上传文件至 'W11/strategy'

W11/strategy/BlogStrategy.java

@@ -0,0 +1,32 @@
+package com.example.datacollect.strategy;
+
+import com.example.datacollect.exception.ParseException;
+import com.example.datacollect.model.Article;
+import org.jsoup.nodes.Document;
+import org.jsoup.nodes.Element;
+import org.jsoup.select.Elements;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+import java.util.ArrayList;
+import java.util.List;
+
+public class BlogStrategy implements CrawlStrategy {
+    private static final Logger logger = LoggerFactory.getLogger(BlogStrategy.class);
+
+    @Override
+    public boolean supports(String url) {
+        return url.contains("blog.example.com");
+    }
+
+    @Override
+    public List<Article> parse(String url, Document doc) throws ParseException {
+        logger.debug("Parsing blog content from: {}", url);
+        List<Article> articles = new ArrayList<>();
+        Elements titles = doc.select(".post-title");
+        for (Element e : titles) {
+            articles.add(new Article(e.text(), url, ""));
+        }
+        logger.debug("Parsed {} articles from blog", articles.size());
+        return articles;
+    }
+}

W11/strategy/CrawlStrategy.java

@@ -0,0 +1,11 @@
+package com.example.datacollect.strategy;
+
+import com.example.datacollect.exception.ParseException;
+import com.example.datacollect.model.Article;
+import org.jsoup.nodes.Document;
+import java.util.List;
+
+public interface CrawlStrategy {
+    List<Article> parse(String url, Document doc) throws ParseException;
+    boolean supports(String url);
+}

W11/strategy/HnuNewsStrategy.java

@@ -0,0 +1,56 @@
+package com.example.datacollect.strategy;
+
+import com.example.datacollect.exception.ParseException;
+import com.example.datacollect.model.Article;
+import org.jsoup.nodes.Document;
+import org.jsoup.nodes.Element;
+import org.jsoup.select.Elements;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+import java.util.ArrayList;
+import java.util.List;
+
+public class HnuNewsStrategy implements CrawlStrategy {
+    private static final Logger logger = LoggerFactory.getLogger(HnuNewsStrategy.class);
+
+    @Override
+    public boolean supports(String url) {
+        return url.contains("news.hnu.edu.cn");
+    }
+
+    @Override
+    public List<Article> parse(String url, Document doc) throws ParseException {
+        logger.debug("Parsing HNU news content from: {}", url);
+        List<Article> articles = new ArrayList<>();
+        Elements listItems = doc.select("ul.list11 li");
+
+        for (Element li : listItems) {
+            Element link = li.selectFirst("a");
+            if (link == null) continue;
+
+            String articleUrl = link.attr("href");
+            if (!articleUrl.startsWith("http")) {
+                articleUrl = "https://news.hnu.edu.cn" + articleUrl.replace("..", "");
+            }
+
+            String title = "";
+            Element titleEl = link.selectFirst("h4.l2.h4s2");
+            if (titleEl != null) {
+                title = titleEl.text().trim();
+            }
+
+            String content = "";
+            Element contentEl = link.selectFirst("p.l3.ps3");
+            if (contentEl != null) {
+                content = contentEl.text().trim();
+            }
+
+            if (!title.isEmpty()) {
+                articles.add(new Article(title, articleUrl, content));
+            }
+        }
+
+        logger.debug("Parsed {} articles from HNU news", articles.size());
+        return articles;
+    }
+}

W11/strategy/NewsStrategy.java

@@ -0,0 +1,32 @@
+package com.example.datacollect.strategy;
+
+import com.example.datacollect.exception.ParseException;
+import com.example.datacollect.model.Article;
+import org.jsoup.nodes.Document;
+import org.jsoup.nodes.Element;
+import org.jsoup.select.Elements;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+import java.util.ArrayList;
+import java.util.List;
+
+public class NewsStrategy implements CrawlStrategy {
+    private static final Logger logger = LoggerFactory.getLogger(NewsStrategy.class);
+
+    @Override
+    public boolean supports(String url) {
+        return url.contains("news.example.com");
+    }
+
+    @Override
+    public List<Article> parse(String url, Document doc) throws ParseException {
+        logger.debug("Parsing news content from: {}", url);
+        List<Article> articles = new ArrayList<>();
+        Elements items = doc.select(".article-headline");
+        for (Element e : items) {
+            articles.add(new Article(e.text(), url, ""));
+        }
+        logger.debug("Parsed {} articles from news", articles.size());
+        return articles;
+    }
+}

W11/strategy/StrategyFactory.java

@@ -0,0 +1,34 @@
+package com.example.datacollect.strategy;
+
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+import java.util.ArrayList;
+import java.util.List;
+
+public class StrategyFactory {
+    private static final Logger logger = LoggerFactory.getLogger(StrategyFactory.class);
+    private final List<CrawlStrategy> strategies = new ArrayList<>();
+
+    public StrategyFactory() {
+        strategies.add(new HnuNewsStrategy());
+        strategies.add(new BlogStrategy());
+        strategies.add(new NewsStrategy());
+        logger.info("StrategyFactory initialized with {} strategies", strategies.size());
+    }
+
+    public CrawlStrategy getStrategy(String url) {
+        for (CrawlStrategy s : strategies) {
+            if (s.supports(url)) {
+                logger.debug("Found strategy for URL: {} -> {}", url, s.getClass().getSimpleName());
+                return s;
+            }
+        }
+        logger.warn("No strategy found for URL: {}", url);
+        return null;
+    }
+
+    public void register(CrawlStrategy strategy) {
+        strategies.add(strategy);
+        logger.info("Registered new strategy: {}", strategy.getClass().getSimpleName());
+    }
+}