Browse Source

w10-张思渊-202401070104

main
zhangsiyuan 1 month ago
parent
commit
621e8b9d4d
  1. 33
      w10/BlogStrategy.java

33
w10/BlogStrategy.java

@ -0,0 +1,33 @@
package com.example.datacollect.strategy;
import com.example.datacollect.model.Article;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Pattern;
public class BlogStrategy implements CrawlStrategy {
private static final Pattern URL_PATTERN = Pattern.compile("https?://[^/]*blog\\.example\\.com.*");
@Override
public boolean supports(String url) {
return url != null && URL_PATTERN.matcher(url).matches();
}
@Override
public int getPriority() {
return 50;
}
@Override
public List<Article> parse(String url, Document doc) {
List<Article> articles = new ArrayList<>();
Elements titles = doc.select(".post-title");
for (Element e : titles) {
articles.add(new Article(e.text(), url, ""));
}
return articles;
}
}
Loading…
Cancel
Save