Selenium FF WebDriver 遍历所有链接(另类爬虫)

时间:2023-03-09 08:00:53
Selenium FF WebDriver 遍历所有链接(另类爬虫)

请看这个页面,我想要找到某个公告的内容,必须一个一个打开链接,尼玛好多啊。

于是,我机智的使用selenium打开每一个链接,然后把公告内容写入txt

那需要做一下步奏

1.依次打开一个公告

2.切换focus到新窗口,找到公告内容,写到txt

3.关闭该窗口

4.切换到主窗口

5.当前页面遍历完,点击下一页

6.重复步奏1

Selenium FF WebDriver 遍历所有链接(另类爬虫)

由于下一页是一个很好用的flag,就可以当做循环条件,因为最后一页没有下一页的element

接下来要找到相关的的xpath

列表数目: count(//tr/td/a[starts-with(@href,'article_show.asp?ID=') and @title!='' ])
列表:      //tr/td/a[starts-with(@href,'article_show.asp?ID=') and @title!='' ]
下一页:   //div/a[text()='下一页']

selenium WebDriver测试网页时,点击target=”_blank”的链接,在打开新页面,切换到新窗口的

这要使用

String currentWindow = driver.getWindowHandle();//获取当前窗口句柄
Set<String> handles = driver.getWindowHandles();//获取所有窗口句

WebDriver window = driver.switchTo().window(it.next());//切换到新窗口

driver.switchTo().window(currentWindow);//回到原来页面

driver=driver.switchTo().window(driver.getWindowHandle()); //把下一页变成当前driver

currentWindow = driver.getWindowHandle();
//get all windows
Set<String> handles= driver.getWindowHandles();
for (String s : handles)
{
//current page is don't close
if (s.equals(currentWindow))
continue;
else
{
window =driver.switchTo().window(s);
}
window .close() ;
}
driver.switchTo().window(currentWindow);

具体代码

package com.packt.webdriver.chapter3;

import java.io.BufferedWriter;
import java.io.FileWriter;
import java.io.IOException;
import java.util.List;
import java.util.Set;
import java.util.concurrent.TimeUnit; import org.openqa.selenium.By;
import org.openqa.selenium.WebDriver;
import org.openqa.selenium.WebElement; public class TraversalAllLinks {
private static String currentWindow; public static void main(String[] args) { WebDriver driver=DriverFactory.getFirefoxDriver();
driver.get("http://www.lhgtj.gov.cn/article.asp?ClassID=86&page=1"); driver.manage().window().maximize();
driver.manage().timeouts().implicitlyWait(60, TimeUnit.SECONDS);
driver.manage().timeouts().pageLoadTimeout(60, TimeUnit.SECONDS);
WebElement nextPage=driver.findElement(By.xpath("//tr/td/a[@title='下一页']"));
while(nextPage.isDisplayed())
{ List<WebElement> links=driver.findElements(By.xpath("//tr/td/a[starts-with(@href,'article_show.asp?ID=') and @title!='' ]")); for(WebElement link:links)
{
WebDriver window;
System.out.println(link.getText());
try {
writeToTXT(link.getText());
} catch (IOException e1) {
// TODO Auto-generated catch block
e1.printStackTrace();
}
link.click();
currentWindow = driver.getWindowHandle();
//get all windows
Set<String> handles= driver.getWindowHandles();
for (String s : handles)
{
//current page is don't close
if (s.equals(currentWindow))
continue;
else
{
window =driver.switchTo().window(s);
window.manage().window().maximize();
window.manage().timeouts().implicitlyWait(60, TimeUnit.SECONDS);
window.manage().timeouts().pageLoadTimeout(60, TimeUnit.SECONDS);
//get all tables
List<WebElement> tbs=window.findElements(By.xpath("//tbody/tr/td/p"));
for(WebElement tb:tbs)
{
System.out.println(tb.getText());
try {
writeToTXT(tb.getText()+"\n");
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} }
//close the table window
window .close() ;
}
//swich to current window
driver.switchTo().window(currentWindow);
} }
// click next page
nextPage.click();
//set next page to current page
driver=driver.switchTo().window(driver.getWindowHandle());
driver.manage().window().maximize();
driver.manage().timeouts().implicitlyWait(60, TimeUnit.SECONDS);
driver.manage().timeouts().pageLoadTimeout(60, TimeUnit.SECONDS);
nextPage=driver.findElement(By.xpath("//tr/td/a[@title='下一页']")); } }
//write logs
public static void writeToTXT(String message) throws IOException
{
BufferedWriter bf = null;
try {
//set true ,avoid
bf = new BufferedWriter(new FileWriter("report.txt", true));
bf.write(message);
bf.flush(); } catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
finally
{
bf.close();
} } }

DriverFactory

public static WebDriver getFirefoxDriver()
{
try
{
WindowsUtils.tryToKillByName("firefox.exe");
}
catch(Exception e)
{
System.out.println("can not find firefox process");
}
File file=new File("d:\\firebug-2.0.4-fx.xpi");
FirefoxProfile profile = new FirefoxProfile(); try {
profile.addExtension(file);
profile.setPreference("extensions.firebug.currentVersion", "2.0.4");
profile.setPreference("extensions.firebug.allPagesActivation", "on");
} catch (IOException e3) {
// TODO Auto-generated catch block
e3.printStackTrace();
} WebDriver driver = new FirefoxDriver(profile);
return driver; }