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

package/lib/routes/seu/cyber/index.ts

@@ -0,0 +1,78 @@
+import { Route } from '@/types';
+import cache from '@/utils/cache';
+import got from '@/utils/got';
+import { load } from 'cheerio';
+import { parseDate } from '@/utils/parse-date';
+
+export const route: Route = {
+    path: '/cyber/tzgg',
+    categories: ['university'],
+    example: '/seu/cyber/tzgg',
+    parameters: {},
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['cyber.seu.edu.cn/tzgg/list.htm', 'cyber.seu.edu.cn/'],
+        },
+    ],
+    name: '网络空间安全学院 - 通知公告',
+    maintainers: ['shrugginG'],
+    handler,
+    description: '东南大学网络空间安全学院通知公告',
+};
+
+async function handler() {
+    const host = 'https://cyber.seu.edu.cn';
+    const link = `${host}/tzgg/list.htm`;
+
+    const { data: response } = await got(link);
+    const $ = load(response);
+
+    const list = $('#wp_news_w6 ul.wp_article_list li.list_item')
+        .toArray()
+        .map((item) => {
+            const e = $(item);
+            const a = e.find('.Article_Title a');
+            const title = a.text().trim();
+            const href = a.attr('href');
+            const dateText = e.find('.Article_PublishDate').text().trim();
+
+            return {
+                title,
+                link: new URL(href || '', host).href,
+                pubDate: parseDate(dateText),
+                description: '',
+            };
+        });
+
+    const out = await Promise.all(
+        list.map((item) =>
+            cache.tryGet(item.link, async () => {
+                try {
+                    const response = await got(item.link);
+                    const $ = load(response.data);
+
+                    item.description = $('.wp_articlecontent').html() || $('.article-content').html() || $('.main-text').html() || $('article').html() || '';
+
+                    return item;
+                } catch {
+                    return item;
+                }
+            })
+        )
+    );
+
+    return {
+        link,
+        title: '东南大学网络空间安全学院 - 通知公告',
+        description: '东南大学网络空间安全学院通知公告RSS',
+        item: out,
+    };
+}

package/lib/routes/sicau/jiaowu.ts

@@ -4,13 +4,21 @@ import { load } from 'cheerio';
 import cache from '@/utils/cache';
 import { parseDate } from '@/utils/parse-date';
 import timezone from '@/utils/timezone';
+import { Language } from '@/routes/kurogames/wutheringwaves/constants';
 
 const $get = async (url: string, encoding = 'gb2312') => new TextDecoder(encoding).decode(await ofetch(url, { responseType: 'arrayBuffer' }));
+const $trim = (str: string) => {
+    let s = str.trim();
+    s = s.startsWith('  ') ? s.slice(12) : s;
+    s = s.endsWith('<br>') ? s.slice(0, Math.max(0, s.length - 4)) : s;
+    return s.trim();
+};
 
 export const route: Route = {
-    path: '/jiaowu/jxtz',
+    path: '/jiaowu/jxtz/:detail?',
     categories: ['university'],
-    example: '/sicau/jiaowu/jxtz',
+    example: '/sicau/jiaowu/jxtz/detail',
+    parameters: { detail: '是否抓取全文，该值只要不为空就抓取全文返回，否则只返回标题' },
     features: {
         requireConfig: false,
         requirePuppeteer: false,
@@ -27,51 +35,51 @@ export const route: Route = {
     ],
     name: '教务处',
     maintainers: ['hualiong'],
+    description: `
+::: tip
+抓取全文返回会导致更长的响应时间，可以尝试使用 \`/sicau/jiaowu/jxtz\` 路径，这将只返回标题，然后再在应用内抓取全文内容。
+:::
+`,
     url: 'jiaowu.sicau.edu.cn/',
-    handler: async () => {
+    handler: async (ctx) => {
         const baseUrl = 'https://jiaowu.sicau.edu.cn/web/web/web';
+        const { detail = null } = ctx.req.param();
 
-        const response = await $get(`${baseUrl}/index.asp`);
+        const response = await $get(`${baseUrl}/gwmore.asp`);
         const $ = load(response);
 
-        const list = $('ul.notice1:nth-child(1) a')
+        let items = $('tbody > .text-c:nth-child(-n+10)')
             .toArray()
             .map((item) => {
-                const a = $(item);
-                const href = a.attr('href')!;
+                const children = $(item).children();
+                const a = children.eq(2).find('a');
                 return {
-                    link: `${baseUrl}/${href.slice(href.lastIndexOf('/') + 1)}`,
+                    category: [children.eq(1).text()],
+                    link: `${baseUrl}/${a.attr('href')!}`,
+                    title: a.children().first().text(),
+                    pubDate: timezone(parseDate(children.eq(3).text(), 'YYYY-M-D'), +8),
+                    author: children.eq(4).text(),
+                    description: '请在应用内抓取全文内容',
                 } as DataItem;
             });
 
-        const items = await Promise.all(
-            list.map((item) =>
-                cache.tryGet(item.link!, async () => {
-                    const response = await $get(item.link!);
-                    const $ = load(response);
-
-                    item.title = $('body > .page-title-2').text();
-
-                    const date = $('body > p.page-title-3').text();
-                    item.pubDate = timezone(parseDate(date.match(/(\d{4}(?:-\d{1,2}){2})/)![0], 'YYYY-M-D'), +8);
-
-                    const str = $('.text1[valign="bottom"]').text();
-                    const match = str.match(/起草：(.+?)\[(.+?)]/)!;
-                    item.author = match[1];
-                    item.category = [match[2]];
-
-                    item.description = $('.text1[width="95%"]').html()!;
-
-                    return item;
-                })
-            )
-        );
+        if (detail) {
+            items = await Promise.all(
+                items.map((item) =>
+                    cache.tryGet(item.link!, async () => {
+                        const $ = load(await $get(item.link!));
+                        item.description = $trim($('.text1[width="95%"] b').html()!);
+                        return item;
+                    })
+                )
+            );
+        }
 
         return {
-            title: '教学通知 - 川农教务处',
-            link: 'https://jiaowu.sicau.edu.cn/web/web/web/index.asp',
-            language: 'zh-cn',
-            item: items as DataItem[],
+            title: '教学通知 - 四川农业大学教务处',
+            link: 'https://jiaowu.sicau.edu.cn/web/web/web/gwmore.asp',
+            language: Language.Chinese,
+            item: items,
         };
     },
 };

package/lib/routes/sis001/forum.ts

@@ -18,6 +18,7 @@ export const route: Route = {
         supportBT: false,
         supportPodcast: false,
         supportScihub: false,
+        nsfw: true,
     },
     name: '子版块',
     maintainers: ['TonyRL'],

package/lib/routes/sjtu/seiee/icisee.ts

@@ -0,0 +1,67 @@
+import { Route } from '@/types';
+import cache from '@/utils/cache';
+import { load } from 'cheerio';
+import { parseDate } from '@/utils/parse-date';
+import timezone from '@/utils/timezone';
+import ofetch from '@/utils/ofetch';
+import { finishArticleItem } from '@/utils/wechat-mp';
+
+export const route: Route = {
+    path: '/seiee/icisee/:cat',
+    categories: ['university'],
+    example: '/sjtu/seiee/icisee/news',
+    parameters: { cat: '子类别' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: true,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [],
+    name: '集成电路学院（信息与电子工程学院）',
+    maintainers: ['dzx-dzx'],
+    handler,
+};
+
+async function handler(ctx) {
+    const cat = ctx.req.param('cat');
+
+    const rootUrl = 'https://icisee.sjtu.edu.cn/';
+    const currentUrl = `${rootUrl}/${cat}.html`;
+    const response = await ofetch(currentUrl);
+
+    const $ = load(response);
+
+    const list = $('.djdt li')
+        .toArray()
+        .map((item) => {
+            item = $(item);
+
+            return {
+                title: item.find('.tit').text().trim(),
+                link: item.find('a').attr('href'),
+                pubDate: timezone(parseDate(item.find('.time').text().trim())),
+            };
+        });
+
+    const items = await Promise.all(
+        list.map((item) =>
+            cache.tryGet(item.link, async () => {
+                const detailResponse = await ofetch.raw(item.link);
+                if (new URL(detailResponse.url).hostname !== 'mp.weixin.qq.com') {
+                    return { ...item, description: $(detailResponse._data).find('.xwxq').html() };
+                }
+                item.link = detailResponse.url;
+                return await finishArticleItem(item);
+            })
+        )
+    );
+
+    return {
+        title: $('title').text(),
+        link: currentUrl,
+        item: items,
+    };
+}

package/lib/routes/sketis/isabelle-dev/blog/index.ts

@@ -44,7 +44,7 @@ export const route: Route = {
     handler: async (ctx) => {
         const baseUrl = 'https://isabelle-dev.sketis.net';
         const { blog } = ctx.req.param();
-        const blogName = blog === '1' ? 'News' : (blog === '2' ? 'Release' : 'UNKNOWN');
+        const blogName = blog === '1' ? 'News' : blog === '2' ? 'Release' : 'UNKNOWN';
         const url = `${baseUrl}/phame/blog/view/${blog}/`;
         const response = await ofetch(url);
         const $ = load(response);

package/lib/routes/smartlink/index.ts

@@ -22,10 +22,20 @@ function parseTitle(smartlinkUrl: string): string {
     }
 }
 
+function isYouTubeUrl(url: string): boolean {
+    try {
+        const parsedUrl = new URL(url);
+        const hostname = parsedUrl.hostname.toLowerCase();
+        return hostname === 'youtube.com' || hostname === 'www.youtube.com' || hostname === 'm.youtube.com' || hostname === 'youtu.be';
+    } catch {
+        return false;
+    }
+}
+
 function getTitle(item: any): string {
-    return item.type === 'video'
-        ? item.smartlink.split('?')[0] // For video items, use the full YouTube URL (without query parameters)
-        : parseTitle(item.smartlink); // Use existing parseTitle for photo items
+    return isYouTubeUrl(item.smartlink)
+        ? item.smartlink.split('?')[0] // For YouTube URLs, use the URL without query parameters
+        : parseTitle(item.smartlink); // Use existing parseTitle for other URLs
 }
 
 export const route: Route = {

package/lib/routes/sohu/mp.ts

@@ -4,6 +4,7 @@ import cache from '@/utils/cache';
 import ofetch from '@/utils/ofetch';
 import * as cheerio from 'cheerio';
 import { parseDate } from '@/utils/parse-date';
+import timezone from '@/utils/timezone';
 import path from 'node:path';
 import { art } from '@/utils/render';
 import CryptoJS from 'crypto-js';
@@ -47,6 +48,12 @@ function decryptImageUrl(cipherText) {
     return cipher.toString(CryptoJS.enc.Utf8);
 }
 
+function createAuthToken() {
+    const t = Date.now();
+    const e = 't' + t;
+    return 'v1' + t + CryptoJS.HmacSHA1(e, '439642a904ef43d092d45509cdc4391c').toString();
+}
+
 function fetchArticle(item) {
     return cache.tryGet(item.link, async () => {
         const response = await ofetch(item.link);
@@ -54,6 +61,7 @@ function fetchArticle(item) {
 
         $('.original-title, .lookall-box').remove();
         item.author = item.author || $('span[data-role="original-link"] a').text();
+        item.pubDate = timezone(parseDate($('meta[itemprop="dateUpdate"]').attr('content')), 8);
 
         if (/window\.sohu_mp\.article_video/.test($('script').text())) {
             const videoSrc = $('script')
@@ -128,6 +136,8 @@ async function handler(ctx) {
             .match(/({.*})/)?.[1]
     );
     const renderData = blockRenderData[Object.keys(blockRenderData).find((e) => e.startsWith('FeedSlideloadAuthor'))];
+    const briefIntroductionCard = blockRenderData[Object.keys(blockRenderData).find((e) => e.startsWith('BriefIntroductionCard'))].param.data.list[0];
+
     const globalConst = JSON.parse(
         $('script:contains("globalConst")')
             .text()
@@ -153,7 +163,7 @@ async function handler(ctx) {
         },
         body: {
             pvId: CBDRenderConst.COMMONCONFIG.pvId || `${Date.now()}_${randomString(7)}`,
-            pageId: `${Date.now()}_${defaultSUV.slice(0, -5)}_${randomString(3)}`,
+            pageId: `${Date.now()}_${defaultSUV?.slice(0, -5)}_${randomString(3)}`,
             mainContent: {
                 productType: contentData.businessType || '13',
                 productId: contentData.id || '324',
@@ -174,11 +184,11 @@ async function handler(ctx) {
                         size: 20,
                         pro: renderData.param.pro || '0,1,3,4,5',
                         feedType: renderData.param.feedType || 'XTOPIC_SYNTHETICAL',
-                        view: '',
+                        view: 'operateFeedMode',
                         innerTag: renderData.param.data2.reqParam.content.innerTag || 'work',
                         spm: renderData.param.data2.reqParam.content.spm || 'smpc.channel_248.block3_308_hHsK47_2_fd',
                         page: 1,
-                        requestId: `${Date.now()}_${randomString(13)}_${contentData.id}`,
+                        requestId: `${Date.now()}${randomString(7)}_${contentData.id}`,
                     },
                     adInfo: {},
                     context: {
@@ -186,22 +196,23 @@ async function handler(ctx) {
                     },
                 },
             ],
+            asId: createAuthToken(),
         },
     });
 
     const list = blockData.data[renderData.param.data2.reqParam.tplCompKey].list.map((item) => ({
         title: item.title,
         description: item.brief,
-        link: `https://www.sohu.com/a/${item.id}_${item.authorId}`,
-        author: item.authorName,
-        pubDate: parseDate(item.postTime, 'x'),
+        link: `https://www.sohu.com/a/${item.id}_${globalConst.mkeyConst_mkey}`,
     }));
 
     const items = await Promise.all(list.map((e) => fetchArticle(e)));
 
     return {
         title: `搜狐号 - ${globalConst.title}`,
+        description: briefIntroductionCard.column_9_text,
         link: originalRequest.url,
+        image: `https:${briefIntroductionCard.column_2_image}`,
         item: items,
     };
 }

package/lib/routes/sotwe/namespace.ts

@@ -0,0 +1 @@
+export { namespace } from '@/routes/twitter/namespace';

package/lib/routes/sotwe/user.ts

@@ -0,0 +1,98 @@
+import { Route, ViewType } from '@/types';
+
+import { parseDate } from '@/utils/parse-date';
+import sanitizeHtml from 'sanitize-html';
+import puppeteer from '@/utils/puppeteer';
+import logger from '@/utils/logger';
+import cache from '@/utils/cache';
+import { config } from '@/config';
+
+export const route: Route = {
+    path: '/user/:id',
+    categories: ['social-media'],
+    example: '/sotwe/user/_RSSHub',
+    parameters: {
+        id: 'Twitter username',
+    },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: true,
+        antiCrawler: true,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['www.sotwe.com/:id'],
+            target: '/user/:id',
+        },
+    ],
+    name: 'User timeline - Sotwe',
+    maintainers: ['TonyRL'],
+    handler,
+    view: ViewType.Pictures,
+};
+
+const renderMedia = (mediaEntities) =>
+    mediaEntities
+        .map((e) => {
+            switch (e.type) {
+                case 'photo':
+                    return `<img src="${e.mediaURL}">`;
+                case 'video': {
+                    const video = e.videoInfo.variants.filter((v) => v.type === 'video/mp4').sort((a, b) => b.bitrate - a.bitrate)[0];
+                    return `<video controls preload="metadata" poster="${e.mediaURL}"><source src="${video.url}" type="video/mp4"></video>`;
+                }
+                default:
+                    return '';
+            }
+        })
+        .join('<br>');
+
+const renderDescription = (item) =>
+    `${renderMedia(item.mediaEntities)}<br>${item.text.replaceAll('\n', '<br>')}${item.quotedStatus ? `<br>${renderDescription(item.quotedStatus)}` : ''}${item.retweetedStatus ? `<br>${renderDescription(item.retweetedStatus)}` : ''}`;
+
+async function handler(ctx) {
+    const baseUrl = 'https://www.sotwe.com';
+    const { id } = ctx.req.param();
+
+    const data = await cache.tryGet(
+        `sotwe:user:${id}`,
+        async () => {
+            const browser = await puppeteer();
+            const page = await browser.newPage();
+            await page.setRequestInterception(true);
+            page.on('request', (request) => {
+                ['document', 'script', 'xhr', 'fetch'].includes(request.resourceType()) ? request.continue() : request.abort();
+            });
+            const apiUrl = `${baseUrl}/api/v3/user/${id}/`;
+            logger.http(`Requesting ${apiUrl}`);
+            await page.goto(apiUrl, {
+                waitUntil: 'domcontentloaded',
+            });
+            const response = await page.evaluate(() => document.documentElement.textContent);
+            await page.close();
+            await browser.close();
+
+            return JSON.parse(response || '{}');
+        },
+        config.cache.routeExpire,
+        false
+    );
+
+    const items = data.data.map((item) => ({
+        title: sanitizeHtml(item.text.split('\n')[0], { allowedTags: [], allowedAttributes: {} }),
+        description: renderDescription(item),
+        link: `https://x.com/${id}/status/${item.id}`,
+        pubDate: parseDate(item.createdAt, 'x'),
+    }));
+
+    return {
+        title: `${data.info.name} @${data.info.screenName} - Twitter Profile | Sotwe`,
+        description: data.info.description,
+        link: `${baseUrl}/${id}`,
+        image: data.info.profileImageThumbnail,
+        item: items,
+    };
+}

package/lib/routes/spankbang/new-videos.ts

@@ -78,6 +78,7 @@ export const route: Route = {
     features: {
         antiCrawler: true,
         requirePuppeteer: true,
+        nsfw: true,
     },
     radar: [
         {

package/lib/routes/spglobal/ratings.ts

@@ -38,7 +38,7 @@ export const route: Route = {
 | ru | Русский |
 | ar | العربية |
     `,
-    maintainers: ['FYLSen'],
+    maintainers: ['Cedaric'],
     handler,
 };
 

package/lib/routes/stanford/blog.ts

@@ -0,0 +1,77 @@
+import { Route } 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';
+
+export const route: Route = {
+    path: ['/hazyresearch/blog'],
+    categories: ['blog'],
+    example: '/stanford/hazyresearch/blog',
+    parameters: {},
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['hazyresearch.stanford.edu/blog'],
+        },
+    ],
+    name: 'Hazy Research Blog',
+    maintainers: ['dvorak0'],
+    handler,
+    url: 'hazyresearch.stanford.edu/blog',
+};
+
+async function handler() {
+    const baseUrl = 'https://hazyresearch.stanford.edu';
+    const currentUrl = `${baseUrl}/blog`;
+    const { data: response } = await got(currentUrl);
+    const $ = load(response);
+
+    // Parse __NEXT_DATA__ for posts
+    const nextDataRaw = $('script#__NEXT_DATA__').text();
+    const nextData = JSON.parse(nextDataRaw);
+
+    const posts = nextData.props.pageProps.posts || [];
+    const buildId = nextData.buildId;
+
+    const list = posts.map((post) => ({
+        title: post.title,
+        link: `${baseUrl}/blog/${post.slug}`,
+        api: `${baseUrl}/_next/data/${buildId}/blog/${post.slug}.json`,
+        author: post.author,
+        pubDate: timezone(parseDate(post.dateString, 'MMM D, YYYY'), -7),
+    }));
+
+    const items = await Promise.all(
+        list.map((item) =>
+            cache.tryGet(item.link, async () => {
+                // ✅ For full content, request real HTML page
+                const { data: html } = await got(item.link);
+                const $post = load(html);
+
+                // Adjust the selector to match your page structure!
+                const content = $post('main [class^="Post_content"]').html();
+
+                item.description = content || '';
+
+                return item;
+            })
+        )
+    );
+
+    return {
+        title: 'Hazy Research Blog',
+        link: currentUrl,
+        description: 'Research updates from Stanford Hazy Research',
+        language: 'en',
+        item: items,
+    };
+}

package/lib/routes/stanford/namespace.ts

@@ -0,0 +1,7 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'Stanford',
+    url: 'hazyresearch.stanford.edu/blog',
+    lang: 'en',
+};

package/lib/routes/syosetu/index.ts

@@ -72,7 +72,7 @@ async function handler(ctx: Context): Promise<Data> {
 
             const item = await fetchChapterContent(chapterUrl, chapterNumber);
             return item;
-        }).reverse()
+        }).toReversed()
     );
 
     return {

package/lib/routes/t66y/index.ts

@@ -17,6 +17,7 @@ export const route: Route = {
         supportBT: false,
         supportPodcast: false,
         supportScihub: false,
+        nsfw: true,
     },
     name: '分区帖子',
     maintainers: ['zhboner'],