fix(route): harden njxzc, gxmzu and jou routes (#22435)

* fix(route): harden njxzc, gxmzu and jou routes - parse all observed date formats (ISO, slash, Chinese with optional time) instead of a fixed YYYY-MM-DD pattern - fall back to list data when an article page fails or lacks content, instead of crashing the whole feed on cheerio load(null) - skip content fetching for off-site links (e.g. WeChat posts) - only override title/pubDate when found on the detail page - resolve relative links and images against the article URL - deduplicate the list/detail scaffold into per-namespace utils - remove dead response.status checks, unused ctx params and noise comments; fix namespace URLs and antiCrawler flags * refactor(route): address review feedback for gxmzu, jou and njxzc - translate code comments to English (AGENTS.md rule 53) - select the date cell via $(selector, context) instead of .find(selector) to avoid unicorn/no-array-callback-reference false positives * refactor(route): simplify gxmzu, jou and njxzc per review - drop the unused type exports, unnecessary .first() calls and the unreachable no-content early returns - restore the original selector object order in gxmzu/jou call sites - gxmzu/jou: drop try-catch in resolveArticles (no failing article observed); keep the same-host guard for off-site list entries - njxzc: drop the same-host guard (list links are same-host /_redirect URLs); keep try-catch for redirects to intranet-only subdomains - gxmzu/lib: read the link text directly (library rows have no title attribute) * refactor(route): drop jou host guard and njxzc intranet handling - jou: remove the same-host guard — no off-site rows on the current first pages, which are all the route reads - njxzc: remove the intranet-notice branch and the try-catch — every article on the current first pages loads fine from off-campus; drop the now-stale route descriptions as well --------- Co-authored-by: real-jiakai <real.jiakai@gmail.com>
2026-09-21 12:49:53 +08:00 · 2026-07-20 13:08:00 +08:00
parent 9d486c3bda
commit 39aa7af02c
12 changed files with 371 additions and 352 deletions
@@ -1,9 +1,11 @@
+import { load } from 'cheerio';
+
 import type { Route } from '@/types';
+import ofetch from '@/utils/ofetch';

-import { getNoticeList } from './utils';
+import { parseNoticeList, resolveArticles } from './utils';

-const url = 'https://ai.gxmzu.edu.cn/index/tzgg.htm';
-const host = 'https://ai.gxmzu.edu.cn';
+const pageUrl = 'https://ai.gxmzu.edu.cn/index/tzgg.htm';

 export const route: Route = {
    path: '/aitzgg',
@@ -13,7 +15,7 @@ export const route: Route = {
    features: {
        requireConfig: false,
        requirePuppeteer: false,
-        antiCrawler: true,
+        antiCrawler: false,
        supportBT: false,
        supportPodcast: false,
        supportScihub: false,
@@ -29,8 +31,12 @@ export const route: Route = {
    url: 'ai.gxmzu.edu.cn/index/tzgg.htm',
 };

-async function handler(ctx) {
-    const out = await getNoticeList(ctx, url, host, 'a', '.timestyle55267', {
+async function handler() {
+    const response = await ofetch(pageUrl);
+    const $ = load(response);
+
+    const list = parseNoticeList($, pageUrl, 'table.winstyle55267 tr[height="20"]', '.timestyle55267');
+    const items = await resolveArticles(list, pageUrl, {
        title: '.titlestyle55269',
        content: '#vsb_newscontent',
        date: '.timestyle55269',
@@ -38,7 +44,7 @@ async function handler(ctx) {

    return {
        title: '广西民族大学人工智能学院 -- 通知公告',
-        link: url,
-        item: out,
+        link: pageUrl,
+        item: items,
    };
 }
@@ -1,13 +1,11 @@
 import { load } from 'cheerio';

 import type { Route } from '@/types';
-import cache from '@/utils/cache';
-import ofetch from '@/utils/ofetch'; // 使用ofetch库代替got
-import { parseDate } from '@/utils/parse-date';
-import timezone from '@/utils/timezone';
+import ofetch from '@/utils/ofetch';

-const url = 'https://library.gxmzu.edu.cn/news/news_list.jsp?urltype=tree.TreeTempUrl&wbtreeid=1010';
-const host = 'https://library.gxmzu.edu.cn';
+import { parsePubDate, resolveArticles } from './utils';
+
+const pageUrl = 'https://library.gxmzu.edu.cn/news/news_list.jsp?urltype=tree.TreeTempUrl&wbtreeid=1010';

 export const route: Route = {
    path: '/libzxxx',
@@ -17,7 +15,7 @@ export const route: Route = {
    features: {
        requireConfig: false,
        requirePuppeteer: false,
-        antiCrawler: true,
+        antiCrawler: false,
        supportBT: false,
        supportPodcast: false,
        supportScihub: false,
@@ -31,50 +29,38 @@ export const route: Route = {
    maintainers: ['real-jiakai'],
    handler,
    url: 'library.gxmzu.edu.cn/news/news_list.jsp',
+    description: '部分消息发布于微信公众号等站外页面，此类消息仅输出标题与原文链接。',
 };

 async function handler() {
-    const response = await ofetch(url);
-    if (!response) {
-        return;
-    }
+    const response = await ofetch(pageUrl);
    const $ = load(response);

    const list = $('#newslist ul li')
        .toArray()
-        .map((item) => {
-            item = $(item);
+        .map((el) => {
+            const $item = $(el);
+            const $link = $item.find('a');
+            const href = $link.attr('href');
+            if (!href) {
+                return null;
+            }
            return {
-                title: item.find('a').text(),
-                link: new URL(item.find('a').attr('href'), host).href,
-                pubDate: timezone(parseDate(item.find('span').text(), 'YYYY-MM-DD'), 8),
+                title: $link.text().trim(),
+                link: new URL(href, pageUrl).href,
+                pubDate: parsePubDate($item.find('span').text()),
            };
-        });
+        })
+        .filter((item) => item !== null);

-    const out = await Promise.all(
-        list.map((item) =>
-            cache.tryGet(item.link, async () => {
-                if (item.link && !item.link.startsWith('https://library.gxmzu.edu.cn/')) {
-                    item.description = '该通知无法直接预览，请点击原文链接↑查看';
-                    return item;
-                }
-
-                const response = await ofetch(item.link);
-                if (!response || (response.status >= 300 && response.status < 400)) {
-                    item.description = '该通知无法直接预览，请点击原文链接↑查看';
-                } else {
-                    const $ = load(response);
-                    item.title = $('h2').text();
-                    item.description = $('.v_news_content').html();
-                }
-                return item;
-            })
-        )
-    );
+    const items = await resolveArticles(list, pageUrl, {
+        title: 'h2',
+        content: '.v_news_content',
+    });

    return {
        title: '广西民族大学图书馆 -- 最新消息',
-        link: url,
-        item: out,
+        link: pageUrl,
+        item: items,
    };
 }
@@ -2,6 +2,6 @@ import type { Namespace } from '@/types';

 export const namespace: Namespace = {
    name: '广西民族大学',
-    url: 'ai.gxmzu.edu.cn',
+    url: 'www.gxmzu.edu.cn',
    lang: 'zh-CN',
 };
@@ -1,72 +1,99 @@
-import { load } from 'cheerio';
+import { type CheerioAPI, load } from 'cheerio';

+import type { DataItem } from '@/types';
 import cache from '@/utils/cache';
-import ofetch from '@/utils/ofetch'; // 使用ofetch库代替got
+import ofetch from '@/utils/ofetch';
 import { parseDate } from '@/utils/parse-date';
 import timezone from '@/utils/timezone';

-async function getNoticeList(ctx, url, host, titleSelector, dateSelector, contentSelector) {
-    const response = await ofetch(url);
-    if (!response) {
-        return [];
-    }
-    const $ = load(response);
+const FALLBACK_DESCRIPTION = '该通知无法直接预览，请点击原文链接↑查看';

-    const list = $('tr[height=20]')
-        .toArray()
-        .map((item) => {
-            item = $(item);
-            return {
-                title: item.find(titleSelector).attr('title'),
-                link: new URL(item.find(titleSelector).attr('href'), host).href,
-                pubDate: timezone(parseDate(item.find(dateSelector).text().trim(), 'YYYY-MM-DD'), 8),
-            };
-        });
-
-    const out = await Promise.all(
-        list.map((item) =>
-            cache.tryGet(item.link, async () => {
-                if (item.link.includes('.jsp')) {
-                    // 特殊处理.jsp文件，直接显示消息而不尝试爬取
-                    return {
-                        ...item,
-                        description: '该通知无法直接预览，请点击原文链接↑查看',
-                    };
-                }
-                const response = await ofetch(item.link);
-                if (!response || (response.status >= 300 && response.status < 400)) {
-                    item.description = '该通知无法直接预览，请点击原文链接↑查看';
-                } else {
-                    const $ = load(response);
-
-                    item.title = $(contentSelector.title).text();
-                    const hasEmbeddedPDFScript = $('script:contains("showVsbpdfIframe")').length > 0;
-
-                    if (hasEmbeddedPDFScript) {
-                        item.description = '该通知无法直接预览，请点击原文链接↑查看';
-                    } else {
-                        const $content = load($(contentSelector.content).html());
-                        $content('a').each((_, el) => {
-                            const a = $(el);
-                            const href = a.attr('href');
-                            if (href && !href.startsWith('http')) {
-                                a.attr('href', new URL(href, host).href);
-                            }
-                        });
-                        item.description = $content.html();
-                    }
-                    const preDate = $(contentSelector.date)
-                        .text()
-                        .replaceAll(/年|月/g, '-')
-                        .replaceAll('日', '');
-                    item.pubDate = timezone(parseDate(preDate), 8);
-                }
-                return item;
-            })
-        )
-    );
-
-    return out;
+interface NoticeItem extends DataItem {
+    link: string;
 }

-export { getNoticeList };
+interface DetailSelectors {
+    title: string;
+    content: string;
+    date?: string;
+}
+
+// Date formats vary across sites: 2026-05-28, 2026/06/02 or 2026年05月28日 14:53, often prefixed with a label such as "发布日期："
+export function parsePubDate(text?: string): Date | undefined {
+    const match = text?.match(/(\d{4})[-/.年]\s*(\d{1,2})[-/.月]\s*(\d{1,2})/);
+    if (!match) {
+        return undefined;
+    }
+    const [, year, month, day] = match;
+    const time = text?.match(/(\d{1,2}:\d{2}(?::\d{2})?)/)?.[1];
+    return timezone(parseDate(`${year}-${month.padStart(2, '0')}-${day.padStart(2, '0')}${time ? ` ${time}` : ''}`), 8);
+}
+
+export function parseNoticeList($: CheerioAPI, pageUrl: string, rowSelector: string, dateSelector: string): NoticeItem[] {
+    return $(rowSelector)
+        .toArray()
+        .map((el) => {
+            const $row = $(el);
+            const $link = $row.find('a');
+            const href = $link.attr('href');
+            if (!href) {
+                return null;
+            }
+            return {
+                title: $link.attr('title') || $link.text().trim(),
+                link: new URL(href, pageUrl).href,
+                pubDate: parsePubDate($(dateSelector, $row).text()),
+            };
+        })
+        .filter((item) => item !== null);
+}
+
+async function fetchArticle(item: NoticeItem, selectors: DetailSelectors): Promise<DataItem> {
+    const response = await ofetch(item.link);
+    const $ = load(response);
+
+    // Pages whose body is an embedded PDF have no extractable content
+    if ($('script:contains("showVsbpdfIframe")').length > 0) {
+        return { ...item, description: FALLBACK_DESCRIPTION };
+    }
+
+    const $content = $(selectors.content);
+
+    $content.find('a').each((_, el) => {
+        const $a = $(el);
+        const href = $a.attr('href');
+        if (href) {
+            $a.attr('href', new URL(href, item.link).href);
+        }
+    });
+    $content.find('img').each((_, el) => {
+        const $img = $(el);
+        const src = $img.attr('src');
+        if (src) {
+            $img.attr('src', new URL(src, item.link).href);
+        }
+    });
+
+    const title = $(selectors.title).text().trim();
+    const pubDate = selectors.date ? parsePubDate($(selectors.date).text()) : undefined;
+
+    return {
+        ...item,
+        title: title || item.title,
+        pubDate: pubDate ?? item.pubDate,
+        description: $content.html() ?? item.description,
+    };
+}
+
+// Content of off-site links (e.g. WeChat posts or sibling-subdomain sites) is not fetched
+export function resolveArticles(list: NoticeItem[], pageUrl: string, selectors: DetailSelectors): Promise<DataItem[]> {
+    const pageHost = new URL(pageUrl).host;
+    return Promise.all(
+        list.map((item) => {
+            if (new URL(item.link).host !== pageHost) {
+                return { ...item, description: FALLBACK_DESCRIPTION };
+            }
+            return cache.tryGet(item.link, () => fetchArticle(item, selectors)) as Promise<DataItem>;
+        })
+    );
+}
@@ -1,9 +1,11 @@
+import { load } from 'cheerio';
+
 import type { Route } from '@/types';
+import ofetch from '@/utils/ofetch';

-import { getNoticeList } from './utils';
+import { parseNoticeList, resolveArticles } from './utils';

-const url = 'https://yjs.gxmzu.edu.cn/tzgg/zsgg.htm';
-const host = 'https://yjs.gxmzu.edu.cn';
+const pageUrl = 'https://yjs.gxmzu.edu.cn/tzgg/zsgg.htm';

 export const route: Route = {
    path: '/yjszsgg',
@@ -13,7 +15,7 @@ export const route: Route = {
    features: {
        requireConfig: false,
        requirePuppeteer: false,
-        antiCrawler: true,
+        antiCrawler: false,
        supportBT: false,
        supportPodcast: false,
        supportScihub: false,
@@ -29,8 +31,13 @@ export const route: Route = {
    url: 'yjs.gxmzu.edu.cn/tzgg/zsgg.htm',
 };

-async function handler(ctx) {
-    const out = await getNoticeList(ctx, url, host, 'a', '.timestyle55267', {
+async function handler() {
+    const response = await ofetch(pageUrl);
+    const $ = load(response);
+
+    // The graduate school shares the same Boda CMS template with the AI college, so the list and article style IDs are identical
+    const list = parseNoticeList($, pageUrl, 'table.winstyle55267 tr[height="20"]', '.timestyle55267');
+    const items = await resolveArticles(list, pageUrl, {
        title: '.titlestyle55269',
        content: '#vsb_newscontent',
        date: '.timestyle55269',
@@ -38,7 +45,7 @@ async function handler(ctx) {

    return {
        title: '广西民族大学研究生院 -- 招生公告',
-        link: url,
-        item: out,
+        link: pageUrl,
+        item: items,
    };
 }
@@ -1,9 +1,11 @@
+import { load } from 'cheerio';
+
 import type { Route } from '@/types';
+import ofetch from '@/utils/ofetch';

-import { getItems } from './utils';
+import { parseNoticeList, resolveArticles } from './utils';

-const url = 'https://www.jou.edu.cn/index/tzgg.htm';
-const host = 'https://www.jou.edu.cn';
+const pageUrl = 'https://www.jou.edu.cn/index/tzgg.htm';

 export const route: Route = {
    path: '/tzgg',
@@ -29,16 +31,20 @@ export const route: Route = {
    url: 'www.jou.edu.cn/index/tzgg.htm',
 };

-async function handler(ctx) {
-    const out = await getItems(ctx, url, host, 'winstyle106390', 'timestyle106390', 'titlestyle106402', 'timestyle106402');
+async function handler() {
+    const response = await ofetch(pageUrl);
+    const $ = load(response);
+
+    const list = parseNoticeList($, pageUrl, 'table.winstyle106390 tr[height="20"]', '.timestyle106390');
+    const items = await resolveArticles(list, {
+        title: '.titlestyle106402',
+        content: '.v_news_content',
+        date: '.timestyle106402',
+    });

-    // 生成RSS源
    return {
-        // 项目标题
        title: '江苏海洋大学 -- 通知公告',
-        // 项目链接
-        link: url,
-        // items的内容
-        item: out,
+        link: pageUrl,
+        item: items,
    };
 }
@@ -1,70 +1,90 @@
-import { load } from 'cheerio';
+import { type CheerioAPI, load } from 'cheerio';

+import type { DataItem } from '@/types';
 import cache from '@/utils/cache';
-import ofetch from '@/utils/ofetch'; // 使用ofetch库
+import ofetch from '@/utils/ofetch';
 import { parseDate } from '@/utils/parse-date';
 import timezone from '@/utils/timezone';

-async function getItems(ctx, url, host, tableClass, timeStyleClass1, titleStyleClass, timeStyleClass2) {
-    const response = await ofetch(url);
-    if (!response) {
-        return [];
-    }
-    const $ = load(response);
+const FALLBACK_DESCRIPTION = '该通知无法直接预览，请点击原文链接↑查看';

-    const list = $(`table.${tableClass} > tbody > tr[height=20]`)
-        .toArray()
-        .map((item) => {
-            const currentItem = $(item);
-            const item1 = currentItem.find('td:eq(1)');
-            const item2 = currentItem.find('td:eq(2)');
-            const link = new URL(item1.find('a').attr('href'), host).href;
-
-            return {
-                title: item1.find('a').attr('title'),
-                link,
-                pubDate: timezone(parseDate(item2.find(`.${timeStyleClass1}`).text(), 'YYYY-MM-DD'), 8),
-            };
-        });
-
-    const out = await Promise.all(
-        list.map((item) =>
-            cache.tryGet(item.link, async () => {
-                const response = await ofetch(item.link);
-                if (!response || (response.status >= 300 && response.status < 400)) {
-                    // 响应为空或状态码表明发生了重定向
-                    return {
-                        ...item,
-                        description: '该通知无法直接预览，请点击原文链接↑查看',
-                    };
-                }
-                const $ = load(response);
-
-                item.title = $(`.${titleStyleClass}`).text();
-                const hasEmbeddedPDFScript = $('script:contains("showVsbpdfIframe")').length > 0;
-
-                if (hasEmbeddedPDFScript) {
-                    item.description = '该通知无法直接预览，请点击原文链接↑查看';
-                } else {
-                    const contentHtml = $('.v_news_content').html();
-                    const $content = load(contentHtml);
-                    $content('a').each((_, el) => {
-                        const a = $(el);
-                        const href = a.attr('href');
-                        if (href && !href.startsWith('http')) {
-                            a.attr('href', new URL(href, host).href);
-                        }
-                    });
-                    item.description = $content.html();
-                }
-                item.pubDate = timezone(parseDate($(`.${timeStyleClass2}`).text().replace('发布时间：', '')), 8);
-
-                return item;
-            })
-        )
-    );
-
-    return out;
+interface NoticeItem extends DataItem {
+    link: string;
 }

-export { getItems };
+interface DetailSelectors {
+    title: string;
+    content: string;
+    date?: string;
+}
+
+// Date formats vary across sites: 2026-03-30, 2026/05/06 or 2026年03月30日 14:37, often prefixed with a label such as "发布时间："
+export function parsePubDate(text?: string): Date | undefined {
+    const match = text?.match(/(\d{4})[-/.年]\s*(\d{1,2})[-/.月]\s*(\d{1,2})/);
+    if (!match) {
+        return undefined;
+    }
+    const [, year, month, day] = match;
+    const time = text?.match(/(\d{1,2}:\d{2}(?::\d{2})?)/)?.[1];
+    return timezone(parseDate(`${year}-${month.padStart(2, '0')}-${day.padStart(2, '0')}${time ? ` ${time}` : ''}`), 8);
+}
+
+export function parseNoticeList($: CheerioAPI, pageUrl: string, rowSelector: string, dateSelector: string): NoticeItem[] {
+    return $(rowSelector)
+        .toArray()
+        .map((el) => {
+            const $row = $(el);
+            const $link = $row.find('a');
+            const href = $link.attr('href');
+            if (!href) {
+                return null;
+            }
+            return {
+                title: $link.attr('title') || $link.text().trim(),
+                link: new URL(href, pageUrl).href,
+                pubDate: parsePubDate($(dateSelector, $row).text()),
+            };
+        })
+        .filter((item) => item !== null);
+}
+
+async function fetchArticle(item: NoticeItem, selectors: DetailSelectors): Promise<DataItem> {
+    const response = await ofetch(item.link);
+    const $ = load(response);
+
+    // Pages whose body is an embedded PDF have no extractable content
+    if ($('script:contains("showVsbpdfIframe")').length > 0) {
+        return { ...item, description: FALLBACK_DESCRIPTION };
+    }
+
+    const $content = $(selectors.content);
+
+    $content.find('a').each((_, el) => {
+        const $a = $(el);
+        const href = $a.attr('href');
+        if (href) {
+            $a.attr('href', new URL(href, item.link).href);
+        }
+    });
+    $content.find('img').each((_, el) => {
+        const $img = $(el);
+        const src = $img.attr('src');
+        if (src) {
+            $img.attr('src', new URL(src, item.link).href);
+        }
+    });
+
+    const title = $(selectors.title).text().trim();
+    const pubDate = selectors.date ? parsePubDate($(selectors.date).text()) : undefined;
+
+    return {
+        ...item,
+        title: title || item.title,
+        pubDate: pubDate ?? item.pubDate,
+        description: $content.html() ?? item.description,
+    };
+}
+
+export function resolveArticles(list: NoticeItem[], selectors: DetailSelectors): Promise<DataItem[]> {
+    return Promise.all(list.map((item) => cache.tryGet(item.link, () => fetchArticle(item, selectors)) as Promise<DataItem>));
+}
@@ -1,9 +1,11 @@
+import { load } from 'cheerio';
+
 import type { Route } from '@/types';
+import ofetch from '@/utils/ofetch';

-import { getItems } from './utils';
+import { parseNoticeList, resolveArticles } from './utils';

-const url = 'https://yz.jou.edu.cn/index/zxgg.htm';
-const host = 'https://yz.jou.edu.cn';
+const pageUrl = 'https://yz.jou.edu.cn/index/zxgg.htm';

 export const route: Route = {
    path: '/yztzgg',
@@ -29,16 +31,20 @@ export const route: Route = {
    url: 'yz.jou.edu.cn/index/zxgg.htm',
 };

-async function handler(ctx) {
-    const out = await getItems(ctx, url, host, 'winstyle207638', 'timestyle207638', 'titlestyle207543', 'timestyle207543');
+async function handler() {
+    const response = await ofetch(pageUrl);
+    const $ = load(response);
+
+    const list = parseNoticeList($, pageUrl, 'table.winstyle207638 tr[height="20"]', '.timestyle207638');
+    const items = await resolveArticles(list, {
+        title: '.titlestyle207543',
+        content: '.v_news_content',
+        date: '.timestyle207543',
+    });

-    // 生成RSS源
    return {
-        // 项目标题
        title: '江苏海洋大学 -- 研招通知公告',
-        // 项目链接
-        link: url,
-        // items的内容
-        item: out,
+        link: pageUrl,
+        item: items,
    };
 }
@@ -1,9 +1,11 @@
+import { load } from 'cheerio';
+
 import type { Route } from '@/types';
+import ofetch from '@/utils/ofetch';

-import { getNoticeList } from './utils';
+import { parsePubDate, resolveArticles } from './utils';

-const url = 'https://www.njxzc.edu.cn/89/list.htm';
-const host = 'https://www.njxzc.edu.cn';
+const pageUrl = 'https://www.njxzc.edu.cn/89/list.htm';

 export const route: Route = {
    path: '/tzgg',
@@ -13,7 +15,7 @@ export const route: Route = {
    features: {
        requireConfig: false,
        requirePuppeteer: false,
-        antiCrawler: true,
+        antiCrawler: false,
        supportBT: false,
        supportPodcast: false,
        supportScihub: false,
@@ -29,24 +31,30 @@ export const route: Route = {
    url: 'www.njxzc.edu.cn/89/list.htm',
 };

-async function handler(ctx) {
-    const out = await getNoticeList(
-        ctx,
-        url,
-        host,
-        'a',
-        '.news_meta',
-        {
-            title: '.arti_title',
-            content: '.wp_articlecontent',
-            date: '.arti_update',
-        },
-        '.news_list .news'
-    );
+async function handler() {
+    const response = await ofetch(pageUrl);
+    const $ = load(response);
+
+    const list = $('.news_list .news')
+        .toArray()
+        .map((el) => {
+            const $item = $(el);
+            const $link = $item.find('a');
+            const href = $link.attr('href');
+            if (!href) {
+                return null;
+            }
+            return {
+                title: $link.attr('title') || $link.text().trim(),
+                link: new URL(href, pageUrl).href,
+                pubDate: parsePubDate($item.find('.news_meta').text()),
+            };
+        })
+        .filter((item) => item !== null);

    return {
        title: '南京晓庄学院 -- 通知公告',
-        link: url,
-        item: out,
+        link: pageUrl,
+        item: await resolveArticles(list),
    };
 }
@@ -1,13 +1,11 @@
 import { load } from 'cheerio';

 import type { Route } from '@/types';
-import cache from '@/utils/cache';
 import ofetch from '@/utils/ofetch';
-import { parseDate } from '@/utils/parse-date';
-import timezone from '@/utils/timezone';

-const url = 'https://lib.njxzc.edu.cn/pxyhd/list.htm';
-const host = 'https://lib.njxzc.edu.cn';
+import { parsePubDate, resolveArticles } from './utils';
+
+const pageUrl = 'https://lib.njxzc.edu.cn/pxyhd/list.htm';

 export const route: Route = {
    path: '/libtzgg',
@@ -17,7 +15,7 @@ export const route: Route = {
    features: {
        requireConfig: false,
        requirePuppeteer: false,
-        antiCrawler: true,
+        antiCrawler: false,
        supportBT: false,
        supportPodcast: false,
        supportScihub: false,
@@ -34,76 +32,30 @@ export const route: Route = {
 };

 async function handler() {
-    const response = await ofetch(url);
-    if (!response) {
-        return {
-            title: '南京晓庄学院 -- 图书馆通知公告',
-            link: url,
-            item: [],
-        };
-    }
+    const response = await ofetch(pageUrl);
    const $ = load(response);

    const list = $('a.btt-2')
        .toArray()
-        .map((item) => {
-            const $item = $(item);
-            const href = $item.attr('href') || '';
-            const link = href.startsWith('http') ? href : new URL(href, host).href;
-            const day = $item.find('.tm-1').text().trim();
-            const yearMonth = $item.find('.tm-2').text().trim();
-            const dateStr = `${yearMonth}-${day}`;
+        .map((el) => {
+            const $link = $(el);
+            const href = $link.attr('href');
+            if (!href) {
+                return null;
+            }
+            const day = $link.find('.tm-1').text().trim();
+            const yearMonth = $link.find('.tm-2').text().trim();
            return {
-                title: $item.find('.btt-4').text().trim(),
-                link,
-                pubDate: timezone(parseDate(dateStr, 'YYYY-MM-DD'), 8),
+                title: $link.find('.btt-4').text().trim(),
+                link: new URL(href, pageUrl).href,
+                pubDate: parsePubDate(`${yearMonth}-${day}`),
            };
-        });
-
-    const out = await Promise.all(
-        list.map((item) =>
-            cache.tryGet(item.link, async () => {
-                const response = await ofetch(item.link);
-                const $ = load(response);
-
-                if ($('.wp_error_msg').length > 0) {
-                    item.description = '您当前ip并非校内地址，该信息仅允许校内地址访问';
-                } else {
-                    const $content = $('.wp_articlecontent');
-                    // Convert wp_pdf_player iframes to download links
-                    $content.find('.wp_pdf_player').each((_, el) => {
-                        const $iframe = $(el);
-                        const pdfSrc = $iframe.attr('pdfsrc') || '';
-                        const pdfUrl = pdfSrc.startsWith('http') ? pdfSrc : new URL(pdfSrc, host).href;
-                        $iframe.replaceWith(`<p><a href="${pdfUrl}">附件下载</a></p>`);
-                    });
-                    // Fix relative URLs
-                    $content.find('a').each((_, el) => {
-                        const $a = $(el);
-                        const href = $a.attr('href');
-                        if (href && !href.startsWith('http')) {
-                            $a.attr('href', new URL(href, host).href);
-                        }
-                    });
-                    item.description = $content.html() || '';
-                    const title = $('.arti_title').text().trim();
-                    if (title) {
-                        item.title = title;
-                    }
-                    const dateText = $('.arti_update').text().replace('发布时间：', '').trim();
-                    if (dateText) {
-                        item.pubDate = timezone(parseDate(dateText, 'YYYY-MM-DD'), 8);
-                    }
-                }
-
-                return item;
-            })
-        )
-    );
+        })
+        .filter((item) => item !== null);

    return {
        title: '南京晓庄学院 -- 图书馆通知公告',
-        link: url,
-        item: out,
+        link: pageUrl,
+        item: await resolveArticles(list),
    };
 }
@@ -2,6 +2,7 @@ import type { Namespace } from '@/types';

 export const namespace: Namespace = {
    name: '南京晓庄学院',
-    url: 'lib.njxzc.edu.cn',
+    url: 'www.njxzc.edu.cn',
+    description: '部分文章仅限校内 IP 访问，此类文章仅输出标题与原文链接',
    lang: 'zh-CN',
 };
@@ -1,67 +1,67 @@
 import { load } from 'cheerio';

+import type { DataItem } from '@/types';
 import cache from '@/utils/cache';
-import ofetch from '@/utils/ofetch'; // 使用默认导出的方式导入ofetch
+import ofetch from '@/utils/ofetch';
 import { parseDate } from '@/utils/parse-date';
 import timezone from '@/utils/timezone';

-async function getNoticeList(ctx, url, host, titleSelector, dateSelector, contentSelector, listSelector) {
-    const response = await ofetch(url);
-    if (!response) {
-        return [];
-    }
-    const $ = load(response);
-
-    const list = $(listSelector)
-        .toArray()
-        .map((item) => {
-            item = $(item);
-            const href = item.find(titleSelector).attr('href') || '';
-            const link = href.startsWith('http') ? href : new URL(href, host).href;
-            return {
-                title: item.find(titleSelector).attr('title'),
-                link,
-                pubDate: timezone(parseDate(item.find(dateSelector).text(), 'YYYY-MM-DD'), 8),
-            };
-        });
-
-    const out = await Promise.all(
-        list.map((item) =>
-            cache.tryGet(item.link, async () => {
-                const response = await ofetch(item.link);
-                const $ = load(response);
-
-                if ($('.wp_error_msg').length > 0) {
-                    item.description = '您当前ip并非校内地址，该信息仅允许校内地址访问';
-                } else {
-                    const $content = $(contentSelector.content);
-                    // Convert wp_pdf_player iframes to download links
-                    $content.find('.wp_pdf_player').each((_, el) => {
-                        const $iframe = $(el);
-                        const pdfSrc = $iframe.attr('pdfsrc') || '';
-                        const pdfUrl = pdfSrc.startsWith('http') ? pdfSrc : new URL(pdfSrc, host).href;
-                        $iframe.replaceWith(`<p><a href="${pdfUrl}">附件下载</a></p>`);
-                    });
-                    // Fix relative URLs
-                    $content.find('a').each((_, el) => {
-                        const $a = $(el);
-                        const href = $a.attr('href');
-                        if (href && !href.startsWith('http')) {
-                            $a.attr('href', new URL(href, host).href);
-                        }
-                    });
-                    item.description = $content.html() || '';
-                    item.title = $(contentSelector.title).text();
-                    const dateText = $(contentSelector.date).text().replace('编辑：', '').replace('发布日期：', '').replace('发布时间：', '');
-                    item.pubDate = timezone(parseDate(dateText, 'YYYY-MM-DD'), 8);
-                }
-
-                return item;
-            })
-        )
-    );
-
-    return out;
+interface NoticeItem extends DataItem {
+    link: string;
 }

-export { getNoticeList };
+// Date formats vary across the site: 2026-07-01, 2026/07/01 or 2026年07月01日 14:53, often prefixed with a label such as "发布时间："
+export function parsePubDate(text?: string): Date | undefined {
+    const match = text?.match(/(\d{4})[-/.年]\s*(\d{1,2})[-/.月]\s*(\d{1,2})/);
+    if (!match) {
+        return undefined;
+    }
+    const [, year, month, day] = match;
+    const time = text?.match(/(\d{1,2}:\d{2}(?::\d{2})?)/)?.[1];
+    return timezone(parseDate(`${year}-${month.padStart(2, '0')}-${day.padStart(2, '0')}${time ? ` ${time}` : ''}`), 8);
+}
+
+async function fetchArticle(item: NoticeItem): Promise<DataItem> {
+    const response = await ofetch(item.link);
+    const $ = load(response);
+
+    const $content = $('.wp_articlecontent');
+
+    $content.find('.wp_pdf_player').each((_, el) => {
+        const $player = $(el);
+        const pdfSrc = $player.attr('pdfsrc');
+        if (pdfSrc) {
+            $player.replaceWith(`<p><a href="${new URL(pdfSrc, item.link).href}">附件下载</a></p>`);
+        } else {
+            $player.remove();
+        }
+    });
+    $content.find('a').each((_, el) => {
+        const $a = $(el);
+        const href = $a.attr('href');
+        if (href) {
+            $a.attr('href', new URL(href, item.link).href);
+        }
+    });
+    $content.find('img').each((_, el) => {
+        const $img = $(el);
+        const src = $img.attr('src');
+        if (src) {
+            $img.attr('src', new URL(src, item.link).href);
+        }
+    });
+
+    const title = $('.arti_title').text().trim();
+    const pubDate = parsePubDate($('.arti_update').text());
+
+    return {
+        ...item,
+        title: title || item.title,
+        pubDate: pubDate ?? item.pubDate,
+        description: $content.html() ?? item.description,
+    };
+}
+
+export function resolveArticles(list: NoticeItem[]): Promise<DataItem[]> {
+    return Promise.all(list.map((item) => cache.tryGet(item.link, () => fetchArticle(item)) as Promise<DataItem>));
+}