Compare commits

..
5 Commits
29 changed files with 5193 additions and 590 deletions

No files matched your search

@@ -1,8 +1,8 @@
using HtmlAgilityPack;
using Microsoft.Extensions.Logging;
using WebImageViewer.Class.Models;
using WebImageViewer.Class.Legacy.Models;
namespace WebImageViewer.Class.Common;
namespace WebImageViewer.Class.Legacy.Common;
/// <summary>
/// 各種Webサイトスクレイパーの共通基底クラス
@@ -101,3 +101,4 @@ public abstract class BaseScraper : IScraper
return HtmlEntity.DeEntitize(input).Trim();
}
}
@@ -4,7 +4,7 @@ using System.Text.Json;
using Microsoft.Extensions.Configuration;
using Microsoft.Extensions.Logging;
namespace WebImageViewer.Class.Common;
namespace WebImageViewer.Class.Legacy.Common;
/// <summary>
/// HTTPリクエスト処理およびFlareSolverr連携を行う共通ヘルパークラス
@@ -178,3 +178,4 @@ public class HttpHelper
}
}
@@ -1,6 +1,6 @@
using WebImageViewer.Class.Models;
using WebImageViewer.Class.Legacy.Models;
namespace WebImageViewer.Class.Common;
namespace WebImageViewer.Class.Legacy.Common;
/// <summary>
/// 各スクレイパーが実装すべき共通インターフェース
@@ -39,3 +39,4 @@ public interface IScraper
/// <returns>取得したGalleryItem(失敗時はnull)</returns>
Task<GalleryItem?> ScrapeAsync(string idOrUrl, string? category = null, CancellationToken cancellationToken = default);
}
@@ -0,0 +1,459 @@
using Microsoft.AspNetCore.Builder;
using Microsoft.AspNetCore.Http;
using Microsoft.Extensions.DependencyInjection;
using Microsoft.Extensions.Logging;
using WebImageViewer.Class.Legacy.Common;
using WebImageViewer.Class.Legacy.Renderers;
using WebImageViewer.Class.Legacy.Scrapers;
using WebImageViewer.Class.Legacy.Services;
namespace WebImageViewer.Class.Legacy;
/// <summary>
/// 旧バージョン(Legacy)のルーティングおよびサービス登録クラス
/// ※ 今後は更新を行わず、過去のURLアクセス互換用として隔離・保持します。
/// </summary>
public static class LegacyEndpoints
{
/// <summary>
/// レガシー用のDIサービスを登録します。
/// </summary>
public static IServiceCollection AddLegacyServices(this IServiceCollection services)
{
services.AddHttpClient<HttpHelper>();
services.AddScoped<IScraper, MomongaScraper>();
services.AddScoped<MomongaScraper>();
services.AddScoped<IScraper, AuraHentaiScraper>();
services.AddScoped<AuraHentaiScraper>();
services.AddScoped<IScraper, HitomiScraper>();
services.AddScoped<HitomiScraper>();
services.AddScoped<IScraper, EHentaiScraper>();
services.AddScoped<EHentaiScraper>();
services.AddScoped<IScraper, MangalearScraper>();
services.AddScoped<MangalearScraper>();
services.AddScoped<IScraper, HentaiPawScraper>();
services.AddScoped<HentaiPawScraper>();
services.AddScoped<GalleryService>();
services.AddScoped<VideoUrlResolver>();
return services;
}
/// <summary>
/// 旧バージョン用のエンドポイント(/view, /video, /{site}/{id} 等)をマッピングします。
/// </summary>
public static WebApplication MapLegacyEndpoints(this WebApplication app)
{
// 汎用ビューアー画面 (旧 /view)
app.MapGet("/view", async (string? url, string? site, string? id, string? category, GalleryService galleryService, CancellationToken ct) =>
{
var target = url ?? id;
if (string.IsNullOrWhiteSpace(target))
{
return Results.Redirect("/");
}
if (IsVideoUrlOrSite(site, target))
{
return Results.Redirect($"/video?url={Uri.EscapeDataString(target)}");
}
return await RenderGalleryResponseAsync(site, target, category, galleryService, ct);
});
// 汎用動画プレイヤー画面 (旧 /video)
app.MapGet("/video", async (
string? url,
string? id,
string? site,
string? play,
string? stream,
string? title,
VideoUrlResolver resolver,
CancellationToken ct) =>
{
var target = url ?? id;
if (string.IsNullOrWhiteSpace(target) && string.IsNullOrWhiteSpace(stream) && string.IsNullOrWhiteSpace(play))
{
return Results.Redirect("/");
}
if (IsGalleryUrlOrSite(site, target))
{
return Results.Redirect($"/view?url={Uri.EscapeDataString(target!)}");
}
if (target != null && target.StartsWith("http", StringComparison.OrdinalIgnoreCase) && string.IsNullOrWhiteSpace(play) && string.IsNullOrWhiteSpace(stream))
{
var resolved = await resolver.ResolveAsync(target, title, ct);
if (resolved.IsSuccess)
{
site ??= resolved.Site;
id ??= resolved.VideoId;
play ??= resolved.PlayerUrl;
stream ??= resolved.StreamUrl;
title ??= resolved.Title;
target = resolved.OriginalUrl ?? target;
}
}
if (string.Equals(site, "123av", StringComparison.OrdinalIgnoreCase) || (target != null && target.Contains("123av", StringComparison.OrdinalIgnoreCase)))
{
var vId = (target != null ? Extract123AvId(target) : null) ?? id?.Trim() ?? "video";
var orig = (target != null && target.StartsWith("http", StringComparison.OrdinalIgnoreCase)) ? target : $"https://123av.com/ja/video/{vId}";
return Results.Content(HtmlRenderer.RenderVideoPlayer("123av", vId, play, null, orig, title ?? $"123av 動画 ({vId})"), "text/html; charset=utf-8");
}
if (string.Equals(site, "missav", StringComparison.OrdinalIgnoreCase) || (target != null && target.Contains("missav", StringComparison.OrdinalIgnoreCase)))
{
var vId = (target != null ? ExtractMissAvId(target) : null) ?? id?.Trim() ?? "video";
var orig = (target != null && target.StartsWith("http", StringComparison.OrdinalIgnoreCase)) ? target : $"https://missav.ai/ja/{vId}";
return Results.Content(HtmlRenderer.RenderVideoPlayer("missav", vId, play, stream, orig, title ?? $"missav 動画 ({vId})"), "text/html; charset=utf-8");
}
if (string.Equals(site, "spankbang", StringComparison.OrdinalIgnoreCase) || (target != null && target.Contains("spankbang", StringComparison.OrdinalIgnoreCase)))
{
var videoId = (target != null ? ExtractSpankBangId(target) : null) ?? id?.Trim() ?? "video";
var orig = (target != null && target.StartsWith("http", StringComparison.OrdinalIgnoreCase)) ? target : $"https://jp.spankbang.com/{videoId}/video/";
return Results.Content(HtmlRenderer.RenderVideoPlayer("spankbang", videoId, play ?? $"https://spankbang.com/{videoId}/embed/", stream, orig, title ?? $"SpankBang 動画 ({videoId})"), "text/html; charset=utf-8");
}
if (string.Equals(site, "doga", StringComparison.OrdinalIgnoreCase) || string.Equals(site, "eroterest_doga", StringComparison.OrdinalIgnoreCase) || (target != null && target.Contains("do-ga.eroterest.net", StringComparison.OrdinalIgnoreCase)))
{
var vId = id?.Trim() ?? (target != null ? System.Text.RegularExpressions.Regex.Match(target, @"detail/([0-9]+)").Groups[1].Value : "") ?? "doga";
if (string.IsNullOrWhiteSpace(vId)) vId = "doga";
var orig = (target != null && target.StartsWith("http", StringComparison.OrdinalIgnoreCase)) ? target : $"https://do-ga.eroterest.net/video/detail/{vId}/";
return Results.Content(HtmlRenderer.RenderVideoPlayer("doga", vId, play, stream, orig, title ?? $"エロタレドーガ ({vId})"), "text/html; charset=utf-8");
}
if (string.Equals(site, "inporn", StringComparison.OrdinalIgnoreCase) || (target != null && target.Contains("inporn.com", StringComparison.OrdinalIgnoreCase)))
{
var vId = id?.Trim() ?? (target != null ? System.Text.RegularExpressions.Regex.Match(target, @"/video/([0-9]+)").Groups[1].Value : "") ?? "video";
play ??= $"https://inporn.com/embed/{vId}/";
var orig = (target != null && target.StartsWith("http", StringComparison.OrdinalIgnoreCase)) ? target : $"https://inporn.com/video/{vId}/";
return Results.Content(HtmlRenderer.RenderVideoPlayer("inporn", vId, play, stream, orig, title ?? $"InPorn 動画 ({vId})"), "text/html; charset=utf-8");
}
if (string.Equals(site, "bdsmx", StringComparison.OrdinalIgnoreCase) || (target != null && target.Contains("bdsmx.tube", StringComparison.OrdinalIgnoreCase)))
{
var vId = id?.Trim() ?? (target != null ? System.Text.RegularExpressions.Regex.Match(target, @"/video/([0-9]+)").Groups[1].Value : "") ?? "video";
play ??= $"https://bdsmx.tube/embed/{vId}/";
var orig = (target != null && target.StartsWith("http", StringComparison.OrdinalIgnoreCase)) ? target : $"https://bdsmx.tube/video/{vId}/";
return Results.Content(HtmlRenderer.RenderVideoPlayer("bdsmx", vId, play, stream, orig, title ?? $"BDSMx 動画 ({vId})"), "text/html; charset=utf-8");
}
if (string.Equals(site, "vjav", StringComparison.OrdinalIgnoreCase) || (target != null && target.Contains("vjav.com", StringComparison.OrdinalIgnoreCase)))
{
var vId = (target != null ? System.Text.RegularExpressions.Regex.Match(target, @"/videos/([0-9]+)").Groups[1].Value : null);
if (string.IsNullOrWhiteSpace(vId)) vId = id?.Trim() ?? "video";
play ??= $"https://vjav.com/embed/{vId}/";
var orig = (target != null && target.StartsWith("http", StringComparison.OrdinalIgnoreCase)) ? target : $"https://vjav.com/videos/{vId}/";
return Results.Content(HtmlRenderer.RenderVideoPlayer("vjav", vId, play, stream, orig, title ?? $"VJAV 動画 ({vId})"), "text/html; charset=utf-8");
}
if (string.Equals(site, "laxd", StringComparison.OrdinalIgnoreCase) || (target != null && (target.Contains("video.laxd.com", StringComparison.OrdinalIgnoreCase) || target.Contains("laxd.com", StringComparison.OrdinalIgnoreCase))))
{
var vId = (target != null ? System.Text.RegularExpressions.Regex.Match(target, @"laxd\.com/(?:a/content/|content/|embed/)?([0-9a-zA-Z_\-]+)").Groups[1].Value : null);
if (string.IsNullOrWhiteSpace(vId)) vId = id?.Trim() ?? "video";
play ??= $"https://video.laxd.com/a/embed/player/{vId}/";
var orig = (target != null && target.StartsWith("http", StringComparison.OrdinalIgnoreCase)) ? target : $"https://video.laxd.com/a/content/{vId}";
return Results.Content(HtmlRenderer.RenderVideoPlayer("laxd", vId, play, stream, orig, title ?? $"LAXD 動画 ({vId})"), "text/html; charset=utf-8");
}
if (string.Equals(site, "fc2", StringComparison.OrdinalIgnoreCase) || string.Equals(site, "fc2video", StringComparison.OrdinalIgnoreCase) || (target != null && (target.Contains("contents.fc2.com", StringComparison.OrdinalIgnoreCase) || target.Contains("video.fc2.com", StringComparison.OrdinalIgnoreCase))))
{
var vId = (target != null ? System.Text.RegularExpressions.Regex.Match(target, @"(?:article/|aid=|content/|video/)([0-9a-zA-Z_\-]+)").Groups[1].Value : null);
if (string.IsNullOrWhiteSpace(vId)) vId = id?.Trim() ?? "video";
play ??= $"https://video.fc2.com/a/embed/player/{vId}/";
var orig = (target != null && target.StartsWith("http", StringComparison.OrdinalIgnoreCase)) ? target : $"https://adult.contents.fc2.com/article/{vId}/";
return Results.Content(HtmlRenderer.RenderVideoPlayer("fc2", vId, play, stream, orig, title ?? $"FC2 動画 ({vId})"), "text/html; charset=utf-8");
}
if (string.Equals(site, "xvideos", StringComparison.OrdinalIgnoreCase) || (target != null && target.Contains("xvideos.com", StringComparison.OrdinalIgnoreCase)))
{
var vId = (target != null ? System.Text.RegularExpressions.Regex.Match(target, @"(?:video\.|video|embedframe/)([0-9]+)").Groups[1].Value : null);
if (string.IsNullOrWhiteSpace(vId)) vId = id?.Trim() ?? "video";
play ??= $"https://www.xvideos.com/embedframe/{vId}";
var orig = (target != null && target.StartsWith("http", StringComparison.OrdinalIgnoreCase)) ? target : $"https://www.xvideos.com/video.{vId}/";
return Results.Content(HtmlRenderer.RenderVideoPlayer("xvideos", vId, play, stream, orig, title ?? $"XVIDEOS 動画 ({vId})"), "text/html; charset=utf-8");
}
if (!string.IsNullOrWhiteSpace(stream) || !string.IsNullOrWhiteSpace(play) || !string.IsNullOrWhiteSpace(site))
{
var currentSite = !string.IsNullOrWhiteSpace(site) ? site : "video";
var videoId = id?.Trim() ?? (!string.IsNullOrWhiteSpace(target) && !target.StartsWith("http") ? target : "video");
var orig = (target != null && target.StartsWith("http", StringComparison.OrdinalIgnoreCase)) ? target : "";
return Results.Content(HtmlRenderer.RenderVideoPlayer(currentSite, videoId, play, stream, orig, title ?? $"{currentSite} 動画プレイヤー"), "text/html; charset=utf-8");
}
if (target != null && target.StartsWith("http", StringComparison.OrdinalIgnoreCase))
{
return Results.Content(HtmlRenderer.RenderVideoPlayer("video", "video", play, stream, target, title ?? "動画プレイヤー"), "text/html; charset=utf-8");
}
return Results.Content(
HtmlRenderer.RenderErrorPage($"指定された動画URLまたはID({target})を認識できませんでした。", 400),
"text/html; charset=utf-8",
statusCode: 400);
});
// 123av プレイヤー画面
app.MapGet("/123av/{id}", (string id, string? play, string? url) =>
{
var videoId = Extract123AvId(id) ?? id.Trim();
var origUrl = !string.IsNullOrEmpty(url) ? url : $"https://123av.com/ja/video/{videoId}";
return Results.Content(HtmlRenderer.RenderVideoPlayer("123av", videoId, play, null, origUrl, $"123av 動画 ({videoId})"), "text/html; charset=utf-8");
});
// missav プレイヤー画面
app.MapGet("/missav/{id}", (string id, string? stream, string? play, string? url) =>
{
var videoId = ExtractMissAvId(id) ?? id.Trim();
var origUrl = !string.IsNullOrEmpty(url) ? url : $"https://missav.ai/ja/{videoId}";
return Results.Content(HtmlRenderer.RenderVideoPlayer("missav", videoId, play, stream, origUrl, $"missav 動画 ({videoId})"), "text/html; charset=utf-8");
});
// SpankBang プレイヤー画面
app.MapGet("/spankbang/{id}", (string id) =>
{
var videoId = ExtractSpankBangId(id) ?? id.Trim();
return Results.Content(HtmlRenderer.RenderVideoPlayer(videoId, $"https://jp.spankbang.com/{videoId}/video/"), "text/html; charset=utf-8");
});
// 統一ビューアー画面(3階層)
app.MapGet("/{site}/{category}/{id}", async (string site, string category, string id, GalleryService galleryService, CancellationToken ct) =>
{
if (string.Equals(site, "123av", StringComparison.OrdinalIgnoreCase))
{
return Results.Content(HtmlRenderer.RenderVideoPlayer("123av", id, null, null, $"https://123av.com/ja/video/{id}", $"123av 動画 ({id})"), "text/html; charset=utf-8");
}
if (string.Equals(site, "missav", StringComparison.OrdinalIgnoreCase))
{
return Results.Content(HtmlRenderer.RenderVideoPlayer("missav", id, null, null, $"https://missav.ai/ja/{id}", $"missav 動画 ({id})"), "text/html; charset=utf-8");
}
return await RenderGalleryResponseAsync(site, id, category, galleryService, ct);
});
// 統一ビューアー画面(2階層)
app.MapGet("/{site}/{id}", async (string site, string id, GalleryService galleryService, CancellationToken ct) =>
{
if (string.Equals(site, "123av", StringComparison.OrdinalIgnoreCase))
{
return Results.Content(HtmlRenderer.RenderVideoPlayer("123av", id, null, null, $"https://123av.com/ja/video/{id}", $"123av 動画 ({id})"), "text/html; charset=utf-8");
}
if (string.Equals(site, "missav", StringComparison.OrdinalIgnoreCase))
{
return Results.Content(HtmlRenderer.RenderVideoPlayer("missav", id, null, null, $"https://missav.ai/ja/{id}", $"missav 動画 ({id})"), "text/html; charset=utf-8");
}
if (string.Equals(site, "spankbang", StringComparison.OrdinalIgnoreCase))
{
return Results.Redirect($"/spankbang/{id}");
}
return await RenderGalleryResponseAsync(site, id, null, galleryService, ct);
});
// 旧JSON API群
app.MapGet("/api/sites", (GalleryService galleryService) =>
{
var sites = galleryService.GetAvailableSites().Select(s => new
{
key = s.Key,
name = s.Name,
aliases = s.Aliases,
exampleUrl = $"/{s.Key}/<ID>"
});
return Results.Ok(sites);
});
app.MapGet("/api/{site}/{category}/{id}", async (string site, string category, string id, GalleryService galleryService, CancellationToken ct) =>
{
return await RenderJsonResponseAsync(site, id, category, galleryService, ct);
});
app.MapGet("/api/{site}/{id}", async (string site, string id, GalleryService galleryService, CancellationToken ct) =>
{
return await RenderJsonResponseAsync(site, id, null, galleryService, ct);
});
app.MapGet("/api/scrape", async (string? url, string? site, 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。" });
}
return await RenderJsonResponseAsync(site, target, category, galleryService, ct);
});
return app;
}
private static async Task<IResult> RenderGalleryResponseAsync(
string? site,
string idOrUrl,
string? category,
GalleryService galleryService,
CancellationToken ct)
{
var gallery = !string.IsNullOrWhiteSpace(site)
? await galleryService.GetGalleryBySiteAsync(site, idOrUrl, category, false, ct)
: await galleryService.GetGalleryAsync(idOrUrl, category, false, ct);
if (gallery == null || gallery.Images.Count == 0)
{
var targetInfo = !string.IsNullOrWhiteSpace(site) ? $"{site}/{idOrUrl}" : idOrUrl;
return Results.Content(
HtmlRenderer.RenderErrorPage($"指定された作品({targetInfo})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");
}
private static async Task<IResult> RenderJsonResponseAsync(
string? site,
string idOrUrl,
string? category,
GalleryService galleryService,
CancellationToken ct)
{
var gallery = !string.IsNullOrWhiteSpace(site)
? await galleryService.GetGalleryBySiteAsync(site, idOrUrl, category, false, ct)
: await galleryService.GetGalleryAsync(idOrUrl, category, false, ct);
if (gallery == null)
{
return Results.NotFound(new { error = "Gallery not found", site, id = idOrUrl, category });
}
return Results.Ok(gallery);
}
private static string? ExtractSpankBangId(string input)
{
if (string.IsNullOrWhiteSpace(input)) return null;
input = input.Trim();
var match = System.Text.RegularExpressions.Regex.Match(
input,
@"spankbang\.(?:com|party)/(?<id>[a-z0-9]+)(?:/(?:video|play|embed)|/|$)",
System.Text.RegularExpressions.RegexOptions.IgnoreCase);
if (match.Success) return match.Groups["id"].Value;
var matchSlash = System.Text.RegularExpressions.Regex.Match(
input,
@"^(?:spankbang/)?(?<id>[a-z0-9]{3,12})$",
System.Text.RegularExpressions.RegexOptions.IgnoreCase);
if (matchSlash.Success) return matchSlash.Groups["id"].Value;
return null;
}
private static string? Extract123AvId(string input)
{
if (string.IsNullOrWhiteSpace(input)) return null;
input = input.Trim();
var match = System.Text.RegularExpressions.Regex.Match(
input,
@"(?:123av\.com/[a-z]{2}/(?:video/)?|^123av/)(?<id>[^/?#]+)",
System.Text.RegularExpressions.RegexOptions.IgnoreCase);
if (match.Success) return match.Groups["id"].Value;
if (input.Contains('/') || input.Contains('\\'))
{
var seg = input.TrimEnd('/', '\\').Split(new[] { '/', '\\' }).Last();
if (!string.IsNullOrWhiteSpace(seg)) return seg;
}
return input;
}
private static string? ExtractMissAvId(string input)
{
if (string.IsNullOrWhiteSpace(input)) return null;
input = input.Trim();
var match = System.Text.RegularExpressions.Regex.Match(
input,
@"(?:missav\.[a-z]+/[a-z]{2}/|^missav/)(?<id>[^/?#]+)",
System.Text.RegularExpressions.RegexOptions.IgnoreCase);
if (match.Success) return match.Groups["id"].Value;
if (input.Contains('/') || input.Contains('\\'))
{
var seg = input.TrimEnd('/', '\\').Split(new[] { '/', '\\' }).Last();
if (!string.IsNullOrWhiteSpace(seg)) return seg;
}
return input;
}
private static bool IsGalleryUrlOrSite(string? site, string? urlOrId)
{
if (string.IsNullOrWhiteSpace(urlOrId)) return false;
var lower = urlOrId.ToLowerInvariant();
if (string.Equals(site, "ehentai", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "hitomi", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "aurahentai", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "momonga", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "mangalear", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "hentaipaw", StringComparison.OrdinalIgnoreCase))
{
return true;
}
return lower.Contains("e-hentai.org") ||
lower.Contains("exhentai.org") ||
lower.Contains("hitomi.la") ||
lower.Contains("aurahentai.com") ||
lower.Contains("momon-ga.com") ||
lower.Contains("mangalear.com") ||
lower.Contains("hentaipaw.com");
}
private static bool IsVideoUrlOrSite(string? site, string? urlOrId)
{
if (string.IsNullOrWhiteSpace(urlOrId)) return false;
var lower = urlOrId.ToLowerInvariant();
if (string.Equals(site, "spankbang", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "123av", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "missav", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "doga", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "eroterest_doga", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "vjav", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "laxd", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "fc2", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "inporn", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "bdsmx", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "senzuri", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "txxx", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "hclips", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "hdzog", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "upornia", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "youjizz", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "xvideos", StringComparison.OrdinalIgnoreCase))
{
return true;
}
return lower.Contains("spankbang") ||
lower.Contains("123av") ||
lower.Contains("missav") ||
lower.Contains("do-ga.eroterest.net") ||
lower.Contains("movie.eroterest.net") ||
lower.Contains("vjav.com") ||
lower.Contains("laxd.com") ||
lower.Contains("fc2.com") ||
lower.Contains("inporn.com") ||
lower.Contains("bdsmx.tube") ||
lower.Contains("senzuri.tube") ||
lower.Contains("txxx.com") ||
lower.Contains("hclips.com") ||
lower.Contains("hdzog.com") ||
lower.Contains("upornia.com") ||
lower.Contains("youjizz.com") ||
lower.Contains("xvideos.com") ||
lower.Contains("blogterest.net") ||
lower.Contains("blog.2nt.com");
}
}
@@ -1,4 +1,4 @@
namespace WebImageViewer.Class.Models;
namespace WebImageViewer.Class.Legacy.Models;
/// <summary>
/// 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
@@ -65,3 +65,4 @@ public class GalleryItem
/// </summary>
public DateTime FetchedAt { get; set; } = DateTime.UtcNow;
}
@@ -1,4 +1,4 @@
namespace WebImageViewer.Class.Models;
namespace WebImageViewer.Class.Legacy.Models;
/// <summary>
/// ギャラリー内の各画像情報を保持するモデル
@@ -35,3 +35,4 @@ public class ImageInfo
/// </summary>
public int? Height { get; set; }
}
@@ -1,8 +1,8 @@
using System.Text.Encodings.Web;
using System.Text.Json;
using WebImageViewer.Class.Models;
using WebImageViewer.Class.Legacy.Models;
namespace WebImageViewer.Class.Renderers;
namespace WebImageViewer.Class.Legacy.Renderers;
/// <summary>
/// WebImageViewerの洗練されたモダンUI HTMLを生成するレンダークラス
@@ -2688,3 +2688,4 @@ public static class HtmlRenderer
""";
}
}
@@ -1,10 +1,10 @@
using System.Text.RegularExpressions;
using HtmlAgilityPack;
using Microsoft.Extensions.Logging;
using WebImageViewer.Class.Common;
using WebImageViewer.Class.Models;
using WebImageViewer.Class.Legacy.Common;
using WebImageViewer.Class.Legacy.Models;
namespace WebImageViewer.Class.Scrapers;
namespace WebImageViewer.Class.Legacy.Scrapers;
/// <summary>
/// aurahentai.com 固有のスクレイパークラス
@@ -300,3 +300,4 @@ public partial class AuraHentaiScraper : BaseScraper
item.Images.AddRange(collectedImages);
}
}
@@ -5,10 +5,10 @@ using System.Text.RegularExpressions;
using HtmlAgilityPack;
using Microsoft.Extensions.Caching.Memory;
using Microsoft.Extensions.Logging;
using WebImageViewer.Class.Common;
using WebImageViewer.Class.Models;
using WebImageViewer.Class.Legacy.Common;
using WebImageViewer.Class.Legacy.Models;
namespace WebImageViewer.Class.Scrapers;
namespace WebImageViewer.Class.Legacy.Scrapers;
/// <summary>
/// E-Hentai (e-hentai.org) 固有のスクレイパークラス
@@ -459,3 +459,4 @@ public class EHentaiScraper : BaseScraper
private record EHGDataResult(string Title, string TitleJpn, string Category, string Thumb, int FileCount, List<string> Tags);
private record EHPageEntry(int Page, string ImgKey, string Url, string? ThumbUrl);
}
@@ -1,10 +1,10 @@
using System.Text.RegularExpressions;
using HtmlAgilityPack;
using Microsoft.Extensions.Logging;
using WebImageViewer.Class.Common;
using WebImageViewer.Class.Models;
using WebImageViewer.Class.Legacy.Common;
using WebImageViewer.Class.Legacy.Models;
namespace WebImageViewer.Class.Scrapers;
namespace WebImageViewer.Class.Legacy.Scrapers;
/// <summary>
/// ja.hentaipaw.com(エロモフ)固有のスクレイパークラス
@@ -333,3 +333,4 @@ public partial class HentaiPawScraper : BaseScraper
item.Images = collectedImages;
}
}
@@ -4,10 +4,10 @@ using System.Text.Json;
using System.Text.RegularExpressions;
using Microsoft.Extensions.Caching.Memory;
using Microsoft.Extensions.Logging;
using WebImageViewer.Class.Common;
using WebImageViewer.Class.Models;
using WebImageViewer.Class.Legacy.Common;
using WebImageViewer.Class.Legacy.Models;
namespace WebImageViewer.Class.Scrapers;
namespace WebImageViewer.Class.Legacy.Scrapers;
/// <summary>
/// Hitomi.la 固有のスクレイパークラス
@@ -353,3 +353,4 @@ public class HitomiScraper : BaseScraper
private record GgData(string B, HashSet<int> Cases);
}
@@ -1,10 +1,10 @@
using System.Text.RegularExpressions;
using HtmlAgilityPack;
using Microsoft.Extensions.Logging;
using WebImageViewer.Class.Common;
using WebImageViewer.Class.Models;
using WebImageViewer.Class.Legacy.Common;
using WebImageViewer.Class.Legacy.Models;
namespace WebImageViewer.Class.Scrapers;
namespace WebImageViewer.Class.Legacy.Scrapers;
/// <summary>
/// mangalear.blog(同人まんがりあ)固有のスクレイパークラス
@@ -358,3 +358,4 @@ public partial class MangalearScraper : BaseScraper
return url;
}
}
@@ -1,10 +1,10 @@
using System.Text.RegularExpressions;
using HtmlAgilityPack;
using Microsoft.Extensions.Logging;
using WebImageViewer.Class.Common;
using WebImageViewer.Class.Models;
using WebImageViewer.Class.Legacy.Common;
using WebImageViewer.Class.Legacy.Models;
namespace WebImageViewer.Class.Scrapers;
namespace WebImageViewer.Class.Legacy.Scrapers;
/// <summary>
/// momon-ga.com 固有のスクレイパークラス
@@ -243,3 +243,4 @@ public partial class MomongaScraper : BaseScraper
}
}
}
@@ -1,9 +1,9 @@
using Microsoft.Extensions.Caching.Memory;
using Microsoft.Extensions.Logging;
using WebImageViewer.Class.Common;
using WebImageViewer.Class.Models;
using WebImageViewer.Class.Legacy.Common;
using WebImageViewer.Class.Legacy.Models;
namespace WebImageViewer.Class.Services;
namespace WebImageViewer.Class.Legacy.Services;
/// <summary>
/// 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
@@ -141,3 +141,4 @@ public class GalleryService
}
}
@@ -1,9 +1,9 @@
using System.Text.RegularExpressions;
using HtmlAgilityPack;
using Microsoft.Extensions.Logging;
using WebImageViewer.Class.Common;
using WebImageViewer.Class.Legacy.Common;
namespace WebImageViewer.Class.Services;
namespace WebImageViewer.Class.Legacy.Services;
/// <summary>
/// 解決された動画情報モデル
@@ -514,3 +514,4 @@ public class VideoUrlResolver
};
}
}
@@ -0,0 +1,58 @@
using HtmlAgilityPack;
using Microsoft.Extensions.Logging;
using WebImageViewer.Class.Unified.Models;
namespace WebImageViewer.Class.Unified.Common;
/// <summary>
/// 統一画像スクレイパーの基底クラス
/// </summary>
public abstract class BaseUnifiedScraper : IUnifiedScraper
{
protected readonly UnifiedHttpHelper HttpHelper;
protected readonly ILogger Logger;
public abstract string SiteName { get; }
public abstract string SiteKey { get; }
public abstract IReadOnlyList<string> SupportedDomains { get; }
protected BaseUnifiedScraper(UnifiedHttpHelper httpHelper, ILogger logger)
{
HttpHelper = httpHelper;
Logger = logger;
}
public virtual bool CanHandle(string urlOrPath)
{
if (string.IsNullOrWhiteSpace(urlOrPath)) return false;
var lower = urlOrPath.ToLowerInvariant();
return SupportedDomains.Any(domain => lower.Contains(domain));
}
public abstract Task<UnifiedGalleryItem?> ScrapeAsync(string urlOrPath, CancellationToken ct = default);
protected async Task<HtmlDocument?> LoadHtmlDocumentAsync(string url, bool useFlareSolverr = false, string? referer = null, CancellationToken ct = default)
{
try
{
var html = await HttpHelper.GetHtmlAsync(url, useFlareSolverr, referer, ct);
if (string.IsNullOrWhiteSpace(html)) return null;
var doc = new HtmlDocument();
doc.LoadHtml(html);
return doc;
}
catch (Exception ex)
{
Logger.LogWarning(ex, "[{SiteName}] HTML取得に失敗しました: {Url}", SiteName, url);
return null;
}
}
protected static string CleanText(string? text)
{
if (string.IsNullOrWhiteSpace(text)) return string.Empty;
var decoded = System.Net.WebUtility.HtmlDecode(text);
return decoded.Trim();
}
}
@@ -0,0 +1,23 @@
using WebImageViewer.Class.Unified.Models;
namespace WebImageViewer.Class.Unified.Common;
/// <summary>
/// 統一画像スクレイパーの共通インターフェース
/// </summary>
public interface IUnifiedScraper
{
string SiteName { get; }
string SiteKey { get; }
IReadOnlyList<string> SupportedDomains { get; }
/// <summary>
/// 指定されたURLまたは識別子をこのスクレイパーが処理可能かどうかを判定します。
/// </summary>
bool CanHandle(string urlOrPath);
/// <summary>
/// ギャラリー情報を取得・解析します。
/// </summary>
Task<UnifiedGalleryItem?> ScrapeAsync(string urlOrPath, CancellationToken ct = default);
}
@@ -0,0 +1,112 @@
using System.Net;
using System.Text.Json;
using Microsoft.Extensions.Logging;
namespace WebImageViewer.Class.Unified.Common;
/// <summary>
/// 統一HTTP通信ヘルパークラス
/// 通常のHttpClientおよびCloudflare保護回避用FlareSolverrとの通信を抽象化します。
/// </summary>
public class UnifiedHttpHelper
{
private readonly HttpClient _httpClient;
private readonly ILogger<UnifiedHttpHelper> _logger;
private const string FlareSolverrUrl = "http://localhost:8191/v1";
public UnifiedHttpHelper(HttpClient httpClient, ILogger<UnifiedHttpHelper> logger)
{
_httpClient = httpClient;
_logger = logger;
_httpClient.Timeout = TimeSpan.FromSeconds(25);
_httpClient.DefaultRequestHeaders.Clear();
_httpClient.DefaultRequestHeaders.Add("User-Agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36");
_httpClient.DefaultRequestHeaders.Add("Accept-Language", "ja,en-US;q=0.9,en;q=0.8");
}
/// <summary>
/// 指定URLからHTML文字列を取得します。必要に応じてFlareSolverrを利用します。
/// </summary>
public async Task<string> GetHtmlAsync(string url, bool useFlareSolverr = false, string? referer = null, CancellationToken ct = default)
{
if (useFlareSolverr)
{
try
{
return await GetHtmlViaFlareSolverrAsync(url, ct);
}
catch (Exception ex)
{
_logger.LogWarning(ex, "FlareSolverrでの取得に失敗しました。通常のHttpClientへフォールバックします: {Url}", url);
}
}
try
{
using var req = new HttpRequestMessage(HttpMethod.Get, url);
if (!string.IsNullOrEmpty(referer))
{
req.Headers.Referrer = new Uri(referer);
}
using var resp = await _httpClient.SendAsync(req, ct);
resp.EnsureSuccessStatusCode();
return await resp.Content.ReadAsStringAsync(ct);
}
catch (Exception ex)
{
_logger.LogError(ex, "HTTPリクエストに失敗しました: {Url}", url);
throw;
}
}
/// <summary>
/// FlareSolverr経由でCloudflare保護下のHTMLを取得します。
/// </summary>
private async Task<string> GetHtmlViaFlareSolverrAsync(string url, CancellationToken ct)
{
var payload = new
{
cmd = "request.get",
url = url,
maxTimeout = 30000
};
var content = new StringContent(
JsonSerializer.Serialize(payload),
System.Text.Encoding.UTF8,
"application/json");
using var resp = await _httpClient.PostAsync(FlareSolverrUrl, content, ct);
resp.EnsureSuccessStatusCode();
var json = await resp.Content.ReadAsStringAsync(ct);
using var doc = JsonDocument.Parse(json);
if (doc.RootElement.TryGetProperty("solution", out var sol) &&
sol.TryGetProperty("response", out var respHtml))
{
return respHtml.GetString() ?? string.Empty;
}
throw new InvalidOperationException("FlareSolverrのレスポンスに有効なHTMLが含まれていませんでした。");
}
/// <summary>
/// 画像などのバイナリデータを取得します(プロキシ配信用)。
/// </summary>
public async Task<(byte[] Data, string ContentType)> GetBinaryAsync(string url, string? referer = null, CancellationToken ct = default)
{
using var req = new HttpRequestMessage(HttpMethod.Get, url);
if (!string.IsNullOrEmpty(referer))
{
req.Headers.Referrer = new Uri(referer);
}
using var resp = await _httpClient.SendAsync(req, ct);
resp.EnsureSuccessStatusCode();
var data = await resp.Content.ReadAsByteArrayAsync(ct);
var contentType = resp.Content.Headers.ContentType?.MediaType ?? "image/jpeg";
return (data, contentType);
}
}
@@ -0,0 +1,74 @@
namespace WebImageViewer.Class.Unified.Models;
/// <summary>
/// メディア種別(画像ギャラリー または 動画)
/// </summary>
public enum MediaType
{
Unknown,
Gallery,
Video
}
/// <summary>
/// ギャラリー内の各画像情報
/// </summary>
public class UnifiedImageInfo
{
public int PageNumber { get; set; }
public string ImageUrl { get; set; } = string.Empty;
public string? ThumbnailUrl { get; set; }
public string? AltText { get; set; }
public int? Width { get; set; }
public int? Height { get; set; }
}
/// <summary>
/// 統一画像ギャラリー情報モデル
/// </summary>
public class UnifiedGalleryItem
{
public string Id { get; set; } = string.Empty;
public string Title { get; set; } = string.Empty;
public string? JapaneseTitle { get; set; }
public string Category { get; set; } = "general";
public string SourceSite { get; set; } = string.Empty;
public string SourceUrl { get; set; } = string.Empty;
public string? ThumbnailUrl { get; set; }
public string? Author { get; set; }
public string? Circle { get; set; }
public List<string> Tags { get; set; } = new();
public List<UnifiedImageInfo> Images { get; set; } = new();
public int TotalPages => Images.Count;
public DateTime FetchedAt { get; set; } = DateTime.UtcNow;
}
/// <summary>
/// 統一動画情報モデル
/// </summary>
public class UnifiedVideoItem
{
public string Site { get; set; } = "video";
public string VideoId { get; set; } = "video";
public string Title { get; set; } = "動画";
public string OriginalUrl { get; set; } = string.Empty;
public string? EmbedUrl { get; set; } // iframe埋め込みプレイヤーURL
public string? StreamUrl { get; set; } // 直接ストリームURL (HLS m3u8 または MP4)
public string? PosterUrl { get; set; } // サムネイル・ポスター画像URL
public string? EmbedHtml { get; set; } // 生のiframeタグやHTML埋め込みコード
public bool HasPlayableContent => !string.IsNullOrEmpty(EmbedUrl) || !string.IsNullOrEmpty(StreamUrl) || !string.IsNullOrEmpty(EmbedHtml);
}
/// <summary>
/// 統一ビューアー解決結果モデル
/// </summary>
public class UnifiedViewerResult
{
public MediaType Type { get; set; } = MediaType.Unknown;
public string OriginalUrl { get; set; } = string.Empty;
public UnifiedGalleryItem? Gallery { get; set; }
public UnifiedVideoItem? Video { get; set; }
public bool IsSuccess { get; set; }
public string? ErrorMessage { get; set; }
public int StatusCode { get; set; } = 200;
}
File diff suppressed because it is too large. Load diff
@@ -0,0 +1,332 @@
using System.Collections.Concurrent;
using System.Text.Json;
using System.Text.RegularExpressions;
using HtmlAgilityPack;
using Microsoft.Extensions.Logging;
using WebImageViewer.Class.Unified.Common;
using WebImageViewer.Class.Unified.Models;
namespace WebImageViewer.Class.Unified.Scrapers;
/// <summary>
/// E-Hentai (e-hentai.org) 固有の統一画像スクレイパー
/// 公式JSON API (gdata) とギャラリーHTML解析、showpage API を組み合わせた画像取得を実装
/// </summary>
public class UnifiedEHentaiScraper : BaseUnifiedScraper
{
private const string BaseDomain = "e-hentai.org";
private const string BaseUrl = "https://e-hentai.org";
private const string ApiEndpoint = "https://api.e-hentai.org/api.php";
private static readonly HttpClient ApiClient = new() { Timeout = TimeSpan.FromSeconds(20) };
public override string SiteName => "E-Hentai";
public override string SiteKey => "ehentai";
public override IReadOnlyList<string> SupportedDomains => new[] { "e-hentai.org", "exhentai.org", "ehentai" };
public UnifiedEHentaiScraper(UnifiedHttpHelper httpHelper, ILogger<UnifiedEHentaiScraper> logger)
: base(httpHelper, logger)
{
}
public override async Task<UnifiedGalleryItem?> ScrapeAsync(string urlOrPath, CancellationToken ct = default)
{
var (gid, token) = await ResolveGidAndTokenAsync(urlOrPath, ct);
if (gid <= 0 || string.IsNullOrWhiteSpace(token))
{
Logger.LogWarning("[{SiteName}] GIDとTokenを抽出できませんでした: {Input}", SiteName, urlOrPath);
return null;
}
var galleryUrl = $"{BaseUrl}/g/{gid}/{token}/";
Logger.LogInformation("[{SiteName}] スクレイピング開始 - GID: {Gid}, Token: {Token}", SiteName, gid, token);
// 1. 公式API (gdata) を呼び出してメタデータを取得
UnifiedGalleryItem? item = null;
int fileCount = 0;
try
{
var meta = await FetchMetadataViaApiAsync(gid, token, ct);
if (meta != null)
{
item = meta.Value.Item;
fileCount = meta.Value.FileCount;
}
}
catch (Exception ex)
{
Logger.LogWarning(ex, "[{SiteName}] 公式APIからのメタデータ取得に失敗しました", SiteName);
}
if (item == null)
{
var doc = await LoadHtmlDocumentAsync(galleryUrl, ct: ct);
if (doc == null) return null;
var title = doc.DocumentNode.SelectSingleNode("//h1[@id='gn']")?.InnerText?.Trim()
?? doc.DocumentNode.SelectSingleNode("//h1[@id='gj']")?.InnerText?.Trim()
?? $"E-Hentai ギャラリー #{gid}";
item = new UnifiedGalleryItem
{
Id = $"{gid}/{token}",
Title = CleanText(title),
Category = "doujinshi",
SourceSite = SiteName,
SourceUrl = galleryUrl,
FetchedAt = DateTime.UtcNow
};
}
// 2. ギャラリーページから各ページのリンクを収集
var pageEntries = await CollectPageEntriesAsync(gid, token, fileCount, ct);
if (pageEntries.Count == 0)
{
Logger.LogWarning("[{SiteName}] ギャラリーページからページリンクを取得できませんでした: {Url}", SiteName, galleryUrl);
return item;
}
// 3. 1ページ目から showkey と 1ページ目画像 URL を取得
var firstEntry = pageEntries[0];
var (showkey, firstImgUrl, firstWidth, firstHeight) = await FetchPage1DetailsAsync(firstEntry.Url, ct);
var images = new ConcurrentDictionary<int, UnifiedImageInfo>();
if (!string.IsNullOrWhiteSpace(firstImgUrl))
{
images[1] = new UnifiedImageInfo
{
PageNumber = 1,
ImageUrl = firstImgUrl,
ThumbnailUrl = firstEntry.ThumbUrl ?? item.ThumbnailUrl,
AltText = $"{item.Title} 1ページ",
Width = firstWidth,
Height = firstHeight
};
}
// 4. 2ページ目以降の画像 URL を showpage API で並列取得
var remainingEntries = pageEntries.Skip(1).ToList();
if (remainingEntries.Count > 0 && !string.IsNullOrWhiteSpace(showkey))
{
using var semaphore = new SemaphoreSlim(10);
var tasks = remainingEntries.Select(async entry =>
{
await semaphore.WaitAsync(ct);
try
{
var imgInfo = await FetchImageViaShowpageApiAsync(gid, entry.Page, entry.ImgKey, showkey, entry.ThumbUrl, item.Title, ct);
if (imgInfo != null)
{
images[entry.Page] = imgInfo;
}
}
catch (Exception ex)
{
Logger.LogWarning(ex, "[{SiteName}] ページ {Page} の画像URL取得に失敗しました", SiteName, entry.Page);
}
finally
{
semaphore.Release();
}
});
await Task.WhenAll(tasks);
}
item.Images = images.Values.OrderBy(img => img.PageNumber).ToList();
if (item.Images.Count > 0 && string.IsNullOrEmpty(item.ThumbnailUrl))
{
item.ThumbnailUrl = item.Images[0].ThumbnailUrl;
}
return item.Images.Count > 0 ? item : null;
}
private async Task<(long Gid, string Token)> ResolveGidAndTokenAsync(string input, CancellationToken ct)
{
var trimmed = input.Trim();
var gMatch = Regex.Match(trimmed, @"/g/(\d+)/([a-z0-9]{10})", RegexOptions.IgnoreCase);
if (gMatch.Success) return (long.Parse(gMatch.Groups[1].Value), gMatch.Groups[2].Value.ToLowerInvariant());
var pairMatch = Regex.Match(trimmed, @"^(\d+)[/_ -]([a-z0-9]{10})$", RegexOptions.IgnoreCase);
if (pairMatch.Success) return (long.Parse(pairMatch.Groups[1].Value), pairMatch.Groups[2].Value.ToLowerInvariant());
var sMatch = Regex.Match(trimmed, @"/s/([a-z0-9]+)/(\d+)-(\d+)", RegexOptions.IgnoreCase);
if (sMatch.Success)
{
var pageUrl = trimmed.StartsWith("http") ? trimmed : $"{BaseUrl}/s/{sMatch.Groups[1].Value}/{sMatch.Groups[2].Value}-{sMatch.Groups[3].Value}";
try
{
var doc = await LoadHtmlDocumentAsync(pageUrl, ct: ct);
var href = doc?.DocumentNode.SelectSingleNode("//a[contains(@href, '/g/')]")?.GetAttributeValue("href", "");
if (!string.IsNullOrEmpty(href))
{
var m = Regex.Match(href, @"/g/(\d+)/([a-z0-9]{10})", RegexOptions.IgnoreCase);
if (m.Success) return (long.Parse(m.Groups[1].Value), m.Groups[2].Value.ToLowerInvariant());
}
}
catch { }
}
return (0, string.Empty);
}
private async Task<(UnifiedGalleryItem Item, int FileCount)?> FetchMetadataViaApiAsync(long gid, string token, CancellationToken ct)
{
var payload = new
{
method = "gdata",
gidlist = new object[] { new object[] { gid, token } },
@namespace = 1
};
var content = new StringContent(JsonSerializer.Serialize(payload), System.Text.Encoding.UTF8, "application/json");
using var resp = await ApiClient.PostAsync(ApiEndpoint, content, ct);
resp.EnsureSuccessStatusCode();
var json = await resp.Content.ReadAsStringAsync(ct);
using var doc = JsonDocument.Parse(json);
if (!doc.RootElement.TryGetProperty("gmetadata", out var list) || list.GetArrayLength() == 0) return null;
var g = list[0];
var title = g.TryGetProperty("title", out var t) ? t.GetString() ?? "" : "";
var titleJpn = g.TryGetProperty("title_jpn", out var tj) ? tj.GetString() : null;
var category = g.TryGetProperty("category", out var c) ? c.GetString() ?? "general" : "general";
var thumb = g.TryGetProperty("thumb", out var th) ? th.GetString() : null;
int fileCount = g.TryGetProperty("filecount", out var fc) && int.TryParse(fc.GetString(), out var count) ? count : 0;
var displayTitle = !string.IsNullOrWhiteSpace(titleJpn) ? titleJpn : title;
var item = new UnifiedGalleryItem
{
Id = $"{gid}/{token}",
Title = displayTitle,
JapaneseTitle = titleJpn,
Category = category,
SourceSite = SiteName,
SourceUrl = $"{BaseUrl}/g/{gid}/{token}/",
ThumbnailUrl = thumb,
FetchedAt = DateTime.UtcNow
};
if (g.TryGetProperty("tags", out var tagsProp) && tagsProp.ValueKind == JsonValueKind.Array)
{
foreach (var elem in tagsProp.EnumerateArray())
{
var tagStr = elem.GetString();
if (string.IsNullOrWhiteSpace(tagStr)) continue;
if (tagStr.StartsWith("artist:", StringComparison.OrdinalIgnoreCase)) item.Author = tagStr.Substring("artist:".Length);
else if (tagStr.StartsWith("group:", StringComparison.OrdinalIgnoreCase)) item.Circle = tagStr.Substring("group:".Length);
else item.Tags.Add(tagStr);
}
}
return (item, fileCount);
}
private async Task<List<EHPageEntry>> CollectPageEntriesAsync(long gid, string token, int totalFiles, CancellationToken ct)
{
var entries = new List<EHPageEntry>();
int pageIndex = 0;
int maxPages = totalFiles > 0 ? (int)Math.Ceiling(totalFiles / 20.0) : 5;
while (pageIndex < maxPages && pageIndex < 20)
{
var pageUrl = $"{BaseUrl}/g/{gid}/{token}/?p={pageIndex}";
var doc = await LoadHtmlDocumentAsync(pageUrl, ct: ct);
if (doc == null) break;
var linkNodes = doc.DocumentNode.SelectNodes("//div[@id='gdt']//a[contains(@href, '/s/')]");
if (linkNodes == null || linkNodes.Count == 0) break;
int addedInThisPage = 0;
foreach (var node in linkNodes)
{
var href = node.GetAttributeValue("href", "");
var match = Regex.Match(href, @"/s/([a-z0-9]+)/(\d+)-(\d+)", RegexOptions.IgnoreCase);
if (match.Success)
{
var imgKey = match.Groups[1].Value;
var pNum = int.Parse(match.Groups[3].Value);
string? thumbUrl = node.SelectSingleNode(".//img")?.GetAttributeValue("src", null);
entries.Add(new EHPageEntry(pNum, imgKey, href, thumbUrl));
addedInThisPage++;
}
}
if (addedInThisPage == 0 || (totalFiles > 0 && entries.Count >= totalFiles)) break;
pageIndex++;
}
return entries.OrderBy(e => e.Page).ToList();
}
private async Task<(string? Showkey, string? ImageUrl, int? Width, int? Height)> FetchPage1DetailsAsync(string page1Url, CancellationToken ct)
{
try
{
var doc = await LoadHtmlDocumentAsync(page1Url, ct: ct);
if (doc == null) return (null, null, null, null);
var rawHtml = doc.DocumentNode.OuterHtml;
var showkeyMatch = Regex.Match(rawHtml, @"var showkey\s*=\s*""([^""]+)"";");
var showkey = showkeyMatch.Success ? showkeyMatch.Groups[1].Value : null;
var imgNode = doc.DocumentNode.SelectSingleNode("//img[@id='img']");
if (imgNode != null)
{
var imgUrl = imgNode.GetAttributeValue("src", null);
return (showkey, imgUrl, null, null);
}
return (showkey, null, null, null);
}
catch
{
return (null, null, null, null);
}
}
private async Task<UnifiedImageInfo?> FetchImageViaShowpageApiAsync(long gid, int page, string imgKey, string showkey, string? thumbUrl, string title, CancellationToken ct)
{
var requestObj = new
{
method = "showpage",
gid = gid,
page = page,
imgkey = imgKey,
showkey = showkey
};
var content = new StringContent(JsonSerializer.Serialize(requestObj), System.Text.Encoding.UTF8, "application/json");
using var resp = await ApiClient.PostAsync(ApiEndpoint, content, ct);
resp.EnsureSuccessStatusCode();
var resJson = await resp.Content.ReadAsStringAsync(ct);
using var doc = JsonDocument.Parse(resJson);
var root = doc.RootElement;
if (root.TryGetProperty("i3", out var i3Prop))
{
var i3Html = i3Prop.GetString();
if (!string.IsNullOrWhiteSpace(i3Html))
{
var imgMatch = Regex.Match(i3Html, @"<img\s+id=""img""\s+src=""([^""]+)""", RegexOptions.IgnoreCase);
if (imgMatch.Success)
{
return new UnifiedImageInfo
{
PageNumber = page,
ImageUrl = imgMatch.Groups[1].Value,
ThumbnailUrl = thumbUrl ?? imgMatch.Groups[1].Value,
AltText = $"{title} {page}ページ"
};
}
}
}
return null;
}
private sealed record EHPageEntry(int Page, string ImgKey, string Url, string? ThumbUrl);
}
@@ -0,0 +1,191 @@
using System.Text.RegularExpressions;
using HtmlAgilityPack;
using Microsoft.Extensions.Logging;
using WebImageViewer.Class.Unified.Common;
using WebImageViewer.Class.Unified.Models;
namespace WebImageViewer.Class.Unified.Scrapers;
/// <summary>
/// ja.hentaipaw.com(エロモフ)固有の統一画像スクレイパー
/// </summary>
public class UnifiedHentaiPawScraper : BaseUnifiedScraper
{
private const string BaseDomain = "hentaipaw.com";
private const string BaseUrl = "https://ja.hentaipaw.com";
public override string SiteName => "エロモフ (HentaiPaw)";
public override string SiteKey => "hentaipaw";
public override IReadOnlyList<string> SupportedDomains => new[] { "hentaipaw.com", "ja.hentaipaw.com" };
public UnifiedHentaiPawScraper(UnifiedHttpHelper httpHelper, ILogger<UnifiedHentaiPawScraper> logger)
: base(httpHelper, logger)
{
}
public override async Task<UnifiedGalleryItem?> ScrapeAsync(string urlOrPath, CancellationToken ct = default)
{
var articleId = ResolveArticleId(urlOrPath);
if (string.IsNullOrEmpty(articleId))
{
Logger.LogWarning("[{SiteName}] 有効な記事IDを抽出できませんでした: {Input}", SiteName, urlOrPath);
return null;
}
var articleUrl = $"{BaseUrl}/articles/{articleId}";
var viewerUrl = $"{BaseUrl}/viewer?articleId={articleId}&page=1";
Logger.LogInformation("[{SiteName}] スクレイピング開始 - ID: {Id}", SiteName, articleId);
var viewerDoc = await LoadHtmlDocumentAsync(viewerUrl, useFlareSolverr: true, ct: ct);
var articleDoc = await LoadHtmlDocumentAsync(articleUrl, useFlareSolverr: true, ct: ct);
if (viewerDoc == null && articleDoc == null)
{
Logger.LogWarning("[{SiteName}] ビュワーページおよび記事詳細ページの取得に失敗しました: ID={Id}", SiteName, articleId);
return null;
}
string title = string.Empty;
if (articleDoc?.DocumentNode != null)
{
var h1 = articleDoc.DocumentNode.SelectSingleNode("//h1");
if (h1 != null) title = CleanText(h1.InnerText);
}
if (string.IsNullOrWhiteSpace(title) && viewerDoc?.DocumentNode != null)
{
var titleNode = viewerDoc.DocumentNode.SelectSingleNode("//title");
title = CleanText(titleNode?.InnerText);
title = Regex.Replace(title, @"\s*[-|–]\s*(?:無料のエロ漫画|エロモフ|HentaiPaw).*$", "", RegexOptions.IgnoreCase).Trim();
}
if (string.IsNullOrWhiteSpace(title))
{
title = $"エロモフ作品 #{articleId}";
}
var galleryItem = new UnifiedGalleryItem
{
Id = articleId,
Title = title,
Category = "doujinshi",
SourceSite = SiteName,
SourceUrl = articleUrl,
ThumbnailUrl = $"https://cdn.imagedeliveries.com/{articleId}/thumbnails/cover.webp",
FetchedAt = DateTime.UtcNow
};
if (articleDoc?.DocumentNode != null)
{
ExtractMetadata(articleDoc, galleryItem);
}
ExtractImages(viewerDoc, articleDoc, galleryItem, articleId);
return galleryItem;
}
private static string ResolveArticleId(string idOrUrl)
{
var trimmed = idOrUrl.Trim();
var matchViewer = Regex.Match(trimmed, @"[?&]articleId=(?<id>\d+)", RegexOptions.IgnoreCase);
if (matchViewer.Success) return matchViewer.Groups["id"].Value;
var matchArticles = Regex.Match(trimmed, @"/articles/(?<id>\d+)", RegexOptions.IgnoreCase);
if (matchArticles.Success) return matchArticles.Groups["id"].Value;
var matchNum = Regex.Match(trimmed, @"\d{6,8}");
return matchNum.Success ? matchNum.Value : "";
}
private static void ExtractMetadata(HtmlDocument articleDoc, UnifiedGalleryItem item)
{
var infoRows = articleDoc.DocumentNode.SelectNodes("//div[contains(@class, 'flex') and contains(@class, 'items-center')]");
if (infoRows == null) return;
foreach (var row in infoRows)
{
var h3 = row.SelectSingleNode(".//h3");
var label = CleanText(h3?.InnerText).Replace(":", "").Trim();
var values = row.SelectNodes(".//a//div | .//a | .//p")?
.Select(v => CleanText(v.InnerText))
.Where(v => !string.IsNullOrEmpty(v) && !string.Equals(v, "N/A", StringComparison.OrdinalIgnoreCase))
.Distinct()
.ToList() ?? new List<string>();
if (values.Count == 0) continue;
if (label.Contains("作者") || label.Contains("作家")) item.Author = string.Join(", ", values);
else if (label.Contains("サークル")) item.Circle = string.Join(", ", values);
else if (label.Contains("カテゴリー")) item.Category = values[0];
else if (label.Contains("タグ") || label.Contains("キャラクター")) item.Tags.AddRange(values);
}
item.Tags = item.Tags.Distinct().ToList();
}
private static void ExtractImages(HtmlDocument? viewerDoc, HtmlDocument? articleDoc, UnifiedGalleryItem item, string articleId)
{
var collectedImages = new List<UnifiedImageInfo>();
if (viewerDoc?.DocumentNode != null)
{
var rawHtml = viewerDoc.DocumentNode.OuterHtml;
var pattern = $@"https://cdn\.imagedeliveries\.com/{Regex.Escape(articleId)}/[a-f0-9]{{32,64}}/(?<page>\d+)\.webp";
var matches = Regex.Matches(rawHtml, pattern, RegexOptions.IgnoreCase);
var pageMap = new Dictionary<int, string>();
foreach (Match match in matches)
{
if (int.TryParse(match.Groups["page"].Value, out var pageNum) && !pageMap.ContainsKey(pageNum))
{
pageMap[pageNum] = match.Value;
}
}
if (pageMap.Count > 0)
{
foreach (var kvp in pageMap.OrderBy(k => k.Key))
{
int page = kvp.Key;
string highResUrl = kvp.Value;
string thumbUrl = $"https://cdn.imagedeliveries.com/{articleId}/thumbnails/{page}.webp";
collectedImages.Add(new UnifiedImageInfo
{
PageNumber = page,
ImageUrl = highResUrl,
ThumbnailUrl = thumbUrl,
AltText = $"{item.Title} - {page}ページ"
});
}
}
}
if (collectedImages.Count == 0 && articleDoc?.DocumentNode != null)
{
var rawHtml = articleDoc.DocumentNode.OuterHtml;
var thumbPattern = $@"https://cdn\.imagedeliveries\.com/{Regex.Escape(articleId)}/thumbnails/(?<page>\d+)\.webp";
var matches = Regex.Matches(rawHtml, thumbPattern, RegexOptions.IgnoreCase);
var pages = new SortedSet<int>();
foreach (Match match in matches)
{
if (int.TryParse(match.Groups["page"].Value, out var pageNum)) pages.Add(pageNum);
}
foreach (var page in pages)
{
string thumbUrl = $"https://cdn.imagedeliveries.com/{articleId}/thumbnails/{page}.webp";
collectedImages.Add(new UnifiedImageInfo
{
PageNumber = page,
ImageUrl = thumbUrl,
ThumbnailUrl = thumbUrl,
AltText = $"{item.Title} - {page}ページ"
});
}
}
item.Images = collectedImages;
}
}
@@ -0,0 +1,226 @@
using System.Globalization;
using System.Text.Encodings.Web;
using System.Text.Json;
using System.Text.RegularExpressions;
using Microsoft.Extensions.Caching.Memory;
using Microsoft.Extensions.Logging;
using WebImageViewer.Class.Unified.Common;
using WebImageViewer.Class.Unified.Models;
namespace WebImageViewer.Class.Unified.Scrapers;
/// <summary>
/// Hitomi.la 固有の統一画像スクレイパー
/// gg.jsの動的パースによるサブドメイン・ハッシュ解決と画像プロキシ連携を実装
/// </summary>
public class UnifiedHitomiScraper : BaseUnifiedScraper
{
private const string BaseDomain = "hitomi.la";
private const string BaseUrl = "https://hitomi.la";
private const string LtnDomain = "https://ltn.gold-usergeneratedcontent.net";
private const string ContentDomain = "gold-usergeneratedcontent.net";
private readonly IMemoryCache _cache;
private static readonly TimeSpan GgCacheDuration = TimeSpan.FromMinutes(15);
public override string SiteName => "Hitomi.la";
public override string SiteKey => "hitomi";
public override IReadOnlyList<string> SupportedDomains => new[] { "hitomi.la", "hitomi" };
public UnifiedHitomiScraper(UnifiedHttpHelper httpHelper, IMemoryCache cache, ILogger<UnifiedHitomiScraper> logger)
: base(httpHelper, logger)
{
_cache = cache;
}
public override async Task<UnifiedGalleryItem?> ScrapeAsync(string urlOrPath, CancellationToken ct = default)
{
var galleryId = ExtractGalleryId(urlOrPath);
if (string.IsNullOrWhiteSpace(galleryId))
{
Logger.LogWarning("[{SiteName}] 有効なギャラリーIDを抽出できませんでした: {Input}", SiteName, urlOrPath);
return null;
}
var galleryJsUrl = $"{LtnDomain}/galleries/{galleryId}.js";
Logger.LogInformation("[{SiteName}] ギャラリーメタデータ取得開始 - ID: {Id}", SiteName, galleryId);
string galleryJs;
try
{
galleryJs = await HttpHelper.GetHtmlAsync(galleryJsUrl, ct: ct);
}
catch (Exception ex)
{
Logger.LogWarning(ex, "[{SiteName}] galleries/{Id}.js の取得に失敗しました。hitomi.laからフォールバック試行します", SiteName, galleryId);
try
{
galleryJs = await HttpHelper.GetHtmlAsync($"https://ltn.hitomi.la/galleries/{galleryId}.js", ct: ct);
}
catch (Exception ex2)
{
Logger.LogError(ex2, "[{SiteName}] フォールバック先からの取得にも失敗しました: ID={Id}", SiteName, galleryId);
return null;
}
}
var json = ExtractJsonFromJs(galleryJs);
if (string.IsNullOrWhiteSpace(json)) return null;
using var doc = JsonDocument.Parse(json);
var root = doc.RootElement;
var title = root.TryGetProperty("title", out var titleProp) ? titleProp.GetString() ?? "" : "";
var japaneseTitle = root.TryGetProperty("japanese_title", out var jtProp) ? jtProp.GetString() : null;
var displayTitle = !string.IsNullOrWhiteSpace(japaneseTitle) ? japaneseTitle : title;
var category = root.TryGetProperty("type", out var typeProp) ? typeProp.GetString() ?? "general" : "general";
var galleryItem = new UnifiedGalleryItem
{
Id = galleryId,
Title = displayTitle,
JapaneseTitle = japaneseTitle,
Category = category,
SourceSite = SiteName,
SourceUrl = $"{BaseUrl}/reader/{galleryId}.html",
FetchedAt = DateTime.UtcNow
};
if (root.TryGetProperty("artists", out var artistsProp) && artistsProp.ValueKind == JsonValueKind.Array)
{
var artists = artistsProp.EnumerateArray().Select(a => a.TryGetProperty("artist", out var v) ? v.GetString() : null).Where(v => !string.IsNullOrEmpty(v)).ToList();
if (artists.Count > 0) galleryItem.Author = string.Join(", ", artists);
}
if (root.TryGetProperty("groups", out var groupsProp) && groupsProp.ValueKind == JsonValueKind.Array)
{
var groups = groupsProp.EnumerateArray().Select(g => g.TryGetProperty("group", out var v) ? v.GetString() : null).Where(v => !string.IsNullOrEmpty(v)).ToList();
if (groups.Count > 0) galleryItem.Circle = string.Join(", ", groups);
}
galleryItem.Tags = ExtractTags(root);
var ggData = await GetGgDataAsync(ct);
if (root.TryGetProperty("files", out var filesProp) && filesProp.ValueKind == JsonValueKind.Array)
{
int pageNum = 1;
foreach (var file in filesProp.EnumerateArray())
{
var hash = file.TryGetProperty("hash", out var hashProp) ? hashProp.GetString() ?? "" : "";
var fileName = file.TryGetProperty("name", out var nameProp) ? nameProp.GetString() ?? "" : "";
var width = file.TryGetProperty("width", out var wProp) && wProp.TryGetInt32(out var w) ? w : (int?)null;
var height = file.TryGetProperty("height", out var hProp) && hProp.TryGetInt32(out var h) ? h : (int?)null;
if (string.IsNullOrWhiteSpace(hash)) continue;
var rawImageUrl = BuildWebpImageUrl(hash, ggData);
var rawThumbUrl = BuildThumbnailUrl(hash, ggData);
var referer = $"{BaseUrl}/reader/{galleryId}.html";
var proxyImageUrl = $"/api/proxy-image?url={UrlEncoder.Default.Encode(rawImageUrl)}&referer={UrlEncoder.Default.Encode(referer)}";
var proxyThumbUrl = $"/api/proxy-image?url={UrlEncoder.Default.Encode(rawThumbUrl)}&referer={UrlEncoder.Default.Encode(referer)}";
galleryItem.Images.Add(new UnifiedImageInfo
{
PageNumber = pageNum++,
ImageUrl = proxyImageUrl,
ThumbnailUrl = proxyThumbUrl,
AltText = $"{displayTitle} {pageNum - 1}ページ ({fileName})",
Width = width,
Height = height
});
}
}
if (galleryItem.Images.Count > 0)
{
galleryItem.ThumbnailUrl = galleryItem.Images[0].ThumbnailUrl;
}
return galleryItem;
}
private static string ExtractGalleryId(string input)
{
var trimmed = input.Trim();
if (Regex.IsMatch(trimmed, @"^\d+$")) return trimmed;
var match = Regex.Match(trimmed, @"(?:-|/|^)(\d{5,8})(?:\.html)?(?:/|$)");
if (match.Success) return match.Groups[1].Value;
var fallback = Regex.Match(trimmed, @"\d{5,8}");
return fallback.Success ? fallback.Value : "";
}
private static string ExtractJsonFromJs(string js)
{
var match = Regex.Match(js, @"var\s+galleryinfo\s*=\s*(\{.*?\});?\s*$", RegexOptions.Singleline);
if (match.Success) return match.Groups[1].Value;
var start = js.IndexOf('{');
var end = js.LastIndexOf('}');
return (start >= 0 && end > start) ? js.Substring(start, end - start + 1) : "";
}
private static List<string> ExtractTags(JsonElement root)
{
var list = new List<string>();
if (root.TryGetProperty("tags", out var arrayProp) && arrayProp.ValueKind == JsonValueKind.Array)
{
foreach (var elem in arrayProp.EnumerateArray())
{
if (elem.TryGetProperty("tag", out var v) && !string.IsNullOrWhiteSpace(v.GetString()))
{
list.Add(v.GetString()!.Trim());
}
}
}
return list;
}
private async Task<GgData> GetGgDataAsync(CancellationToken ct)
{
const string cacheKey = "unified_hitomi_gg_data";
if (_cache.TryGetValue(cacheKey, out GgData? cached) && cached != null) return cached;
try
{
var ggJs = await HttpHelper.GetHtmlAsync($"{LtnDomain}/gg.js", ct: ct);
var bMatch = Regex.Match(ggJs, @"b:\s*['""]([^'""]+)['""]");
var b = bMatch.Success ? bMatch.Groups[1].Value : "1788710402/";
var cases = new HashSet<int>();
foreach (Match m in Regex.Matches(ggJs, @"case\s+(\d+):"))
{
if (int.TryParse(m.Groups[1].Value, out var c)) cases.Add(c);
}
var result = new GgData(b, cases);
_cache.Set(cacheKey, result, GgCacheDuration);
return result;
}
catch
{
return new GgData("1788710402/", new HashSet<int>());
}
}
private static string BuildWebpImageUrl(string hash, GgData gg)
{
if (hash.Length < 3) return "";
var m1 = hash.Substring(hash.Length - 3, 2);
var m2 = hash.Substring(hash.Length - 1, 1);
var g = int.Parse(m2 + m1, NumberStyles.HexNumber);
var subNum = 1 + (gg.Cases.Contains(g) ? 0 : 1);
return $"https://w{subNum}.{ContentDomain}/{gg.B}{g}/{hash}.webp";
}
private static string BuildThumbnailUrl(string hash, GgData gg)
{
if (hash.Length < 3) return "";
var m1 = hash.Substring(hash.Length - 3, 2);
var m2 = hash.Substring(hash.Length - 1, 1);
var g = int.Parse(m2 + m1, NumberStyles.HexNumber);
var subLet = (char)('a' + (gg.Cases.Contains(g) ? 0 : 1));
return $"https://{subLet}tn.{ContentDomain}/webpbigtn/{m2}/{m1}/{hash}.webp";
}
private record GgData(string B, HashSet<int> Cases);
}
@@ -0,0 +1,601 @@
using System.Text.RegularExpressions;
using HtmlAgilityPack;
using Microsoft.Extensions.Logging;
using WebImageViewer.Class.Unified.Common;
using WebImageViewer.Class.Unified.Models;
namespace WebImageViewer.Class.Unified.Scrapers;
/// <summary>
/// モモンガ (momon-ga.com) 固有の統一画像スクレイパー
/// </summary>
public class UnifiedMomongaScraper : BaseUnifiedScraper
{
private const string BaseUrl = "https://momon-ga.com";
public override string SiteName => "モモンガ";
public override string SiteKey => "momonga";
public override IReadOnlyList<string> SupportedDomains => new[] { "momon-ga.com", "momonga" };
public UnifiedMomongaScraper(UnifiedHttpHelper httpHelper, ILogger<UnifiedMomongaScraper> logger)
: base(httpHelper, logger)
{
}
public override async Task<UnifiedGalleryItem?> ScrapeAsync(string urlOrPath, CancellationToken ct = default)
{
var (targetUrl, normalizedId, resolvedCategory) = ResolveUrlAndId(urlOrPath);
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, ct: ct);
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(div#post-data h1、h1、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);
if (string.IsNullOrWhiteSpace(title)) title = 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 item = new UnifiedGalleryItem
{
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, item);
// 画像一覧の抽出(#post-hentai img, .entry-content img, article img)
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)
{
int pageNum = 1;
foreach (var img in imgNodes)
{
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 UnifiedImageInfo
{
PageNumber = pageNum++,
ImageUrl = src.Trim(),
ThumbnailUrl = src.Trim(),
AltText = CleanText(alt) ?? $"{item.Title} - {pageNum - 1}ページ",
Width = width,
Height = height
});
}
}
// サムネイルの決定(data-thumb属性、または1枚目の画像)
var historyNode = doc.DocumentNode.SelectSingleNode("//div[contains(@class, 'history')]");
var dataThumb = historyNode?.GetAttributeValue("data-thumb", null);
if (!string.IsNullOrWhiteSpace(dataThumb))
{
item.ThumbnailUrl = dataThumb.Trim();
}
else if (item.Images.Count > 0)
{
item.ThumbnailUrl = item.Images[0].ImageUrl;
}
Logger.LogInformation("[{SiteName}] スクレイピング完了: 『{Title}』, 画像数: {Count}枚",
SiteName, item.Title, item.Images.Count);
return item.Images.Count > 0 ? item : null;
}
private static (string TargetUrl, string NormalizedId, string ResolvedCategory) ResolveUrlAndId(string idOrUrl)
{
var trimmed = idOrUrl.Trim();
string resolvedCategory = "fanzine";
string normalizedId;
if (trimmed.StartsWith("http://", StringComparison.OrdinalIgnoreCase) ||
trimmed.StartsWith("https://", StringComparison.OrdinalIgnoreCase))
{
var uri = new Uri(trimmed);
var segments = uri.AbsolutePath.Split('/', StringSplitOptions.RemoveEmptyEntries);
if (segments.Length >= 2)
{
resolvedCategory = segments[0];
normalizedId = segments[1];
}
else if (segments.Length == 1)
{
normalizedId = segments[0];
}
else
{
normalizedId = trimmed;
}
return ($"{BaseUrl}/{resolvedCategory}/{normalizedId}/", normalizedId, resolvedCategory);
}
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;
}
return ($"{BaseUrl}/{resolvedCategory}/{normalizedId}/", normalizedId, resolvedCategory);
}
private static void ExtractTagsAndMetadata(HtmlDocument doc, UnifiedGalleryItem 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))
{
foreach (var tag in tagValues)
{
if (!item.Tags.Contains(tag)) item.Tags.Add(tag);
}
}
}
}
}
/// <summary>
/// AuraHentai (aurahentai.com) 固有の統一画像スクレイパー
/// </summary>
public class UnifiedAuraHentaiScraper : BaseUnifiedScraper
{
private const string BaseUrl = "https://aurahentai.com";
private const string ImageBaseUrl = "https://img.aurahentai.com";
public override string SiteName => "AuraHentai";
public override string SiteKey => "aurahentai";
public override IReadOnlyList<string> SupportedDomains => new[] { "aurahentai.com", "aurahentai" };
public UnifiedAuraHentaiScraper(UnifiedHttpHelper httpHelper, ILogger<UnifiedAuraHentaiScraper> logger)
: base(httpHelper, logger)
{
}
public override async Task<UnifiedGalleryItem?> ScrapeAsync(string urlOrPath, CancellationToken ct = default)
{
var (targetUrl, normalizedId) = ResolveUrlAndId(urlOrPath);
Logger.LogInformation("[{SiteName}] スクレイピング開始 - ID: {Id}, URL: {Url}", SiteName, normalizedId, targetUrl);
var doc = await LoadHtmlDocumentAsync(targetUrl, useFlareSolverr: true, ct: ct);
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;
}
var titleNode = doc.DocumentNode.SelectSingleNode("//main//h1[not(@id='age-gate-title')]") ??
doc.DocumentNode.SelectSingleNode("//h1[not(@id='age-gate-title')]") ??
doc.DocumentNode.SelectSingleNode("//title");
var title = CleanText(titleNode?.InnerText) ?? normalizedId;
if (title.Contains(" ? "))
{
title = title.Split(" ? ")[0].Trim();
}
else if (title.Contains(" | "))
{
title = title.Split(" | ")[0].Trim();
}
var item = new UnifiedGalleryItem
{
Id = normalizedId,
Title = string.IsNullOrEmpty(title) ? normalizedId : title,
SourceSite = SiteName,
SourceUrl = targetUrl,
FetchedAt = DateTime.UtcNow
};
int pageCount = ExtractMetadata(doc, item);
// 画像一覧の抽出
var imgNodes = doc.DocumentNode.SelectNodes("//div[contains(@class, 'page-grid')]//img") ??
doc.DocumentNode.SelectNodes("//main//img[contains(@src, '/g/')]");
if (imgNodes != null)
{
int pageNum = 1;
foreach (var img in imgNodes)
{
var src = img.GetAttributeValue("src", null) ??
img.GetAttributeValue("data-src", null);
if (string.IsNullOrWhiteSpace(src) || src.Contains("cover.webp") || src.Contains("logo"))
{
continue;
}
var thumbUrl = src.StartsWith("http") ? src : $"{ImageBaseUrl}{src}";
var fullImageUrl = thumbUrl.Replace("/thumb/g/", "/g/");
var alt = img.GetAttributeValue("alt", null);
item.Images.Add(new UnifiedImageInfo
{
PageNumber = pageNum++,
ImageUrl = fullImageUrl,
ThumbnailUrl = thumbUrl,
AltText = CleanText(alt) ?? $"{item.Title} {pageNum - 1}ページ"
});
}
}
// HTMLから取得できなかった場合、ページ数情報があれば連番URLを補完生成
if (item.Images.Count == 0 && pageCount > 0)
{
for (int i = 1; i <= pageCount; i++)
{
var pageStr = i.ToString("D3");
item.Images.Add(new UnifiedImageInfo
{
PageNumber = i,
ImageUrl = $"{ImageBaseUrl}/g/{normalizedId}/{pageStr}.webp",
ThumbnailUrl = $"{ImageBaseUrl}/thumb/g/{normalizedId}/{pageStr}.webp",
AltText = $"{item.Title} {i}ページ"
});
}
}
if (item.Images.Count > 0) item.ThumbnailUrl = item.Images[0].ThumbnailUrl;
return item.Images.Count > 0 ? item : null;
}
private static (string TargetUrl, string NormalizedId) ResolveUrlAndId(string idOrUrl)
{
var trimmed = idOrUrl.Trim();
string normalizedId;
if (trimmed.StartsWith("http://", StringComparison.OrdinalIgnoreCase) ||
trimmed.StartsWith("https://", StringComparison.OrdinalIgnoreCase))
{
var uri = new Uri(trimmed);
var segments = uri.AbsolutePath.Split('/', StringSplitOptions.RemoveEmptyEntries);
normalizedId = segments.Length > 0 ? segments[^1] : trimmed;
}
else if (trimmed.Contains('/'))
{
var parts = trimmed.Split('/', StringSplitOptions.RemoveEmptyEntries);
normalizedId = parts.Length > 0 ? parts[^1] : trimmed;
}
else
{
normalizedId = trimmed;
}
if (int.TryParse(normalizedId, out var num) && normalizedId.Length < 6)
{
normalizedId = num.ToString("D6");
}
var fullUrl = $"{BaseUrl}/gallery/{normalizedId}";
return (fullUrl, normalizedId);
}
private static int ExtractMetadata(HtmlDocument doc, UnifiedGalleryItem item)
{
int detectedPageCount = 0;
var dlNode = doc.DocumentNode.SelectSingleNode("//main//dl");
if (dlNode == null) return detectedPageCount;
var dtNodes = dlNode.SelectNodes(".//dt");
if (dtNodes == null) return detectedPageCount;
foreach (var dt in dtNodes)
{
var label = CleanText(dt.InnerText).ToLowerInvariant();
var dd = dt.ParentNode?.SelectSingleNode(".//dd");
if (dd == null) continue;
var links = dd.SelectNodes(".//a");
var values = links != null
? links.Select(a => CleanText(a.InnerText)).Where(s => !string.IsNullOrEmpty(s)).ToList()
: new List<string> { CleanText(dd.InnerText) };
switch (label)
{
case "artists":
case "artist":
item.Author = string.Join(", ", values);
break;
case "groups":
case "group":
case "circles":
case "circle":
item.Circle = string.Join(", ", values);
break;
case "category":
if (values.Count > 0) item.Category = values[0];
break;
case "tags":
case "characters":
case "character":
case "parodies":
case "parody":
foreach (var val in values)
{
if (!item.Tags.Contains(val)) item.Tags.Add(val);
}
break;
case "pages":
var rawPages = CleanText(dd.InnerText);
var match = Regex.Match(rawPages, @"\d+");
if (match.Success && int.TryParse(match.Value, out var count))
{
detectedPageCount = count;
}
break;
}
}
return detectedPageCount;
}
}
/// <summary>
/// Mangalear (mangalear.com) 固有の統一画像スクレイパー
/// </summary>
public class UnifiedMangalearScraper : BaseUnifiedScraper
{
private const string BaseUrl = "https://mangalear.com";
public override string SiteName => "Mangalear";
public override string SiteKey => "mangalear";
public override IReadOnlyList<string> SupportedDomains => new[] { "mangalear.com", "mangalear" };
public UnifiedMangalearScraper(UnifiedHttpHelper httpHelper, ILogger<UnifiedMangalearScraper> logger)
: base(httpHelper, logger)
{
}
public override async Task<UnifiedGalleryItem?> ScrapeAsync(string urlOrPath, CancellationToken ct = default)
{
var (targetUrl, normalizedId, resolvedCategory) = ResolveUrlAndId(urlOrPath);
Logger.LogInformation("[{SiteName}] スクレイピング開始 - ID: {Id}, URL: {Url}", SiteName, normalizedId, targetUrl);
var doc = await LoadHtmlDocumentAsync(targetUrl, ct: ct);
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;
}
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 = Regex.Replace(title, @"^[▲\s]+", string.Empty);
if (title.Contains(" - "))
{
title = title.Split(" - ")[0].Trim();
}
var item = new UnifiedGalleryItem
{
Id = normalizedId,
Title = string.IsNullOrEmpty(title) ? normalizedId : title,
Category = resolvedCategory,
SourceSite = SiteName,
SourceUrl = targetUrl,
FetchedAt = DateTime.UtcNow
};
ExtractMetadata(doc, item);
// 画像一覧の抽出
var contentNode = doc.DocumentNode.SelectSingleNode("//div[contains(@class, 'entry-content')]") ??
doc.DocumentNode.SelectSingleNode("//article");
if (contentNode != null)
{
var imgNodes = contentNode.SelectNodes(".//img");
if (imgNodes != null)
{
var seenUrls = new HashSet<string>(StringComparer.OrdinalIgnoreCase);
int pageNum = 1;
foreach (var img in imgNodes)
{
var cssClass = img.GetAttributeValue("class", string.Empty);
if (cssClass.Contains("wp-smiley") || cssClass.Contains("avatar")) continue;
string? highResUrl = null;
string? thumbUrl = null;
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;
}
}
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) || !seenUrls.Add(highResUrl)) continue;
var alt = img.GetAttributeValue("alt", null);
item.Images.Add(new UnifiedImageInfo
{
PageNumber = pageNum++,
ImageUrl = highResUrl,
ThumbnailUrl = !string.IsNullOrEmpty(thumbUrl) ? thumbUrl : highResUrl,
AltText = CleanText(alt) ?? $"{item.Title} - {pageNum - 1}ページ"
});
}
}
}
if (item.Images.Count > 0) item.ThumbnailUrl = item.Images[0].ThumbnailUrl;
return item.Images.Count > 0 ? item : null;
}
private static (string TargetUrl, string NormalizedId, string Category) ResolveUrlAndId(string idOrUrl)
{
var trimmed = idOrUrl.Trim();
string normalizedId = string.Empty;
string resolvedCategory = "doujinshi";
if (trimmed.StartsWith("http://", StringComparison.OrdinalIgnoreCase) ||
trimmed.StartsWith("https://", StringComparison.OrdinalIgnoreCase))
{
var uri = new Uri(trimmed);
var query = System.Web.HttpUtility.ParseQueryString(uri.Query);
var pVal = query.Get("p");
if (!string.IsNullOrWhiteSpace(pVal))
{
normalizedId = pVal.Trim();
return ($"{BaseUrl}/?p={normalizedId}", normalizedId, resolvedCategory);
}
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 ($"{BaseUrl}/{resolvedCategory}/{normalizedId}/", normalizedId, resolvedCategory);
}
return ($"{BaseUrl}/{resolvedCategory}/{trimmed}/", trimmed, resolvedCategory);
}
private static void ExtractMetadata(HtmlDocument doc, UnifiedGalleryItem item)
{
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))
{
item.Category = catText;
break;
}
}
}
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);
}
}
}
var authorNode = doc.DocumentNode.SelectSingleNode("//div[contains(@class, 'author-info')]//*[contains(@class, 'author-name')]");
if (authorNode != null)
{
item.Author = CleanText(authorNode.InnerText);
}
}
private static bool IsImageExtension(string url)
{
var ext = Path.GetExtension(url.Split('?')[0]).ToLowerInvariant();
return ext is ".jpg" or ".jpeg" or ".png" or ".webp" or ".gif" or ".bmp";
}
}
@@ -0,0 +1,144 @@
using WebImageViewer.Class.Unified.Models;
namespace WebImageViewer.Class.Unified.Services;
/// <summary>
/// ドメインごとの自動振り分け情報
/// </summary>
public record DomainClassificationResult(
MediaType MediaType,
string SiteKey,
string DisplayName,
string Host
);
/// <summary>
/// URLまたはドメインから動画サイトか画像ギャラリーサイトかを自動判定・振り分けるクラス
/// </summary>
public static class DomainClassifier
{
// 画像ギャラリーサイトのドメイン定義
private static readonly Dictionary<string, (string SiteKey, string DisplayName)> GalleryDomains = new(StringComparer.OrdinalIgnoreCase)
{
{ "hitomi.la", ("hitomi", "Hitomi.la") },
{ "e-hentai.org", ("ehentai", "E-Hentai") },
{ "exhentai.org", ("ehentai", "ExHentai") },
{ "hentaipaw.com", ("hentaipaw", "エロモフ (HentaiPaw)") },
{ "ja.hentaipaw.com", ("hentaipaw", "エロモフ (HentaiPaw)") },
{ "momon-ga.com", ("momonga", "モモンガ") },
{ "aurahentai.com", ("aurahentai", "AuraHentai") },
{ "mangalear.com", ("mangalear", "Mangalear") }
};
// 動画サイトのドメイン定義
private static readonly Dictionary<string, (string SiteKey, string DisplayName)> VideoDomains = new(StringComparer.OrdinalIgnoreCase)
{
{ "missav.ai", ("missav", "MissAV") },
{ "missav.com", ("missav", "MissAV") },
{ "missav.ws", ("missav", "MissAV") },
{ "missav.net", ("missav", "MissAV") },
{ "spankbang.com", ("spankbang", "SpankBang") },
{ "jp.spankbang.com", ("spankbang", "SpankBang") },
{ "spankbang.party", ("spankbang", "SpankBang") },
{ "movie.eroterest.net", ("eroterest", "動画エロタレスト") },
{ "do-ga.eroterest.net", ("doga", "エロタレドーガ") },
{ "123av.com", ("123av", "123av") },
{ "vjav.com", ("vjav", "VJAV") },
{ "video.laxd.com", ("laxd", "LAXD") },
{ "laxd.com", ("laxd", "LAXD") },
{ "contents.fc2.com", ("fc2", "FC2動画") },
{ "video.fc2.com", ("fc2", "FC2動画") },
{ "adult.contents.fc2.com", ("fc2", "FC2動画") },
{ "xvideos.com", ("xvideos", "XVIDEOS") },
{ "www.xvideos.com", ("xvideos", "XVIDEOS") },
{ "inporn.com", ("inporn", "InPorn") },
{ "bdsmx.tube", ("bdsmx", "BDSMx") },
{ "senzuri.tube", ("senzuri", "Senzuri") },
{ "txxx.com", ("txxx", "TXXX") },
{ "hclips.com", ("hclips", "HClips") },
{ "hdzog.com", ("hdzog", "HDZog") },
{ "upornia.com", ("upornia", "Upornia") },
{ "youjizz.com", ("youjizz", "YouJizz") },
// まとめブログ系(内部の実動画へ解決)
{ "galgaldoga.blogterest.net", ("blog", "GalGalドーガ") },
{ "blogterest.net", ("blog", "まとめブログ") },
{ "blog.2nt.com", ("blog", "2NTブログ") }
};
/// <summary>
/// URLまたは文字列からドメインを抽出し、画像または動画の振り分け結果を返します。
/// </summary>
public static DomainClassificationResult Classify(string urlOrString)
{
if (string.IsNullOrWhiteSpace(urlOrString))
{
return new DomainClassificationResult(MediaType.Unknown, "unknown", "不明", "");
}
var trimmed = urlOrString.Trim();
string host = "";
// URL形式であればホスト名を抽出
if (Uri.TryCreate(trimmed, UriKind.Absolute, out var uri))
{
host = uri.Host.ToLowerInvariant();
}
else
{
// ドメイン名直接入力などの救済
var slashIdx = trimmed.IndexOf('/');
host = (slashIdx >= 0 ? trimmed[..slashIdx] : trimmed).ToLowerInvariant();
}
// 1. 完全一致チェック
if (GalleryDomains.TryGetValue(host, out var galleryInfo))
{
return new DomainClassificationResult(MediaType.Gallery, galleryInfo.SiteKey, galleryInfo.DisplayName, host);
}
if (VideoDomains.TryGetValue(host, out var videoInfo))
{
return new DomainClassificationResult(MediaType.Video, videoInfo.SiteKey, videoInfo.DisplayName, host);
}
// 2. 部分一致チェック(サブドメイン対応)
foreach (var (domain, info) in GalleryDomains)
{
if (host.EndsWith(domain, StringComparison.OrdinalIgnoreCase) || host.Contains(domain, StringComparison.OrdinalIgnoreCase))
{
return new DomainClassificationResult(MediaType.Gallery, info.SiteKey, info.DisplayName, host);
}
}
foreach (var (domain, info) in VideoDomains)
{
if (host.EndsWith(domain, StringComparison.OrdinalIgnoreCase) || host.Contains(domain, StringComparison.OrdinalIgnoreCase))
{
return new DomainClassificationResult(MediaType.Video, info.SiteKey, info.DisplayName, host);
}
}
// 3. まとめブログ系のドメインチェック
if (host.Contains("blogterest.net", StringComparison.OrdinalIgnoreCase) ||
host.Contains("blog.2nt.com", StringComparison.OrdinalIgnoreCase) ||
host.Contains("galgal", StringComparison.OrdinalIgnoreCase))
{
return new DomainClassificationResult(MediaType.Video, "blog", "まとめブログ", host);
}
// 4. URLパス・キーワードによるフォールバック推定
var lower = trimmed.ToLowerInvariant();
if (lower.Contains("/video") || lower.Contains("/watch") || lower.Contains("/embed") || lower.Contains("/movie") || lower.Contains("play"))
{
return new DomainClassificationResult(MediaType.Video, "video", "動画サイト", host);
}
if (lower.Contains("/gallery") || lower.Contains("/reader") || lower.Contains("/manga") || lower.Contains("/comic") || lower.Contains("/cg/"))
{
return new DomainClassificationResult(MediaType.Gallery, "gallery", "画像サイト", host);
}
// 判定不能な場合は動画解決(埋め込み・リンク探索)を優先して試す
return new DomainClassificationResult(MediaType.Video, "video", host, host);
}
}
@@ -0,0 +1,149 @@
using Microsoft.Extensions.Logging;
using WebImageViewer.Class.Unified.Common;
using WebImageViewer.Class.Unified.Models;
namespace WebImageViewer.Class.Unified.Services;
/// <summary>
/// 統一ビューアー統括サービス
/// ドメインごとの自動振り分け(画像 vs 動画)、各スクレイパーおよび埋め込み抽出エンジンの連携を行います。
/// </summary>
public class UnifiedViewerService
{
private readonly IEnumerable<IUnifiedScraper> _scrapers;
private readonly VideoEmbedExtractor _videoExtractor;
private readonly ILogger<UnifiedViewerService> _logger;
public UnifiedViewerService(
IEnumerable<IUnifiedScraper> scrapers,
VideoEmbedExtractor videoExtractor,
ILogger<UnifiedViewerService> logger)
{
_scrapers = scrapers;
_videoExtractor = videoExtractor;
_logger = logger;
}
/// <summary>
/// 入力されたURLまたはIDを自動解析し、動画または画像ギャラリーの解決結果を返します。
/// </summary>
public async Task<UnifiedViewerResult> ResolveAsync(string urlOrInput, CancellationToken ct = default)
{
if (string.IsNullOrWhiteSpace(urlOrInput))
{
return new UnifiedViewerResult
{
Type = MediaType.Unknown,
IsSuccess = false,
ErrorMessage = "URLまたはIDが入力されていません。",
StatusCode = 400
};
}
var trimmed = urlOrInput.Trim();
var classification = DomainClassifier.Classify(trimmed);
_logger.LogInformation("URL解析結果: Host={Host}, SiteKey={SiteKey}, Type={MediaType}",
classification.Host, classification.SiteKey, classification.MediaType);
// 1. 動画サイト判定の場合
if (classification.MediaType == MediaType.Video)
{
var video = await _videoExtractor.ResolveAsync(trimmed, ct);
return new UnifiedViewerResult
{
Type = MediaType.Video,
OriginalUrl = trimmed,
Video = video,
IsSuccess = true,
StatusCode = 200
};
}
// 2. 画像ギャラリーサイト判定の場合
if (classification.MediaType == MediaType.Gallery)
{
var scraper = _scrapers.FirstOrDefault(s => s.CanHandle(trimmed));
if (scraper != null)
{
var gallery = await scraper.ScrapeAsync(trimmed, ct);
if (gallery != null && gallery.Images.Count > 0)
{
return new UnifiedViewerResult
{
Type = MediaType.Gallery,
OriginalUrl = trimmed,
Gallery = gallery,
IsSuccess = true,
StatusCode = 200
};
}
}
// 画像サイトとしての取得に失敗した場合、動画の可能性もフォールバック試行
var fallbackVideo = await _videoExtractor.ResolveAsync(trimmed, ct);
if (fallbackVideo.HasPlayableContent)
{
return new UnifiedViewerResult
{
Type = MediaType.Video,
OriginalUrl = trimmed,
Video = fallbackVideo,
IsSuccess = true,
StatusCode = 200
};
}
return new UnifiedViewerResult
{
Type = MediaType.Gallery,
OriginalUrl = trimmed,
IsSuccess = false,
ErrorMessage = $"指定された画像ギャラリー({classification.DisplayName})から画像一覧を取得できませんでした。URLをご確認ください。",
StatusCode = 404
};
}
// 3. 不明・汎用URLの場合: まず動画の埋め込み・ストリーム検出を試行
var unknownVideo = await _videoExtractor.ResolveAsync(trimmed, ct);
if (unknownVideo.HasPlayableContent)
{
return new UnifiedViewerResult
{
Type = MediaType.Video,
OriginalUrl = trimmed,
Video = unknownVideo,
IsSuccess = true,
StatusCode = 200
};
}
// 次に登録されている画像スクレイパーを順次試行
foreach (var s in _scrapers)
{
if (s.CanHandle(trimmed))
{
var g = await s.ScrapeAsync(trimmed, ct);
if (g != null && g.Images.Count > 0)
{
return new UnifiedViewerResult
{
Type = MediaType.Gallery,
OriginalUrl = trimmed,
Gallery = g,
IsSuccess = true,
StatusCode = 200
};
}
}
}
return new UnifiedViewerResult
{
Type = MediaType.Unknown,
OriginalUrl = trimmed,
IsSuccess = false,
ErrorMessage = $"指定されたURL({trimmed})のメディア種別を判別できませんでした。対応サイトのURLをご確認ください。",
StatusCode = 404
};
}
}
@@ -0,0 +1,774 @@
using System.Text.RegularExpressions;
using HtmlAgilityPack;
using Microsoft.Extensions.Logging;
using WebImageViewer.Class.Unified.Common;
using WebImageViewer.Class.Unified.Models;
namespace WebImageViewer.Class.Unified.Services;
/// <summary>
/// 各種動画サイトおよび記事ページから、埋め込みプレイヤー(iframe)やストリームURL(HLS m3u8 / MP4)を自動抽出・解決するクラス
/// </summary>
public class VideoEmbedExtractor
{
private readonly UnifiedHttpHelper _httpHelper;
private readonly ILogger<VideoEmbedExtractor> _logger;
public VideoEmbedExtractor(UnifiedHttpHelper httpHelper, ILogger<VideoEmbedExtractor> logger)
{
_httpHelper = httpHelper;
_logger = logger;
}
/// <summary>
/// URLを解析し、埋め込まれた状態の動画情報を取得・構築します。
/// </summary>
public async Task<UnifiedVideoItem> ResolveAsync(string url, CancellationToken ct = default)
{
if (string.IsNullOrWhiteSpace(url))
{
return new UnifiedVideoItem { Title = "無効なURL", OriginalUrl = url };
}
var trimmedUrl = url.Trim();
var domainInfo = DomainClassifier.Classify(trimmedUrl);
// 1. 各サイト固有の埋め込み解決処理
try
{
switch (domainInfo.SiteKey.ToLowerInvariant())
{
case "missav":
return await ResolveMissAvAsync(trimmedUrl, ct);
case "spankbang":
return ResolveSpankBang(trimmedUrl);
case "123av":
return Resolve123Av(trimmedUrl);
case "fc2":
return ResolveFc2(trimmedUrl);
case "laxd":
return ResolveLaxd(trimmedUrl);
case "vjav":
return ResolveVjav(trimmedUrl);
case "xvideos":
return ResolveXvideos(trimmedUrl);
case "inporn":
return ResolveInporn(trimmedUrl);
case "bdsmx":
return ResolveBdsmx(trimmedUrl);
case "doga":
return await ResolveEroterestDogaAsync(trimmedUrl, ct);
case "eroterest":
case "blog":
// まとめブログやエロタレスト記事から実動画の埋め込みを再帰探索
return await ResolveFromArticlePageAsync(trimmedUrl, null, 1, ct);
case "senzuri":
case "txxx":
case "hclips":
case "hdzog":
case "upornia":
case "youjizz":
return ResolveGenericTube(domainInfo.SiteKey, trimmedUrl);
}
}
catch (Exception ex)
{
_logger.LogWarning(ex, "サイト固有の埋め込み解決に失敗しました。汎用埋め込み抽出を試みます: {Url}", trimmedUrl);
}
// 2. 未知の動画サイトまたは汎用ページからの動的埋め込み抽出
try
{
return await ExtractGenericEmbedFromHtmlAsync(trimmedUrl, ct);
}
catch (Exception ex)
{
_logger.LogWarning(ex, "汎用埋め込み抽出にも失敗しました: {Url}", trimmedUrl);
return new UnifiedVideoItem
{
Site = domainInfo.SiteKey,
VideoId = "video",
Title = domainInfo.DisplayName,
OriginalUrl = trimmedUrl
};
}
}
#region 各サイト別リゾルバー
/// <summary>
/// MissAV の埋め込み・HLSストリームを解決します。
/// </summary>
private async Task<UnifiedVideoItem> ResolveMissAvAsync(string url, CancellationToken ct)
{
var match = Regex.Match(url, @"(?:missav\.[a-z]+/(?:ja/)?|missav/)(?<id>[^/?#]+)", RegexOptions.IgnoreCase);
var id = match.Success ? match.Groups["id"].Value : "video";
var item = new UnifiedVideoItem
{
Site = "missav",
VideoId = id,
Title = $"MissAV ({id})",
OriginalUrl = url
};
// HTMLを取得して Dean Edwards packer スクリプトおよび m3u8 を探索
try
{
var html = await _httpHelper.GetHtmlAsync(url, ct: ct);
if (!string.IsNullOrWhiteSpace(html))
{
// タイトル抽出
var titleMatch = Regex.Match(html, @"<meta property=""og:title"" content=""([^""]+)""");
if (titleMatch.Success) item.Title = CleanText(titleMatch.Groups[1].Value);
// ポスター画像抽出
var posterMatch = Regex.Match(html, @"<meta property=""og:image"" content=""([^""]+)""");
if (posterMatch.Success) item.PosterUrl = posterMatch.Groups[1].Value;
// 1. surrit.com の直接m3u8探索
var directM3u8 = Regex.Match(html, @"https://surrit\.com/[a-f0-9\-]+/(?:playlist|\d+p/video)\.m3u8");
if (directM3u8.Success)
{
item.StreamUrl = directM3u8.Value;
return item;
}
// 2. Dean Edwards Packer のアンパック試行
var packerMatch = Regex.Match(html, @"eval\(function\(p,a,c,k,e,d\)\{.+?\.split\('\|'\),\d+,\{\}\)\)");
if (packerMatch.Success)
{
var unpacked = UnpackDeanEdwards(packerMatch.Value);
var m3u8Match = Regex.Match(unpacked, @"https://surrit\.com/[a-f0-9\-]+/(?:playlist|\d+p/video)\.m3u8");
if (m3u8Match.Success)
{
item.StreamUrl = m3u8Match.Value;
return item;
}
}
// 3. 一般的な UUID パターンから surrit.com m3u8 を推測復元
var uuidMatch = Regex.Match(html, @"[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12}");
if (uuidMatch.Success)
{
item.StreamUrl = $"https://surrit.com/{uuidMatch.Value}/playlist.m3u8";
return item;
}
}
}
catch (Exception ex)
{
_logger.LogWarning(ex, "MissAV の HTML からの m3u8 抽出に失敗しました: {Url}", url);
}
return item;
}
/// <summary>
/// SpankBang の公式埋め込みプレイヤーを解決します。
/// </summary>
private static UnifiedVideoItem ResolveSpankBang(string url)
{
var match = Regex.Match(url, @"spankbang\.(?:com|party)/(?<id>[a-z0-9]+)(?:/(?:video|play|embed)|/|$)", RegexOptions.IgnoreCase);
var id = match.Success ? match.Groups["id"].Value : "video";
return new UnifiedVideoItem
{
Site = "spankbang",
VideoId = id,
Title = $"SpankBang ({id})",
OriginalUrl = url,
EmbedUrl = $"https://spankbang.com/{id}/embed/"
};
}
/// <summary>
/// 123av の公式埋め込みプレイヤーを解決します。
/// </summary>
private static UnifiedVideoItem Resolve123Av(string url)
{
var match = Regex.Match(url, @"video/([a-zA-Z0-9_-]+)", RegexOptions.IgnoreCase);
var id = match.Success ? match.Groups[1].Value : "video";
return new UnifiedVideoItem
{
Site = "123av",
VideoId = id,
Title = $"123av ({id})",
OriginalUrl = url,
EmbedUrl = $"https://javplayer.cc/v/{id}"
};
}
/// <summary>
/// FC2動画の公式埋め込みプレイヤーを解決します。
/// </summary>
private static UnifiedVideoItem ResolveFc2(string url)
{
var match = Regex.Match(url, @"(?:article/|aid=|content/|video/)([0-9a-zA-Z_\-]+)", RegexOptions.IgnoreCase);
var id = match.Success ? match.Groups[1].Value : "video";
return new UnifiedVideoItem
{
Site = "fc2",
VideoId = id,
Title = $"FC2動画 ({id})",
OriginalUrl = url,
EmbedUrl = $"https://video.fc2.com/a/embed/player/{id}/"
};
}
/// <summary>
/// LAXDの公式埋め込みプレイヤーを解決します。
/// </summary>
private static UnifiedVideoItem ResolveLaxd(string url)
{
var match = Regex.Match(url, @"laxd\.com/(?:a/content/|content/|embed/)?([0-9a-zA-Z_\-]+)", RegexOptions.IgnoreCase);
var id = match.Success ? match.Groups[1].Value : "video";
return new UnifiedVideoItem
{
Site = "laxd",
VideoId = id,
Title = $"LAXD ({id})",
OriginalUrl = url,
EmbedUrl = $"https://video.laxd.com/a/embed/player/{id}/"
};
}
/// <summary>
/// VJAVの公式埋め込みプレイヤーを解決します。
/// </summary>
private static UnifiedVideoItem ResolveVjav(string url)
{
var match = Regex.Match(url, @"/videos/([0-9]+)", RegexOptions.IgnoreCase);
var id = match.Success ? match.Groups[1].Value : "video";
return new UnifiedVideoItem
{
Site = "vjav",
VideoId = id,
Title = $"VJAV ({id})",
OriginalUrl = url,
EmbedUrl = $"https://vjav.com/embed/{id}/"
};
}
/// <summary>
/// XVIDEOSの公式埋め込みプレイヤーを解決します。
/// </summary>
private static UnifiedVideoItem ResolveXvideos(string url)
{
var match = Regex.Match(url, @"(?:video\.|video|embedframe/)([0-9]+)", RegexOptions.IgnoreCase);
var id = match.Success ? match.Groups[1].Value : "video";
return new UnifiedVideoItem
{
Site = "xvideos",
VideoId = id,
Title = $"XVIDEOS ({id})",
OriginalUrl = url,
EmbedUrl = $"https://www.xvideos.com/embedframe/{id}"
};
}
/// <summary>
/// InPornの公式埋め込みプレイヤーを解決します。
/// </summary>
private static UnifiedVideoItem ResolveInporn(string url)
{
var match = Regex.Match(url, @"/video/([0-9]+)", RegexOptions.IgnoreCase);
var id = match.Success ? match.Groups[1].Value : "video";
return new UnifiedVideoItem
{
Site = "inporn",
VideoId = id,
Title = $"InPorn ({id})",
OriginalUrl = url,
EmbedUrl = $"https://inporn.com/embed/{id}/"
};
}
/// <summary>
/// BDSMxの公式埋め込みプレイヤーを解決します。
/// </summary>
private static UnifiedVideoItem ResolveBdsmx(string url)
{
var match = Regex.Match(url, @"/video/([0-9]+)", RegexOptions.IgnoreCase);
var id = match.Success ? match.Groups[1].Value : "video";
return new UnifiedVideoItem
{
Site = "bdsmx",
VideoId = id,
Title = $"BDSMx ({id})",
OriginalUrl = url,
EmbedUrl = $"https://bdsmx.tube/embed/{id}/"
};
}
/// <summary>
/// エロタレドーガの直接HLSストリームを解決します。
/// </summary>
private async Task<UnifiedVideoItem> ResolveEroterestDogaAsync(string url, CancellationToken ct)
{
var match = Regex.Match(url, @"detail/([0-9]+)", RegexOptions.IgnoreCase);
var id = match.Success ? match.Groups[1].Value : "doga";
var item = new UnifiedVideoItem
{
Site = "doga",
VideoId = id,
Title = $"エロタレドーガ ({id})",
OriginalUrl = url
};
try
{
var html = await _httpHelper.GetHtmlAsync(url, ct: ct);
if (!string.IsNullOrWhiteSpace(html))
{
// JSON-LD から contentUrl (HLS m3u8) を抽出
var contentUrlMatch = Regex.Match(html, @"""contentUrl""\s*:\s*""(https?:[^""]+\.m3u8[^""]*)""");
if (contentUrlMatch.Success)
{
item.StreamUrl = contentUrlMatch.Groups[1].Value.Replace(@"\/", "/");
}
// ポスター画像
var thumbMatch = Regex.Match(html, @"""thumbnailUrl""\s*:\s*""([^""]+)""");
if (thumbMatch.Success)
{
item.PosterUrl = thumbMatch.Groups[1].Value.Replace(@"\/", "/");
}
// タイトル
var titleMatch = Regex.Match(html, @"<meta property=""og:title"" content=""([^""]+)""");
if (titleMatch.Success) item.Title = CleanText(titleMatch.Groups[1].Value);
}
}
catch (Exception ex)
{
_logger.LogWarning(ex, "エロタレドーガのHLS取得に失敗しました: {Url}", url);
}
return item;
}
/// <summary>
/// 一般的なチューブサイト(Senzuri, TXXX, HClips等)の公式埋め込みプレイヤーを解決します。
/// </summary>
private static UnifiedVideoItem ResolveGenericTube(string site, string url)
{
var match = Regex.Match(url, @"/videos/([0-9]+)", RegexOptions.IgnoreCase);
var id = match.Success ? match.Groups[1].Value : "video";
var host = site.ToLowerInvariant();
string embedBase = host switch
{
"senzuri" => "https://senzuri.tube/embed/",
"txxx" => "https://txxx.com/embed/",
"hclips" => "https://www.hclips.com/embed/",
"hdzog" => "https://www.hdzog.com/embed/",
"upornia" => "https://upornia.com/embed/",
"youjizz" => "https://www.youjizz.com/embed/",
_ => $"https://{host}.com/embed/"
};
return new UnifiedVideoItem
{
Site = site,
VideoId = id,
Title = $"{site} 動画 ({id})",
OriginalUrl = url,
EmbedUrl = $"{embedBase}{id}/"
};
}
#endregion
#region 記事ページ(まとめブログ・エロタレスト等)からの再帰的動画解決
/// <summary>
/// まとめ記事(movie.eroterest.net 等)のHTMLから実動画リンク(動画の再生はこちら等)を探索し、その埋め込みを解決します。
/// </summary>
private async Task<UnifiedVideoItem> ResolveFromArticlePageAsync(
string pageUrl,
string? customTitle,
int currentDepth,
CancellationToken ct)
{
if (currentDepth > 10)
{
return new UnifiedVideoItem { Title = customTitle ?? "動画プレイヤー", OriginalUrl = pageUrl };
}
var html = await _httpHelper.GetHtmlAsync(pageUrl, ct: ct);
if (string.IsNullOrWhiteSpace(html))
{
return new UnifiedVideoItem { Title = customTitle ?? "動画プレイヤー", OriginalUrl = pageUrl };
}
var doc = new HtmlDocument();
doc.LoadHtml(html);
var title = customTitle;
if (string.IsNullOrWhiteSpace(title))
{
var titleNode = doc.DocumentNode.SelectSingleNode("//meta[@property='og:title']/@content")
?? doc.DocumentNode.SelectSingleNode("//title")
?? doc.DocumentNode.SelectSingleNode("//h1");
title = titleNode?.InnerText?.Trim() ?? titleNode?.GetAttributeValue("content", "")?.Trim();
if (!string.IsNullOrWhiteSpace(title))
{
title = Regex.Replace(title, @"\s*[-|–]\s*(?:GalGalドーガ|動画エロタレスト|blogterest).*$", "", RegexOptions.IgnoreCase).Trim();
}
}
// 1. 中間ブログ(.gotoBlog a)の探索
var gotoBlog = doc.DocumentNode.SelectSingleNode("//div[contains(@class, 'gotoBlog')]//a[@href]")
?? doc.DocumentNode.SelectSingleNode("//div[contains(@class, 'pageDetail')]//a[contains(@href, 'blogterest') or contains(@href, 'blog')]");
if (gotoBlog != null)
{
var nextBlogUrl = gotoBlog.GetAttributeValue("href", "")?.Trim();
if (!string.IsNullOrWhiteSpace(nextBlogUrl))
{
return await ResolveFromArticlePageAsync(nextBlogUrl, title, currentDepth + 1, ct);
}
}
// 2. 「動画の再生はこちら」「動画を見る」等のリンク探索
string? candidateUrl = null;
var playTextLinks = doc.DocumentNode.SelectNodes("//a[contains(., '動画の再生') or contains(., '動画再生') or contains(., '再生はこちら') or contains(., '再生は此方') or contains(., '本編') or contains(., '動画を見る') or contains(., '動画を視聴')]");
if (playTextLinks != null && playTextLinks.Count > 0)
{
foreach (var node in playTextLinks)
{
var href = node.GetAttributeValue("href", "")?.Trim();
if (!string.IsNullOrWhiteSpace(href) && !href.StartsWith("#") && !href.StartsWith("javascript:", StringComparison.OrdinalIgnoreCase))
{
candidateUrl = href;
break;
}
}
}
// 3. .movie-frame 配下の a タグ
if (string.IsNullOrWhiteSpace(candidateUrl))
{
var mf = doc.DocumentNode.SelectSingleNode("//div[contains(@class, 'movie-frame')]//a[@href]");
candidateUrl = mf?.GetAttributeValue("href", "")?.Trim();
}
// 4. すべてのリンクから動画ホスト(DomainClassifier判定および主要チューブサイト)を探索
if (string.IsNullOrWhiteSpace(candidateUrl))
{
var allLinks = doc.DocumentNode.SelectNodes("//a[@href]");
if (allLinks != null)
{
// 画像(サムネイル)を含むリンクを最優先にソート(ブログ記事本文のアイキャッチ動画リンクを確実に拾う)
var prioritizedLinks = allLinks.OrderByDescending(a => a.SelectSingleNode(".//img") != null ? 1 : 0);
foreach (var a in prioritizedLinks)
{
var href = a.GetAttributeValue("href", "")?.Trim();
if (string.IsNullOrWhiteSpace(href) || href.StartsWith("#") || href.StartsWith("javascript:", StringComparison.OrdinalIgnoreCase)) continue;
// 相対URLの場合は絶対URLへ補正
if (href.StartsWith("//"))
{
href = "https:" + href;
}
else if (href.StartsWith("/") && Uri.TryCreate(pageUrl, UriKind.Absolute, out var baseUri))
{
href = new Uri(baseUri, href).ToString();
}
// ドメイン分類による判定
var classification = DomainClassifier.Classify(href);
if (classification.MediaType == MediaType.Video)
{
// まとめブログ自身やエロタレストのトップ・記事一覧リンク等は実動画ホストではないためスキップ
if (classification.SiteKey.Equals("blog", StringComparison.OrdinalIgnoreCase) ||
classification.SiteKey.Equals("eroterest", StringComparison.OrdinalIgnoreCase))
{
continue;
}
candidateUrl = href;
break;
}
// 既知の動画ホストパターン(フォールバック)
if (href.Contains("txxx.com/videos/", StringComparison.OrdinalIgnoreCase) ||
href.Contains("senzuri.tube/videos/", StringComparison.OrdinalIgnoreCase) ||
href.Contains("hclips.com/videos/", StringComparison.OrdinalIgnoreCase) ||
href.Contains("hdzog.com/videos/", StringComparison.OrdinalIgnoreCase) ||
href.Contains("upornia.com/videos/", StringComparison.OrdinalIgnoreCase) ||
href.Contains("youjizz.com/videos/", StringComparison.OrdinalIgnoreCase) ||
href.Contains("do-ga.eroterest.net/video/", StringComparison.OrdinalIgnoreCase) ||
href.Contains("spankbang.com/", StringComparison.OrdinalIgnoreCase) ||
href.Contains("missav", StringComparison.OrdinalIgnoreCase) ||
href.Contains("123av.com/", StringComparison.OrdinalIgnoreCase) ||
href.Contains("video.fc2.com", StringComparison.OrdinalIgnoreCase) ||
href.Contains("contents.fc2.com", StringComparison.OrdinalIgnoreCase) ||
href.Contains("vjav.com/", StringComparison.OrdinalIgnoreCase) ||
href.Contains("laxd.com/", StringComparison.OrdinalIgnoreCase) ||
href.Contains("inporn.com/", StringComparison.OrdinalIgnoreCase) ||
href.Contains("bdsmx.tube/", StringComparison.OrdinalIgnoreCase) ||
href.Contains("xvideos.com/", StringComparison.OrdinalIgnoreCase))
{
candidateUrl = href;
break;
}
}
}
}
if (!string.IsNullOrWhiteSpace(candidateUrl))
{
var subResult = await ResolveAsync(candidateUrl, ct);
if (subResult.HasPlayableContent)
{
if (string.IsNullOrWhiteSpace(subResult.Title) || subResult.Title.StartsWith("動画") || subResult.Title.Contains("動画 ("))
{
subResult.Title = title ?? subResult.Title;
}
// ポスター画像が未設定の場合、記事からサムネイル画像を引き継ぐ
if (string.IsNullOrWhiteSpace(subResult.PosterUrl))
{
var posterNode = doc.DocumentNode.SelectSingleNode("//meta[@property='og:image']/@content")
?? doc.DocumentNode.SelectSingleNode("//div[contains(@class, 'pageDetail')]//img[@src]")
?? doc.DocumentNode.SelectSingleNode("//img[contains(@class, 'img-thumbnail') or contains(@class, 'img-fluid')]");
var poster = posterNode?.GetAttributeValue("content", "") ?? posterNode?.GetAttributeValue("src", "");
if (!string.IsNullOrWhiteSpace(poster))
{
if (poster.StartsWith("//")) poster = "https:" + poster;
subResult.PosterUrl = poster;
}
}
return subResult;
}
// まだ別のブログページであれば再帰
return await ResolveFromArticlePageAsync(candidateUrl, title, currentDepth + 1, ct);
}
// 見つからなかった場合は汎用埋め込み抽出を試行
var generic = await ExtractGenericEmbedFromHtmlAsync(pageUrl, ct);
if (!string.IsNullOrWhiteSpace(title)) generic.Title = title;
return generic;
}
#endregion
#region 汎用埋め込み抽出エンジン
/// <summary>
/// HTMLページから &lt;iframe&gt;, &lt;video&gt;, metaタグ(og:video, twitter:player)などの埋め込み記述を動的抽出します。
/// </summary>
private async Task<UnifiedVideoItem> ExtractGenericEmbedFromHtmlAsync(string pageUrl, CancellationToken ct)
{
var html = await _httpHelper.GetHtmlAsync(pageUrl, ct: ct);
var doc = new HtmlDocument();
doc.LoadHtml(html);
var item = new UnifiedVideoItem
{
Site = "web",
VideoId = "web",
Title = "ウェブ動画",
OriginalUrl = pageUrl
};
// タイトル
var titleNode = doc.DocumentNode.SelectSingleNode("//meta[@property='og:title']/@content")
?? doc.DocumentNode.SelectSingleNode("//title");
if (titleNode != null)
{
item.Title = CleanText(titleNode.InnerText ?? titleNode.GetAttributeValue("content", ""));
}
// ポスター画像
var posterNode = doc.DocumentNode.SelectSingleNode("//meta[@property='og:image']/@content");
if (posterNode != null)
{
item.PosterUrl = posterNode.GetAttributeValue("content", "");
}
// 1. &lt;iframe src="..."&gt; の探索(広告用・バナー用iframeなどを徹底除外)
var iframeNodes = doc.DocumentNode.SelectNodes("//iframe[@src]");
if (iframeNodes != null)
{
foreach (var ifr in iframeNodes)
{
var src = ifr.GetAttributeValue("src", "")?.Trim();
if (string.IsNullOrWhiteSpace(src)) continue;
var lowerSrc = src.ToLowerInvariant();
// 広告、バナー、トラッキング用の除外判定
if (lowerSrc.Contains("googletagmanager") || lowerSrc.Contains("doubleclick") ||
lowerSrc.Contains("googleads") || lowerSrc.Contains("okbp.xyz") || lowerSrc.Contains("pic-stash") ||
lowerSrc.Contains("dmm.co.jp") || lowerSrc.Contains("fanza") || lowerSrc.Contains("online-banner") ||
lowerSrc.Contains("banner") || lowerSrc.Contains("yomeno.xyz") || lowerSrc.Contains("vstserv.com") ||
lowerSrc.Contains("gggpppht.com") || lowerSrc.Contains("ad-stir") || lowerSrc.Contains("i-mobile") ||
lowerSrc.Contains("trafficjunky") || lowerSrc.Contains("juicyads") || lowerSrc.Contains("exoclick") ||
lowerSrc.Contains("popcash") || lowerSrc.Contains("syndication") || lowerSrc.Contains("mman.link") ||
lowerSrc.Contains("fam-ad") || lowerSrc.Contains("adarea") || lowerSrc.Contains("kokarea"))
{
continue;
}
// iframe属性(id, class)の広告キーワード判定
var idClass = (ifr.GetAttributeValue("id", "") + " " + ifr.GetAttributeValue("class", "")).ToLowerInvariant();
if (idClass.Contains("banner") || idClass.Contains("advert") || idClass.Contains("kokarea") || idClass.Contains("ad-"))
{
continue;
}
// 相対URLの場合は絶対URLへ変換
if (src.StartsWith("//"))
{
src = "https:" + src;
}
else if (src.StartsWith("/") && Uri.TryCreate(pageUrl, UriKind.Absolute, out var baseUri))
{
src = new Uri(baseUri, src).ToString();
}
item.EmbedUrl = src;
break;
}
}
// 2. meta (og:video, twitter:player) の探索
if (string.IsNullOrWhiteSpace(item.EmbedUrl) && string.IsNullOrWhiteSpace(item.StreamUrl))
{
var metaVideo = doc.DocumentNode.SelectSingleNode("//meta[@property='og:video' or @property='og:video:url' or @name='twitter:player']/@content");
if (metaVideo != null)
{
var content = metaVideo.GetAttributeValue("content", "")?.Trim();
if (!string.IsNullOrWhiteSpace(content))
{
if (content.Contains(".m3u8") || content.Contains(".mp4"))
{
item.StreamUrl = content;
}
else
{
item.EmbedUrl = content;
}
}
}
}
// 3. &lt;video&gt; または &lt;source&gt; の探索
if (string.IsNullOrWhiteSpace(item.EmbedUrl) && string.IsNullOrWhiteSpace(item.StreamUrl))
{
var videoSource = doc.DocumentNode.SelectSingleNode("//video//source[@src]")
?? doc.DocumentNode.SelectSingleNode("//video[@src]");
if (videoSource != null)
{
var src = videoSource.GetAttributeValue("src", "")?.Trim();
if (!string.IsNullOrWhiteSpace(src))
{
item.StreamUrl = src;
}
}
}
return item;
}
#endregion
#region Dean Edwards Packer アンパッカー
/// <summary>
/// Dean Edwards の p,a,c,k,e,d JavaScript をアンパックします。
/// </summary>
private static string UnpackDeanEdwards(string packedJs)
{
try
{
var match = Regex.Match(packedJs, @"}\('(.*)',\s*(\d+),\s*(\d+),\s*'(.*)'\.split\('\|'\)");
if (!match.Success) return packedJs;
var payload = match.Groups[1].Value;
var radix = int.Parse(match.Groups[2].Value);
var count = int.Parse(match.Groups[3].Value);
var symTab = match.Groups[4].Value.Split('|');
return Regex.Replace(payload, @"\b\w+\b", m =>
{
var word = m.Value;
var val = BaseDecode(word, radix);
if (val >= 0 && val < symTab.Length && !string.IsNullOrEmpty(symTab[val]))
{
return symTab[val];
}
return word;
});
}
catch
{
return packedJs;
}
}
private static int BaseDecode(string str, int radix)
{
try
{
int result = 0;
const string chars = "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ";
foreach (var c in str)
{
int val = chars.IndexOf(c);
if (val < 0 || val >= radix) return -1;
result = result * radix + val;
}
return result;
}
catch
{
return -1;
}
}
private static string BaseEncode(int num, int radix)
{
const string chars = "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ";
if (num == 0) return "0";
var res = "";
while (num > 0)
{
res = chars[num % radix] + res;
num /= radix;
}
return res;
}
private static string CleanText(string? text)
{
if (string.IsNullOrWhiteSpace(text)) return string.Empty;
return System.Net.WebUtility.HtmlDecode(text).Trim();
}
#endregion
}
@@ -0,0 +1,34 @@
using Microsoft.Extensions.DependencyInjection;
using WebImageViewer.Class.Unified.Common;
using WebImageViewer.Class.Unified.Scrapers;
using WebImageViewer.Class.Unified.Services;
namespace WebImageViewer.Class.Unified;
public static class UnifiedServiceExtensions
{
/// <summary>
/// 新アーキテクチャ(Unified)のサービス群をDIコンテナに登録します。
/// </summary>
public static IServiceCollection AddUnifiedServices(this IServiceCollection services)
{
// HTTP通信ヘルパー
services.AddHttpClient<UnifiedHttpHelper>();
// 画像スクレイパー群
services.AddScoped<IUnifiedScraper, UnifiedHitomiScraper>();
services.AddScoped<IUnifiedScraper, UnifiedEHentaiScraper>();
services.AddScoped<IUnifiedScraper, UnifiedHentaiPawScraper>();
services.AddScoped<IUnifiedScraper, UnifiedMomongaScraper>();
services.AddScoped<IUnifiedScraper, UnifiedAuraHentaiScraper>();
services.AddScoped<IUnifiedScraper, UnifiedMangalearScraper>();
// 動画埋め込み抽出エンジン
services.AddScoped<VideoEmbedExtractor>();
// 統一ビューアー統括サービス
services.AddScoped<UnifiedViewerService>();
return services;
}
}
+39 -558
View File
@@ -1,60 +1,37 @@
using Microsoft.AspNetCore.HttpOverrides;
using WebImageViewer.Class.Common;
using WebImageViewer.Class.Renderers;
using WebImageViewer.Class.Scrapers;
using WebImageViewer.Class.Services;
using WebImageViewer.Class.Legacy;
using WebImageViewer.Class.Unified;
using WebImageViewer.Class.Unified.Common;
using WebImageViewer.Class.Unified.Models;
using WebImageViewer.Class.Unified.Renderers;
using WebImageViewer.Class.Unified.Services;
var builder = WebApplication.CreateBuilder(args);
// =========================================================================
// 【重要】IIS ホスト時のポート設定
// IIS (AspNetCoreModuleV2) がポートを動的に割り当てて制御するため、
// builder.WebHost.UseUrls(...) は呼び出さず、IIS のバインディング (8080) に委ねます。
// ※ローカルで IIS を介さず exe 単体でデバッグ起動したい場合のみ、環境変数がない時に UseUrls を有効にします。
// =========================================================================
if (!builder.Environment.IsProduction() && string.IsNullOrEmpty(Environment.GetEnvironmentVariable("ASPNETCORE_PORT")))
{
builder.WebHost.UseUrls("http://0.0.0.0:5000");
}
// =========================================================================
// ==========================================
// 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
builder.Services.AddMemoryCache();
// HTTP通信用ヘルパーの登録
builder.Services.AddHttpClient<HttpHelper>();
// 1. 新アーキテクチャ(Unified)のサービス登録
builder.Services.AddUnifiedServices();
// 各種スクレイパークラスの登録
builder.Services.AddScoped<IScraper, MomongaScraper>();
builder.Services.AddScoped<MomongaScraper>();
builder.Services.AddScoped<IScraper, AuraHentaiScraper>();
builder.Services.AddScoped<AuraHentaiScraper>();
builder.Services.AddScoped<IScraper, HitomiScraper>();
builder.Services.AddScoped<HitomiScraper>();
builder.Services.AddScoped<IScraper, EHentaiScraper>();
builder.Services.AddScoped<EHentaiScraper>();
builder.Services.AddScoped<IScraper, MangalearScraper>();
builder.Services.AddScoped<MangalearScraper>();
builder.Services.AddScoped<IScraper, HentaiPawScraper>();
builder.Services.AddScoped<HentaiPawScraper>();
// ギャラリー統括管理サービスの登録
builder.Services.AddScoped<GalleryService>();
// 動画URL・記事解決サービスの登録
builder.Services.AddScoped<VideoUrlResolver>();
// 2. 旧バージョン(Legacy)のサービス登録(今後更新しないものとして隔離)
builder.Services.AddLegacyServices();
// VPS / Caddy リバースプロキシ環境対応のフォワードヘッダー設定
builder.Services.Configure<ForwardedHeadersOptions>(options =>
{
options.ForwardedHeaders = ForwardedHeaders.XForwardedFor | ForwardedHeaders.XForwardedProto | ForwardedHeaders.XForwardedHost;
// 多段プロキシ(Caddy -> IIS -> Kestrel)経由でもヘッダーを最後まで反映させる
options.ForwardLimit = null;
// 非推奨となった KnownNetworks は使わず、KnownIPNetworks をクリア
options.KnownIPNetworks.Clear();
options.KnownProxies.Clear();
});
@@ -64,363 +41,52 @@ var app = builder.Build();
// ==========================================
// ミドルウェアパイプラインの設定
// ==========================================
// プロキシヘッダーの反映(ルーティング等の前で必ず実行)
app.UseForwardedHeaders();
// ==========================================
// ルーティング・エンドポイントの定義 (統一アクセス方式)
// 統一アクセス方式 (/?url=[各ページURL])
// ==========================================
// トップページ
app.MapGet("/", () => Results.Content(HtmlRenderer.RenderHomePage(), "text/html; charset=utf-8"));
// 汎用ビューアー画面
app.MapGet("/view", async (string? url, string? site, string? id, string? category, GalleryService galleryService, CancellationToken ct) =>
app.MapGet("/", async (string? url, UnifiedViewerService viewerService, CancellationToken ct) =>
{
var target = url ?? id;
if (string.IsNullOrWhiteSpace(target))
// URLパラメータが未指定の場合は統一トップページを表示
if (string.IsNullOrWhiteSpace(url))
{
return Results.Redirect("/");
return Results.Content(UnifiedHtmlRenderer.RenderHomePage(), "text/html; charset=utf-8");
}
// 動画サイト・動画URL判定(各種動画サイトまたはまとめブログのURLであれば /video へ自動リダイレクト)
if (IsVideoUrlOrSite(site, target))
// ドメイン自動判定およびメディア(動画 / 画像)解決を実行
var result = await viewerService.ResolveAsync(url, ct);
if (!result.IsSuccess)
{
return Results.Redirect($"/video?url={Uri.EscapeDataString(target)}");
return Results.Content(
UnifiedHtmlRenderer.RenderErrorPage(result.ErrorMessage ?? "指定されたコンテンツを読み込めませんでした。", result.StatusCode),
"text/html; charset=utf-8",
statusCode: result.StatusCode);
}
return await RenderGalleryResponseAsync(site, target, category, galleryService, ct);
});
// 汎用動画プレイヤー画面
app.MapGet("/video", async (
string? url,
string? id,
string? site,
string? play,
string? stream,
string? title,
VideoUrlResolver resolver,
CancellationToken ct) =>
{
var target = url ?? id;
if (string.IsNullOrWhiteSpace(target) && string.IsNullOrWhiteSpace(stream) && string.IsNullOrWhiteSpace(play))
// 動画の場合は埋め込みプレイヤー画面を同一URLのままレンダリング
if (result.Type == MediaType.Video && result.Video != null)
{
return Results.Redirect("/");
return Results.Content(UnifiedHtmlRenderer.RenderVideoViewer(result.Video), "text/html; charset=utf-8");
}
// 画像ギャラリーURL判定(画像サイトのURLであれば /view へ自動リダイレクト)
if (IsGalleryUrlOrSite(site, target))
// 画像の場合はギャラリービューアー画面を同一URLのままレンダリング
if (result.Type == MediaType.Gallery && result.Gallery != null)
{
return Results.Redirect($"/view?url={Uri.EscapeDataString(target!)}");
return Results.Content(UnifiedHtmlRenderer.RenderGalleryViewer(result.Gallery), "text/html; charset=utf-8");
}
// 1. target が URL かつ play/stream が渡されていない場合、記事URL(galgaldoga等)または未解決動画URLを自動探索
if (target != null && target.StartsWith("http", StringComparison.OrdinalIgnoreCase) && string.IsNullOrWhiteSpace(play) && string.IsNullOrWhiteSpace(stream))
{
// 直接の動画ホスト判定または記事ページからの実動画解決
var resolved = await resolver.ResolveAsync(target, title, ct);
if (resolved.IsSuccess)
{
site ??= resolved.Site;
id ??= resolved.VideoId;
play ??= resolved.PlayerUrl;
stream ??= resolved.StreamUrl;
title ??= resolved.Title;
target = resolved.OriginalUrl ?? target;
}
}
// 123av 判定
if (string.Equals(site, "123av", StringComparison.OrdinalIgnoreCase) || (target != null && target.Contains("123av", StringComparison.OrdinalIgnoreCase)))
{
var vId = (target != null ? Extract123AvId(target) : null) ?? id?.Trim() ?? "video";
var orig = (target != null && target.StartsWith("http", StringComparison.OrdinalIgnoreCase)) ? target : $"https://123av.com/ja/video/{vId}";
return Results.Content(HtmlRenderer.RenderVideoPlayer("123av", vId, play, null, orig, title ?? $"123av 動画 ({vId})"), "text/html; charset=utf-8");
}
// missav 判定
if (string.Equals(site, "missav", StringComparison.OrdinalIgnoreCase) || (target != null && target.Contains("missav", StringComparison.OrdinalIgnoreCase)))
{
var vId = (target != null ? ExtractMissAvId(target) : null) ?? id?.Trim() ?? "video";
var orig = (target != null && target.StartsWith("http", StringComparison.OrdinalIgnoreCase)) ? target : $"https://missav.ai/ja/{vId}";
return Results.Content(HtmlRenderer.RenderVideoPlayer("missav", vId, play, stream, orig, title ?? $"missav 動画 ({vId})"), "text/html; charset=utf-8");
}
// SpankBang 判定
if (string.Equals(site, "spankbang", StringComparison.OrdinalIgnoreCase) || (target != null && target.Contains("spankbang", StringComparison.OrdinalIgnoreCase)))
{
var videoId = (target != null ? ExtractSpankBangId(target) : null) ?? id?.Trim() ?? "video";
var orig = (target != null && target.StartsWith("http", StringComparison.OrdinalIgnoreCase)) ? target : $"https://jp.spankbang.com/{videoId}/video/";
return Results.Content(HtmlRenderer.RenderVideoPlayer("spankbang", videoId, play ?? $"https://spankbang.com/{videoId}/embed/", stream, orig, title ?? $"SpankBang 動画 ({videoId})"), "text/html; charset=utf-8");
}
// エロタレドーガ 判定
if (string.Equals(site, "doga", StringComparison.OrdinalIgnoreCase) || string.Equals(site, "eroterest_doga", StringComparison.OrdinalIgnoreCase) || (target != null && target.Contains("do-ga.eroterest.net", StringComparison.OrdinalIgnoreCase)))
{
var vId = id?.Trim() ?? (target != null ? System.Text.RegularExpressions.Regex.Match(target, @"detail/([0-9]+)").Groups[1].Value : "") ?? "doga";
if (string.IsNullOrWhiteSpace(vId)) vId = "doga";
var orig = (target != null && target.StartsWith("http", StringComparison.OrdinalIgnoreCase)) ? target : $"https://do-ga.eroterest.net/video/detail/{vId}/";
return Results.Content(HtmlRenderer.RenderVideoPlayer("doga", vId, play, stream, orig, title ?? $"エロタレドーガ ({vId})"), "text/html; charset=utf-8");
}
// InPorn 判定
if (string.Equals(site, "inporn", StringComparison.OrdinalIgnoreCase) || (target != null && target.Contains("inporn.com", StringComparison.OrdinalIgnoreCase)))
{
var vId = id?.Trim() ?? (target != null ? System.Text.RegularExpressions.Regex.Match(target, @"/video/([0-9]+)").Groups[1].Value : "") ?? "video";
play ??= $"https://inporn.com/embed/{vId}/";
var orig = (target != null && target.StartsWith("http", StringComparison.OrdinalIgnoreCase)) ? target : $"https://inporn.com/video/{vId}/";
return Results.Content(HtmlRenderer.RenderVideoPlayer("inporn", vId, play, stream, orig, title ?? $"InPorn 動画 ({vId})"), "text/html; charset=utf-8");
}
// BDSMx 判定
if (string.Equals(site, "bdsmx", StringComparison.OrdinalIgnoreCase) || (target != null && target.Contains("bdsmx.tube", StringComparison.OrdinalIgnoreCase)))
{
var vId = id?.Trim() ?? (target != null ? System.Text.RegularExpressions.Regex.Match(target, @"/video/([0-9]+)").Groups[1].Value : "") ?? "video";
play ??= $"https://bdsmx.tube/embed/{vId}/";
var orig = (target != null && target.StartsWith("http", StringComparison.OrdinalIgnoreCase)) ? target : $"https://bdsmx.tube/video/{vId}/";
return Results.Content(HtmlRenderer.RenderVideoPlayer("bdsmx", vId, play, stream, orig, title ?? $"BDSMx 動画 ({vId})"), "text/html; charset=utf-8");
}
// VJAV 判定
if (string.Equals(site, "vjav", StringComparison.OrdinalIgnoreCase) || (target != null && target.Contains("vjav.com", StringComparison.OrdinalIgnoreCase)))
{
var vId = (target != null ? System.Text.RegularExpressions.Regex.Match(target, @"/videos/([0-9]+)").Groups[1].Value : null);
if (string.IsNullOrWhiteSpace(vId)) vId = id?.Trim() ?? "video";
play ??= $"https://vjav.com/embed/{vId}/";
var orig = (target != null && target.StartsWith("http", StringComparison.OrdinalIgnoreCase)) ? target : $"https://vjav.com/videos/{vId}/";
return Results.Content(HtmlRenderer.RenderVideoPlayer("vjav", vId, play, stream, orig, title ?? $"VJAV 動画 ({vId})"), "text/html; charset=utf-8");
}
// LAXD 判定
if (string.Equals(site, "laxd", StringComparison.OrdinalIgnoreCase) || (target != null && (target.Contains("video.laxd.com", StringComparison.OrdinalIgnoreCase) || target.Contains("laxd.com", StringComparison.OrdinalIgnoreCase))))
{
var vId = (target != null ? System.Text.RegularExpressions.Regex.Match(target, @"laxd\.com/(?:a/content/|content/|embed/)?([0-9a-zA-Z_\-]+)").Groups[1].Value : null);
if (string.IsNullOrWhiteSpace(vId)) vId = id?.Trim() ?? "video";
play ??= $"https://video.laxd.com/a/embed/player/{vId}/";
var orig = (target != null && target.StartsWith("http", StringComparison.OrdinalIgnoreCase)) ? target : $"https://video.laxd.com/a/content/{vId}";
return Results.Content(HtmlRenderer.RenderVideoPlayer("laxd", vId, play, stream, orig, title ?? $"LAXD 動画 ({vId})"), "text/html; charset=utf-8");
}
// FC2 判定
if (string.Equals(site, "fc2", StringComparison.OrdinalIgnoreCase) || string.Equals(site, "fc2video", StringComparison.OrdinalIgnoreCase) || (target != null && (target.Contains("contents.fc2.com", StringComparison.OrdinalIgnoreCase) || target.Contains("video.fc2.com", StringComparison.OrdinalIgnoreCase))))
{
var vId = (target != null ? System.Text.RegularExpressions.Regex.Match(target, @"(?:article/|aid=|content/|video/)([0-9a-zA-Z_\-]+)").Groups[1].Value : null);
if (string.IsNullOrWhiteSpace(vId)) vId = id?.Trim() ?? "video";
play ??= $"https://video.fc2.com/a/embed/player/{vId}/";
var orig = (target != null && target.StartsWith("http", StringComparison.OrdinalIgnoreCase)) ? target : $"https://adult.contents.fc2.com/article/{vId}/";
return Results.Content(HtmlRenderer.RenderVideoPlayer("fc2", vId, play, stream, orig, title ?? $"FC2 動画 ({vId})"), "text/html; charset=utf-8");
}
// XVIDEOS 判定
if (string.Equals(site, "xvideos", StringComparison.OrdinalIgnoreCase) || (target != null && target.Contains("xvideos.com", StringComparison.OrdinalIgnoreCase)))
{
var vId = (target != null ? System.Text.RegularExpressions.Regex.Match(target, @"(?:video\.|video|embedframe/)([0-9]+)").Groups[1].Value : null);
if (string.IsNullOrWhiteSpace(vId)) vId = id?.Trim() ?? "video";
play ??= $"https://www.xvideos.com/embedframe/{vId}";
var orig = (target != null && target.StartsWith("http", StringComparison.OrdinalIgnoreCase)) ? target : $"https://www.xvideos.com/video.{vId}/";
return Results.Content(HtmlRenderer.RenderVideoPlayer("xvideos", vId, play, stream, orig, title ?? $"XVIDEOS 動画 ({vId})"), "text/html; charset=utf-8");
}
// target が URL で site 未指定の場合のドメイン自動判定
if (string.IsNullOrWhiteSpace(site) && target != null)
{
if (target.Contains("senzuri.tube", StringComparison.OrdinalIgnoreCase))
{
site = "senzuri";
id ??= System.Text.RegularExpressions.Regex.Match(target, @"/videos/([0-9]+)").Groups[1].Value;
play ??= $"https://senzuri.tube/embed/{id}/";
}
else if (target.Contains("txxx.com", StringComparison.OrdinalIgnoreCase))
{
site = "txxx";
id ??= System.Text.RegularExpressions.Regex.Match(target, @"/videos/([0-9]+)").Groups[1].Value;
play ??= $"https://www.txxx.com/embed/{id}/";
}
else if (target.Contains("hclips.com", StringComparison.OrdinalIgnoreCase))
{
site = "hclips";
id ??= System.Text.RegularExpressions.Regex.Match(target, @"/videos/([0-9]+)").Groups[1].Value;
play ??= $"https://www.hclips.com/embed/{id}/";
}
else if (target.Contains("hdzog.com", StringComparison.OrdinalIgnoreCase))
{
site = "hdzog";
id ??= System.Text.RegularExpressions.Regex.Match(target, @"/videos/([0-9]+)").Groups[1].Value;
play ??= $"https://www.hdzog.com/embed/{id}/";
}
else if (target.Contains("upornia.com", StringComparison.OrdinalIgnoreCase))
{
site = "upornia";
id ??= System.Text.RegularExpressions.Regex.Match(target, @"/videos/([0-9]+)").Groups[1].Value;
play ??= $"https://upornia.com/embed/{id}/";
}
else if (target.Contains("youjizz.com", StringComparison.OrdinalIgnoreCase))
{
site = "youjizz";
id ??= System.Text.RegularExpressions.Regex.Match(target, @"/videos/([0-9]+)").Groups[1].Value;
play ??= $"https://www.youjizz.com/embed/{id}";
}
}
// stream (HLS m3u8 / MP4 等) または play (iframe player) が渡されている場合、または site が指定されている場合
if (!string.IsNullOrWhiteSpace(stream) || !string.IsNullOrWhiteSpace(play) || !string.IsNullOrWhiteSpace(site))
{
var currentSite = !string.IsNullOrWhiteSpace(site) ? site : "video";
var videoId = id?.Trim() ?? (!string.IsNullOrWhiteSpace(target) && !target.StartsWith("http") ? target : "video");
var orig = (target != null && target.StartsWith("http", StringComparison.OrdinalIgnoreCase)) ? target : "";
return Results.Content(HtmlRenderer.RenderVideoPlayer(currentSite, videoId, play, stream, orig, title ?? $"{currentSite} 動画プレイヤー"), "text/html; charset=utf-8");
}
// target が URL の場合は汎用プレイヤーとして開く
if (target != null && target.StartsWith("http", StringComparison.OrdinalIgnoreCase))
{
return Results.Content(HtmlRenderer.RenderVideoPlayer("video", "video", play, stream, target, title ?? "動画プレイヤー"), "text/html; charset=utf-8");
}
// どの形式にも一致しない場合のエラー表示
return Results.Content(
HtmlRenderer.RenderErrorPage($"指定された動画URLまたはID({target})を認識できませんでした。有効な動画URLまたはIDをご確認ください。", 400),
UnifiedHtmlRenderer.RenderErrorPage("コンテンツの種別を認識できませんでした。", 404),
"text/html; charset=utf-8",
statusCode: 400);
statusCode: 404);
});
// 123av 統一プレイヤー画面
app.MapGet("/123av/{id}", (string id, string? play, string? url) =>
{
var videoId = Extract123AvId(id) ?? id.Trim();
var origUrl = !string.IsNullOrEmpty(url) ? url : $"https://123av.com/ja/video/{videoId}";
return Results.Content(HtmlRenderer.RenderVideoPlayer("123av", videoId, play, null, origUrl, $"123av 動画 ({videoId})"), "text/html; charset=utf-8");
});
// missav 統一プレイヤー画面
app.MapGet("/missav/{id}", (string id, string? stream, string? play, string? url) =>
{
var videoId = ExtractMissAvId(id) ?? id.Trim();
var origUrl = !string.IsNullOrEmpty(url) ? url : $"https://missav.ai/ja/{videoId}";
return Results.Content(HtmlRenderer.RenderVideoPlayer("missav", videoId, play, stream, origUrl, $"missav 動画 ({videoId})"), "text/html; charset=utf-8");
});
// SpankBang 統一プレイヤー画面
app.MapGet("/spankbang/{id}", (string id) =>
{
var videoId = ExtractSpankBangId(id) ?? id.Trim();
return Results.Content(HtmlRenderer.RenderVideoPlayer(videoId, $"https://jp.spankbang.com/{videoId}/video/"), "text/html; charset=utf-8");
});
// 動画情報 JSON API
app.MapGet("/api/video/123av/{id}", (string id, string? play) =>
{
var videoId = Extract123AvId(id) ?? id.Trim();
return Results.Ok(new
{
site = "123av",
id = videoId,
playerUrl = play ?? $"https://javplayer.cc/v/{videoId}",
sourceUrl = $"https://123av.com/ja/video/{videoId}"
});
});
app.MapGet("/api/video/missav/{id}", (string id, string? stream) =>
{
var videoId = ExtractMissAvId(id) ?? id.Trim();
return Results.Ok(new
{
site = "missav",
id = videoId,
streamUrl = stream,
sourceUrl = $"https://missav.ai/ja/{videoId}"
});
});
app.MapGet("/api/video/spankbang/{id}", (string id) =>
{
var videoId = ExtractSpankBangId(id) ?? id.Trim();
return Results.Ok(new
{
site = "spankbang",
id = videoId,
embedUrl = $"https://spankbang.com/{videoId}/embed/",
sourceUrl = $"https://jp.spankbang.com/{videoId}/video/"
});
});
// 統一ビューアー画面(3階層)
app.MapGet("/{site}/{category}/{id}", async (string site, string category, string id, GalleryService galleryService, CancellationToken ct) =>
{
// 動画サイトの場合は動画プレイヤー画面へルーティング
if (string.Equals(site, "123av", StringComparison.OrdinalIgnoreCase))
{
return Results.Content(HtmlRenderer.RenderVideoPlayer("123av", id, null, null, $"https://123av.com/ja/video/{id}", $"123av 動画 ({id})"), "text/html; charset=utf-8");
}
if (string.Equals(site, "missav", StringComparison.OrdinalIgnoreCase))
{
return Results.Content(HtmlRenderer.RenderVideoPlayer("missav", id, null, null, $"https://missav.ai/ja/{id}", $"missav 動画 ({id})"), "text/html; charset=utf-8");
}
return await RenderGalleryResponseAsync(site, id, category, galleryService, ct);
});
// 統一ビューアー画面(2階層)
app.MapGet("/{site}/{id}", async (string site, string id, GalleryService galleryService, CancellationToken ct) =>
{
// 動画サイトの場合は動画プレイヤー画面へルーティング
if (string.Equals(site, "123av", StringComparison.OrdinalIgnoreCase))
{
return Results.Content(HtmlRenderer.RenderVideoPlayer("123av", id, null, null, $"https://123av.com/ja/video/{id}", $"123av 動画 ({id})"), "text/html; charset=utf-8");
}
if (string.Equals(site, "missav", StringComparison.OrdinalIgnoreCase))
{
return Results.Content(HtmlRenderer.RenderVideoPlayer("missav", id, null, null, $"https://missav.ai/ja/{id}", $"missav 動画 ({id})"), "text/html; charset=utf-8");
}
if (string.Equals(site, "spankbang", StringComparison.OrdinalIgnoreCase))
{
return Results.Redirect($"/spankbang/{id}");
}
return await RenderGalleryResponseAsync(site, id, null, galleryService, ct);
});
// 対応サイト一覧 JSON API
app.MapGet("/api/sites", (GalleryService galleryService) =>
{
var sites = galleryService.GetAvailableSites().Select(s => new
{
key = s.Key,
name = s.Name,
aliases = s.Aliases,
exampleUrl = $"/{s.Key}/<ID>"
});
return Results.Ok(sites);
});
// 統一 JSON API(3階層)
app.MapGet("/api/{site}/{category}/{id}", async (string site, string category, string id, GalleryService galleryService, CancellationToken ct) =>
{
return await RenderJsonResponseAsync(site, id, category, galleryService, ct);
});
// 統一 JSON API(2階層)
app.MapGet("/api/{site}/{id}", async (string site, string id, GalleryService galleryService, CancellationToken ct) =>
{
return await RenderJsonResponseAsync(site, id, null, galleryService, ct);
});
// 汎用スクレイピング JSON API
app.MapGet("/api/scrape", async (string? url, string? site, 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。" });
}
return await RenderJsonResponseAsync(site, target, category, galleryService, ct);
});
// 画像プロキシエンドポイント
app.MapGet("/api/proxy-image", async (string url, string? referer, HttpHelper httpHelper, ILoggerFactory loggerFactory, CancellationToken ct) =>
// ==========================================
// 画像プロキシAPI (Referer制限回避・高速キャッシュ配信)
// ==========================================
app.MapGet("/api/proxy-image", async (string url, string? referer, UnifiedHttpHelper httpHelper, ILoggerFactory loggerFactory, CancellationToken ct) =>
{
if (string.IsNullOrWhiteSpace(url))
{
@@ -441,194 +107,9 @@ app.MapGet("/api/proxy-image", async (string url, string? referer, HttpHelper ht
});
// ==========================================
// 共通レスポンス生成ヘルパー関数
// 旧バージョン(Legacy)のエンドポイント登録
// (/view, /video, /{site}/{id}, /spankbang/{id}, 旧API等を過去互換用として保持)
// ==========================================
static async Task<IResult> RenderGalleryResponseAsync(
string? site,
string idOrUrl,
string? category,
GalleryService galleryService,
CancellationToken ct)
{
var gallery = !string.IsNullOrWhiteSpace(site)
? await galleryService.GetGalleryBySiteAsync(site, idOrUrl, category, false, ct)
: await galleryService.GetGalleryAsync(idOrUrl, category, false, ct);
if (gallery == null || gallery.Images.Count == 0)
{
var targetInfo = !string.IsNullOrWhiteSpace(site) ? $"{site}/{idOrUrl}" : idOrUrl;
return Results.Content(
HtmlRenderer.RenderErrorPage($"指定された作品({targetInfo})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");
}
static async Task<IResult> RenderJsonResponseAsync(
string? site,
string idOrUrl,
string? category,
GalleryService galleryService,
CancellationToken ct)
{
var gallery = !string.IsNullOrWhiteSpace(site)
? await galleryService.GetGalleryBySiteAsync(site, idOrUrl, category, false, ct)
: await galleryService.GetGalleryAsync(idOrUrl, category, false, ct);
if (gallery == null)
{
return Results.NotFound(new { error = "Gallery not found", site, id = idOrUrl, category });
}
return Results.Ok(gallery);
}
static string? ExtractSpankBangId(string input)
{
if (string.IsNullOrWhiteSpace(input)) return null;
input = input.Trim();
// URL形式 (例: https://jp.spankbang.com/56b3d/video/... または /embed/ または /play/)
var match = System.Text.RegularExpressions.Regex.Match(
input,
@"spankbang\.(?:com|party)/(?<id>[a-z0-9]+)(?:/(?:video|play|embed)|/|$)",
System.Text.RegularExpressions.RegexOptions.IgnoreCase);
if (match.Success)
{
return match.Groups["id"].Value;
}
// spankbang/<id> 形式
var matchSlash = System.Text.RegularExpressions.Regex.Match(
input,
@"^(?:spankbang/)?(?<id>[a-z0-9]{3,12})$",
System.Text.RegularExpressions.RegexOptions.IgnoreCase);
if (matchSlash.Success)
{
return matchSlash.Groups["id"].Value;
}
return null;
}
static string? Extract123AvId(string input)
{
if (string.IsNullOrWhiteSpace(input)) return null;
input = input.Trim();
// URL形式 (例: https://123av.com/ja/video/12345 または /ja/12345)
var match = System.Text.RegularExpressions.Regex.Match(
input,
@"(?:123av\.com/[a-z]{2}/(?:video/)?|^123av/)(?<id>[^/?#]+)",
System.Text.RegularExpressions.RegexOptions.IgnoreCase);
if (match.Success)
{
return match.Groups["id"].Value;
}
// パス末尾のセグメント
if (input.Contains('/') || input.Contains('\\'))
{
var seg = input.TrimEnd('/', '\\').Split(new[] { '/', '\\' }).Last();
if (!string.IsNullOrWhiteSpace(seg)) return seg;
}
return input;
}
static string? ExtractMissAvId(string input)
{
if (string.IsNullOrWhiteSpace(input)) return null;
input = input.Trim();
// URL形式 (例: https://missav.ai/ja/ssis-123 または /ja/12345)
var match = System.Text.RegularExpressions.Regex.Match(
input,
@"(?:missav\.[a-z]+/[a-z]{2}/|^missav/)(?<id>[^/?#]+)",
System.Text.RegularExpressions.RegexOptions.IgnoreCase);
if (match.Success)
{
return match.Groups["id"].Value;
}
// パス末尾のセグメント
if (input.Contains('/') || input.Contains('\\'))
{
var seg = input.TrimEnd('/', '\\').Split(new[] { '/', '\\' }).Last();
if (!string.IsNullOrWhiteSpace(seg)) return seg;
}
return input;
}
static bool IsGalleryUrlOrSite(string? site, string? urlOrId)
{
if (string.IsNullOrWhiteSpace(urlOrId)) return false;
var lower = urlOrId.ToLowerInvariant();
if (string.Equals(site, "ehentai", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "hitomi", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "aurahentai", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "momonga", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "mangalear", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "hentaipaw", StringComparison.OrdinalIgnoreCase))
{
return true;
}
return lower.Contains("e-hentai.org") ||
lower.Contains("exhentai.org") ||
lower.Contains("hitomi.la") ||
lower.Contains("aurahentai.com") ||
lower.Contains("momon-ga.com") ||
lower.Contains("mangalear.com") ||
lower.Contains("hentaipaw.com");
}
static bool IsVideoUrlOrSite(string? site, string? urlOrId)
{
if (string.IsNullOrWhiteSpace(urlOrId)) return false;
var lower = urlOrId.ToLowerInvariant();
if (string.Equals(site, "spankbang", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "123av", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "missav", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "doga", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "eroterest_doga", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "vjav", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "laxd", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "fc2", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "inporn", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "bdsmx", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "senzuri", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "txxx", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "hclips", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "hdzog", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "upornia", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "youjizz", StringComparison.OrdinalIgnoreCase) ||
string.Equals(site, "xvideos", StringComparison.OrdinalIgnoreCase))
{
return true;
}
return lower.Contains("spankbang") ||
lower.Contains("123av") ||
lower.Contains("missav") ||
lower.Contains("do-ga.eroterest.net") ||
lower.Contains("movie.eroterest.net") ||
lower.Contains("vjav.com") ||
lower.Contains("laxd.com") ||
lower.Contains("fc2.com") ||
lower.Contains("inporn.com") ||
lower.Contains("bdsmx.tube") ||
lower.Contains("senzuri.tube") ||
lower.Contains("txxx.com") ||
lower.Contains("hclips.com") ||
lower.Contains("hdzog.com") ||
lower.Contains("upornia.com") ||
lower.Contains("youjizz.com") ||
lower.Contains("xvideos.com") ||
lower.Contains("blogterest.net") ||
lower.Contains("blog.2nt.com");
}
app.MapLegacyEndpoints();
app.Run();