浏览代码

HtmlUnitTest

Signed-off-by: tangsong <86121657@qq.com>
tangsong 4 月之前
父节点
当前提交
39d5fc1b3b
共有 1 个文件被更改,包括 31 次插入8 次删除
  1. 31 8
      unis-web-app/src/test/java/htmlUnit/HtmlUnitTest.java

+ 31 - 8
unis-web-app/src/test/java/htmlUnit/HtmlUnitTest.java

@@ -2,10 +2,20 @@ package htmlUnit;
2 2
 
3 3
 import org.htmlunit.BrowserVersion;
4 4
 import org.htmlunit.WebClient;
5
-import org.htmlunit.html.HtmlBody;
5
+import org.htmlunit.WebConnection;
6
+import org.htmlunit.WebRequest;
7
+import org.htmlunit.WebResponse;
8
+import org.htmlunit.html.HtmlAcronym;
9
+import org.htmlunit.html.HtmlAnchor;
10
+import org.htmlunit.html.HtmlDivision;
11
+import org.htmlunit.html.HtmlElement;
6 12
 import org.htmlunit.html.HtmlPage;
13
+import org.htmlunit.html.HtmlParagraph;
14
+
15
+import org.htmlunit.html.HtmlSpan;
7 16
 import org.junit.Test;
8 17
 
18
+import java.io.IOException;
9 19
 import java.util.List;
10 20
 
11 21
 /**
@@ -23,19 +33,32 @@ public class HtmlUnitTest {
23 33
         WebClient webClient=null;
24 34
         try {
25 35
             webClient= new WebClient(BrowserVersion.CHROME);    //定义一个WebClient
26
-            final HtmlPage page=webClient.getPage("http://fgw.qinghai.gov.cn//");    //从指定URL获取HtmlPage
27
-
28
-            List<HtmlBody> divList=page.getByXPath("//body");
29
-            for (HtmlBody htmlBody : divList) {
30
-                System.out.println("***********************************************8");
31
-                System.out.println("输出:"+htmlBody.asXml());
36
+            // 自定义一个处理404的处理器
37
+            webClient.getOptions().setJavaScriptEnabled(false);
38
+            webClient.getOptions().setTimeout(10000*6); // 设置超时时间为10秒
39
+            final HtmlPage page=webClient.getPage("http://www.qinghai.gov.cn/zwgk/xwdt/qhyw/");    //从指定URL获取HtmlPage
40
+            List<HtmlParagraph> divList=page.getByXPath("//p[@class='item']");
41
+            int i = 0;
42
+            for (HtmlParagraph node : divList) {
43
+                System.out.println("***********************************************"+i);
44
+                HtmlSpan span = node.getFirstByXPath("span[@class='gray']");
45
+                if (span != null){
46
+                    System.out.println(span.getTextContent());
47
+                    String[] string = span.getTextContent().split("]");
48
+                    System.out.println("[[["+string[0].replace("[","").replace("/","-").trim()+"1111");
49
+                }
50
+                HtmlAnchor anchors = node.getFirstByXPath("a[@target='_blank']");
51
+                System.out.println(anchors.getAttribute("href"));
52
+                System.out.println(anchors.getAttribute("title"));
53
+                System.out.println("输出:"+node.asXml());
54
+                i++;
32 55
             }
33 56
 
34 57
         } catch (Exception e) {
35 58
             // TODO: handle exception
36 59
             e.printStackTrace();
37 60
         }finally {
38
-            webClient.close();    //关闭客户端
61
+         //   webClient.close();    //关闭客户端
39 62
         }
40 63
     }
41 64