people.com.cn parsing

src/main/java/internal/hw/crawler/models/Article.java

@@ -8,7 +8,7 @@ public class Article {
     private String source;
     private URL url;
     private String title;
-    private Set<String> authors;
+    private Set<String> authors = Set.of();
     private String content;
 
     public String getId() {

src/main/java/internal/hw/crawler/strategies/crawl/CrawlStrategyFactory.java

@@ -9,6 +9,7 @@ public class CrawlStrategyFactory {
 
     public CrawlStrategyFactory() {
         register(new IthomeCrawlStrategy());
+        register(new PeopleCnCrawlStrategy());
     }
 
     public CrawlStrategy getStrategy(URL url) {

src/main/java/internal/hw/crawler/strategies/crawl/PeopleCnCrawlStrategy.java

@@ -0,0 +1,97 @@
+package internal.hw.crawler.strategies.crawl;
+
+import internal.hw.crawler.models.Article;
+import org.jsoup.Jsoup;
+import org.jsoup.nodes.Document;
+import org.jsoup.nodes.Element;
+import org.jsoup.select.Elements;
+
+import java.net.URL;
+import java.util.ArrayList;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Set;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+import java.util.stream.Collectors;
+
+public class PeopleCnCrawlStrategy implements CrawlStrategy {
+    private final List<String> supportedDomains = List.of("people.cn", "people.com.cn");
+    /* 示例 URL：http://env.people.com.cn/n1/2026/0530/c1010-40730688.html */
+    private final Pattern idRegex = Pattern.compile("(\\d+)/(\\d+)/c(\\d+)-(\\d+).html");
+
+    @Override
+    public boolean supports(URL url) {
+        for (String domain : supportedDomains) {
+            if (url.getHost().endsWith(domain)) {
+                return true;
+            }
+        }
+
+        return false;
+    }
+
+    @Override
+    public List<Article> parse(URL url, Document doc) throws CrawlException {
+        List<String> homepage = supportedDomains.stream().map(it -> "https://www." + it).collect(Collectors.toList());
+
+        if (homepage.contains(url.toString())) {
+            // 传入的是首页，解析所有链接
+            return parseHomepage(doc);
+        } else {
+            return List.of(parseSingle(url, doc));
+        }
+    }
+
+    private List<Article> parseHomepage(Document doc) {
+        List<Article> articles = new ArrayList<>();
+        Elements links = doc.getElementsByTag("a");
+        for (Element link : links) {
+            String href = link.attr("href");
+            Matcher matcher = idRegex.matcher(href);
+            if (!matcher.find()) {
+                continue;
+            }
+
+            try {
+                URL articleUrl = new URL(href);
+                Document articleDoc = Jsoup.parse(articleUrl, 5000);
+                articles.add(parseSingle(articleUrl, articleDoc));
+            } catch (Exception ignored) {
+            }
+        }
+        return articles;
+    }
+
+    private Article parseSingle(URL url, Document doc) throws CrawlException {
+        Matcher matcher = idRegex.matcher(url.getPath());
+        if (!matcher.find()) {
+            throw new CrawlException(String.format("Cannot determine id for %s", url));
+        }
+
+        String id = String.format("%s%s-c%s-%s", matcher.group(1), matcher.group(2), matcher.group(3), matcher.group(4));
+        Element titleEl = doc.selectFirst(".layout.rm_txt h1");
+        if (titleEl == null) throw new CrawlException(String.format("Cannot find title for %s", url));
+        String title = titleEl.text();
+
+        Set<String> authors = new HashSet<>();
+        Element authorEl = doc.selectFirst("div.author.cf");
+        if (authorEl != null) {
+            authors.add(authorEl.text());
+        }
+
+        Element contentEl = doc.selectFirst("div#rm_txt_zw");
+        if (contentEl == null) throw new CrawlException(String.format("Cannot find content for %s", url));
+        String content = contentEl.text();
+
+        Article article = new Article();
+        article.setId(id);
+        article.setSource("people-cn");
+        article.setUrl(url);
+        article.setTitle(title);
+        article.setAuthors(authors);
+        article.setContent(content);
+
+        return article;
+    }
+}