Python3爬蟲（十四） 驗證碼處理

 Infi-chu:

http://www.cnblogs.com/Infi-chu/

一、圖形驗證碼識別
1.使用tesserocr

import tesserocr
from PIL import Image

# 在本地存儲一張驗證碼的圖片做測試
image = Image.open('test.jpg')
result = tesserocr.image_to_text(image)
print(result)

# 直接將文本轉為字符串
import tesserocr
print(tesserocr.file_to_text('test.jpg'))

2.處理驗證碼圖片
convert()方法，可將圖片轉化為灰度圖像、二值化圖像

image = image.convert('L')	# 將圖像轉化為灰度圖像
image.show()
image = image.convert('1')	# 將圖像轉化為二值化圖像，二值化閾值默認是127

# 現將圖片轉化成灰度圖像，再轉化成二值化圖像
image = image.convert('L')
threshold = 80	# 設定閾值
table = []
for i in range(256):
    if i < threshold:
		table.append(0)
	else:
		table.append(1)
image = image.point(table,'1')
image.show()	# 圖像變得清晰
result = tesserocr.image_to_text(image)
print(result)

二、滑動驗證碼識別
滑動驗證碼就如同用一塊拼圖去在圖片中填充
1.滑動驗證碼特點：
防模擬
防偽造
防暴力

2.如何識別：
采用瀏覽器模擬驗證

3.初始化：

EMAIL = '[e-mail]'
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.模擬點擊：

# 尋找按鈕
def get_geetest_button(self):
    button = self.wait.until(EC.element_to_be_clickable((BY.CLASS_NAME,'geetest_radar_tip')))
	return button
# 點擊驗證按鈕
button = self.get_geetest_button()
button.click()

5.識別缺口：
首先對比原圖和現圖，利用selenium選取圖片元素，得到位置和size，然后獲取截圖

# 
# 獲取位置和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)
# 獲取網頁截圖
def get_geetest_image(self,name='captcha.png'):
    top,bottom,left,right = self.get_position()	# 獲取圖片的位置和寬高，隨后返回左上角和右下角的坐標
	print('驗證碼位置',top,bottom,left,right)
	screenshot = self.get_screenshot()	# 得到屏幕目標
	captcha = screenshot.crop((left,top,right,bottom))
# 獲取第二張圖片（帶有缺口的圖片）
def get_slider(self):
    slider = self.wait.until(EC.element_to_be_clickable((By.CLASS_NAME,'geetest_slider_button')))
	return slider
# 點擊后出現接口
slider = self.get_slider()
slider.click()
# 在調用 get_geetest_image()函數獲取第二張圖，分別命名為img1和img2
'''
對比圖像的缺口，需要遍歷圖片的每一個坐標點，獲取兩張圖片對應像素點的RGB數據，如果差距在一定范圍內，則代表兩個像素相同，接着繼續對比下一個像素點。如果差距在一定范圍之外，則說明不是相同的像素點，則該位置就是缺口位置
'''
def is_pixel_equal(self,img1,img2,x,y):
    # 取兩個圖片的像素點
	pixel1 = img1.load()[x,y]
	pixel2 = img2.load()[x,y]
	threshold = 60
	# 兩張圖RGB的絕對值小於定義的閾值，則代表像素點相同，繼續遍歷。否則不相同，為缺口位置
	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):	# 判斷兩個圖片的某一點的像素是否相同
			    left = i
				return left
	return left

6.模擬拖動：

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的驗證碼類似
2.思路：
文字識別、圖像識別
3.使用超級鷹平台識別
修改Python API

import requests
from 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 = '[e-mail]'
PASSWORD = ''
CHAOJIYING_USERNAME='test'
CHAOJIYING_PASSWORD=''
CHAOJIYING_SOFT_ID=893590    # 軟件ID
CHAOJIYING_KIND=9102    # 驗證碼類型
class CrackTouClick():
    def __init__(self):
	    self.url='輸入要識別的網站'
		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.獲取驗證碼：

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('驗證碼位置',top,bottom,left,right)
	screenshot = self.get_screenshot()
	captcha = screenshot.crop((left,top,right,bottom))
	return captcha

6.識別驗證碼：

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)