feat(route): add Meritalk latest articles (#21282)

* feat: add route and namespace for MeriTalk articles

* feat: update articles route to support pagination and add description rendering

* feat: enhance articles route with improved description and error handling

* feat(meritalk): add articles route with pagination limit

- Add latest articles route for Meritalk
- Update route example and parameter description
- Implement pagination limit to avoid Cloudflare anti-bot

* fix(meritalk): remove nums param and fetch only first page

* fix(meritalk): update route category to new-media

Co-authored-by: Tony <TonyRL@users.noreply.github.com>

* fix(meritalk): remove the post-processing of items and modify some of the logic in the handler

- Remove unnecessary sorting.
- Remove custom limit logic.

---------

lib/routes/meritalk/articles.ts

@@ -0,0 +1,80 @@
+import { load } from 'cheerio';
+
+import type { Route } from '@/types';
+import cache from '@/utils/cache';
+import got from '@/utils/got';
+import { parseDate } from '@/utils/parse-date';
+
+import { renderDescription } from './templates/description';
+
+export const route: Route = {
+    path: '/articles',
+    categories: ['new-media'],
+    example: '/meritalk/articles',
+    features: {
+        requireConfig: false,
+        requirePuppeteer: false,
+        antiCrawler: false,
+        supportBT: false,
+        supportPodcast: false,
+        supportScihub: false,
+    },
+    radar: [
+        {
+            source: ['meritalk.com/articles/'],
+            target: '/articles',
+        },
+    ],
+    name: 'Latest Articles',
+    maintainers: ['superguyDiluc'],
+    handler,
+};
+
+async function handler() {
+    const baseUrl = 'https://www.meritalk.com/articles';
+
+    const { data: response } = await got(baseUrl);
+    const $ = load(response);
+
+    const list = $('div.news-block-sm')
+        .toArray()
+        .map((item) => {
+            const $item = $(item);
+            const a = $item.find('.news-block-title a');
+            const link = a.attr('href');
+            return {
+                title: a.text().trim(),
+                link: link as string,
+                pubDate: parseDate($item.find('time[datetime]').attr('datetime') as string),
+                category: $item
+                    .find('.category-header-name a')
+                    .toArray()
+                    .map((elem) => $(elem).text()),
+                description: '',
+            };
+        });
+
+    const items = await Promise.all(
+        list.map((item) =>
+            cache.tryGet(item.link, async () => {
+                const { data: response } = await got(item.link);
+                const $ = load(response);
+
+                const featuredImage = $('.single-featured-image').first().html() || '';
+                const fullContent = $('.single-body').first().html() || '';
+                item!.description = renderDescription({
+                    featuredImage,
+                    fullContent,
+                });
+
+                return item;
+            })
+        )
+    );
+
+    return {
+        title: 'News – MeriTalk',
+        link: 'https://www.meritalk.com/articles/',
+        item: items,
+    };
+}

lib/routes/meritalk/namespace.ts

@@ -0,0 +1,6 @@
+import type { Namespace } from '@/types';
+
+export const namespace: Namespace = {
+    name: 'MeriTalk',
+    url: 'meritalk.com',
+};

lib/routes/meritalk/templates/description.tsx

@@ -0,0 +1,21 @@
+import { raw } from 'hono/html';
+import { renderToString } from 'hono/jsx/dom/server';
+
+type DescriptionParams = {
+    featuredImage?: string;
+    fullContent?: string;
+};
+
+export const renderDescription = ({ featuredImage, fullContent }: DescriptionParams) =>
+    renderToString(
+        <>
+            {featuredImage ? (
+                <>
+                    {raw(featuredImage)}
+                    <br />
+                </>
+            ) : null}
+
+            {fullContent ? raw(fullContent) : null}
+        </>
+    );