from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait # 等待元素加载的
from selenium.webdriver.common.action_chains import ActionChains #拖拽
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException, NoSuchElementException
from selenium.webdriver.common.by import By
from PIL import Image
import requests
import time
import re
import random
from io import BytesIO
def merge_image(image_file,location_list):
"""
拼接图片
:param image_file:
:param location_list:
:return:
"""
im = Image.open(image_file)
im.save('code.jpg')
new_im = Image.new('RGB',(260,116))
# 把无序的图片 切成52张小图片
im_list_upper = []
im_list_down = []
# print(location_list)
for location in location_list:
# print(location['y'])
if location['y'] == -58: # 上半边
im_list_upper.append(im.crop((abs(location['x']),58,abs(location['x'])+10,116)))
if location['y'] == 0: # 下半边
im_list_down.append(im.crop((abs(location['x']),0,abs(location['x'])+10,58)))
x_offset = 0
for im in im_list_upper:
new_im.paste(im,(x_offset,0)) # 把小图片放到 新的空白图片上
x_offset += im.size[0]
x_offset = 0
for im in im_list_down:
new_im.paste(im,(x_offset,58))
x_offset += im.size[0]
# new_im.show()
return new_im
def get_image(driver,div_path):
'''
下载无序的图片 然后进行拼接 获得完整的图片
:param driver:
:param div_path:
:return:
'''
time.sleep(2)
background_images = driver.find_elements_by_xpath(div_path)
location_list = []
for background_image in background_images:
location = {}
result = re.findall('background-image: url\("(.*?)"\); background-position: (.*?)px (.*?)px;',background_image.get_attribute('style'))
# print(result)
location['x'] = int(result[0][1])
location['y'] = int(result[0][2])
image_url = result[0][0]
location_list.append(location)
print('==================================')
image_url = image_url.replace('webp','jpg')
# '替换url http://static.geetest.com/pictures/gt/579066de6/579066de6.webp'
image_result = requests.get(image_url).content
image_file = BytesIO(image_result) # 是一张无序的图片
image = merge_image(image_file,location_list)
return image
def get_track(distance):
'''
拿到移动轨迹，模仿人的滑动行为，先匀加速后匀减速
匀变速运动基本公式：
①v=v0+at
②s=v0t+(1/2)at²
③v²-v0²=2as
:param distance: 需要移动的距离
:return: 存放每0.2秒移动的距离
'''
# 移动轨迹
track = []
# 当前位移
current = 0
# 减速阈值
mid = distance * 8 / 10
# 计算间隔
t = 0.2
# t = random.randint(2, 3) / 10
# 初速度
v = 0
while current < distance:
if current < mid:
# 加速度为正4
a = 3
else:
# 加速度为负2
a = -2
# 初速度v0
v0 = v
# 当前速度v = v0 + at
v = v0 + a * t
# 移动距离x = v0t + 1/2 * a * t^2
move = v0 * t + 1 / 2 * a * t * t
# 当前位移
current += move
# 加入轨迹
track.append(round(move))
return track
def get_distance(image1,image2):
'''
拿到滑动验证码需要移动的距离
:param image1:没有缺口的图片对象
:param image2:带缺口的图片对象
:return:需要移动的距离
'''
# print('size', image1.size)
left = 50
for i in range(0,image1.size[0]): # 260
for j in range(0,image1.size[1]): # 160
if not is_pixel_equal(image1, image2, i, j):
left = i
return left
# return left
# pixel1 = image1.getpixel((i,j))
# pixel2 = image2.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:
# return i +1 # 需要移动的距离
def is_pixel_equal(image1, image2, x, y):
"""
判断两个像素是否相同
:param image1: 图片1
:param image2: 图片2
:param x: 位置x
:param y: 位置y
:return: 像素是否相同
"""
# 取两个图片的像素点
pixel1 = image1.load()[x, y]
pixel2 = image2.load()[x, y]
threshold = 60
if abs(pixel1[0] - pixel2[0]) < threshold and abs(pixel1[1] - pixel2[1]) < threshold and abs(
pixel1[2] - pixel2[2]) < threshold:
return True
else:
return False
def main_check_code(driver, element):
"""
拖动识别验证码
:param driver:
:param element:
:return:
"""
image1 = get_image(driver, '//div[@class="gt_cut_bg gt_show"]/div')
image2 = get_image(driver, '//div[@class="gt_cut_fullbg gt_show"]/div')
# 图片上 缺口的位置的x坐标
# 2 对比两张图片的所有RBG像素点，得到不一样像素点的x值，即要移动的距离
l = get_distance(image2,image1)
print('l=',l)
# 3 获得移动轨迹
track_list = get_track(l-8)
print('第一步,点击滑动按钮')
ActionChains(driver).click_and_hold(on_element=element).perform() # 点击鼠标左键，按住不放
# time.sleep(1)
print('第二步,拖动元素')
for track in track_list:
ActionChains(driver).move_by_offset(xoffset=track, yoffset=0).perform() # 鼠标移动到距离当前位置（x,y）
time.sleep(0.3)
# if l>100:
# ActionChains(driver).move_by_offset(xoffset=-random.randint(2,5), yoffset=0).perform()
# time.sleep(1)
print('第三步,释放鼠标')
ActionChains(driver).release(on_element=element).perform()
# time.sleep(5)
def main_check_slider(driver):
"""
检查滑动按钮是否加载
:param driver:
:return:
"""
while True:
try :
driver.get('http://www.cnbaowen.net/api/geetest/')
element = WebDriverWait(driver, 30, 0.5).until(EC.element_to_be_clickable((By.CLASS_NAME, 'gt_slider_knob')))
if element:
return element
except TimeoutException as e:
print('超时错误，继续')
time.sleep(5)
if __name__ == '__main__':
try:
count = 6 # 最多识别6次
driver = webdriver.Chrome(executable_path=r"C:\software\Python37\chromedriver_win32\chromedriver.exe")
# 等待滑动按钮加载完成
element = main_check_slider(driver)
while count > 0:
main_check_code(driver,element)
time.sleep(2)
try:
success_element = (By.CSS_SELECTOR, '.gt_holder .gt_ajax_tip.gt_success')
# 得到成功标志
print('suc=',driver.find_element_by_css_selector('.gt_holder .gt_ajax_tip.gt_success'))
success_images = WebDriverWait(driver, 20).until(EC.presence_of_element_located(success_element))
if success_images:
print('成功识别！！！！！！')
count = 0
break
except NoSuchElementException as e:
print('识别错误，继续')
count -= 1
time.sleep(2)
else:
print('too many attempt check code ')
exit('退出程序')
finally:
driver.close()
网友评论