from selenium import webdriver
from PIL import Image
import time
import random
from selenium.webdriver import ActionChains
import cv2
from matplotlib import pyplot as plt
class slide():
#初始化
def __init__(self):
self.driver = webdriver.Chrome(executable_path=\'..\') #自己的驱动地址
self.driver.maximize_window()
self.trance =0
self.driver.get("https://passport.bilibili.com/login")
self.driver.find_element_by_id(\'login-username\').send_keys(\'....\')#用户名
self.driver.find_element_by_id(\'login-passwd\').send_keys(\'....\')#密码
self.driver.find_element_by_class_name(\'btn-login\').click()
print(\'login..........\')
time.sleep(3)
#有完整背景图的网页截图
def before_deal_image(self):
self.js1 = \'document.getElementsByClassName("geetest_canvas_fullbg")[0].style.display="block"\' #获得
self.driver.execute_script(self.js1)
time.sleep(2)
self.location = self.driver.find_element_by_class_name(\'geetest_widget\').location
self.size = self.driver.find_element_by_class_name(\'geetest_widget\').size
time.sleep(2)
self.driver.save_screenshot(\'capture1.png\') # 截取全屏
self.left = self.location[\'x\'] + 220 # 后面的数字自己调节控制截图包含验证码图片
self.top = self.location[\'y\'] + 57
self.right = self.location[\'x\'] + self.size[\'width\'] + 295
self.bottom = self.location[\'y\'] + self.size[\'height\'] + 113
# print(self.location, self.size)
self.im = Image.open(\'capture1.png\')
self.im = self.im.crop((self.left, self.top, self.right, self.bottom))
self.im.save(\'ele_capture1.png\')
# 滑块移动
def slide(self,num):
self.num=num
print(\'滑块应该移动距离------------->\',self.num)
self.button = self.driver.find_element_by_class_name(\'geetest_slider_button\')
#处理人机行为
first_distance = self.num/4*3
second_distance = self.num-first_distance-3
third_distance = self.num-second_distance-first_distance
ActionChains(self.driver).click_and_hold(self.button).move_by_offset(first_distance,random.random()).perform()
time.sleep(0.5)
ActionChains(self.driver).click_and_hold(self.button).move_by_offset(second_distance,random.random()).perform()
time.sleep(0.9)
ActionChains(self.driver).click_and_hold(self.button).move_by_offset(third_distance,random.random()).release().perform()
# 有缺口背景图的网页截图
def after_deal_image(self):
self.js2 = \'document.getElementsByClassName("geetest_canvas_fullbg")[0].style.display="none"\'
self.driver.execute_script(self.js2)
self.driver.save_screenshot(\'capture2.png\') #整张网页图
self.left = self.location[\'x\'] + 220#与上面相同
self.top = self.location[\'y\'] + 57
self.right = self.location[\'x\'] + self.size[\'width\'] + 295
self.bottom = self.location[\'y\'] + self.size[\'height\'] + 113
# print(self.location, self.size)
self.im = Image.open(\'capture2.png\')
self.im = self.im.crop((self.left, self.top, self.right, self.bottom))
self.im.save(\'ele_capture2.png\') #元素切割图
#---------------------获得移动距离-----------------#
#获得滑动距离
def slide_distance(self,image1, image2):
cut_image = Image.open(image2)
full_image = Image.open(image1)
threshold = 86 # 边界值颜色都为85,85,85
for i in range(75, cut_image.size[0]):
for j in range(0, cut_image.size[1]):
pixel1 = cut_image.getpixel((i, j))
pixel2 = full_image.getpixel((i, j))
res_R = abs(pixel1[0] - pixel2[0]) # 计算RGB差
res_G = abs(pixel1[1] - pixel2[1]) # 计算RGB差
res_B = abs(pixel1[2] - pixel2[2]) # 计算RGB差
if res_R > threshold and res_G > threshold and res_B > threshold:
print(i - 7)
return i - 7
#-------------------------------------处理相似度问题--------------------------------#
# size=(256, 256)
def classify_gray_hist(self,image1, image2, size=(328, 211)): #截图大小
# 先计算直方图
# 几个参数必须用方括号括起来
# 这里直接用灰度图计算直方图，所以是使用第一个通道，
# 也可以进行通道分离后，得到多个通道的直方图
# bins 取为16
image1 = cv2.resize(image1, size)
image2 = cv2.resize(image2, size)
hist1 = cv2.calcHist([image1], [0], None, [256], [0.0, 255.0]) #缺口背景图
hist2 = cv2.calcHist([image2], [0], None, [256], [0.0, 255.0]) #完整背景图
# 可以比较下直方图
# plt.plot(range(256),hist1,\'r\')
# plt.plot(range(256),hist2,\'b\')
# plt.show()
# 计算直方图的重合度
degree = 0
for i in range(75,len(hist1)):
if hist1[i] != hist2[i]:
degree = degree + (1 - abs(hist1[i] - hist2[i]) / max(hist1[i], hist2[i]))
else:
degree = degree + 1
degree = degree / len(hist1)
return degree
# -------------------------------------获得相似度-------------------------------#
def run0(self,image1, image2):
img1 = cv2.imread(image1)
# cv2.imshow(\'img1\', img1)
img2 = cv2.imread(image2)
# cv2.imshow(\'img2\', img2)
degree = self.classify_gray_hist(img1, img2)
print(\'两张图片相似度为。。。。。\',int(100 * degree[0])) #这是完整背景图和验证码图的相似度
cv2.waitKey(0)
return int(degree[0] * 100)
# 函数的启动
def run(self):
try:
self.before_deal_image()
self.after_deal_image()
self.num = self.slide_distance(\'ele_capture1.png\', \'ele_capture2.png\')
print(\'原始距离--------->\',self.num)
# \'ele_capture1.png\', \'ele_capture2.png\'
self.image1 = \'ele_capture1.png\'
self.image2 = \'ele_capture2.png\'
self.result = self.run0(self.image1, self.image2)
real_distance = self.num*(262/328) #这是实际截图大长度和验证码实际图片的的长度，自己更改
print(\'按照图像大小比列计算实际移动距离\',real_distance)
self.slide(real_distance)
time.sleep(6)
except:
print(\'login_out..............\')
time.sleep(7)
finally:
self.driver.quit()
print(\'程序运行结束\')
slide().run()
透明度0 和1 的色差85,86左右徘徊，R,G,B三值都相等，均为左边的85,86，因此。阀值86,85均可，即上面函数的 threshold，主要的难点就是缺口位置的查找。故此需要一个函数来测试是否符合下面介绍。
import cv2
from PIL import Image
def get_distance(cut_image, full_image):
cut_image = Image.open(cut_image) #缺口背景图
full_image = Image.open(full_image) #完整背景图
threshold = 86 #灰度值正好为86,86,86 这个是透明度的差值，边界值像素的RGB中的B值为准
for i in range(75, cut_image.size[0]): #75为滑块的截图最右边阴影到图片最左端的长度
for j in range(0, cut_image.size[1]):
pixel1 = cut_image.getpixel((i, j))
pixel2 = full_image.getpixel((i, j))
res_R = abs(pixel1[0] - pixel2[0]) # 计算RGB差
res_G = abs(pixel1[1] - pixel2[1]) # 计算RGB差
res_B = abs(pixel1[2] - pixel2[2]) # 计算RGB差
if res_R > threshold and res_G > threshold and res_B > threshold:
print(i-7)
return i-7
get_distance(\'ele_capture2.png\',\'ele_capture1.png\')
#\'ele_capture2.png\',\'ele_capture1.png\'（缺口背景图，完整背景图）
执行完第一个类，如果没登陆成功，就执行第上面这个，更改threshold ，并且将第一个类中的slide_distance（）函数替换，上面函数中75均为为滑块的截图最右边阴影到图片最左端的长度，这个得自己修改。
还有另一个方法就是移动滑块进行截图，86的色差变小，然后移动距离变小，移动一次进行图片相似度处理，与背景完全图相似度90%之上后将移动的距离保留，进行行为处理，模拟人的移动方法，然后移动滑块，也可以成功，这需要图像算法，我是不会，但我找到资料后测试过，也能通过验证。慢，但是准确度100%。
如果都能成功，就可以将driver设置为无头模式，让selenium不在界面上显示。
后续会出更好的爬虫博文。
喜欢就点个赞，萌萌哒。