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

package/lib/routes/weibo/super-index.ts

@@ -37,11 +37,15 @@ export const route: Route = {
 | feed       | 最新评论         |`,
 };
 
+interface Card {
+    card_group?: Card[];
+}
+
 async function handler(ctx) {
     const id = ctx.req.param('id');
     const type = ctx.req.param('type') ?? 'feed';
 
-    const containerData = await cache.tryGet(
+    const containerData = (await cache.tryGet(
         `weibo:super_index:container:${id}:${type}`,
         async () => {
             const _r = await got('https://m.weibo.cn/api/container/getIndex', {
@@ -61,27 +65,35 @@ async function handler(ctx) {
         },
         config.cache.routeExpire,
         false
-    );
+    )) as {
+        cards?: Card[];
+        pageInfo?: {
+            page_title: string;
+        };
+    };
 
     const resultItems = [];
 
-    for (const card of containerData.cards) {
+    function handleCard(ctx, card, resultItems) {
+        if (card.card_type === '9' && 'mblog' in card) {
+            const formatExtended = weiboUtils.formatExtended(ctx, card.mblog, undefined);
+            resultItems.push(formatExtended);
+        }
+    }
+    for (const card of containerData?.cards ?? []) {
+        handleCard(ctx, card, resultItems);
         if (!('card_group' in card)) {
             continue;
         }
-        for (const mblogCard of card.card_group) {
-            if (mblogCard.card_type === '9' && 'mblog' in mblogCard) {
-                const mblog = mblogCard.mblog;
-                const formatExtended = weiboUtils.formatExtended(ctx, mblog);
-                resultItems.push(formatExtended);
-            }
+        for (const mblogCard of card.card_group!) {
+            handleCard(ctx, mblogCard, resultItems);
         }
     }
 
     return weiboUtils.sinaimgTvax({
-        title: `微博超话 - ${containerData.pageInfo.page_title}`,
+        title: `微博超话 - ${containerData?.pageInfo?.page_title}`,
         link: `https://weibo.com/p/${id}/super_index`,
-        description: `#${containerData.pageInfo.page_title}# 的超话`,
+        description: `#${containerData?.pageInfo?.page_title}# 的超话`,
         item: resultItems,
     });
 }

package/lib/routes/weibo/user.ts

@@ -30,12 +30,20 @@ export const route: Route = {
     },
     radar: [
         {
-            source: ['m.weibo.cn/u/:uid', 'm.weibo.cn/profile/:uid', 'www.weibo.com/u/:uid'],
+            source: ['m.weibo.cn/u/:uid', 'm.weibo.cn/profile/:uid'],
+            target: '/user/:uid',
+        },
+        {
+            source: ['weibo.com/u/:uid'],
+            target: '/user/:uid',
+        },
+        {
+            source: ['www.weibo.com/u/:uid'],
             target: '/user/:uid',
         },
     ],
     name: '博主',
-    maintainers: ['DIYgod', 'iplusx', 'Rongronggg9'],
+    maintainers: ['DIYgod', 'iplusx', 'Rongronggg9', 'Konano'],
     handler,
     description: `:::warning
   部分博主仅登录可见，未提供 Cookie 的情况下不支持订阅，可以通过打开 \`https://m.weibo.cn/u/:uid\` 验证
@@ -47,6 +55,7 @@ async function handler(ctx) {
     let displayVideo = '1';
     let displayArticle = '0';
     let displayComments = '0';
+    let showRetweeted = '1';
     if (ctx.req.param('routeParams')) {
         if (ctx.req.param('routeParams') === '1' || ctx.req.param('routeParams') === '0') {
             displayVideo = ctx.req.param('routeParams');
@@ -55,6 +64,7 @@ async function handler(ctx) {
             displayVideo = fallback(undefined, queryToBoolean(routeParams.displayVideo), true) ? '1' : '0';
             displayArticle = fallback(undefined, queryToBoolean(routeParams.displayArticle), false) ? '1' : '0';
             displayComments = fallback(undefined, queryToBoolean(routeParams.displayComments), false) ? '1' : '0';
+            showRetweeted = fallback(undefined, queryToBoolean(routeParams.showRetweeted), false) ? '1' : '0';
         }
     }
     const containerData = await cache.tryGet(
@@ -102,7 +112,15 @@ async function handler(ctx) {
 
     let resultItems = await Promise.all(
         cards
-            .filter((item) => item.mblog)
+            .filter((item) => {
+                if (item.mblog === undefined) {
+                    return false;
+                }
+                if (showRetweeted === '0' && item.mblog.retweeted_status) {
+                    return false;
+                }
+                return true;
+            })
             .map(async (item) => {
                 // TODO: unify cache key and let weiboUtils.getShowData() handle the cache? It seems safe to do so.
                 //       Need more investigation, pending for now since the current version works fine.
@@ -180,5 +198,6 @@ async function handler(ctx) {
         description,
         image: profileImageUrl,
         item: resultItems,
+        allowEmpty: true,
     });
 }

package/lib/routes/weibo/utils.ts

@@ -171,10 +171,6 @@ const weiboUtils = {
                     html += '</a>';
                 }
 
-                if (!readable) {
-                    html += '<br><br>';
-                }
-
                 htmlNewLineUnreplaced += '<img src="" />';
             }
         }

package/lib/routes/whu/cs.ts

@@ -71,10 +71,16 @@ async function handler(ctx) {
             };
         });
 
-    const items = await Promise.all(
+    let items = await Promise.all(
         list.map((item) =>
             cache.tryGet(item.link, async () => {
-                const response = await got(item.link);
+                let response;
+                try {
+                    // 实测发现有些链接无法访问
+                    response = await got(item.link);
+                } catch {
+                    return null;
+                }
                 const $ = load(response.data);
 
                 if ($('.prompt').length) {
@@ -87,7 +93,8 @@ async function handler(ctx) {
                 content.find('img').each((_, e) => {
                     e = $(e);
                     if (e.attr('orisrc')) {
-                        e.attr('src', new URL(e.attr('orisrc'), response.url).href);
+                        const newUrl = new URL(e.attr('orisrc'), 'https://cs.whu.edu.cn');
+                        e.attr('src', newUrl.href);
                         e.removeAttr('orisrc');
                         e.removeAttr('vurl');
                     }
@@ -100,6 +107,7 @@ async function handler(ctx) {
             })
         )
     );
+    items = items.filter((item) => item !== null);
 
     return {
         title: $('title').first().text(),

package/lib/routes/whu/gs/index.ts

@@ -46,7 +46,8 @@ export const route: Route = {
 
 async function handler(ctx) {
     const host = 'https://gs.whu.edu.cn/';
-    const type = (ctx.params && Number.parseInt(ctx.req.param('type'))) || 0;
+    const paremType = ctx.req.param('type');
+    const type = paremType ? Number.parseInt(paremType) : 0;
     const response = await got(host + gsIndexMap.get(type));
 
     const $ = load(response.data);

package/lib/routes/whu/news.ts

@@ -13,15 +13,40 @@ import { domain, processMeta, getMeta, processItems } from './util';
 
 export const route: Route = {
     path: '/news/:category{.+}?',
-    name: 'Unknown',
+    categories: ['university'],
+    example: '/whu/news',
+    parameters: { category: '新闻栏目，可选' },
+    name: '新闻网',
     maintainers: [],
     handler,
+    description: `
+category 参数可选，范围如下:
+
+| 新闻栏目 | 武大资讯 | 学术动态 | 珞珈影像 | 武大视频 |
+| -------- | -------- | -------- | -------- | -------- |
+| 参数     |  0 或 \`wdzx/wdyw\`  | 1 或 \`kydt\` | 2 或 \`stkj/ljyx\` | 3 或 \`stkj/wdsp\` |
+
+此外 route 后可以加上 \`?limit=n\` 的查询参数，表示只获取前 n 条新闻；如果不指定默认为 10。
+`,
+};
+
+const parseCategory = (category: string | number) => {
+    const outputs = ['wdzx/wdyw', 'kydt', 'stkj/ljyx', 'stkj/wdsp'];
+    if (['0', '1', '2', '3'].includes(category)) {
+        return outputs[category];
+    }
+    if (outputs.includes(category)) {
+        return category;
+    }
+    return 'wdzx/wdyw';
 };
 
 async function handler(ctx) {
-    const { category = 'wdzx/wdyw' } = ctx.req.param();
+    let { category } = ctx.req.param();
     const limit = ctx.req.query('limit') ? Number.parseInt(ctx.req.query('limit'), 10) : 10;
 
+    category = parseCategory(category);
+
     const rootUrl = `https://news.${domain}`;
     const currentUrl = new URL(`${category}.htm`, rootUrl).href;
 

package/lib/routes/withgoogle/explorables.ts

@@ -0,0 +1,54 @@
+import type { Route, DataItem } from '@/types';
+import cache from '@/utils/cache';
+import ofetch from '@/utils/ofetch';
+import { load } from 'cheerio';
+
+export const route: Route = {
+    name: 'PAIR - AI Exploreables',
+    url: 'pair.withgoogle.com/explorables',
+    path: '/explorables',
+    maintainers: ['cesaryuan'],
+    example: '/withgoogle/explorables',
+    categories: ['blog'],
+    radar: [
+        {
+            source: ['pair.withgoogle.com/explorables'],
+            target: '',
+        },
+    ],
+    handler: async () => {
+        const baseUrl = 'https://pair.withgoogle.com';
+        const response = await ofetch(baseUrl + '/explorables', {
+            method: 'GET',
+        });
+        const $ = load(response);
+        const items = await Promise.all(
+            $('div.explorable-card')
+                .map(async (_, el) => {
+                    const title = $(el).find('h3').text();
+                    const image = $(el).find('img').attr('src');
+                    const link = baseUrl + $(el).find('a').attr('href');
+                    return (await cache.tryGet(link, async () => {
+                        const response = await ofetch(link);
+                        const $item = load(response);
+                        let description = $item('body').html();
+                        if (!description || description.trim() === '') {
+                            description = $('p').text();
+                        }
+                        return {
+                            title,
+                            link,
+                            description,
+                            image,
+                        };
+                    })) as DataItem;
+                })
+                .toArray()
+        );
+        return {
+            title: 'PAIR - AI Exploreables',
+            link: 'https://pair.withgoogle.com/explorables',
+            item: items,
+        };
+    },
+};

package/lib/routes/withgoogle/namespace.ts

@@ -0,0 +1,6 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'People + AI Research (PAIR)',
+    url: 'pair.withgoogle.com',
+};

package/lib/routes/xbookcn/blog.ts

@@ -0,0 +1,66 @@
+import { Route } from '@/types';
+import ofetch from '@/utils/ofetch';
+import { load } from 'cheerio';
+import cache from '@/utils/cache';
+
+export const route: Route = {
+    path: '/:label?', // 路由路径
+    categories: ['reading'], // 分类
+    example: '/xbookcn/精选作品', // 示例路径
+    parameters: { label: '按名称分类，详见https://blog.xbookcn.net/p/all.html' }, // 参数
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    name: '短篇', // 源名称
+    maintainers: ['Lyunvy'], // 维护者
+    handler: async (ctx) => {
+        const { label = '精选作品' } = ctx.req.param(); // 从请求参数中获取 label
+        const url = `https://blog.xbookcn.net/search/label/${label}`; // 使用反引号构建 URL
+        const response = await ofetch(url); // 请求源链接
+        const $ = load(response); // 加载 HTML
+
+        const articles = $('.blog-posts.hfeed .date-outer').find('.post'); // 查找文章
+
+        const list = articles.toArray().map((elem) => {
+            const a = $(elem).find('.post-title a'); // 获取标题链接
+            return {
+                title: a.text().trim(), // 标题
+                link: a.attr('href'), // 链接
+                category: [], // 分类
+            };
+        });
+
+        const items = await Promise.all(
+            list.map(
+                async (item) =>
+                    // 使用缓存以避免重复请求
+                    await cache.tryGet(item.link, async () => {
+                        const response = await ofetch(item.link); // 请求文章链接
+                        const $ = load(response); // 加载文章页面
+
+                        // 获取文章的完整描述
+                        item.description = $('.post-body.entry-content').html() || '无内容'; // 抓取指定内容
+
+                        // 获取分类信息
+                        const categories = $('.post-labels a')
+                            .toArray()
+                            .map((el) => $(el).text().trim());
+                        item.category = categories; // 添加多个分类信息
+
+                        return item; // 返回带有描述和分类的文章对象
+                    })
+            )
+        );
+
+        return {
+            title: 'xbookcn', // 源标题
+            link: url, // 源链接
+            item: items, // 源文章
+        };
+    },
+};

package/lib/routes/xbookcn/namespace.ts

@@ -0,0 +1,6 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: '中文成人文學網',
+    url: 'www.xbookcn.net',
+};

package/lib/routes/xiaohongshu/notes.ts

@@ -10,9 +10,17 @@ export const route: Route = {
             target: '/user/:user_id/notes',
         },
     ],
-    name: 'Unknown',
-    maintainers: [],
+    name: '用户笔记 全文',
+    maintainers: ['howerhe'],
     handler,
+    example: '/xiaohongshu/user/52d8c541b4c4d60e6c867480/notes/fulltext',
+    features: {
+        antiCrawler: true,
+        requirePuppeteer: true,
+    },
+    parameters: {
+        user_id: 'user id, length 24 characters',
+    },
 };
 
 async function handler(ctx) {

package/lib/routes/xiaohongshu/user.ts

@@ -1,13 +1,36 @@
-import { Route } from '@/types';
+import { Route, ViewType } from '@/types';
 import cache from '@/utils/cache';
 import { getUser } from './util';
 import InvalidParameterError from '@/errors/types/invalid-parameter';
 
 export const route: Route = {
     path: '/user/:user_id/:category',
-    name: 'Unknown',
-    maintainers: [],
+    name: '用户笔记',
+    categories: ['social-media', 'popular'],
+    view: ViewType.Articles,
+    maintainers: ['lotosbin'],
     handler,
+    example: '/xiaohongshu/user/593032945e87e77791e03696/notes',
+    features: {
+        antiCrawler: true,
+        requirePuppeteer: true,
+    },
+    parameters: {
+        user_id: 'user id, length 24 characters',
+        category: {
+            description: 'category, notes or collect',
+            options: [
+                {
+                    value: 'notes',
+                    label: 'notes',
+                },
+                {
+                    value: 'collect',
+                    label: 'collect',
+                },
+            ],
+        },
+    },
 };
 
 async function handler(ctx) {
@@ -21,15 +44,16 @@ async function handler(ctx) {
         collect,
     } = await getUser(url, cache);
 
-    const title = `${basicInfo.nickname} - ${category === 'notes' ? '笔记' : '收藏'} • 小红书 / RED`;
+    const title = `${basicInfo.nickname} - 小红书${category === 'notes' ? '笔记' : '收藏'}`;
     const description = `${basicInfo.desc} ${tags.map((t) => t.name).join(' ')} ${interactions.map((i) => `${i.count} ${i.name}`).join(' ')}`;
     const image = basicInfo.imageb || basicInfo.images;
 
     const renderNote = (notes) =>
         notes.flatMap((n) =>
-            n.map(({ noteCard }) => ({
+            n.map(({ id, noteCard }) => ({
                 title: noteCard.displayTitle,
-                link: `${url}/${noteCard.noteId}`,
+                link: `${url}/${noteCard.noteId || id}`,
+                guid: noteCard.noteId || id || noteCard.displayTitle,
                 description: `<img src ="${noteCard.cover.infoList.pop().url}"><br>${noteCard.displayTitle}`,
                 author: noteCard.user.nickname,
                 upvotes: noteCard.interactInfo.likedCount,

package/lib/routes/xiaohongshu/util.ts

@@ -7,7 +7,9 @@ const getUser = (url, cache) =>
     cache.tryGet(
         url,
         async () => {
-            const browser = await puppeteer();
+            const browser = await puppeteer({
+                stealth: true,
+            });
             try {
                 const page = await browser.newPage();
                 await page.setRequestInterception(true);

package/lib/routes/xiaoyuzhou/podcast.ts

@@ -8,7 +8,7 @@ export const route: Route = {
     categories: ['multimedia', 'popular'],
     view: ViewType.Audios,
     example: '/xiaoyuzhou/podcast/6021f949a789fca4eff4492c',
-    parameters: { id: '播客id，可以在小宇宙播客的 URL 中找到' },
+    parameters: { id: '播客 id 或单集 id，可以在小宇宙播客的 URL 中找到' },
     features: {
         requireConfig: false,
         requirePuppeteer: false,
@@ -19,25 +19,53 @@ export const route: Route = {
     },
     radar: [
         {
-            source: ['xiaoyuzhoufm.com/podcast/:id'],
+            source: ['xiaoyuzhoufm.com/podcast/:id', 'xiaoyuzhoufm.com/episode/:id'],
         },
     ],
     name: '播客',
-    maintainers: ['hondajojo', 'jtsang4'],
+    maintainers: ['hondajojo', 'jtsang4', 'pseudoyu'],
     handler,
     url: 'xiaoyuzhoufm.com/',
 };
 
 async function handler(ctx) {
-    const link = `https://www.xiaoyuzhoufm.com/podcast/${ctx.req.param('id')}`;
-    const response = await got({
+    const id = ctx.req.param('id');
+    let link = `https://www.xiaoyuzhoufm.com/podcast/${id}`;
+    let response = await got({
         method: 'get',
         url: link,
     });
 
-    const $ = load(response.data);
+    let $ = load(response.data);
+    let page_data = JSON.parse($('#__NEXT_DATA__')[0].children[0].data);
 
-    const page_data = JSON.parse($('#__NEXT_DATA__')[0].children[0].data);
+    if (!page_data.props.pageProps.podcast?.episodes) {
+        // If episodes are not found, it might be an episode page
+        // Try to get the podcast id from the episode page
+        link = `https://www.xiaoyuzhoufm.com/episode/${id}`;
+        response = await got({
+            method: 'get',
+            url: link,
+        });
+
+        $ = load(response.data);
+        const podcastLink = $('.jsx-605929003.podcast-title .jsx-605929003.name').attr('href');
+        if (podcastLink) {
+            const podcastId = podcastLink.split('/').pop();
+            link = `https://www.xiaoyuzhoufm.com/podcast/${podcastId}`;
+            response = await got({
+                method: 'get',
+                url: link,
+            });
+
+            $ = load(response.data);
+            page_data = JSON.parse($('#__NEXT_DATA__')[0].children[0].data);
+        }
+    }
+
+    if (!page_data.props.pageProps.podcast?.episodes) {
+        throw new Error('Failed to fetch podcast episodes');
+    }
 
     const episodes = page_data.props.pageProps.podcast.episodes.map((item) => ({
         title: item.title,

package/lib/routes/xidian/cs.ts

@@ -0,0 +1,143 @@
+import { Route } from '@/types';
+import cache from '@/utils/cache';
+import got from '@/utils/got';
+import { load } from 'cheerio';
+import { parseDate } from '@/utils/parse-date';
+
+const baseUrl = 'https://cs.xidian.edu.cn';
+
+const struct = {
+    xyxw: {
+        selector: {
+            list: '.n_wenzhang ul li',
+        },
+        name: '主页-学院新闻',
+        path: '/xyxw',
+    },
+    tzgg: {
+        selector: {
+            list: '.n_wenzhang ul li',
+        },
+        name: '主页-通知公告',
+        path: '/tzgg',
+    },
+    jlhz1: {
+        selector: {
+            list: '.n_wenzhang ul li',
+        },
+        name: '主页-交流合作',
+        path: '/jlhz1',
+    },
+    rsrc: {
+        selector: {
+            list: '.n_wenzhang ul li',
+        },
+        name: '主页-人事人才',
+        path: 'rsrc',
+    },
+    bkjy_jxxw: {
+        selector: {
+            list: '.n_wenzhang ul li',
+        },
+        name: '主页-本科生教育 / 本科教育-教学新闻',
+        path: 'bkjy/jxxw',
+    },
+    yjsjy_yjstz: {
+        selector: {
+            list: '.n_wenzhang ul li',
+        },
+        name: '主页-研究生教育 / 研究生教育-研究生通知',
+        path: 'yjsjy/yjstz',
+    },
+    jyzhaop: {
+        selector: {
+            list: '.n_wenzhang ul li',
+        },
+        name: '主页-就业招聘',
+        path: 'jyzhaop',
+    },
+};
+
+export const route: Route = {
+    path: '/cs/:category?',
+    categories: ['university'],
+    example: '/xidian/cs/xyxw',
+    parameters: { category: '通知类别，默认为主页-学院新闻' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    name: '计算机科学与技术学院',
+    url: 'cs.xidian.edu.cn',
+    maintainers: ['ZiHao256'],
+    handler,
+    description: `| 文章来源                   | 参数          |
+| ---------------------- | ----------- |
+| ✅主页-学院新闻                | xyxw        |
+| ✅主页-通知公告                | tzgg        |
+| ✅主页-交流合作                | jlhz1       |
+| ✅主页-人事人才                | rsrc        |
+| ✅主页-本科生教育 / 本科教育-教学新闻   | bkjy_jxxw   |
+| ✅主页-研究生教育 / 研究生教育-研究生通知 | yjsjy_yjstz |
+| ✅主页-就业招聘                | jyzhaop     |`,
+    radar: [
+        {
+            source: ['cs.xidian.edu.cn/'],
+        },
+    ],
+};
+
+async function handler(ctx) {
+    const { category = 'xyxw' } = ctx.req.param();
+    const url = `${baseUrl}/${struct[category].path}.htm`;
+    const response = await got(url, {
+        headers: {
+            referer: baseUrl,
+        },
+        https: {
+            rejectUnauthorized: false,
+        },
+    });
+
+    const $ = load(response.data);
+
+    let items = $(struct[category].selector.list)
+        .toArray()
+        .map((item) => {
+            item = $(item);
+            return {
+                title: item.find('a').text(),
+                link: new URL(item.find('a').attr('href'), baseUrl).href,
+                pubDate: parseDate(item.find('span').text()),
+            };
+        });
+
+    items = await Promise.all(
+        items.map((item) =>
+            cache.tryGet(item.link, async () => {
+                const detailResponse = await got(item.link, {
+                    headers: {
+                        referer: url,
+                    },
+                    https: {
+                        rejectUnauthorized: false,
+                    },
+                });
+                const content = load(detailResponse.data);
+                content('.content-sxt').remove();
+                item.description = content('[name="_newscontent_fromname"]').html();
+                return item;
+            })
+        )
+    );
+
+    return {
+        title: $('title').text(),
+        link: url,
+        item: items,
+    };
+}