需要使用selenium从多个网页捕捉数据

网页： http ： //www.forbes.com/companies/icbc/

package selenium; import java.util.List; import java.util.concurrent.TimeUnit; import org.junit.After; import org.junit.Before; import org.junit.Test; import org.openqa.selenium.By; import org.openqa.selenium.By.ByTagName; import org.openqa.selenium.WebDriver; import org.openqa.selenium.WebElement; import org.openqa.selenium.ie.InternetExplorerDriver; import org.openqa.selenium.support.ui.ExpectedConditions; import org.openqa.selenium.support.ui.WebDriverWait; public class ForbesTest { WebDriver driver; String url; @Before public void setUp() throws Exception { System.setProperty("webdriver.ie.driver","D:\\IEDriverServer_x64_2.53.1\\IEDriverServer.exe"); driver=new InternetExplorerDriver(); driver.manage().timeouts().implicitlyWait(10, TimeUnit.SECONDS); url="http://www.forbes.com/companies/icbc/"; driver.get(url); } @After public void tearDown() throws Exception { driver.quit(); driver.close(); } @Test public void test() throws InterruptedException { Thread.sleep(10000); WebElement tab=driver.findElement(By.className("large")); Thread.sleep(1000); String text= tab.getText(); System.out.println(text); WebElement col1=driver.findElement(By.tagName("dt")); //Thread.sleep(1000); String industry= col1.getText(); if(industry.matches("Industry")){ System.out.println(industry); WebElement col2=driver.findElement(By.tagName("dd")); //Thread.sleep(1000); String industryName= col2.getText(); System.out.println(industryName); } String forbesWebsite= driver.getCurrentUrl(); System.out.println(forbesWebsite); WebElement nextPage=driver.findElement(By.className("next-number")); nextPage.click(); driver.close(); } } 

我想了解排名，公司，国家，销售，销售排名，利润，排名利润，资产，排名资产，市场价值，排名市值，行业，成立，公司网站，员工，总部城市，CEO名称，Forbes.com公司信息页面和年份

Answer 1

要获取行业的文本：

 String industryName= driver.findElement(By.xpath("//*[contains(text(),'Industry')]//following::dd[1]")).getText(); 

获取文字成立时间：

 String Founded= driver.findElement(By.xpath("//*[contains(text(),'Founded')]//following::dd[1]")).getText(); 

所以你只需要用下面的文本replaceString

 xpath = //*[contains(text(),'String')]//following::dd[1]