diff --git a/WebImageViewer/Class/Renderers/HtmlRenderer.cs b/WebImageViewer/Class/Renderers/HtmlRenderer.cs index 87a6418..3710344 100644 --- a/WebImageViewer/Class/Renderers/HtmlRenderer.cs +++ b/WebImageViewer/Class/Renderers/HtmlRenderer.cs @@ -1269,12 +1269,13 @@ public static class HtmlRenderer +
- +
@@ -1322,6 +1323,16 @@ public static class HtmlRenderer
開く →
+ +
+
+ MANGALEAR + /mangalear/289385 +
+
これが…本当のセクササイズだ… / 羽川ハスミ (24ページ)
+
+
開く →
+
@@ -1479,6 +1490,17 @@ public static class HtmlRenderer window.location.href = '/momonga/' + id + '/'; return; } + if (host.includes('mangalear.blog')) { + const p = url.searchParams.get('p'); + if (p) { + window.location.href = '/mangalear/' + p + '/'; + return; + } + const segs = path.split('/'); + const id = segs.length >= 2 ? segs[1] : segs[0]; + window.location.href = '/mangalear/' + id + '/'; + return; + } // 汎用ビューアーへ window.location.href = '/view?url=' + encodeURIComponent(input); diff --git a/WebImageViewer/Class/Scrapers/MangalearScraper.cs b/WebImageViewer/Class/Scrapers/MangalearScraper.cs new file mode 100644 index 0000000..35bc821 --- /dev/null +++ b/WebImageViewer/Class/Scrapers/MangalearScraper.cs @@ -0,0 +1,360 @@ +using System.Text.RegularExpressions; +using HtmlAgilityPack; +using Microsoft.Extensions.Logging; +using WebImageViewer.Class.Common; +using WebImageViewer.Class.Models; + +namespace WebImageViewer.Class.Scrapers; + +/// +/// mangalear.blog(同人まんがりあ)固有のスクレイパークラス +/// +public partial class MangalearScraper : BaseScraper +{ + private const string BaseDomain = "mangalear.blog"; + private const string BaseUrl = "https://www.mangalear.blog"; + + public override string SiteName => "mangalear"; + public override string SiteKey => "mangalear"; + public override IReadOnlyList Aliases => new[] { "mangalear.blog", "doujinshi", "まんがりあ" }; + + public MangalearScraper(HttpHelper httpHelper, ILogger logger) + : base(httpHelper, logger) + { + } + + /// + public override bool CanHandle(string urlOrPath) + { + if (string.IsNullOrWhiteSpace(urlOrPath)) + { + return false; + } + + var trimmed = urlOrPath.Trim(); + + // サイトキーまたはエイリアスと完全一致 + if (string.Equals(trimmed, SiteKey, StringComparison.OrdinalIgnoreCase) || + Aliases.Any(a => string.Equals(trimmed, a, StringComparison.OrdinalIgnoreCase))) + { + return true; + } + + // mangalear のドメインが含まれているか + if (trimmed.Contains(BaseDomain, StringComparison.OrdinalIgnoreCase)) + { + return true; + } + + // doujinshi パスが含まれているか + if (trimmed.Contains("doujinshi", StringComparison.OrdinalIgnoreCase)) + { + return true; + } + + return false; + } + + /// + 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entry-titleクラス、またはtitleタグ) + var titleNode = doc.DocumentNode.SelectSingleNode("//h1[contains(@class, 'entry-title')]") ?? + doc.DocumentNode.SelectSingleNode("//h1") ?? + doc.DocumentNode.SelectSingleNode("//title"); + var title = CleanText(titleNode?.InnerText) ?? normalizedId; + + // タイトルの整形(先頭の「▲」記号や末尾のサイト名を除去) + title = CleanTitle(title); + + var galleryItem = new GalleryItem + { + Id = normalizedId, + Title = string.IsNullOrEmpty(title) ? normalizedId : title, + Category = resolvedCategory, + SourceSite = SiteName, + SourceUrl = targetUrl, + FetchedAt = DateTime.UtcNow + }; + + // メタデータ(カテゴリ、タグ、作者等)の抽出 + ExtractMetadata(doc, galleryItem); + + // 画像一覧の抽出 + ExtractImages(doc, galleryItem); + + 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 Category) ResolveUrlAndId(string idOrUrl, string? category) + { + var trimmed = idOrUrl.Trim(); + string normalizedId = string.Empty; + string resolvedCategory = !string.IsNullOrWhiteSpace(category) ? category.Trim() : "doujinshi"; + + if (trimmed.StartsWith("http://", StringComparison.OrdinalIgnoreCase) || + trimmed.StartsWith("https://", StringComparison.OrdinalIgnoreCase)) + { + var uri = new Uri(trimmed); + + // ?p=12345 形式のクエリパラメータ判定 + var query = System.Web.HttpUtility.ParseQueryString(uri.Query); + var pVal = query.Get("p"); + if (!string.IsNullOrEmpty(pVal)) + { + normalizedId = pVal; + } + else + { + // パスからカテゴリとIDを取得 (例: /doujinshi/289385/) + 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]; + } + } + + return (trimmed, normalizedId, resolvedCategory); + } + + // パス形式 (例: doujinshi/289385) + 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; + } + + // URLを構築 (例: https://www.mangalear.blog/doujinshi/289385/) + var fullUrl = $"{BaseUrl}/{resolvedCategory}/{normalizedId}/"; + return (fullUrl, normalizedId, resolvedCategory); + } + + /// + /// タイトル文字列から不要な記号やサイト名サフィックスを除去します。 + /// + private static string CleanTitle(string title) + { + if (string.IsNullOrWhiteSpace(title)) return title; + + // 先頭の「▲」を除去 + title = title.TrimStart('▲', '▼', ' ', '\t'); + + // 末尾のサイト名表記を除去 (例: "タイトル - 同人まんがりあ") + if (title.Contains(" - ")) + { + var parts = title.Split(" - "); + if (parts.Length > 1 && parts[^1].Contains("まんがりあ", StringComparison.OrdinalIgnoreCase)) + { + title = string.Join(" - ", parts.Take(parts.Length - 1)); + } + } + + return title.Trim(); + } + + /// + /// メタデータ(タグ、カテゴリ、作者)をHTMLから抽出します。 + /// + private static void ExtractMetadata(HtmlDocument doc, GalleryItem item) + { + // 1. カテゴリの抽出 (.entry-categories a.cat-link) + var catNodes = doc.DocumentNode.SelectNodes("//div[contains(@class, 'entry-categories')]//a[contains(@class, 'cat-link')]"); + if (catNodes != null) + { + foreach (var node in catNodes) + { + var catText = CleanText(node.InnerText); + if (!string.IsNullOrEmpty(catText) && (string.IsNullOrEmpty(item.Category) || item.Category == "doujinshi")) + { + item.Category = catText; + break; + } + } + } + + // 2. タグの抽出 (.entry-tags a.tag-link) + var tagNodes = doc.DocumentNode.SelectNodes("//div[contains(@class, 'entry-tags')]//a[contains(@class, 'tag-link')]"); + if (tagNodes != null) + { + foreach (var node in tagNodes) + { + var tag = CleanText(node.InnerText); + if (!string.IsNullOrEmpty(tag) && !item.Tags.Contains(tag)) + { + item.Tags.Add(tag); + } + } + } + + // 3. 作者の抽出 (.author-info .author-name) + var authorNode = doc.DocumentNode.SelectSingleNode("//div[contains(@class, 'author-info')]//*[contains(@class, 'author-name')]"); + if (authorNode != null) + { + var author = CleanText(authorNode.InnerText); + if (!string.IsNullOrEmpty(author)) + { + item.Author = author; + } + } + else + { + item.Author = "同人まんがりあ"; + } + } + + /// + /// 記事本文から全画像一覧を抽出します。 + /// + private static void ExtractImages(HtmlDocument doc, GalleryItem item) + { + // 本文コンテナの取得 (.entry-content または article) + var contentNode = doc.DocumentNode.SelectSingleNode("//div[contains(@class, 'entry-content')]") ?? + doc.DocumentNode.SelectSingleNode("//article"); + + if (contentNode == null) return; + + // 本文内のすべての img タグを取得 + var imgNodes = contentNode.SelectNodes(".//img"); + if (imgNodes == null || imgNodes.Count == 0) return; + + var seenUrls = new HashSet(StringComparer.OrdinalIgnoreCase); + int pageIndex = 1; + + foreach (var img in imgNodes) + { + // 広告やアイコンなどの不要な画像を除外 + var cssClass = img.GetAttributeValue("class", string.Empty); + if (cssClass.Contains("wp-smiley") || cssClass.Contains("avatar")) + { + continue; + } + + string? highResUrl = null; + string? thumbUrl = null; + + // 1. 親要素が タグの場合、href属性からオリジナル画像URLの取得を試みる + var parentAnchor = img.ParentNode?.Name.Equals("a", StringComparison.OrdinalIgnoreCase) == true + ? img.ParentNode + : img.Ancestors("a").FirstOrDefault(); + + if (parentAnchor != null) + { + var href = parentAnchor.GetAttributeValue("href", null)?.Trim(); + if (!string.IsNullOrEmpty(href) && IsImageExtension(href)) + { + highResUrl = href; + } + } + + // 2. img タグの属性(src / data-src)からURLを取得 + var src = img.GetAttributeValue("src", null)?.Trim(); + var dataSrc = img.GetAttributeValue("data-src", null)?.Trim(); + var candidateSrc = !string.IsNullOrEmpty(dataSrc) ? dataSrc : src; + + if (string.IsNullOrEmpty(highResUrl)) + { + highResUrl = candidateSrc; + } + else + { + thumbUrl = candidateSrc; + } + + if (string.IsNullOrEmpty(highResUrl)) + { + continue; + } + + // 混在コンテンツ警告を防ぐため、http:// を https:// に正規化 + highResUrl = NormalizeToHttps(highResUrl); + if (!string.IsNullOrEmpty(thumbUrl)) + { + thumbUrl = NormalizeToHttps(thumbUrl); + } + + // 重複チェック + if (!seenUrls.Add(highResUrl)) + { + continue; + } + + var altText = img.GetAttributeValue("alt", null); + + var imageInfo = new ImageInfo + { + PageNumber = pageIndex++, + ImageUrl = highResUrl, + ThumbnailUrl = thumbUrl ?? highResUrl, + AltText = !string.IsNullOrEmpty(altText) ? altText : $"{item.Title} - {pageIndex - 1}ページ" + }; + + item.Images.Add(imageInfo); + } + + // カバー画像(1枚目)を設定 + if (item.Images.Count > 0) + { + item.ThumbnailUrl = item.Images[0].ThumbnailUrl ?? item.Images[0].ImageUrl; + } + } + + /// + /// 指定されたURLが画像ファイルの拡張子を持つかどうかを判定します。 + /// + private static bool IsImageExtension(string url) + { + var cleanUrl = url.Split('?')[0].Split('#')[0]; + return cleanUrl.EndsWith(".jpg", StringComparison.OrdinalIgnoreCase) || + cleanUrl.EndsWith(".jpeg", StringComparison.OrdinalIgnoreCase) || + cleanUrl.EndsWith(".png", StringComparison.OrdinalIgnoreCase) || + cleanUrl.EndsWith(".webp", StringComparison.OrdinalIgnoreCase) || + cleanUrl.EndsWith(".gif", StringComparison.OrdinalIgnoreCase); + } + + /// + /// http:// で始まるURLを https:// に変換します。 + /// + private static string NormalizeToHttps(string url) + { + if (url.StartsWith("http://", StringComparison.OrdinalIgnoreCase)) + { + return "https://" + url.Substring(7); + } + return url; + } +} diff --git a/WebImageViewer/Program.cs b/WebImageViewer/Program.cs index c9de800..0a09945 100644 --- a/WebImageViewer/Program.cs +++ b/WebImageViewer/Program.cs @@ -35,6 +35,8 @@ builder.Services.AddScoped(); builder.Services.AddScoped(); builder.Services.AddScoped(); builder.Services.AddScoped(); +builder.Services.AddScoped(); +builder.Services.AddScoped(); // ギャラリー統括管理サービスの登録 builder.Services.AddScoped();