rsshub 1.0.0-master.ff3a9ce → 1.0.0-master.ff3ea5a

package/lib/routes/newslaundry/nl-collaborations.ts

@@ -0,0 +1,30 @@
+import { Data, Route, ViewType } from '@/types';
+import { fetchCollection, rootUrl } from './utils';
+
+export const route: Route = {
+    path: '/nl-collaborations',
+    view: ViewType.Articles,
+    categories: ['new-media'],
+    example: '/newslaundry/nl-collaborations',
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['newslaundry.com/nl-collaborations'],
+            target: '/nl-collaborations',
+        },
+    ],
+    name: 'NL Collaboration',
+    maintainers: ['Rjnishant530'],
+    handler,
+};
+
+async function handler(): Promise<Data> {
+    return await fetchCollection('nl-collaborations', `${rootUrl}/nl-collaborations`);
+}

package/lib/routes/newslaundry/podcast.ts

@@ -0,0 +1,61 @@
+import { Data, Route, ViewType } from '@/types';
+import { fetchCollection, rootUrl } from './utils';
+
+export const route: Route = {
+    path: '/podcast/:category?',
+    view: ViewType.Articles,
+    categories: ['new-media'],
+    example: '/newslaundry/podcast',
+    parameters: { category: 'Podcast category, see below for details' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: true,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['newslaundry.com/podcast'],
+            target: '/podcast',
+        },
+        {
+            source: ['newslaundry.com/collection/nl-hafta-podcast'],
+            target: '/podcast/nl-hafta',
+        },
+        {
+            source: ['newslaundry.com/podcast/whats-your-ism'],
+            target: '/podcast/whats-your-ism',
+        },
+    ],
+    name: 'Podcast',
+    description: `| Category | URL |
+| -------- | --- |
+| All Podcasts | [/podcast](https://rsshub.app/newslaundry/podcast) |
+| NL Hafta | [/podcast/nl-hafta](https://rsshub.app/newslaundry/podcast/nl-hafta) |
+| What's Your Ism? | [/podcast/whats-your-ism](https://rsshub.app/newslaundry/podcast/whats-your-ism) |`,
+    maintainers: ['Rjnishant530'],
+    handler,
+};
+
+async function handler(ctx): Promise<Data> {
+    const category = ctx.req.param('category');
+
+    // Map category to collection slug and URL
+    const categoryMap = {
+        'nl-hafta': {
+            slug: 'nl-hafta-podcast',
+            url: `${rootUrl}/collection/nl-hafta-podcast`,
+        },
+        'whats-your-ism': {
+            slug: 'whats-your-ism-podcast-newslaundry-hindi',
+            url: `${rootUrl}/podcast/whats-your-ism`,
+        },
+    };
+
+    // For main podcast route, skip the first item
+    const skipFirstItem = !category;
+
+    return category && categoryMap[category] ? await fetchCollection(categoryMap[category].slug, categoryMap[category].url) : await fetchCollection('podcast', undefined, skipFirstItem);
+}

package/lib/routes/newslaundry/reports.ts

@@ -0,0 +1,30 @@
+import { Data, Route, ViewType } from '@/types';
+import { fetchCollection } from './utils';
+
+export const route: Route = {
+    path: '/reports',
+    view: ViewType.Articles,
+    categories: ['new-media'],
+    example: '/newslaundry/reports',
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['newslaundry.com/reports'],
+            target: '/reports',
+        },
+    ],
+    name: 'Reports',
+    maintainers: ['Rjnishant530'],
+    handler,
+};
+
+async function handler(): Promise<Data> {
+    return await fetchCollection('reports', undefined, true);
+}

package/lib/routes/newslaundry/shot.ts

@@ -0,0 +1,30 @@
+import { Data, Route, ViewType } from '@/types';
+import { fetchCollection } from './utils';
+
+export const route: Route = {
+    path: '/shot',
+    view: ViewType.Articles,
+    categories: ['new-media'],
+    example: '/newslaundry/shot',
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['newslaundry.com/shot'],
+            target: '/shot',
+        },
+    ],
+    name: 'Shot',
+    maintainers: ['Rjnishant530'],
+    handler,
+};
+
+async function handler(): Promise<Data> {
+    return await fetchCollection('shot');
+}

package/lib/routes/newslaundry/subscriber-only.ts

@@ -0,0 +1,30 @@
+import { Data, Route, ViewType } from '@/types';
+import { fetchCollection } from './utils';
+
+export const route: Route = {
+    path: '/subscriber-only',
+    view: ViewType.Articles,
+    categories: ['new-media'],
+    example: '/newslaundry/subscriber-only',
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['newslaundry.com/subscriber-only'],
+            target: '/subscriber-only',
+        },
+    ],
+    name: 'Subscriber Only',
+    maintainers: ['Rjnishant530'],
+    handler,
+};
+
+async function handler(): Promise<Data> {
+    return await fetchCollection('subscriber-only');
+}

package/lib/routes/newslaundry/templates/description.art

@@ -0,0 +1,28 @@
+{{if subheadline}}
+<p><strong>{{subheadline}}</strong></p>
+{{/if}}
+
+{{if heroImage}}
+<figure>
+  <img src="{{heroImage}}" alt="{{heroAlt}}">
+  <figcaption>{{heroCaption}}{{if heroAttribution}} ({{heroAttribution}}){{/if}}</figcaption>
+</figure>
+{{/if}}
+
+{{each elements}}
+  {{if $value.type === 'text'}}
+    {{@ $value.text}}
+  {{else if $value.type === 'image'}}
+    <figure>
+      <img src="{{$value.url}}" alt="{{$value.alt}}">
+      <figcaption>{{$value.title}}</figcaption>
+    </figure>
+  {{else if $value.type === 'jsembed'}}
+    {{@ $value.content}}
+  {{else if $value.type === 'youtube-video'}}
+    <figure>
+      <iframe width="560" height="315" src="{{$value.embedUrl}}" frameborder="0" allowfullscreen></iframe>
+      <figcaption><a href="{{$value.url}}" target="_blank" rel="noopener noreferrer">Watch on YouTube</a></figcaption>
+    </figure>
+  {{/if}}
+{{/each}}

package/lib/routes/newslaundry/utils.ts

@@ -0,0 +1,108 @@
+import { Data, DataItem } from '@/types';
+import ofetch from '@/utils/ofetch';
+import { parseDate } from '@/utils/parse-date';
+import { art } from '@/utils/render';
+import path from 'node:path';
+
+export const rootUrl = 'https://www.newslaundry.com';
+
+export async function fetchCollection(collectionSlug: string, customUrl?: string, skipFirstItem: boolean = false) {
+    const apiUrl = `${rootUrl}/api/v1/collections/${collectionSlug}`;
+    const currentUrl = customUrl || `${rootUrl}/${collectionSlug}`;
+
+    const response = await ofetch(apiUrl);
+
+    if (!response.items || !response.items.length) {
+        throw new Error('No articles found');
+    }
+
+    // Skip first item if requested
+    const itemsToProcess = skipFirstItem ? response.items.slice(1) : response.items;
+    const items = itemsToProcess.map((item) => processStory(item.story));
+
+    return {
+        title: `${response.name} - Newslaundry`,
+        description: response.summary || `${response.name} articles from Newslaundry`,
+        link: currentUrl,
+        item: items,
+        language: 'en',
+        logo: `${rootUrl}/favicon.ico`,
+        icon: `${rootUrl}/favicon.ico`,
+    } as Data;
+}
+
+function processStory(story: any): DataItem {
+    const articleUrl = story.url;
+    const pubDate = story['published-at'] ? parseDate(story['published-at']) : null;
+
+    // Prepare data for template
+    const heroImage = story['hero-image-s3-key'] ? `https://media.assettype.com/${story['hero-image-s3-key']}?auto=format%2Ccompress&fit=max&dpr=1.0&format=webp` : null;
+
+    // Extract elements from cards
+    const elements =
+        story.cards?.flatMap(
+            (card) =>
+                card?.['story-elements']
+                    ?.map((element) => {
+                        if (element.type === 'text' && element.text) {
+                            return {
+                                type: 'text',
+                                text: element.text,
+                            };
+                        } else if (element.type === 'image' && element['image-s3-key']) {
+                            return {
+                                type: 'image',
+                                url: `https://media.assettype.com/${element['image-s3-key']}?auto=format%2Ccompress&format=webp`,
+                                alt: element['alt-text'] || '',
+                                title: element.title || '',
+                            };
+                        } else if (element.type === 'jsembed' && element['embed-js']) {
+                            try {
+                                return {
+                                    type: 'jsembed',
+                                    content: Buffer.from(element['embed-js'], 'base64').toString(),
+                                };
+                            } catch {
+                                // Skip if unable to decode
+                                return null;
+                            }
+                        } else if (element.type === 'youtube-video' && element.url) {
+                            return {
+                                type: 'youtube-video',
+                                url: element.url,
+                                embedUrl: element['embed-url'] || '',
+                            };
+                        }
+                        return null;
+                    })
+                    .filter(Boolean) || []
+        ) || [];
+
+    // Render content using template
+    const content = art(path.join(__dirname, 'templates/description.art'), {
+        heroImage,
+        heroAlt: story['hero-image-alt-text'] || '',
+        heroCaption: story['hero-image-caption'] || '',
+        heroAttribution: story['hero-image-attribution'],
+        elements,
+        subheadline: story.subheadline,
+    });
+
+    // Extract author information
+    const authors =
+        story.authors?.map((author) => ({
+            name: author.name,
+            url: author.slug ? `${rootUrl}/author/${author.slug}` : undefined,
+        })) || [];
+
+    return {
+        title: story.headline,
+        link: articleUrl,
+        image: heroImage,
+        description: content || story.subheadline,
+        pubDate,
+        updated: story['last-correction-published-at'] ? parseDate(story['last-correction-published-at']) : undefined,
+        author: authors.length > 0 ? authors : story['author-name'],
+        category: story.tags?.map((tag) => tag.name) || [],
+    } as DataItem;
+}

package/lib/routes/newswav/latest.ts

@@ -0,0 +1,100 @@
+import { Route } from '@/types';
+import cache from '@/utils/cache';
+import ofetch from '@/utils/ofetch';
+import { load } from 'cheerio';
+import { parseDate } from '@/utils/parse-date';
+
+export const route: Route = {
+    path: '/',
+    categories: ['new-media'],
+    example: '/newswav',
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['newswav.com/latest', 'newswav.com'],
+        },
+    ],
+    name: 'Latest',
+    maintainers: ['TonyRL'],
+    handler,
+};
+
+async function handler() {
+    const baseUrl = 'https://newswav.com';
+
+    const response = await ofetch(`https://feed-api.newswav.com/api/web/feeds/latest`, {
+        query: {
+            languages: 'en,ms,zh',
+        },
+    });
+
+    const list = response.data.content
+        .filter((i) => i.contentId !== 'AD')
+        .map((i) => ({
+            title: i.title,
+            description: i.description,
+            category: i.topics.map((topic) => topic.en),
+            link: `${baseUrl}/article/${i.permalink}`,
+            permalink: i.permalink,
+            pubDate: parseDate(i.publishedAt),
+            author: i.publisher.name,
+            image: i.thumbnailUrl,
+        }));
+
+    const items = await Promise.all(
+        list.map((item) =>
+            cache.tryGet(item.link, async () => {
+                const response = await ofetch(`https://api.newswav.com/v4/api/v1/web/contents/${item.permalink}`);
+
+                if (response.contentType === 'video') {
+                    const video = response.meta.video;
+                    item.description = `<video controls preload="metadata" poster="${video.thumbnailUrl}"><source src="${video.videoUrl}" type="${video.mimeType}"></video><br>${video.content}`;
+
+                    return item;
+                } else if (response.contentType === 'podcast') {
+                    const podcast = response.meta.podcast;
+                    item.description = `<audio controls"><source src="${podcast.url}" type="audio/mpeg"></audio><br>${podcast.content}`;
+                    item.enclosure_type = 'audio/mpeg';
+
+                    return item;
+                }
+
+                const article = response.meta.article;
+                const $ = load(article.content);
+
+                $('*')
+                    .contents()
+                    .filter((_, element) => element.type === 'comment' && element.data.trim() === 'AD')
+                    .remove();
+
+                $('iframe').each((_, element) => {
+                    const $element = $(element);
+                    if ($element.attr('src')?.includes('ga4-track.html') || $element.attr('src')?.includes('ga4-v2-track.html')) {
+                        $element.remove();
+                    }
+                });
+
+                item.description = $.html();
+
+                const image = new URL(article.originalUrl);
+                item.image = image.pathname.startsWith('/1000x0,q50=/') ? image.pathname.replace('/1000x0,q50=/', '') : image.pathname;
+
+                return item;
+            })
+        )
+    );
+
+    return {
+        title: 'Newswav - Malaysia’s #1 Content Aggregator | Malaysia Breaking News, World News, and Latest News',
+        description: 'Latest news, videos and podcasts on Politics, Lifestyle, Sports, Current Affairs, Business & Finance, Entertainment and more from Malaysia & around the world.',
+        link: `${baseUrl}/latest`,
+        item: items,
+    };
+}

package/lib/routes/newswav/namespace.ts

@@ -0,0 +1,7 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'Newswav',
+    url: 'newswav.com',
+    lang: 'en',
+};

package/lib/routes/nhentai/index.ts

@@ -16,6 +16,7 @@ export const route: Route = {
     features: {
         antiCrawler: true,
         supportBT: true,
+        nsfw: true,
     },
     radar: [
         {

package/lib/routes/nifd/research.ts

@@ -62,6 +62,22 @@ async function handler(ctx) {
                 const content = load(detailResponse.data);
                 item.description = content('div.qrd-content').html();
 
+                const $enclosureEl = content('div.report-bottom a').first();
+                const enclosureUrl = $enclosureEl.attr('href');
+
+                if (enclosureUrl) {
+                    const enclosureItem = {
+                        enclosure_url: new URL(enclosureUrl, rootUrl).href,
+                        enclosure_type: `application/${enclosureUrl.split(/\./).pop() ?? 'pdf'}`,
+                        enclosure_title: $enclosureEl.prev().text(),
+                    };
+
+                    item = {
+                        ...item,
+                        ...enclosureItem,
+                    };
+                }
+
                 return item;
             })
         )

package/lib/routes/nio/namespace.ts

@@ -0,0 +1,9 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'NIO',
+    url: 'nio.com',
+    zh: {
+        name: '蔚来',
+    },
+};

package/lib/routes/nio/nioradio.ts

@@ -0,0 +1,75 @@
+import { Route } from '@/types';
+import ofetch from '@/utils/ofetch';
+import { parseDate } from '@/utils/parse-date';
+import { URLSearchParams } from 'node:url';
+
+export const route: Route = {
+    path: '/nioradio/:albumid',
+    categories: ['multimedia'],
+    description: `
+:::tip
+**如何获取电台 ID？**
+打开蔚来 APP 后，点击“此地”→“NIO Radio”，找到自己想要转换为播客的专辑，分享后在生成的链接中找到\`container_id=\`后方的数字即可。
+常见电台 ID：
+| 电台名称          | 电台 ID |
+| :------------ | :---- |
+| 资讯充电站（早间版）    | 5     |
+| 资讯充电站（晚间版）    | 23    |
+| E 次元财经报       | 148   |
+| 塞萌不塞车         | 661   |
+| 乐行记           | 11    |
+| Weekend Dance | 547   |
+:::`,
+    example: '/nio/nioradio/5',
+    parameters: { albumid: '电台专辑 ID' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: true,
+        supportScihub: false,
+    },
+    name: 'NIO Radio',
+    maintainers: ['marcosteam'],
+    handler: async (ctx) => {
+        const { albumid } = ctx.req.param();
+        const req = new URLSearchParams({
+            albumId: albumid,
+            sorttype: '2',
+            pagenum: '1',
+            pagesize: '10',
+        }).toString();
+        const data = await ofetch('https://gateway-front-external.nio.com/moat/100914/v2/audio/list', {
+            method: 'POST',
+            body: req,
+            headers: {
+                'Content-Type': 'application/x-www-form-urlencoded',
+            },
+        });
+
+        const podcasts = data.result.dataList;
+        const podcastName = podcasts[0].albumName;
+        const podcastImage = podcasts[0].albumPic;
+
+        const items = podcasts.map((podcast) => ({
+            title: podcast.audioName,
+            link: `https://app.nio.com/app/radio/share/?item_type=1&item_id=${String(podcast.audioId).slice(1)}&container_id=${albumid}`,
+            pubDate: parseDate(podcast.onlineTime),
+            description: podcast.albumDesc,
+            author: podcast.host.join(', '),
+            itunes_item_image: podcast.albumPic,
+            itunes_duration: podcast.duration / 1000,
+            enclosure_url: podcast.aacPlayUrl192,
+            enclosure_length: podcast.aacFileSize192,
+            enclosure_type: 'audio/x-m4a',
+        }));
+        return {
+            title: `NIO Radio - ${podcastName}`,
+            link: 'https://www.nio.com',
+            itunes_author: podcasts[0].host.join(', '),
+            image: podcastImage,
+            item: items,
+        };
+    },
+};

package/lib/routes/njust/cs.ts

@@ -0,0 +1,58 @@
+import { Route } from '@/types';
+import { load } from 'cheerio';
+import { parseDate } from '@/utils/parse-date';
+import timezone from '@/utils/timezone';
+import { getContent } from './utils';
+import InvalidParameterError from '@/errors/types/invalid-parameter';
+
+const map = new Map([
+    ['xyxw', { title: '南京理工大学计算机学院 -- 学院新闻', id: '/1817' }],
+    ['tzgg', { title: '南京理工大学计算机学院 -- 通知公告', id: '/1820' }],
+    ['xsdt', { title: '南京理工大学计算机学院 -- 学术动态', id: '/5790' }],
+]);
+
+const host = 'https://cs.njust.edu.cn';
+
+export const route: Route = {
+    path: '/cs/:type?',
+    categories: ['university'],
+    example: '/njust/cs/xyxw',
+    parameters: { type: '分类名，见下表，默认为学院新闻' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: true,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    name: '计算机学院',
+    maintainers: ['Horacecxk', 'jasongzy'],
+    handler,
+    description: `| 学院新闻 | 通知公告 | 学术动态 |
+| -------- | -------- | -------- |
+| xyxw     | tzgg     | xsdt     |`,
+};
+
+async function handler(ctx) {
+    const type = ctx.req.param('type') ?? 'xyxw';
+    const info = map.get(type);
+    if (!info) {
+        throw new InvalidParameterError('invalid type');
+    }
+    const id = info.id;
+    const siteUrl = host + id + '/list.htm';
+    const html = await getContent(siteUrl, true);
+    const $ = load(html);
+    const list = $('div#wp_news_w9').find('a');
+
+    return {
+        title: info.title,
+        link: siteUrl,
+        item: list.toArray().map((item) => ({
+            title: $(item).find('span[class="column-news-title"]').text().trim(),
+            pubDate: timezone(parseDate($(item).find('span[class="column-news-date news-date-hide"]').text(), 'YYYY-MM-DD'), +8),
+            link: $(item).attr('href'),
+        })),
+    };
+}

package/lib/routes/njust/utils.ts

@@ -3,7 +3,7 @@ import puppeteer from '@/utils/puppeteer';
 
 async function getContent(url, pptr = false) {
     if (pptr) {
-        const browser = await puppeteer({ stealth: true });
+        const browser = await puppeteer();
         try {
             const page = await browser.newPage();
             // 更改 window.navigator.webdriver 值以避开反爬

package/lib/routes/ntdm/video.ts

@@ -47,7 +47,7 @@ async function handler(ctx) {
                 link: `${rootUrl}${a.attr('href')}`,
             };
         })
-        .reverse();
+        .toReversed();
     return {
         title: `NT动漫 - ${dmtitle}`,
         link: `${rootUrl}/video/${id}.html`,

package/lib/routes/nuaa/utils/pypasswaf.ts

@@ -6,7 +6,7 @@ import puppeteer from '@/utils/puppeteer';
  * @desc 返回一个可用的cookie，使用 `got` 发起请求的时候，传入到`options.headers.cookie`即可
  */
 export default async function getCookie(host) {
-    const browser = await puppeteer({ stealth: true });
+    const browser = await puppeteer();
     const page = await browser.newPage();
     await page.setRequestInterception(true);
     page.on('request', (request) => {

package/lib/routes/oilchem/index.ts

@@ -39,7 +39,7 @@ async function handler(ctx) {
     const route = category === '' ? '' : `/${category}${subCategory === '' ? '' : `/${subCategory}`}`;
 
     const rootUrl = `https://${type === '' ? 'www' : 'list'}.oilchem.net`;
-    const currentUrl = `${rootUrl}${type === '' ? '/1/' : (type === 'list' ? route : `/${routes[`/${type}${route}`]}`)}`;
+    const currentUrl = `${rootUrl}${type === '' ? '/1/' : type === 'list' ? route : `/${routes[`/${type}${route}`]}`}`;
 
     const response = await got({
         method: 'get',

package/lib/routes/oncc/money18.ts

@@ -54,7 +54,7 @@ async function handler(ctx) {
 
     const toApiUrl = (date) => `${rootUrl}/cnt/utf8/content/${date}/articleList/list_${id}_all.js`;
 
-    let apiUrl = id === 'ipo' ? ipoApiUrl : (id === 'industry' ? industryApiUrl : toApiUrl(dayjs().format('YYYYMMDD'))),
+    let apiUrl = id === 'ipo' ? ipoApiUrl : id === 'industry' ? industryApiUrl : toApiUrl(dayjs().format('YYYYMMDD')),
         hasArticle = false,
         items = [],
         i = 0,

package/lib/routes/openai/cookbook.ts

@@ -29,7 +29,7 @@ async function handler() {
         const response = await ofetch(currentUrl);
         const $ = load(response);
 
-        let items = $('[class="min-h-[90vh]"] .grid a')
+        let items = $('[class="min-h-[90vh] mt-4"] .grid a')
             .toArray()
             .map((element) => {
                 const $element = $(element);