Files
WebImageViewer/WebImageViewer/Class/Scrapers/MomongaScraper.cs
T

246 lines
9.7 KiB
C#
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
using System.Text.RegularExpressions;
using HtmlAgilityPack;
using Microsoft.Extensions.Logging;
using WebImageViewer.Class.Common;
using WebImageViewer.Class.Models;
namespace WebImageViewer.Class.Scrapers;
/// <summary>
/// momon-ga.com 固有のスクレイパークラス
/// </summary>
public partial class MomongaScraper : BaseScraper
{
private const string BaseDomain = "momon-ga.com";
private const string BaseUrl = "https://momon-ga.com";
public override string SiteName => "momon-ga";
public override string SiteKey => "momonga";
public override IReadOnlyList<string> Aliases => new[] { "momon-ga", "momon-ga.com", "mo", "fanzine", "magazine" };
public MomongaScraper(HttpHelper httpHelper, ILogger<MomongaScraper> logger)
: base(httpHelper, logger)
{
}
/// <inheritdoc/>
public override bool CanHandle(string urlOrPath)
{
if (string.IsNullOrWhiteSpace(urlOrPath))
{
return false;
}
var trimmed = urlOrPath.Trim();
// サイトキーまたはエイリアスと完全一致
if (string.Equals(trimmed, SiteKey, StringComparison.OrdinalIgnoreCase) ||
Aliases.Any(a => string.Equals(trimmed, a, StringComparison.OrdinalIgnoreCase)))
{
return true;
}
// momon-ga のドメインが含まれているか、または典型的なID形式(moから始まる等)かパス形式
return trimmed.Contains(BaseDomain, StringComparison.OrdinalIgnoreCase) ||
trimmed.StartsWith("mo", StringComparison.OrdinalIgnoreCase) ||
trimmed.Contains("fanzine", StringComparison.OrdinalIgnoreCase) ||
trimmed.Contains("magazine", StringComparison.OrdinalIgnoreCase);
}
/// <inheritdoc/>
public override async Task<GalleryItem?> ScrapeAsync(string idOrUrl, string? category = null, CancellationToken cancellationToken = default)
{
var (targetUrl, normalizedId, resolvedCategory) = ResolveUrlAndId(idOrUrl, category);
Logger.LogInformation("[{SiteName}] スクレイピング開始 - ID: {Id}, Category: {Category}, URL: {Url}",
SiteName, normalizedId, resolvedCategory, targetUrl);
var doc = await LoadHtmlDocumentAsync(targetUrl, cancellationToken);
if (doc == null || doc.DocumentNode == null)
{
Logger.LogWarning("[{SiteName}] ドキュメントの読み込みに失敗しました: {Url}", SiteName, targetUrl);
return null;
}
// タイトルの抽出(h1タグ、またはpost-data内のh1、またはtitleタグ)
var titleNode = doc.DocumentNode.SelectSingleNode("//div[@id='post-data']//h1") ??
doc.DocumentNode.SelectSingleNode("//h1") ??
doc.DocumentNode.SelectSingleNode("//title");
var title = CleanText(titleNode?.InnerText) ?? normalizedId;
// 余分なサイト名表記を除去(例: "新妻契約 - 同人誌 - エロ漫画 momon:GA(モモンガッ!!)" -> "新妻契約")
if (title.Contains(" - "))
{
title = title.Split(" - ")[0].Trim();
}
var galleryItem = new GalleryItem
{
Id = normalizedId,
Title = string.IsNullOrEmpty(title) ? normalizedId : title,
Category = resolvedCategory,
SourceSite = SiteName,
SourceUrl = targetUrl,
FetchedAt = DateTime.UtcNow
};
// サークル、作者、タグの抽出
ExtractTagsAndMetadata(doc, galleryItem);
// 画像一覧の抽出(#post-hentai img)
ExtractImages(doc, galleryItem);
// サムネイルの決定(data-thumb属性、または1枚目の画像)
var historyNode = doc.DocumentNode.SelectSingleNode("//div[contains(@class, 'history')]");
var dataThumb = historyNode?.GetAttributeValue("data-thumb", null);
if (!string.IsNullOrWhiteSpace(dataThumb))
{
galleryItem.ThumbnailUrl = dataThumb;
}
else if (galleryItem.Images.Count > 0)
{
galleryItem.ThumbnailUrl = galleryItem.Images[0].ImageUrl;
}
Logger.LogInformation("[{SiteName}] スクレイピング完了: 『{Title}』, 画像数: {Count}枚",
SiteName, galleryItem.Title, galleryItem.Images.Count);
return galleryItem;
}
/// <summary>
/// IDまたはURLから完全なリクエストURL、正規化されたID、カテゴリを解決します。
/// </summary>
private static (string TargetUrl, string NormalizedId, string ResolvedCategory) ResolveUrlAndId(string idOrUrl, string? category)
{
var trimmed = idOrUrl.Trim();
string resolvedCategory = string.IsNullOrWhiteSpace(category) ? "fanzine" : category.Trim().ToLowerInvariant();
string normalizedId;
if (trimmed.StartsWith("http://", StringComparison.OrdinalIgnoreCase) ||
trimmed.StartsWith("https://", StringComparison.OrdinalIgnoreCase))
{
// URL形式の場合
var uri = new Uri(trimmed);
var segments = uri.AbsolutePath.Split('/', StringSplitOptions.RemoveEmptyEntries);
if (segments.Length >= 2)
{
resolvedCategory = segments[0];
normalizedId = segments[1];
}
else if (segments.Length == 1)
{
normalizedId = segments[0];
}
else
{
normalizedId = trimmed;
}
return ($"{BaseUrl}/{resolvedCategory}/{normalizedId}/", normalizedId, resolvedCategory);
}
// パスまたはIDのみの場合(例: "fanzine/mo3469109" や "mo3469109")
if (trimmed.Contains('/'))
{
var parts = trimmed.Split('/', StringSplitOptions.RemoveEmptyEntries);
if (parts.Length >= 2)
{
resolvedCategory = parts[0];
normalizedId = parts[1];
}
else
{
normalizedId = parts[0];
}
}
else
{
normalizedId = trimmed;
}
var fullUrl = $"{BaseUrl}/{resolvedCategory}/{normalizedId}/";
return (fullUrl, normalizedId, resolvedCategory);
}
/// <summary>
/// タグテーブルからサークル、作者、内容タグを抽出します。
/// </summary>
private static void ExtractTagsAndMetadata(HtmlDocument doc, GalleryItem item)
{
var tagTables = doc.DocumentNode.SelectNodes("//div[@id='post-tag']//div[contains(@class, 'post-tag-table')]");
if (tagTables == null) return;
foreach (var table in tagTables)
{
var titleNode = table.SelectSingleNode(".//div[contains(@class, 'post-tag-title')]");
var titleText = CleanText(titleNode?.InnerText);
var linkNodes = table.SelectNodes(".//div[contains(@class, 'post-tags')]//a");
if (linkNodes == null) continue;
var tagValues = linkNodes.Select(n => CleanText(n.InnerText)).Where(s => !string.IsNullOrEmpty(s)).ToList();
if (titleText.Contains("サークル", StringComparison.OrdinalIgnoreCase) || titleText.Contains("グループ", StringComparison.OrdinalIgnoreCase))
{
item.Circle = string.Join(", ", tagValues);
}
else if (titleText.Contains("作者", StringComparison.OrdinalIgnoreCase) || titleText.Contains("漫画家", StringComparison.OrdinalIgnoreCase))
{
item.Author = string.Join(", ", tagValues);
}
else if (titleText.Contains("内容", StringComparison.OrdinalIgnoreCase) || titleText.Contains("タグ", StringComparison.OrdinalIgnoreCase) || titleText.Contains("キャラクター", StringComparison.OrdinalIgnoreCase))
{
item.Tags.AddRange(tagValues);
}
}
}
/// <summary>
/// 本文領域から画像一覧を抽出します。
/// </summary>
private static void ExtractImages(HtmlDocument doc, GalleryItem item)
{
var imgNodes = doc.DocumentNode.SelectNodes("//div[@id='post-hentai']//img") ??
doc.DocumentNode.SelectNodes("//div[contains(@class, 'entry-content')]//img") ??
doc.DocumentNode.SelectNodes("//article//img");
if (imgNodes == null) return;
int pageNum = 1;
foreach (var img in imgNodes)
{
// src または data-src, data-lazy-src 属性から画像URLを取得
var src = img.GetAttributeValue("src", null) ??
img.GetAttributeValue("data-src", null) ??
img.GetAttributeValue("data-lazy-src", null);
if (string.IsNullOrWhiteSpace(src)) continue;
// 広告画像やアイコン等を除外
if (src.Contains("themes", StringComparison.OrdinalIgnoreCase) ||
src.Contains("plugins", StringComparison.OrdinalIgnoreCase) ||
src.Contains("banner", StringComparison.OrdinalIgnoreCase) ||
src.Contains("ad_", StringComparison.OrdinalIgnoreCase))
{
continue;
}
var alt = img.GetAttributeValue("alt", null);
int? width = int.TryParse(img.GetAttributeValue("width", null), out var w) ? w : null;
int? height = int.TryParse(img.GetAttributeValue("height", null), out var h) ? h : null;
item.Images.Add(new ImageInfo
{
PageNumber = pageNum++,
ImageUrl = src,
ThumbnailUrl = src,
AltText = CleanText(alt),
Width = width,
Height = height
});
}
}
}