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

package/lib/routes/hexun/index.ts

@@ -0,0 +1,74 @@
+import { Route } from '@/types';
+
+import cache from '@/utils/cache';
+import got from '@/utils/got';
+import { load } from 'cheerio';
+import { parseDate } from '@/utils/parse-date';
+
+const decoder = new TextDecoder('gbk');
+
+export const route: Route = {
+    path: '/pe/news',
+    categories: ['finance'],
+    example: '/hexun/pe/news',
+    url: 'pe.hexun.com/news/',
+    name: '创投行业新闻',
+    maintainers: ['p3psi-boo'],
+    handler,
+};
+
+async function handler() {
+    const baseUrl = 'https://pe.hexun.com/news/';
+
+    const response = await got({
+        method: 'get',
+        url: baseUrl,
+        responseType: 'arrayBuffer',
+    });
+
+    const $ = load(decoder.decode(response.data));
+
+    const list = $('.listNews li')
+        .toArray()
+        .map((item) => {
+            const element = $(item);
+            const a = element.find('a');
+
+            const link = a.attr('href')?.replace('http://', 'https://') || '';
+            const title = a.text() || '';
+
+            const timeSpan = element.find('span');
+            const dateText = timeSpan.text().slice(1, timeSpan.text().length - 1);
+            const pubDate = parseDate(dateText, 'MM/DD HH:mm');
+
+            return {
+                title,
+                link,
+                pubDate,
+            };
+        });
+
+    const items = await Promise.all(
+        list.map((item) =>
+            cache.tryGet(item.link, async () => {
+                const response = await got({
+                    method: 'get',
+                    url: item.link,
+                    responseType: 'arrayBuffer',
+                });
+
+                const $ = load(decoder.decode(response.data));
+
+                item.description = $('.art_contextBox').html() || '';
+
+                return item;
+            })
+        )
+    );
+
+    return {
+        title: '和讯创投 - 创投行业新闻',
+        link: baseUrl,
+        item: items,
+    };
+}

package/lib/routes/hexun/namespace.ts

@@ -0,0 +1,8 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: '和讯网',
+    url: 'hexun.com',
+    description: '',
+    lang: 'zh-CN',
+};

package/lib/routes/hiring.cafe/jobs.ts

@@ -0,0 +1,152 @@
+import ofetch from '@/utils/ofetch';
+import path from 'node:path';
+import { art } from '@/utils/render';
+import { Context } from 'hono';
+import { getCurrentPath } from '@/utils/helpers';
+import { Route } from '@/types';
+
+const __dirname = getCurrentPath(import.meta.url);
+
+const CONFIG = {
+    DEFAULT_PAGE_SIZE: 20,
+    MAX_PAGE_SIZE: 100,
+} as const;
+
+const API = {
+    BASE_URL: 'https://hiring.cafe/api/search-jobs',
+    HEADERS: {
+        'Content-Type': 'application/json',
+    },
+} as const;
+
+interface GeoLocation {
+    readonly lat: number;
+    readonly lon: number;
+}
+
+interface JobInformation {
+    readonly title: string;
+    readonly description: string;
+}
+
+interface ProcessedJobData {
+    readonly company_name: string;
+    readonly is_compensation_transparent: boolean;
+    readonly yearly_min_compensation?: number;
+    readonly yearly_max_compensation?: number;
+    readonly workplace_type?: string;
+    readonly requirements_summary?: string;
+    readonly job_category: string;
+    readonly role_activities: readonly string[];
+    readonly formatted_workplace_location?: string;
+    readonly estimated_publish_date_millis: string;
+}
+
+interface JobResult {
+    readonly id: string;
+    readonly apply_url: string;
+    readonly job_information: JobInformation;
+    readonly v5_processed_job_data: ProcessedJobData;
+    readonly _geoloc: readonly GeoLocation[];
+}
+
+interface ApiResponse {
+    readonly results: readonly JobResult[];
+    readonly total: number;
+}
+
+interface SearchParams {
+    readonly keywords: string;
+    readonly page?: number;
+    readonly size?: number;
+    readonly sortBy?: 'date' | 'default' | 'compensation_desc' | 'experience_asc';
+}
+
+const validateSearchParams = ({ keywords, page = 0, size = CONFIG.DEFAULT_PAGE_SIZE }: SearchParams): SearchParams => ({
+    keywords: keywords.trim(),
+    page: Math.max(0, Math.floor(Number(page))),
+    size: Math.min(Math.max(1, Math.floor(Number(size))), CONFIG.MAX_PAGE_SIZE),
+});
+
+const fetchJobs = async (searchParams: SearchParams): Promise<ApiResponse> => {
+    const payload = {
+        size: searchParams.size || 20,
+        page: searchParams.page || 0,
+        searchState: {
+            searchQuery: searchParams.keywords,
+            sortBy: searchParams.sortBy || 'date',
+        },
+    };
+
+    return await ofetch<ApiResponse>(API.BASE_URL, {
+        method: 'POST',
+        body: payload,
+        headers: API.HEADERS,
+    });
+};
+
+const renderJobDescription = (jobInfo: JobInformation, processedData: ProcessedJobData): string =>
+    art(path.join(__dirname, 'templates/jobs.art'), {
+        company_name: processedData.company_name,
+        location: processedData.formatted_workplace_location ?? 'Remote/Unspecified',
+        is_compensation_transparent: Boolean(processedData.is_compensation_transparent && processedData.yearly_min_compensation && processedData.yearly_max_compensation),
+        yearly_min_compensation_formatted: processedData.yearly_min_compensation?.toLocaleString() ?? '',
+        yearly_max_compensation_formatted: processedData.yearly_max_compensation?.toLocaleString() ?? '',
+        workplace_type: processedData.workplace_type ?? 'Not specified',
+        requirements_summary: processedData.requirements_summary ?? 'No requirements specified',
+        job_description: jobInfo.description ?? '',
+    });
+
+const transformJobItem = (item: JobResult) => {
+    const { job_information: jobInfo, v5_processed_job_data: processedData, apply_url, id } = item;
+
+    return {
+        title: `${jobInfo.title} - ${processedData.company_name}`,
+        description: renderJobDescription(jobInfo, processedData),
+        link: apply_url,
+        pubDate: new Date(processedData.estimated_publish_date_millis).toUTCString(),
+        category: [processedData.job_category, ...processedData.role_activities, processedData.workplace_type].filter((x): x is string => !!x),
+        author: processedData.company_name,
+        guid: id,
+    };
+};
+
+async function handler(ctx: Context) {
+    const searchParams = validateSearchParams({
+        keywords: ctx.req.param('keywords'),
+    });
+
+    const response = await fetchJobs(searchParams);
+    const items = response.results.map((item) => transformJobItem(item));
+
+    return {
+        title: `HiringCafe Jobs: ${searchParams.keywords}`,
+        description: `Job search results for "${searchParams.keywords}" on HiringCafe`,
+        link: `https://hiring.cafe/jobs?q=${encodeURIComponent(searchParams.keywords)}`,
+        item: items,
+        total: response.total,
+    };
+}
+
+export const route: Route = {
+    path: '/jobs/:keywords',
+    categories: ['other'],
+    example: '/hiring.cafe/jobs/sustainability',
+    parameters: { keywords: 'Keywords to search for' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['hiring.cafe'],
+        },
+    ],
+    name: 'Jobs',
+    maintainers: ['mintyfrankie'],
+    handler,
+};

package/lib/routes/hiring.cafe/namespace.ts

@@ -0,0 +1,10 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'HiringCafe',
+    url: 'hiring.cafe',
+    description: 'HiringCafe is a platform for job seekers to find job opportunities and for employers to post job listings.',
+    zh: {
+        name: 'HiringCafe',
+    },
+};

package/lib/routes/hiring.cafe/templates/jobs.art

@@ -0,0 +1,18 @@
+<p><strong>Company:</strong> {{ company_name }}</p>
+<p><strong>Location:</strong> {{ location }}</p>
+
+{{if is_compensation_transparent}}
+<p><strong>Compensation:</strong> ${{ yearly_min_compensation_formatted }} - ${{ yearly_max_compensation_formatted }} per year</p>
+{{/if}}
+
+<p><strong>Workplace Type:</strong> {{ workplace_type }}</p>
+<p><strong>Requirements:</strong> {{ requirements_summary }}</p>
+
+<div class="job-description">
+    {{@ job_description }}
+</div>
+
+{{if has_company_info}}
+<h2>About {{ company_name }}</h2>
+{{@ company_info_description }}
+{{/if}}

package/lib/routes/hit/namespace.ts

@@ -3,7 +3,7 @@ import type { Namespace } from '@/types';
 export const namespace: Namespace = {
     name: '哈尔滨工业大学',
     url: 'jwc.hit.edu.cn',
-    description: `:::warning
+    description: `::: warning
 哈工大网站疑似禁止了\`rsshub.app\`的访问，使用路由需要自行 [部署](https://docs.rsshub.app/deploy/)。
 :::`,
     lang: 'zh-CN',

package/lib/routes/hit/today.ts

@@ -26,14 +26,14 @@ export const route: Route = {
     name: '今日哈工大',
     maintainers: ['ranpox'],
     handler,
-    description: `:::tip
+    description: `::: tip
   今日哈工大的文章分为公告公示和新闻快讯，每个页面右侧列出了更详细的分类，其编号为每个 URL 路径的最后一个数字。
   例如会议讲座的路径为\`/taxonomy/term/10/25\`，则可以通过 [\`/hit/today/25\`](https://rsshub.app/hit/today/25) 订阅该详细类别。
-  :::
+:::
 
-  :::warning
+::: warning
   部分文章需要经过统一身份认证后才能阅读全文。
-  :::`,
+:::`,
 };
 
 async function handler(ctx) {

package/lib/routes/hkepc/index.ts

@@ -8,7 +8,7 @@ import { baseUrl, categoryMap } from './data';
 
 export const route: Route = {
     path: '/:category?',
-    categories: ['new-media'],
+    categories: ['new-media', 'popular'],
     example: '/hkepc/news',
     parameters: { category: '分类，见下表，默认为最新消息' },
     features: {

package/lib/routes/hket/index.ts

@@ -40,7 +40,19 @@ export const route: Route = {
     },
     radar: [
         {
-            source: ['china.hket.com/:category/*', 'inews.hket.com/:category/*', 'topick.hket.com/:category/*', 'wealth.hket.com/:category/*'],
+            source: ['china.hket.com/:category/*'],
+            target: '/:category',
+        },
+        {
+            source: ['inews.hket.com/:category/*'],
+            target: '/:category',
+        },
+        {
+            source: ['topick.hket.com/:category/*'],
+            target: '/:category',
+        },
+        {
+            source: ['wealth.hket.com/:category/*'],
             target: '/:category',
         },
         {
@@ -121,7 +133,7 @@ async function handler(ctx) {
 
     const $ = cheerio.load(response);
 
-    const list = $('div.listing-title > a')
+    const list = $('.main-listing-container div.listing-title > a')
         .toArray()
         .map((item) => {
             item = $(item);

package/lib/routes/home-assistant/hacs.ts

@@ -0,0 +1,50 @@
+import { Route } from '@/types';
+
+import ofetch from '@/utils/ofetch';
+
+export const route: Route = {
+    path: '/hacs/repositories',
+    name: 'HACS Repositories',
+    maintainers: ['DIYgod'],
+    categories: ['program-update'],
+    example: '/home-assistant/hacs/repositories',
+    handler,
+};
+
+async function handler() {
+    const sections = ['appdaemon', 'critical', 'integration', 'theme', 'python_script', 'plugin'];
+    const dataList = (
+        await Promise.all(
+            sections.map(async (section) => {
+                const url = `https://data-v2.hacs.xyz/${section}/data.json`;
+                const response = await ofetch(url);
+                return Object.values(response);
+            })
+        )
+    ).flat() as {
+        manifest: {
+            name: string;
+        };
+        manifest_name: string;
+        description: string;
+        full_name: string;
+        domain: string;
+        stargazers_count: number;
+        topics?: string[];
+        last_updated: string;
+        last_fetched: number;
+    }[];
+
+    return {
+        title: 'HACS Repositories',
+        link: `https://www.hacs.xyz/`,
+        item: dataList.map((item) => ({
+            title: item.manifest_name || item.manifest?.name || item.full_name,
+            description: `${item.domain ? `<img src="https://brands.home-assistant.io/_/${item.domain}/icon.png" />` : ''}<br>${item.description}<br><br>Last updated: ${item.last_updated}<br>Stars: ${item.stargazers_count}<br>Topics: ${item.topics?.join(', ')}`,
+            link: `https://github.com/${item.full_name}`,
+            guid: item.domain || item.full_name,
+            tags: item.topics,
+            pubDate: new Date(item.last_fetched * 1000),
+        })),
+    };
+}

package/lib/routes/home-assistant/namespace.ts

@@ -0,0 +1,7 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'Home Assistant',
+    url: 'www.home-assistant.io',
+    lang: 'en',
+};

package/lib/routes/hostmonit/cloudflareyesv6.ts

@@ -7,5 +7,5 @@ export const route: Route = {
 };
 
 function handler(ctx) {
-    ctx.redirect('/hostmonit/cloudflareyes/v6');
+    ctx.set('redirect', '/hostmonit/cloudflareyes/v6');
 }

package/lib/routes/hrbeu/sec/list.ts

@@ -0,0 +1,80 @@
+import { Route } from '@/types';
+import cache from '@/utils/cache';
+import got from '@/utils/got';
+import { load } from 'cheerio';
+import { parseDate } from '@/utils/parse-date';
+const rootUrl = 'http://sec.hrbeu.edu.cn';
+
+export const route: Route = {
+    path: '/sec/:id',
+    categories: ['university'],
+    example: '/hrbeu/sec/xshd',
+    parameters: { id: '栏目编号，由 `URL` 中获取。' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['sec.hrbeu.edu.cn/:id/list.htm'],
+        },
+    ],
+    name: '船舶工程学院',
+    maintainers: ['Chi-hong22'],
+    handler,
+    description: `| 学院要闻 | 学术活动 | 通知公告 | 学科方向 |
+| :------: | :------: |:------: | :------: |
+|   xyyw   |   xshd   |  229   |   xkfx   |`,
+};
+
+async function handler(ctx) {
+    const id = ctx.req.param('id');
+    const response = await got(`${rootUrl}/${id}/list.htm`, {
+        headers: {
+            Referer: rootUrl,
+        },
+    });
+
+    const $ = load(response.data);
+
+    const bigTitle = $('div [class=lanmuInnerMiddleBigClass_right]').find('div [portletmode=simpleColumnAttri]').text().replaceAll(/[\s·]/g, '').trim();
+
+    const list = $('li.list_item')
+        .toArray()
+        .map((item) => {
+            let link = $(item).find('a').attr('href');
+            if (link && link.includes('page.htm')) {
+                link = `${rootUrl}${link}`;
+            }
+            return {
+                title: $(item).find('a').attr('title'),
+                pubDate: parseDate($(item).find('span.Article_PublishDate').text()),
+                link,
+            };
+        });
+
+    const items = await Promise.all(
+        list.map((item) =>
+            cache.tryGet(item.link, async () => {
+                if (item.link.includes('page.htm')) {
+                    const detailResponse = await got(item.link);
+                    const content = load(detailResponse.data);
+                    item.description = content('div.wp_articlecontent').html();
+                } else {
+                    item.description = '本文需跳转，请点击标题后阅读';
+                }
+                return item;
+            })
+        )
+    );
+
+    return {
+        title: '船舶工程学院 - ' + bigTitle,
+        link: rootUrl.concat('/', id, '/list.htm'),
+        item: items,
+    };
+}

package/lib/routes/hrbust/jwzx.ts

@@ -37,6 +37,12 @@ export const route: Route = {
     description: `| 名师风采 | 热点新闻 | 教务公告 | 教学新闻 |
   | -------- | -------- | -------- | -------- |
   | 351      | 353      | 354      | 355      |`,
+    radar: [
+        {
+            source: ['jwzx.hrbust.edu.cn/homepage/index.do'],
+            target: '/jwzx',
+        },
+    ],
 };
 
 async function handler(ctx) {

package/lib/routes/hrbust/namespace.ts

@@ -2,6 +2,7 @@ import type { Namespace } from '@/types';
 
 export const namespace: Namespace = {
     name: '哈尔滨理工大学',
-    url: 'jwzx.hrbust.edu.cn',
+    url: 'hrbust.edu.cn',
+    categories: ['university'],
     lang: 'zh-CN',
 };

package/lib/routes/hrbust/news.ts

@@ -0,0 +1,81 @@
+import { Route, ViewType } 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';
+
+const rootUrl = 'https://news.hrbust.edu.cn';
+
+export const route: Route = {
+    path: '/news/:category?',
+    name: '新闻网',
+    url: 'news.hrbust.edu.cn',
+    maintainers: ['cscnk52'],
+    handler,
+    example: '/hrbust/news',
+    parameters: { category: '栏目标识，默认为理工要闻' },
+    description: `
+| lgyw | xwdd | zhenew | jxky | ycdt | xskc | jlhz | zsjy | djsz | zxbf | lgxb | mtlg | jzlt |
+| ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- |
+| 理工要闻 | 新闻导读 | 综合新闻 | 教学科研 | 院处动态 | 学术科创 | 交流合作 | 招生就业 | 党建思政 | 在线播放 | 理工校报 | 媒体理工 | 讲座论坛 |
+`,
+    categories: ['university'],
+    features: {
+        supportRadar: true,
+    },
+    radar: [
+        {
+            source: ['news.hrbust.edu.cn/:category.htm'],
+        },
+    ],
+    view: ViewType.Notifications,
+};
+
+async function handler(ctx) {
+    const { category = 'lgyw' } = ctx.req.param();
+
+    const response = await got(`${rootUrl}/${category}.htm`);
+
+    const $ = load(response.data);
+
+    const bigTitle = $('title').text().split('-')[0].trim();
+
+    const list = $('div.main-liebiao-con-left-bottom li[id^=line_u10]')
+        .toArray()
+        .map((item) => {
+            const element = $(item);
+            const link = new URL(element.find('a').attr('href'), rootUrl).href;
+            const pubDateText = element.find('span').text().trim();
+            const pubDate = pubDateText ? timezone(parseDate(pubDateText), +8) : null;
+            return {
+                title: element.find('a').text().trim(),
+                pubDate,
+                link,
+            };
+        });
+
+    const items = await Promise.all(
+        list.map((item) =>
+            cache.tryGet(item.link, async () => {
+                const detailResponse = await got(item.link);
+                const content = load(detailResponse.data);
+
+                const dateText = content('p.xinxi span:contains("日期时间：")').text().replace('日期时间：', '').trim();
+                const pubTime = dateText ? timezone(parseDate(dateText), +8) : null;
+                if (pubTime) {
+                    item.pubDate = pubTime;
+                }
+
+                item.description = content('div.v_news_content').html() || '本文需跳转，请点击标题后阅读';
+                return item;
+            })
+        )
+    );
+
+    return {
+        title: `哈尔滨理工大学新闻网 - ${bigTitle}`,
+        link: `${rootUrl}/${category}.htm`,
+        item: items,
+    };
+}

package/lib/routes/hubu/index.ts

@@ -90,9 +90,9 @@ export const route: Route = {
     handler,
     example: '/hubu/www/index/tzgg',
     parameters: { category: '分类，可在对应分类页 URL 中找到，默认为[通知公告](https://www.hubu.edu.cn/index/tzgg.htm)' },
-    description: `:::tip
+    description: `::: tip
   若订阅 [通知公告](https://www.hubu.edu.cn/index/tzgg.htm)，网址为 \`https://www.hubu.edu.cn/index/tzgg.htm\`。截取 \`https://www.hubu.edu.cn/\` 到末尾 \`.htm\` 的部分 \`index/tzgg\` 作为参数填入，此时路由为 [\`/hubu/www/index/tzgg\`](https://rsshub.app/hubu/www/index/tzgg)。
-  :::
+:::
 
   | 通知公告   | 学术预告   |
   | ---------- | ---------- |

package/lib/routes/hubu/zhxy.ts

@@ -90,9 +90,9 @@ export const route: Route = {
     handler,
     example: '/hubu/zhxy/index/tzgg',
     parameters: { category: '分类，可在对应分类页 URL 中找到，默认为[通知公告](https://zhxy.hubu.edu.cn/index/tzgg.htm)' },
-    description: `:::tip
+    description: `::: tip
   若订阅 [通知公告](https://zhxy.hubu.edu.cn/index/tzgg.htm)，网址为 \`https://zhxy.hubu.edu.cn/index/tzgg.htm\`。截取 \`https://zhxy.hubu.edu.cn/\` 到末尾 \`.htm\` 的部分 \`index/tzgg\` 作为参数填入，此时路由为 [\`/hubu/zhxy/index/tzgg\`](https://rsshub.app/hubu/zhxy/index/tzgg)。
-  :::
+:::
 
   | [通知公告](https://zhxy.hubu.edu.cn/index/tzgg.htm) | [新闻动态](https://zhxy.hubu.edu.cn/index/xwdt.htm) |
   | --------------------------------------------------- | --------------------------------------------------- |