Java selenium處理極驗滑動驗證碼示例
要爬取一個網(wǎng)站遇到了極驗的驗證碼,這周都在想著怎么破解這個,網(wǎng)上搜了好多知乎上看到有人問了這問題,我按照這思路去大概實現(xiàn)了一下。

1.使用htmlunit(這種方式我沒成功,模擬鼠標拖拽后軌跡沒生成,可以跳過)
我用的是java,我首先先想到了用直接用htmlunit,我做了點初始化
private void initWebClient() {
if (webClient != null) {
return;
}
webClient = new WebClient(BrowserVersion.FIREFOX_24);
webClient.getOptions().setProxyConfig(new ProxyConfig("127.0.0.1",8888));
webClient.getOptions().setActiveXNative(true);
webClient.getOptions().setUseInsecureSSL(true); // 配置證書
webClient.getOptions().setJavaScriptEnabled(true);
webClient.getOptions().setCssEnabled(true);
webClient.setCssErrorHandler(new SilentCssErrorHandler());
webClient.getOptions().setThrowExceptionOnScriptError(false);
webClient.getOptions().setThrowExceptionOnFailingStatusCode(false);
CookieManager cookieManager = new CookieManager();
List<org.apache.http.cookie.Cookie> httpCookies = client.getCookies();//其方式獲取的cookie
for (org.apache.http.cookie.Cookie cookie : httpCookies) {
cookieManager.addCookie(new com.gargoylesoftware.htmlunit.util.Cookie(cookie));
}
webClient.setCookieManager(cookieManager);
}
初始化代理,cookie..然后就能正常調(diào)用了
HtmlPage page = webClient.getPage("http://www.qixin.com/login");//企信寶
gePageInfor(page);
下面就是我獲取圖片,還原圖片并且模擬拖拽,(這里我覺得是有些問題的,可能是拖拽我模擬的不對導致觸發(fā)的js并沒有生成正確的軌跡,還請大家?guī)兔纯茨睦镥e了)
private void gePageInfor(HtmlPage page) {
String[] img_slice={"div", "class", "gt_cut_fullbg_slice"};
String[] img_bg_slice={"div", "class", "gt_cut_bg_slice"};
HtmlDivision div = (HtmlDivision) page.getElementById("captcha");
int deCAPTCHA = 0;
try {
byte[] img_slice_binary = client.get(getImgUrl(img_slice, div, true)).getBinary();//獲取圖片byte
byte[] img_bg_slice_binary = client.get(getImgUrl(img_bg_slice, div, false)).getBinary();
//獲取還原后的圖片
BufferedImage geetestImg = ImgTest.getGeetestImg(img_slice_binary, ImgTest.imgArray);
BufferedImage geetestImg2 = ImgTest.getGeetestImg(img_bg_slice_binary, ImgTest.imgArray);
//獲得圖片移動位置(目前還有問題,需改用第三方圖片識別)
deCAPTCHA =ImgTest.deCAPTCHA(geetestImg,geetestImg2);
System.out.println(deCAPTCHA);
} catch (IOException | FetchException e) {
e.printStackTrace();
}
HtmlDivision div_slider_knob = get_div_slider_knob(page,"gt_slider_knob gt_show");//獲取要移動div
HtmlPage mouseOver = (HtmlPage) div_slider_knob.mouseOver();
HtmlPage mouseDownPage = (HtmlPage)div_slider_knob.mouseDown();
div_slider_knob = get_div_slider_knob(mouseDownPage,"gt_slider_knob gt_show moving");
mouseMoveX(deCAPTCHA, div_slider_knob, mouseDownPage);
HtmlPage newPage =(HtmlPage)div_slider_knob.mouseOver();
// newPage =(HtmlPage)div_slider_knob.mouseDown();
System.out.println(newPage.asXml());
div = (HtmlDivision)newPage.getElementById("captcha");
HtmlElement htmlElement = div.getElementsByAttribute("div", "class", "gt_slice gt_show moving").get(0);
System.out.println(htmlElement);
newPage =(HtmlPage)div_slider_knob.mouseUp();//觸發(fā)js,軌跡沒有生成
System.out.println("---------------");
System.out.println(newPage.asXml());
if (newPage.getElementById("captcha")!=null) {//錯誤重試
//gePageInfor(newPage);
}
}
private void mouseMoveX(int deCAPTCHA, HtmlDivision div_slider_knob, HtmlPage mouseDown) {
MouseEvent mouseEvent = new MouseEvent(div_slider_knob, MouseEvent.TYPE_MOUSE_MOVE, false, false, false, MouseEvent.BUTTON_LEFT);
mouseEvent.setClientX( mouseEvent.getClientX()+((deCAPTCHA!=0)?deCAPTCHA:99)); //移動x坐標
ScriptResult scriptResult = mouseDown.getDocumentElement().fireEvent(mouseEvent);
}
private HtmlDivision get_div_slider_knob(HtmlPage page,String classString) {
return (HtmlDivision)(((HtmlDivision) page.getElementById("captcha")).getElementsByAttribute("div", "class", classString).get(0));
}
private String getImgUrl(String[] img_slice, HtmlDivision div, boolean isNeedCheckPostion) {
String url ="";
int[] postion = new int[2];
boolean empty = div.getElementsByAttribute(img_slice[0],img_slice[1],img_slice[2]).isEmpty();
if (div.hasChildNodes() && !empty) {
List<HtmlElement> elementsByAttribute = div.getElementsByAttribute(img_slice[0],img_slice[1],img_slice[2]);
for(int i = 0;i<elementsByAttribute.size();i++){
HtmlDivision div_img = (HtmlDivision)elementsByAttribute.get(i);
String style = div_img.getAttribute("style");
String[] imge_url_position = style.split(";");
if(StringUtils.isBlank(url)){//確認url
url = StringUtils.replacePattern(imge_url_position[0], ".*\\(", "").replace(")", "");
}
if (isNeedCheckPostion) {//確認圖片切割postion,兩張圖切割方式一樣 background-position: -157px -58px
// String[] positionS = StringUtils.split(StringUtils.remove(imge_url_position[1], "px").replace("-", "").replaceAll(".*:", ""), null);
String[] positionS = StringUtils.split(StringUtils.removePattern(imge_url_position[1], "[^\\d+ \\s]"),null);
postion[0] = Integer.parseInt(positionS[0]);
postion[1] = Integer.parseInt(positionS[1]);
int[] is = ImgTest.imgArray[i];
if (is[0]!=postion[0]||is[1]!=postion[1]) {
logger.debug("更新分割postion");
ImgTest.imgArray[i] = postion;
}
System.out.println(ImgTest.imgArray);
isNeedCheckPostion= false;
}
}
}
return url;
}
對比圖片獲取位移方法(deCAPTCHA)是錯的我就不放代碼了,下面是其中還原圖片用的方法,目前是其實審查元素后你就明白怎么還原這個圖片了,這里是每次讀的10px,58px
public static BufferedImage getGeetestImg(byte[] binary, int[][] imgArray) throws IOException {
BufferedImage img = ImageIO.read(new ByteArrayInputStream(binary));
List<BufferedImage> list = new ArrayList<>();
for (int i=0;i< imgArray.length;i++) {
BufferedImage subimage = img.getSubimage(imgArray[i][0], imgArray[i][1], 10, 58);
list.add(subimage);
// ImageIO.write(subimage, "jpg", new File("d:\\image\\imgs"+i+".jpg"));
}
BufferedImage mergeImageUp = null;
BufferedImage mergeImageDown = null;
int mid = list.size()>>>1;
for (int i = 0; i <mid-1 ; i++) {
mergeImageUp = mergeImage(mergeImageUp==null?list.get(i):mergeImageUp, list.get(i+1), true);
}
for(int i = mid;i<list.size()-1;i++){
mergeImageDown = mergeImage(mergeImageDown==null?list.get(i):mergeImageDown,list.get(i+1), true);
}
img = mergeImage(mergeImageUp, mergeImageDown, false);
return img;
}
public static BufferedImage mergeImage(BufferedImage img1,
BufferedImage img2, boolean isHorizontal) throws IOException {
int w1 = img1.getWidth();
int h1 = img1.getHeight();
int w2 = img2.getWidth();
int h2 = img2.getHeight();
// 從圖片中讀取RGB
int[] ImageArrayOne = new int[w1 * h1];
ImageArrayOne = img1.getRGB(0, 0, w1, h1, ImageArrayOne, 0, w1); // 逐行掃描圖像中各個像素的RGB到數(shù)組中
int[] ImageArrayTwo = new int[w2 * h2];
ImageArrayTwo = img2.getRGB(0, 0, w2, h2, ImageArrayTwo, 0, w2);
// 生成新圖片
BufferedImage DestImage = null;
if (isHorizontal) { // 水平方向合并
DestImage = new BufferedImage(w1+w2, h1, BufferedImage.TYPE_INT_RGB);
DestImage.setRGB(0, 0, w1, h1, ImageArrayOne, 0, w1); // 設(shè)置上半部分或左半部分的RGB
DestImage.setRGB(w1, 0, w2, h2, ImageArrayTwo, 0, w2);
} else { // 垂直方向合并
DestImage = new BufferedImage(w1, h1 + h2,
BufferedImage.TYPE_INT_RGB);
DestImage.setRGB(0, 0, w1, h1, ImageArrayOne, 0, w1); // 設(shè)置上半部分或左半部分的RGB
DestImage.setRGB(0, h1, w2, h2, ImageArrayTwo, 0, w2); // 設(shè)置下半部分的RGB
}
return DestImage;
}
2.使用selenium
后來我想著是我模擬鼠標這個動作哪里有問題,我就又找到了selenium(2.42.2),他也能操作htmlunit關(guān)鍵他的鼠標動作好像封裝比較完全
但是我嘗試了以后發(fā)現(xiàn)了這個,HtmlUnitMouse這個動作沒有實現(xiàn)
public void mouseMove(Coordinates where, long xOffset, long yOffset) {
throw new UnsupportedOperationException("Moving to arbitrary X,Y coordinates not supported.");
}
好吧,于是調(diào)用chrome吧
System.setProperty("webdriver.chrome.driver","C:\\chromedriver.exe");
Proxy proxy = new Proxy();
//設(shè)置代理服務(wù)器地址
proxy.setHttpProxy("127.0.0.1:8888");
// DesiredCapabilities capabilities = DesiredCapabilities.htmlUnitWithJs();
DesiredCapabilities capabilities = DesiredCapabilities.chrome();
capabilities.setCapability(CapabilityType.PROXY, proxy);
// final WebDriver driver = new HtmlUnitDriver(capabilities);
WebDriver driver = new ChromeDriver(capabilities);
driver.get("http://www.qixin.com/login");
driver.manage().timeouts().implicitlyWait(10, TimeUnit.SECONDS);
checkPage(driver,"return $('.gt_cut_fullbg_slice');");
// 獲取 網(wǎng)頁的 title
System.out.println("1 Page title is: " + driver.getTitle());
// 通過 id 找到 input 的 DOM
String pageSource = driver.getPageSource();
System.out.println(pageSource);
org.openqa.selenium.JavascriptExecutor executor = (org.openqa.selenium.JavascriptExecutor)driver;
boolean equals = executor.executeScript("return document.readyState").equals("complete");
int moveX =99;//移動位置
if (equals) {
WebElement element = driver.findElement(By.className("gt_slider_knob"));//(".gt_slider_knob"));
Point location = element.getLocation();
element.getSize();
Actions action = new Actions(driver);
// action.clickAndHold().perform();// 鼠標在當前位置點擊后不釋放
// action.clickAndHold(element).perform();// 鼠標在 onElement 元素的位置點擊后不釋放
// action.clickAndHold(element).moveByOffset(location.x+99,location.y).release().perform(); //選中source元素->拖放到(xOffset,yOffset)位置->釋放左鍵
action.dragAndDropBy(element, location.x+moveX,location.y).perform();
// action.dragAndDrop(element,newelement).perform();
pageSource = driver.getPageSource();
}
//更新cookie
Set<org.openqa.selenium.Cookie> cookies = driver.manage().getCookies();
Set<Cookie> cookies2 = new HashSet<>();
for (org.openqa.selenium.Cookie cookie : cookies) {
cookies2.add((Cookie) new Cookie(cookie.getDomain(), cookie.getName(), cookie.getValue(), cookie.getPath(), cookie.getExpiry(), true));
}
for (Cookie cookie : cookies2) {
org.apache.http.cookie.Cookie httpClient = cookie.toHttpClient();
}
System.out.println(pageSource);
這樣提交的表單確實是有軌跡的,這里移動位置我先寫了個固定值,可以由上面圖片還原,以及一些開源的圖片識別工具識別出位置。以上應(yīng)該就能解決這個滑動驗證碼了
以上就是本文的全部內(nèi)容,希望對大家的學習有所幫助,也希望大家多多支持腳本之家。
相關(guān)文章
基于Spring定時任務(wù)的fixedRate和fixedDelay的區(qū)別
這篇文章主要介紹了基于Spring定時任務(wù)的fixedRate和fixedDelay的區(qū)別,具有很好的參考價值,希望對大家有所幫助。如有錯誤或未考慮完全的地方,望不吝賜教2021-10-10
Java創(chuàng)建線程的七種方法總結(jié)(全網(wǎng)最全面)
線程是Java中的基本執(zhí)行單元,它允許程序在同一時間執(zhí)行多個任務(wù),下面這篇文章主要給大家總結(jié)介紹了關(guān)于Java創(chuàng)建線程的七種方法,文中通過實例代碼將這七種方法介紹的非常詳細,需要的朋友可以參考下2023-05-05
SpringBoot中使用MyBatis-Plus實現(xiàn)分頁接口的詳細教程
MyBatis-Plus是一個MyBatis的增強工具,在MyBatis的基礎(chǔ)上只做增強不做改變,為簡化開發(fā)、提高效率而生,在SpringBoot項目中使用MyBatis-Plus可以大大簡化分頁邏輯的編寫,本文將介紹如何在 SpringBoot項目中使用MyBatis-Plus實現(xiàn)分頁接口2024-03-03
MybatisGenerator文件生成不出對應(yīng)文件的問題
本文介紹了使用MybatisGenerator生成文件時遇到的問題及解決方法,主要步驟包括檢查目標表是否存在、是否能連接到數(shù)據(jù)庫、配置生成器的路徑等,通過在項目結(jié)構(gòu)中引入相應(yīng)的jar包,并在GeneratorSqlmap.java文件中運行,可以成功生成對應(yīng)的文件2025-01-01
Java實現(xiàn)批量導入excel表格數(shù)據(jù)到數(shù)據(jù)庫中的方法
這篇文章主要介紹了Java實現(xiàn)批量導入excel表格數(shù)據(jù)到數(shù)據(jù)庫中的方法,結(jié)合實例形式詳細分析了java導入Excel數(shù)據(jù)到數(shù)據(jù)庫的具體步驟與相關(guān)操作技巧,需要的朋友可以參考下2017-10-10

