From 1066f75e91b974c5b4979b5580af57db8221d17a Mon Sep 17 00:00:00 2001
From: Hanminxi <1772454398@qq.com>
Date: Sun, 31 May 2026 00:05:26 +0800
Subject: [PATCH] =?UTF-8?q?=E4=B8=8A=E4=BC=A0=E6=96=87=E4=BB=B6=E8=87=B3?=
 =?UTF-8?q?=20''?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 BaiduStrategy.java   | 32 ++++++++++++++++++++++++++++++++
 BingStrategy.java    | 32 ++++++++++++++++++++++++++++++++
 CrawlStrategy.java   | 10 ++++++++++
 HttpBinStrategy.java | 33 +++++++++++++++++++++++++++++++++
 JjwxcStrategy.java   | 33 +++++++++++++++++++++++++++++++++
 5 files changed, 140 insertions(+)
 create mode 100644 BaiduStrategy.java
 create mode 100644 BingStrategy.java
 create mode 100644 CrawlStrategy.java
 create mode 100644 HttpBinStrategy.java
 create mode 100644 JjwxcStrategy.java

diff --git a/BaiduStrategy.java b/BaiduStrategy.java
new file mode 100644
index 0000000..71273ab
--- /dev/null
+++ b/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;
+    }
+}
diff --git a/BingStrategy.java b/BingStrategy.java
new file mode 100644
index 0000000..1029b7a
--- /dev/null
+++ b/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;
+    }
+}
diff --git a/CrawlStrategy.java b/CrawlStrategy.java
new file mode 100644
index 0000000..78e1325
--- /dev/null
+++ b/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;
+}
diff --git a/HttpBinStrategy.java b/HttpBinStrategy.java
new file mode 100644
index 0000000..8683ac9
--- /dev/null
+++ b/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;
+    }
+}
diff --git a/JjwxcStrategy.java b/JjwxcStrategy.java
new file mode 100644
index 0000000..e6fe34f
--- /dev/null
+++ b/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;
+    }
+}