rsshub 1.0.0-master.f71451d → 1.0.0-master.f72af1b

package/lib/routes/uestc/bbs.ts

@@ -0,0 +1,97 @@
+import { Route } from '@/types';
+import ofetch from '@/utils/ofetch'; // 统一使用的请求库
+import { parseDate } from '@/utils/parse-date'; // 解析日期的工具函数
+import timezone from '@/utils/timezone';
+import { config } from '@/config';
+import { load } from 'cheerio';
+import cache from '@/utils/cache';
+import ConfigNotFoundError from '@/errors/types/config-not-found';
+
+export const route: Route = {
+    path: '/bbs/:types?',
+    name: '清水河畔',
+    maintainers: ['huyyi'],
+    categories: ['university'],
+    url: 'bbs.uestc.edu.cn',
+    example: '/uestc/bbs/newthread',
+    parameters: { types: '选择内容类型(多选`,`分割），可选值：[newreply,newthread,digest,life,hotlist]。默认为所有。' },
+    features: {
+        requireConfig: [
+            {
+                name: 'UESTC_BBS_COOKIE',
+                optional: false,
+                description: '河畔的cookie',
+            },
+            {
+                name: 'UESTC_BBS_AUTH_KEY',
+                optional: false,
+                description: '河畔Header中的authorization字段',
+            },
+        ],
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    description: `
+:::tip
+仅支持自建，您需要设置以下配置才能正常使用：
+-   河畔cookie: \`UESTC_BBS_COOKIE\`
+-   Header中的授权字段: \`UESTC_BBS_AUTH_KEY\`
+:::
+`,
+    radar: [
+        {
+            source: ['bbs.uestc.edu.cn/*'],
+            target: '/bbs/newthread',
+        },
+    ],
+    handler: async (ctx) => {
+        const { bbsCookie, bbsAuthStr } = config.uestc;
+        if (!bbsCookie || !bbsAuthStr) {
+            throw new ConfigNotFoundError('未配置 Cookie 或 Authorization。请检查配置。');
+        }
+        const { types = 'newreply,newthread,digest,life,hotlist' } = ctx.req.param();
+        const data = await ofetch(`https://bbs.uestc.edu.cn/star/api/v1/index?top_list=${types}`, {
+            headers: {
+                Cookie: bbsCookie,
+                Referer: 'https://bbs.uestc.edu.cn/new',
+                authorization: bbsAuthStr,
+            },
+        });
+        const itemsRaw = Object.entries(data.data.top_list).flatMap(([label, items]) => items.map((item) => ({ ...item, label })));
+        const items = await Promise.all(
+            itemsRaw.map((item) =>
+                cache.tryGet(`https://bbs.uestc.edu.cn/forum.php?mod=viewthread&tid=${item.thread_id}`, async () => {
+                    const response = await ofetch(`https://bbs.uestc.edu.cn/forum.php?mod=viewthread&tid=${item.thread_id}`, {
+                        headers: {
+                            Cookie: bbsCookie,
+                            Referer: 'https://bbs.uestc.edu.cn',
+                            authorization: bbsAuthStr,
+                        },
+                    });
+                    const $ = load(response);
+                    item.description = $('div#postlist').html();
+                    return {
+                        title: item.subject,
+                        link: `https://bbs.uestc.edu.cn/thread/${item.thread_id}`,
+                        author: item.author,
+                        category: item.label,
+                        img: item.icon,
+                        pubDate: timezone(parseDate(item.dateline), +8),
+                        description: item.description,
+                    };
+                })
+            )
+        );
+        return {
+            // 源标题
+            title: '清水河畔',
+            // 源链接
+            link: 'https://bbs.uestc.edu.cn/new',
+            // 源文章
+            item: items,
+        };
+    },
+};

package/lib/routes/uestc/namespace.ts

@@ -2,5 +2,5 @@ import type { Namespace } from '@/types';
 
 export const namespace: Namespace = {
     name: '电子科技大学',
-    url: 'gr.uestc.edu.cn',
+    url: 'www.uestc.edu.cn',
 };

package/lib/routes/upc/jwc.ts

@@ -0,0 +1,121 @@
+// 导入必要的模组
+import { Route } from '@/types';
+import got from '@/utils/got';
+import { load } from 'cheerio';
+import { parseDate } from '@/utils/parse-date';
+import cache from '@/utils/cache';
+import timezone from '@/utils/timezone';
+
+const typeDict = {
+    tzgg: '', // 默认为所有通知
+    '18519': '教学·运行-', // 教学·运行
+    '18520': '学业·学籍-', // 学业·学籍
+    '18521': '教学·研究-', // 教学·研究
+    '18522': '课程·教材-', // 课程·教材
+    '18523': '实践·教学-', // 实践·教学
+    '18524': '创新·创业-', // 创新·创业
+    yywwz: '语言·文字-', // 语言·文字
+    jxwjy: '继续·教育-', // 继续·教育
+    bkwzs: '本科·招生-', // 本科·招生
+};
+
+// module.exports = async (ctx) => {
+const handler = async (ctx) => {
+    // 从 URL 参数中获取通知分类
+    const { type = 'tzgg' } = ctx.req.param();
+    // console.log(type);
+    const baseUrl = 'https://jwc.upc.edu.cn';
+    const { data: response } = await got(`${baseUrl}/${type}/list.htm`);
+    // console.log(`${baseUrl}/${typeDict[type]}/list.htm`);
+    const $ = load(response);
+    // const listItems = $('ul.news_list').find('li');
+    // console.log(`List item count: ${listItems.length}`);
+    // const list = $('ul.news_list')  只会得到第一个li
+    const list = $('ul.news_list')
+        .find('li')
+        // 使用“toArray()”方法将选择的所有 DOM 元素以数组的形式返回。
+        .toArray()
+        // 使用“map()”方法遍历数组，并从每个元素中解析需要的数据。
+        .map((item) => {
+            // console.log(item);
+            item = $(item);
+            const a = item.find('a').first();
+            let linkStr = a.attr('href');
+            // 若链接不是以http开头，则加上前缀
+            if (a.attr('href').startsWith('http://')) {
+                // 改为https访问
+                linkStr.replace('http://', 'https://');
+            } else {
+                linkStr = `${baseUrl}${a.attr('href')}`;
+            }
+            return {
+                title: a.text(),
+                link: linkStr,
+                pubDate: timezone(parseDate(item.find('.news_meta').text()), +8), // 添加发布日期查询
+            };
+        });
+
+    const items = await Promise.all(
+        list.map((item) =>
+            cache.tryGet(item.link, async () => {
+                const { data: response } = await got(item.link);
+                const $ = load(response);
+                // 选择类名为“comment-body”的第一个元素
+                item.description = $('.read').first().html();
+                // item.pubDate = $('.arti_update').html() === null ? '' : $('.arti_update').html().slice(5, 15);
+                // item.publisher = $('.arti_publisher').html();
+                item.author = $('.arti_publisher').html();
+                // console.log($('.arti_update').html().slice(5, 15));
+                // 上面每个列表项的每个属性都在此重用，
+                // 并增加了一个新属性“description”
+                return item;
+            })
+        )
+    );
+
+    /*     ctx.state.data = {
+        // 源标题
+        title: `${typeDict[type]}教务处通知-中国石油大学（华东）`,
+        // 源链接
+        link: `https://jwc.upc.edu.cn/tzgg/list.htm`,
+        // 源文章
+        item: items,
+    }; */
+
+    return {
+        // 源标题
+        title: `${typeDict[type]}教务处通知-中国石油大学（华东）`,
+        // 源链接
+        link: `${baseUrl}/${type}/list.htm`,
+        // 源文章
+        item: items,
+    };
+};
+
+export const route: Route = {
+    path: '/jwc/:type?',
+    categories: ['university'],
+    example: '/upc/jwc/tzgg',
+    parameters: { type: '分类，见下表，其值与对应网页url路径参数一致，默认为所有通知' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: true,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['jwc.upc.edu.cn', 'jwc.upc.edu.cn/:type/list.htm'],
+            target: '/jwc/:type?',
+        },
+    ],
+    name: '教务处通知公告',
+    maintainers: ['sddzhyc'],
+    description: `| 所有通知 | 教学·运行 | 学业·学籍 | 教学·研究 | 课程·教材 | 实践·教学 | 创新·创业 | 语言·文字 | 继续·教育 | 本科·招生 |
+  | -------- | -------- | -------- | -------- | -------- | -------- | -------- | -------- | -------- | -------- |
+  | tzgg     | 18519    | 18520   | 18521    |    18522 |    18523 | 18524    |  yywwz   |  jxwjy   |   bkwzs  |`,
+    url: 'jwc.upc.edu.cn/tzgg/list.htm',
+    handler,
+};

package/lib/routes/usenix/usenix.ts

@@ -1,6 +1,6 @@
 import { Route } from '@/types';
 import cache from '@/utils/cache';
-import got from '@/utils/got';
+import ofetch from '@/utils/ofetch';
 import { load } from 'cheerio';
 const url = 'https://www.usenix.org';
 import { parseDate } from '@/utils/parse-date';
@@ -11,15 +11,6 @@ export const route: Route = {
     path: '/usenix-security-sympoium',
     categories: ['journal'],
     example: '/usenix/usenix-security-sympoium',
-    parameters: {},
-    features: {
-        requireConfig: false,
-        requirePuppeteer: false,
-        antiCrawler: false,
-        supportBT: false,
-        supportPodcast: false,
-        supportScihub: false,
-    },
     radar: [
         {
             source: ['usenix.org/conferences/all', 'usenix.org/conferences', 'usenix.org/'],
@@ -35,11 +26,11 @@ export const route: Route = {
 async function handler() {
     const last = new Date().getFullYear() + 1;
     const urlList = Array.from({ length: last - 2020 }, (_, v) => `${url}/conference/usenixsecurity${v + 20}`).flatMap((url) => seasons.map((season) => `${url}/${season}-accepted-papers`));
-    const responses = await got.all(
+    const responses = await Promise.allSettled(
         urlList.map(async (url) => {
             let res;
             try {
-                res = await got(url);
+                res = await ofetch(url);
             } catch {
                 // ignore 404
             }
@@ -47,27 +38,29 @@ async function handler() {
         })
     );
 
-    const list = responses.filter(Boolean).flatMap((response) => {
-        const $ = load(response.data);
-        const pubDate = parseDate($('meta[property=article:modified_time]').attr('content'));
-        return $('article.node-paper')
-            .toArray()
-            .map((item) => {
-                item = $(item);
-                return {
-                    title: item.find('h2.node-title > a').text().trim(),
-                    link: `${url}${item.find('h2.node-title > a').attr('href')}`,
-                    author: item.find('div.field.field-name-field-paper-people-text.field-type-text-long.field-label-hidden p').text().trim(),
-                    pubDate,
-                };
-            });
-    });
+    const list = responses
+        .filter((r) => r.status === 'fulfilled' && r.value)
+        .flatMap((response) => {
+            const $ = load(response.value);
+            const pubDate = parseDate($('meta[property=article:modified_time]').attr('content'));
+            return $('article.node-paper')
+                .toArray()
+                .map((item) => {
+                    item = $(item);
+                    return {
+                        title: item.find('h2.node-title > a').text().trim(),
+                        link: `${url}${item.find('h2.node-title > a').attr('href')}`,
+                        author: item.find('div.field.field-name-field-paper-people-text.field-type-text-long.field-label-hidden p').text().trim(),
+                        pubDate,
+                    };
+                });
+        });
 
-    const items = await Promise.all(
+    const items = await Promise.allSettled(
         list.map((item) =>
             cache.tryGet(item.link, async () => {
-                const response = await got(item.link);
-                const $ = load(response.data);
+                const response = await ofetch(item.link);
+                const $ = load(response);
                 item.description = $('.content').html();
 
                 return item;
@@ -80,6 +73,6 @@ async function handler() {
         link: url,
         description: 'USENIX Security Symposium Accpeted Papers',
         allowEmpty: true,
-        item: items,
+        item: items.filter((r) => r.status === 'fulfilled').map((r) => (r as PromiseFulfilledResult<any>).value),
     };
 }

package/lib/routes/ustc/scms.ts

@@ -0,0 +1,97 @@
+import { Route } from '@/types';
+import cache from '@/utils/cache';
+import got from '@/utils/got';
+import { load } from 'cheerio';
+import { parseDate } from '@/utils/parse-date';
+import timezone from '@/utils/timezone';
+// import InvalidParameterError from '@/errors/types/invalid-parameter';
+
+const map = new Map([
+    ['kydt', { title: '科研动态', id: '2404' }],
+    ['tzgg', { title: '通知公告', id: '2402' }],
+    ['xshd', { title: '学术活动', id: 'xshd' }],
+    ['ynxw', { title: '院内新闻', id: '2405' }],
+]);
+
+const host = 'https://scms.ustc.edu.cn';
+
+export const route: Route = {
+    path: '/scms/:type?',
+    categories: ['university'],
+    example: '/ustc/scms/tzgg',
+    parameters: { type: '分类，见下表，默认为通知公告' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['scms.ustc.edu.cn/:id/list.htm'],
+            target: '/scms',
+        },
+    ],
+    name: '化学与材料科学学院',
+    maintainers: ['boxie123'],
+    handler,
+    url: 'scms.ustc.edu.cn/',
+    description: `| 院内新闻 | 通知公告 | 科研动态 | 学术活动 | 其他 |
+  | -------- | -------- | -------- | -------- | -------- |
+  | ynxw     | tzgg     | kydt     | xshd     | 自定义id  |`,
+};
+
+async function handler(ctx) {
+    const type = ctx.req.param('type') ?? 'tzgg';
+    const info = map.get(type);
+    //  ?? { title: `中国科学技术大学化学与材料科学学院 - ${type}`, id: type };
+    // if (!info) {
+    //     throw new InvalidParameterError('invalid type');
+    // }
+    const id = info?.id ?? type;
+
+    const response = await got(`${host}/${id}/list.htm`);
+    const $ = load(response.data);
+
+    const pageTitle = info?.title ?? $('head > title').text();
+
+    let items = $('#wp_news_w6 > .wp_article_list > .list_item')
+        .toArray()
+        .map((item) => {
+            const elem = $(item);
+            const title = elem.find('.Article_Title > a').attr('title').trim();
+            let link = elem.find('.Article_Title > a').attr('href');
+            link = link.startsWith('/') ? host + link : link;
+            // Assume that the articles are published at 12:00 UTC+8
+            const pubDate = timezone(parseDate(elem.find('.Article_PublishDate').text(), 'YYYY-MM-DD'), -4);
+            return {
+                title,
+                pubDate,
+                link,
+            };
+        });
+
+    items = await Promise.all(
+        items.map((item) =>
+            cache.tryGet(item.link, async () => {
+                let desc = '';
+                try {
+                    const response = await got(item.link);
+                    desc = load(response.data)('div.wp_articlecontent').html();
+                    item.description = desc;
+                } catch {
+                    // Intranet only contents
+                }
+                return item;
+            })
+        )
+    );
+
+    return {
+        title: `中国科学技术大学化学与材料科学学院 - ${pageTitle}`,
+        link: `${host}/${id}/list.htm`,
+        item: items,
+    };
+}

package/lib/routes/utgd/category.ts

@@ -1,22 +1,12 @@
 import { Route } from '@/types';
-import { getCurrentPath } from '@/utils/helpers';
-const __dirname = getCurrentPath(import.meta.url);
 
-import cache from '@/utils/cache';
-import got from '@/utils/got';
-import timezone from '@/utils/timezone';
-import { parseDate } from '@/utils/parse-date';
-import { art } from '@/utils/render';
-import path from 'node:path';
-import MarkdownIt from 'markdown-it';
-const md = MarkdownIt({
-    html: true,
-});
+import ofetch from '@/utils/ofetch';
+import { rootUrl, apiRootUrl, parseResult, parseArticle } from './utils';
 
 export const route: Route = {
-    path: '/:category?',
+    path: '/category/:category?',
     categories: ['new-media'],
-    example: '/utgd/method',
+    example: '/utgd/category/method',
     parameters: { category: '分类，可在对应分类页的 URL 中找到，默认为方法' },
     features: {
         requireConfig: false,
@@ -29,7 +19,7 @@ export const route: Route = {
     radar: [
         {
             source: ['utgd.net/category/s/:category', 'utgd.net/'],
-            target: '/:category',
+            target: '/category/:category',
         },
     ],
     name: '分类',
@@ -42,61 +32,30 @@ export const route: Route = {
 
 async function handler(ctx) {
     const category = ctx.req.param('category') ?? 'method';
-    const limit = ctx.req.query('limit') ? Number.parseInt(ctx.req.query('limit')) : 20;
+    const limit = ctx.req.query('limit') ? Number.parseInt(ctx.req.query('limit')) : 9;
 
-    const rootUrl = 'https://utgd.net';
-    const apiUrl = `${rootUrl}/api/v2/pages/`;
+    const apiUrl = `${apiRootUrl}/api/v2/categories`;
     const currentUrl = `${rootUrl}/category/s/${category}`;
-    const slugUrl = `${rootUrl}/api/v2/category/slug/${category}/`;
+    const slugUrl = `${apiRootUrl}/api/v2/category/slug/${category}/`;
 
-    let response = await got({
-        method: 'get',
-        url: slugUrl,
-    });
-
-    const data = response.data;
+    const categoryData = await ofetch(slugUrl);
 
-    response = await got({
-        method: 'get',
-        url: apiUrl,
-        searchParams: {
-            type: 'article.Article',
-            fields: `article_category(category_name),article_tag(tag_name),title,article_image,article_author,article_description,article_published_time`,
-            article_category: data.id,
-            order: '-article_published_time',
-            limit,
+    const response = await ofetch(`${apiUrl}/${categoryData.id}/related_articles`, {
+        query: {
+            page: 1,
+            page_size: limit,
         },
     });
 
-    const items = await Promise.all(
-        response.data.items.map((item) =>
-            cache.tryGet(`untag-${item.id}`, async () => {
-                const authorResponse = await got({
-                    method: 'get',
-                    url: `${rootUrl}/api/v2/user/profile/${item.article_author.id}/`,
-                });
+    const list = parseResult(response.results, limit);
 
-                return {
-                    title: item.title,
-                    link: `${rootUrl}/article/${item.id}`,
-                    description: art(path.join(__dirname, 'templates/description.art'), {
-                        membership: item.article_for_membership,
-                        image: item.article_image,
-                        description: md.render(item.article_description),
-                    }),
-                    author: authorResponse.data.display_name,
-                    pubDate: timezone(parseDate(item.article_published_time), +8),
-                    category: [...item.article_category.map((c) => c.category_name), ...item.article_tag.map((t) => t.tag_name)],
-                };
-            })
-        )
-    );
+    const items = await Promise.all(list.map((item) => parseArticle(item)));
 
     return {
-        title: `UNTAG - ${data.category_name}`,
+        title: `UNTAG - ${categoryData.category_name}`,
         link: currentUrl,
         item: items,
-        image: data.category_image,
-        description: data.category_description,
+        image: categoryData.category_image,
+        description: categoryData.category_description,
     };
 }

package/lib/routes/utgd/timeline.ts

@@ -1,17 +1,7 @@
 import { Route } from '@/types';
-import { getCurrentPath } from '@/utils/helpers';
-const __dirname = getCurrentPath(import.meta.url);
 
-import cache from '@/utils/cache';
-import got from '@/utils/got';
-import timezone from '@/utils/timezone';
-import { parseDate } from '@/utils/parse-date';
-import { art } from '@/utils/render';
-import path from 'node:path';
-import MarkdownIt from 'markdown-it';
-const md = MarkdownIt({
-    html: true,
-});
+import ofetch from '@/utils/ofetch';
+import { rootUrl, apiRootUrl, parseResult, parseArticle } from './utils';
 
 export const route: Route = {
     path: '/timeline',
@@ -40,42 +30,16 @@ export const route: Route = {
 async function handler(ctx) {
     const limit = ctx.req.query('limit') ? Number.parseInt(ctx.req.query('limit')) : 20;
 
-    const rootUrl = 'https://utgd.net';
-    const apiUrl = `${rootUrl}/api/v2/timeline/?page=1&page_size=${limit}`;
-
-    const response = await got({
-        method: 'get',
-        url: apiUrl,
+    const response = await ofetch(`${apiRootUrl}/api/v2/timeline/`, {
+        query: {
+            page: 1,
+            page_size: limit,
+        },
     });
 
-    const items = await Promise.all(
-        response.data.results.slice(0, limit).map((item) =>
-            cache.tryGet(`untag-${item.id}`, async () => {
-                const detailResponse = await got({
-                    method: 'get',
-                    url: `${rootUrl}/api/v2/article/${item.id}/`,
-                    searchParams: {
-                        fields: 'article_description,article_category(category_name),article_tag(tag_name)',
-                    },
-                });
-
-                const data = detailResponse.data;
+    const list = parseResult(response.results, limit);
 
-                return {
-                    title: item.title,
-                    link: `${rootUrl}/article/${item.id}`,
-                    description: art(path.join(__dirname, 'templates/description.art'), {
-                        membership: data.article_for_membership,
-                        image: item.article_image,
-                        description: md.render(data.article_description),
-                    }),
-                    author: item.article_author_displayname,
-                    pubDate: timezone(parseDate(item.article_published_time), +8),
-                    category: [...data.article_category.map((c) => c.category_name), ...data.article_tag.map((t) => t.tag_name)],
-                };
-            })
-        )
-    );
+    const items = await Promise.all(list.map((item) => parseArticle(item)));
 
     return {
         title: 'UNTAG',