0
捕捉來自多個網頁的數據頁面:http://www.forbes.com/companies/icbc/需要使用硒
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();
}
}
我想捕捉排名,公司,國家,銷售量,銷售額排名,利潤,排名利潤,資產,等級的資產,市場價值,排名市場價值,行業,公司成立,公司網站,員工,總部城,CEO名稱,Forbes.com公司信息頁面和年
而你的問題是......? – Guy
我需要捕捉Industry,Established等,但它們具有相同的標籤。我應該怎樣使用XPath?如果XPath我怎麼得到它? – Parithi