上传文件至 'project/strategy'

project/strategy/DoubanBookStrategy.java

@@ -0,0 +1,33 @@
+package com.example.moviecli.strategy;
+
+import com.example.moviecli.model.Movie;
+import com.example.moviecli.exception.ParseFailedException;
+import org.jsoup.nodes.Document;
+import org.jsoup.nodes.Element;
+import org.jsoup.select.Elements;
+import java.util.ArrayList;
+import java.util.List;
+
+public class DoubanBookStrategy implements MovieCrawlStrategy {
+    @Override
+    public boolean supports(String url) {
+        return url.contains("book.douban.com/top250");
+    }
+
+    @Override
+    public List<Movie> parse(Document doc) throws ParseFailedException {
+        try {
+            List<Movie> books = new ArrayList<>();
+            Elements items = doc.select(".item");
+            int rank = 1;
+            for (Element item : items) {
+                String title = item.select(".pl2 a").text().trim();
+                String score = item.select(".rating_nums").text();
+                books.add(new Movie(rank++, title, "", score, "图书", "豆瓣图书"));
+            }
+            return books;
+        } catch (Exception e) {
+            throw new ParseFailedException("豆瓣图书解析失败", e);
+        }
+    }
+}

project/strategy/DoubanTop250Strategy.java

@@ -0,0 +1,59 @@
+package com.example.moviecli.strategy;
+
+import com.example.moviecli.model.Movie;
+import com.example.moviecli.exception.ParseFailedException;
+import org.jsoup.nodes.Document;
+import org.jsoup.nodes.Element;
+import org.jsoup.select.Elements;
+import java.util.ArrayList;
+import java.util.List;
+
+public class DoubanTop250Strategy implements MovieCrawlStrategy {
+    @Override
+    public boolean supports(String url) {
+        return url.contains("movie.douban.com/top250");
+    }
+
+    @Override
+    public List<Movie> parse(Document doc) throws ParseFailedException {
+        try {
+            List<Movie> movies = new ArrayList<>();
+            Elements items = doc.select(".item");
+            for (Element item : items) {
+                String rankText = item.select(".pic em").text();
+                int rank = Integer.parseInt(rankText);
+                String title = item.select(".title").first().text();
+                String originalTitle = "";
+                Elements titles = item.select(".title");
+                if (titles.size() > 1) {
+                    originalTitle = titles.get(1).text().replace("/", "").trim();
+                }
+                String score = item.select(".rating_num").text();
+                String info = item.select(".bd p").first().text();
+                String year = extractYear(info);
+                String director = extractDirector(info);
+                movies.add(new Movie(rank, title, originalTitle, score, year, director));
+            }
+            return movies;
+        } catch (Exception e) {
+            throw new ParseFailedException("豆瓣电影解析失败", e);
+        }
+    }
+
+    private String extractYear(String info) {
+        for (String part : info.split(" ")) {
+            if (part.matches("\\d{4}")) return part;
+        }
+        return "未知";
+    }
+
+    private String extractDirector(String info) {
+        if (info.contains("导演:")) {
+            int start = info.indexOf("导演:") + 3;
+            int end = info.indexOf(" ", start);
+            if (end == -1) end = info.length();
+            return info.substring(start, end).trim();
+        }
+        return "未知";
+    }
+}

project/strategy/MovieCrawlStrategy.java

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

project/strategy/MovieStrategyFactory.java

@@ -0,0 +1,25 @@
+package com.example.moviecli.strategy;
+
+import java.util.ArrayList;
+import java.util.List;
+
+public class MovieStrategyFactory {
+    private final List<MovieCrawlStrategy> strategies = new ArrayList<>();
+
+    public MovieStrategyFactory() {
+        strategies.add(new DoubanTop250Strategy());
+        strategies.add(new SinaNewsStrategy());   // 新增
+        strategies.add(new DoubanBookStrategy());
+    }
+
+    public MovieCrawlStrategy getStrategy(String url) {
+        for (MovieCrawlStrategy s : strategies) {
+            if (s.supports(url)) return s;
+        }
+        return null;
+    }
+
+    public void register(MovieCrawlStrategy strategy) {
+        strategies.add(strategy);
+    }
+}

project/strategy/SinaNewsStrategy.java

@@ -0,0 +1,59 @@
+package com.example.moviecli.strategy;
+
+import com.example.moviecli.model.Movie;
+import com.example.moviecli.exception.ParseFailedException;
+import org.jsoup.nodes.Document;
+import org.jsoup.nodes.Element;
+import org.jsoup.select.Elements;
+import java.util.ArrayList;
+import java.util.LinkedHashSet;
+import java.util.List;
+import java.util.Set;
+
+public class SinaNewsStrategy implements MovieCrawlStrategy {
+    @Override
+    public boolean supports(String url) {
+        return url.contains("news.sina.com.cn");
+    }
+
+    @Override
+    public List<Movie> parse(Document doc) throws ParseFailedException {
+        try {
+            List<Movie> newsList = new ArrayList<>();
+            Set<String> titleSet = new LinkedHashSet<>();
+
+            // 抓取所有 a 标签，过滤出标题较长的（通常新闻标题长度 > 8）
+            Elements allLinks = doc.select("a");
+            for (Element link : allLinks) {
+                String title = link.text().trim();
+                // 过滤短文本、纯数字、纯符号、常见非标题文字
+                if (title.length() > 8 && !title.matches("^[\\d\\s]+$") 
+                        && !title.contains("评论") && !title.contains("举报")) {
+                    // 进一步过滤：通常新闻标题不会太短且不会包含过多标点
+                    titleSet.add(title);
+                }
+                if (titleSet.size() >= 120) break; // 最多抓取120条
+            }
+
+            // 如果数量不够 30，再尝试抓取特定区域
+            if (titleSet.size() < 30) {
+                Elements newsItems = doc.select(".news-item, .blk, .main-content a");
+                for (Element item : newsItems) {
+                    String title = item.text().trim();
+                    if (title.length() > 8 && !titleSet.contains(title)) {
+                        titleSet.add(title);
+                    }
+                    if (titleSet.size() >= 120) break;
+                }
+            }
+
+            int rank = 1;
+            for (String title : titleSet) {
+                newsList.add(new Movie(rank++, title, "", "新闻", "新浪", ""));
+            }
+            return newsList;
+        } catch (Exception e) {
+            throw new ParseFailedException("新浪新闻解析失败", e);
+        }
+    }
+}