python3.5+tesseract+adb实现西瓜视频或头脑王者辅助答题

174 阅读 0 评论 115 点赞

我是靠谱客的博主传统蜻蜓，最近开发中收集的这篇文章主要介绍python3.5+tesseract+adb实现西瓜视频或头脑王者辅助答题，觉得挺不错的，现在分享给大家，希望可以做个参考。

概述

最近的答题赢钱很火爆，我也参与了几次，有些题目确实很难答，但是10秒钟的时间根本不够百度的，所以写了个辅助挂，这样可以出现题目时自动百度，这个时间也就花掉2秒钟，剩下的7、8秒钟可以进行分析和作答，提升了赢钱概率。

源码可以见我的github：点击链接

原理分析下：使用adb命令，抓取手机视频播放的界面，然后通过python的截取和ocr，获得到题目和答案, 然后百度得到结果。这个环境怎么搭建，有需要的童鞋可以联系我，因为使用本地的ocr所以解析不花钱，也没有使用的限制。

github上的代码中

ocr_bw.py，这个是自动根据题目去百度，然后打开浏览器，展示检索结果

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

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



def main():
 """
 主函数
 """
 op = yes_or_no('请确保手机打开了 ADB 并连接了电脑，'
     '然后打开西瓜视频后再用本程序，确定开始？')
 if not op:
  print('bye')
  return
 #核心递归
 ocr_subject_parent()

 # for root, sub_dirs, files in os.walk('E:/临时接收的文件/知乎答题/百万/'):
 #  for file in files:
 #   print('发现图片:' + file)
 #   img = Image.open('E:/临时接收的文件/知乎答题/百万/'+file)
 #   ocr_subject(img)


def yes_or_no(prompt, true_value='y', false_value='n', default=True):
 """
 检查是否已经为启动程序做好了准备
 """
 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 = '当出现题目时，请按下回车进行识别 '
 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 距离上530开始 940结束
 # 截取 距离上260 570结束
 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("耗时:" + 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,这个是根据题目+答案，去百度检索，通过爬虫抓取百度的收录数，然后在控制台打印结果

__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():
 """
 主函数
 """
 op = yes_or_no('请确保手机打开了 ADB 并连接了电脑，'
     '然后打开西瓜视频后再用本程序，确定开始？')
 if not op:
  print('bye')
  return
 # 核心递归
 ocr_subject_parent()

 # for root, sub_dirs, files in os.walk('E:/临时接收的文件/知乎答题/百万/'):
 #  for file in files:
 #   print('发现图片:' + file)
 #   img = Image.open('E:/临时接收的文件/知乎答题/百万/'+file)
 #   ocr_subject(img)


def yes_or_no(prompt, true_value='y', false_value='n', default=True):
 """
 检查是否已经为启动程序做好了准备
 """
 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 = '当出现题目时，请按下回车进行识别 \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 距离上530开始 940结束
 # 截取 距离上260 570结束
 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("结束:" + 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('百度为您找到相关结果约'))
 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("开始:" + 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()

由于很多题目是下列哪个不是，所以我更喜欢用第一个方式，基本上识别时间在0.5-0.6秒之间。