对代码进行重构

README.md

@@ -82,4 +82,8 @@
 - 算法
     - DFS 深度优先算法
     - BFS 广度优先
-
+- 重构
+    - 短方法：
+        - a.便于人脑理解
+        - b.越短越容易复用
+        - c.对于Java来说可以方便的对方法进行覆盖

src/main/java/com/github/weiranyi/Main.java

@@ -37,50 +37,80 @@ public class Main {
                 continue;
             }
             // 判断是否是感兴趣滴内容【新浪站内的网页】
-            // link.contains("sina.cn") && !link.contains("passport.sina.cn") &&
-            if ((link.contains("news.sina.cn")) || "https://sina.cn".equals(link)) {
-                try (CloseableHttpClient httpclient = HttpClients.createDefault()) {
-                    if (link.startsWith("//")) {
-                        link = "https:" + link;
-                    }
-                    HttpGet httpGet = new HttpGet(link);
-                    httpGet.addHeader("user-agent", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.212 Safari/537.36");
-                    try (CloseableHttpResponse response1 = httpclient.execute(httpGet)) {
-                        System.out.println(response1.getStatusLine());
-                        System.out.println(link);
-                        HttpEntity entity1 = response1.getEntity();
-                        String html = EntityUtils.toString(entity1);
+            if (isInterestingLink(link)) {
+                Document doc = httpGetAndParseHtml(link);
+                // 使用CSS选择器,html中去获取
+                ArrayList<Element> links = doc.select("a");
+                links.stream().map(aTag -> aTag.attr("href")).forEach(linkPool::add);
+                // 假设这是一个新闻的详情页，就存入数据库，否则，就什么都不做
+                storeIntoDatabaseIfItIsNewsPage(doc);
+                processedLinks.add(link);
 
-                        Document doc = Jsoup.parse(html);
-                        // 使用CSS选择器,html中去获取
-                        ArrayList<Element> links = doc.select("a");
-                        for (Element aTag : links) {
-                            // 获取href属性
-                            linkPool.add(aTag.attr("href"));
-                        }
-                        // 假设这是一个新闻的详情页，就存入数据库，否则，就什么都不做
-                        ArrayList<Element> articleTags = doc.select("article");
-                        if (!articleTags.isEmpty()) {
-                            for (Element articleTag : articleTags) {
-                                String titile = articleTags.get(0).child(0).text();
-                                System.out.println(titile);
-                            }
-                        }
-                        processedLinks.add(link);
-                    }
-                }
             } else {
                 // 不感兴趣
                 continue;
             }
         }
-//        try (CloseableHttpClient httpclient = HttpClients.createDefault()) {
-//            HttpGet httpGet = new HttpGet("https://sina.cn/");
-//            try (CloseableHttpResponse response1 = httpclient.execute(httpGet)) {
-//                System.out.println(response1.getStatusLine());
-//                HttpEntity entity1 = response1.getEntity();
-//                System.out.println(EntityUtils.toString(entity1));
-//            }
-//        }
     }
+
+
+    /*
+     * 2、将表达不同逻辑的代码抽象为短方法
+     * 优点：
+     * a.便于人脑理解
+     * b.越短越容易复用
+     * c.对于Java来说可以方便的对方法进行覆盖
+     */
+    // 通过http请求拿到HTML文档
+    private static Document httpGetAndParseHtml(String link) throws IOException {
+        try (CloseableHttpClient httpclient = HttpClients.createDefault()) {
+            if (link.startsWith("//")) {
+                link = "https:" + link;
+            }
+            HttpGet httpGet = new HttpGet(link);
+            httpGet.addHeader("user-agent", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.212 Safari/537.36");
+            try (CloseableHttpResponse response1 = httpclient.execute(httpGet)) {
+                System.out.println(response1.getStatusLine());
+                System.out.println(link);
+                HttpEntity entity1 = response1.getEntity();
+                String html = EntityUtils.toString(entity1);
+                return Jsoup.parse(html);
+            }
+        }
+    }
+
+    // 若是新闻页面就存到数据库中
+    private static void storeIntoDatabaseIfItIsNewsPage(Document doc) {
+        ArrayList<Element> articleTags = doc.select("article");
+        if (!articleTags.isEmpty()) {
+            for (Element articleTag : articleTags) {
+                String titile = articleTags.get(0).child(0).text();
+                System.out.println(titile);
+            }
+        }
+    }
+
+    /*
+     * 1、将长的判断条件抽取为不同的方法
+     */
+    // 感兴趣的链接
+    private static boolean isInterestingLink(String link) {
+        return (isNewsPage(link) || isIndexPage(link) && isNotLoginPage(link));
+    }
+
+    // 首页
+    private static boolean isIndexPage(String link) {
+        return "https://sina.cn".equals(link);
+    }
+
+    // 新闻页
+    private static boolean isNewsPage(String link) {
+        return link.contains("news.sina.cn");
+    }
+
+    // 登录页
+    private static boolean isNotLoginPage(String link) {
+        return !link.contains("passport.sina.cn");
+    }
+
 }