Java爬虫实现Jsoup利用dom方法遍历Document对象

https://wall.alphacoders.com/featured.php?lang=Chinese

String html = "https://wall.alphacoders.com/featured.php?lang=Chinese" ;

Document doc = Jsoup.connect(html).get();

< ul class = "nav nav-pills" >

     < li >< a href = "https://alphacoders.com/site/about-us" rel = "external nofollow"   rel = "external nofollow"   >About Us</ a ></ li >

     < li >< a href = "https://alphacoders.com/site/faq" rel = "external nofollow"   rel = "external nofollow"   >FAQ</ a ></ li >

     < li >< a href = "https://alphacoders.com/site/privacy" rel = "external nofollow"   rel = "external nofollow"   >Privacy Policy</ a ></ li >

     < li >< a href = "https://alphacoders.com/site/tos" rel = "external nofollow"   rel = "external nofollow"   >Terms Of Service</ a ></ li >

     < li >< a href = "https://alphacoders.com/site/acceptable_use" rel = "external nofollow"   rel = "external nofollow"   >Acceptable Use</ a ></ li >

     < li >< a href = "https://alphacoders.com/site/etiquette" rel = "external nofollow"   rel = "external nofollow"   >Etiquette</ a ></ li >

     < li >< a href = "https://alphacoders.com/site/advertising" rel = "external nofollow"   rel = "external nofollow"   >Advertise With Us</ a ></ li >

     < li >< a id = "change_consent" >Change Consent</ a ></ li >

</ ul >

Elements elements = doc.getElementsByTag( "ul" );

< ul class = "nav navbar-nav center" >

  < li > < a title = "Submit Wallpapers" href = "https://alphacoders.com/site/submit-wallpaper" rel = "external nofollow" >< i class = "el el-circle-arrow-up" ></ i > 提交</ a > </ li >

  < li > < a href = "https://alphacoders.com/contest" rel = "external nofollow" >< i class = "el el-gift" ></ i > 精美奖品</ a > </ li >

</ ul >

< ul class = "nav navbar-nav navbar-right center" >

  < li > < a href = "language.php?lang=Chinese" rel = "external nofollow" > < img src = "https://static.alphacoders.com/wa/Chinese-flag.png" alt = "Chinese-flag" >   中文    </ a > </ li >

  < li > < a   href = "https://alphacoders.com/users/login" rel = "external nofollow" >< i class = "el el-user" ></ i > 登录</ a > </ li >

  < li > < a href = "https://alphacoders.com/users/register" rel = "external nofollow" >< i class = "el el-edit" ></ i > 注册</ a > </ li >

</ ul >

< ul class = "pagination" >

  < li class = "active" >< a id = "prev_page" href = "#" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >&lt; 上一页</ a ></ li >

  < li class = "active" >< a >1</ a ></ li >

  < li >< a href = "https://wall.alphacoders.com/featured.php?lang=Chinese&amp;page=2" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >2</ a ></ li >

  < li >< a href = "https://wall.alphacoders.com/featured.php?lang=Chinese&amp;page=3" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >3</ a ></ li >

  < li >< a href = "https://wall.alphacoders.com/featured.php?lang=Chinese&amp;page=4" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >4</ a ></ li >

  < li >< a href = "https://wall.alphacoders.com/featured.php?lang=Chinese&amp;page=5" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >5</ a ></ li >

  < li >< a href = "https://wall.alphacoders.com/featured.php?lang=Chinese&amp;page=6" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >6</ a ></ li >

  < li >< a href = "https://wall.alphacoders.com/featured.php?lang=Chinese&amp;page=7" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >7</ a ></ li >

  < li >< a href = "https://wall.alphacoders.com/featured.php?lang=Chinese&amp;page=8" rel = "external nofollow" >8</ a ></ li >

  < li >< a href = "https://wall.alphacoders.com/featured.php?lang=Chinese&amp;page=9" rel = "external nofollow" >9</ a ></ li >

  < li >< a href = "https://wall.alphacoders.com/featured.php?lang=Chinese&amp;page=10" rel = "external nofollow" >10</ a ></ li >

  < li >< a >...</ a ></ li >

  < li >< a href = "https://wall.alphacoders.com/featured.php?lang=Chinese&amp;page=319" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >319</ a ></ li >

  < li >< a id = "next_page" href = "https://wall.alphacoders.com/featured.php?lang=Chinese&amp;page=2" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >下一页 &gt;</ a ></ li >

</ ul >

< ul class = "pagination" >

  < li class = "active" >< a href = "#" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >&lt; 上一页</ a ></ li >

  < li class = "active" >< a >1</ a ></ li >

  < li >< a href = "https://wall.alphacoders.com/featured.php?lang=Chinese&amp;page=2" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >2</ a ></ li >

  < li >< a href = "https://wall.alphacoders.com/featured.php?lang=Chinese&amp;page=3" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >3</ a ></ li >

  < li >< a href = "https://wall.alphacoders.com/featured.php?lang=Chinese&amp;page=4" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >4</ a ></ li >

  < li >< a href = "https://wall.alphacoders.com/featured.php?lang=Chinese&amp;page=5" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >5</ a ></ li >

  < li >< a href = "https://wall.alphacoders.com/featured.php?lang=Chinese&amp;page=6" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >6</ a ></ li >

  < li >< a href = "https://wall.alphacoders.com/featured.php?lang=Chinese&amp;page=7" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >7</ a ></ li >

  < li >< a >...</ a ></ li >

  < li >< a href = "https://wall.alphacoders.com/featured.php?lang=Chinese&amp;page=319" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >319</ a ></ li >

  < li >< a href = "https://wall.alphacoders.com/featured.php?lang=Chinese&amp;page=2" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >下一页 &gt;</ a ></ li >

</ ul >

< ul class = "pagination" >

  < li class = "active" >< a href = "#" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >&lt;&lt; </ a ></ li >

  < li class = "active" >< a href = "#" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >&lt; 上一页</ a ></ li >

  < li >< a href = "https://wall.alphacoders.com/featured.php?lang=Chinese&amp;page=2" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >下一页 &gt;</ a ></ li >

  < li >< a title = "末页 (319)" href = "https://wall.alphacoders.com/featured.php?lang=Chinese&amp;page=319" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" > &gt;&gt;</ a ></ li >

</ ul >

< ul class = "pagination" >

  < li class = "active" >< a href = "#" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >1</ a ></ li >

  < li >< a href = "https://wall.alphacoders.com/featured.php?lang=Chinese&amp;page=2" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >2</ a ></ li >

  < li >< a href = "https://wall.alphacoders.com/featured.php?lang=Chinese&amp;page=3" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >3</ a ></ li >

  < li >< a href = "https://wall.alphacoders.com/featured.php?lang=Chinese&amp;page=4" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >4</ a ></ li >

  < li >< a href = "https://wall.alphacoders.com/featured.php?lang=Chinese&amp;page=5" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >5</ a ></ li >

  < li >< a href = "https://wall.alphacoders.com/featured.php?lang=Chinese&amp;page=6" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >6</ a ></ li >

  < li >< a href = "https://wall.alphacoders.com/featured.php?lang=Chinese&amp;page=7" rel = "external nofollow"   rel = "external nofollow"   rel = "external nofollow" >7</ a ></ li >

</ ul >

< ul class = "nav nav-pills" >

  < li >< a href = "https://alphacoders.com/site/about-us" rel = "external nofollow"   rel = "external nofollow"   >About Us</ a ></ li >

  < li >< a href = "https://alphacoders.com/site/faq" rel = "external nofollow"   rel = "external nofollow"   >FAQ</ a ></ li >

  < li >< a href = "https://alphacoders.com/site/privacy" rel = "external nofollow"   rel = "external nofollow"   >Privacy Policy</ a ></ li >

  < li >< a href = "https://alphacoders.com/site/tos" rel = "external nofollow"   rel = "external nofollow"   >Terms Of Service</ a ></ li >

  < li >< a href = "https://alphacoders.com/site/acceptable_use" rel = "external nofollow"   rel = "external nofollow"   >Acceptable Use</ a ></ li >

  < li >< a href = "https://alphacoders.com/site/etiquette" rel = "external nofollow"   rel = "external nofollow"   >Etiquette</ a ></ li >

  < li >< a href = "https://alphacoders.com/site/advertising" rel = "external nofollow"   rel = "external nofollow"   >Advertise With Us</ a ></ li >

  < li >< a id = "change_consent" >Change Consent</ a ></ li >

</ ul >

Elements elements = doc.getElementsByTag( "ul" );

         //System.out.println(elements);

Element tempElement = null ;

for (Element element : elements) {

     if (element.className().equals( "nav nav-pills" )) {

         tempElement = element;

         //System.out.println(element.className());

         break ;

     }

}

Elements li = tempElement.getElementsByTag( "li" );

for (Element element : li) {

     Elements element2 = element.getElementsByTag( "a" );

     for (Element element3 : element2) {

         String hrefString = element3.attr( "href" );

         String relString = element3.attr( "rel" );

         if (hrefString != "" && relString != "" ) {

             System.out.println( "href=" + hrefString + " rel=" external nofollow "  rel=" external nofollow "  " + "rel=" + relString);

         }

     }

}

import org.jsoup.nodes.Document;

import org.jsoup.nodes.Element;

import org.jsoup.select.Elements;

import java.io.IOException;

import org.jsoup.Jsoup;

/** 

  * @ClassName: Jsoup_Test

  * @description: 

  * @author: KI

  * @Date: 2020年8月17日 下午8:15:14

  */

public class Jsoup_Test {

     public static void main(String[] args) throws IOException {

         // TODO 自动生成的方法存根

         String html = "https://wall.alphacoders.com/featured.php?lang=Chinese" ;

         Document doc = Jsoup.connect(html).get();

         System.out.println(doc);

         Elements elements = doc.getElementsByTag( "ul" );

         //System.out.println(elements);

         Element tempElement = null ;

         for (Element element : elements) {

             if (element.className().equals( "nav nav-pills" )) {

                 tempElement = element;

                 //System.out.println(element.className());

                 break ;

             }

         }

         System.out.println(tempElement);

         Elements li = tempElement.getElementsByTag( "li" );

         for (Element element : li) {

             Elements element2 = element.getElementsByTag( "a" );

             for (Element element3 : element2) {

                 String hrefString = element3.attr( "href" );

                 String relString = element3.attr( "rel" );

                 if (hrefString != "" && relString != "" ) {

                     System.out.println( "href=" + hrefString + " rel=" external nofollow "  rel=" external nofollow "  " + "rel=" + relString);

                 }

             }

         }        

     }

}