python+selenium滑動式驗證碼:
實列：
# -*- coding:utf-8 -*-
from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.common.action_chains import ActionChains
import PIL.Image as image
from PIL import Image,ImageEnhance
import time,re, random
import requests
try:
from StringIO import StringIO
except ImportError:
from io import StringIO
#爬蟲模擬的瀏覽器頭部信息
agent = "Mozilla/5.0 (Windows NT 5.1; rv:33.0) Gecko/20100101 Firefox/33.0"
headers = {
"User-Agent": agent
}
# 根據位置對圖片進行合並還原
# filename:圖片
# location_list:圖片位置
#內部兩個圖片處理函數的介紹
#crop函數帶的參數為(起始點的橫坐標，起始點的縱坐標，寬度，高度）
#paste函數的參數為(需要修改的圖片，粘貼的起始點的橫坐標，粘貼的起始點的縱坐標）
def get_merge_image(filename,location_list):
#打開圖片文件
im = image.open(filename)
#創建新的圖片,大小為260*116
new_im = image.new("RGB", (260,116))
im_list_upper=[]
im_list_down=[]
# 拷貝圖片
for location in location_list:
#上面的圖片
if location["y"]==-58:
im_list_upper.append(im.crop((abs(location["x"]),58,abs(location["x"])+10,166)))
#下面的圖片
if location["y"]==0:
im_list_down.append(im.crop((abs(location["x"]),0,abs(location["x"])+10,58)))
new_im = image.new("RGB", (260,116))
x_offset = 0
#黏貼圖片
for im in im_list_upper:
new_im.paste(im, (x_offset,0))
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]
return new_im
#對比RGB值
def is_similar(image1,image2,x,y):
pass
#獲取指定位置的RGB值
pixel1=image1.getpixel((x,y))
pixel2=image2.getpixel((x,y))
for i in range(0,3):
# 如果相差超過50則就認為找到了缺口的位置
if abs(pixel1[i]-pixel2[i])>=50:
return False
return True
#計算缺口的位置
def get_diff_location(image1,image2):
i=0
# 兩張原始圖的大小都是相同的260*116
# 那就通過兩個for循環依次對比每個像素點的RGB值
# 如果相差超過50則就認為找到了缺口的位置
for i in range(62,260):#有人可能看不懂這個位置為什么要從62開始看最后一張圖（圖：3）
for j in range(0,116):
if is_similar(image1,image2,i,j)==False:
return i
#根據缺口的位置模擬x軸移動的軌跡
def get_track(length):
pass
list=[]
#間隔通過隨機范圍函數來獲得,每次移動一步或者兩步
x=random.randint(1,3)
#生成軌跡並保存到list內
while length-x>=5:
list.append(x)
length=length-x
x=random.randint(1,3)
#最后五步都是一步步移動
for i in range(length):
list.append(1)
return list
#滑動驗證碼破解程序
def main():
#打開火狐瀏覽器
driver = webdriver.Firefox()
#用火狐瀏覽器打開網頁
driver.get("https://account.geetest.com/register")
time.sleep(2)
driver.find_element_by_xpath('//*[@id="captcha"]/div/div[3]/span[2]').click()
time.sleep(5)
driver.get_screenshot_as_file("D:/test2/滑動驗證/img.jpg")#對整個頁面截圖
imgelement = driver.find_element_by_xpath('/html/body/div[2]/div[2]/div[1]/div/div[2]/div[1]/div/a/div[1]/canvas') # 定位驗證碼
location = imgelement.location # 獲取驗證碼x,y軸坐標
size = imgelement.size # 獲取驗證碼的長寬
rangle = (int(location['x'] ), int(location['y']), int(location['x'] + size['width']),
int(location['y'] + size['height'])) # 寫成我們需要截取的位置坐標
i = Image.open("D:/test2/滑動驗證/img.jpg") # 打開截圖
i = i.convert('RGB')
frame1 = i.crop(rangle) # 使用Image的crop函數，從截圖中再次截取我們需要的區域
frame1.save('D:/test2/滑動驗證/new.jpg')
driver.find_element_by_xpath('/html/body/div[2]/div[2]/div[1]/div/div[2]/div[2]/div[2]').click()
time.sleep(4)
driver.get_screenshot_as_file("D:/test2/滑動驗證/img.jpg")
imgelement = driver.find_element_by_xpath('/html/body/div[2]/div[2]/div[1]/div/div[2]/div[1]/div/a/div[1]/div/canvas[2]') # 定位驗證碼
location = imgelement.location # 獲取驗證碼x,y軸坐標
size = imgelement.size # 獲取驗證碼的長寬
rangle = (int(location['x'] ), int(location['y']), int(location['x'] + size['width']),
int(location['y'] + size['height'])) # 寫成我們需要截取的位置坐標
i = Image.open("D:/test2/滑動驗證/img.jpg") # 打開截圖
i = i.convert('RGB')
frame2 = i.crop(rangle) # 使用Image的crop函數，從截圖中再次截取我們需要的區域
frame2.save('D:/test2/滑動驗證/new2.jpg')
#計算缺口位置
loc=get_diff_location(frame1, frame2)
print('-------------')
print(loc)
#找到滑動的圓球
element=driver.find_element_by_xpath('/html/body/div[2]/div[2]/div[1]/div/div[2]/div[2]/div[2]')
location=element.location
#獲得滑動圓球的高度
y=location["y"]
#鼠標點擊元素並按住不放
print ("第一步,點擊元素")
ActionChains(driver).click_and_hold(on_element=element).perform()
time.sleep(0.15)
print ("第二步，拖動元素")
ActionChains(driver).move_to_element_with_offset(to_element=element, xoffset=loc + 30, yoffset=y - 445).perform()
#釋放鼠標
ActionChains(driver).release(on_element=element).perform()
#關閉瀏覽器,為了演示方便,暫時注釋掉.
#driver.quit()
#主函數入口
if __name__ == "__main__":
pass
main()
破解滑動驗證:
from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait # 等待元素加載的
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 re
import random
from io import BytesIO
import time
def merge_image(image_file,location_list):
"""
拼接圖片
"""
im = Image.open(image_file)
im.save('code.jpg')
new_im = Image.new('RGB',(260,116))
# 把無序的圖片 切成52張小圖片
im_list_upper = []
im_list_down = []
# print(location_list)
for location in location_list:
# print(location['y'])
if location['y'] == -58: # 上半邊
im_list_upper.append(im.crop((abs(location['x']),58,abs(location['x'])+10,116)))
if location['y'] == 0: # 下半邊
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)) # 把小圖片放到 新的空白圖片上
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):
'''
下載無序的圖片 然后進行拼接 獲得完整的圖片
:param driver:
:param div_path:
:return:
'''
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)
image_url = image_url.replace('webp','jpg')
# '替換url http://static.geetest.com/pictures/gt/579066de6/579066de6.webp'
image_result = requests.get(image_url).content
image_file = BytesIO(image_result) # 是一張無序的圖片
image = merge_image(image_file,location_list)
return image
def get_track(distance):
# 初速度
v=0
# 單位時間為0.2s來統計軌跡，軌跡即0.2內的位移
t=0.2
# 位移/軌跡列表，列表內的一個元素代表0.2s的位移
tracks=[]
tracks_back=[]
# 當前的位移
current=0
# 到達mid值開始減速
mid=distance * 7/8
print("distance",distance)
global random_int
random_int=8
distance += random_int # 先滑過一點，最后再反着滑動回來
while current < distance:
if current < mid:
# 加速度越小，單位時間的位移越小,模擬的軌跡就越多越詳細
a = random.randint(2,5) # 加速運動
else:
a = -random.randint(2,5) # 減速運動
# 初速度
v0 = v
# 0.2秒時間內的位移
s = v0*t+0.5*a*(t**2)
# 當前的位置
current += s
# 添加到軌跡列表
if round(s)>0:
tracks.append(round(s))
else:
tracks_back.append(round(s))
# 速度已經達到v,該速度作為下次的初速度
v= v0+a*t
print("tracks:",tracks)
print("tracks_back:",tracks_back)
print("current:",current)
# 反着滑動到大概准確位置
tracks_back.append(distance-current)
tracks_back.extend([-2,-5,-8,])
return tracks,tracks_back
def get_distance(image1,image2):
'''
拿到滑動驗證碼需要移動的距離
:param image1:沒有缺口的圖片對象
:param image2:帶缺口的圖片對象
:return:需要移動的距離
'''
# print('size', image1.size)
threshold = 50
for i in range(0,image1.size[0]): # 260
for j in range(0,image1.size[1]): # 160
pixel1 = image1.getpixel((i,j))
pixel2 = image2.getpixel((i,j))
res_R = abs(pixel1[0]-pixel2[0]) # 計算RGB差
res_G = abs(pixel1[1] - pixel2[1]) # 計算RGB差
res_B = abs(pixel1[2] - pixel2[2]) # 計算RGB差
if res_R > threshold and res_G > threshold and res_B > threshold:
return i # 需要移動的距離
def main_check_code(driver,element):
"""
拖動識別驗證碼
:param driver:
:param element:
:return:
"""
login_btn = driver.find_element_by_class_name('js-login')
login_btn.click()
element = WebDriverWait(driver, 30, 0.5).until(EC.element_to_be_clickable((By.CLASS_NAME, 'gt_guide_tip')))
slide_btn = driver.find_element_by_class_name('gt_guide_tip')
slide_btn.click()
image1 = get_image(driver, '//div[@class="gt_cut_bg gt_show"]/div')
image2 = get_image(driver, '//div[@class="gt_cut_fullbg gt_show"]/div')
# 圖片上 缺口的位置的x坐標
# 2 對比兩張圖片的所有RBG像素點，得到不一樣像素點的x值，即要移動的距離
l = get_distance(image1, image2)
print('l=',l)
# 3 獲得移動軌跡
track_list = get_track(l)
print('第一步,點擊滑動按鈕')
element = WebDriverWait(driver, 30, 0.5).until(EC.element_to_be_clickable((By.CLASS_NAME, 'gt_slider_knob')))
ActionChains(driver).click_and_hold(on_element=element).perform() # 點擊鼠標左鍵，按住不放
import time
time.sleep(0.4)
print('第二步,拖動元素')
for track in track_list[0]:
ActionChains(driver).move_by_offset(xoffset=track, yoffset=0).perform() # 鼠標移動到距離當前位置（x,y）
#time.sleep(0.4)
for track in track_list[1]:
ActionChains(driver).move_by_offset(xoffset=track, yoffset=0).perform() # 鼠標移動到距離當前位置（x,y）
time.sleep(0.1)
import time
time.sleep(0.6)
# ActionChains(driver).move_by_offset(xoffset=2, yoffset=0).perform() # 鼠標移動到距離當前位置（x,y）
# ActionChains(driver).move_by_offset(xoffset=8, yoffset=0).perform() # 鼠標移動到距離當前位置（x,y）
# ActionChains(driver).move_by_offset(xoffset=2, yoffset=0).perform() # 鼠標移動到距離當前位置（x,y）
print('第三步,釋放鼠標')
ActionChains(driver).release(on_element=element).perform()
time.sleep(1)
def main_check_slider(driver):
"""
檢查滑動按鈕是否加載
:param driver:
:return:
"""
while True:
try :
driver.get('https://www.huxiu.com/')
element = WebDriverWait(driver, 30, 0.5).until(EC.element_to_be_clickable((By.CLASS_NAME, 'js-login')))
if element:
return element
except TimeoutException as e:
print('超時錯誤，繼續')
time.sleep(5)
if __name__ == '__main__':
try:
count = 3 # 最多識別3次
driver = webdriver.Chrome()
while count > 0:
# 等待滑動按鈕加載完成
element = main_check_slider(driver)
main_check_code(driver,element)
try:
success_element = (By.CSS_SELECTOR, '.gt_success')
# 得到成功標志
success_images = WebDriverWait(driver,3).until(EC.presence_of_element_located(success_element))
if success_images:
print('成功識別！！！！！！')
count = 0
import sys
sys.exit()
except Exception as e:
print('識別錯誤，繼續')
count -= 1
time.sleep(1)
else:
print('too many attempt check code ')
exit('退出程序')
finally:
driver.close()
