fix njupt posts with url redirections (#8961)

* fix njupt posts with url redirections

skip posts that are redirected to error pages due to access control

* fix: migrate to v2

* fix: pubDate depreciated url.resolve

Co-authored-by: TonyRL <TonyRL@users.noreply.github.com>

lib/router.js

@@ -607,9 +607,6 @@ router.get('/ustc/job/:category?', lazyloadRouteHandler('./routes/universities/u
 // UTdallas ISSO
 router.get('/utdallas/isso', lazyloadRouteHandler('./routes/universities/utdallas/isso'));
 
-// 南京邮电大学
-router.get('/njupt/jwc/:type?', lazyloadRouteHandler('./routes/universities/njupt/jwc'));
-
 // 南昌航空大学
 router.get('/nchu/jwc/:type?', lazyloadRouteHandler('./routes/universities/nchu/jwc'));
 

lib/routes/universities/njupt/jwc.js

@@ -1,84 +0,0 @@
-const got = require('@/utils/got');
-const cheerio = require('cheerio');
-const url = require('url');
-
-const host = 'http://jwc.njupt.edu.cn';
-
-const map = {
-    notice: '/1594',
-    news: '/1596',
-};
-
-module.exports = async (ctx) => {
-    const type = ctx.params.type || 'notice';
-    const link = host + map[type] + '/list.htm';
-    const response = await got({
-        method: 'get',
-        url: link,
-        headers: {
-            Referer: host,
-        },
-    });
-    const $ = cheerio.load(response.data);
-
-    const urlList = $('.content')
-        .find('a')
-        .slice(0, 10)
-        .map((i, e) => $(e).attr('href'))
-        .get();
-
-    const titleList = $('.content')
-        .find('a')
-        .slice(0, 10)
-        .map((i, e) => $(e).attr('title'))
-        .get();
-
-    const dateList = $('.content tr')
-        .find('div')
-        .slice(0, 10)
-        .map((i, e) => $(e).text().replace('发布时间：', ''))
-        .get();
-
-    const out = await Promise.all(
-        urlList.map(async (itemUrl, index) => {
-            itemUrl = url.resolve(host, itemUrl);
-            if (itemUrl.indexOf('.htm') !== -1) {
-                const cache = await ctx.cache.get(itemUrl);
-                if (cache) {
-                    return Promise.resolve(JSON.parse(cache));
-                }
-                const response = await got.get(itemUrl);
-                const $ = cheerio.load(response.data);
-                const single = {
-                    title: $('.Article_Title').text(),
-                    link: itemUrl,
-                    description: $('.wp_articlecontent')
-                        .html()
-                        .replace(/src="\//g, `src="${url.resolve(host, '.')}`)
-                        .replace(/href="\//g, `href="${url.resolve(host, '.')}`)
-                        .trim(),
-                    pubDate: new Date($('.Article_PublishDate').text().replace('发布时间：', '')).toUTCString(),
-                };
-                ctx.cache.set(itemUrl, JSON.stringify(single));
-                return Promise.resolve(single);
-            } else {
-                const single = {
-                    title: titleList[index],
-                    link: itemUrl,
-                    description: '该通知为文件，请点击原文链接↑下载',
-                    pubDate: new Date(dateList[index]).toUTCString(),
-                };
-                return Promise.resolve(single);
-            }
-        })
-    );
-    let info = '通知公告';
-    if (type === 'news') {
-        info = '教务快讯';
-    }
-    ctx.state.data = {
-        title: '南京邮电大学 -- ' + info,
-        link,
-        item: out,
-    };
-};

lib/v2/njupt/jwc.js

@@ -0,0 +1,90 @@
+const got = require('@/utils/got');
+const cheerio = require('cheerio');
+const { parseDate } = require('@/utils/parse-date');
+
+const host = 'https://jwc.njupt.edu.cn';
+
+const map = {
+    notice: '/1594',
+    news: '/1596',
+};
+
+module.exports = async (ctx) => {
+    const type = ctx.params.type ?? 'notice';
+    const link = host + map[type] + '/list.htm';
+    const response = await got({
+        method: 'get',
+        url: link,
+        headers: {
+            Referer: host,
+        },
+    });
+    const $ = cheerio.load(response.data);
+
+    const urlList = $('.content')
+        .find('a')
+        .slice(0, 10)
+        .map((i, e) => $(e).attr('href'))
+        .get();
+
+    const titleList = $('.content')
+        .find('a')
+        .slice(0, 10)
+        .map((i, e) => $(e).attr('title'))
+        .get();
+
+    const dateList = $('.content tr')
+        .find('div')
+        .slice(0, 10)
+        .map((i, e) => $(e).text().replace('发布时间：', ''))
+        .get();
+
+    const out = await Promise.all(
+        urlList.map((itemUrl, index) => {
+            itemUrl = new URL(itemUrl, host).href;
+            if (itemUrl.indexOf('.htm') !== -1) {
+                return ctx.cache.tryGet(itemUrl, async () => {
+                    const response = await got.get(itemUrl);
+                    if (response.redirectUrls.length !== 0) {
+                        const single = {
+                            title: titleList[index],
+                            link: itemUrl,
+                            description: '该通知无法直接预览, 请点击原文链接↑查看',
+                            pubDate: parseDate(dateList[index]),
+                        };
+                        return single;
+                    }
+                    const $ = cheerio.load(response.data);
+                    const single = {
+                        title: $('.Article_Title').text(),
+                        link: itemUrl,
+                        description: $('.wp_articlecontent')
+                            .html()
+                            .replace(/src="\//g, `src="${new URL('.', host).href}`)
+                            .replace(/href="\//g, `href="${new URL('.', host).href}`)
+                            .trim(),
+                        pubDate: parseDate($('.Article_PublishDate').text().replace('发布时间：', '')),
+                    };
+                    return single;
+                });
+            } else {
+                const single = {
+                    title: titleList[index],
+                    link: itemUrl,
+                    description: '该通知为文件，请点击原文链接↑下载',
+                    pubDate: parseDate(dateList[index]),
+                };
+                return single;
+            }
+        })
+    );
+    let info = '通知公告';
+    if (type === 'news') {
+        info = '教务快讯';
+    }
+    ctx.state.data = {
+        title: '南京邮电大学 -- ' + info,
+        link,
+        item: out,
+    };
+};

lib/v2/njupt/maintainer.js

@@ -0,0 +1,3 @@
+module.exports = {
+    '/jwc/:type?': ['shaoye'],
+};

lib/v2/njupt/radar.js

@@ -0,0 +1,20 @@
+module.exports = {
+    'njupt.edu.cn': {
+        _name: '南京邮电大学',
+        jwc: [
+            {
+                title: '教务处通知与新闻',
+                docs: 'https://docs.rsshub.app/university.html#nan-jing-you-dian-da-xue',
+                source: '/*/list.htm',
+                target: (_params, url) => {
+                    url = new URL(url);
+                    if (url.pathname.indexOf('/1594') !== -1) {
+                        return '/njupt/notice';
+                    } else if (url.pathname.indexOf('/1596') !== -1) {
+                        return '/njupt/news';
+                    }
+                },
+            },
+        ],
+    },
+};

lib/v2/njupt/router.js

@@ -0,0 +1,3 @@
+module.exports = (router) => {
+    router.get('/jwc/:type?', require('./jwc'));
+};