rsshub 1.0.0-master.ff487f3 → 1.0.0-master.ff76aa7

package/lib/routes/gov/ndrc/xwdt.ts

@@ -2,16 +2,36 @@ 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';
 
 export const route: Route = {
     path: '/ndrc/xwdt/:category{.+}?',
-    name: 'Unknown',
-    maintainers: [],
+    name: '新闻动态',
+    example: '/gov/ndrc/xwdt',
+    parameters: { category: '分类，见下表，默认为新闻发布' },
+    maintainers: ['nczitzk'],
+    categories: ['government'],
     handler,
+    radar: [
+        {
+            title: '中华人民共和国国家发展和改革委员会 - 新闻动态',
+            source: ['ndrc.gov.cn/xwdt/:category*'],
+            target: (params) => {
+                const category = params.category;
+
+                return `/gov/ndrc/xwdt/${category ? `/${category.endsWith('/') ? category : `${category}/`}` : '/'}`;
+            },
+        },
+    ],
+    description: `| 新闻发布 | 通知通告 | 委领导动态 | 司局动态 | 地方动态 |
+| -------- | -------- | ---------- | -------- | -------- |
+| xwfb     | tzgg     | wlddt      | sjdt     | dfdt     |`,
 };
 
 async function handler(ctx) {
     const category = ctx.req.param('category') || 'xwfb';
+    const limit = ctx.req.query('limit') ? Number.parseInt(ctx.req.query('limit'), 10) : 25;
 
     const rootUrl = 'https://www.ndrc.gov.cn';
     const currentUrl = category.includes('dt') ? `${rootUrl}/xwdt/dt/${category}` : `${rootUrl}/xwdt/${category}`;
@@ -22,8 +42,9 @@ async function handler(ctx) {
 
     const $ = load(response.data);
     const list = $('.u-list li a')
-        .slice(0, 10)
-        .map((_, item) => {
+        .slice(0, limit)
+        .toArray()
+        .map((item) => {
             item = $(item);
             let link = item.attr('href');
             if (link.indexOf('../../..') === 0) {
@@ -35,8 +56,7 @@ async function handler(ctx) {
                 title: item.text(),
                 link,
             };
-        })
-        .get();
+        });
 
     const items = await Promise.all(
         list.map((item) =>
@@ -47,8 +67,8 @@ async function handler(ctx) {
                 });
                 const content = load(detailResponse.data);
 
-                item.description = content('.TRS_Editor').html() || content('.article_con').html();
-                item.pubDate = new Date(content('meta[name="PubDate"]').attr('content') + ' GMT+8').toUTCString();
+                item.description = (content('.TRS_Editor').html() || content('.article_con').html() || '') + (content('.attachment').html() || '');
+                item.pubDate = timezone(parseDate(content('meta[name="PubDate"]').attr('content')!), 8);
 
                 return item;
             })

package/lib/routes/gov/ndrc/zfxxgk.ts

@@ -0,0 +1,106 @@
+import { Route } from '@/types';
+
+import cache from '@/utils/cache';
+import got from '@/utils/got';
+import { load } from 'cheerio';
+import { parseDate } from '@/utils/parse-date';
+
+export const handler = async (ctx) => {
+    const limit = ctx.req.query('limit') ? Number.parseInt(ctx.req.query('limit'), 10) : 15;
+
+    const rootUrl = 'https://zfxxgk.ndrc.gov.cn';
+    const currentUrl = new URL('web/dirlist.jsp', rootUrl).href;
+
+    const { data: response } = await got(currentUrl);
+
+    const $ = load(response);
+
+    const language = $('html').prop('lang');
+
+    $('th').parent().remove();
+
+    let items = $('div.zwxxkg-result tr')
+        .slice(0, limit)
+        .toArray()
+        .map((item) => {
+            item = $(item);
+
+            const a = item.find('a.xxgk_list1');
+
+            return {
+                title: a.text(),
+                pubDate: parseDate(item.find('td').last().text()),
+                link: new URL(a.prop('href'), currentUrl).href,
+                language,
+            };
+        });
+
+    items = await Promise.all(
+        items.map((item) =>
+            cache.tryGet(item.link, async () => {
+                const { data: detailResponse } = await got(item.link);
+
+                const $$ = load(detailResponse);
+
+                const title = $$('meta[name="ArticleTitle"]').prop('content');
+                const description = $$('div.zwgkdetail').html();
+
+                item.title = title;
+                item.description = description;
+                item.category = [...new Set([$$('meta[name="ContentSource"]').prop('content'), $$('meta[name="ColumnName"]').prop('content'), $$('meta[name="ColumnType"]').prop('content')])].filter(Boolean);
+                item.author = $$('meta[name="ContentSource"]').prop('content');
+                item.content = {
+                    html: description,
+                    text: $$('div.article').text(),
+                };
+                item.language = language;
+                item.enclosure_url = $$('table.enclosure a.xxgk_list1').length === 0 ? undefined : new URL($$('table.enclosure a.xxgk_list1').first().prop('href'), currentUrl).href;
+                item.enclosure_title = item.enclosure_url ? $$('table.enclosure a.xxgk_list1').first().text() : undefined;
+
+                return item;
+            })
+        )
+    );
+
+    const image = new URL($('div.zwgklogo img').prop('src'), currentUrl).href;
+
+    return {
+        title: `${$('meta[name="SiteName"]').prop('content')} - ${$('div.zwgktoptitle').text()}`,
+        description: $('meta[name="ColumnDescription"]').prop('content'),
+        link: currentUrl,
+        item: items,
+        allowEmpty: true,
+        image,
+        author: $('meta[name="SiteName"]').prop('content'),
+        language,
+    };
+};
+
+export const route: Route = {
+    path: ['/ndrc/zfxxgk'],
+    // path: ['/ndrc/zfxxgk', '/ndrc/zfxxgk/iteminfo'],
+    name: '中华人民共和国国家发展和改革委员会政府信息公开',
+    url: 'zfxxgk.ndrc.gov.cn',
+    maintainers: ['howfool', 'nczitzk'],
+    handler,
+    example: '/gov/ndrc/zfxxgk',
+    parameters: undefined,
+    description: undefined,
+    categories: ['government'],
+
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportRadar: true,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['zfxxgk.ndrc.gov.cn/web/dirlist.jsp'],
+            target: '/ndrc/zfxxgk',
+        },
+    ],
+};

package/lib/routes/gov/zj/search.ts

@@ -1,9 +1,8 @@
-import { Route } from '@/types';
+import { Route, DataItem } from '@/types';
 import { parseDate } from '@/utils/parse-date';
 import got from '@/utils/got';
 import { load } from 'cheerio';
 import dayjs from 'dayjs';
-
 export const route: Route = {
     path: '/zj/search/:websiteid?/:word/:cateid?',
     categories: ['government'],
@@ -24,18 +23,18 @@ export const route: Route = {
     url: 'search.zj.gov.cn/jsearchfront/search.do',
     maintainers: ['HaoyuLee'],
     description: `
-        | 行政区域         | websiteid |
-        | ------------ | -- |
-        | 宁波市本级     | 330201000000000  |
+| 行政区域         | websiteid |
+| ------------ | -- |
+| 宁波市本级     | 330201000000000  |
 
-        | 搜索关键词         | word    |
+| 搜索关键词         | word    |
 
-        | 信息分类         | cateid    |
+| 信息分类         | cateid    |
 
-        | 排序类型         | sortType    |
-        | ------------ | -- |
-        | 按相关度     | 1  |
-        | 按时间     | 2  |
+| 排序类型         | sortType    |
+| ------------ | -- |
+| 按相关度     | 1  |
+| 按时间     | 2  |
     `,
     async handler(ctx) {
         const { websiteid = '330201000000000', word = '人才', cateid = 658, sortType = 2 } = ctx.req.param();
@@ -71,10 +70,16 @@ export const route: Route = {
                     description: $('.newsDescribe>a').text() || '',
                 };
             }) || [];
+        const res = {};
+        for (const current of items) {
+            if (!res[current.link]) {
+                res[current.link] = current;
+            }
+        }
         return {
             title: '浙江省人民政府-全省政府网站统一搜索',
             link: 'https://search.zj.gov.cn/jsearchfront/search.do',
-            item: items,
+            item: Object.entries(res).map(([, value]) => value) as DataItem[],
         };
     },
 };

package/lib/routes/gq/news.ts

@@ -1,4 +1,4 @@
-import { Route } from '@/types';
+import { Route, ViewType } from '@/types';
 import cache from '@/utils/cache';
 import parser from '@/utils/rss-parser';
 import { load } from 'cheerio';
@@ -6,7 +6,8 @@ import ofetch from '@/utils/ofetch';
 const host = 'https://www.gq.com';
 export const route: Route = {
     path: '/news',
-    categories: ['traditional-media'],
+    categories: ['traditional-media', 'popular'],
+    view: ViewType.Articles,
     example: '/gq/news',
     parameters: {},
     features: {

package/lib/routes/gs/developer/blog.ts

@@ -0,0 +1,58 @@
+import { Route, Data } from '@/types';
+import ofetch from '@/utils/ofetch';
+import { load } from 'cheerio';
+
+export const route: Route = {
+    path: '/developer/blog',
+    categories: ['blog'],
+    example: '/gs/developer/blog',
+    parameters: {},
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['developer.gs.com/blog/posts'],
+            target: '/developer/blog',
+        },
+    ],
+    name: 'Goldman Sachs Developer Blog',
+    zh: {
+        name: '高盛开发者博客',
+    },
+    maintainers: ['chesha1'],
+    handler: handlerRoute,
+};
+
+async function handlerRoute(): Promise<Data> {
+    const response = await ofetch('https://developer.gs.com/blog/posts');
+    const $ = load(response);
+
+    const items = $('div[data-cy="blog-card-grid"] a')
+        .toArray()
+        .map((item) => {
+            const link = 'https://developer.gs.com' + $(item).attr('href');
+            const title = $(item).find('span').eq(1).text();
+            const author = $(item).find('span').eq(2).text();
+            const description = $(item).find('span').eq(3).text();
+            const pubDate = $(item).find('span').eq(0).text();
+            return {
+                title,
+                link,
+                author,
+                description,
+                pubDate,
+            };
+        });
+
+    return {
+        title: 'Goldman Sachs Developer Blog',
+        link: 'https://developer.gs.com/blog/posts',
+        item: items,
+    };
+}

package/lib/routes/gs/namespace.ts

@@ -0,0 +1,9 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'Goldman Sachs',
+    url: 'goldmansachs.com',
+    zh: {
+        name: '高盛',
+    },
+};

package/lib/routes/guancha/member.ts

@@ -68,7 +68,7 @@ async function handler(ctx) {
 
                 for (const i of item.items) {
                     const newPubDate = new Date(i.publish_time);
-                    pubDate = pubDate > newPubDate ? pubDate : newPubDate;
+                    pubDate = Math.max(pubDate, newPubDate);
                     description += `<a href="${rootUrl}/zaixianke/content.html?id=${i.id}">${i.title}</a><br>`;
                 }
 

package/lib/routes/hackernews/index.ts

@@ -1,4 +1,4 @@
-import { Route } from '@/types';
+import { Route, ViewType } from '@/types';
 import cache from '@/utils/cache';
 import got from '@/utils/got';
 import { load } from 'cheerio';
@@ -6,9 +6,20 @@ import { parseDate } from '@/utils/parse-date';
 
 export const route: Route = {
     path: '/:section?/:type?/:user?',
-    categories: ['programming'],
+    categories: ['programming', 'popular'],
+    view: ViewType.Articles,
     example: '/hackernews/threads/comments_list/dang',
-    parameters: { section: '内容分区，见上表，默认为 `index`', type: '链接类型，见上表，默认为 `sources`', user: '设定用户，只在 `threads` 和 `submitted` 分区有效' },
+    parameters: {
+        section: {
+            description: 'Content section, default to `index`',
+        },
+        type: {
+            description: 'Link type, default to `sources`',
+        },
+        user: {
+            description: 'Set user, only valid in `threads` and `submitted` sections',
+        },
+    },
     features: {
         requireConfig: false,
         requirePuppeteer: false,
@@ -22,10 +33,10 @@ export const route: Route = {
             source: ['news.ycombinator.com/:section', 'news.ycombinator.com/'],
         },
     ],
-    name: '用户',
+    name: 'User',
     maintainers: ['nczitzk', 'xie-dongping'],
     handler,
-    description: `订阅特定用户的内容`,
+    description: `Subscribe to the content of a specific user`,
 };
 
 async function handler(ctx) {

package/lib/routes/healthz.ts

@@ -0,0 +1,8 @@
+import type { Handler } from 'hono';
+
+const handler: Handler = (ctx) => {
+    ctx.header('Cache-Control', 'no-cache');
+    return ctx.text('ok');
+};
+
+export default handler;

package/lib/routes/hellogithub/index.ts

@@ -1,24 +1,19 @@
 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 { load } from 'cheerio';
 import { parseDate } from '@/utils/parse-date';
-import { art } from '@/utils/render';
-import path from 'node:path';
 
 const sorts = {
-    hot: '热门',
-    last: '最近',
+    featured: '精选',
+    all: '全部',
 };
 
 export const route: Route = {
-    path: ['/article/:sort?/:id?'],
+    path: ['/home/:sort?/:id?'],
     categories: ['programming'],
-    example: '/hellogithub/article',
-    parameters: { sort: '排序方式，见下表，默认为 `hot`，即热门', id: '标签 id，可在对应标签页 URL 中找到，默认为全部标签' },
+    example: '/hellogithub/home',
+    parameters: { sort: '排序方式，见下表，默认为 `featured`，即精选', id: '标签 id，可在对应标签页 URL 中找到，默认为全部标签' },
     features: {
         requireConfig: false,
         requirePuppeteer: false,
@@ -27,16 +22,16 @@ export const route: Route = {
         supportPodcast: false,
         supportScihub: false,
     },
-    name: '文章',
+    name: '开源项目',
     maintainers: ['moke8', 'nczitzk'],
     handler,
-    description: `| 热门 | 最近 |
+    description: `| 精选 | 全部 |
   | ---- | ---- |
-  | hot  | last |`,
+  | featured  | all |`,
 };
 
 async function handler(ctx) {
-    const sort = ctx.req.param('sort') ?? 'hot';
+    const sort = ctx.req.param('sort') ?? 'featured';
     const id = ctx.req.param('id') ?? '';
     const limit = ctx.req.query('limit') ? Number.parseInt(ctx.req.query('limit')) : 20;
 
@@ -50,7 +45,7 @@ async function handler(ctx) {
         url: apiUrl,
     });
 
-    let buildId, tag;
+    let tag;
     if (id) {
         const tagUrl = `${rootUrl}/tags/${id}`;
 
@@ -62,66 +57,21 @@ async function handler(ctx) {
         const $ = load(tagResponse.data);
 
         tag = $('meta[property="og:title"]')?.attr('content')?.split(' ').pop();
-        buildId = tagResponse.data.match(/"buildId":"(.*?)",/)[1];
-    }
-
-    if (!buildId) {
-        const buildResponse = await got({
-            method: 'get',
-            url: rootUrl,
-        });
-
-        buildId = buildResponse.data.match(/"buildId":"(.*?)",/)[1];
     }
 
-    let items = response.data.data.slice(0, limit).map((item) => ({
+    const items = response.data.data.slice(0, limit).map((item) => ({
         guid: item.item_id,
-        title: item.title,
+        title: `${item.name}: ${item.title}`,
         author: item.author,
         link: `${rootUrl}/repository/${item.item_id}`,
-        description: item.description,
         pubDate: parseDate(item.updated_at),
+        name: `${item.author}/${item.name}`,
+        summary: item.summary,
+        language: item.primary_lang,
     }));
 
-    items = await Promise.all(
-        items.map((item) =>
-            cache.tryGet(item.link, async () => {
-                const detailUrl = `${rootUrl}/_next/data/${buildId}/repository/${item.guid}.json`;
-
-                const detailResponse = await got({
-                    method: 'get',
-                    url: detailUrl,
-                });
-
-                const data = detailResponse.data.pageProps.repo;
-
-                item.title = `${data.name}: ${data.title}`;
-                item.category = [`No.${data.volume_name}`, ...data.tags.map((t) => t.name)];
-                item.description = art(path.join(__dirname, 'templates/description.art'), {
-                    name: data.full_name,
-                    description: data.description,
-                    summary: data.summary,
-                    image: data.image_url,
-                    stars: data.stars ?? data.stars_str,
-                    isChinese: data.has_chinese,
-                    language: data.primary_lang,
-                    isActive: data.is_active,
-                    license: data.license,
-                    isOrganization: data.is_org,
-                    forks: data.forks,
-                    openIssues: data.open_issues,
-                    subscribers: data.subscribers,
-                    homepage: data.homepage,
-                    url: data.url,
-                });
-
-                return item;
-            })
-        )
-    );
-
     return {
-        title: `HelloGithub - ${sorts[sort]}${tag || ''}项目`,
+        title: `HelloGithub - ${sorts[sort]}${tag || ''}开源项目`,
         link: currentUrl,
         item: items,
     };

package/lib/routes/hellogithub/report.ts

@@ -39,7 +39,7 @@ async function handler(ctx) {
 
     const buildId = buildResponse.data.match(/"buildId":"(.*?)",/)[1];
 
-    const apiUrl = `${rootUrl}/_next/data/${buildId}/report/${type}.json`;
+    const apiUrl = `${rootUrl}/_next/data/${buildId}/zh/report/${type}.json`;
 
     const response = await got({
         method: 'get',

package/lib/routes/hex-rays/index.ts

@@ -1,4 +1,4 @@
-import { Route } from '@/types';
+import type { Data, DataItem, Route } from '@/types';
 import cache from '@/utils/cache';
 import got from '@/utils/got';
 import { load } from 'cheerio';
@@ -23,51 +23,45 @@ export const route: Route = {
         },
     ],
     name: 'Hex-Rays News',
-    maintainers: ['hellodword ', 'TonyRL'],
+    maintainers: ['hellodword ', 'TonyRL', 'Mas0n'],
     handler,
     url: 'hex-rays.com/',
 };
 
-async function handler() {
-    const link = 'https://www.hex-rays.com/blog/';
+async function handler(/* ctx*/): Promise<Data> {
+    const link = 'https://hex-rays.com/blog/';
     const response = await got.get(link);
     const $ = load(response.data);
 
-    const list = $('.post-list-container')
-        .map((_, ele) => ({
-            title: $('h3 > a', ele).text(),
-            link: $('h3 > a', ele).attr('href'),
-            pubDate: parseDate($('.post-meta:nth-of-type(1)', ele).first().text().trim().replace('Posted on:', '')),
-            author: $('.post-meta:nth-of-type(2)', ele).first().text().replace('By:', '').trim(),
-        }))
-        .get();
+    const list: DataItem[] = $('.article  ')
+        .toArray()
+        .map(
+            (ele): DataItem => ({
+                title: $('h2 > a', ele).text(),
+                link: $('h2 > a', ele).attr('href'),
+                pubDate: parseDate($('div.by-line > time', ele).attr('datetime')!),
+                author: $('div.by-line > a', ele).text(),
+            })
+        );
 
-    const items = await Promise.all(
-        list.map((item) =>
-            cache.tryGet(item.link, async () => {
+    const items: DataItem[] = await Promise.all(
+        list.map((item: DataItem) =>
+            cache.tryGet(item.link!, async () => {
                 const detailResponse = await got.get(item.link);
                 const content = load(detailResponse.data);
-
-                item.category = (
-                    content('.category-link')
-                        .toArray()
-                        .map((e) => $(e).text()) +
-                    ',' +
-                    content('.tag-link')
-                        .toArray()
-                        .map((e) => $(e).text())
-                ).split(',');
-
-                item.description = content('.post-content').html();
-
+                item.category = content('.div.topics > a')
+                    .toArray()
+                    .map((ele) => content(ele).text());
+                item.description = content('.post-body').toString();
                 return item;
             })
-        )
+        ) as Promise<DataItem>[]
     );
 
     return {
         title: 'Hex-Rays Blog',
         link,
         item: items,
+        image: 'https://hex-rays.com/hubfs/Ico-logo.png',
     };
 }

package/lib/routes/hfut/hf/notice.ts

@@ -0,0 +1,43 @@
+import { Route } from '@/types';
+import parseList from './utils';
+
+export const route: Route = {
+    path: '/hf/notice/:type?',
+    categories: ['university'],
+    example: '/hfut/hf/notice/tzgg',
+    parameters: { type: '分类，见下表（默认为 `tzgg`)' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportRadar: true,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['news.hfut.edu.cn'],
+        },
+    ],
+    name: '合肥校区通知',
+    maintainers: ['batemax'],
+    handler,
+    description: `| 通知公告(https://news.hfut.edu.cn/tzgg2.htm) | 教学科研(https://news.hfut.edu.cn/tzgg2/jxky.htm) | 其他通知(https://news.hfut.edu.cn/tzgg2/qttz.htm) |
+  | ------------ | -------------- | ------------------ |
+  | tzgg         | jxky            | qttz              |`,
+};
+
+async function handler(ctx) {
+    // set default router type
+    const type = ctx.req.param('type') ?? 'tzgg';
+
+    const { link, title, resultList } = await parseList(ctx, type);
+
+    return {
+        title,
+        link,
+        description: '合肥工业大学 - 通知公告',
+        item: resultList,
+    };
+}