rsshub 1.0.0-master.f72af1b → 1.0.0-master.f7347d9

package/lib/routes/misskon/posts.ts

@@ -0,0 +1,33 @@
+import { Route } from '@/types';
+import { ENDPOINT, getPosts } from './utils';
+
+export const route: Route = {
+    path: '/posts/:routeParams?',
+    categories: ['picture'],
+    example: '/misskon/posts/search=video&tags_exclude=353,3100&per_page=5',
+    parameters: { routeParams: 'Additional parameters for filtering posts, refer to [WordPress API Reference](https://developer.wordpress.org/rest-api/reference/posts/#arguments) for details.' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['misskon.com/'],
+            target: '/posts',
+        },
+    ],
+    name: 'Posts',
+    maintainers: ['Urabartin'],
+    handler: async (ctx) => {
+        const { routeParams = '' } = ctx.req.param();
+        return {
+            title: `MissKON - ${routeParams || 'Posts'}`,
+            link: `${ENDPOINT}/posts` + (routeParams ? `?${routeParams}` : ''),
+            item: await getPosts(routeParams),
+        };
+    },
+};

package/lib/routes/misskon/tag.ts

@@ -0,0 +1,38 @@
+import { Route } from '@/types';
+import { getPosts, getTags } from './utils';
+
+export const route: Route = {
+    path: '/tag/:tag',
+    categories: ['picture'],
+    example: '/misskon/tag/cosplay',
+    parameters: { tag: 'Any tag that exists in MissKon' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['misskon.com/tag/:tag/'],
+            target: '/tag/:tag',
+        },
+    ],
+    name: 'Tag',
+    maintainers: ['Urabartin'],
+    handler: async (ctx) => {
+        const { tag } = ctx.req.param();
+        const tagData = await getTags(tag);
+        const searchParams = new URLSearchParams();
+        searchParams.set('tags', tagData.id);
+        const items = await getPosts(searchParams.toString());
+        return {
+            title: `MissKON - ${tagData.name}`,
+            link: tagData.link,
+            description: tagData.description,
+            item: items,
+        };
+    },
+};

package/lib/routes/misskon/top.ts

@@ -0,0 +1,67 @@
+import { Route } from '@/types';
+import ofetch from '@/utils/ofetch';
+import { load } from 'cheerio';
+import { getPosts } from './utils';
+
+export const route: Route = {
+    path: '/top/:k',
+    categories: ['picture'],
+    example: '/misskon/top/60',
+    parameters: { k: 'Top k days, can be 3, 7, 30 or 60' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            title: 'Top 3 days',
+            source: ['misskon.com/top3/'],
+            target: '/top/3',
+        },
+        {
+            title: 'Top 7 days',
+            source: ['misskon.com/top7/'],
+            target: '/top/7',
+        },
+        {
+            title: 'Top 30 days',
+            source: ['misskon.com/top30/'],
+            target: '/top/30',
+        },
+        {
+            title: 'Top 60 days',
+            source: ['misskon.com/top60/'],
+            target: '/top/60',
+        },
+    ],
+    name: 'Top k days',
+    maintainers: ['Urabartin'],
+    handler: async (ctx) => {
+        const { k } = ctx.req.param();
+        if (!['3', '7', '30', '60'].includes(k)) {
+            throw new Error(`Invalid k: k=${k}`);
+        }
+        const topLink = `https://misskon.com/top${k}/`;
+        const response = await ofetch(topLink);
+        const $ = load(response);
+
+        const feedTitle = $('.page-title').text();
+        const feedDesc = $('.content > p').first().text();
+        const itemSlugs = $('#main-content article.item-list > h2 a')
+            .toArray()
+            .map((link) => new URL($(link).attr('href') || '').pathname.slice(1, -1));
+        const searchParams = new URLSearchParams();
+        searchParams.set('slug', itemSlugs.join(','));
+        searchParams.set('per_page', itemSlugs.length.toString());
+        return {
+            title: `MissKON - ${feedTitle}`,
+            link: topLink,
+            description: feedDesc,
+            item: await getPosts(searchParams),
+        };
+    },
+};

package/lib/routes/misskon/utils.ts

@@ -0,0 +1,41 @@
+import ofetch from '@/utils/ofetch';
+import { load } from 'cheerio';
+import { parseDate } from '@/utils/parse-date';
+import timezone from '@/utils/timezone';
+
+const ENDPOINT = 'https://misskon.com/wp-json/wp/v2';
+const getPosts = async (searchParams) => {
+    const url = new URL(`${ENDPOINT}/posts?${searchParams}`);
+    url.searchParams.append('_embed', 'wp:term');
+    const data = await ofetch(url.href);
+    return data.map((item) => {
+        const $ = load(item.content.rendered);
+        $('input').each(function () {
+            $(this).replaceWith($(this).attr('value') || '');
+        });
+        $('script').remove();
+        return {
+            title: item.title.rendered,
+            link: item.link,
+            description: $.html(),
+            pubDate: timezone(parseDate(item.date_gmt), 0),
+            category: item._embedded['wp:term']
+                .flat()
+                .filter((x) => x.taxonomy === 'post_tag')
+                .map((x) => x.name),
+        };
+    });
+};
+const getTags = async (slug) => {
+    const data = await ofetch(`${ENDPOINT}/tags?slug=${slug}`);
+    if (data.length === 0) {
+        throw new Error(`Invalid tag slug: ${slug}`);
+    }
+    return {
+        id: data[0].id,
+        name: data[0].name,
+        link: data[0].link,
+        description: data[0].description,
+    };
+};
+export { ENDPOINT, getPosts, getTags };

package/lib/routes/natgeo/dailyphoto.ts

@@ -12,7 +12,7 @@ import { config } from '@/config';
 
 export const route: Route = {
     path: '/dailyphoto',
-    categories: ['picture', 'popular'],
+    categories: ['picture'],
     view: ViewType.Pictures,
     example: '/natgeo/dailyphoto',
     parameters: {},

package/lib/routes/natgeo/dailyselection.ts

@@ -21,7 +21,7 @@ export const route: Route = {
             source: ['nationalgeographic.com/'],
         },
     ],
-    maintainers: ['OrangeEd1t', 'pseudoyu'],
+    maintainers: ['OrangeEd1t'],
     handler,
 };
 

package/lib/routes/ncku/namespace.ts

@@ -2,5 +2,5 @@ import type { Namespace } from '@/types';
 
 export const namespace: Namespace = {
     name: 'National Cheng Kung University',
-    url: 'ncku.edu.tw',
+    url: 'www.ncku.edu.tw',
 };

package/lib/routes/ncku/phys.ts

@@ -0,0 +1,95 @@
+import type { Route } from '@/types';
+import { CheerioAPI, load } from 'cheerio';
+import ofetch from '@/utils/ofetch';
+
+const currentURL = (catagory: string) => `https://phys.ncku.edu.tw/news/${catagory === '_all' ? '' : catagory}`;
+
+const catagories = {
+    '24': '物理系',
+    scholarship: '獎助學金',
+    admission: '招生與錄取報到',
+    'course-announcement': '助教公告',
+    'bachelor-announcement': '大學部',
+    'master-announcement': '研究所',
+    graduation: '畢業離校',
+    'student-guide': '學生手冊與新生入學',
+    honor: '榮譽榜',
+    career: '求才公告',
+    others: '其他',
+    _all: '所有訊息',
+};
+
+export const route: Route = {
+    'zh-TW': {
+        name: '國立成功大學物理系公告',
+    },
+    name: 'Phys News',
+    description: `| 分類 | catagory |
+| 物理系 | 24 |
+| 獎助學金 | scholarship |
+| 招生與錄取報到 | admission |
+| 助教公告 | course-announcement |
+| 大學部 | bachelor-announcement |
+| 研究所 | master-announcement |
+| 畢業離校 | graduation |
+| 學生手冊與新生入學 | student-guide |
+| 榮譽榜 | honor |
+| 求才公告 | career |
+| 其他 | others |
+| 所有訊息 | _all |
+`,
+    path: '/phys/:catagory?',
+    parameters: {
+        catagory: 'catagory, default is _all',
+    },
+    categories: ['university'],
+    example: '/ncku/phys/_all',
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['phys.ncku.edu.tw/news/'],
+            target: '/phys/_all',
+        },
+        {
+            source: ['phys.ncku.edu.tw/news/:catagory/'],
+            target: '/phys/:catagory',
+        },
+    ],
+    maintainers: ['simbafs'],
+    handler: async (ctx) => {
+        let catagory = ctx.req.param('catagory') ?? '_all';
+        if (catagories[catagory] === undefined) {
+            catagory = '_all';
+        }
+
+        const $ = await ofetch<CheerioAPI>(currentURL(catagory), {
+            parseResponse: load,
+        });
+
+        const item = $('.newsList .Txt')
+            .toArray()
+            .map((e) => ({
+                title: $('a', e).text(),
+                pubDate: new Date(
+                    $('.newsDate', e)
+                        .text()
+                        .match(/\d{4}(?: \/ \d{2}){2}/)?.[0] || ''
+                ),
+                link: $('a', e).attr('href'),
+                catagory: $('.newIcon', e).text(),
+            }));
+
+        return {
+            title: `成大物理系公告 - ${catagories[catagory]}`,
+            link: currentURL(catagory),
+            item,
+        };
+    },
+};

package/lib/routes/news/namespace.ts

@@ -1,6 +1,6 @@
 import type { Namespace } from '@/types';
 
 export const namespace: Namespace = {
-    name: '小黑盒',
+    name: '新华社',
     url: 'news.cn',
 };

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

@@ -5,7 +5,18 @@ import got from '@/utils/got';
 import { load } from 'cheerio';
 import timezone from '@/utils/timezone';
 import { parseDate } from '@/utils/parse-date';
-import parser from '@/utils/rss-parser';
+import { config } from '@/config';
+import Parser from 'rss-parser';
+
+const parser = new Parser({
+    customFields: {
+        item: ['magnet'],
+    },
+    headers: {
+        'User-Agent': config.ua,
+    },
+    defaultRSS: 0.9,
+});
 
 export const route: Route = {
     path: '/cn/*',

package/lib/routes/nudt/yjszs.ts

@@ -5,21 +5,35 @@ import { parseDate } from '@/utils/parse-date';
 import InvalidParameterError from '@/errors/types/invalid-parameter';
 import timezone from '@/utils/timezone';
 
-/* 研究生院*/
+/* 研究生院 */
 const host = 'http://yjszs.nudt.edu.cn';
 
+// 目前研究生院最近仍在更新的链接
 const yjszs = new Map([
+    // http://yjszs.nudt.edu.cn/pubweb/homePageList/recruitStudents.view?keyId=2
     // 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' }],
+    ['2', { title: '国防科技大学研究生院 - 通知公告' }],
+    // http://yjszs.nudt.edu.cn/pubweb/homePageList/recruitStudents.view?keyId=1
+    ['1', { title: '国防科技大学研究生院 - 首页' }],
+    // http://yjszs.nudt.edu.cn/pubweb/homePageList/recruitStudents.view?keyId=8
+    ['8', { title: '国防科技大学研究生院 - 招生简章' }],
+    // http://yjszs.nudt.edu.cn/pubweb/homePageList/recruitStudents.view?keyId=12
+    ['12', { title: '国防科技大学研究生院 - 学校政策' }],
     // 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' }],
+    ['16', { title: '国防科技大学研究生院 - 硕士招生' }],
+    // http://yjszs.nudt.edu.cn/pubweb/homePageList/recruitStudents.view?keyId=17
+    ['17', { title: '国防科技大学研究生院 - 博士招生' }],
+    // http://yjszs.nudt.edu.cn/pubweb/homePageList/recruitStudents.view?keyId=23
+    ['23', { title: '国防科技大学研究生院 - 院所发文' }],
+    // http://yjszs.nudt.edu.cn/pubweb/homePageList/recruitStudents.view?keyId=25
+    ['25', { title: '国防科技大学研究生院 - 数据统计' }],
 ]);
 
 export const route: Route = {
-    path: '/yjszs/:type?',
+    path: '/yjszs/:keyId?',
     categories: ['university'],
-    example: '/nudt/yjszs/sszs',
-    parameters: { type: '分类，见下表，默认为硕士招生' },
+    example: '/nudt/yjszs/2',
+    parameters: { keyId: '分类，见下表，默认为通知公告' },
     features: {
         requireConfig: false,
         requirePuppeteer: false,
@@ -28,22 +42,28 @@ export const route: Route = {
         supportPodcast: false,
         supportScihub: false,
     },
+    radar: [
+        {
+            source: ['yjszs.nudt.edu.cn'],
+        },
+    ],
     name: '研究生院',
     maintainers: ['Blank0120'],
     handler,
     url: 'yjszs.nudt.edu.cn/',
-    description: `| 通知公告 | 硕士招生 |
-  | -------- | -------- |
-  | tzgg     | sszs     |`,
+    description: `| 通知公告 | 首页 | 招生简章 | 学校政策 | 硕士招生 | 博士招生 | 院所发文 | 数据统计 |
+  | -------- | -------- | -------- | -------- | -------- | -------- | -------- | -------- |
+  | 2     | 1     | 8     | 12     | 16     | 17     | 23     | 25     |`,
 };
 
 async function handler(ctx) {
-    const type = ctx.req.param('type') ?? 'sszs';
-    const info = yjszs.get(type);
+    const keyId = ctx.req.param('keyId') ?? '2';
+    const info = yjszs.get(keyId);
     if (!info) {
-        throw new InvalidParameterError('invalid type');
+        throw new InvalidParameterError('invalid keyId');
     }
-    const link = `${host}/pubweb/homePageList/${info.view}.view?keyId=${info.keyId ?? ''}`;
+    let link = `${host}/pubweb/homePageList`;
+    link += keyId === '2' ? `/searchContent.view` : `/recruitStudents.view?keyId=${keyId}`;
     const response = await got({
         method: 'get',
         url: link,

package/lib/routes/nytimes/book.ts

@@ -3,17 +3,17 @@ import got from '@/utils/got';
 import { load } from 'cheerio';
 
 const categoryList = {
-    'combined-print-and-e-book-nonfiction': '非虚构类 - 综合',
-    'hardcover-nonfiction': '非虚构类 - 精装本',
-    'paperback-nonfiction': '非虚构类 - 平装本',
-    'advice-how-to-and-miscellaneous': '工具类',
-    'combined-print-and-e-book-fiction': '虚构类 - 综合',
-    'hardcover-fiction': '虚构类 - 精装本',
-    'trade-fiction-paperback': '虚构类 - 平装本',
-    'childrens-middle-grade-hardcover': '儿童 - 中年级',
-    'picture-books': '儿童 - 绘本',
-    'series-books': '儿童 - 系列图书',
-    'young-adult-hardcover': '青少年',
+    'combined-print-and-e-book-nonfiction': 'Combined Print & E-Book Nonfiction',
+    'hardcover-nonfiction': 'Hardcover Nonfiction',
+    'paperback-nonfiction': 'Paperback Nonfiction',
+    'advice-how-to-and-miscellaneous': 'Advice, How-To & Miscellaneous',
+    'combined-print-and-e-book-fiction': 'Combined Print & E-Book Fiction',
+    'hardcover-fiction': 'Hardcover Fiction',
+    'trade-fiction-paperback': 'Paperback Trade Fiction',
+    'childrens-middle-grade-hardcover': "Children's Middle Grade Hardcover",
+    'picture-books': 'Picture Books',
+    'series-books': 'Series Books',
+    'young-adult-hardcover': 'Young Adult Hardcover',
 };
 
 export const route: Route = {

package/lib/routes/nytimes/daily-briefing-chinese.ts

@@ -11,7 +11,7 @@ import path from 'node:path';
 
 export const route: Route = {
     path: '/daily_briefing_chinese',
-    categories: ['traditional-media'],
+    categories: ['traditional-media', 'popular'],
     example: '/nytimes/daily_briefing_chinese',
     parameters: {},
     features: {
@@ -28,11 +28,11 @@ export const route: Route = {
             target: '',
         },
     ],
-    name: '新闻简报',
+    name: 'Daily Briefing',
     maintainers: ['yueyericardo', 'nczitzk'],
     handler,
     url: 'nytimes.com/',
-    description: `网站地址：[https://www.nytimes.com/zh-hans/series/daily-briefing-chinese](https://www.nytimes.com/zh-hans/series/daily-briefing-chinese)`,
+    description: `URL: [https://www.nytimes.com/zh-hans/series/daily-briefing-chinese](https://www.nytimes.com/zh-hans/series/daily-briefing-chinese)`,
 };
 
 async function handler() {
@@ -91,7 +91,7 @@ async function handler() {
     );
 
     return {
-        title: '新闻简报 - The New York Times',
+        title: 'Daily Briefing - The New York Times',
         link: currentUrl,
         item: items,
     };

package/lib/routes/nytimes/namespace.ts

@@ -1,6 +1,6 @@
 import type { Namespace } from '@/types';
 
 export const namespace: Namespace = {
-    name: 'The New York Times 纽约时报',
+    name: 'The New York Times',
     url: 'nytimes.com',
 };

package/lib/routes/oncc/templates/article.art

@@ -1,2 +1,2 @@
 <img src="{{ imageUrl }}">
-{{ content }}
+{{@ content }}

package/lib/routes/papers/index.ts

@@ -20,7 +20,7 @@ export const handler = async (ctx) => {
     const feedUrl = new URL(`${category}/feed`, rootUrl).href;
 
     const site = category.split(/\//)[0];
-    const apiKimiUrl = new URL(`${site}/kimi/`, rootUrl).href;
+    const apiKimiUrl = new URL(`${site}/kimi?paper=`, rootUrl).href;
 
     const feed = await parser.parseURL(feedUrl);
 
@@ -91,6 +91,7 @@ export const route: Route = {
   | arXiv Computation and Language (cs.CL)                | arxiv/cs.CL |
   | arXiv Computer Vision and Pattern Recognition (cs.CV) | arxiv/cs.CV |
   | arXiv Machine Learning (cs.LG)                        | arxiv/cs.LG |
+  | arXiv Robotics (cs.RO)                        | arxiv/cs.RO |
   `,
     categories: ['journal'],
 
@@ -124,5 +125,10 @@ export const route: Route = {
             source: ['papers.cool/arxiv/cs.LG'],
             target: '/arxiv/cs.LG',
         },
+        {
+            title: 'arXiv Robotics (cs.RO)',
+            source: ['papers.cool/arxiv/cs.RO'],
+            target: '/arxiv/cs.RO',
+        },
     ],
 };

package/lib/routes/parliament.uk/commonslibrary.ts

@@ -0,0 +1,55 @@
+import { load } from 'cheerio';
+import { Route } from '@/types';
+import puppeteer from '@/utils/puppeteer';
+import timezone from '@/utils/timezone';
+
+export const route: Route = {
+    path: '/commonslibrary/type/:topic?',
+    categories: ['government'],
+    example: '/parliament.uk/commonslibrary/type/research-briefing',
+    parameters: { topic: 'research by topic, string, example: [research-briefing|data-dashboard]' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: true,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    name: 'Commonlibrary',
+    maintainers: ['AntiKnot'],
+    handler,
+};
+
+async function handler(ctx) {
+    const { topic } = ctx.req.param();
+    const baseUrl = 'https://commonslibrary.parliament.uk';
+    const url = `${baseUrl}/type/${topic}/`;
+    const browser = await puppeteer();
+    const page = await browser.newPage();
+    await page.setRequestInterception(true);
+    page.on('request', (request) => {
+        request.resourceType() === 'document' ? request.continue() : request.abort();
+    });
+    await page.goto(url, {
+        waitUntil: 'domcontentloaded',
+    });
+
+    const html = await page.evaluate(() => document.documentElement.innerHTML);
+    await page.close();
+    const $ = load(html);
+    const items = $('div.l-box.l-box--no-border.card__text')
+        .map((_, article) => ({
+            title: $(article).find('.card__text a').text().trim(),
+            link: $(article).find('.card__text a').attr('href'),
+            description: $(article).find('p').last().text().trim(),
+            pubDate: timezone($(article).find('.card__date time').attr('datetime')),
+        }))
+        .toArray();
+    browser.close();
+    return {
+        title: `parliament - lordslibrary - ${topic}`,
+        link: url,
+        item: items,
+    };
+}

package/lib/routes/parliament.uk/lordslibrary.ts

@@ -0,0 +1,55 @@
+import { load } from 'cheerio';
+import { Route } from '@/types';
+import puppeteer from '@/utils/puppeteer';
+import timezone from '@/utils/timezone';
+
+export const route: Route = {
+    path: '/lordslibrary/type/:topic?',
+    categories: ['government'],
+    example: '/parliament.uk/lordslibrary/type/research-briefing',
+    parameters: { topic: 'research by topic, string, example: [research-briefing|buisness|economy]' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: true,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    name: 'House of Lords Library',
+    maintainers: ['AntiKnot'],
+    handler,
+};
+
+async function handler(ctx) {
+    const { topic } = ctx.req.param();
+    const baseUrl = 'https://lordslibrary.parliament.uk';
+    const url = `${baseUrl}/type/${topic}/`;
+    const browser = await puppeteer();
+    const page = await browser.newPage();
+    await page.setRequestInterception(true);
+    page.on('request', (request) => {
+        request.resourceType() === 'document' ? request.continue() : request.abort();
+    });
+    await page.goto(url, {
+        waitUntil: 'domcontentloaded',
+    });
+
+    const html = await page.evaluate(() => document.documentElement.innerHTML);
+    await page.close();
+    const $ = load(html);
+    const items = $('div.l-box.l-box--no-border.card__text')
+        .map((_, article) => ({
+            title: $(article).find('.card__text a').text().trim(),
+            link: $(article).find('.card__text a').attr('href'),
+            description: $(article).find('p').last().text().trim(),
+            pubDate: timezone($(article).find('.card__date time').attr('datetime')),
+        }))
+        .toArray();
+    browser.close();
+    return {
+        title: `parliament - lordslibrary - ${topic}`,
+        link: url,
+        item: items,
+    };
+}

package/lib/routes/parliament.uk/namespace.ts

@@ -0,0 +1,6 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'UK Parliament',
+    url: 'parliament.uk',
+};