rsshub 1.0.0-master.f6c2ebb → 1.0.0-master.f70afef

package/lib/routes/linkresearcher/index.ts

@@ -1,76 +1,138 @@
-import { Route } from '@/types';
-import got from '@/utils/got';
-import qs from 'query-string';
+import { ViewType, type Data, type DataItem, type Route } from '@/types';
+import ofetch from '@/utils/ofetch';
 import { parseDate } from '@/utils/parse-date';
+import InvalidParameterError from '@/errors/types/invalid-parameter';
+import crypto from 'crypto';
+import type { Context } from 'hono';
+import type { DetailResponse, SearchResultItem } from './types';
+import cache from '@/utils/cache';
+import { getCurrentPath } from '@/utils/helpers';
+import { art } from '@/utils/render';
+import path from 'node:path';
+
+const __dirname = getCurrentPath(import.meta.url);
+const templatePath = path.join(__dirname, 'templates/bilingual.art');
 
 const baseURL = 'https://www.linkresearcher.com';
+const apiURL = `${baseURL}/api`;
 
 export const route: Route = {
+    name: 'Articles',
     path: '/:params',
-    name: 'Unknown',
-    maintainers: ['yech1990'],
+    example: '/linkresearcher/category=theses&columns=Nature%20导读&subject=生物',
+    maintainers: ['y9c', 'KarasuShin'],
     handler,
+    view: ViewType.Articles,
+    categories: ['journal'],
+    parameters: {
+        params: {
+            description: 'search parameters, support `category`, `subject`, `columns`, `query`',
+        },
+    },
+    zh: {
+        name: '文章',
+    },
+    'zh-TW': {
+        name: '文章',
+    },
 };
 
-async function handler(ctx) {
-    // parse params
+async function handler(ctx: Context): Promise<Data> {
+    const categoryMap = { theses: '论文', information: '新闻', careers: '职业' } as const;
     const params = ctx.req.param('params');
-    const query = qs.parse(params);
-
-    const categoryMap = { theses: '论文', information: '新闻', careers: '职业' };
-    const category = query.category;
-    let title = categoryMap[category];
-
-    // get XSRF token from main page
-    const metaURL = `${baseURL}/${category}`;
-    const metaResponse = await got(metaURL);
-    const xsrfToken = metaResponse.headers['set-cookie'][0].split(';')[0].split('=')[1];
-
-    let data = { filters: { status: false } };
-    if (query.subject !== undefined && query.columns !== undefined) {
-        data = { filters: { status: true, subject: query.subject, columns: query.columns } };
-        title = `${title}「${query.subject} & ${query.columns}」`;
-    } else if (query.subject !== undefined && query.columns === undefined) {
-        data = { filters: { status: true, subject: query.subject } };
-        title = `${title}「${query.subject}」`;
-    } else if (query.subject === undefined && query.columns !== undefined) {
-        data = { filters: { status: true, columns: query.columns } };
-        title = `${title}「${query.columns}」`;
+    const filters = new URLSearchParams(params);
+
+    const subject = filters.get('subject');
+    const columns = filters.get('columns');
+    const query = filters.get('query') ?? '';
+    const category = filters.get('category') ?? ('theses' as keyof typeof categoryMap);
+
+    if (!(category in categoryMap)) {
+        throw new InvalidParameterError('Invalid category');
+    }
+    let title = categoryMap[category] as string;
+
+    const token = crypto.randomUUID();
+
+    const data: {
+        filters: {
+            status: boolean;
+            subject?: string;
+            columns?: string;
+        };
+    } = { filters: { status: true } };
+
+    if (subject) {
+        data.filters.subject = subject;
+        title = `${title}「${subject}」`;
     }
-    data.query = query.query;
+
+    if (columns) {
+        data.filters.columns = columns;
+        title = `${title}「${columns}」`;
+    }
+
     const dataURL = `${baseURL}/api/${category === 'careers' ? 'articles' : category}/search`;
-    const pageResponse = await got.post(dataURL, {
+    const pageResponse = await ofetch<{
+        hits: SearchResultItem[];
+    }>(dataURL, {
+        method: 'POST',
         headers: {
             'content-type': 'application/json; charset=UTF-8',
-            'x-xsrf-token': xsrfToken,
-            cookie: `XSRF-TOKEN=${xsrfToken}`,
+            'x-xsrf-token': token,
+            cookie: `XSRF-TOKEN=${token}`,
         },
-        searchParams: {
+        params: {
             from: 0,
             size: 20,
             type: category === 'careers' ? 'CAREER' : 'SEARCH',
         },
-        json: data,
+        body: {
+            ...data,
+            query,
+        },
     });
 
-    const list = pageResponse.data.hits;
+    const items = await Promise.all(
+        pageResponse.hits.map((item) => {
+            const link = `${baseURL}/${category}/${item.id}`;
+            return cache.tryGet(link, async () => {
+                const response = await ofetch<DetailResponse>(`${apiURL}/${category === 'theses' ? 'theses' : 'information'}/${item.id}`, {
+                    responseType: 'json',
+                });
+
+                const dataItem: DataItem = {
+                    title: response.title,
+                    pubDate: parseDate(response.onlineTime),
+                    link,
+                    image: response.cover,
+                };
+
+                dataItem.description =
+                    'zhTextList' in response && 'enTextList' in response
+                        ? art(templatePath, {
+                              zh: response.zhTextList,
+                              en: response.enTextList,
+                          })
+                        : response.content;
+
+                if ('paperList' in response) {
+                    const { doi, authors } = response.paperList[0];
+                    dataItem.doi = doi;
+                    dataItem.author = authors.map((author) => ({ name: author }));
+                }
 
-    const out = list.map((item) => ({
-        title: item.title,
-        description: item.content,
-        pubDate: parseDate(item.createdAt, 'x'),
-        link: `${metaURL}/${item.id}`,
-        guid: `${metaURL}/${item.id}`,
-        doi: item.identCode === undefined ? '' : item.identCode,
-        author: item.authors === undefined ? '' : item.authors.join(', '),
-    }));
+                return dataItem;
+            }) as unknown as DataItem;
+        })
+    );
 
     return {
         title: `领研 | ${title}`,
         description:
             '领研是链接华人学者的人才及成果平台。领研为国内外高校、科研机构及科技企业提供科研人才招聘服务，也是青年研究者的职业发展指导及线上培训平台；研究者还可将自己的研究论文上传至领研，与超过五十万华人学者分享工作的最新进展。',
-        image: 'https://www.linkresearcher.com/assets/images/logo-app.png',
+        image: `${baseURL}/assets/images/logo-app.png`,
         link: baseURL,
-        item: out,
+        item: items,
     };
 }

package/lib/routes/linkresearcher/namespace.ts

@@ -2,6 +2,12 @@ import type { Namespace } from '@/types';
 
 export const namespace: Namespace = {
     name: 'Link Research',
-    url: 'linkresearcher',
-    lang: 'en',
+    url: 'www.linkresearcher.com',
+    lang: 'zh-CN',
+    zh: {
+        name: '领研',
+    },
+    'zh-TW': {
+        name: '領研',
+    },
 };

package/lib/routes/linkresearcher/templates/bilingual.art

@@ -0,0 +1,7 @@
+{{ each en }}
+{{ if $index !== 0 }}
+<br>
+{{ /if }}
+<p>{{ $value }}</p>
+<p>{{ zh[$index] }}</p>
+{{ /each }}

package/lib/routes/linkresearcher/types.ts

@@ -0,0 +1,103 @@
+interface BaseItem {
+    id: string;
+    title: string;
+    tags: string[];
+    onlineTime: number;
+    cover: string;
+}
+
+export interface InformationItem extends BaseItem {
+    summary: string;
+}
+
+export interface ThesesItem extends BaseItem {
+    authors: string[];
+    content: string;
+    journals: string[];
+    publishDate: string;
+    source: {
+        sourceType: string;
+    };
+    subject: string;
+    thesisTitle: string;
+}
+
+export interface ArticleItem extends BaseItem {
+    columns: string[];
+    source: {
+        logo: string;
+        sourceId: string;
+        sourceName: string;
+        sourceType: string;
+    };
+    summary: string;
+    type: string;
+}
+
+export type SearchResultItem = InformationItem | ThesesItem | ArticleItem;
+
+export interface ThesesDetailResponse {
+    columns: string[];
+    content: string;
+    cover: string;
+    enTextList: string[];
+    id: string;
+    journals: string[];
+    link: string;
+    onlineTime: number;
+    original: boolean;
+    paperList: {
+        authors: string[];
+        checkname: string;
+        doi: string;
+        id: string;
+        journal: string;
+        link: string;
+        publishDate: string;
+        subjects: string[];
+        summary: string;
+        title: string;
+        translateSummary: string;
+        type: string;
+    }[];
+    relevant: {
+        timestamp: number;
+        type: string;
+    }[];
+    source: {
+        sourceId: string;
+        sourceName: string;
+    };
+    sourceKey: string;
+    sourceType: string;
+    tags: string[];
+    template: boolean;
+    title: string;
+    userType: number;
+    zhTextList?: string[];
+}
+
+export interface InformationDetailResponse {
+    columns: string[];
+    content: string;
+    cover: string;
+    id: string;
+    onlineTime: number;
+    original: boolean;
+    relevant: {
+        timestamp: number;
+        type: string;
+    }[];
+    source: {
+        sourceId: string;
+        sourceName: string;
+    };
+    sourceKey: string;
+    subject: string;
+    summary: string;
+    tags: string[];
+    title: string;
+    type: string;
+}
+
+export type DetailResponse = ThesesDetailResponse | InformationDetailResponse;

package/lib/routes/liveuamap/index.ts

@@ -6,7 +6,7 @@ import InvalidParameterError from '@/errors/types/invalid-parameter';
 
 export const route: Route = {
     path: '/:region?',
-    categories: ['new-media'],
+    categories: ['new-media', 'popular'],
     example: '/liveuamap',
     parameters: { region: 'region 热点地区，默认为`ukraine`，其他选项见liveuamap.com的三级域名' },
     features: {

package/lib/routes/lmu/namespace.ts

@@ -6,7 +6,7 @@ export const namespace: Namespace = {
     description: `
 This namespace provides RSS feeds for various sections of the Ludwig Maximilian University of Munich (LMU) website, particularly for job openings in the academic staff section.
 
-:::tip
+::: tip
 For more information about LMU and their job offerings, visit their official website.
 :::
 `,

package/lib/routes/lofter/collection.ts

@@ -6,7 +6,7 @@ import { parseDate } from '@/utils/parse-date';
 
 export const route: Route = {
     path: '/collection/:collectionID',
-    categories: ['social-media'],
+    categories: ['social-media', 'popular'],
     example: '/lofter/collection/552041',
     parameters: { collectionID: 'Lofter collection ID, can be found in the share URL' },
     features: {

package/lib/routes/lofter/tag.ts

@@ -6,7 +6,7 @@ import { JSDOM } from 'jsdom';
 
 export const route: Route = {
     path: '/tag/:name?/:type?',
-    categories: ['social-media'],
+    categories: ['social-media', 'popular'],
     example: '/lofter/tag/cosplay/date',
     parameters: { name: 'tag name, such as `名侦探柯南`, `摄影` by default', type: 'ranking type, see below, new by default' },
     features: {

package/lib/routes/logrocket/index.ts

@@ -0,0 +1,71 @@
+import { parseDate } from '@/utils/parse-date';
+import ofetch from '@/utils/ofetch'; // 统一使用的请求库
+import { load } from 'cheerio'; // 类似 jQuery 的 API HTML 解析器
+import { Route } from '@/types';
+import cache from '@/utils/cache';
+// import { getCurrentPath } from '@/utils/helpers';
+// import { art } from '@/utils/render';
+// import path from 'node:path';
+// const __dirname = getCurrentPath(import.meta.url);
+export const route: Route = {
+    path: '/:type',
+    categories: ['blog'],
+    example: '/logrocket/dev',
+    parameters: { type: 'dev | product-management | ux-design' },
+    radar: [
+        {
+            source: ['blog.logrocket.com'],
+        },
+    ],
+    name: 'blog.logrocket',
+    maintainers: ['findwei'],
+    handler,
+    url: 'blog.logrocket.com/',
+};
+async function handler(ctx) {
+    const type = ctx.req.param('type');
+    const link = 'https://blog.logrocket.com/';
+    let title = 'Dev';
+    if (type === 'product-management') {
+        title = 'Product Management';
+    } else if (type === 'ux-design') {
+        title = 'UX Design';
+    }
+    const response = await ofetch(`${link}${type}`);
+    const $ = load(response);
+    const list = $('div.post-list .post-card')
+        .toArray()
+        .map((item) => {
+            item = $(item);
+            const a = item.find('a').first();
+            const title = item.find('.post-card-title').first();
+            return {
+                title: title.text(),
+                link: a.attr('href'),
+                pubDate: parseDate(item.find('.post-card-author-name').next().text().split(' ⋅ ')[0], 'MMM D, YYYY'),
+                author: item.find('.post-card-author-name').text(),
+            };
+        });
+    const items = await Promise.all(
+        list.map((item) =>
+            cache.tryGet(item.link, async () => {
+                const response = await ofetch(item.link);
+                const $ = load(response);
+                //
+                $('div.content-max-width .sidebar-container div.code-block').remove();
+                item.description = $('div.content-max-width .sidebar-container').html();
+                // item.description = art(path.join(__dirname, 'templates/description.art'), {
+                //     // header: $('#post-header').html(),
+                //     description: $('div.content-max-width .the-content-container').remove('.lr-content div.code-block.code-block-77').remove('.lr-content .code-block.code-block-57').html(),
+                // });
+                return item;
+            })
+        )
+    );
+    return {
+        title: `logrocket-${title}`,
+        link,
+        description: `logrocket-${title}`,
+        item: items,
+    };
+}

package/lib/routes/logrocket/namespace.ts

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

package/lib/routes/lorientlejour/index.ts

@@ -47,10 +47,10 @@ export const route: Route = {
     name: 'Category',
     maintainers: ['quiniapiezoelectricity'],
     handler,
-    description: `  :::tip
+    description: `  ::: tip
 For example, the path for the sites https://today.lorientlejour.com/section/977-lebanon and https://www.lorientlejour.com/rubrique/1-liban would be /lorientlejour/977-lebanon and /lorientlejour/1-liban respectively. 
 Multiple categories seperated by '|' is also supported, e.g. /lorientlejour/977-lebanon|1-liban.
-  :::`,
+:::`,
     radar: [
         {
             source: ['www.lorientlejour.com/*/:category'],

package/lib/routes/lrepacks/index.ts

@@ -117,7 +117,7 @@ export const route: Route = {
     handler,
     example: '/lrepacks',
     parameters: { category: 'Category, Homepage by default' },
-    description: `:::tip
+    description: `::: tip
   If you subscribe to [Системные программы](https://lrepacks.net/repaki-sistemnyh-programm/)，where the URL is \`https://lrepacks.net/repaki-sistemnyh-programm/\`, extract the part \`https://lrepacks.net/\` to the end, which is \`repaki-sistemnyh-programm\`, and use it as the parameter to fill in. Therefore, the route will be [\`/lrepacks/repaki-sistemnyh-programm\`](https://rsshub.app/lrepacks/repaki-sistemnyh-programm).
 
   | Category                                                                        | ID                                                                                           |
@@ -131,7 +131,7 @@ export const route: Route = {
   | [Разные программы](https://lrepacks.net/repaki-raznyh-programm/)                | [repaki-raznyh-programm](https://rsshub.app/lrepacks/repaki-raznyh-programm)                 |
   | [Системные библиотеки](https://lrepacks.net/sistemnye-biblioteki/)              | [sistemnye-biblioteki](https://rsshub.app/lrepacks/sistemnye-biblioteki)                     |
   | [Важная информация](https://lrepacks.net/informaciya/)                          | [informaciya](https://rsshub.app/lrepacks/informaciya)                                       |
-  :::`,
+:::`,
     categories: ['program-update'],
 
     features: {

package/lib/routes/luogu/daily.ts

@@ -23,7 +23,7 @@ export const route: Route = {
         },
     ],
     name: '日报',
-    maintainers: ['LogicJake ', 'prnake ', 'nczitzk'],
+    maintainers: ['LogicJake', 'prnake', 'nczitzk'],
     handler,
     url: 'luogu.com.cn/discuss/47327',
 };

package/lib/routes/luogu/user-article.ts

@@ -0,0 +1,75 @@
+import { Route } from '@/types';
+import cache from '@/utils/cache';
+import ofetch from '@/utils/ofetch';
+import * as cheerio from 'cheerio';
+import { getUserInfoFromUID } from './utils';
+import { parseDate } from '@/utils/parse-date';
+
+export const route: Route = {
+    path: '/user/article/:uid',
+    categories: ['programming'],
+    example: '/luogu/user/article/1',
+    parameters: { name: '用户 UID' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['luogu.com/user/:uid'],
+        },
+        {
+            source: ['luogu.com.cn/user/:uid'],
+        },
+    ],
+    name: '用户文章',
+    maintainers: ['TonyRL'],
+    handler,
+};
+
+const baseUrl = 'https://www.luogu.com';
+
+async function handler(ctx) {
+    const { uid } = ctx.req.param();
+
+    const userInfo = await getUserInfoFromUID(uid);
+    const response = await ofetch(`${baseUrl}/api/article/find`, {
+        query: {
+            user: uid,
+            page: 1,
+            ascending: false,
+        },
+    });
+
+    const posts = response.articles.result.map((item) => ({
+        title: item.title,
+        link: `${baseUrl}/article/${item.lid}`,
+        author: item.author.name,
+        pubDate: parseDate(item.time, 'X'),
+        description: item.content,
+    }));
+
+    const item = await Promise.all(
+        posts.map((item) =>
+            cache.tryGet(item.link, async () => {
+                const response = await ofetch(item.link);
+                const $ = cheerio.load(response);
+                item.description = $('div#rendered-preview').html();
+
+                return item;
+            })
+        )
+    );
+
+    return {
+        title: `${userInfo.name} 的个人中心 - 洛谷 | 计算机科学教育新生态`,
+        description: userInfo.description,
+        link: `${baseUrl}/user/${uid}#article`,
+        image: userInfo.avatar,
+        item,
+    };
+}

package/lib/routes/luogu/user-blog.ts

@@ -17,12 +17,15 @@ export const route: Route = {
         supportScihub: false,
     },
     radar: [
+        {
+            source: ['luogu.com/blog/:name'],
+        },
         {
             source: ['luogu.com.cn/blog/:name'],
         },
     ],
     name: '用户博客',
-    maintainers: [],
+    maintainers: ['ftiasch'],
     handler,
 };
 

package/lib/routes/luogu/user-feed.ts

@@ -1,8 +1,8 @@
 import { Route } from '@/types';
-import cache from '@/utils/cache';
 import got from '@/utils/got';
 import { parseDate } from '@/utils/parse-date';
 import MarkdownIt from 'markdown-it';
+import { getUserInfoFromUID } from './utils';
 const md = MarkdownIt();
 
 export const route: Route = {
@@ -19,6 +19,9 @@ export const route: Route = {
         supportScihub: false,
     },
     radar: [
+        {
+            source: ['luogu.com/user/:uid'],
+        },
         {
             source: ['luogu.com.cn/user/:uid'],
         },
@@ -29,27 +32,23 @@ export const route: Route = {
 };
 
 async function handler(ctx) {
-    const getUsernameFromUID = (uid) =>
-        cache.tryGet('luogu:username:' + uid, async () => {
-            const { data } = await got(`https://www.luogu.com.cn/user/${uid}?_contentOnly=1`);
-            return data.currentData.user.name;
-        });
-
     const uid = ctx.req.param('uid');
-    const name = await getUsernameFromUID(uid);
+    const userInfo = await getUserInfoFromUID(uid);
     const { data: response } = await got(`https://www.luogu.com.cn/api/feed/list?user=${uid}`);
 
     const data = response.feeds.result;
 
     return {
-        title: `${name} 的洛谷动态`,
+        title: `${userInfo.name} 的洛谷动态`,
+        description: userInfo.description,
+        image: userInfo.avatar,
         link: `https://www.luogu.com.cn/user/${uid}#activity`,
         allowEmpty: true,
         item: data.map((item) => ({
             title: item.content,
             description: md.render(item.content),
             pubDate: parseDate(item.time, 'X'),
-            author: name,
+            author: userInfo.name,
             link: `https://www.luogu.com.cn/user/${uid}#activity`,
             guid: item.id,
         })),

package/lib/routes/luogu/utils.ts

@@ -0,0 +1,17 @@
+import cache from '@/utils/cache';
+import ofetch from '@/utils/got';
+
+export const getUserInfoFromUID = (uid) =>
+    cache.tryGet('luogu:username:' + uid, async () => {
+        const data = await ofetch(`https://www.luogu.com/user/${uid}`, {
+            query: {
+                _contentOnly: 1,
+            },
+        });
+
+        return {
+            name: data.data.currentData.user.name,
+            description: data.data.currentData.user.slogan,
+            avatar: data.data.currentData.user.avatar,
+        };
+    }) as Promise<{ name: string; description: string; avatar: string }>;

package/lib/routes/m-78/namespace.ts

@@ -0,0 +1,7 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: '円谷ステーション',
+    url: 'm-78.jp',
+    lang: 'ja',
+};