赞
踩
目前所用的自动化框架是基于java写的,所以下载该缺口图片的代码也是java代码,后续的图片识别对比是基于python
String yzmPath="D:\\yanzhengma.png"; // wd为webdriver对象 TakesScreenshot takesScreenshot=(TakesScreenshot)wd; WebElement we = wd.findElement(By.xpath("//*[@id='slideVerify']/canvas[1]")); Point location = we.getLocation(); Dimension size = we.getSize(); // 创建全屏截图。 BufferedImage originalImage =ImageIO.read(new ByteArrayInputStream(takesScreenshot.getScreenshotAs(OutputType.BYTES))); // 截取webElement所在位置的子图。 BufferedImage croppedImage = originalImage.getSubimage( location.getX(), location.getY(), size.getWidth(), size.getHeight()); File f = new File(yzmPath); //写入保存图片 ImageIO.write(croppedImage,"PNG",f);
因为是公司内部项目,发现滑块验证码的图片总共只有三张,所以直接将三张完整的图片全部下载下来了,如果是做第三方的爬虫的话,可能需要找别的办法下载原图进行对比
因为将三张完整的图片全部下载下来了,所以下载了缺口图片后,首先要从三张图片中找到与缺口图片最相似的那张,如果直接有确定原图的可以跳过该步骤
# 对图片进行统一化处理 def get_thum(image, size=(64, 64), greyscale=False): # 利用image对图像大小重新设置, Image.ANTIALIAS为高质量的 image = image.resize(size, Image.ANTIALIAS) if greyscale: # 将图片转换为L模式,其为灰度图,其每个像素用8个bit表示 image = image.convert('L') return image # 计算图片的余弦距离 def image_similarity_vectors_via_numpy(image1, image2): image1 = get_thum(image1) image2 = get_thum(image2) images = [image1, image2] vectors = [] norms = [] for image in images: vector = [] for pixel_tuple in image.getdata(): vector.append(average(pixel_tuple)) vectors.append(vector) norms.append(linalg.norm(vector, 2)) a, b = vectors a_norm, b_norm = norms res = dot(a / a_norm, b / b_norm) return res def getSimilarityImgPath(resourcePath,pngName): """ # 获取预期图片中与验证码图片最相似图片的路径 :param resourcePath: 图片存放目录 :param pngName: 验证码图片 :return: """ verificationPath=os.path.join(resourcePath,pngName) verificationImg=Image.open(verificationPath) cosin=0 expectImgPath="" for root, dirs, files in os.walk(resourcePath): for f in files: # 缺口图片和目标图片存在同一个目录,所以排除掉自己 if f==pngName: continue tempPath=os.path.join(resourcePath,f) expectImg=Image.open(tempPath) temp=image_similarity_vectors_via_numpy(expectImg,verificationImg) if temp>cosin: cosin=temp expectImgPath=os.path.join(resourcePath,f) return expectImgPath
之前在网上找的算法,很多都是基于一个像素一个像素对比的,很容易出现误判,所以想了一个思路就是,将图片分割成N多个10x10的小图片,然后逐步对比每个小图片的相似度,当相似度超过一定数值时,则判断是缺口的位置。 注:(需要保持原始图片和缺口图片的图片尺寸一致)
def pil_image_similarity(image1, image2): ''' 对比图片相似度 :param image1: :param image2: :return: ''' h1 = image1.histogram() h2 = image2.histogram() rms = math.sqrt(reduce(operator.add, list(map(lambda a,b: (a-b)**2, h1, h2)))/len(h1)) return rms def diffImg(image1,image2): # 把左侧区域,顶部和右上角刷新按钮都截掉,具体说明可以看下图 # 因为我的原始图片大小为310*160,所以具体需要裁剪的距离可以根据自己的实际情况调整 image1 = image1.crop((60, 10, 280, 160)) image2 = image2.crop((60, 10, 280, 160)) # 将大图分割成10x10的多个小图,逐一进行相似度对比 for x in range(int(image1.size[0]/10)): for y in range(int(image1.size[1]/10)): tempImage1=image1.crop(((x-1)*10,(y-1)*10,x*10,y*10)) tempImage2=image2.crop(((x-1)*10,(y-1)*10,x*10,y*10)) rms=pil_image_similarity(tempImage1,tempImage2) # 按照实践,目前当返回的差异度大于2时,就是差异较大的区域 if rms>2: # 找到差异度大的图片块之后,将左侧裁掉的距离加上该图片所在的x距离,即为需要滑动的距离 return 60+(x-1)*10
代码中间对图片做了裁剪,是裁掉了下图的区域
左侧的原始滑块所在的区域,顶部经常会出现一个黑边也裁掉了,右侧的刷新按钮也裁掉了
import math import operator import os from functools import reduce from PIL import Image from numpy import average, dot, linalg # 对图片进行统一化处理 def get_thum(image, size=(64, 64), greyscale=False): # 利用image对图像大小重新设置, Image.ANTIALIAS为高质量的 image = image.resize(size, Image.ANTIALIAS) if greyscale: # 将图片转换为L模式,其为灰度图,其每个像素用8个bit表示 image = image.convert('L') return image # 计算图片的余弦距离 def image_similarity_vectors_via_numpy(image1, image2): image1 = get_thum(image1) image2 = get_thum(image2) images = [image1, image2] vectors = [] norms = [] for image in images: vector = [] for pixel_tuple in image.getdata(): vector.append(average(pixel_tuple)) vectors.append(vector) norms.append(linalg.norm(vector, 2)) a, b = vectors a_norm, b_norm = norms res = dot(a / a_norm, b / b_norm) return res def getSimilarityImgPath(resourcePath,pngName): """ # 获取预期图片中与验证码图片最相似图片的路径 :param resourcePath: 图片存放目录 :param pngName: 验证码图片 :return: """ verificationPath=os.path.join(resourcePath,pngName) verificationImg=Image.open(verificationPath) cosin=0 expectImgPath="" for root, dirs, files in os.walk(resourcePath): for f in files: # 排除掉自己 if f==pngName: continue tempPath=os.path.join(resourcePath,f) expectImg=Image.open(tempPath) temp=image_similarity_vectors_via_numpy(expectImg,verificationImg) if temp>cosin: cosin=temp expectImgPath=os.path.join(resourcePath,f) return expectImgPath def pil_image_similarity(image1, image2): ''' 对比图片相似度 :param image1: :param image2: :return: ''' h1 = image1.histogram() h2 = image2.histogram() rms = math.sqrt(reduce(operator.add, list(map(lambda a,b: (a-b)**2, h1, h2)))/len(h1)) return rms def diffImg(image1,image2): # 把左侧区域,顶部和右上角刷新按钮都截掉 image1 = image1.crop((60, 10, 280, 160)) image2 = image2.crop((60, 10, 280, 160)) # 将大图分割成10x10的多个小图,逐一进行相似度对比 for x in range(int(image1.size[0]/10)): for y in range(int(image1.size[1]/10)): tempImage1=image1.crop(((x-1)*10,(y-1)*10,x*10,y*10)) tempImage2=image2.crop(((x-1)*10,(y-1)*10,x*10,y*10)) rms=pil_image_similarity(tempImage1,tempImage2) # 按照实践,目前当返回的差异度大于2时,就是差异较大的区域 if rms>2: # 找到差异度大的图片块之后,将左侧裁掉的距离加上该图片所在的x距离,即为需要滑动的距离 return 60+(x-1)*10 return 0 if __name__ == '__main__': filePath = os.path.dirname(os.path.dirname(__file__)) resourcePath = os.path.join(filePath, "resource") # 缺口图片 verificationPath = os.path.join(resourcePath, "quekou.png") verificationImg = Image.open(verificationPath) # 原始完整图片 expectPath=getSimilarityImgPath(resourcePath,"quekou.png") expectImg=Image.open(expectPath) # 打印缺口距离 print(diffImg(verificationImg,expectImg))
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。