feat(route): Add stats.gov 国家统计局 (#10860)

* add new statsgov

* Fix radar.js

* 1. Fix the missing optional chaining operator in reg matching 2. add the missing timezone change

* remove the dup $ in item

* optimize url

* stats.gov.cn refactored

* Modify doc

* more flexible pathname parsing

* Fix radar data

docs/government.md

@@ -184,6 +184,22 @@ pageClass: routes
 
 <Route author="nczitzk" example="/gov/chinatax/latest" path="/gov/chinatax/latest"/>
 
+## 国家统计局
+
+### 统计数据 > 最新发布
+
+<Route author="bigfei" example="/gov/stats/tjsj/zxfb" path="/gov/stats/:path+" :paramsDesc="['路径，默认为 统计数据 > 最新发布']">
+
+::: tip 提示
+
+路径处填写对应页面 URL 中 `http://www.stats.gov.cn/` 后的字段。下面是一个例子。
+
+若订阅 [统计数据 > 统计标准](http://www.stats.gov.cn/tjsj/tjbz/) 则将对应页面 URL <http://www.stats.gov.cn/tjsj/tjbz/> 中 `http://www.stats.gov.cn/` 后的字段 `tjsj/tjbz` 作为路径填入。此时路由为 [`/gov/stats/tjsj/tjbz`](https://rsshub.app/gov/stats/tjsj/tjbz)
+
+:::
+
+</Route>
+
 ## 国家新闻出版广电总局（弃用）
 
 ### 游戏审批结果

lib/v2/gov/maintainer.js

@@ -33,6 +33,7 @@ module.exports = {
     '/pbc/gzlw': ['Fatpandac'],
     '/pbc/tradeAnnouncement': ['nczitzk'],
     '/pbc/zcyj': ['Fatpandac'],
+    '/stats/:path+': ['bigfei'],
     // province
     '/anhui/kjt/:path?': ['nczitzk'],
     '/beijing/jw/tzgg': ['nczitzk'],

lib/v2/gov/radar.js

@@ -688,6 +688,17 @@ module.exports = {
             },
         ],
     },
+    'stats.gov.cn': {
+        _name: '国家统计局',
+        www: [
+            {
+                title: '统计数据 > 最新发布',
+                docs: 'https://docs.rsshub.app/government.html#guo-jia-tong-ji-ju-tong-ji-shu-ju-zui-xin-fa-bu',
+                source: ['/*'],
+                target: (params, url) => `/gov/stats/${new URL(url).href.match(/stats\.gov\.cn\/(.*)/)[1]}`,
+            },
+        ],
+    },
     'sz.gov.cn': {
         _name: '深圳政府在线移动门户',
         hrss: [

lib/v2/gov/router.js

@@ -25,6 +25,7 @@ module.exports = function (router) {
     router.get('/pbc/gzlw', require('./pbc/gzlw'));
     router.get('/pbc/tradeAnnouncement', require('./pbc/tradeAnnouncement'));
     router.get('/pbc/zcyj', require('./pbc/zcyj'));
+    router.get(/stats(\/[\w/-]+)?/, require('./stats'));
     // province
     router.get(/anhui\/kjt\/([\w\d/-]+)?/, require('./anhui/kjt'));
     router.get('/beijing/jw/tzgg', require('./beijing/jw/tzgg'));

lib/v2/gov/stats/index.js

@@ -0,0 +1,19 @@
+const { parseContList, parseXilan } = require('./utils');
+
+module.exports = async (ctx) => {
+    const rootUrl = 'http://www.stats.gov.cn';
+    const defaultPath = '/tjsj/zxfb/';
+
+    let pathname = ctx.path.replace(/(^\/stats|\/$)/g, '');
+    pathname = pathname === '' ? defaultPath : pathname.endsWith('/') ? pathname : pathname + '/';
+    const currentUrl = `${rootUrl}${pathname}`;
+
+    const { list, title } = await parseContList(currentUrl, 'ul.center_list_contlist li a:not([id])', ctx);
+    const items = await Promise.all(list.map((item) => parseXilan(item, ctx)));
+
+    ctx.state.data = {
+        title,
+        link: currentUrl,
+        item: items,
+    };
+};

lib/v2/gov/stats/templates/attachments.art

@@ -0,0 +1,5 @@
+{{ each attachments }}
+    <p>
+        <a href="{{ $value.href }}" >{{ $value.text }}</a>
+    </p>
+{{ /each}}

lib/v2/gov/stats/utils.js

@@ -0,0 +1,64 @@
+const cheerio = require('cheerio');
+const { parseDate } = require('@/utils/parse-date');
+const got = require('@/utils/got');
+const timezone = require('@/utils/timezone');
+const { art } = require('@/utils/render');
+const path = require('path');
+
+const parseContList = async (url, selector, ctx) => {
+    const response = await got(url);
+    const $ = cheerio.load(response.data);
+    const list = $(selector)
+        .slice(0, ctx.query.limit ? parseInt(ctx.query.limit) : 12)
+        .toArray()
+        .map((item) => {
+            item = $(item);
+            return {
+                title: item.find('.cont_tit03').text(),
+                link: new URL(item.attr('href'), url).href,
+                pubDate: parseDate(item.find('.cont_tit02').text(), 'YYYY-MM-DD'),
+            };
+        })
+        .filter((item) => item.title); // exclude the empty title
+    const title = $('#PL_DAOHANG')
+        .text()
+        .replace(/(.+)首页/, '国家统计局');
+    return { list, title };
+};
+
+const parseXilan = async (item, ctx) =>
+    await ctx.cache.tryGet(item.link, async () => {
+        const response = await got(item.link);
+        const $ = cheerio.load(response.data);
+        const title = $('.xilan_titf').text();
+        item.author = title.match(/来源：(.*)发布时间/)?.[1].trim() ?? '国家统计局';
+        item.pubDate = timezone(parseDate(title.match(/发布时间：(.*)/)?.[1].trim() ?? item.pubDate), +8);
+        item.description = $('.xilan_con').html();
+
+        const attachmentTitle = $('.wenzhang_tit').filter(function () {
+            return $(this).text().trim() === '相关附件';
+        });
+        if (attachmentTitle.length > 0) {
+            const attachments = attachmentTitle
+                .first()
+                .next('.wenzhang_list')
+                .find('a')
+                .toArray()
+                .map((attachment) => {
+                    attachment = $(attachment);
+                    return {
+                        href: new URL(attachment.attr('href'), item.link).href,
+                        text: attachment.text().trim(),
+                    };
+                });
+            item.description += art(path.join(__dirname, 'templates/attachments.art'), {
+                attachments,
+            });
+        }
+        return item;
+    });
+
+module.exports = {
+    parseXilan,
+    parseContList,
+};