htmlunit提供了对table表格的操作支持:
这里先演示下操作简单表格:
<!DOCTYPE html> <html> <head> <meta charset="UTF-8"> <title>简单表格</title> </head> <body> <table id="table1"> <tr> <th>学号</th> <th>姓名</th> </tr> <tr> <td>007</td> <td>米歇尔</td> </tr> </table> </body> </html>
地址:http://www.java1234.com/crawler/table01.html
遍历所有行所有列代码:
package com.open1111; import java.io.IOException; import java.net.MalformedURLException; import com.gargoylesoftware.htmlunit.BrowserVersion; import com.gargoylesoftware.htmlunit.FailingHttpStatusCodeException; import com.gargoylesoftware.htmlunit.WebClient; import com.gargoylesoftware.htmlunit.html.HtmlPage; import com.gargoylesoftware.htmlunit.html.HtmlTable; import com.gargoylesoftware.htmlunit.html.HtmlTableCell; import com.gargoylesoftware.htmlunit.html.HtmlTableRow; public class HtmlUnitTest6 { public static void main(String[] args) { WebClient webClient=new WebClient(BrowserVersion.FIREFOX_52); // 实例化Web客户端 webClient.getOptions().setCssEnabled(false); // 取消css支持 webClient.getOptions().setJavaScriptEnabled(false); // 取消javascript支持 try { HtmlPage page=webClient.getPage("http://www.java1234.com/crawler/table01.html"); // 解析获取页面 HtmlTable table=page.getHtmlElementById("table1"); for(HtmlTableRow row:table.getRows()){ // 遍历所有行 for(HtmlTableCell cell:row.getCells()){ // 遍历所有列 System.out.print(cell.asText()+" "); } System.out.println(); } } catch (FailingHttpStatusCodeException e) { // TODO Auto-generated catch block e.printStackTrace(); } catch (MalformedURLException e) { // TODO Auto-generated catch block e.printStackTrace(); } catch (IOException e) { // TODO Auto-generated catch block e.printStackTrace(); }finally{ webClient.close(); // 关闭客户端,释放内存 } } }
运行输出:
学号 姓名
007 米歇尔
当然也提供了直接获取指定行指定列的api:
package com.open1111; import java.io.IOException; import java.net.MalformedURLException; import com.gargoylesoftware.htmlunit.BrowserVersion; import com.gargoylesoftware.htmlunit.FailingHttpStatusCodeException; import com.gargoylesoftware.htmlunit.WebClient; import com.gargoylesoftware.htmlunit.html.HtmlPage; import com.gargoylesoftware.htmlunit.html.HtmlTable; import com.gargoylesoftware.htmlunit.html.HtmlTableCell; import com.gargoylesoftware.htmlunit.html.HtmlTableRow; public class HtmlUnitTest6 { public static void main(String[] args) { WebClient webClient=new WebClient(BrowserVersion.FIREFOX_52); // 实例化Web客户端 webClient.getOptions().setCssEnabled(false); // 取消css支持 webClient.getOptions().setJavaScriptEnabled(false); // 取消javascript支持 try { HtmlPage page=webClient.getPage("http://www.java1234.com/crawler/table01.html"); // 解析获取页面 HtmlTable table=page.getHtmlElementById("table1"); System.out.println("获取第1行第2列:"+table.getCellAt(0, 1).asText()); System.out.println("获取第2行第1列:"+table.getCellAt(1, 0).asText()); } catch (FailingHttpStatusCodeException e) { // TODO Auto-generated catch block e.printStackTrace(); } catch (MalformedURLException e) { // TODO Auto-generated catch block e.printStackTrace(); } catch (IOException e) { // TODO Auto-generated catch block e.printStackTrace(); }finally{ webClient.close(); // 关闭客户端,释放内存 } } }
运行输出:
获取第1行第2列:姓名
获取第2行第1列:007