使用Selenium破解新浪微博的四宮格驗證碼
阿新 • • 發佈:2021-06-18
在我們爬蟲的時候經常會遇到驗證碼,新浪微博的驗證碼是四宮格形式。
可以採用模板驗證碼的破解方式,也就是把所有驗證碼的情況全部列出來,然後拿驗證碼的圖片和這所有情況中的圖片進行對比,然後獲取驗證碼,再通過selenium自動拖拽點選,進行破解。
我們將驗證碼四個點標註為1234,那麼所有的情況就是以下24種情況。
數字代表箭頭指向:
1234 | 2134 | 3124 | 4321 |
---|---|---|---|
1243 | 2143 | 3142 | 4312 |
1342 | 2314 | 3214 | 4123 |
1324 | 2341 | 3241 | 4132 |
1423 | 2413 | 3412 | 4213 |
1432 | 2431 | 3421 | 4231 |
所有的情況就是以上24種。我們將這24中驗證碼的情況放在一個資料夾內,當我們在登入的時候用獲取的驗證碼截圖去和所有的情況一一對比,然後獲取完全相同的驗證碼,進行點選即可。程式碼如下:
from selenium import webdriver from selenium.webdriver.support.ui import WebDriverWait from selenium.webdriver.support import expected_conditions as EC from selenium.webdriver.common.by import By from selenium.common.exceptions import TimeoutException from selenium.webdriver.common.action_chains import ActionChains import time from PIL import Image from io import BytesIO from os import listdir USERNAME = '' PASSWORD = '' class CrackWeiboSlide(): def __init__(self): self.url = 'https://passport.weibo.cn/signin/login' self.browser = webdriver.Chrome() self.wait = WebDriverWait(self.browser,20) self.username = USERNAME self.password = PASSWORD def __del__(self): self.browser.close() def open(self): """ 開啟網頁輸入使用者名稱密碼登入 :return: None """ self.browser.get(self.url) username = self.wait.until(EC.presence_of_element_located((By.ID,'loginName'))) password = self.wait.until(EC.presence_of_element_located((By.ID,'loginPassword'))) submit = self.wait.until(EC.element_to_be_clickable((By.ID, 'loginAction'))) username.send_keys(self.username) password.send_keys(self.password) submit.click() def get_position(self): """ 獲取驗證碼的位置 :return: 位置 """ try: img = self.wait.until(EC.presence_of_element_located((By.CLASS_NAME,'patt-shadow'))) except TimeoutException: print('未出現驗證碼') self.open() time.sleep(2) location = img.location size = img.size top=location['y'] bottom = location['y']+size['height'] left = location['x'] right = location['x']+size['width'] return (top,bottom,left,right) def get_screenshot(self): """ 獲取截圖 :return:截圖 """ screentshot = self.browser.get_screenshot_as_png() # BytesIO將網頁截圖轉換成二進位制 screentshot = Image.open(BytesIO(screentshot)) return screentshot def get_image(self,name): """獲取驗證碼圖片""" top,bottom,left,right = self.get_position() print('驗證碼位置',top,bottom,left,right) screenshot = self.get_screenshot() # crop()將圖片裁剪出來,後面需要一個引數 captcha = screenshot.crop((left,top,right,bottom)) captcha.save(name) return captcha def detect_image(self,image): """ 匹配圖片 :param self: :param image: 圖片 :return: 拖動順序 """ # 圖片所在的資料夾 for template_name in listdir('templates/'): print('正在匹配',template_name) template = Image.open('templates/'+template_name) # 匹配圖片 if self.same_img(image,template): # 將匹配到的檔名轉換為列表 numbers = [int(number)for number in list(template_name.split('.')[0])] print('拖動順序',numbers) return numbers def is_pixel_equal(self,image1,image2,x,y): """ 判斷兩個畫素的相似度 :param image1: 圖片1 :param image2: 圖片2 :param x: 位置x :param y: 位置y :return: 畫素是否相同 """ # 取畫素點 pixel1 = image1.load()[x,y] pixel2 = image2.load()[x,y] # 偏差量等於60 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 same_img(self,image,template): """ 識別相似的驗證碼 :param image: 準備識別的驗證碼 :param template: 模板 :return: """ # 相似度閾值 threshold = 0.99 count = 0 # 匹配所有畫素點 for x in range(image.width): for y in range(image.height): # 判斷畫素 if self.is_pixel_equal(image,template,x,y): count+=1 result = float(count)/(image.width*image.height) if result>threshold: print('成功匹配') return True return False def move(self,numbers): """ 根據順序拖動,此處接收的引數為前面的驗證碼的順序列表 :param numbers: :return: """ # 獲取四宮格的四個點 circles = self.browser.find_elements_by_css_selector('.patt-wrap .patt-circ') print('-----------------',circles) dx = dy =0 for index in range(4): circle = circles[numbers[index]-1] if index == 0: # 點選第一個點 ActionChains(self.browser).move_to_element_with_offset(circle,circle.size['width']/2,circle.size['height']/2).click_and_hold().perform() else: # 慢慢移動 times = 30 for i in range(times): ActionChains(self.browser).move_by_offset(dx/times,dy/times).perform() time.sleep(1/times) if index == 3: # 鬆開滑鼠 ActionChains(self.browser).release().perform() else: # 計算下次的偏移 dx = circles[numbers[index+1]-1].location['x'] - circle.location['x'] dy = circles[numbers[index+1]-1].location['y'] - circle.location['y'] def crack(self): """ 破解入口 :return: """ self.open() # 獲取驗證碼圖片 image = self.get_image('captcha.png') numbers = self.detect_image(image) self.move(numbers) time.sleep(10) print('識別結束') if __name__ == '__main__': crack = CrackWeiboSlide() crack.crack()
設定自己的賬號密碼即可實現。
有時候會匹配不上,圖片相似度閾值達不到0.99以上,這個時候可能是我們收集的驗證碼圖片過時了,重新開啟圖片收集程式,執行收集一下即可。
收集圖片程式程式碼如下:
from selenium import webdriver from selenium.webdriver.support.ui import WebDriverWait from selenium.webdriver.support import expected_conditions as EC from selenium.webdriver.common.by import By from selenium.common.exceptions import TimeoutException import time from PIL import Image from io import BytesIO from os import listdir USERNAME = '18239831004' PASSWORD = 'qweqweqwe' class CrackWeiboSlide(): def __init__(self): self.url = 'https://passport.weibo.cn/signin/login' self.browser = webdriver.Chrome() self.wait = WebDriverWait(self.browser,20) self.username = USERNAME self.password = PASSWORD def __del__(self): self.browser.close() def open(self): """ 開啟網頁輸入使用者名稱密碼登入 :return: None """ self.browser.get(self.url) username = self.wait.until(EC.presence_of_element_located((By.ID,'loginName'))) password = self.wait.until(EC.presence_of_element_located((By.ID,'loginPassword'))) submit = self.wait.until(EC.element_to_be_clickable((By.ID, 'loginAction'))) username.send_keys(self.username) password.send_keys(self.password) submit.click() def get_position(self): """ 獲取驗證碼的位置 :return: 位置 """ try: img = self.wait.until(EC.presence_of_element_located((By.CLASS_NAME,'patt-shadow'))) except TimeoutException: print('未出現驗證碼') self.open() time.sleep(2) location = img.location size = img.size top=location['y'] bottom = location['y']+size['height'] left = location['x'] right = location['x']+size['width'] return (top,bottom,left,right) def get_screenshot(self): """ 獲取截圖 :return:截圖 """ screentshot = self.browser.get_screenshot_as_png() # BytesIO將網頁截圖轉換成二進位制 screentshot = Image.open(BytesIO(screentshot)) return screentshot def get_image(self,name): """獲取驗證碼圖片""" top,bottom,left,right = self.get_position() print('驗證碼位置',top,bottom,left,right) screenshot = self.get_screenshot() # crop()將圖片裁剪出來,後面需要一個引數 captcha = screenshot.crop((left,top,right,bottom)) captcha.save(name) return captcha # 獲取所有的驗證碼 def main(self): count = 0 while True: name = str(count)+'.png' self.open() self.get_image(name) count+=1 if __name__ == '__main__': crack = CrackWeiboSlide() crack.main()
總結
以上就是這篇文章的全部內容了,希望本文的內容對大家的學習或者工作具有一定的參考學習價值,謝謝大家對指令碼之家的支援。如果你想了解更多相關內容請檢視下面相關連結