版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/weixin_40313634/article/details/84591042
环境
- python3.6.7
- OCR识别库： OCR工具(exe)安装：选择语言库，其他默认。 tesserocr库安装：pip3 install tesserocr pillow PIL库安装：pip install pillow
- Sublime Text编辑器安装
- ChromeDriver 安装 可能遇到的问题： 问题1：tesserocr安装失败，报错如下： install --record C:UsersZy129AppDataLocalTemppip-record-r5t7l43tinstall-record.txt --single-version-externally-managed --compile" failed with error code 1 in C:UsersZy129AppDataLocalTemppip-install-5z4ljbyjtesserocr 解决办法：手动下载和python版本对应的原始whl文件安装即可（tesserocr-2.3.1-cp36-cp36m-win_amd64.whl）。 whl 文件：https://github.com/simonflueckiger/tesserocr-windows_build/releases 方法参考：http://www.mamicode.com/info-detail-2353336.html 建议：通常情况下，不要安装最新版本的python，因为可能某库还没有升级，导致无法使用。 问题2：调用tesserocr.image_to_text(image)方法时，报如下错： RuntimeError: Failed to init API, possibly an invalid tessdata path: C:UsersZy129AppDataLocalProgramsPythonPython36/tessdata/ 解决：拷贝OCR库文件夹tessdata（默认路径：C:Program Files (x86)Tesseract-OCR）到python安装路径下(默认路径：C:UsersZy129AppDataLocalProgramsPythonPython36)即可。 参考方法：https://www.jianshu.com/p/dcad7ee3b162
图形验证
1. version1.0 import tesserocr
from PIL import Image
image = Image.open('code.jpg')
result = tesserocr.image_to_text(image)
print(result)效果：
2. version2.0 问题：部分图片背景上有条纹，可能导致图片识别错误。 改进点：将图片转化为灰度图像，设定阈值，小于阈值的像素点置为0，大于的置为1。即把彩色图片转化为黑白图片，忽略掉背景色的影响，从而增大验证码识别率。
代码语言：javascript复制import tesserocr
from PIL import Image
image = Image.open('code.jpg')
# 转化成灰度图像
image = image.convert('L')
# 设置阈值（1--500）
threshold = 127
table = []
for i in range(256):
if i < threshold:
table.append(0)
else:
table.append(1)
image = image.point(table, '1')
# 转化后的图片
image.show()
result = tesserocr.image_to_text(image)
print(result)效果：
滑块验证
version：
代码语言：javascript复制import time
from io import BytesIO
from PIL import Image
from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
EMAIL = 'cqc@cuiqingcai.com'
PASSWORD = ''
BORDER = 6
INIT_LEFT = 60
class CrackGeetest():
def __init__(self):
self.url = 'https://account.geetest.com/login'
self.browser = webdriver.Chrome()
self.wait = WebDriverWait(self.browser, 20)
self.email = EMAIL
self.password = PASSWORD
def __del__(self):
self.browser.close()
def get_geetest_button(self):
"""
获取初始验证按钮
:return:
"""
button = self.wait.until(EC.element_to_be_clickable((By.CLASS_NAME, 'geetest_radar_tip')))
return button
def get_position(self):
"""
获取验证码位置
:return: 验证码位置元组
"""
img = self.wait.until(EC.presence_of_element_located((By.CLASS_NAME, 'geetest_canvas_img')))
time.sleep(2)
location = img.location
size = img.size
top, bottom, left, right = location['y'], location['y'] size['height'], location['x'], location['x'] size[
'width']
return (top, bottom, left, right)
def get_screenshot(self):
"""
获取网页截图
:return: 截图对象
"""
screenshot = self.browser.get_screenshot_as_png()
screenshot = Image.open(BytesIO(screenshot))
return screenshot
def get_slider(self):
"""
获取滑块
:return: 滑块对象
"""
slider = self.wait.until(EC.element_to_be_clickable((By.CLASS_NAME, 'geetest_slider_button')))
return slider
def get_geetest_image(self, name='captcha.png'):
"""
获取验证码图片
:return: 图片对象
"""
top, bottom, left, right = self.get_position()
print('验证码位置', top, bottom, left, right)
screenshot = self.get_screenshot()
captcha = screenshot.crop((left, top, right, bottom))
captcha.save(name)
return captcha
def open(self):
"""
打开网页输入用户名密码
:return: None
"""
self.browser.get(self.url)
email = self.wait.until(EC.presence_of_element_located((By.ID, 'email')))
password = self.wait.until(EC.presence_of_element_located((By.ID, 'password')))
email.send_keys(self.email)
password.send_keys(self.password)
def get_gap(self, image1, image2):
"""
获取缺口偏移量
:param image1: 不带缺口图片
:param image2: 带缺口图片
:return:
"""
left = 60
for i in range(left, image1.size[0]):
for j in range(image1.size[1]):
if not self.is_pixel_equal(image1, image2, i, j):
left = i
return left
return left
def is_pixel_equal(self, 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 get_track(self, distance):
"""
根据偏移量获取移动轨迹
:param distance: 偏移量
:return: 移动轨迹
"""
# 移动轨迹
track = []
# 当前位移
current = 0
# 减速阈值
mid = distance * 4 / 5
# 计算间隔
t = 0.2
# 初速度
v = 0
while current < distance:
if current < mid:
# 加速度为正2
a = 2
else:
# 加速度为负3
a = -3
# 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 move_to_gap(self, slider, track):
"""
拖动滑块到缺口处
:param slider: 滑块
:param track: 轨迹
:return:
"""
ActionChains(self.browser).click_and_hold(slider).perform()
for x in track:
ActionChains(self.browser).move_by_offset(xoffset=x, yoffset=0).perform()
time.sleep(0.5)
ActionChains(self.browser).release().perform()
def login(self):
"""
登录
:return: None
"""
submit = self.wait.until(EC.element_to_be_clickable((By.CLASS_NAME, 'login-btn')))
submit.click()
time.sleep(10)
print('登录成功')
def crack(self):
# 输入用户名密码
self.open()
# 点击验证按钮
button = self.get_geetest_button()
button.click()
# 获取验证码图片
image1 = self.get_geetest_image('captcha1.png')
# 点按呼出缺口
slider = self.get_slider()
slider.click()
# 获取带缺口的验证码图片
image2 = self.get_geetest_image('captcha2.png')
# 获取缺口位置
gap = self.get_gap(image1, image2)
print('缺口位置', gap)
# 减去缺口位移
gap -= BORDER
# 获取移动轨迹
track = self.get_track(gap)
print('滑动轨迹', track)
# 拖动滑块
self.move_to_gap(slider, track)
success = self.wait.until(
EC.text_to_be_present_in_element((By.CLASS_NAME, 'geetest_success_radar_tip_content'), '验证成功'))
print(success)
# 失败后重试
if not success:
self.crack()
else:
self.login()
if __name__ == '__main__':
crack = CrackGeetest()
crack.crack()错误1. 报错：[17672:21484:0802/155619.485:ERROR:install_util.cc(603)] Failed to read HKLMSOFTWAREPoliciesGoogleChromeMachineLevelUserCloudPolicyEnrollmentToken: 系统找不到指定 的文件。 (0x2) 解决：命令行运行「reg add HKLMSOFTWAREPoliciesGoogleChrome /v MachineLevelUserCloudPolicyEnrollmentToken /t REG_SZ」，添加报错信息中提示的注册表值。
