這篇文章主要介紹了python3.5+tesseract+adb如何實現西瓜視頻或頭腦王者輔助答題,具有一定借鑒價值,感興趣的朋友可以參考下,希望大家閱讀完這篇文章之后大有收獲,下面讓小編帶著大家一起了解一下。
原理分析下:使用adb命令,抓取手機視頻播放的界面,然后通過python的截取和ocr,獲得到題目和答案, 然后百度得到結果。這個環境怎么搭建,有需要的童鞋可以聯系我,因為使用本地的ocr所以解析不花錢,也沒有使用的限制。
github上的代碼中
ocr_bw.py,這個是自動根據題目去百度,然后打開瀏覽器,展示檢索結果
# -*- coding: utf-8 -*-
import pytesseract
import time
import webbrowser
import subprocess
from PIL import Image
def main():
"""
主函數
"""
op = yes_or_no('請確保手機打開了 ADB 并連接了電腦,'
'然后打開西瓜視頻后再用本程序,確定開始?')
if not op:
print('bye')
return
#核心遞歸
ocr_subject_parent()
# for root, sub_dirs, files in os.walk('E:/臨時接收的文件/知乎答題/百萬/'):
# for file in files:
# print('發現圖片:' + file)
# img = Image.open('E:/臨時接收的文件/知乎答題/百萬/'+file)
# ocr_subject(img)
def yes_or_no(prompt, true_value='y', false_value='n', default=True):
"""
檢查是否已經為啟動程序做好了準備
"""
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 = '當出現題目時,請按下回車進行識別 '
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開始 940結束
# 截取 距離上260 570結束
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:" + 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,這個是根據題目+答案,去百度檢索,通過爬蟲抓取百度的收錄數,然后在控制臺打印結果
__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
"""
op = yes_or_no('請確保手機打開了 ADB 并連接了電腦,'
'然后打開西瓜視頻后再用本程序,確定開始?')
if not op:
print('bye')
return
# 核心遞歸
ocr_subject_parent()
# for root, sub_dirs, files in os.walk('E:/臨時接收的文件/知乎答題/百萬/'):
# for file in files:
# print('發現圖片:' + file)
# img = Image.open('E:/臨時接收的文件/知乎答題/百萬/'+file)
# ocr_subject(img)
def yes_or_no(prompt, true_value='y', false_value='n', default=True):
"""
檢查是否已經為啟動程序做好了準備
"""
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 = '當出現題目時,請按下回車進行識別 \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開始 940結束
# 截取 距離上260 570結束
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('百度為您找到相關結果約'))
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不是,所以我更喜歡用第一個方式,基本上識別時間在0.5-0.6秒之間。

最后里面的ocr_zh.py是可以用來抓取頭腦王者的輔助。
感謝你能夠認真閱讀完這篇文章,希望小編分享的“python3.5+tesseract+adb如何實現西瓜視頻或頭腦王者輔助答題”這篇文章對大家有幫助,同時也希望大家多多支持億速云,關注億速云行業資訊頻道,更多相關知識等著你來學習!
免責聲明:本站發布的內容(圖片、視頻和文字)以原創、轉載和分享為主,文章觀點不代表本網站立場,如果涉及侵權請聯系站長郵箱:is@yisu.com進行舉報,并提供相關證據,一經查實,將立刻刪除涉嫌侵權內容。