python爬虫之验证码识别
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/84574797
环境：
- subline: https://download.sublimetext.com/Sublime Text Build 3176 x64 Setup.exe
- python: https://www.python.org/ftp/python/3.7.0/python-3.7.0-amd64.exe
- OCR识别库工具：https://digi.bib.uni-mannheim.de/tesseract/tesseract-ocr-setup-3.05.01.exe
- 图形验证码：https://github.com/Python3WebSpider/CrackImageCode/archive/master.zip
- 滑动验证码：https://github.com/Python3WebSpider/CrackGeetest/archive/master.zip 平台：https://passport.cnblogs.com/user/signin 例子：https://www.cnblogs.com/moning/p/8318475.html
import tesserocr from PIL import Image
image = Image.open(‘code2.jpg’)
image = image.convert(‘L’) threshold = 127 table = [] for i in range(256): if i < threshold: table.append(0) else: table.append(1)
image = image.point(table, ‘1’) image.show()
result = tesserocr.image_to_text(image) print(result)
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()