#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import glob
from os import path
import os
import pytesseract
from PIL import Image
from queue import Queue
import threading
import datetime
import cv2

def convertimg(picfile, outdir):
  '''調(diào)整圖片大小，對于過大的圖片進(jìn)行壓縮
  picfile:  圖片路徑
  outdir：  圖片輸出路徑
  '''
  img = Image.open(picfile)
  width, height = img.size
  while (width * height > 4000000): # 該數(shù)值壓縮后的圖片大約 兩百多k
    width = width // 2
    height = height // 2
  new_img = img.resize((width, height), Image.BILINEAR)
  new_img.save(path.join(outdir, os.path.basename(picfile)))


def baiduOCR(ts_queue):
  while not ts_queue.empty():
    picfile = ts_queue.get()
    filename = path.basename(picfile)
    outfile = 'D:\Study\pythonProject\scrapy\IpProxy\port_zidian.txt'
    img = cv2.imread(picfile, cv2.IMREAD_COLOR)
    print("正在識別圖片：\t" + filename)
    message = pytesseract.image_to_string(img,lang = 'eng')
    message = message.replace('', '')
    message = message.replace('\n', '')
    # message = client.basicAccurate(img)  # 通用文字高精度識別，每天 800 次免費(fèi)
    #print("識別成功！"))
    try:
      filename1 = filename.split('.')[0]
      filename1 = ''.join(filename1)
      with open(outfile, 'a+') as fo:
        fo.writelines('\'' + filename1 + '\'' + ':' + message + ',')
        fo.writelines('\n')
        # fo.writelines("+" * 60 + '\n')
        # fo.writelines("識別圖片：\t" + filename + "\n" * 2)
        # fo.writelines("文本內(nèi)容：\n")
        # # 輸出文本內(nèi)容
        # for text in message.get('words_result'):
        #   fo.writelines(text.get('words') + '\n')
        # fo.writelines('\n' * 2)
      os.remove(filename)
      print("識別成功！")
    except:
      print('識別失敗')



    print("文本導(dǎo)出成功！")
    print()
def duqu_tupian(dir):
  ts_queue = Queue(10000)

  outdir = dir
  # if path.exists(outfile):
  #   os.remove(outfile)
  if not path.exists(outdir):
    os.mkdir(outdir)
  print("壓縮過大的圖片...")
  # 首先對過大的圖片進(jìn)行壓縮，以提高識別速度，將壓縮的圖片保存與臨時(shí)文件夾中
  try:
    for picfile in glob.glob(r"D:\Study\pythonProject\scrapy\IpProxy\tmp\*"):
      convertimg(picfile, outdir)
    print("圖片識別...")
    for picfile in glob.glob("tmp1/*"):
      ts_queue.put(picfile)
      #baiduOCR(picfile, outfile)
      #os.remove(picfile)
    print('圖片文本提取結(jié)束！文本輸出結(jié)果位于文件中。' )
    #os.removedirs(outdir)
    return ts_queue
  except:
    print('失敗')

if __name__ == "__main__":

  start = datetime.datetime.now().replace(microsecond=0)
  t = 'tmp1'
  s = duqu_tupian(t)
  threads = []
  try:
    for i in range(100):
      t = threading.Thread(target=baiduOCR, name='th-' + str(i), kwargs={'ts_queue': s})
      threads.append(t)
    for t in threads:
      t.start()
    for t in threads:
      t.join()
    end = datetime.datetime.now().replace(microsecond=0)
    print('刪除耗時(shí)：' + str(end - start))
  except:
    print('識別失敗')