Browse Source

w10-张思渊-202401070104”

main
zhangsiyuan 1 month ago
parent
commit
13f7033c61
  1. 47
      w10/DefaultStrategy.java

47
w10/DefaultStrategy.java

@ -0,0 +1,47 @@
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;
public class DefaultStrategy implements CrawlStrategy {
@Override
public boolean supports(String url) {
return true;
}
@Override
public int getPriority() {
return 0;
}
@Override
public List<Article> parse(String url, Document doc) {
List<Article> articles = new ArrayList<>();
Elements titles = doc.select("h1, h2, h3, .title, .article-title, [class*=title], [id*=title]");
for (Element e : titles) {
String title = e.text().trim();
if (!title.isEmpty()) {
articles.add(new Article(title, url, ""));
}
}
if (articles.isEmpty()) {
Elements links = doc.select("a[href]");
for (Element link : links) {
String linkText = link.text().trim();
String linkUrl = link.attr("abs:href");
if (!linkText.isEmpty()) {
articles.add(new Article(linkText, linkUrl, ""));
}
}
}
return articles;
}
}
Loading…
Cancel
Save