feat: add 中国政协网 (#6555)

docs/government.md

@@ -280,6 +280,18 @@ pageClass: routes
 
 <Route author="EsuRt" example="/gov/statecouncil/briefing" path="/gov/statecouncil/briefing"/>
 
+## 中国政协网
+
+### 栏目
+
+<Route author="nczitzk" example="/cppcc" path="/cppcc/:slug?" :paramsDesc="['见下文']">
+
+将目标栏目的网址拆解为 `http://www.cppcc.gov.cn/` 和后面的字段，去掉 `.shtml` 后，把后面的字段中的 `/` 替换为 `-`，即为该路由的 slug
+
+如：(委员建言)[http://www.cppcc.gov.cn/zxww/newcppcc/wyjy/index.shtml] 的网址在 `http://www.cppcc.gov.cn/` 后的字段是 `zxww/newcppcc/wyjy/index.shtml`，则对应的 slug 为 `zxww-newcppcc-wyjy-index`，对应的路由即为 `/cppcc/zxww-newcppcc-wyjy-index`
+
+</Route>
+
 ### 北京市人民政府
 
 #### 北京教育考试院

lib/router.js

@@ -3767,6 +3767,9 @@ router.get('/sciencenet/blog/:type?/:time?/:sort?', require('./routes/sciencenet
 // DailyArt
 router.get('/dailyart/:language?', require('./routes/dailyart/index'));
 
+// 中国政协网
+router.get('/cppcc/:slug?', require('./routes/gov/cppcc/index'));
+
 // National Association of Colleges and Employers
 router.get('/nace/blog/:sort?', require('./routes/nace/blog'));
 

lib/routes/gov/cppcc/index.js

@@ -0,0 +1,49 @@
+const got = require('@/utils/got');
+const cheerio = require('cheerio');
+
+module.exports = async (ctx) => {
+    const slug = ctx.params.slug || 'zxww-newcppcc-zxyw-index';
+
+    const rootUrl = 'http://www.cppcc.gov.cn';
+    const currentUrl = `${rootUrl}/${slug.replace(/-/g, '/')}.shtml`;
+    const response = await got({
+        method: 'get',
+        url: currentUrl,
+    });
+
+    const list = response.data
+        .match(/new title_array\('(.*)','(.*)','\d{4}-\d{2}-\d{2}'\);/g)
+        .slice(0, 15)
+        .map((item) => {
+            const array = item.replace(/new title_array\(|\);|'/g, '').split(',');
+            return {
+                link: array[0],
+                title: array[1],
+                pubDate: new Date(array[2]).toUTCString(),
+            };
+        });
+
+    const items = await Promise.all(
+        list.map(
+            async (item) =>
+                await ctx.cache.tryGet(item.link, async () => {
+                    const detailResponse = await got({
+                        method: 'get',
+                        url: item.link,
+                    });
+                    const content = cheerio.load(detailResponse.data);
+
+                    item.description = content('.cnt_box .con').html();
+                    item.author = content('.info em').text().split('：')[1];
+
+                    return item;
+                })
+        )
+    );
+
+    ctx.state.data = {
+        title: `${response.data.match(/<span>><\/span>(.*)<\/p>/)[1]} - 中国政协网`,
+        link: currentUrl,
+        item: items,
+    };
+};