先給出網(wǎng)頁(yè)地址:
https://wall.alphacoders.com/featured.php?lang=Chinese
主要步驟:
利用Jsoup的connect方法獲取Document對(duì)象
String html = "https://wall.alphacoders.com/featured.php?lang=Chinese";
Document doc = Jsoup.connect(html).get();
內(nèi)容過(guò)長(zhǎng),就不再顯示。
我們以這部分為例:
<ul class="nav nav-pills">
<li><a rel="external nofollow" rel="external nofollow" >About Us</a></li>
<li><a rel="external nofollow" rel="external nofollow" >FAQ</a></li>
<li><a rel="external nofollow" rel="external nofollow" >Privacy Policy</a></li>
<li><a rel="external nofollow" rel="external nofollow" >Terms Of Service</a></li>
<li><a rel="external nofollow" rel="external nofollow" >Acceptable Use</a></li>
<li><a rel="external nofollow" rel="external nofollow" >Etiquette</a></li>
<li><a rel="external nofollow" rel="external nofollow" >Advertise With Us</a></li>
<li><a id="change_consent">Change Consent</a></li>
</ul>
我們先找到所有的ul:
Elements elements = doc.getElementsByTag("ul");
輸出如下:
<ul class="nav navbar-nav center">
<li> <a title="Submit Wallpapers" rel="external nofollow" ><i class="el el-circle-arrow-up"></i> 提交</a> </li>
<li> <a rel="external nofollow" ><i class="el el-gift"></i> 精美獎(jiǎng)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 rel="external nofollow" ><i class="el el-user"></i> 登錄</a> </li>
<li> <a rel="external nofollow" ><i class="el el-edit"></i> 注冊(cè)</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" >< 上一頁(yè)</a></li>
<li class="active"><a>1</a></li>
<li><a rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" >2</a></li>
<li><a rel="external nofollow" rel="external nofollow" rel="external nofollow" >3</a></li>
<li><a rel="external nofollow" rel="external nofollow" rel="external nofollow" >4</a></li>
<li><a rel="external nofollow" rel="external nofollow" rel="external nofollow" >5</a></li>
<li><a rel="external nofollow" rel="external nofollow" rel="external nofollow" >6</a></li>
<li><a rel="external nofollow" rel="external nofollow" rel="external nofollow" >7</a></li>
<li><a rel="external nofollow" >8</a></li>
<li><a rel="external nofollow" >9</a></li>
<li><a rel="external nofollow" >10</a></li>
<li><a>...</a></li>
<li><a rel="external nofollow" rel="external nofollow" rel="external nofollow" >319</a></li>
<li><a id="next_page" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" >下一頁(yè) ></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" >< 上一頁(yè)</a></li>
<li class="active"><a>1</a></li>
<li><a rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" >2</a></li>
<li><a rel="external nofollow" rel="external nofollow" rel="external nofollow" >3</a></li>
<li><a rel="external nofollow" rel="external nofollow" rel="external nofollow" >4</a></li>
<li><a rel="external nofollow" rel="external nofollow" rel="external nofollow" >5</a></li>
<li><a rel="external nofollow" rel="external nofollow" rel="external nofollow" >6</a></li>
<li><a rel="external nofollow" rel="external nofollow" rel="external nofollow" >7</a></li>
<li><a>...</a></li>
<li><a rel="external nofollow" rel="external nofollow" rel="external nofollow" >319</a></li>
<li><a rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" >下一頁(yè) ></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" ><< </a></li>
<li class="active"><a href="#" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" >< 上一頁(yè)</a></li>
<li><a rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" >下一頁(yè) ></a></li>
<li><a title="末頁(yè) (319)" rel="external nofollow" rel="external nofollow" rel="external nofollow" > >></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 rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" >2</a></li>
<li><a rel="external nofollow" rel="external nofollow" rel="external nofollow" >3</a></li>
<li><a rel="external nofollow" rel="external nofollow" rel="external nofollow" >4</a></li>
<li><a rel="external nofollow" rel="external nofollow" rel="external nofollow" >5</a></li>
<li><a rel="external nofollow" rel="external nofollow" rel="external nofollow" >6</a></li>
<li><a rel="external nofollow" rel="external nofollow" rel="external nofollow" >7</a></li>
</ul>
<ul class="nav nav-pills">
<li><a rel="external nofollow" rel="external nofollow" >About Us</a></li>
<li><a rel="external nofollow" rel="external nofollow" >FAQ</a></li>
<li><a rel="external nofollow" rel="external nofollow" >Privacy Policy</a></li>
<li><a rel="external nofollow" rel="external nofollow" >Terms Of Service</a></li>
<li><a rel="external nofollow" rel="external nofollow" >Acceptable Use</a></li>
<li><a rel="external nofollow" rel="external nofollow" >Etiquette</a></li>
<li><a rel="external nofollow" rel="external nofollow" >Advertise With Us</a></li>
<li><a id="change_consent">Change Consent</a></li>
</ul>
可以發(fā)現(xiàn)class為"nav nav-pills"的只有一個(gè),我們找到它:
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;
}
}
循環(huán)遍歷這個(gè)ul,輸出其中每一個(gè)li里每一個(gè)a的href和rel屬性:
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);
}
}
}
最終結(jié)果:
href=https://alphacoders.com/site/about-us rel=nofollow
href=https://alphacoders.com/site/faq rel=nofollow
href=https://alphacoders.com/site/privacy rel=nofollow
href=https://alphacoders.com/site/tos rel=nofollow
href=https://alphacoders.com/site/acceptable_use rel=nofollow
href=https://alphacoders.com/site/etiquette rel=nofollow
href=https://alphacoders.com/site/advertising rel=nofollow
完整代碼:
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 自動(dòng)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);
?? ??? ??? ??? ?}
?? ??? ??? ?}
?? ??? ?}?? ??? ?
?? ?}
}
到此這篇關(guān)于Java爬蟲實(shí)現(xiàn)Jsoup利用dom方法遍歷Document對(duì)象的文章就介紹到這了,更多相關(guān)Java Jsoup遍歷Document對(duì)象內(nèi)容請(qǐng)搜索html5模板網(wǎng)以前的文章希望大家以后多多支持html5模板網(wǎng)!