Last active
September 9, 2018 06:30
-
-
Save zhangjaycee/ddb53306e49125fd6ab6f7da6d9b5d54 to your computer and use it in GitHub Desktop.
"百万英雄"辅助工具 http://blog.jcix.top/2018-01-12/million_ocr/
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/local/bin/python | |
# -*- coding: utf-8 -*- | |
import pytesseract | |
from PIL import Image | |
from PIL import ImageGrab | |
import webbrowser | |
import time | |
import jieba | |
import urllib | |
import threading | |
from multiprocessing import Process, Queue | |
#DEBUG = True | |
DEBUG = False | |
#CUT = False | |
CUT = True | |
def start_browser(s): | |
#pass | |
webbrowser.open_new_tab(s) | |
def options(q): | |
o = ImageGrab.grab((60, 395, 380, 640)) | |
if DEBUG: | |
o.save('/Users/Jaycee/test/ocr/iphone/options.png') | |
ostr = pytesseract.image_to_string(o, lang='chi_sim').encode(encoding='UTF-8',errors='strict') | |
ostr_l = ostr.split('\n') | |
q.put(ostr_l) | |
#@profile | |
def main(): | |
while True: | |
t00 = time.time() | |
q = Queue(maxsize = 10) | |
o_p = Process(target = options, args = (q, )) | |
o_p.start() | |
# (y1, x1, y2, x2) | |
# 50 170 520 320 | |
# 40 140 445 300 | |
image = ImageGrab.grab((50, 170, 540, 330)) | |
t0 = time.time() | |
#image = ImageGrab.grab((40, 140, 455, 300)) | |
#image.save('/Users/Jaycee/test/ocr/iphone/1.png') | |
if DEBUG: | |
t1 = time.time() # grab time | |
grab_time = t1 - t0 | |
image.save('/Users/Jaycee/test/ocr/iphone/1.png') | |
#image = Image.open('/Users/Jaycee/test/ocr/iphone/1.png') | |
t1 = time.time() | |
# open image | |
#code = pytesseract.image_to_string(image, lang='chi_sim').encode(encoding='UTF-8',errors='strict') | |
code = pytesseract.image_to_string(image, lang='chi_sim') | |
print code | |
if CUT: | |
jieba_s = jieba.cut_for_search(code) | |
jieba_s = ' '.join(jieba_s) | |
code = jieba_s | |
if DEBUG: | |
t2 = time.time() # ocr time | |
ocr_time = t2 - t1 | |
url = "http://www.baidu.com/s?rn=50&wd=" + code.encode(encoding='UTF-8',errors='strict') | |
#url = "https://www.google.com/search?q=" + code.encode(encoding='UTF-8',errors='strict') | |
p = Process(target = start_browser, args = (url, )) | |
p.start() | |
if DEBUG: | |
t3 = time.time() | |
open_browser_time = t3 - t2 | |
t000 = time.time() | |
res = urllib.urlopen(url).read() | |
t111 = time.time() | |
print "Download Html Time:", t111 - t000 | |
o_p.join() | |
ostr_l = q.get() | |
try: | |
o1str = ostr_l[0] | |
o2str = ostr_l[2] | |
o3str = ostr_l[4] | |
except: | |
a = raw_input("Error! Press 'Enter' to process next..") | |
continue | |
else: | |
pass | |
o1str_c = jieba.cut_for_search(o1str) | |
o2str_c = jieba.cut_for_search(o2str) | |
o3str_c = jieba.cut_for_search(o3str) | |
o1cnt = 0 | |
o2cnt = 0 | |
o3cnt = 0 | |
for i in o1str_c: | |
o1cnt += res.count(i.encode(encoding='UTF-8')) | |
for i in o2str_c: | |
o2cnt += res.count(i.encode(encoding='UTF-8')) | |
for i in o3str_c: | |
o3cnt += res.count(i.encode(encoding='UTF-8')) | |
if DEBUG: | |
t4 = time.time() | |
option_count_time = t4 - t3 | |
print "grab time:", grab_time, "ocr time:", ocr_time, "open browser time:", open_browser_time, "open_browser_time:", open_browser_time | |
print "A:\t[OCR] %s [COUNT] %d" % (o1str, o1cnt) | |
print "B:\t[OCR] %s [COUNT] %d" % (o2str, o2cnt) | |
print "C:\t[OCR] %s [COUNT] %d" % (o3str, o3cnt) | |
t11 = time.time() | |
print "Total Time:", t11-t00 | |
a = raw_input("Press 'Enter' to process next..") | |
if __name__ == "__main__": | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment