网页爬取Jsoup的Document转换（含html字符串转）带maven

<!-- 解析网页 -->
<dependency>
  <groupId>org.jsoup</groupId>
  <artifactId>jsoup</artifactId>
<version>1.10.2</version>
</dependency>

html字符串转Document

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

String html = ""
                + "
"
                + " IT学习者论坛 "
                + " "
                + " "
                + "
";
                
Document doc = Jsoup.parse(html);
 Element content = doc.getElementById("content");
 Elements links = content.getElementsByTag("a");

 for (Element link : links) {
     String linkHref = link.attr("href");
     String linkText = link.text();
     System.out.println("linkHref:" + linkHref);
     System.out.println("linkText:" + linkText);
 }
 //---------两种获取不同内容
Elements links = content.getElementsByTag("img");
for (Element link : links) {
     String linkHref = link.getElementsByTag("img").eq(0).attr("src");
     System.out.println("linkHref:" + linkHref);

 }

URL直接转Document（弊端ajax无法获取，需要自己找模拟打开网页后在获取）

String url="https:///";
Document document=Jsoup.parse(new URL(url),30000);
Element content = doc.getElementById("content");
Elements links = content.getElementsByTag("a");
for (Element link : links) {
     String linkHref = link.attr("href");
     String linkText = link.text();
     System.out.println("linkHref:" + linkHref);
     System.out.println("linkText:" + linkText);
 }