feat: add arxiv search (#4859)

docs/journal.md

@@ -4,6 +4,18 @@ pageClass: routes
 
 # 科学期刊
 
+## arXiv
+
+### 搜索关键字
+
+<Route author="nczitzk" example="/arxiv/search_query=all:electron&start=0&max_results=10" path="/arxiv/:query" :paramsDesc="['查询语句']" anticrawler="1">
+
+参见 [arXiv API 用户手册](https://arxiv.org/help/api/user-manual) 查看所有查询参数。
+
+路由中的参数 query 处填写 `http://export.arxiv.org/api/query?` 后的内容。
+
+</Route>
+
 ## Cell
 
 ### 主刊

lib/router.js

@@ -2768,4 +2768,7 @@ router.get('/stork/keyword/:trackID/:displayKey', require('./routes/stork/keywor
 // 致美化
 router.get('/zhutix/latest', require('./routes/zhutix/latest'));
 
+// arXiv
+router.get('/arxiv/:query', require('./routes/arxiv/query'));
+
 module.exports = router;

lib/routes/arxiv/query.js

@@ -0,0 +1,28 @@
+const got = require('@/utils/got');
+const cheerio = require('cheerio');
+
+module.exports = async (ctx) => {
+    const currentUrl = `http://export.arxiv.org/api/query?${ctx.params.query}`;
+    const response = await got({
+        method: 'get',
+        url: currentUrl,
+    });
+    const $ = cheerio.load(response.data);
+    const list = $('entry')
+        .map((_, item) => {
+            item = $(item);
+            return {
+                title: item.find('title').text(),
+                link: item.find('link[type="text/html"]').attr('href'),
+                pubDate: new Date(item.find('published').text()).toUTCString(),
+                description: item.find('summary').text(),
+            };
+        })
+        .get();
+
+    ctx.state.data = {
+        title: 'arXiv (' + ctx.params.query + ')',
+        link: currentUrl,
+        item: list,
+    };
+};