rsshub 1.0.0-master.f9ec483 → 1.0.0-master.fa04a11

package/lib/routes/visionias/templates/description-sub.art

@@ -0,0 +1,6 @@
+{{ if heading }}
+  <h2>{{ heading }}</h2>
+{{ /if }}
+{{ if articleContent }}
+  {{@ articleContent }}
+{{ /if }}

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

@@ -0,0 +1,12 @@
+{{ if heading }}
+  <h1>{{ heading }}</h1>
+{{ /if }}
+{{ if subItems }}
+  {{ each subItems item }}
+    {{ if item?.description }}
+       {{@ item.description }}
+    {{ /if }}
+  {{ /each }}
+{{else}}
+   {{@ articleContent }}
+{{ /if }}

package/lib/routes/visionias/utils.ts

@@ -0,0 +1,109 @@
+import { getCurrentPath } from '@/utils/helpers';
+const __dirname = getCurrentPath(import.meta.url);
+
+import { DataItem } from '@/types';
+import { parseDate } from '@/utils/parse-date';
+import { art } from '@/utils/render';
+import path from 'node:path';
+import ofetch from '@/utils/ofetch';
+import { load } from 'cheerio';
+import cache from '@/utils/cache';
+
+export const baseUrl = 'https://visionias.in';
+
+export async function extractNews(item, selector) {
+    if (item.link === '') {
+        return item;
+    }
+    return await cache.tryGet(item.link, async () => {
+        const response = await ofetch(item.link || '');
+        const $$ = load(response);
+        const postedDate = String($$('meta[property="article:published_time"]').attr('content'));
+        const updatedDate = String($$('meta[property="article:modified_time"]').attr('content'));
+        const tags = $$('meta[property="article:tag"]')
+            .toArray()
+            .map((tag) => $$(tag).attr('content'));
+        const content = $$(selector);
+        const heading = content.find('div.space-y-4 > h1').text();
+        const mainGroup = content.find('div.flex > div.w-full');
+
+        const shortArticles = mainGroup.find('[x-data^="{isShortArticleOpen"]');
+        const sections = mainGroup.find('[x-data^="{isSectionOpen"]');
+        if (shortArticles.length !== 0) {
+            const items = shortArticles.toArray().map((element) => {
+                const mainDiv = $$(element);
+                const title = mainDiv.find('a > div > h1').text().trim();
+                const id = mainDiv.find('a').attr('href');
+                const htmlContent = extractArticle(mainDiv.html());
+                const innerTags = mainDiv
+                    .find('ul > li:contains("Tags :")')
+                    ?.nextAll('li')
+                    .toArray()
+                    .map((tag) => $$(tag).text());
+                const description = art(path.join(__dirname, `templates/description.art`), {
+                    heading: title,
+                    articleContent: htmlContent,
+                });
+                return {
+                    title: `${title} | ${heading}`,
+                    pubDate: parseDate(postedDate),
+                    category: innerTags,
+                    description,
+                    link: `${item.link}${id}`,
+                    author: 'Vision IAS',
+                } as DataItem;
+            });
+            return items;
+        } else if (sections.length === 0) {
+            const htmlContent = extractArticle(mainGroup.html());
+            const description = art(path.join(__dirname, 'templates/description.art'), {
+                heading,
+                articleContent: htmlContent,
+            });
+            return {
+                title: item.title,
+                pubDate: parseDate(postedDate),
+                category: tags,
+                description,
+                link: item.link,
+                updated: updatedDate ? parseDate(updatedDate) : null,
+                author: 'Vision IAS',
+            } as DataItem;
+        } else {
+            const items = sections.toArray().map((element) => {
+                const mainDiv = $$(element);
+                const title = mainDiv.find('a > div > h2').text().trim();
+                const htmlContent = extractArticle(mainDiv.html(), 'div.ck-content');
+                const description = art(path.join(__dirname, `templates/description-sub.art`), {
+                    heading: title,
+                    articleContent: htmlContent,
+                });
+                return { description };
+            });
+            const description = art(path.join(__dirname, `templates/description.art`), {
+                heading,
+                subItems: items,
+            });
+            return {
+                title: heading,
+                pubDate: parseDate(postedDate),
+                category: tags,
+                description,
+                link: item.link,
+                updated: updatedDate ? parseDate(updatedDate) : null,
+                author: 'Vision IAS',
+            } as DataItem;
+        }
+    });
+}
+
+function extractArticle(articleDiv, selectorString: string = '#article-content') {
+    const $ = load(articleDiv, null, false);
+    const articleDiv$ = $(articleDiv);
+    const articleContent = articleDiv$.find(String(selectorString));
+    articleContent.find('figure').each((_, element) => {
+        $(element).css('width', '');
+    });
+    const htmlContent = articleContent.html();
+    return htmlContent;
+}

package/lib/routes/visionias/weekly-focus.ts

@@ -0,0 +1,56 @@
+import { Data, Route } from '@/types';
+import { baseUrl, extractNews } from './utils';
+import ofetch from '@/utils/ofetch';
+import { load } from 'cheerio';
+
+export const route: Route = {
+    path: '/weeklyFocus',
+    example: '/visionias/weeklyFocus',
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['visionias.in/current-affairs/weekly-focus'],
+            target: '/weeklyFocus',
+        },
+    ],
+    name: 'Weekly Focus',
+    maintainers: ['Rjnishant530'],
+    handler,
+};
+
+async function handler(ctx): Promise<Data> {
+    const limit = ctx.req.query('limit') ? Number.parseInt(ctx.req.query('limit'), 10) : 1;
+    const response = await ofetch(`${baseUrl}/current-affairs/weekly-focus/archive`);
+    const $ = load(response);
+    const cards = $('div.weekly-focus-single-card').slice(0, limit).toArray();
+    const individualLinks = cards.flatMap((card) =>
+        $(card)
+            .find('a:has(p)')
+            .toArray()
+            .map((item) => {
+                const link = $(item).attr('href');
+                return { link: link?.startsWith('http') ? link : `${baseUrl}${link}` };
+            })
+    );
+
+    const itemsPromise = await Promise.allSettled(individualLinks.map(({ link }) => extractNews({ link }, 'main > div > div.flex > div.flex.w-full > div.w-full.mt-6')));
+
+    return {
+        title: 'Weekly Focus | Current Affairs | Vision IAS',
+        link: `${baseUrl}/current-affairs/weekly-focus/archive`,
+        description: 'Weekly Focus provides weekly comprehensive analysis of current themes with multidimensional and consolidated content.',
+        language: 'en',
+        item: itemsPromise.map((item) => (item.status === 'fulfilled' ? item.value : { title: 'Error Parse News' })),
+        image: `${baseUrl}/current-affairs/images/weekly-focus-logo.svg`,
+        icon: `${baseUrl}/current-affairs/favicon.ico`,
+        logo: `${baseUrl}/current-affairs/favicon.ico`,
+        allowEmpty: true,
+    };
+}

package/lib/routes/vocus/publication.ts

@@ -5,7 +5,7 @@ import { processList, ProcessFeed, baseUrl, apiUrl } from './utils';
 
 export const route: Route = {
     path: '/publication/:id',
-    categories: ['social-media'],
+    categories: ['social-media', 'popular'],
     example: '/vocus/publication/bass',
     parameters: { id: '出版專題 id，可在出版專題主页的 URL 找到' },
     features: {

package/lib/routes/vocus/user.ts

@@ -5,7 +5,7 @@ import { processList, ProcessFeed, baseUrl, apiUrl } from './utils';
 
 export const route: Route = {
     path: '/user/:id',
-    categories: ['social-media'],
+    categories: ['social-media', 'popular'],
     example: '/vocus/user/tsetyan',
     parameters: { id: '用户 id，可在用户主页的 URL 找到' },
     features: {

package/lib/routes/wabei/index.ts

@@ -0,0 +1,75 @@
+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: '/hot-recommend',
+    categories: ['finance'],
+    example: '/wabei/hot-recommend',
+    url: 'www.wabei.cn',
+    name: '热门推荐',
+    maintainers: ['p3psi-boo'],
+    handler,
+};
+
+async function handler() {
+    const baseUrl = 'https://www.wabei.cn';
+
+    const response = await got({
+        method: 'get',
+        url: baseUrl,
+    });
+
+    const $ = load(response.data);
+
+    const list = $('.hot-news.visible-lg')
+        .toArray()
+        .map((item) => {
+            const elem = $(item);
+            const title = elem.find('h4 a').text().trim();
+            const link = elem.find('h4 a').attr('href');
+            const author = elem.find('span.author').text().trim();
+            const description = elem.find('p.visible-lg a').text().trim();
+
+            const label = elem.find('span.lable').text().trim();
+            const tags = elem
+                .find('span.blue-btn')
+                .toArray()
+                .map((tag) => $(tag).text().trim());
+            const category = [label, ...tags];
+
+            return {
+                title,
+                link: `${baseUrl}${link}`,
+                category,
+                author,
+                description,
+            };
+        });
+
+    const items = await Promise.all(
+        list.map((item) =>
+            cache.tryGet(item.link, async () => {
+                const detailResponse = await got({
+                    method: 'get',
+                    url: item.link,
+                });
+
+                const content = load(detailResponse.data);
+
+                item.description = content('.subject-content').html() || item.description;
+                item.pubDate = parseDate(content('.attr .time').text().trim(), 'YYYY/MM/DD HH:mm:ss');
+
+                return item;
+            })
+        )
+    );
+
+    return {
+        title: '挖贝网 - 热门推荐',
+        link: baseUrl,
+        item: items,
+    };
+}

package/lib/routes/wabei/namespace.ts

@@ -0,0 +1,8 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: '挖贝网',
+    url: 'www.wabei.cn',
+    description: '挖贝网专注于新三板、A股和港股报道',
+    lang: 'zh-CN',
+};

package/lib/routes/wallhaven/index.ts

@@ -28,11 +28,11 @@ export const route: Route = {
     maintainers: ['nczitzk', 'Fatpandac'],
     handler,
     url: 'wallhaven.cc/',
-    description: `:::tip
+    description: `::: tip
   Subscribe pages starting with \`https://wallhaven.cc/search\`, fill the text after \`?\` as \`filter\` in the route. The following is an example:
 
   The text after \`?\` is \`q=id%3A711&sorting=random&ref=fp&seed=8g0dgd\` for [Wallpaper Search: #landscape - wallhaven.cc](https://wallhaven.cc/search?q=id%3A711\&sorting=random\&ref=fp\&seed=8g0dgd), so the route is [/wallhaven/q=id%3A711\&sorting=random\&ref=fp\&seed=8g0dgd](https://rsshub.app/wallhaven/q=id%3A711\&sorting=random\&ref=fp\&seed=8g0dgd)
-  :::`,
+:::`,
 };
 
 async function handler(ctx) {

package/lib/routes/wallhaven/namespace.ts

@@ -3,7 +3,7 @@ import type { Namespace } from '@/types';
 export const namespace: Namespace = {
     name: 'wallhaven',
     url: 'wallhaven.cc',
-    description: `:::tip
+    description: `::: tip
 When parameter **Need Details** is set to \`true\` \`yes\` \`t\` \`y\`, RSS will add the title, uploader, upload time, and category information of each image, which can support the filtering function of RSS reader.
 
 However, the number of requests to the site increases a lot when it is turned on, which causes the site to return \`Response code 429 (Too Many Requests)\`. So you need to specify a smaller \`limit\` parameter, i.e. add \`?limit=<the number of posts for a request>\` after the route, here is an example.

package/lib/routes/wallstreetcn/calendar.ts

@@ -0,0 +1,90 @@
+import { Route } from '@/types';
+import ofetch from '@/utils/ofetch';
+import { parseDate } from '@/utils/parse-date';
+
+export const route: Route = {
+    path: '/calendar/:section?',
+    categories: ['finance'],
+    example: '/wallstreetcn/calendar',
+    parameters: { section: '`macrodatas` 或 `report`，默认为 `macrodatas`' },
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['wallstreetcn.com/calendar'],
+        },
+    ],
+    name: '财经日历',
+    maintainers: ['TonyRL'],
+    handler,
+    url: 'wallstreetcn.com/calendar',
+};
+
+const rootUrl = 'https://wallstreetcn.com';
+
+const MacrodataSuffix = {
+    CA: 'CA10YR.OTC',
+    CN: 'USDCNH.OTC',
+    DE: 'DE30.OTC',
+    FR: 'FR40.OTC',
+    // HK: '',
+    IT: 'EURUSD.OTC',
+    JP: 'USDJPY.OTC',
+    UK: 'UK100.OTC',
+    US: 'DXY.OTC',
+};
+
+const getMacrodataUrl = (countryId, wscnTicker) => `${rootUrl}/data-analyse/${wscnTicker}/${MacrodataSuffix[countryId]}`;
+
+async function handler(ctx) {
+    const { section = 'macrodatas' } = ctx.req.param();
+
+    const link = `${rootUrl}/calendar`;
+    const apiRootUrl = section === 'macrodatas' ? 'https://api-one-wscn.awtmt.com' : 'https://api-ddc-wscn.awtmt.com';
+    const apiUrl = section === 'macrodatas' ? `${apiRootUrl}/apiv1/finance/macrodatas` : `${apiRootUrl}/finance/report/list`;
+
+    const response = await ofetch(apiUrl, {
+        query:
+            section === 'macrodatas'
+                ? {
+                      start: new Date().setHours(0, 0, 0, 0) / 1000,
+                      end: Math.trunc(new Date().setHours(23, 59, 59, 999) / 1000),
+                  }
+                : undefined,
+    });
+
+    const items =
+        section === 'macrodatas'
+            ? response.data.items.map((item) => ({
+                  title: `${item.country}${item.title}`,
+                  description: `${item.country}${item.title} 重要性: ${'★'.repeat(item.importance)} 今值: ${item.actual || '-'}${item.actual && item.unit} 预期: ${item.forecast || '-'}${item.forecast && item.unit} 前值: ${item.revised || item.previous || '-'}${(item.revised || item.previous) && item.unit}`,
+                  link: item.uri && MacrodataSuffix[item.country_id] && getMacrodataUrl(item.country_id, item.wscn_ticker),
+                  guid: item.id,
+                  pubDate: parseDate(item.public_date, 'X'),
+                  category: item.country,
+              }))
+            : // report
+              response.data.items
+                  .map((item) => Object.fromEntries(response.data.fields.map((field, index) => [field, item[index]])))
+                  .map((item) => ({
+                      title: `${item.company_name} ${item.observation_date}`,
+                      description: `${item.code} ${item.company_name} ${item.observation_date} 预期EPS: ${item.eps_estimate === 0 ? '-' : item.eps_estimate} 实际EPS: ${item.reported_eps === 0 ? '-' : item.reported_eps} 差异度: ${item.surprise === 0 || item.surprise === -1 ? '-' : (item.surprise * 100).toFixed(2) + '%'}`,
+                      link,
+                      guid: item.id,
+                      pubDate: parseDate(item.public_date, 'X'),
+                  }));
+
+    return {
+        title: '财经日历 - 华尔街见闻',
+        link,
+        item: items,
+        itunes_author: '华尔街见闻',
+        image: 'https://static.wscn.net/wscn/_static/favicon.png',
+    };
+}

package/lib/routes/wallstreetcn/hot.ts

@@ -5,7 +5,7 @@ import { parseDate } from '@/utils/parse-date';
 
 export const route: Route = {
     path: '/hot/:period?',
-    categories: ['traditional-media'],
+    categories: ['finance'],
     example: '/wallstreetcn/hot',
     parameters: { period: '时期，可选 `day` 即 当日 或 `week` 即 当周，默认为当日' },
     features: {
@@ -77,6 +77,6 @@ async function handler(ctx) {
         link: rootUrl,
         item: items,
         itunes_author: '华尔街见闻',
-        image: 'https://static-alpha-wscn.awtmt.com/wscn-static/qrcode.jpg',
+        image: 'https://static.wscn.net/wscn/_static/favicon.png',
     };
 }

package/lib/routes/wallstreetcn/live.ts

@@ -19,7 +19,7 @@ const titles = {
 
 export const route: Route = {
     path: '/live/:category?/:score?',
-    categories: ['traditional-media'],
+    categories: ['finance'],
     example: '/wallstreetcn/live',
     parameters: { category: '快讯分类，默认`global`，见下表', score: '快讯重要度，默认`1`全部快讯，可设置为`2`只看重要的' },
     features: {

package/lib/routes/wallstreetcn/news.ts

@@ -18,13 +18,15 @@ const titles = {
 };
 
 export const route: Route = {
-    path: ['/news/:category?', '/:category?'],
+    path: '/news/:category?',
+    categories: ['finance'],
+    example: '/wallstreetcn/news',
     radar: [
         {
             source: ['wallstreetcn.com/news/:category', 'wallstreetcn.com/'],
         },
     ],
-    name: 'Unknown',
+    name: '资讯',
     maintainers: ['nczitzk'],
     handler,
     description: `| id           | 分类 |
@@ -72,7 +74,14 @@ async function handler(ctx) {
                     url: `${apiRootUrl}/apiv1/content/${item.type === 'live' ? `lives/${item.guid}` : `articles/${item.guid}?extract=0`}`,
                 });
 
-                const data = detailResponse.data.data;
+                const responseData = detailResponse.data;
+
+                // 处理 { code: 60301, message: '内容不存在或已被删除', data: {} }
+                if (responseData.code !== 20000) {
+                    return null;
+                }
+
+                const data = responseData.data;
 
                 item.title = data.title || data.content_text;
                 item.author = data.source_name ?? data.author.display_name;
@@ -93,11 +102,13 @@ async function handler(ctx) {
         )
     );
 
+    items = items.filter((item) => item !== null);
+
     return {
         title: `华尔街见闻 - 资讯 - ${titles[category]}`,
         link: currentUrl,
         item: items,
         itunes_author: '华尔街见闻',
-        image: 'https://static-alpha-wscn.awtmt.com/wscn-static/qrcode.jpg',
+        image: 'https://static.wscn.net/wscn/_static/favicon.png',
     };
 }

package/lib/routes/washingtonpost/app.ts

@@ -33,7 +33,7 @@ export const route: Route = {
         },
     ],
     handler,
-    description: `:::tip
+    description: `::: tip
 For example, the category for https://www.washingtonpost.com/national/investigations would be /national/investigations.
 :::`,
 };

package/lib/routes/web/series.ts

@@ -15,7 +15,7 @@ export const route: Route = {
     name: 'Series',
     maintainers: ['KarasuShin'],
     handler,
-    description: `:::tip
+    description: `::: tip
     The \`seriesName\` can be extracted from the Series page URL: \`https://web.dev/series/:seriesName\`
 :::`,
 };

package/lib/routes/webcatalog/changelog.ts

@@ -0,0 +1,59 @@
+import { Route } from '@/types';
+import { load } from 'cheerio';
+import { parseDate } from '@/utils/parse-date';
+import ofetch from '@/utils/ofetch';
+
+export const route: Route = {
+    path: '/changelog',
+    categories: ['program-update'],
+    example: '/webcatalog/changelog',
+    parameters: {},
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['desktop.webcatalog.io/:lang/changelog'],
+        },
+    ],
+    name: 'Changelog',
+    maintainers: ['Tsuyumi25'],
+    handler,
+    url: 'desktop.webcatalog.io/en/changelog',
+};
+
+async function handler() {
+    const url = 'https://desktop.webcatalog.io/en/changelog';
+    const response = await ofetch(url);
+    const $ = load(response);
+
+    // remove What's new
+    $('.container article div.mb-20').remove();
+    const items = $('.container article')
+        .html()
+        ?.split('<hr>')
+        ?.map((section) => {
+            const $section = load(section);
+            const month = $section('h1').remove().text();
+            const title = $section('h2').first().remove().text();
+            return {
+                title: `${month} - ${title}`,
+                description: $section.html(),
+                link: url,
+                pubDate: parseDate(month),
+                guid: `webcatalog-${month}-${title}`,
+            };
+        });
+
+    return {
+        title: 'WebCatalog Changelog',
+        link: url,
+        item: items,
+        language: 'en',
+    };
+}

package/lib/routes/webcatalog/namespace.ts

@@ -0,0 +1,7 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'WebCatalog',
+    url: 'desktop.webcatalog.io',
+    lang: 'en',
+};

package/lib/routes/wechat/namespace.ts

@@ -3,7 +3,7 @@ import type { Namespace } from '@/types';
 export const namespace: Namespace = {
     name: '微信小程序',
     url: 'posts.careerengine.us',
-    description: `:::tip
+    description: `::: tip
 公众号直接抓取困难，故目前提供几种间接抓取方案，请自行选择
 :::`,
     lang: 'zh-CN',

package/lib/routes/wechat/tgchannel.ts

@@ -25,13 +25,13 @@ export const route: Route = {
   |      \`1\`     |     公众号全名     | 未启用 efb-patch-middleware |
   |      \`2\`     |     #公众号全名    | 已启用 efb-patch-middleware |
 
-  :::tip
+::: tip
   启用搜索有助于在订阅了过多公众号的频道里有效筛选，不易因为大量公众号同时推送导致一些公众号消息被遗漏，但必须正确选择搜索查询类型，否则会搜索失败。
-  :::
+:::
 
-  :::warning
+::: warning
   该方法需要通过 efb 进行频道绑定，具体操作见 [https://github.com/DIYgod/RSSHub/issues/2172](https://github.com/DIYgod/RSSHub/issues/2172)
-  :::`,
+:::`,
 };
 
 async function handler(ctx) {

package/lib/routes/weibo/friends.ts

@@ -36,13 +36,13 @@ export const route: Route = {
     maintainers: ['CaoMeiYouRen'],
     handler,
     url: 'weibo.com/',
-    description: `:::warning
+    description: `::: warning
   此方案必须使用用户\`Cookie\`进行抓取
 
   因微博 cookies 的过期与更新方案未经验证，部署一次 Cookie 的有效时长未知
 
   微博用户 Cookie 的配置可参照部署文档
-  :::`,
+:::`,
 };
 
 async function handler(ctx) {

package/lib/routes/weibo/group.ts

@@ -29,13 +29,13 @@ export const route: Route = {
     name: '自定义分组',
     maintainers: ['monologconnor', 'Rongronggg9'],
     handler,
-    description: `:::warning
+    description: `::: warning
   由于微博官方未提供自定义分组相关 api, 此方案必须使用用户\`Cookie\`进行抓取
 
   因微博 cookies 的过期与更新方案未经验证，部署一次 Cookie 的有效时长未知
 
   微博用户 Cookie 的配置可参照部署文档
-  :::`,
+:::`,
 };
 
 async function handler(ctx) {

package/lib/routes/weibo/namespace.ts

@@ -3,7 +3,7 @@ import type { Namespace } from '@/types';
 export const namespace: Namespace = {
     name: '微博',
     url: 'weibo.com',
-    description: `:::warning
+    description: `::: warning
 微博会针对请求的来源地区返回不同的结果。\
 一个已知的例子为：部分视频因未知原因仅限中国大陆境内访问 (CDN 域名为 \`locallimit.us.sinaimg.cn\` 而非 \`f.video.weibocdn.com\`)。若一条微博含有这种视频且 RSSHub 实例部署在境外，抓取到的微博可能不含视频。将 RSSHub 部署在境内有助于抓取这种视频，但阅读器也必须处于境内网络环境以加载视频。
 :::