上传文件至 ''

BaiduStrategy.java

@@ -0,0 +1,32 @@
+package strategy;
+
+import model.Article;
+import util.HttpUtil;
+import exception.SpiderException;
+
+public class BaiduStrategy implements CrawlStrategy {
+    @Override
+    public String getName() {
+        return "百度";
+    }
+    
+    @Override
+    public String getUrl() {
+        return "https://www.baidu.com/";
+    }
+    
+    @Override
+    public Article crawl() throws SpiderException {
+        String html = HttpUtil.get(getUrl(), "UTF-8");
+        
+        String title = HttpUtil.extractTagSafe(html, "<title>", "</title>");
+        
+        Article article = new Article();
+        article.setTitle(title);
+        article.setContent("百度首页");
+        article.setUrl(getUrl());
+        article.setSource(getName());
+        
+        return article;
+    }
+}

BingStrategy.java

@@ -0,0 +1,32 @@
+package strategy;
+
+import model.Article;
+import util.HttpUtil;
+import exception.SpiderException;
+
+public class BingStrategy implements CrawlStrategy {
+    @Override
+    public String getName() {
+        return "必应搜索";
+    }
+    
+    @Override
+    public String getUrl() {
+        return "https://cn.bing.com/";
+    }
+    
+    @Override
+    public Article crawl() throws SpiderException {
+        String html = HttpUtil.get(getUrl(), "UTF-8");
+        
+        String title = HttpUtil.extractTagSafe(html, "<title>", "</title>");
+        
+        Article article = new Article();
+        article.setTitle(title);
+        article.setContent("微软必应搜索引擎首页");
+        article.setUrl(getUrl());
+        article.setSource(getName());
+        
+        return article;
+    }
+}

CrawlStrategy.java

@@ -0,0 +1,10 @@
+package strategy;
+
+import model.Article;
+import exception.SpiderException;
+
+public interface CrawlStrategy {
+    String getName();
+    String getUrl();
+    Article crawl() throws SpiderException;
+}

HttpBinStrategy.java

@@ -0,0 +1,33 @@
+package strategy;
+
+import model.Article;
+import util.HttpUtil;
+import exception.SpiderException;
+
+public class HttpBinStrategy implements CrawlStrategy {
+    @Override
+    public String getName() {
+        return "HttpBin";
+    }
+    
+    @Override
+    public String getUrl() {
+        return "https://httpbin.org/html";
+    }
+    
+    @Override
+    public Article crawl() throws SpiderException {
+        String html = HttpUtil.get(getUrl(), "UTF-8");
+        
+        String title = HttpUtil.extractTagSafe(html, "<h1>", "</h1>");
+        String content = HttpUtil.extractTagSafe(html, "<p>", "</p>");
+        
+        Article article = new Article();
+        article.setTitle(title);
+        article.setContent(content);
+        article.setUrl(getUrl());
+        article.setSource(getName());
+        
+        return article;
+    }
+}

JjwxcStrategy.java

@@ -0,0 +1,33 @@
+package strategy;
+
+import model.Article;
+import util.HttpUtil;
+import exception.SpiderException;
+
+public class JjwxcStrategy implements CrawlStrategy {
+    @Override
+    public String getName() {
+        return "晋江文学城";
+    }
+    
+    @Override
+    public String getUrl() {
+        return "https://www.jjwxc.net/";
+    }
+    
+    @Override
+    public Article crawl() throws SpiderException {
+        String html = HttpUtil.get(getUrl(), "GB18030");
+        
+        String title = HttpUtil.extractTagSafe(html, "<title>", "</title>");
+        String description = "晋江文学城(www.jjwxc.net)创立于2003年8月，是具备相当规模女性网络文学原创基地";
+        
+        Article article = new Article();
+        article.setTitle(title);
+        article.setContent(description);
+        article.setUrl(getUrl());
+        article.setSource(getName());
+        
+        return article;
+    }
+}