feat(route): nmpa (#10108)

* feat(route): nmpa

* docs: add puppeteer attr

* fix: close puppeteer page

docs/government.md

@@ -215,6 +215,22 @@ pageClass: routes
 
 <Route author="y2361547758" example="/gov/nppa/318/45948" path="/gov/nppa/:channel/:content" :paramsDesc="['栏目名 id', '文章 id']" radar="1" rssbud="1"/>
 
+## 国家药品监督管理局
+
+### 通用
+
+<Route author="TonyRL" example="/gov/nmpa/xxgk/ggtg" path="/gov/nmpa/:path+" :paramsDesc="['路径，默认为公告通告']" radar="1" rssbud="1" puppeteer="1">
+
+::: tip 提示
+
+路径处填写对应页面 URL 中 `https://www.nmpa.gov.cn/` 与 `/index.html` 之间的字段，下面是一个例子。
+
+若订阅 [公告通告](https://www.nmpa.gov.cn/xxgk/ggtg/index.html) 则将对应页面 URL <https://www.nmpa.gov.cn/xxgk/ggtg/index.html> 中 `https://www.nmpa.gov.cn/` 和 `/index.html` 之间的字段 `xxgk/ggtg` 作为路径填入。此时路由为 [`/gov/nmpa/xxgk/ggtg`](https://rsshub.app/gov/nmpa/xxgk/ggtg)
+
+:::
+
+</Route>
+
 ## 国家药品审评网站
 
 ### 首页

lib/v2/gov/maintainer.js

@@ -11,6 +11,7 @@ module.exports = {
     '/miit/wjgs': ['Yoge-Code'],
     '/miit/zcjd': ['Yoge-Code'],
     '/moe/:type': ['Crawler995'],
+    '/nmpa/:path+': ['TonyRL'],
     '/nrta/news/:category?': ['yuxinliu-alex'],
     '/pbc/goutongjiaoliu': ['nczitzk'],
     '/pbc/gzlw': ['Fatpandac'],

lib/v2/gov/nmpa/generic.js

@@ -0,0 +1,76 @@
+const cheerio = require('cheerio');
+const { parseDate } = require('@/utils/parse-date');
+const config = require('@/config').value;
+const baseUrl = 'https://www.nmpa.gov.cn';
+
+module.exports = async (ctx) => {
+    const path = ctx.params[0];
+    const url = `${baseUrl}/${path.endsWith('/') ? path.slice(0, -1) : path}/index.html`;
+    const browser = await require('@/utils/puppeteer')();
+    const data = await ctx.cache.tryGet(
+        url,
+        async () => {
+            const page = await browser.newPage();
+            await page.setRequestInterception(true);
+            page.on('request', (request) => {
+                request.resourceType() === 'document' || request.resourceType() === 'script' ? request.continue() : request.abort();
+            });
+            await page.goto(url, {
+                waitUntil: 'domcontentloaded',
+            });
+            await page.waitForSelector('.list');
+
+            const html = await page.evaluate(() => document.documentElement.innerHTML);
+            await page.close();
+            const $ = cheerio.load(html);
+
+            return {
+                title: $('head title').text(),
+                description: $('meta[name=ColumnDescription]').attr('content'),
+                items: $('.list ul li')
+                    .toArray()
+                    .map((item) => {
+                        item = $(item);
+                        return {
+                            title: item.find('a').text().trim(),
+                            link: new URL(item.find('a').attr('href'), baseUrl).href,
+                            pubDate: parseDate(item.find('span').text(), 'YYYY-MM-DD'),
+                        };
+                    }),
+            };
+        },
+        config.cache.routeExpire,
+        false
+    );
+
+    const items = await Promise.all(
+        data.items.map((item) =>
+            ctx.cache.tryGet(item.link, async () => {
+                const page = await browser.newPage();
+                await page.setRequestInterception(true);
+                page.on('request', (request) => {
+                    request.resourceType() === 'document' || request.resourceType() === 'script' ? request.continue() : request.abort();
+                });
+                await page.goto(item.link, {
+                    waitUntil: 'domcontentloaded',
+                });
+                await page.waitForSelector('.text');
+
+                const html = await page.evaluate(() => document.documentElement.innerHTML);
+                await page.close();
+                const $ = cheerio.load(html);
+                item.description = $('.text').html();
+                return item;
+            })
+        )
+    );
+
+    await browser.close();
+
+    ctx.state.data = {
+        title: data.title,
+        description: data.description,
+        link: url,
+        item: items,
+    };
+};

lib/v2/gov/radar.js

@@ -455,12 +455,23 @@ module.exports = {
         '.': [
             {
                 title: '分类',
-                docs: 'https://docs.rsshub.app/government.html#nrta-gov',
+                docs: 'https://docs.rsshub.app/government.html#guo-jia-guang-bo-dian-shi-zong-ju',
                 source: ['/col/*category'],
                 target: (params) => `/gov/nrta/news/${params.category.replace('col', '').replace('/index.html', '')}`,
             },
         ],
     },
+    'nmpa.gov.cn': {
+        _name: '国家药品监督管理局',
+        '.': [
+            {
+                title: '通用',
+                docs: 'https://docs.rsshub.app/government.html#guo-jia-yao-pin-jian-du-guan-li-ju',
+                source: ['/*path'],
+                target: (params) => `/gov/nmpa/${params.path.replace('/index.html', '')}`,
+            },
+        ],
+    },
     'pbc.gov.cn': {
         _name: '中国人民银行',
         '.': [

lib/v2/gov/router.js

@@ -11,6 +11,7 @@ module.exports = function (router) {
     router.get('/miit/wjgs', require('./miit/wjgs'));
     router.get('/miit/zcjd', require('./miit/zcjd'));
     router.get('/moe/:type', require('./moe/moe'));
+    router.get(/\/nmpa\/([\w][\w/]+)?/, require('./nmpa/generic'));
     router.get('/nrta/news/:category?', require('./nrta/news'));
     router.get('/pbc/goutongjiaoliu', require('./pbc/goutongjiaoliu'));
     router.get('/pbc/gzlw', require('./pbc/gzlw'));