jsoup解析html页面

电玩女神 2022-04-10 07:13 317阅读 0赞

maven依赖

<dependency>
                <groupId>org.jsoup</groupId>
                <artifactId>jsoup</artifactId>
                <version>1.11.3</version>
            </dependency>

要解析的html内容 我主要解析table部分 只给出table部分内容

<table class="logview">
                        <tr class="header">
                            <td colspan=5>HT2 cat localhost.localdomain 192.168.104.165 Cat-ConfigSyncTask 167 Cat-ConfigSyncTask-2 cat-c0a868a5-429415-1544 null null  </td>
                        </tr>
                        <tr class="odd">
                            <td>t15:25:04.453</td>
                            <td>TimerSync</td>
                            <td>resource-config</td>
                            <td></td>
                            <td></td>
                        </tr>
                        <tr class="even">
                            <td>  t15:25:04.453</td>
                            <td>SQL</td>
                            <td>config.findByName</td>
                            <td></td>
                            <td></td>
                        </tr>
                        <tr class="odd">
                            <td>    E15:25:04.702</td>
                            <td>SQL.Method</td>
                            <td>SELECT</td>
                            <td> </td>
                            <td>["resource-config"]</td>
                        </tr>
                        <tr class="even">
                            <td>    E15:25:04.702</td>
                            <td>SQL.Database</td>
                            <td>jdbc:mysql://192.168.104.101:3306/cat?useUnicode=true&characterEncoding=UTF-8&autoReconnect=true&socketTimeout=120000</td>
                            <td> </td>
                            <td></td>
                        </tr>
                        <tr class="odd">
                            <td>  T15:25:04.702</td>
                            <td>SQL</td>
                            <td>config.findByName</td>
                            <td> </td>
                            <td>249ms SELECT c.id,c.`name`,c.content,c.creation_date,c.modify_date FROM config c WHERE c.name = ?</td>
                        </tr>
                        <tr class="even">
                            <td>T15:25:04.702</td>
                            <td>TimerSync</td>
                            <td>resource-config</td>
                            <td> </td>
                            <td>249ms </td>
                        </tr>
                    </table>

java 代码

api参考

[https://www.cnblogs.com/boy1025/p/5040495.html][https_www.cnblogs.com_boy1025_p_5040495.html]

[http://www.open-open.com/jsoup/load-document-from-url.htm][http_www.open-open.com_jsoup_load-document-from-url.htm]

本例的代码

package com.flyer;
    
    import org.jsoup.Jsoup;
    import org.jsoup.nodes.Document;
    import org.jsoup.nodes.Element;
    
    import org.jsoup.select.Elements;
    
    import java.io.IOException;
    
    /**
     * flyer 2018.12.28
     */
    public class Test {
        public static void main(String[] args) {
            Document doc = null;
            try {
                doc = Jsoup.connect("http://192.168.104.164:8080/cat/r/m/cat-c0a868a5-429353-669?domain=cat").get();
                Elements container = doc.getElementsByClass("logview");
    
                Elements trList = container.select("tr");
                for (Element tr : trList) {
                    if (tr.getElementsByClass("header") != null && tr.getElementsByClass("header").size() > 0)
                        continue;
                    Elements tdList = tr.select("td");
                    for (Element td : tdList) {
                        String text = td.text();
    //                    System.out.println(tr.text()+"*******"+ text);
                        System.out.println("*******" + text);
                    }
                    System.out.println("开始下一个tr:");
                    System.out.println("");
                }
    //            Document containerDoc = Jsoup.parse(container.toString());
    //            System.out.println(containerDoc.toString());
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }

输出

"C:\Program Files\Java\jdk1.8.0_152\bin\java.exe" "-javaagent:D:\program Files\JetBrains\IntelliJ IDEA 2018.3.2\lib\idea_rt.jar=60158:D:\program Files\JetBrains\IntelliJ IDEA 2018.3.2\bin" -Dfile.encoding=UTF-8 -classpath "C:\Program Files\Java\jdk1.8.0_152\jre\lib\charsets.jar;C:\Program Files\Java\jdk1.8.0_152\jre\lib\deploy.jar;C:\Program Files\Java\jdk1.8.0_152\jre\lib\ext\access-bridge-64.jar;C:\Program Files\Java\jdk1.8.0_152\jre\lib\ext\cldrdata.jar;C:\Program Files\Java\jdk1.8.0_152\jre\lib\ext\dnsns.jar;C:\Program Files\Java\jdk1.8.0_152\jre\lib\ext\jaccess.jar;C:\Program Files\Java\jdk1.8.0_152\jre\lib\ext\jfxrt.jar;C:\Program Files\Java\jdk1.8.0_152\jre\lib\ext\localedata.jar;C:\Program Files\Java\jdk1.8.0_152\jre\lib\ext\nashorn.jar;C:\Program Files\Java\jdk1.8.0_152\jre\lib\ext\sunec.jar;C:\Program Files\Java\jdk1.8.0_152\jre\lib\ext\sunjce_provider.jar;C:\Program Files\Java\jdk1.8.0_152\jre\lib\ext\sunmscapi.jar;C:\Program Files\Java\jdk1.8.0_152\jre\lib\ext\sunpkcs11.jar;C:\Program Files\Java\jdk1.8.0_152\jre\lib\ext\zipfs.jar;C:\Program Files\Java\jdk1.8.0_152\jre\lib\javaws.jar;C:\Program Files\Java\jdk1.8.0_152\jre\lib\jce.jar;C:\Program Files\Java\jdk1.8.0_152\jre\lib\jfr.jar;C:\Program Files\Java\jdk1.8.0_152\jre\lib\jfxswt.jar;C:\Program Files\Java\jdk1.8.0_152\jre\lib\jsse.jar;C:\Program Files\Java\jdk1.8.0_152\jre\lib\management-agent.jar;C:\Program Files\Java\jdk1.8.0_152\jre\lib\plugin.jar;C:\Program Files\Java\jdk1.8.0_152\jre\lib\resources.jar;C:\Program Files\Java\jdk1.8.0_152\jre\lib\rt.jar;D:\work\code\test2018\target\classes;C:\Users\fei.jiang\.m2\repository\org\apache\httpcomponents\httpclient\4.5.2\httpclient-4.5.2.jar;C:\Users\fei.jiang\.m2\repository\org\apache\httpcomponents\httpcore\4.4.4\httpcore-4.4.4.jar;C:\Users\fei.jiang\.m2\repository\commons-logging\commons-logging\1.2\commons-logging-1.2.jar;C:\Users\fei.jiang\.m2\repository\commons-codec\commons-codec\1.9\commons-codec-1.9.jar;C:\Users\fei.jiang\.m2\repository\org\apache\httpcomponents\httpclient-cache\4.5\httpclient-cache-4.5.jar;C:\Users\fei.jiang\.m2\repository\org\apache\httpcomponents\httpmime\4.3.2\httpmime-4.3.2.jar;C:\Users\fei.jiang\.m2\repository\org\jsoup\jsoup\1.11.3\jsoup-1.11.3.jar" com.flyer.Test
    *******t01:11:03.993
    *******TimerSync
    *******server-config
    *******
    *******
    开始下一个tr:
    
    *******t01:11:03.994
    *******SQL
    *******config.findByName
    *******
    *******
    开始下一个tr:
    
    *******E01:11:04.270
    *******SQL.Method
    *******SELECT
    *******
    *******["server-config"]
    开始下一个tr:
    
    *******E01:11:04.270
    *******SQL.Database
    *******jdbc:mysql://192.168.104.101:3306/cat?useUnicode=true&characterEncoding=UTF-8&autoReconnect=true&socketTimeout=120000
    *******
    *******
    开始下一个tr:
    
    *******T01:11:04.271
    *******SQL
    *******config.findByName
    *******
    *******277ms SELECT c.id,c.`name`,c.content,c.creation_date,c.modify_date FROM config c WHERE c.name = ?
    开始下一个tr:
    
    *******T01:11:04.270
    *******TimerSync
    *******server-config
    *******
    *******277ms
    开始下一个tr:
    
    
    Process finished with exit code 0

[https_www.cnblogs.com_boy1025_p_5040495.html]: https://www.cnblogs.com/boy1025/p/5040495.html
[http_www.open-open.com_jsoup_load-document-from-url.htm]: http://www.open-open.com/jsoup/load-document-from-url.htm