软件测试

利用selenium截取站内所有的页面截图

需求：截取一个站点内所有的页面的截图，比如wordpress所有文章页

实现思路：获取页面所有a标签，获取a标签的链接href，判读是否为本站的链接，是的话截图，然后再递归遍历

import org.apache.commons.io.FileUtils; import org.openqa.selenium.*; import org.openqa.selenium.firefox.FirefoxDriver; import org.openqa.selenium.htmlunit.HtmlUnitDriver; import java.io.File; import java.io.IOException; import java.io.UnsupportedEncodingException; import java.net.MalformedURLException; import java.net.URL; import java.util.List; import java.util.regex.Matcher; import java.util.regex.Pattern; /** * Created by zsn on 2015/4/7. */ public class WebsiteScreenshot { public static void main(String[] args) { getAElement("http://www.izsn.cn"); } private static void getAElement(String url){ WebDriver driver = new FirefoxDriver(); //不能使用HtmlUnitDriver，因为HtmlUnitDriver不支持截图 // 具体解释->https://code.google.com/p/selenium/issues/detail?id=1361 driver.get(url); //创建保存目录 File saveDir = new File("./screenshot"); if(!saveDir.exists()) saveDir.mkdir(); //保存截图 pickScreenshot(driver, url); //获得网页所有a标签 List<WebElement> list = driver.findElements(By.tagName("a")); for(WebElement element : list){ try{ String href = element.getAttribute("href"); System.out.print("current url:"+href+"\n"); //是否为站内链接 if(getDomain(url).equals(getDomain(href))){ if(!isExist(href)){ //递归执行 getAElement(href); } } }catch (Exception e){ e.printStackTrace(); } } } /** * 获取网页截图 * @param driver * @param url */ private static void pickScreenshot(WebDriver driver, String url){ TakesScreenshot screenshot = (TakesScreenshot) driver; File file = screenshot.getScreenshotAs(OutputType.FILE); try { //将文件保存在当前目录下screenshot文件夹下 String fileName = "./screenshot/"+java.net.URLEncoder.encode(url,"utf-8")+".jpg"; FileUtils.copyFile(file, new File(fileName)); } catch (IOException e) { e.printStackTrace(); }finally { driver.close(); } } /** * 截图是否存在，不重复截图 * @param href * @return */ private static boolean isExist(String href){ try { String fileName = "./screenshot/"+java.net.URLEncoder.encode(href,"utf-8")+".jpg"; return new File(fileName).exists(); } catch (UnsupportedEncodingException e) { e.printStackTrace(); } return false; } /** * 获取url中的域名 * @param url * @return */ private static String getDomain(String url){ try { return new URL(url).getHost(); } catch (MalformedURLException e) { e.printStackTrace(); } return ""; } }

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104

import org.apache.commons.io.FileUtils; import org.openqa.selenium.*; import org.openqa.selenium.firefox.FirefoxDriver; import org.openqa.selenium.htmlunit.HtmlUnitDriver;   import java.io.File; import java.io.IOException; import java.io.UnsupportedEncodingException; import java.net.MalformedURLException; import java.net.URL; import java.util.List; import java.util.regex.Matcher; import java.util.regex.Pattern;   /** * Created by zsn on 2015/4/7. */ public class WebsiteScreenshot {       public static void main(String[] args) {         getAElement("http://www.izsn.cn");     }         private static void getAElement(String url){         WebDriver driver =  new FirefoxDriver();         //不能使用HtmlUnitDriver，因为HtmlUnitDriver不支持截图         // 具体解释->https://code.google.com/p/selenium/issues/detail?id=1361         driver.get(url);           //创建保存目录         File saveDir = new File("./screenshot");         if(!saveDir.exists()) saveDir.mkdir();           //保存截图         pickScreenshot(driver, url);           //获得网页所有a标签         List<WebElement> list = driver.findElements(By.tagName("a"));         for(WebElement element : list){             try{                 String href = element.getAttribute("href");                 System.out.print("current url:"+href+"\n");                 //是否为站内链接                 if(getDomain(url).equals(getDomain(href))){                     if(!isExist(href)){                         //递归执行                         getAElement(href);                     }                 }             }catch (Exception e){                 e.printStackTrace();             }         }     }       /**      * 获取网页截图      * @param driver      * @param url      */     private static void pickScreenshot(WebDriver driver, String url){         TakesScreenshot screenshot = (TakesScreenshot) driver;         File file = screenshot.getScreenshotAs(OutputType.FILE);         try {             //将文件保存在当前目录下screenshot文件夹下             String fileName = "./screenshot/"+java.net.URLEncoder.encode(url,"utf-8")+".jpg";             FileUtils.copyFile(file, new File(fileName));         } catch (IOException e) {             e.printStackTrace();         }finally {             driver.close();         }     }       /**      * 截图是否存在，不重复截图      * @param href      * @return      */     private static boolean isExist(String href){         try {             String fileName = "./screenshot/"+java.net.URLEncoder.encode(href,"utf-8")+".jpg";             return new File(fileName).exists();         } catch (UnsupportedEncodingException e) {             e.printStackTrace();         }         return false;     }       /**      * 获取url中的域名      * @param url      * @return      */     private static String getDomain(String url){         try {             return new URL(url).getHost();         } catch (MalformedURLException e) {             e.printStackTrace();         }         return "";     } }




转载请注明：软件测试 » 利用selenium截取站内所有的页面截图

喜欢 0