rsshub 1.0.0-master.f9ec483 → 1.0.0-master.fa04a11

package/lib/routes/shu/index.ts

@@ -1,23 +1,20 @@
 import { Route } from '@/types';
 import cache from '@/utils/cache';
 import got from '@/utils/got';
-import { load } from 'cheerio';
+import { load } from 'cheerio'; // cheerio@1.0.0
 import { parseDate } from '@/utils/parse-date';
+import timezone from '@/utils/timezone';
 
-const host = 'https://www.shu.edu.cn/';
-const alias = new Map([
-    ['news', 'zhxw'], // 综合新闻
-    ['research', 'kydt1'], // 科研动态
-    ['kydt', 'kydt1'], // 科研动态
-    ['notice', 'tzgg'], // 通知公告
-    ['important', 'zyxw'], // 重要新闻
-]);
+const noticeType = {
+    tzgg: { title: '上海大学 - 通知公告', url: 'https://www.shu.edu.cn/tzgg.htm' },
+    zyxw: { title: '上海大学 - 重要新闻', url: 'https://www.shu.edu.cn/zyxw.htm' },
+};
 
 export const route: Route = {
-    path: '/:type?',
+    path: '/news/:type?',
     categories: ['university'],
-    example: '/shu/news',
-    parameters: { type: '消息类型,默认为`news`' },
+    example: '/shu/news/tzgg',
+    parameters: { type: '分类，默认为通知公告' },
     features: {
         requireConfig: false,
         requirePuppeteer: false,
@@ -28,50 +25,71 @@ export const route: Route = {
     },
     radar: [
         {
-            source: ['www.shu.edu.cn/:type'],
-            target: '/:type',
+            source: ['www.shu.edu.cn/'],
+            target: '/news',
         },
     ],
-    name: '官网信息',
-    maintainers: ['lonelyion'],
+    name: '官网通知公告',
+    maintainers: ['lonelyion', 'GhhG123'],
     handler,
-    description: `| 综合新闻 | 科研动态 | 通知公告 | 重要新闻  |
-  | -------- | -------- | -------- | --------- |
-  | news     | research | notice   | important |`,
+    url: 'www.shu.edu.cn/',
+    description: `| 通知公告 | 重要新闻 |
+  | -------- | --------- |
+  | tzgg     | zyxw      |`,
 };
 
 async function handler(ctx) {
-    const type = ctx.req.param('type') || 'news';
-    const link = `https://www.shu.edu.cn/${alias.get(type) || type}.htm`;
-    const respond = await got.get(link);
-    const $ = load(respond.data);
-    const title = $('title').text();
-    const list = $('.ej_main .list')
-        .find('li')
-        .slice(0, 5)
+    const type = ctx.req.param('type') ?? 'tzgg';
+    const rootUrl = 'https://www.shu.edu.cn';
+
+    // 发起 HTTP GET 请求
+    const response = await got({
+        method: 'get',
+
+        /* headers: {
+            'user-agent': UA,
+            cookie: await getCookie(ctx),
+        }, */
+        url: noticeType[type].url,
+    });
+
+    const $ = load(response.data);
+
+    const list = $('div.list ul li') // 以下获取信息需要根据网页结构定制
+        // For cheerio 1.x.x . The item parameter in the .map callback is now explicitly typed as a Cheerio<Element>, not just Element. --fixed
         .toArray()
-        .map((ele) => ({
-            title: $(ele).find('.bt').text(),
-            link: new URL($(ele).find('a').attr('href'), host).href,
-            date: $(ele).find('.sj').text(),
-        }));
+        .map((el) => {
+            const item = $(el); // Wrap `el` in a Cheerio object
+            const rawLink = item.find('a').attr('href');
+            return {
+                title: item.find('p.bt').text().trim(),
+                link: rawLink ? new URL(rawLink, rootUrl).href : rootUrl,
+                pubDate: timezone(parseDate(item.find('p.sj').text().trim(), 'YYYY.MM.DD'), +8),
+                description: item.find('p.zy').text().trim(),
+            };
+        });
 
-    const all = await Promise.all(
+    const items = await Promise.all(
         list.map((item) =>
             cache.tryGet(item.link, async () => {
-                const response = await got.get(item.link);
-                const $ = load(response.data);
-                item.author = $('.xx>:nth-child(2)').text().trim().slice(3); // 投稿：xxx
-                item.pubDate = parseDate(item.date, 'YYYY.MM.DD');
-                item.description = $('.v_news_content').html() || item.title;
+                const detailResponse = await got({
+                    method: 'get',
+                    url: item.link,
+                });
+                const content = load(detailResponse.data);
+
+                item.description = content('#vsb_content .v_news_content').html() || item.description;
+
                 return item;
             })
         )
     );
 
     return {
-        title,
-        link,
-        item: all,
+        title: noticeType[type].title,
+        description: noticeType[type].title,
+        link: noticeType[type].url,
+        image: 'https://www.shu.edu.cn/__local/0/08/C6/1EABE492B0CF228A5564D6E6ABE_779D1EE3_5BF7.png',
+        item: items,
     };
 }

package/lib/routes/shu/jwb.ts

@@ -8,21 +8,21 @@ const host = 'https://jwb.shu.edu.cn/';
 const alias = new Map([
     ['notice', 'tzgg'], // 通知公告
     ['news', 'xw'], // 新闻动态
-    ['policy', 'zcwj'], // 政策文件
+    /* ['policy', 'zcwj'],  政策文件 //BUG */
 ]);
 
 export const route: Route = {
-    path: ['/jwc/:type?', '/jwb/:type?'],
+    path: ['/jwb/:type?'],
     radar: [
         {
-            source: ['www.shu.edu.cn/:type'],
-            target: '/:type',
+            source: ['www.shu.edu.cn/index'],
+            target: '/:type?',
         },
     ],
-    name: 'Unknown',
-    maintainers: [],
+    name: '教务部',
+    maintainers: ['tuxinghuan', 'GhhG123'],
     handler,
-    description: `| 通知通告 | 新闻 | 政策文件 |
+    description: `| 通知通告 | 新闻 | 政策文件(bug) |
   | -------- | ---- | -------- |
   | notice   | news | policy   |`,
 };
@@ -58,6 +58,7 @@ async function handler(ctx) {
     return {
         title,
         link,
+        image: 'https://www.shu.edu.cn/__local/0/08/C6/1EABE492B0CF228A5564D6E6ABE_779D1EE3_5BF7.png',
         item: all,
     };
 }

package/lib/routes/shu/namespace.ts

@@ -2,6 +2,7 @@ import type { Namespace } from '@/types';
 
 export const namespace: Namespace = {
     name: '上海大学',
-    url: 'jwb.shu.edu.cn',
+    url: 'www.shu.edu.cn',
+    description: '上海大学相关网网站',
     lang: 'zh-CN',
 };

package/lib/routes/shu/society.ts

@@ -0,0 +1,62 @@
+import { Route } from '@/types';
+import got from '@/utils/got';
+import { load } from 'cheerio';
+import { parseDate } from '@/utils/parse-date';
+
+export const route: Route = {
+    path: '/journals/society/current',
+    categories: ['journal'],
+    example: '/journals/society/current',
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    name: '《社会》杂志当期目录',
+    maintainers: ['CNYoki'],
+    handler,
+};
+
+async function handler() {
+    const url = 'https://www.society.shu.edu.cn/CN/1004-8804/current.shtml';
+    const response = await got(url);
+    const $ = load(response.body);
+
+    // 提取刊出日期
+    const pubDateText = $('.dqtab .njq')
+        .text()
+        .match(/刊出日期：(\d{4}-\d{2}-\d{2})/);
+    const pubDate = pubDateText ? parseDate(pubDateText[1]) : null;
+
+    const items = $('.wenzhanglanmu')
+        .nextAll('.noselectrow')
+        .toArray()
+        .map((item) => {
+            const $item = $(item);
+            const titles = $item.find('.biaoti').text().trim();
+            const links = $item.find('.biaoti').attr('href');
+            const authors = $item.find('.zuozhe').text().trim();
+            const abstract = $item.find('div[id^="Abstract"]').text().trim();
+
+            if (titles && links) {
+                return {
+                    title: titles,
+                    link: links,
+                    description: abstract,
+                    author: authors,
+                    pubDate,
+                };
+            }
+            return null;
+        })
+        .filter((item) => item !== null);
+
+    return {
+        title: '《社会》当期目录',
+        link: url,
+        item: items,
+    };
+}

package/lib/routes/shu/xykd.ts

@@ -0,0 +1,99 @@
+import { Route } from '@/types';
+import cache from '@/utils/cache';
+import got from '@/utils/got';
+import { load } from 'cheerio'; // cheerio@1.0.0
+import { parseDate } from '@/utils/parse-date';
+import timezone from '@/utils/timezone';
+
+const noticeType = {
+    whxx: { title: '上海大学 - 文化信息', url: 'https://www.shu.edu.cn/xnrc/whxx.htm' },
+    xsbg: { title: '上海大学 - 学术报告', url: 'https://www.shu.edu.cn/xnrc/xsbg.htm' },
+};
+
+export const route: Route = {
+    path: '/xykd/:type?',
+    categories: ['university'],
+    example: '/shu/xykd/xsbg',
+    parameters: { type: '分类，默认为学术公告' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['www.shu.edu.cn/'],
+            target: '/xykd',
+        },
+    ],
+    name: '校园看点',
+    maintainers: ['GhhG123'],
+    handler,
+    url: 'www.shu.edu.cn/',
+    description: `| 文化信息 | 学术报告 |
+  | -------- | --------- |
+  | whxx     | xsbg      |`,
+};
+
+async function handler(ctx) {
+    const type = ctx.req.param('type') ?? 'xsbg';
+    const rootUrl = 'https://www.shu.edu.cn';
+
+    // 发起 HTTP GET 请求
+    const response = await got({
+        method: 'get',
+
+        /* headers: {
+            'user-agent': UA,
+            cookie: await getCookie(ctx),
+        }, */
+        url: noticeType[type].url,
+    });
+
+    const $ = load(response.data);
+
+    const list = $('div.xsbg_list ul li') // 定位到HTML结构中的li元素
+        .toArray()
+        .map((el) => {
+            const item = $(el); // 使用Cheerio包装每个li元素
+            const rawLink = item.find('a').attr('href');
+            const dateParts = item
+                .find('div.sj p')
+                .toArray()
+                .map((p) => $(p).text().trim()); // 提取日期部分
+
+            return {
+                title: item.find('p.bt').text().trim(), // 获取标题
+                link: rawLink ? new URL(rawLink, rootUrl).href : rootUrl, // 生成完整链接
+                pubDate: timezone(parseDate(`${dateParts[1]}-${dateParts[0]}`, 'MM-DD'), +8), // 拼接并解析日期
+                description: item.find('div.zy').text().trim(), // 提取简要描述
+            };
+        });
+
+    const items = await Promise.all(
+        list.map((item) =>
+            cache.tryGet(item.link, async () => {
+                const detailResponse = await got({
+                    method: 'get',
+                    url: item.link,
+                }); // 获取详情页内容
+                const content = load(detailResponse.data); // 使用cheerio解析内容
+
+                item.description = content('#vsb_content_500 .v_news_content').html() || item.description; // 提取内容区详情
+
+                return item; // 返回完整的item
+            })
+        )
+    );
+
+    return {
+        title: noticeType[type].title,
+        description: noticeType[type].title,
+        link: noticeType[type].url,
+        image: 'https://www.shu.edu.cn/__local/0/08/C6/1EABE492B0CF228A5564D6E6ABE_779D1EE3_5BF7.png',
+        item: items,
+    };
+}

package/lib/routes/sicau/jk.ts

@@ -27,7 +27,7 @@ export const route: Route = {
     url: 'jk.sicau.edu.cn',
     description: `
 
-:::tip
+::: tip
 **本校学生**可以直接 POST \`https://jk.sicau.edu.cn/user/login/v1.0.0/snoLogin\` 从返回结果中的 \`token\` 字段拿到个人令牌，记得在url后添加以下**查询参数**：
 
 -   sid: \`f1c97a0e81c24e98adb1ebdadca0699b\`
@@ -36,7 +36,7 @@ export const route: Route = {
 
 :::
 
-:::warning
+::: warning
 由于i川农后台有请求限制，为避免一次性大量请求而被限流，每次只请求结果的第一页数据，即前20条
 :::
 

package/lib/routes/simpleinfo/index.ts

@@ -12,7 +12,7 @@ import { parseDate } from '@/utils/parse-date';
 
 export const route: Route = {
     path: '/:category?',
-    categories: ['new-media'],
+    categories: ['new-media', 'popular'],
     example: '/simpleinfo',
     parameters: { category: '分类名' },
     features: {

package/lib/routes/sina/sports.ts

@@ -6,7 +6,10 @@ import { parseArticle } from './utils';
 
 export const route: Route = {
     path: '/sports/:type?',
-    name: 'Unknown',
+    name: '新浪体育',
+    categories: ['new-media'],
+    example: '/sports',
+    parameters: { type: '类别' },
     maintainers: ['nczitzk'],
     handler,
 };

package/lib/routes/sjtu/jwc.ts

@@ -4,7 +4,7 @@ import got from '@/utils/got';
 import { load } from 'cheerio';
 import { parseDate } from '@/utils/parse-date';
 
-const urlRoot = 'https://jwc.sjtu.edu.cn/xwtg';
+const urlRoot = 'https://jwc.sjtu.edu.cn';
 
 async function getFullArticle(link) {
     const response = await got(link).catch(() => null);
@@ -46,9 +46,9 @@ export const route: Route = {
     name: '教务处通知公告',
     maintainers: ['SeanChao'],
     handler,
-    description: `| 新闻中心 | 通知通告 | 教学运行  | 注册学务 | 研究办 | 教改办 | 综合办 | 语言文字 | 工会与支部 | 通识教育 |
+    description: `| 新闻中心 | 通知通告 | 教学运行  | 注册学务 | 研究办 | 教改办 | 综合办 | 语言文字 | 工会与支部 | 通识教育 | 面向学生的通知 |
   | -------- | -------- | --------- | -------- | ------ | ------ | ------ | -------- | ---------- | -------- |
-  | news     | notice   | operation | affairs  | yjb    | jgb    | zhb    | language | party      | ge       |`,
+  | news     | notice   | operation | affairs  | yjb    | jgb    | zhb    | language | party      | ge       | students  |`,
 };
 
 async function handler(ctx) {
@@ -56,48 +56,52 @@ async function handler(ctx) {
     const config = {
         all: {
             section: '通知通告',
-            link: '/tztg.htm',
+            link: '/xwtg/tztg.htm',
         },
         news: {
-            link: '/xwzx.htm',
+            link: '/xwtg/xwzx.htm',
             section: '新闻中心',
         },
         notice: {
-            link: '/tztg.htm',
+            link: '/xwtg/tztg.htm',
             section: '通知通告',
         },
         operation: {
-            link: '/jxyx.htm',
+            link: '/xwtg/jxyx.htm',
             section: '教学运行',
         },
         affairs: {
-            link: '/zcxw.htm',
+            link: '/xwtg/zcxw.htm',
             section: '注册学务',
         },
         yjb: {
-            link: '/yjb.htm',
+            link: '/xwtg/yjb.htm',
             section: '研究办',
         },
         jgb: {
-            link: '/jgb.htm',
+            link: '/xwtg/jgb.htm',
             section: '教改办',
         },
         zhb: {
-            link: '/zhb.htm',
+            link: '/xwtg/zhb.htm',
             section: '综合办',
         },
         language: {
-            link: '/yywz.htm',
+            link: '/xwtg/yywz.htm',
             section: '语言文字',
         },
         party: {
-            link: '/ghyzb.htm',
+            link: '/xwtg/ghyzb.htm',
             section: '工会与支部',
         },
         ge: {
-            link: '/tsjy.htm',
+            link: '/xwtg/tsjy.htm',
             section: '通识教育',
         },
+        students: {
+            link: '/index/mxxsdtz.htm',
+            section: '面向学生的通知',
+        },
     };
 
     const sectionLink = urlRoot + config[type].link;

package/lib/routes/slowmist/slowmist.ts

@@ -6,7 +6,7 @@ import { finishArticleItem } from '@/utils/wechat-mp';
 
 export const route: Route = {
     path: '/:type?',
-    categories: ['new-media'],
+    categories: ['new-media', 'popular'],
     example: '/slowmist/research',
     parameters: { type: '分类，见下表，默认为公司新闻' },
     features: {

package/lib/routes/smzdm/haowen.ts

@@ -1,6 +1,6 @@
-import { Route } from '@/types';
+import { DataItem, Route } from '@/types';
 import cache from '@/utils/cache';
-import got from '@/utils/got';
+import ofetch from '@/utils/ofetch';
 import { load } from 'cheerio';
 import { parseDate } from '@/utils/parse-date';
 import timezone from '@/utils/timezone';
@@ -9,7 +9,17 @@ export const route: Route = {
     path: '/haowen/:day?',
     categories: ['shopping'],
     example: '/smzdm/haowen/1',
-    parameters: { day: '以天为时间跨度，默认为 `all`，其余可以选择 `1`，`7`，`30`，`365`' },
+    parameters: {
+        day: {
+            description: '以天为时间跨度，默认为 `1`',
+            options: [
+                { value: '1', label: '今日热门' },
+                { value: '7', label: '周热门' },
+                { value: '30', label: '月热门' },
+            ],
+            default: '1',
+        },
+    },
     features: {
         requireConfig: false,
         requirePuppeteer: false,
@@ -19,43 +29,49 @@ export const route: Route = {
         supportScihub: false,
     },
     name: '好文',
-    maintainers: ['LogicJake'],
+    maintainers: ['LogicJake', 'pseudoyu'],
     handler,
 };
 
 async function handler(ctx) {
-    const day = ctx.req.param('day') ?? 'all';
+    const day = ctx.req.param('day') ?? '1';
     const link = `https://post.smzdm.com/hot_${day}/`;
 
-    const response = await got(link);
-    const $ = load(response.data);
+    const response = await ofetch(link);
+    const $ = load(response);
     const title = $('li.filter-tab.active').text();
 
     const list = $('li.feed-row-wide')
         .toArray()
         .map((item) => {
-            item = $(item);
+            const $item = $(item);
             return {
-                title: item.find('h5.z-feed-title a').text(),
-                link: item.find('h5.z-feed-title a').attr('href'),
-                pubDate: timezone(parseDate(item.find('span.z-publish-time').text()), 8),
+                title: $item.find('h5.z-feed-title a').text(),
+                link: $item.find('h5.z-feed-title a').attr('href'),
+                pubDate: timezone(parseDate($item.find('span.z-publish-time').text()), 8),
             };
         });
 
     const out = await Promise.all(
         list.map((item) =>
-            cache.tryGet(item.link, async () => {
-                const response = await got(item.link);
-                const $ = load(response.data);
+            cache.tryGet(item.link ?? '', async () => {
+                const response = await ofetch(item.link ?? '');
+                const $ = load(response);
                 const content = $('#articleId');
                 content.find('.item-name').remove();
                 content.find('.recommend-tab').remove();
 
-                item.description = content.html();
-                item.pubDate = timezone(parseDate($('meta[property="og:release_date"]').attr('content')), 8);
-                item.author = $('meta[property="og:author"]').attr('content');
+                const releaseDate = $('meta[property="og:release_date"]').attr('content');
+
+                const outItem: DataItem = {
+                    title: item.title,
+                    link: item.link,
+                    description: content.html() || '',
+                    pubDate: releaseDate ? timezone(parseDate(releaseDate), 8) : item.pubDate,
+                    author: $('meta[property="og:author"]').attr('content') || '',
+                };
 
-                return item;
+                return outItem;
             })
         )
     );
@@ -63,6 +79,6 @@ async function handler(ctx) {
     return {
         title: `${title}-什么值得买好文`,
         link,
-        item: out,
+        item: out.filter((item): item is DataItem => item !== null),
     };
 }

package/lib/routes/smzdm/namespace.ts

@@ -3,7 +3,7 @@ import type { Namespace } from '@/types';
 export const namespace: Namespace = {
     name: '什么值得买',
     url: 'post.smzdm.com',
-    description: `:::tip
+    description: `::: tip
 网站也提供了部分 RSS: [https://www.smzdm.com/dingyue](https://www.smzdm.com/dingyue)
 :::`,
     lang: 'zh-CN',

package/lib/routes/sohu/mp.ts

@@ -8,10 +8,11 @@ import * as cheerio from 'cheerio';
 import { parseDate } from '@/utils/parse-date';
 import path from 'node:path';
 import { art } from '@/utils/render';
+import CryptoJS from 'crypto-js';
 
 export const route: Route = {
     path: '/mp/:xpt',
-    categories: ['new-media'],
+    categories: ['new-media', 'popular'],
     example: '/sohu/mp/c29odXptdGhnbjZ3NEBzb2h1LmNvbQ==',
     parameters: { xpt: '搜狐号 xpt ，可在URL中找到或搜狐号 ID' },
     radar: [
@@ -39,6 +40,15 @@ function randomString(length = 32) {
 }
 const defaultSUV = '1612268936507kas0gk';
 
+function decryptImageUrl(cipherText) {
+    const key = CryptoJS.enc.Utf8.parse('www.sohu.com6666');
+    const cipher = CryptoJS.AES.decrypt(cipherText, key, {
+        mode: CryptoJS.mode.ECB,
+        padding: CryptoJS.pad.Pkcs7,
+    });
+    return cipher.toString(CryptoJS.enc.Utf8);
+}
+
 function fetchArticle(item) {
     return cache.tryGet(item.link, async () => {
         const response = await ofetch(item.link);
@@ -64,6 +74,13 @@ function fetchArticle(item) {
             article.find('#backsohucom, p[data-role="editor-name"]').each((i, e) => {
                 $(e).remove();
             });
+            article.find('img').each((_, e) => {
+                const $e = $(e);
+                if ($e.attr('data-src') && !$e.attr('src')) {
+                    $e.attr('src', decryptImageUrl($e.attr('data-src')));
+                    $e.removeAttr('data-src');
+                }
+            });
 
             item.description = article.html();
         }

package/lib/routes/solidot/namespace.ts

@@ -3,5 +3,5 @@ import type { Namespace } from '@/types';
 export const namespace: Namespace = {
     name: 'Solidot',
     url: 'www.solidot.org',
-    lang: 'en',
+    lang: 'zh-CN',
 };

package/lib/routes/sony/downloads.ts

@@ -23,9 +23,9 @@ export const route: Route = {
     name: 'Software Downloads',
     maintainers: ['EthanWng97'],
     handler,
-    description: `:::tip
+    description: `::: tip
   Open \`https://www.sony.com/electronics/support\` and search for the corresponding product, such as \`Sony A7M4\`, the website corresponding to which is \`https://www.sony.com/electronics/support/e-mount-body-ilce-7-series/ilce-7m4/downloads\`, where \`productType\` is \`e-mount-body-ilce-7-series\` and \`productId\` is \`ilce-7m4\`.
-  :::`,
+:::`,
 };
 
 async function handler(ctx) {

package/lib/routes/southcn/nfapp/column.ts

@@ -26,9 +26,9 @@ export const route: Route = {
     name: '南方 +（按栏目 ID）',
     maintainers: ['TimWu007'],
     handler,
-    description: `:::tip
+    description: `::: tip
   若此处输入的是栏目 ID（而非南方号 ID），则该接口会返回与输入栏目相关联栏目的文章。例如，输入栏目 ID \`38\`（广州），则返回的结果还会包含 ID 为 \`3547\`（市长报道集）的文章。
-  :::
+:::
 
   1.  \`pc.nfapp.southcn.com\` 下的文章页面，可通过 url 查看，例：\`http://pc.nfapp.southcn.com/13707/7491109.html\` 的栏目 ID 为 \`13707\`。
   2.  \`static.nfapp.southcn.com\` 下的文章页面，可查看网页源代码，搜索 \`columnid\`。