爬蟲05-B站驗證碼破解
阿新 • • 發佈:2018-11-01
import random import time from selenium.webdriver import ActionChains from selenium.webdriver.support import expected_conditions as EC from selenium.webdriver.support.ui import WebDriverWait from selenium.webdriver.common.by import By from urllib.request import urlretrieve from selenium import webdriver from bs4 import BeautifulSoup import PIL.Image as image import re class Crack(): def __init__(self, username, passwd): self.url = 'https://passport.bilibili.com/login' self.browser = webdriver.Chrome() self.wait = WebDriverWait(self.browser, 100) self.BORDER = 6 self.passwd = passwd self.username = username def open(self): """ 開啟瀏覽器,並輸入查詢內容 """ self.browser.get(self.url) keyword = self.wait.until(EC.presence_of_element_located((By.ID, 'login-username'))) keyword.send_keys(self.username) keyword = self.wait.until(EC.presence_of_element_located((By.ID, 'login-passwd'))) keyword.send_keys(self.passwd) # bowton.click() def get_images(self, bg_filename='bg.jpg', fullbg_filename='fullbg.jpg'): """ 獲取驗證碼圖片 :return: 圖片的location資訊 """ bg = [] fullgb = [] while bg == [] and fullgb == []: bf = BeautifulSoup(self.browser.page_source, 'lxml') bg = bf.find_all('div', class_='gt_cut_bg_slice') fullgb = bf.find_all('div', class_='gt_cut_fullbg_slice') bg_url = re.findall('url\(\"(.*)\"\);', bg[0].get('style'))[0].replace('webp', 'jpg') fullgb_url = re.findall('url\(\"(.*)\"\);', fullgb[0].get('style'))[0].replace('webp', 'jpg') bg_location_list = [] fullbg_location_list = [] for each_bg in bg: location = {} location['x'] = int(re.findall('background-position: (.*)px (.*)px;', each_bg.get('style'))[0][0]) location['y'] = int(re.findall('background-position: (.*)px (.*)px;', each_bg.get('style'))[0][1]) bg_location_list.append(location) for each_fullgb in fullgb: location = {} location['x'] = int(re.findall('background-position: (.*)px (.*)px;', each_fullgb.get('style'))[0][0]) location['y'] = int(re.findall('background-position: (.*)px (.*)px;', each_fullgb.get('style'))[0][1]) fullbg_location_list.append(location) # 把資源下載到臨時目錄 urlretrieve(url=bg_url, filename=bg_filename) print('缺口圖片下載完成') urlretrieve(url=fullgb_url, filename=fullbg_filename) print('背景圖片下載完成') return bg_location_list, fullbg_location_list def get_merge_image(self, filename, location_list): """ 根據位置對圖片進行合併還原 :filename:圖片 :location_list:圖片位置 """ im = image.open(filename) # 拼圖上部分的列表 im_list_upper = [] # 拼圖下部分的列表 im_list_down = [] for location in location_list: if location['y'] == -58: im_list_upper.append(im.crop((abs(location['x']), 58, abs(location['x']) + 10, 166))) if location['y'] == 0: im_list_down.append(im.crop((abs(location['x']), 0, abs(location['x']) + 10, 58))) # 建立一個新的圖片物件 new_im = image.new('RGB', (260, 116)) x_offset = 0 # 向new_im上畫圖 for im in im_list_upper: new_im.paste(im, (x_offset, 0)) x_offset += im.size[0] x_offset = 0 # 向new_im上畫圖 for im in im_list_down: new_im.paste(im, (x_offset, 58)) x_offset += im.size[0] # new_im.save(filename) return new_im def is_pixel_equal(self, img1, img2, x, y): """ 判斷兩個畫素是否相同 :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 """ # 取兩個圖片的畫素點 pix1 = img1.load()[x, y] pix2 = img2.load()[x, y] threshold = 60 if (abs(pix1[0] - pix2[0] < threshold) and abs(pix1[1] - pix2[1] < threshold) and abs( pix1[2] - pix2[2] < threshold)): return True else: return False def get_gap(self, img1, img2): """ 獲取缺口偏移量 :param img1: 不帶缺口圖片 :param img2: 帶缺口圖片 :return: """ left = 43 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): left = i return left return left def get_track(self, distance): """ 根據偏移量獲取移動軌跡 :param distance: 偏移量 :return: 移動軌跡 """ # 移動軌跡 track = [] # 當前位移 current = 0 # 減速閾值 mid = distance * 4 / 5 # 計算間隔 t = 0.2 # 初速度 v = 0 while current < distance: if current < mid: # 加速度為正2 a = 2 else: # 加速度為負3 a = -3 # 初速度v0 v0 = v # 當前速度v = v0 + at v = v0 + a * t # 移動距離x = v0t + 1/2 * a * t^2 move = v0 * t + 1 / 2 * a * t * t # 當前位移 current += move # 加入軌跡 track.append(round(move)) return track def get_slider(self): """ 獲取滑塊 :return: 滑塊物件 """ while True: try: slider = self.browser.find_element_by_xpath("//div[@class='gt_slider_knob gt_show']") break except: time.sleep(0.5) return slider def move_to_gap(self, slider, track): """ 拖動滑塊到缺口處 :param slider: 滑塊 :param track: 軌跡 :return: """ ActionChains(self.browser).click_and_hold(slider).perform() while track: x = random.choice(track) ActionChains(self.browser).move_by_offset(xoffset=x, yoffset=0).perform() track.remove(x) time.sleep(1.0) ActionChains(self.browser).release(slider).perform() time.sleep(2) #self.browser.quit() def crack(self): # 開啟瀏覽器 self.open() # 儲存的圖片名字 bg_filename = './images/bg.jpg' fullbg_filename = './images/fullbg.jpg' # 獲取圖片 bg_location_list, fullbg_location_list = self.get_images(bg_filename, fullbg_filename) # 根據位置對圖片進行合併還原 bg_img = self.get_merge_image(bg_filename, bg_location_list) fullbg_img = self.get_merge_image(fullbg_filename, fullbg_location_list) # 獲取缺口位置 gap = self.get_gap(fullbg_img, bg_img) print('缺口位置', gap) track = self.get_track(gap - self.BORDER) print('滑動滑塊') #print(track) # 點按撥出缺口 slider = self.get_slider() # 拖動滑塊到缺口處 self.move_to_gap(slider, track) # time.sleep(1) try: mspan = self.browser.find_element_by_class_name('gt_info_content') info = mspan.text if '怪物吃了拼圖' in info: print(mspan.text) time.sleep(2) self.crack() except Exception as e: print(e) if __name__ == '__main__': crack = Crack('username', 'passwd') crack.crack() print('驗證成功')