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

package/lib/routes/nhk/news.ts

@@ -1,4 +1,4 @@
-import { Route } from '@/types';
+import { Route, ViewType } from '@/types';
 import { getCurrentPath } from '@/utils/helpers';
 const __dirname = getCurrentPath(import.meta.url);
 
@@ -12,9 +12,37 @@ const apiUrl = 'https://nwapi.nhk.jp';
 
 export const route: Route = {
     path: '/news/:lang?',
-    categories: ['traditional-media'],
+    categories: ['traditional-media', 'popular'],
+    view: ViewType.Articles,
     example: '/nhk/news/en',
-    parameters: { lang: 'Language, see below, `en` by default' },
+    parameters: {
+        lang: {
+            description: 'Language, see below',
+            options: [
+                { value: 'ar', label: 'العربية' },
+                { value: 'bn', label: 'বাংলা' },
+                { value: 'my', label: 'မြန်မာဘာသာစကား' },
+                { value: 'zh', label: '中文（简体）' },
+                { value: 'zt', label: '中文（繁體）' },
+                { value: 'en', label: 'English' },
+                { value: 'fr', label: 'Français' },
+                { value: 'hi', label: 'हिन्दी' },
+                { value: 'id', label: 'Bahasa Indonesia' },
+                { value: 'ko', label: '코리언' },
+                { value: 'fa', label: 'فارسی' },
+                { value: 'pt', label: 'Português' },
+                { value: 'ru', label: 'Русский' },
+                { value: 'es', label: 'Español' },
+                { value: 'sw', label: 'Kiswahili' },
+                { value: 'th', label: 'ภาษาไทย' },
+                { value: 'tr', label: 'Türkçe' },
+                { value: 'uk', label: 'Українська' },
+                { value: 'ur', label: 'اردو' },
+                { value: 'vi', label: 'Tiếng Việt' },
+            ],
+            default: 'en',
+        },
+    },
     features: {
         requireConfig: false,
         requirePuppeteer: false,
@@ -30,19 +58,8 @@ export const route: Route = {
         },
     ],
     name: 'WORLD-JAPAN - Top Stories',
-    maintainers: ['TonyRL'],
+    maintainers: ['TonyRL', 'pseudoyu'],
     handler,
-    description: `| العربية | বাংলা | မြန်မာဘာသာစကား | 中文（简体） | 中文（繁體） | English | Français |
-  | ------- | -- | ------------ | ------------ | ------------ | ------- | -------- |
-  | ar      | bn | my           | zh           | zt           | en      | fr       |
-
-  | हिन्दी | Bahasa Indonesia | 코리언 | فارسی | Português | Русский | Español |
-  | -- | ---------------- | ------ | ----- | --------- | ------- | ------- |
-  | hi | id               | ko     | fa    | pt        | ru      | es      |
-
-  | Kiswahili | ภาษาไทย | Türkçe | Українська | اردو | Tiếng Việt |
-  | --------- | ------- | ------ | ---------- | ---- | ---------- |
-  | sw        | th      | tr     | uk         | ur   | vi         |`,
 };
 
 async function handler(ctx) {

package/lib/routes/nicovideo/namespace.ts

@@ -0,0 +1,7 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'Niconico',
+    url: 'www.nicovideo.jp',
+    categories: ['multimedia'],
+};

package/lib/routes/nicovideo/templates/video.art

@@ -0,0 +1,7 @@
+{{ if embed }}
+    <iframe src="https://embed.nicovideo.jp/watch/{{ video.id }}" style="top: 0; left: 0; width: 100%; height: 100%; position: absolute; border: 0;" allowfullscreen></iframe>
+{{ else }}
+    <img src="{{ video.thumbnail.nHdUrl || video.thumbnail.largeUrl || video.thumbnail.middleUrl }}">
+{{ /if }}
+<br>
+{{@ video.shortDescription }}

package/lib/routes/nicovideo/types.ts

@@ -0,0 +1,54 @@
+export interface UserInfo {
+    id: number;
+    nickname: string;
+    icon: string;
+    smallIcon: string;
+}
+
+interface Count {
+    view: number;
+    comment: number;
+    mylist: number;
+    like: number;
+}
+
+interface Thumbnail {
+    url: string;
+    middleUrl: string | null;
+    largeUrl: string | null;
+    listingUrl: string;
+    nHdUrl: string;
+}
+
+interface Owner {
+    ownerType: string;
+    type: string;
+    visibility: string;
+    id: string;
+    name: string;
+    iconUrl: string;
+}
+
+export interface Essential {
+    type: string;
+    id: string;
+    title: string;
+    registeredAt: string;
+    count: Count;
+    thumbnail: Thumbnail;
+    duration: number;
+    shortDescription: string;
+    latestCommentSummary: string;
+    isChannelVideo: boolean;
+    isPaymentRequired: boolean;
+    playbackPosition: null;
+    owner: Owner;
+    requireSensitiveMasking: boolean;
+    videoLive: null;
+    isMuted: boolean;
+}
+
+export interface VideoItem {
+    series: null;
+    essential: Essential;
+}

package/lib/routes/nicovideo/utils.ts

@@ -0,0 +1,37 @@
+import { Essential, UserInfo, VideoItem } from './types';
+
+import ofetch from '@/utils/ofetch';
+import cache from '@/utils/cache';
+import { config } from '@/config';
+import path from 'node:path';
+import { art } from '@/utils/render';
+import { getCurrentPath } from '@/utils/helpers';
+
+const __dirname = getCurrentPath(import.meta.url);
+
+export const getUserInfoById = (id: string) => cache.tryGet(`nicovideo:user:${id}`, () => ofetch<UserInfo>(`https://embed.nicovideo.jp/users/${id}`)) as Promise<UserInfo>;
+
+export const getUserVideosById = (id: string) =>
+    cache.tryGet(
+        `nicovideo:user:${id}:videos`,
+        async () => {
+            const { data } = await ofetch(`https://nvapi.nicovideo.jp/v3/users/${id}/videos`, {
+                headers: {
+                    'X-Frontend-Id': '6',
+                },
+                query: {
+                    sortKey: 'registeredAt',
+                    sortOrder: 'desc',
+                    sensitiveContents: 'mask',
+                    pageSize: 100,
+                    page: 1,
+                },
+            });
+
+            return data.items;
+        },
+        config.cache.routeExpire,
+        false
+    ) as Promise<VideoItem[]>;
+
+export const renderVideo = (video: Essential, embed: boolean) => art(path.join(__dirname, 'templates', 'video.art'), { video, embed });

package/lib/routes/nicovideo/video.ts

@@ -0,0 +1,47 @@
+import type { Context } from 'hono';
+import { DataItem, Route } from '@/types';
+import { UserInfo, VideoItem } from './types';
+
+import { parseDate } from '@/utils/parse-date';
+import { getUserInfoById, getUserVideosById, renderVideo } from './utils';
+
+const handler = async (ctx: Context) => {
+    const { id } = ctx.req.param();
+    const embed = !ctx.req.param('embed');
+
+    const userInfo: UserInfo = await getUserInfoById(id);
+    const videos: VideoItem[] = await getUserVideosById(id);
+
+    const items = videos.map(({ essential: video }) => ({
+        title: video.title,
+        link: `https://www.nicovideo.jp/watch/${video.id}`,
+        pubDate: parseDate(video.registeredAt),
+        author: [{ name: video.owner.name, avatar: video.owner.iconUrl, url: `https://www.nicovideo.jp/user/${video.owner.id}` }],
+        description: renderVideo(video, embed),
+        image: video.thumbnail.nHdUrl || video.thumbnail.largeUrl || video.thumbnail.middleUrl,
+        upvotes: video.count.like,
+        comments: video.count.comment,
+    })) as DataItem[];
+
+    return {
+        title: `${userInfo.nickname} - ニコニコ`,
+        link: `https://www.nicovideo.jp/user/${id}/video`,
+        image: userInfo.icon,
+        item: items,
+    };
+};
+
+export const route: Route = {
+    name: 'User Videos',
+    path: '/user/:id/video/:embed?',
+    parameters: { id: 'User ID', embed: 'Default to embed the video, set to any value to disable embedding' },
+    example: '/nicovideo/user/16690815/video',
+    maintainers: ['TonyRL'],
+    radar: [
+        {
+            source: ['www.nicovideo.jp/user/:id', 'www.nicovideo.jp/user/:id/video'],
+            target: '/user/:id/video',
+        },
+    ],
+    handler,
+};

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/nytimes/book.ts

@@ -1,26 +1,36 @@
-import { Route } from '@/types';
+import { Route, ViewType } from '@/types';
 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 = {
     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/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/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/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/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',
+    },
+};

package/lib/routes/oct0pu5/rss.ts

@@ -0,0 +1,48 @@
+import { Route } from '@/types';
+import buildData from '@/utils/common-config';
+
+const baseUrl = 'https://oct0pu5.cn/';
+
+export const route: Route = {
+    path: '/',
+    categories: ['blog'],
+    example: '/oct0pu5',
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['oct0pu5.cn'],
+            target: '/',
+        },
+    ],
+    name: 'Oct的小破站',
+    maintainers: ['octopus058', 'wiketool'],
+    handler,
+};
+
+async function handler() {
+    const link = baseUrl;
+    return await buildData({
+        link,
+        url: link,
+        title: `%title%`,
+        description: `%description%`,
+        params: {
+            title: '博客',
+            description: 'Oct0pu5的博客',
+        },
+        item: {
+            item: '.recent-posts > .recent-post-item',
+            title: `$('.recent-post-info > a').text()`,
+            link: `$('.recent-post-info > a').attr('href')`,
+            description: `$('.recent-post-info > .content').text()`,
+            pubDate: `Date.parse($('div.recent-post-info > div.article-meta-wrap > span.post-meta-date > time').text().trim())`,
+        },
+    });
+}

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,
+    };
+}