fix(route): 国家药品监督管理局医疗器械标准管理中心 (#13919)

* fix(route): 国家药品监督管理局医疗器械标准管理中心 * fix: radar path matching ---------
DIYgod · Nov 29, 2023 · e6770d3 · e6770d3
1 parent a322dae
commit e6770d3
Show file tree

Hide file tree

Showing 5 changed files with 45 additions and 38 deletions.
diff --git a/lib/v2/gov/maintainer.js b/lib/v2/gov/maintainer.js
@@ -37,7 +37,7 @@ module.exports = {
     '/moj/aac/news/:type?': ['TonyRL'],
     '/mot/:category?': ['nczitzk'],
     '/news/:uid': ['EsuRt'],
-    '/nifdc/:path+': ['nczitzk'],
+    '/nifdc/:path?': ['nczitzk'],
     '/nmpa/:path+': ['TonyRL'],
     '/nopss/:path+': ['nczitzk'],
     '/npc/:caty': ['233yeee'],

diff --git a/lib/v2/gov/nifdc/index.js b/lib/v2/gov/nifdc/index.js
@@ -4,68 +4,75 @@ const timezone = require('@/utils/timezone');
 const { parseDate } = require('@/utils/parse-date');
 
 module.exports = async (ctx) => {
-    const params = ctx.path === '/nifdc' ? '/nifdc/bshff/ylqxbzhgl/qxggtzh' : ctx.path;
+    const { path = 'bshff/ylqxbzhgl/qxggtzh' } = ctx.params;
+    const limit = ctx.query.limit ? parseInt(ctx.query.limit, 10) : 30;
 
     const rootUrl = 'https://www.nifdc.org.cn';
-    const currentUrl = `${rootUrl}${params}/index.html`;
+    const currentUrl = new URL(`nifdc/${path}/`, rootUrl).href;
 
-    const response = await got({
-        method: 'get',
-        url: currentUrl,
-    });
+    const { data: response } = await got(currentUrl);
 
-    const $ = cheerio.load(response.data);
+    const $ = cheerio.load(response);
 
-    let items = $('.list ul li a')
-        .slice(0, ctx.query.limit ? parseInt(ctx.query.limit) : 20)
+    let items = $('div.list ul li')
+        .slice(0, limit)
         .toArray()
         .map((item) => {
             item = $(item);
 
-            const link = item.attr('href');
+            const a = item.find('a');
+            const link = a.prop('href');
 
             return {
-                title: item.text(),
-                link: /^http/.test(link) ? link : new URL(link, currentUrl).href,
-                pubDate: parseDate(
-                    item
-                        .next()
-                        .text()
-                        .match(/\((.*)\)/)
-                ),
+                title: a.prop('title') || a.text(),
+                link: link.startsWith('http') ? link : new URL(link, currentUrl).href,
+                pubDate: parseDate(item.find('span').text().replace(/\(|\)/g, '')),
             };
         });
 
     items = await Promise.all(
         items.map((item) =>
             ctx.cache.tryGet(item.link, async () => {
-                if (/^https:\/\/www\.nmpa\.gov\.cn\//.test(item.link)) {
-                    const { data: html } = await got(item.link);
+                try {
+                    const { data: detailResponse } = await got(item.link);
 
-                    const content = cheerio.load(html);
+                    const content = cheerio.load(detailResponse);
 
-                    item.description = content('.text').html();
-                    item.pubDate = timezone(parseDate($('meta[name="PubDate"]').attr('content')), +8);
-                } else {
-                    const detailResponse = await got({
-                        method: 'get',
-                        url: item.link,
-                    });
+                    item.title = content('.title').text();
+                    item.description = content('div.text').append(content('div.fujian')).html();
+                    item.author = content('meta[name="ContentSource"]').prop('content');
+                    item.category = [
+                        ...new Set([content('meta[name="ColumnName"]').prop('content'), content('meta[name="ColumnType"]').prop('content'), ...(content('meta[name="ColumnKeywords"]').prop('content').split(/,|;/) ?? [])]),
+                    ].filter((c) => c);
+                    item.pubDate = timezone(parseDate(content('meta[name="PubDate"]').prop('content')), +8);
+                    item.enclosure_url = content('a.fujianClass').first().prop('href');
 
-                    const content = cheerio.load(detailResponse.data);
-
-                    item.description = content('.text').append(content('.fujian')).html();
-                    item.pubDate = timezone(parseDate(content('meta[name="PubDate"]').attr('content')), +8);
+                    if (item.enclosure_url) {
+                        item.enclosure_url = new URL(item.enclosure_url, rootUrl).href;
+                        item.enclosure_type = `application/${item.enclosure_url.split(/\./).pop()}`;
+                    }
+                } catch (e) {
+                    // no-empty
                 }
 
                 return item;
             })
         )
     );
 
+    const image = new URL($('div.logo img').prop('src'), currentUrl).href;
+    const icon = new URL($('link[rel="shortcut icon"]').prop('href'), currentUrl).href;
+
     ctx.state.data = {
+        item: items,
         title: $('title').text().replace(/----/, ' - '),
         link: currentUrl,
-        item: items,
+        description: $('meta[name="ColumnDescription"]').prop('content'),
+        language: 'zh',
+        image,
+        icon,
+        logo: icon,
+        subtitle: $('meta[ name="ColumnName"]').prop('content'),
+        author: $('meta[name="SiteName"]').prop('content'),
     };
 };
diff --git a/lib/v2/gov/radar.js b/lib/v2/gov/radar.js
@@ -1054,8 +1054,8 @@ module.exports = {
             {
                 title: '通用',
                 docs: 'https://docs.rsshub.app/routes/government#guo-jia-yao-pin-jian-du-guan-li-ju-yi-liao-qi-xie-biao-zhun-guan-li-zhong-xin',
-                source: ['/*path'],
-                target: (params) => `/gov/nifdc/${params.path.replace('/index.html', '')}`,
+                source: ['/*'],
+                target: (params) => `/gov/nifdc/${params.path.replace(/\/index\.html$/, '')}`,
             },
         ],
     },

diff --git a/lib/v2/gov/router.js b/lib/v2/gov/router.js
@@ -30,7 +30,7 @@ module.exports = function (router) {
     router.get('/mofcom/article/:suffix+', require('./mofcom/article'));
     router.get('/moj/aac/news/:type?', require('./moj/aac/news'));
     router.get('/news/:uid', require('./news'));
-    router.get(/nifdc\/([\w/-]+)?/, require('./nifdc'));
+    router.get('/nifdc/:path*', require('./nifdc'));
     router.get(/\/nmpa\/([\w][\w/]+)?/, require('./nmpa/generic'));
     router.get(/nopss(\/[\w/-]+)?/, require('./nopss'));
     router.get('/npc/:caty', require('./npc/index'));

diff --git a/website/docs/routes/government.mdx b/website/docs/routes/government.mdx
@@ -669,7 +669,7 @@ Language
 
 ### 通用 {#guo-jia-yao-pin-jian-du-guan-li-ju-yi-liao-qi-xie-biao-zhun-guan-li-zhong-xin-tong-yong}
 
-<Route author="nczitzk" example="/gov/nifdc/bshff/ylqxbzhgl/qxggtzh" path="/gov/nifdc/:path+" paramsDesc={['路径，默认为公告通告']} radar="1" rssbud="1">
+<Route author="nczitzk" example="/gov/nifdc/bshff/ylqxbzhgl/qxggtzh" path="/gov/nifdc/:path?" paramsDesc={['路径，默认为公告通告']} radar="1" rssbud="1">
 
 :::tip
-Original file line number
+Diff line change
@@ Expand Up / @@ -669,7 +669,7 @@ Language @@
     ### 通用 {#guo-jia-yao-pin-jian-du-guan-li-ju-yi-liao-qi-xie-biao-zhun-guan-li-zhong-xin-tong-yong}
-    <Route author="nczitzk" example="/gov/nifdc/bshff/ylqxbzhgl/qxggtzh" path="/gov/nifdc/:path+" paramsDesc={['路径，默认为公告通告']} radar="1" rssbud="1">
+    <Route author="nczitzk" example="/gov/nifdc/bshff/ylqxbzhgl/qxggtzh" path="/gov/nifdc/:path?" paramsDesc={['路径，默认为公告通告']} radar="1" rssbud="1">
     :::tip
@@ Expand Down @@