快捷導(dǎo)航

python3.5+tesseract+adb實(shí)現(xiàn)西瓜視頻或頭腦王者輔助答題

更新時(shí)間：2018年01月17日 09:54:27 作者：zjy105

這篇文章主要介紹了python3.5+tesseract+adb實(shí)現(xiàn)西瓜視頻或頭腦王者輔助答題，具有一定的參考價(jià)值，感興趣的小伙伴們可以參考一下

最近的答題贏錢(qián)很火爆，我也參與了幾次，有些題目確實(shí)很難答，但是10秒鐘的時(shí)間根本不夠百度的，所以寫(xiě)了個(gè)輔助掛，這樣可以出現(xiàn)題目時(shí)自動(dòng)百度，這個(gè)時(shí)間也就花掉2秒鐘，剩下的7、8秒鐘可以進(jìn)行分析和作答，提升了贏錢(qián)概率。

源碼可以見(jiàn)我的github：點(diǎn)擊鏈接

原理分析下：使用adb命令，抓取手機(jī)視頻播放的界面，然后通過(guò)python的截取和ocr，獲得到題目和答案, 然后百度得到結(jié)果。這個(gè)環(huán)境怎么搭建，有需要的童鞋可以聯(lián)系我，因?yàn)槭褂帽镜氐膐cr所以解析不花錢(qián)，也沒(méi)有使用的限制。

github上的代碼中

ocr_bw.py，這個(gè)是自動(dòng)根據(jù)題目去百度，然后打開(kāi)瀏覽器，展示檢索結(jié)果

# -*- coding: utf-8 -*-

import pytesseract
import time
import webbrowser
import subprocess
from PIL import Image



def main():
 """
 主函數(shù)
 """
 op = yes_or_no('請(qǐng)確保手機(jī)打開(kāi)了 ADB 并連接了電腦，'
     '然后打開(kāi)西瓜視頻后再用本程序，確定開(kāi)始？')
 if not op:
  print('bye')
  return
 #核心遞歸
 ocr_subject_parent()

 # for root, sub_dirs, files in os.walk('E:/臨時(shí)接收的文件/知乎答題/百萬(wàn)/'):
 #  for file in files:
 #   print('發(fā)現(xiàn)圖片:' + file)
 #   img = Image.open('E:/臨時(shí)接收的文件/知乎答題/百萬(wàn)/'+file)
 #   ocr_subject(img)


def yes_or_no(prompt, true_value='y', false_value='n', default=True):
 """
 檢查是否已經(jīng)為啟動(dòng)程序做好了準(zhǔn)備
 """
 default_value = true_value if default else false_value
 prompt = '{} {}/{} [{}]: '.format(prompt, true_value,
          false_value, default_value)
 i = input(prompt)
 if not i:
  return default
 while True:
  if i == true_value:
   return True
  elif i == false_value:
   return False
  prompt = 'Please input {} or {}: '.format(true_value, false_value)
  i = input(prompt)


def screenImg(true_value='', default=True):
 prompt = '當(dāng)出現(xiàn)題目時(shí)，請(qǐng)按下回車進(jìn)行識(shí)別 '
 i = input(prompt)
 if not i:
  return default
 while True:
  if i == true_value:
   return True
  else:
   return False
  i = input(prompt)


def ocr_subject(p):
 # 截取 距離上530開(kāi)始 940結(jié)束
 # 截取 距離上260 570結(jié)束
 p = cut_img(p)
 pytesseract.pytesseract.tesseract_cmd = 'E:/Program Files (x86)/Tesseract-OCR/tesseract'
 subject = pytesseract.image_to_string(p, lang='chi_sim')
 subject = "".join(subject.split())
 subject = subject.split('.')[1]
 print(subject)
 openPage(subject)
 ocr_subject_parent()


def ocr_subject_parent():
 result = screenImg()
 if result:
  start = time.time()
  # screenshot.check_screenshot()
  process = subprocess.Popen(
   'adb shell screencap -p',
   shell=True, stdout=subprocess.PIPE)
  binary_screenshot = process.stdout.read()
  binary_screenshot = binary_screenshot.replace(b'\r\n', b'\n')
  f = open('autojump.png', 'wb')
  f.write(binary_screenshot)
  f.close()
  # screenshot.pull_screenshot()
  img = Image.open('autojump.png')
  print("耗時(shí):" + str(time.time() - start))
  ocr_subject(img)


def openPage(subject):
 url = 'https://www.baidu.com/s?wd={}'.format(
  subject)
 webbrowser.open(url)
 webbrowser.get()



def cut_img(img):
 region = img.crop((70, 260, 1025, 570))
 #region.save("temp/cut_first.png")
 return region


if __name__ == '__main__':
 main()

ocr_bw2.py,這個(gè)是根據(jù)題目+答案，去百度檢索，通過(guò)爬蟲(chóng)抓取百度的收錄數(shù)，然后在控制臺(tái)打印結(jié)果

__author__ = 'zjy'
# -*- coding:utf-8 -*-

import pytesseract
import time
import webbrowser
import subprocess
from PIL import Image
import urllib
import urllib.request
import threading
from urllib.parse import quote


def main():
 """
 主函數(shù)
 """
 op = yes_or_no('請(qǐng)確保手機(jī)打開(kāi)了 ADB 并連接了電腦，'
     '然后打開(kāi)西瓜視頻后再用本程序，確定開(kāi)始？')
 if not op:
  print('bye')
  return
 # 核心遞歸
 ocr_subject_parent()

 # for root, sub_dirs, files in os.walk('E:/臨時(shí)接收的文件/知乎答題/百萬(wàn)/'):
 #  for file in files:
 #   print('發(fā)現(xiàn)圖片:' + file)
 #   img = Image.open('E:/臨時(shí)接收的文件/知乎答題/百萬(wàn)/'+file)
 #   ocr_subject(img)


def yes_or_no(prompt, true_value='y', false_value='n', default=True):
 """
 檢查是否已經(jīng)為啟動(dòng)程序做好了準(zhǔn)備
 """
 default_value = true_value if default else false_value
 prompt = '{} {}/{} [{}]: '.format(prompt, true_value,
          false_value, default_value)
 i = input(prompt)
 if not i:
  return default
 while True:
  if i == true_value:
   return True
  elif i == false_value:
   return False
  prompt = 'Please input {} or {}: '.format(true_value, false_value)
  i = input(prompt)


def screenImg(true_value='', default=True):
 prompt = '當(dāng)出現(xiàn)題目時(shí)，請(qǐng)按下回車進(jìn)行識(shí)別 \n'
 i = input(prompt)
 if not i:
  return default
 while True:
  if i == true_value:
   return True
  else:
   return False
  i = input(prompt)


def ocr_subject(p):
 # 截取 距離上530開(kāi)始 940結(jié)束
 # 截取 距離上260 570結(jié)束
 subImg = cut_img(p)
 pytesseract.pytesseract.tesseract_cmd = 'E:/Program Files (x86)/Tesseract-OCR/tesseract'
 subject = pytesseract.image_to_string(subImg, lang='chi_sim')
 subject = "".join(subject.split())
 subject = subject.split('.')[1].replace("\"", "")
 print(subject)
 ocr_answer(p, subject)
 # openPage(subject)
 # print("結(jié)束:" + str(time.time()))
 ocr_subject_parent()


def getSearchNum(key):
 key = quote(key)
 # print(key)
 url = 'http://www.baidu.com/s?wd={}'.format(key)
 # print(url)
 response = urllib.request.urlopen(url)
 page = response.read().decode("utf-8")
 i = int(page.index('百度為您找到相關(guān)結(jié)果約'))
 start = i + 10
 end = i + 25
 page = page[start: end]
 return page


def ocr_answer(p, subject):
 list = cut_question(p)
 pytesseract.pytesseract.tesseract_cmd = 'E:/Program Files (x86)/Tesseract-OCR/tesseract'
 for p in list:
  t = threading.Thread(target=ocr_answer_thread, args=(p, subject))
  t.start()


def ocr_answer_thread(p, subject):
 answer = pytesseract.image_to_string(p, lang='chi_sim')
 answer = "".join(answer.split())
 v = getSearchNum(subject + ' ' + answer)
 print(answer + ' ' + v)
 # print(time.time())


def ocr_subject_parent():
 result = screenImg()
 if result:
  start = time.time()
  # print("開(kāi)始:" + str(start))
  # screenshot.check_screenshot()
  process = subprocess.Popen(
   'adb shell screencap -p',
   shell=True, stdout=subprocess.PIPE)
  binary_screenshot = process.stdout.read()
  binary_screenshot = binary_screenshot.replace(b'\r\n', b'\n')
  f = open('autojump.png', 'wb')
  f.write(binary_screenshot)
  f.close()
  # screenshot.pull_screenshot()
  img = Image.open('autojump.png')
  ocr_subject(img)


def openPage(subject):
 url = 'https://www.baidu.com/s?wd={}'.format(
  subject)
 webbrowser.open(url)
 webbrowser.get()


def cut_img(img):
 region = img.crop((70, 260, 1025, 570))
 # region.save("temp/cut_first.png")
 return region


def cut_question(img):
 list = []
 question1 = img.crop((70, 590, 1025, 768))
 question2 = img.crop((70, 769, 1025, 947))
 question3 = img.crop((70, 948, 1025, 1130))
 list.append(question1)
 list.append(question2)
 list.append(question3)
 # question1.save("temp/cut_1.png")
 # question2.save("temp/cut_2.png")
 # question3.save("temp/cut_3.png")
 return list


if __name__ == '__main__':
 main()

由于很多題目是下列哪個(gè)不是，所以我更喜歡用第一個(gè)方式，基本上識(shí)別時(shí)間在0.5-0.6秒之間。