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

package/lib/routes/gamebase/news.ts

@@ -1,98 +1,181 @@
-import { Route } from '@/types';
+import { type Data, type DataItem, type Route, ViewType } from '@/types';
+
+import { art } from '@/utils/render';
 import cache from '@/utils/cache';
-import got from '@/utils/got';
-import { load } from 'cheerio';
-import timezone from '@/utils/timezone';
+import { getCurrentPath } from '@/utils/helpers';
+import InvalidParameterError from '@/errors/types/invalid-parameter';
+import ofetch from '@/utils/ofetch';
 import { parseDate } from '@/utils/parse-date';
+import timezone from '@/utils/timezone';
+
+import { type CheerioAPI, load } from 'cheerio';
+import { type Context } from 'hono';
+import path from 'node:path';
+
+const __dirname = getCurrentPath(import.meta.url);
 
 const types = {
     newslist: 'newsList',
     r18list: 'newsPornList',
 };
 
-export const route: Route = {
-    path: '/news/:type?/:category?',
-    categories: ['game'],
-    example: '/gamebase/news',
-    parameters: { type: '类型，见下表，默认为 newslist', category: '分类，可在对应分类页 URL 中找到，默认为 `all` 即全部' },
-    features: {
-        requireConfig: false,
-        requirePuppeteer: false,
-        antiCrawler: false,
-        supportBT: false,
-        supportPodcast: false,
-        supportScihub: false,
-    },
-    name: '新聞',
-    maintainers: ['nczitzk'],
-    handler,
-    description: `类型
-
-  | newslist | r18list |
-  | -------- | ------- |`,
-};
+export const handler = async (ctx: Context): Promise<Data> => {
+    const { type = 'newslist', category = 'all' } = ctx.req.param();
 
-async function handler(ctx) {
-    const type = ctx.req.param('type') ?? 'newslist';
-    const category = ctx.req.param('category') ?? 'all';
-    const limit = ctx.req.query('limit') ? Number.parseInt(ctx.req.query('limit')) : 20;
+    if (!types.hasOwnProperty(type)) {
+        throw new InvalidParameterError(`Invalid type: ${type}`);
+    }
 
-    const rootUrl = 'https://news.gamebase.com.tw';
-    const currentUrl = `${rootUrl}/news/${type}?type=${category}`;
+    const limit: number = Number.parseInt(ctx.req.query('limit') ?? '30', 10);
 
-    const apiRootUrl = 'https://api.gamebase.com.tw';
-    const apiUrl = `${apiRootUrl}/api/news/getNewsList`;
+    const baseUrl: string = 'https://news.gamebase.com.tw';
+    const targetUrl: string = new URL(`news${category === 'all' ? '' : `/newslist?type=${category}`}`, baseUrl).href;
+    const apiBaseUrl: string = 'https://api.gamebase.com.tw';
+    const apiUrl: string = new URL('api/news/getNewsList', apiBaseUrl).href;
 
-    const response = await got({
+    const response = await ofetch(apiUrl, {
         method: 'post',
-        url: apiUrl,
-        json: {
+        body: {
             GB_type: types[type],
             category,
             page: 1,
         },
     });
 
-    const titleResponse = await got({
-        method: 'get',
-        url: currentUrl,
-    });
+    const targetResponse = await ofetch(targetUrl);
+    const $: CheerioAPI = load(targetResponse);
+    const language = $('html').attr('lang') ?? 'zh-TW';
 
-    const $ = load(titleResponse.data);
+    const items: DataItem[] = await Promise.all(
+        response.return_msg?.list?.slice(0, limit).map((item) =>
+            cache.tryGet(`gamebase-news-${item.news_no}`, async (): Promise<DataItem> => {
+                const title: string = item.news_title;
+                const pubDate: number | string = item.post_time;
+                const linkUrl: string | undefined = item.news_no ? `news/detail/${item.news_no}` : undefined;
+                const categories: string[] = [item.system];
+                const authors: DataItem['author'] = item.nickname;
+                const guid: string = `gamebase-news-${item.news_no}`;
+                const image: string | undefined = item.news_img;
+                const updated: number | string = item.updated ?? pubDate;
 
-    const items = await Promise.all(
-        response.data.return_msg.list.slice(0, limit).map((item) =>
-            cache.tryGet(`gamebase:news:${type}:${category}:${item.news_no}`, async () => {
-                const i = {};
+                let metaDesc = item.news_meta?.meta_des;
 
-                i.author = item.nickname;
-                i.title = item.news_title;
-                i.link = `${rootUrl}/news/detail/${item.news_no}`;
-                i.description = item.news_meta?.meta_des ?? '';
-                i.pubDate = timezone(parseDate(item.post_time), +8);
-                i.category = [item.system];
+                if (!metaDesc) {
+                    const detailResponse = await ofetch(item.link);
 
-                if (i.description) {
-                    return i;
+                    metaDesc = (detailResponse.match(/(\\u003C.*?)","/)?.[1] ?? '').replaceAll(String.raw`\"`, '"').replaceAll(/\\u([\da-f]{4})/gi, (match, hex) => String.fromCodePoint(Number.parseInt(hex, 16)));
                 }
 
-                const detailResponse = await got({
-                    method: 'get',
-                    url: i.link,
+                const description: string = art(path.join(__dirname, 'templates/description.art'), {
+                    images:
+                        image && !metaDesc
+                            ? [
+                                  {
+                                      src: image,
+                                      alt: title,
+                                  },
+                              ]
+                            : undefined,
+                    intro: item.news_short_desc,
+                    description: metaDesc,
                 });
 
-                const description = detailResponse.data.match(/(\\u003C.*?)","/)[1].replaceAll(String.raw`\"`, '"');
-
-                i.description = description.replaceAll(/\\u[\da-f]{4}/gi, (match) => String.fromCharCode(Number.parseInt(match.replaceAll(String.raw`\u`, ''), 16)));
-
-                return i;
+                const processedItem: DataItem = {
+                    title,
+                    description,
+                    pubDate: pubDate ? timezone(parseDate(pubDate), +8) : undefined,
+                    link: linkUrl ? new URL(linkUrl, baseUrl).href : undefined,
+                    category: categories,
+                    author: authors,
+                    guid,
+                    id: guid,
+                    content: {
+                        html: description,
+                        text: description,
+                    },
+                    image,
+                    banner: image,
+                    updated: updated ? timezone(parseDate(updated), +8) : undefined,
+                    language,
+                };
+
+                return processedItem;
             })
-        )
+        ) ?? []
     );
 
     return {
         title: $('title').text(),
-        link: currentUrl,
+        description: $('meta[property="og:description"]').attr('content'),
+        link: targetUrl,
         item: items,
+        allowEmpty: true,
+        image: $('meta[property="og:image"]').attr('content'),
+        author: $('meta[property="og:title"]').attr('content')?.split(/\|/).pop()?.trim(),
+        language,
+        id: $('meta[property="og:url"]').attr('content'),
     };
-}
+};
+
+export const route: Route = {
+    path: '/news/:type?/:category?',
+    name: '新聞',
+    url: 'news.gamebase.com.tw',
+    maintainers: ['nczitzk'],
+    handler,
+    example: '/gamebase/news',
+    parameters: {
+        type: '類型，見下表，預設為 newslist',
+        category: '分類，預設為 `all`，即全部，可在對應分類頁 URL 中找到',
+    },
+    description: `:::tip
+若訂閱 [手機遊戲新聞](https://news.gamebase.com.tw/news/newslist?type=mobile)，網址為 \`https://news.gamebase.com.tw/news/newslist?type=mobile\`，請截取 \`https://news.gamebase.com.tw/news/\` 到末尾的部分 \`newslist\` 作為 \`type\` 參數填入，\`mobile\` 作為 \`category\` 參數填入，此時目標路由為 [\`/gamebase/news/newslist/mobile\`](https://rsshub.app/gamebase/news/newslist/mobile)。
+:::
+
+| newslist | r18list |
+| -------- | ------- |
+`,
+    categories: ['game'],
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportRadar: true,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['news.gamebase.com.tw/news', 'news.gamebase.com.tw/news/:type'],
+            target: (params, url) => {
+                const type: string = params.type;
+                const urlObj: URL = new URL(url);
+                const category: string | undefined = urlObj.searchParams.get('type') ?? undefined;
+
+                return `/gamebase/news${type ? `/${type}${category ? `/${category}` : ''}` : ''}`;
+            },
+        },
+    ],
+    view: ViewType.Articles,
+
+    zh: {
+        path: '/news/:type?/:category?',
+        name: '新闻',
+        url: 'news.gamebase.com.tw',
+        maintainers: ['nczitzk'],
+        handler,
+        example: '/gamebase/news',
+        parameters: {
+            type: '类型，见下表，默认为 newslist',
+            category: '分类，默认为 `all`，即全部，可在对应分类页 URL 中找到',
+        },
+        description: `:::tip
+若订阅 [手机游戏新闻](https://news.gamebase.com.tw/news/newslist?type=mobile)，网址为 \`https://news.gamebase.com.tw/news/newslist?type=mobile\`，请截取 \`https://news.gamebase.com.tw/news/\` 到末尾的部分 \`newslist\` 作为 \`type\` 参数填入，\`mobile\` 作为 \`category\` 参数填入，此时目标路由为 [\`/gamebase/news/newslist/mobile\`](https://rsshub.app/gamebase/news/newslist/mobile)。
+:::
+
+| newslist | r18list |
+| -------- | ------- |
+`,
+    },
+};

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

@@ -0,0 +1,21 @@
+{{ if images }}
+  {{ each images image }}
+    {{ if image?.src }}
+      <figure>
+        <img
+          {{ if image.alt }}
+            alt="{{ image.alt }}"
+          {{ /if }}
+        src="{{ image.src }}">
+      </figure>
+    {{ /if }}
+  {{ /each }}
+{{ /if }}
+
+{{ if intro }}
+  <blockquote>{{ intro }}</blockquote>
+{{ /if }}
+
+{{ if description }}
+  {{@ description }}
+{{ /if }}

package/lib/routes/gcores/category.ts

@@ -6,7 +6,7 @@ import { load } from 'cheerio';
 
 export const route: Route = {
     path: '/category/:category',
-    categories: ['new-media'],
+    categories: ['new-media', 'popular'],
     example: '/gcores/category/news',
     parameters: { category: '分类名' },
     features: {

package/lib/routes/gcores/collection.ts

@@ -5,7 +5,7 @@ import got from '@/utils/got';
 
 export const route: Route = {
     path: '/collections/:collection',
-    categories: ['new-media'],
+    categories: ['new-media', 'popular'],
     example: '/gcores/collections/64',
     parameters: { collection: '专题id，可在专题页面的 URL 中找到，如 游戏开发设计心得分享 -- 64' },
     features: {

package/lib/routes/gcores/radio.ts

@@ -11,7 +11,7 @@ import path from 'node:path';
 
 export const route: Route = {
     path: '/radios/:category?',
-    categories: ['new-media'],
+    categories: ['new-media', 'popular'],
     example: '/gcores/radios/45',
     parameters: { category: '分类名，默认为全部，可在分类页面的 URL 中找到，如 Gadio News -- 45' },
     features: {

package/lib/routes/gcores/tag.ts

@@ -6,7 +6,7 @@ import { load } from 'cheerio';
 
 export const route: Route = {
     path: '/tag/:tag/:category?',
-    categories: ['new-media'],
+    categories: ['new-media', 'popular'],
     example: '/gcores/tag/42/articles',
     parameters: { tag: '标签名，可在选定标签分类页面的 URL 中找到，如视觉动物——42', category: '分类名' },
     features: {

package/lib/routes/gdufs/namespace.ts

@@ -0,0 +1,7 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: '广东外语外贸大学',
+    url: 'gdufs.edu.cn',
+    lang: 'zh-CN',
+};

package/lib/routes/gdufs/news.ts

@@ -0,0 +1,94 @@
+import { Route } from '@/types';
+import { load } from 'cheerio';
+import cache from '@/utils/cache';
+import got from '@/utils/got';
+import { parseDate } from '@/utils/parse-date';
+
+const site = 'https://www.gdufs.edu.cn';
+
+export const route: Route = {
+    path: '/news',
+    categories: ['university'],
+    example: '/gdufs/news',
+    parameters: {},
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['www.gdufs.edu.cn/gwxw/gwxw1.htm', 'www.gdufs.edu.cn/'],
+        },
+    ],
+    name: '新闻',
+    maintainers: ['gz4zzxc'],
+    handler,
+    url: 'www.gdufs.edu.cn/gwxw/gwxw1.htm',
+};
+
+async function handler() {
+    const link = 'https://www.gdufs.edu.cn/gwxw/gwxw1.htm';
+
+    const response = await got(link);
+    const $ = load(response.body);
+    const list = $('ul.list_luntan li');
+
+    const items = await Promise.all(
+        list.toArray().map((element) => {
+            const item = $(element);
+            const href = item.find('a').attr('href') || '';
+            const title = item.find('h5').text().trim();
+            const day = item.find('h3').text().trim();
+            const yearMonth = item.find('h6').text().trim();
+            const dateString = yearMonth + '/' + day;
+            const fullLink = href.startsWith('http') ? href : new URL(href, site).href;
+            const pubDate = parseDate(dateString).toUTCString();
+
+            return cache.tryGet(fullLink, async () => {
+                try {
+                    const articleRes = await got(fullLink);
+                    const $$ = load(articleRes.body);
+                    const description = $$('.v_news_content').html()?.trim() || '';
+
+                    let author = '';
+                    const authorSpans = $$('.nav01 h6 .ll span');
+                    authorSpans.each((_, el) => {
+                        const text = $$(el).text().trim();
+                        if (text.includes('责任编辑：')) {
+                            author = text.replace('责任编辑：', '').trim();
+                        } else if (text.includes('文字：')) {
+                            author = text.replace('文字：', '').trim();
+                        }
+                    });
+
+                    return {
+                        title,
+                        link: fullLink,
+                        description,
+                        pubDate,
+                        author,
+                    };
+                } catch {
+                    return {
+                        title,
+                        link: fullLink,
+                        description: '内容获取失败。',
+                        pubDate,
+                        author: '',
+                    };
+                }
+            });
+        })
+    );
+
+    return {
+        title: '广外-大学要闻',
+        link,
+        description: '广东外语外贸大学-大学要闻',
+        item: items,
+    };
+}

package/lib/routes/gdufs/xwxy/xwxy-news.ts

@@ -0,0 +1,90 @@
+import { Route } from '@/types';
+import { load } from 'cheerio';
+import cache from '@/utils/cache';
+import got from '@/utils/got';
+import { parseDate } from '@/utils/parse-date';
+
+export const route: Route = {
+    path: '/xwxy-news',
+    categories: ['university'],
+    example: '/gdufs/xwxy-news',
+    parameters: {},
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['xwxy.gdufs.edu.cn/xwzx/xyxw', 'xwxy.gdufs.edu.cn/'],
+        },
+    ],
+    name: '新闻学院-学院新闻',
+    maintainers: ['gz4zzxc'],
+    handler,
+    url: 'xwxy.gdufs.edu.cn/xwzx/xyxw',
+};
+
+async function handler() {
+    const BASE_URL = 'https://xwxy.gdufs.edu.cn';
+    const link = `${BASE_URL}/xwzx/xyxw.htm`;
+
+    const response = await got(link);
+    if (!response.body) {
+        throw new Error('No response body');
+    }
+    const $ = load(response.body);
+    const list = $('div.flex-center a.clearfix');
+
+    const items = list.toArray().map((element) => {
+        const item = $(element);
+        const href = item.attr('href') || '';
+        const dateText = item.find('i').text().trim();
+        const pubDate = parseDate(dateText).toUTCString();
+        return {
+            title: item.find('h5').text().trim(),
+            link: href.startsWith('http') ? href : new URL(href, BASE_URL).href,
+            pubDate,
+        };
+    });
+
+    const enhancedItems = await Promise.all(
+        items.map((item) =>
+            cache.tryGet(item.link, async () => {
+                try {
+                    const articleResponse = await got(item.link);
+                    if (!articleResponse.body) {
+                        throw new Error('No article body');
+                    }
+                    const $$ = load(articleResponse.body);
+                    const content = $$('#vsb_content .v_news_content').html() || '';
+                    const authors = $$('.show01 p i')
+                        .toArray()
+                        .map((el) => $$(el).text().trim());
+
+                    return {
+                        ...item,
+                        description: content,
+                        author: authors.join(' '),
+                    };
+                } catch {
+                    return {
+                        ...item,
+                        description: '无法获取内容',
+                        author: '',
+                    };
+                }
+            })
+        )
+    );
+
+    return {
+        title: '广外新传学院-学院新闻',
+        link,
+        description: '广东外语外贸大学新闻与传播学院官网-学院新闻',
+        item: enhancedItems,
+    };
+}

package/lib/routes/geekpark/index.ts

@@ -136,10 +136,10 @@ export const route: Route = {
     handler,
     example: '/geekpark',
     parameters: { column: '栏目 id，默认为空，即首页资讯，可在对应栏目页 URL 中找到' },
-    description: `:::tip
+    description: `::: tip
   若订阅 [综合报道](https://www.geekpark.net/column/179)，网址为 \`https://www.geekpark.net/column/179\`。截取 \`https://www.geekpark.net/column/\` 到末尾的部分 \`179\` 作为参数填入，此时路由为 [\`/geekpark/179\`](https://rsshub.app/geekpark/179)。
-  :::
-  
+:::
+
   | 栏目                                                         | ID                                     |
   | ------------------------------------------------------------ | -------------------------------------- |
   | [综合报道](https://www.geekpark.net/column/179)              | [179](https://rsshub.app/geekpark/179) |
@@ -151,7 +151,7 @@ export const route: Route = {
   | [心科技](https://www.geekpark.net/column/307)                | [307](https://rsshub.app/geekpark/307) |
   | [行业资讯](https://www.geekpark.net/column/2)                | [2](https://rsshub.app/geekpark/2)     |
   `,
-    categories: ['new-media'],
+    categories: ['new-media', 'popular'],
 
     features: {
         requireConfig: false,

package/lib/routes/genossenschaften/index.ts

@@ -0,0 +1,123 @@
+import { load } from 'cheerio';
+import ofetch from '@/utils/ofetch';
+import type { Data, DataItem, Route } from '@/types';
+
+const FEED_TITLE = 'Genossenschaften.immo' as const;
+const FEED_LOGO = 'https://genossenschaften.immo/static/gimmo/img/favicon/favicon-128x128.png' as const;
+const FEED_LANGUAGE = 'de' as const;
+const BASE_URL = 'https://genossenschaften.immo' as const;
+const PATH_PREFIX = '/genossenschaften/' as const;
+
+export const route: Route = {
+    name: 'Immobiliensuche',
+    path: '*',
+    maintainers: ['sk22'],
+    categories: ['other'],
+    description: `
+Note that all parameters are optional and many can be specified multiple times
+(e.g. \`district=wien-1-innere-stadt&district=wien-2-leopoldstadt\`).
+
+Only returns the first page of search results, allowing you to keep track of
+newly added apartments. If you're looking for an apartment, make sure to also
+look through the other pages on the website.
+
+:::tip
+To get your query URL, go to https://genossenschaften.immo and apply all
+desired filters. If you want to filter by (all districts of a) federal state
+(e.g. \`/immobilien/regionen/wien/\`), please open the district selector and
+de- and re-select any district, so that the region in the URL gets replaced
+with a number of \`district\` parameters. Once you've set up all desired
+filters, copy the part of the URL after the \`?\`.
+:::
+`,
+    example:
+        PATH_PREFIX +
+        'district=wien-1-innere-stadt&district=wien-2-leopoldstadt&district=wien-3-landstrasse&district=wien-4-wieden&district=wien-5-margareten&district=wien-6-mariahilf&district=wien-7-neubau&district=wien-8-josefstadt&district=wien-9-alsergrund&district=wien-10-favoriten&district=wien-11-simmering&district=wien-12-meidling&district=wien-13-hietzing&district=wien-14-penzing&district=wien-15-rudolfsheim-fuenfhaus&district=wien-16-ottakring&district=wien-17-hernals&district=wien-18-waehring&district=wien-19-doebling&district=wien-20-brigittenau&district=wien-21-floridsdorf&district=wien-22-donaustadt&district=wien-23-liesing' +
+        '&has_rent=on&has_rent_option=on' +
+        '&status=available&status=construction' +
+        '&cost=1000&room=2&size=50' +
+        '&has_property=off&has_rent=on&has_rent_option=on' +
+        '&status=available&status=construction&status=planned' +
+        '&type=residence&type=project',
+    parameters: {
+        // labels are in german language because it's the same on the website
+        cost: 'Miete bis (in €, number)',
+        district: 'Bezirk (string, multiple)',
+        size: 'Größe ab (in m², number)',
+        room: 'Zimmer ab (number)',
+        genossenschaft: 'Bauvereinigung (string, multiple)',
+        own_funds: 'Eigenkapital bis',
+        has_property: 'Eigentum (`on` | `off`)',
+        has_rent: 'Miete (`on` | `off`)',
+        has_rent_option: 'Miete mit Kaufoption (`on` | `off`)',
+        status: 'multiple, `available` | `construction` | `planned`',
+        type: 'multiple, `residence` | `project`',
+        keywords: 'Keyword search',
+    },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    async handler(ctx) {
+        let path = ctx.req.path.slice(PATH_PREFIX.length);
+        if (path.startsWith('&')) {
+            // in case request url is something like `/genossenschaften/&cost=…`
+            path = path.slice(1);
+        }
+
+        const link = `${BASE_URL}/?${path}`;
+        const response = await ofetch(link);
+        const $ = load(response);
+
+        const items = $('[itemtype="https://schema.org/Apartment"]')
+            .toArray()
+            .map((el) => {
+                const $el = $(el);
+                const name = $el.find('[itemprop=name]').text();
+                const body = $el.find('.card-body').text().trim();
+                // UTC timestamp: <time datetime="2025-01-07T15:48:07.089153">
+                const dateTime = $el.find('time').attr('datetime');
+                const itemPubDate = dateTime ? new Date(dateTime + 'Z') : undefined;
+                const itemLink = BASE_URL + $el.find('[itemprop=url]').attr('href');
+                const itemImage = $el.find('[itemprop=image]').attr('href');
+
+                // e.g. ['2', '60,00 m²', '500,00 €', '10.000,00 €']
+                const numbers = $el
+                    .find('.card-body .fs-5')
+                    .toArray()
+                    .map((el) => $(el).text().trim());
+
+                // e.g. ['Verfügbar', 'OEVW', 'Miete', 'Wohneinheit']
+                const itemCategories = $el
+                    .find('.badge')
+                    .toArray()
+                    .map((el) => $(el).text().trim());
+
+                const titleAppendix = numbers.length ? ` | ${numbers.join(' · ')}` : '';
+                const itemTitle = name + titleAppendix;
+                const itemDescription = itemCategories.join(' · ') + (body.length ? ` / ${body}` : '');
+
+                return {
+                    title: itemTitle,
+                    link: itemLink,
+                    pubDate: itemPubDate,
+                    description: itemDescription,
+                    category: itemCategories,
+                    image: itemImage,
+                } satisfies DataItem;
+            });
+
+        return {
+            title: FEED_TITLE,
+            language: FEED_LANGUAGE,
+            logo: FEED_LOGO,
+            allowEmpty: true,
+            item: items,
+            link,
+        } satisfies Data;
+    },
+};

package/lib/routes/genossenschaften/namespace.ts

@@ -0,0 +1,8 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'Genossenschaften.immo',
+    url: 'genossenschaften.immo',
+    description: 'Search engine for Genossenschaft housing in Austria',
+    lang: 'de',
+};