Python3爬虫（十四） 验证码处理
Infi-chu:
http://www.cnblogs.com/Infi-chu/
一、图形验证码识别
1.使用tesserocr
import tesserocrfrom PIL import Image
# 在本地存储一张验证码的图片做测试
image = Image.open(\'test.jpg\')
result = tesserocr.image_to_text(image)
print(result)
# 直接将文本转为字符串
import tesserocr
print(tesserocr.file_to_text(\'test.jpg\'))
2.处理验证码图片
convert()方法，可将图片转化为灰度图像、二值化图像
image = image.convert(\'L\') # 将图像转化为灰度图像image.show()
image = image.convert(\'1\') # 将图像转化为二值化图像，二值化阈值默认是127
# 现将图片转化成灰度图像，再转化成二值化图像
image = image.convert(\'L\')
threshold = 80 # 设定阈值
table = []
for i in range(256):
if i < threshold:
table.append(0)
else:
table.append(1)
image = image.point(table,\'1\')
image.show() # 图像变得清晰
result = tesserocr.image_to_text(image)
print(result)
二、滑动验证码识别
滑动验证码就如同用一块拼图去在图片中填充
1.滑动验证码特点：
防模拟
防伪造
防暴力
2.如何识别：
采用浏览器模拟验证
3.初始化：
EMAIL = \'test@test.com\'PASSWORD = \'123456\'
class CrackGeetest():
def __init__(self):
self.url = \'https://account.geetest.com/login\'
self.browser = webdriver.Chome()
self.wait = WebDriverWait(self.browser,20)
self.email = EMAIL
self.pasword = PASSWORD
4.模拟点击：
# 寻找按钮def get_geetest_button(self):
button = self.wait.until(EC.element_to_be_clickable((BY.CLASS_NAME,\'geetest_radar_tip\')))
return button
# 点击验证按钮
button = self.get_geetest_button()
button.click()
5.识别缺口：
首先对比原图和现图，利用selenium选取图片元素，得到位置和size，然后获取截图
## 获取位置和size
def position(self):
img = self.wait.until(EC.persence_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)
# 获取网页截图
def get_geetest_image(self,name=\'captcha.png\'):
top,bottom,left,right = self.get_position() # 获取图片的位置和宽高，随后返回左上角和右下角的坐标
print(\'验证码位置\',top,bottom,left,right)
screenshot = self.get_screenshot() # 得到屏幕目标
captcha = screenshot.crop((left,top,right,bottom))
# 获取第二张图片（带有缺口的图片）
def get_slider(self):
slider = self.wait.until(EC.element_to_be_clickable((By.CLASS_NAME,\'geetest_slider_button\')))
return slider
# 点击后出现接口
slider = self.get_slider()
slider.click()
# 在调用 get_geetest_image()函数获取第二张图，分别命名为img1和img2
\'\'\'
对比图像的缺口，需要遍历图片的每一个坐标点，获取两张图片对应像素点的RGB数据，如果差距在一定范围内，则代表两个像素相同，接着继续对比下一个像素点。如果差距在一定范围之外，则说明不是相同的像素点，则该位置就是缺口位置
\'\'\'
def is_pixel_equal(self,img1,img2,x,y):
# 取两个图片的像素点
pixel1 = img1.load()[x,y]
pixel2 = img2.load()[x,y]
threshold = 60
# 两张图RGB的绝对值小于定义的阈值，则代表像素点相同，继续遍历。否则不相同，为缺口位置
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_gap(self,img1,img2):
left = 60
for i in range(left,img1.size[0]):
for j in range(img1.size[1]):
if not self.is_pixel_equal(img1.img2,i,j): # 判断两个图片的某一点的像素是否相同
left = i
return left
return left
6.模拟拖动：
def get_track():track = []
current = 0
mid = distance * 4 / 5
t = 0.2
v = 0
while current < distance:
if current < mid:
a = 2
else:
a = -3
v0 = v
v = v0 + a * t
x = v0*t+1/2*a*t^2
move = v0*t+1/2*a*t^2
current += move
track.append(round(move))
return track
def move_to_gap(self,slider,tracks):
ActionChains(self.browser).click_and_hold(slider).perform()
for x in tracks:
ActionChains(self.browser).move_by_offset(xoffset=x,yoffset=0).perform()
time.sleep(0.3)
ActionChains(self.browser).release().perform()
1.和12306的验证码类似
2.思路：
文字识别、图像识别
3.使用超级鹰平台识别
修改Python API
import requestsfrom hashlib import md5
class Chaojiying(obj):
def __init__(self,username,password,soft_id):
self.username=username
self.password=md5(password.encode(\'utf-8\')).hexdigest()
self.soft_id=soft_id
self.base_params = {
\'user\':self.username,
\'pass2\':self.password,
\'softid\':self.soft_id,
}
self.headers = {
\'Connection\':\'Keep-Alive\',
\'User-Agent\':\'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko)\'
}
def post_pic(self,im,codetype):
params = {
\'codetype\':codetype,
}
params.update(self.base_params)
files = {\'userfile\':(\'test.jpg\',im)}
r = requests.post(\'http://upload.chaojiying.net/Upload/Processing.php\',data=params,files=files,headers=self.headers)
return r.json()
def report_error(self,im_id):
params = {\'id\':im_id,}
params.update(self.base_params)
r = requests.post(\'http://upload.chaojiying.net/Upload/ReportError.php\',data=params,headers=self.headers)
return r.json()
4.初始化：
EMAIL = \'test@test.com\'PASSWORD = \'\'
CHAOJIYING_USERNAME=\'test\'
CHAOJIYING_PASSWORD=\'\'
CHAOJIYING_SOFT_ID=893590 # 软件ID
CHAOJIYING_KIND=9102 # 验证码类型
class CrackTouClick():
def __init__(self):
self.url=\'输入要识别的网站\'
self.browser=webdriver.Chome()
self.wait=WebDriverWait(self.browser,20)
self.email=EMAIL
self.password=PASSWORD
self.chaojiying=Chaojiying(CHAOJIYING_USERNAME,CHAOJIYING_PASSWORD,CHAOJIYING_SOFT_ID,CHAOJIYING_KIND)
5.获取验证码：
def open():self.browser.get(self.url)
email=self.wait.until(EC.persence_of_element_located((By.ID,\'email\')))
password=self.wait.until(EC.persence_of_element_located((By.ID,\'password\')))
email.send_keys(self.password)
def get_touclick_button(self):
button = self.wait.until(EC.element_to_be_clickable((By.CLASS_NAME,\'touclick-hod-wrap\')))
return button
def get_touclick_element(self):
element = self.wait.until(EC.persence_of_element_located((By.CLASS_NAME,\'touclick-pub-content\')))
return element
def get_position(self):
element=self.get_touclick_element()
time.sleep(1)
location=element.location
size=element.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):
screenshot=self.browser.get_screenshot_as_png()
screenshot=Image.open(BytesIO(screenshot))
return screenshot
def get_touclick_image(self,name=\'captcha.png\')
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))
return captcha
6.识别验证码：
image = self.get_touclick_image()bytes_array=BytesIO()
image.save(bytes_array,format=\'PNG\')
res = self.chaojiying.post_pic(bytes_array,getvalue(),CHAOJIYING_KIND)
print(res)
def get_points(self,captcha_result):
groups=captcha_result.get(\'pic_str\').split(\'|\')
locations=[[int(number) for number in group.split(\',\')]for group in groups]
return locations
def touch_click_words(self,locations):
for location in locations:
print(location)
ActionChains(self.browser).move_to_element_with_offset(self.get_touclick_element(),location[0],location[1]).click().perform()
time.sleep(1)
以上是 Python3爬虫（十四） 验证码处理 的全部内容， 来源链接： utcz.com/z/386561.html
