtmlRenderer.RenderGalleryViewer(gallery), "text/html; charset=utf-8"); +}); + +// JSON API: 同人誌メタデータおよび画像リストの取得(例: /api/fanzine/mo3469109) +app.MapGet("/api/fanzine/{id}", async (string id, GalleryService galleryService, CancellationToken ct) => +{ + var gallery = await galleryService.GetGalleryAsync(id, "fanzine", false, ct); + if (gallery == null) + { + return Results.NotFound(new { error = "Gallery not found", id, category = "fanzine" }); + } + + return Results.Ok(gallery); +}); + +// JSON API: 商業誌メタデータおよび画像リストの取得 +app.MapGet("/api/magazine/{id}", async (string id, GalleryService galleryService, CancellationToken ct) => +{ + var gallery = await galleryService.GetGalleryAsync(id, "magazine", false, ct); + if (gallery == null) + { + return Results.NotFound(new { error = "Gallery not found", id, category = "magazine" }); + } + + return Results.Ok(gallery); +}); + +// 汎用スクレイピングAPI(URLまたはIDを受け取り画像一覧を取得) +app.MapGet("/api/scrape", async (string? url, string? id, string? category, GalleryService galleryService, CancellationToken ct) => +{ + var target = url ?? id; + if (string.IsNullOrWhiteSpace(target)) + { + return Results.BadRequest(new { error = "url または id パラメータを指定してください。" }); + } + + var gallery = await galleryService.GetGalleryAsync(target, category, false, ct); + if (gallery == null) + { + return Results.NotFound(new { error = "Gallery not found", target }); + } + + return Results.Ok(gallery); +}); + +// 画像プロキシエンドポイント(CORSや外部Referer制約を回避する必要がある場合に使用) +app.MapGet("/api/proxy-image", async (string url, string? referer, HttpHelper httpHelper, CancellationToken ct) => +{ + if (string.IsNullOrWhiteSpace(url)) + { + return Results.BadRequest("URL is required"); + } + + try + { + var (data, contentType) = await httpHelper.GetBinaryAsync(url, referer, ct); + return Results.File(data, contentType); + } + catch (Exception ex) + { + return Results.Problem(detail: ex.Message, statusCode: 502); + } +}); + +app.Run(); diff --git a/WebImageViewer/Properties/PublishProfiles/FolderProfile.pubxml b/WebImageViewer/Properties/PublishProfiles/FolderProfile.pubxml new file mode 100644 index 0000000..92637e6 --- /dev/null +++ b/WebImageViewer/Properties/PublishProfiles/FolderProfile.pubxml @@ -0,0 +1,15 @@ + + + + + false + false + true + Release + Any CPU + FileSystem + C:\docker\web\ + FileSystem + <_TargetId>Folder + + \ No newline at end of file diff --git a/WebImageViewer/Properties/launchSettings.json b/WebImageViewer/Properties/launchSettings.json new file mode 100644 index 0000000..4d11d9e --- /dev/null +++ b/WebImageViewer/Properties/launchSettings.json @@ -0,0 +1,14 @@ +{ + "$schema": "https://json.schemastore.org/launchsettings.json", + "profiles": { + "http": { + "commandName": "Project", + "dotnetRunMessages": true, + "launchBrowser": false, + "applicationUrl": "http://localhost:5175", + "environmentVariables": { + "ASPNETCORE_ENVIRONMENT": "Development" + } + } + } +} diff --git a/WebImageViewer/WebImageViewer.csproj b/WebImageViewer/WebImageViewer.csproj new file mode 100644 index 0000000..7d7b4d6 --- /dev/null +++ b/WebImageViewer/WebImageViewer.csproj @@ -0,0 +1,13 @@ + + + + net10.0 + enable + enable + + + + + + + diff --git a/WebImageViewer/WebImageViewer.http b/WebImageViewer/WebImageViewer.http new file mode 100644 index 0000000..185094f --- /dev/null +++ b/WebImageViewer/WebImageViewer.http @@ -0,0 +1,6 @@ +@WebImageViewer_HostAddress = http://localhost:5175 + +GET {{WebImageViewer_HostAddress}}/fanzine/mo3469109 +Accept: application/json + +### diff --git a/WebImageViewer/appsettings.Development.json b/WebImageViewer/appsettings.Development.json new file mode 100644 index 0000000..0c208ae --- /dev/null +++ b/WebImageViewer/appsettings.Development.json @@ -0,0 +1,8 @@ +{ + "Logging": { + "LogLevel": { + "Default": "Information", + "Microsoft.AspNetCore": "Warning" + } + } +} diff --git a/WebImageViewer/appsettings.json b/WebImageViewer/appsettings.json new file mode 100644 index 0000000..10f68b8 --- /dev/null +++ b/WebImageViewer/appsettings.json @@ -0,0 +1,9 @@ +{ + "Logging": { + "LogLevel": { + "Default": "Information", + "Microsoft.AspNetCore": "Warning" + } + }, + "AllowedHosts": "*" +}