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

package/lib/routes/nikkei/cn/index.ts

@@ -9,9 +9,45 @@ import parser from '@/utils/rss-parser';
 
 export const route: Route = {
     path: '/cn/*',
-    name: 'Unknown',
-    maintainers: [],
+    name: '中文版新闻',
+    example: '/nikkei/cn',
+    maintainers: ['nczitzk'],
     handler,
+    description: `::: tip
+  如 [中国 经济 日经中文网](https://cn.nikkei.com/china/ceconomy.html) 的 URL 为 \`https://cn.nikkei.com/china/ceconomy.html\` 对应路由为 [\`/nikkei/cn/cn/china/ceconomy\`](https://rsshub.app/nikkei/cn/cn/china/ceconomy)
+
+  如 [中國 經濟 日經中文網](https://zh.cn.nikkei.com/china/ceconomy.html) 的 URL 为 \`https://zh.cn.nikkei.com/china/ceconomy.html\` 对应路由为 [\`/nikkei/cn/zh/china/ceconomy\`](https://rsshub.app/nikkei/cn/zh/china/ceconomy)
+
+  特别地，当 \`path\` 填入 \`rss\` 后（如路由为 [\`/nikkei/cn/cn/rss\`](https://rsshub.app/nikkei/cn/cn/rss)），此时返回的是 [官方 RSS 的内容](https://cn.nikkei.com/rss.html)
+:::`,
+    radar: [
+        {
+            title: '中文版新闻',
+            source: ['cn.nikkei.com/:category/:type', 'cn.nikkei.com/:category', 'cn.nikkei.com/'],
+            target: (params) => {
+                if (params.category && params.type) {
+                    return `/nikkei/cn/cn/${params.category}/${params.type.replace('.html', '')}`;
+                } else if (params.category && !params.type) {
+                    return `/nikkei/cn/cn/${params.category.replace('.html', '')}`;
+                } else {
+                    return `/nikkei/cn/cn`;
+                }
+            },
+        },
+        {
+            title: '中文版新聞',
+            source: ['zh.cn.nikkei.com/:category/:type', 'zh.cn.nikkei.com/:category', 'zh.cn.nikkei.com/'],
+            target: (params) => {
+                if (params.category && params.type) {
+                    return `/nikkei/cn/zh/${params.category}/${params.type.replace('.html', '')}`;
+                } else if (params.category && !params.type) {
+                    return `/nikkei/cn/zh/${params.category.replace('.html', '')}`;
+                } else {
+                    return `/nikkei/cn/zh`;
+                }
+            },
+        },
+    ],
 };
 
 async function handler(ctx) {
@@ -20,7 +56,7 @@ async function handler(ctx) {
 
     if (/^\/cn\/(cn|zh)/.test(path)) {
         language = path.match(/^\/cn\/(cn|zh)/)[1];
-        path = path.match(new RegExp('\\/cn\\/' + language + '(.*)'))[1];
+        path = path.match(new RegExp(String.raw`\/cn\/` + language + '(.*)'))[1];
     } else {
         language = 'cn';
     }
@@ -40,7 +76,7 @@ async function handler(ctx) {
         officialFeed = await parser.parseURL(currentUrl);
         items = officialFeed.items.slice(0, limit).map((item) => ({
             title: item.title,
-            link: new URL(item.attr('href'), rootUrl).href,
+            link: new URL(item.link, rootUrl).href,
         }));
     } else {
         const response = await got({

package/lib/routes/nikkei/index.ts

@@ -3,11 +3,12 @@ import got from '@/utils/got';
 import { load } from 'cheerio';
 
 export const route: Route = {
-    path: ['/', '/index'],
-    name: 'Unknown',
-    maintainers: [],
+    path: '/index',
+    name: 'Home',
+    example: '/nikkei/index',
+    maintainers: ['zjysdhr'],
     handler,
-    url: 'www.nikkei.com/',
+    url: 'www.nikkei.com',
 };
 
 async function handler() {

package/lib/routes/nikkei/namespace.ts

@@ -2,5 +2,5 @@ import type { Namespace } from '@/types';
 
 export const namespace: Namespace = {
     name: 'The Nikkei 日本経済新聞',
-    url: 'asia.nikkei.com',
+    url: 'nikkei.com',
 };

package/lib/routes/nikkei/news.ts

@@ -10,9 +10,9 @@ import { art } from '@/utils/render';
 import path from 'node:path';
 
 export const route: Route = {
-    path: '/:category/:article_type?',
+    path: '/news/:category/:article_type?',
     categories: ['traditional-media'],
-    example: '/nikkei/news',
+    example: '/nikkei/news/news',
     parameters: { category: 'Category, see table below', article_type: 'Only includes free articles, set `free` to enable, disabled by default' },
     radar: [
         {

package/lib/routes/njxzc/utils/index.ts

@@ -1,12 +1,15 @@
 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 ofetch from '@/utils/ofetch'; // 使用默认导出的方式导入ofetch
 
 async function getNoticeList(ctx, url, host, titleSelector, dateSelector, contentSelector, listSelector) {
-    const response = await got(url);
-    const $ = load(response.data);
+    const response = await ofetch(url).catch(() => null);
+    if (!response) {
+        return [];
+    }
+    const $ = load(response);
 
     const list = $(listSelector)
         .toArray()
@@ -22,20 +25,35 @@ async function getNoticeList(ctx, url, host, titleSelector, dateSelector, conten
     const out = await Promise.all(
         list.map((item) =>
             cache.tryGet(item.link, async () => {
-                const response = await got(item.link);
-                if (response.redirectUrls.length) {
-                    item.link = response.redirectUrls[0];
+                const response = await ofetch(item.link).catch(() => null);
+                if (!response || (response.status >= 300 && response.status < 400)) {
+                    return {
+                        ...item,
+                        description: '该通知无法直接预览，请点击原文链接↑查看',
+                    };
+                }
+                const $ = load(response);
+
+                if ($('.wp_error_msg').length > 0) {
+                    item.description = '您当前ip并非校内地址，该信息仅允许校内地址访问';
+                } else if ($('.wp_pdf_player').length > 0) {
                     item.description = '该通知无法直接预览，请点击原文链接↑查看';
                 } else {
-                    const $ = load(response.data);
+                    const contentHtml = $(contentSelector.content).html();
+                    const $content = load(contentHtml);
+                    $content('a').each(function () {
+                        const a = $(this);
+                        const href = a.attr('href');
+                        if (href && !href.startsWith('http')) {
+                            a.attr('href', new URL(href, host).href);
+                        }
+                    });
+                    item.description = $content.html();
                     item.title = $(contentSelector.title).text();
-                    item.description = $(contentSelector.content)
-                        .html()
-                        .replaceAll('src="/', `src="${new URL('.', host).href}`)
-                        .replaceAll('href="/', `href="${new URL('.', host).href}`)
-                        .trim();
-                    item.pubDate = timezone(parseDate($(contentSelector.date).text().replace('编辑：', '').replace('发布日期：', '').replace('发布时间：', '')), +8);
+                    const dateText = $(contentSelector.date).text().replace('编辑：', '').replace('发布日期：', '').replace('发布时间：', '');
+                    item.pubDate = timezone(parseDate(dateText, 'YYYY-MM-DD'), +8);
                 }
+
                 return item;
             })
         )

package/lib/routes/nmc/weatheralarm.ts

@@ -69,6 +69,7 @@ async function handler(ctx) {
     return {
         title: '中央气象台全国气象预警',
         link: 'http://www.nmc.cn/publish/alarm.html',
+        allowEmpty: true,
         item: items,
     };
 }

package/lib/routes/notion/release.ts

@@ -0,0 +1,81 @@
+import type { DataItem, Route } from '@/types';
+import { load } from 'cheerio';
+import ofetch from '@/utils/ofetch';
+import { parseDate } from '@/utils/parse-date';
+import cache from '@/utils/cache';
+import day from 'dayjs';
+
+const handler: Route['handler'] = async () => {
+    const data = await ofetch('https://notion.so/releases', {
+        headers: {
+            'Accept-Language': 'en-US', // TODO accept param
+        },
+    });
+
+    const $ = load(data);
+
+    // the first post, do not cache
+    const title = $('h2').first().text() ?? '';
+    const pubDate = parseDate($('time').first().text());
+    const description = $('article.release article').first().html() ?? '';
+    const link = `https://notion.so/releases/${day(pubDate).format('YYYY-MM-DD')}`;
+
+    // archive
+    const item = (await Promise.all(
+        $('div[class^="releasePreviewsSection"] h3 a[href^="/releases/"]')
+            .toArray()
+            .slice(0, 5)
+            .map((item) => {
+                const link = `https://notion.so${item.attribs.href}`;
+
+                return cache.tryGet(`notion:release:${link}`, async () => {
+                    const data = await ofetch(link, {
+                        headers: {
+                            'Accept-Language': 'en-US', // Notion will adjust returned content based on this header
+                        },
+                    });
+
+                    const $ = load(data);
+
+                    return {
+                        title: $('h2').first().text() ?? '',
+                        pubDate: parseDate($('time').first().text()),
+                        description: $('article.release article').first().html() ?? '',
+                        link,
+                    };
+                });
+            })
+    )) as DataItem[];
+
+    return {
+        title: 'Notion Releases',
+        link: 'https://notion.so/releases',
+        item: [
+            {
+                title,
+                description,
+                pubDate,
+                link,
+            },
+            ...item,
+        ],
+    };
+};
+
+export const route: Route = {
+    name: 'Release',
+    path: '/release',
+    url: 'notion.so/releases',
+    example: '/notion/release',
+    categories: ['program-update'],
+    maintainers: ['equt'],
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    handler,
+};

package/lib/routes/npm/package.ts

@@ -2,14 +2,21 @@ import { Route } from '@/types';
 import { getCurrentPath } from '@/utils/helpers';
 const __dirname = getCurrentPath(import.meta.url);
 
-import got from '@/utils/got';
+import ofetch from '@/utils/ofetch';
 import { art } from '@/utils/render';
 import path from 'node:path';
 
 export const route: Route = {
-    path: 'package/:name{(@[a-z0-9-~][a-z0-9-._~]*/)?[a-z0-9-~][a-z0-9-._~]*}',
-    name: 'Unknown',
-    maintainers: [],
+    path: '/package/:name{(@[a-z0-9-~][a-z0-9-._~]*/)?[a-z0-9-~][a-z0-9-._~]*}',
+    name: 'Package',
+    maintainers: ['Fatpandac'],
+    categories: ['program-update'],
+    example: '/npm/package/rsshub',
+    radar: [
+        {
+            source: ['www.npmjs.com/package/:name'],
+        },
+    ],
     handler,
 };
 
@@ -20,10 +27,10 @@ async function handler(ctx) {
     const packageDownloadLastDayAPI = `https://api.npmjs.org/downloads/point/last-day/${name}`; // 按天统计
     const packageVersionAPI = `https://registry.npmjs.org/${name}`; // 包基本信息
 
-    const downloadCountLastMonthRes = await got(packageDownloadLastMonthAPI).json();
-    const downloadCountLastWeekRes = await got(packageDownloadLastWeekAPI).json();
-    const downloadCountLastDayRes = await got(packageDownloadLastDayAPI).json();
-    const packageVersionRes = await got(packageVersionAPI).json();
+    const downloadCountLastMonthRes = await ofetch(packageDownloadLastMonthAPI);
+    const downloadCountLastWeekRes = await ofetch(packageDownloadLastWeekAPI);
+    const downloadCountLastDayRes = await ofetch(packageDownloadLastDayAPI);
+    const packageVersionRes = await ofetch(packageVersionAPI);
 
     const packageVersion = packageVersionRes.time;
     const packageVersionList = Object.keys(packageVersion)

package/lib/routes/nudt/namespace.ts

@@ -0,0 +1,6 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: '中国人民解放军国防科技大学',
+    url: 'www.nudt.edu.cn',
+};

package/lib/routes/nudt/yjszs.ts

@@ -0,0 +1,68 @@
+import { Route } from '@/types';
+import got from '@/utils/got';
+import { load } from 'cheerio';
+import { parseDate } from '@/utils/parse-date';
+import InvalidParameterError from '@/errors/types/invalid-parameter';
+import timezone from '@/utils/timezone';
+
+/* 研究生院*/
+const host = 'http://yjszs.nudt.edu.cn';
+
+const yjszs = new Map([
+    // http://yjszs.nudt.edu.cn//pubweb/homePageList/searchContent.view
+    ['tzgg', { title: '国防科技大学研究生院 - 通知公告', view: 'searchContent' }],
+    // http://yjszs.nudt.edu.cn//pubweb/homePageList/recruitStudents.view?keyId=16
+    ['sszs', { title: '国防科技大学研究生院 - 硕士招生', view: 'recruitStudents', keyId: '16' }],
+]);
+
+export const route: Route = {
+    path: '/yjszs/:type?',
+    categories: ['university'],
+    example: '/nudt/yjszs/sszs',
+    parameters: { type: '分类，见下表，默认为硕士招生' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    name: '研究生院',
+    maintainers: ['Blank0120'],
+    handler,
+    url: 'yjszs.nudt.edu.cn/',
+    description: `| 通知公告 | 硕士招生 |
+  | -------- | -------- |
+  | tzgg     | sszs     |`,
+};
+
+async function handler(ctx) {
+    const type = ctx.req.param('type') ?? 'sszs';
+    const info = yjszs.get(type);
+    if (!info) {
+        throw new InvalidParameterError('invalid type');
+    }
+    const link = `${host}/pubweb/homePageList/${info.view}.view?keyId=${info.keyId ?? ''}`;
+    const response = await got({
+        method: 'get',
+        url: link,
+    });
+
+    const $ = load(response.data);
+    const content = $('.news-list li');
+    const items = content.toArray().map((elem) => {
+        elem = $(elem);
+        return {
+            link: new URL(elem.find('a').attr('href'), host).href,
+            title: elem.find('h3').text().trim(),
+            pubDate: timezone(parseDate(elem.find('.time').text(), 'YYYY-MM-DD'), -8),
+        };
+    });
+
+    return {
+        title: info.title,
+        link,
+        item: items,
+    };
+}

package/lib/routes/nyaa/main.ts

@@ -16,7 +16,7 @@ export const route: Route = {
         supportScihub: false,
     },
     name: 'Search Result',
-    maintainers: ['Lava-Swimmer', 'noname1776'],
+    maintainers: ['Lava-Swimmer', 'noname1776', 'camera-2018'],
     handler,
 };
 
@@ -32,7 +32,7 @@ async function handler(ctx) {
 
     const { query, username } = ctx.req.param();
 
-    const rootURL = ctx.routerPath.split('/')[1] === 'sukebei' ? 'https://sukebei.nyaa.si' : 'https://nyaa.si';
+    const rootURL = ctx.req.path.split('/')[2] === 'sukebei' ? 'https://sukebei.nyaa.si' : 'https://nyaa.si';
 
     let currentRSSURL = `${rootURL}/?page=rss`;
     let currentLink = `${rootURL}/`;
@@ -48,7 +48,6 @@ async function handler(ctx) {
     const feed = await parser.parseURL(currentRSSURL);
 
     feed.items.map((item) => {
-        item.link = item.guid;
         item.description = item.content;
         item.enclosure_url = `magnet:?xt=urn:btih:${item.infoHash}`;
         item.enclosure_type = 'application/x-bittorrent';

package/lib/routes/nyaa/namespace.ts

@@ -3,4 +3,14 @@ import type { Namespace } from '@/types';
 export const namespace: Namespace = {
     name: 'Nyaa',
     url: 'nyaa.si',
+    description: `
+    :::tip
+The 'Nyaa' includes several routes to access different parts of the site:
+1. \`/nyaa/search/:query?\` - Use this route to search for content with a specific query. For example, \`/nyaa/search/bocchi\` to search for bocchi related content.
+2. \`/nyaa/user/:username?\` - Access a user's profile by their username, e.g., \`/nyaa/user/ANiTorrent\`.
+3. \`/nyaa/user/:username/search/:query?\` - Search within a specific user's submissions using a query, e.g., \`/nyaa/user/ANiTorrent/search/bocchi\`.
+4. \`/nyaa/sukebei/search/:query?\` - This route is for searching adult content with a specific query, e.g., \`/nyaa/sukebei/search/hentai\`.
+5. \`/nyaa/sukebei/user/:username?\` - Access an adult content user's profile, e.g., \`/nyaa/sukebei/user/milannews\`.
+6. \`/nyaa/sukebei/user/:username/search/:query?\` - Search within a specific user's adult content submissions, e.g., \`/nyaa/sukebei/user/milannews/search/hentai\`.
+:::`,
 };

package/lib/routes/nytimes/book.ts

@@ -1,4 +1,4 @@
-import { Route } from '@/types';
+import { Route, ViewType } from '@/types';
 import got from '@/utils/got';
 import { load } from 'cheerio';
 
@@ -18,9 +18,19 @@ const categoryList = {
 
 export const route: Route = {
     path: '/book/:category?',
-    categories: ['traditional-media'],
+    categories: ['traditional-media', 'popular'],
+    view: ViewType.Notifications,
     example: '/nytimes/book/combined-print-and-e-book-nonfiction',
-    parameters: { category: 'N' },
+    parameters: {
+        category: {
+            description: 'Category, can be found on the [official page](https://www.nytimes.com/books/best-sellers/)',
+            options: Object.keys(categoryList).map((key) => ({
+                value: key,
+                label: categoryList[key],
+            })),
+            default: 'combined-print-and-e-book-nonfiction',
+        },
+    },
     features: {
         requireConfig: false,
         requirePuppeteer: false,
@@ -36,22 +46,9 @@ export const route: Route = {
         },
     ],
     name: 'Best Seller Books',
-    maintainers: ['melvinto'],
+    maintainers: ['melvinto', 'pseudoyu'],
     handler,
     url: 'nytimes.com/',
-    description: `| Category                             |
-| ------------------------------------ |
-| combined-print-and-e-book-nonfiction |
-| hardcover-nonfiction                 |
-| paperback-nonfiction                 |
-| advice-how-to-and-miscellaneous      |
-| combined-print-and-e-book-fiction    |
-| hardcover-fiction                    |
-| trade-fiction-paperback              |
-| childrens-middle-grade-hardcover     |
-| picture-books                        |
-| series-books                         |
-| young-adult-hardcover                |`,
 };
 
 async function handler(ctx) {

package/lib/routes/nytimes/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 parser from '@/utils/rss-parser';
@@ -8,9 +8,20 @@ import puppeteer from '@/utils/puppeteer';
 
 export const route: Route = {
     path: '/:lang?',
-    categories: ['traditional-media'],
+    categories: ['traditional-media', 'popular'],
+    view: ViewType.Articles,
     example: '/nytimes/dual',
-    parameters: { lang: 'language, default to Chinese' },
+    parameters: {
+        lang: {
+            description: 'language, default to Chinese',
+            options: [
+                { value: 'dual', label: 'Chinese-English' },
+                { value: 'en', label: 'English' },
+                { value: 'traditionalchinese', label: 'Traditional Chinese' },
+                { value: 'dual-traditionalchinese', label: 'Chinese-English (Traditional Chinese)' },
+            ],
+        },
+    },
     features: {
         requireConfig: false,
         requirePuppeteer: false,
@@ -26,14 +37,10 @@ export const route: Route = {
         },
     ],
     name: 'News',
-    maintainers: ['HenryQW'],
+    maintainers: ['HenryQW', 'pseudoyu'],
     handler,
     url: 'nytimes.com/',
-    description: `By extracting the full text of articles, we provide a better reading experience (full text articles) over the official one.
-
-  | Default to Chinese | Chinese-English | English | Chinese-English (Traditional Chinese) | Traditional Chinese |
-  | ------------------ | --------------- | ------- | ------------------------------------- | ------------------- |
-  | (empty)            | dual            | en      | dual-traditionalchinese               | traditionalchinese  |`,
+    description: `By extracting the full text of articles, we provide a better reading experience (full text articles) over the official one.`,
 };
 
 async function handler(ctx) {

package/lib/routes/obsidian/namespace.ts

@@ -0,0 +1,6 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'Obsidian',
+    url: 'obsidian.md',
+};

package/lib/routes/obsidian/publish.ts

@@ -0,0 +1,83 @@
+import { Route, DataItem } from '@/types';
+import { load } from 'cheerio';
+import ofetch from '@/utils/ofetch';
+import { getTitle } from './utils';
+import { config } from '@/config';
+import { parseDate } from '@/utils/parse-date';
+
+export const route: Route = {
+    path: '/publish/:id',
+    categories: ['blog'],
+    example: '/obsidian/publish/marshallontheroad',
+    parameters: { id: '网站 id，由Publish持有者自定义' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['publish.obsidian.md/'],
+        },
+    ],
+    name: 'Publish',
+    maintainers: ['Xy2002'],
+    handler,
+    url: 'publish.obsidian.md/',
+};
+
+async function handler(ctx) {
+    const id = ctx.req.param('id');
+    const items = await fetchPage(id);
+
+    return {
+        title: 'Obsidian Publish',
+        language: 'en-us',
+        item: items,
+        link: 'https://publish.obsidian.md/',
+    };
+}
+
+async function fetchPage(id: string) {
+    const baseUrl = `https://publish.obsidian.md/${id}`;
+    const response = await ofetch(baseUrl);
+    const $ = load(response);
+    const preloadCacheUrl =
+        $('script:contains("preloadCache")')
+            .text()
+            .match(/preloadCache\s*=\s*f\("([^"]+)"\);/)?.[1] || '';
+
+    let preloadCacheResponse: Record<string, { frontmatter?: Record<string, string> }>;
+    try {
+        preloadCacheResponse = await ofetch(preloadCacheUrl, {
+            headers: {
+                'User-Agent': config.trueUA,
+                Referer: 'https://publish.obsidian.md/',
+                Origin: 'https://publish.obsidian.m/',
+            },
+        });
+    } catch {
+        preloadCacheResponse = {};
+    }
+
+    const items: DataItem[] = Object.entries(preloadCacheResponse)
+        .map(([postKey, post]) => {
+            if (!post) {
+                return null;
+            }
+            const item: DataItem = {
+                title: post.frontmatter?.title || getTitle(postKey),
+                link: `${baseUrl}/${postKey.replaceAll(' ', '+').split('.md')[0]}`,
+                pubDate: post.frontmatter?.['date created'] ? parseDate(post.frontmatter['date created']) : undefined,
+                ...post.frontmatter,
+            };
+
+            return item;
+        })
+        .filter(Boolean) as DataItem[];
+
+    return items;
+}

package/lib/routes/obsidian/utils.ts

@@ -0,0 +1,8 @@
+const regex = /([^/]+)\.md$/;
+
+const getTitle = (path: string): string => {
+    const match = path.match(regex);
+    return match ? match[1] : '';
+};
+
+export { getTitle };

package/lib/routes/oct0pu5/namespace.ts

@@ -0,0 +1,10 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'Oct0pu5 blog',
+    url: 'Oct0pu5.cn',
+
+    zh: {
+        name: 'Oct0pu5的小破站',
+    },
+};