koishi-plugin-video-parser-all 0.9.7 → 0.9.8

package/lib/index.js

@@ -7,7 +7,6 @@ exports.Config = exports.name = void 0;
 exports.apply = apply;
 const koishi_1 = require("koishi");
 const axios_1 = __importDefault(require("axios"));
-const fast_xml_parser_1 = require("fast-xml-parser");
 exports.name = 'video-parser-all';
 exports.Config = koishi_1.Schema.intersect([
     koishi_1.Schema.object({
@@ -54,85 +53,62 @@ function debugLog(level, ...args) {
     const message = `[${timestamp}] [${level}] ${args.map(a => typeof a === 'object' ? JSON.stringify(a, null, 2) : String(a)).join(' ')}`;
     logger.info(message);
 }
-const PLATFORM_KEYWORDS = {
-    bilibili: ['bilibili', 'b23', 'www.bilibili.com', 'm.bilibili.com', 'b23.tv', 't.bilibili.com', 'bilibili.com/video', 'bilibili.com/opus', 'bilibili.com/bangumi'],
-    kuaishou: ['kuaishou', 'v.kuaishou.com', 'www.kuaishou.com', 'kwimgs.com'],
-    weibo: ['weibo', 'weibo.com', 'video.weibo.com', 'm.weibo.cn', 'weibo.com/tv/show', 'weibo.com/feed'],
-    toutiao: ['toutiao', 'm.toutiao.com', 'toutiao.com', 'ixigua.com', 'toutiao.com/video'],
-    pipigx: ['pipigx', 'h5.pipigx.com', 'ippzone.com'],
-    pipixia: ['pipixia', 'pipix', 'h5.pipix.com', 'ppxsign.byteimg.com', 'pipix.com'],
-    douyin: ['douyin', 'v.douyin.com', 'douyinpic.com', 'douyinvod.com', 'douyin.com/video', 'douyin.com/note', 'www.douyin.com'],
-    zuiyou: ['zuiyou', 'xiaochuankeji.cn', 'izuiyou.com'],
-    xiaohongshu: ['xiaohongshu', 'xhslink.com', 'www.xiaohongshu.com'],
-    jianying: ['jianying', 'jimeng.jianying.com', 'lv.ulikecam.com'],
-    acfun: ['acfun', 'acfun.cn', 'www.acfun.cn'],
-    zhihu: ['zhihu', 'zhihu.com', 'www.zhihu.com'],
-    weishi: ['weishi', 'weishi.qq.com'],
-    huya: ['huya', 'huya.com', 'www.huya.com'],
-    youtube: ['youtube', 'youtube.com', 'youtu.be', 'www.youtube.com'],
-    tiktok: ['tiktok', 'tiktok.com', 'www.tiktok.com'],
-    xigua: ['xigua', 'ixigua.com'],
-    haokan: ['haokan', 'haokan.baidu.com'],
-    li: ['video.li'],
-    meipai: ['meipai', 'meipai.com'],
-    quanmin: ['quanmin', 'quanmin.tv'],
-    twitter: ['twitter', 'x.com'],
-    instagram: ['instagram', 'instagram.com'],
-    doubao: ['doubao', 'doubao.com'],
-    jimeng: ['jimeng', 'jimeng.ai'],
-};
-function getErrorMessage(error) {
-    if (error instanceof Error)
-        return error.message;
-    return String(error);
-}
-const xmlParser = new fast_xml_parser_1.XMLParser({
-    ignoreAttributes: false,
-    attributeNamePrefix: '@_',
-    allowBooleanAttributes: true,
-    trimValues: true,
-    parseTagValue: false,
-    isArray: (name) => name === 'item' || name === 'picture',
-});
-function extractUrlsFromXml(xml) {
-    const urls = [];
-    try {
-        const parsed = xmlParser.parse(xml);
-        const msg = parsed?.msg;
-        if (!msg)
-            return urls;
-        if (msg.source && typeof msg.source === 'object') {
-            const sourceUrl = msg.source['@_url'];
-            if (sourceUrl && typeof sourceUrl === 'string')
-                urls.push(sourceUrl);
-        }
-        const items = Array.isArray(msg.item) ? msg.item : (msg.item ? [msg.item] : []);
-        for (const item of items) {
-            const pictures = Array.isArray(item.picture) ? item.picture : (item.picture ? [item.picture] : []);
-            for (const pic of pictures) {
-                if (pic['@_cover'] && typeof pic['@_cover'] === 'string')
-                    urls.push(pic['@_cover']);
-            }
-            if (item.title && typeof item.title === 'string') {
-                const match = item.title.match(/https?:\/\/[^\s<>"']+/i);
-                if (match)
-                    urls.push(match[0]);
-            }
-            if (item.summary && typeof item.summary === 'string') {
-                const matches = item.summary.match(/https?:\/\/[^\s<>"']+/gi);
-                if (matches)
-                    urls.push(...matches);
-            }
+function linkTypeParser(content) {
+    content = content.replace(/\\\//g, '/');
+    const rules = [
+        { pattern: /bilibili\.com\/video\/([ab]v[0-9a-zA-Z]+)/gi, type: 'bilibili', buildUrl: (id) => `https://www.bilibili.com/video/${id}` },
+        { pattern: /b23\.tv(?:\\)?\/([0-9a-zA-Z]+)/gi, type: 'bilibili', buildUrl: (id) => `https://b23.tv/${id}` },
+        { pattern: /bili(?:22|23|33)\.cn\/([0-9a-zA-Z]+)/gi, type: 'bilibili', buildUrl: (id) => `https://bili23.cn/${id}` },
+        { pattern: /bili2233\.cn\/([0-9a-zA-Z]+)/gi, type: 'bilibili', buildUrl: (id) => `https://bili2233.cn/${id}` },
+        { pattern: /douyin\.com\/video\/(\d+)/gi, type: 'douyin', buildUrl: (id) => `https://www.douyin.com/video/${id}` },
+        { pattern: /v\.douyin\.com\/([0-9a-zA-Z]+)/gi, type: 'douyin', buildUrl: (id) => `https://v.douyin.com/${id}` },
+        { pattern: /kuaishou\.com\/short-video\/([0-9a-zA-Z]+)/gi, type: 'kuaishou', buildUrl: (id) => `https://www.kuaishou.com/short-video/${id}` },
+        { pattern: /v\.kuaishou\.com\/([0-9a-zA-Z]+)/gi, type: 'kuaishou', buildUrl: (id) => `https://v.kuaishou.com/${id}` },
+        { pattern: /xiaohongshu\.com\/discovery\/item\/([0-9a-zA-Z]+)/gi, type: 'xiaohongshu', buildUrl: (id) => `https://www.xiaohongshu.com/discovery/item/${id}` },
+        { pattern: /xhslink\.com\/([0-9a-zA-Z]+)/gi, type: 'xiaohongshu', buildUrl: (id) => `https://xhslink.com/${id}` },
+        { pattern: /weibo\.com\/\d+\/([0-9a-zA-Z]+)/gi, type: 'weibo', buildUrl: (id) => `https://weibo.com/${id}` },
+        { pattern: /video\.weibo\.com\/show\?fid=([0-9a-zA-Z]+)/gi, type: 'weibo', buildUrl: (id) => `https://video.weibo.com/show?fid=${id}` },
+        { pattern: /ixigua\.com\/(\d+)/gi, type: 'xigua', buildUrl: (id) => `https://www.ixigua.com/${id}` },
+        { pattern: /youtube\.com\/watch\?v=([a-zA-Z0-9_-]+)/gi, type: 'youtube', buildUrl: (id) => `https://www.youtube.com/watch?v=${id}` },
+        { pattern: /youtu\.be\/([a-zA-Z0-9_-]+)/gi, type: 'youtube', buildUrl: (id) => `https://youtu.be/${id}` },
+        { pattern: /tiktok\.com\/@[\w.]+\/video\/(\d+)/gi, type: 'tiktok', buildUrl: (id) => `https://www.tiktok.com/@user/video/${id}` },
+        { pattern: /vm\.tiktok\.com\/([0-9a-zA-Z]+)/gi, type: 'tiktok', buildUrl: (id) => `https://vm.tiktok.com/${id}` },
+        { pattern: /acfun\.cn\/v\/(ac\d+)/gi, type: 'acfun', buildUrl: (id) => `https://www.acfun.cn/v/${id}` },
+        { pattern: /zhihu\.com\/video\/(\d+)/gi, type: 'zhihu', buildUrl: (id) => `https://www.zhihu.com/video/${id}` },
+        { pattern: /weishi\.qq\.com\/weishi\/feed\/([0-9a-zA-Z]+)/gi, type: 'weishi', buildUrl: (id) => `https://weishi.qq.com/weishi/feed/${id}` },
+        { pattern: /huya\.com\/video\/([0-9a-zA-Z]+)/gi, type: 'huya', buildUrl: (id) => `https://www.huya.com/video/${id}` },
+        { pattern: /haokan\.baidu\.com\/v\?vid=([0-9a-zA-Z]+)/gi, type: 'haokan', buildUrl: (id) => `https://haokan.baidu.com/v?vid=${id}` },
+        { pattern: /meipai\.com\/media\/(\d+)/gi, type: 'meipai', buildUrl: (id) => `https://www.meipai.com/media/${id}` },
+        { pattern: /twitter\.com\/\w+\/status\/(\d+)/gi, type: 'twitter', buildUrl: (id) => `https://twitter.com/i/status/${id}` },
+        { pattern: /x\.com\/\w+\/status\/(\d+)/gi, type: 'twitter', buildUrl: (id) => `https://x.com/i/status/${id}` },
+        { pattern: /instagram\.com\/p\/([0-9a-zA-Z_-]+)/gi, type: 'instagram', buildUrl: (id) => `https://www.instagram.com/p/${id}` },
+        { pattern: /doubao\.com\/video\/(\d+)/gi, type: 'doubao', buildUrl: (id) => `https://www.doubao.com/video/${id}` },
+    ];
+    const matches = [];
+    const seen = new Set();
+    for (const rule of rules) {
+        let match;
+        while ((match = rule.pattern.exec(content)) !== null) {
+            const id = match[1];
+            if (seen.has(id))
+                continue;
+            seen.add(id);
+            const url = rule.buildUrl(id);
+            matches.push({ type: rule.type, url, id });
         }
     }
-    catch (err) {
-        debugLog('WARN', `解析 XML 卡片失败: ${getErrorMessage(err)}`);
-    }
-    return urls;
+    return matches;
 }
 function extractAllUrlsFromMessage(session) {
-    const urls = [];
     const content = session.content?.trim() || '';
+    const urls = [];
+    const linkMatches = linkTypeParser(content);
+    if (linkMatches.length > 0) {
+        for (const match of linkMatches) {
+            urls.push(match.url);
+        }
+        return [...new Set(urls)];
+    }
     if (content) {
         const textUrls = extractUrl(content);
         urls.push(...textUrls);
@@ -140,7 +116,7 @@ function extractAllUrlsFromMessage(session) {
     if (session.elements) {
         for (const elem of session.elements) {
             if (elem.type === 'xml' && elem.data) {
-                const xmlUrls = extractUrlsFromXml(elem.data);
+                const xmlUrls = extractUrlsFromXmlLegacy(elem.data);
                 urls.push(...xmlUrls);
             }
             else if (elem.type === 'json' && elem.data) {
@@ -167,6 +143,15 @@ function extractAllUrlsFromMessage(session) {
     }
     return [...new Set(urls)];
 }
+function extractUrlsFromXmlLegacy(xml) {
+    const urls = [];
+    const urlRegex = /https?:\/\/[^\s<>"']+/gi;
+    let match;
+    while ((match = urlRegex.exec(xml)) !== null) {
+        urls.push(match[0]);
+    }
+    return urls;
+}
 function extractUrl(content) {
     const urlMatches = content.match(/https?:\/\/[^\s\"\'\>]+/gi) || [];
     return urlMatches.filter(url => {
@@ -174,27 +159,13 @@ function extractUrl(content) {
             const hostname = new URL(url).hostname.toLowerCase();
             if (hostname === 'multimedia.nt.qq.com.cn')
                 return false;
-            return Object.values(PLATFORM_KEYWORDS).some(group => group.some(keyword => hostname.includes(keyword) || (!keyword.includes('.') && url.toLowerCase().includes(keyword))));
+            return true;
         }
         catch {
-            const lower = url.toLowerCase();
-            return Object.values(PLATFORM_KEYWORDS).some(group => group.some(keyword => lower.includes(keyword)));
+            return false;
         }
     });
 }
-function getPlatformType(url) {
-    try {
-        const hostname = new URL(url).hostname.toLowerCase();
-        if (hostname === 'multimedia.nt.qq.com.cn')
-            return null;
-        for (const [platform, keywords] of Object.entries(PLATFORM_KEYWORDS)) {
-            if (keywords.some(k => hostname.includes(k) || (!k.includes('.') && url.toLowerCase().includes(k))))
-                return platform;
-        }
-    }
-    catch { }
-    return null;
-}
 function cleanUrl(url) {
     try {
         url = url.replace(/&amp;/g, '&');
@@ -219,7 +190,7 @@ async function resolveShortUrl(url) {
                 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36',
                 'Referer': 'https://www.baidu.com/',
             },
-            validateStatus: status => status >= 200 && status < 400,
+            validateStatus: (status) => status >= 200 && status < 400,
         });
         const finalUrl = res.request?.res?.responseUrl || url;
         return cleanUrl(finalUrl);
@@ -443,10 +414,6 @@ function apply(ctx, config) {
     }
     async function parseUrl(url) {
         const realUrl = await resolveShortUrl(url);
-        const platform = getPlatformType(realUrl);
-        if (!platform) {
-            return { success: false, msg: texts.unsupportedPlatformText };
-        }
         const candidates = [realUrl, url];
         for (const candidate of [...new Set(candidates)]) {
             try {
@@ -457,7 +424,7 @@ function apply(ctx, config) {
                 debugLog('ERROR', `候选链接解析失败: ${candidate}`, getErrorMessage(error));
             }
         }
-        return { success: false, msg: '解析失败' };
+        return { success: false, msg: texts.unsupportedPlatformText };
     }
     async function processSingleUrl(url) {
         const result = await parseUrl(url);
@@ -623,3 +590,8 @@ function apply(ctx, config) {
     }, 60000);
     debugLog('INFO', '插件初始化完成');
 }
+function getErrorMessage(error) {
+    if (error instanceof Error)
+        return error.message;
+    return String(error);
+}

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "koishi-plugin-video-parser-all",
-  "description": "Koishi 全平台视频解析插件，支持抖音/快手/B站/微博/小红书/剪映/YouTube/TikTok等20+平台，新增XML卡片链接提取",
-  "version": "0.9.7",
+  "description": "Koishi 全平台视频解析插件，支持抖音/快手/B站/微博/小红书/剪映/YouTube/TikTok等20+平台",
+  "version": "0.9.8",
   "main": "lib/index.js",
   "typings": "lib/index.d.ts",
   "files": [