tesseract imagename outputbase [-l lang]

#顯示安裝的語言包
tesseract --list-langs

#顯示幫助
tesseract --help
tesseract --help-extra
tesseract --version

pip install pytesseract

import pytesseract
from PIL import Image

im=Image.open('image.png')
print(pytesseract.image_to_string(im))

#安裝tesseract
sudo apt-get install -y tesseract-ocr libtesseract-dev libleptonica-dev

#安裝語言包
git clone https://github.com/tesseract-ocr/tessdata.git
sudo mv tessdata/* /usr/share/tesseract-ocr/tessdata

#安裝tesserocr
pip3 install tesserocr

#安裝pytesseract
pip3 install pytesseract

#安裝tesseract
yum install -y tesseract

#安裝語言包
git clone https://github.com/tesseract-ocr/tessdata.git
mv tessdata/* /usr/share/tesseract/tessdata

#安裝tesserocr
pip3 install tesserocr

#安裝pytesseract
pip3 install pytesseract

#從文件識(shí)別圖像字符
In [7]: tesserocr.file_to_text('image.png')
Out[7]: 'Python3WebSpider\n\n'

#查看tesseract已安裝的語言包
In [8]: tesserocr.get_languages()
Out[8]: ('/usr/share/tesseract/tessdata/', ['eng'])

#從圖片數(shù)據(jù)識(shí)別圖像字符
In [9]: tesserocr.image_to_text(im)
Out[9]: 'Python3WebSpider\n\n'

#查看版本信息
In [10]: tesserocr.tesseract_version()
Out[10]: 'tesseract 3.04.00\n leptonica-1.72\n libgif 4.1.6(?) : libjpeg 6b (libjpeg-turbo 1.2.90) : libpng 1.5.13 : libtiff 4.0.3 : zlib 1.2.7 : libwebp 0.3.0\n'

from PIL import Image
import pytesseract

#如果PATH中沒有tesseract可執(zhí)行文件，請(qǐng)指定tesseract路徑
pytesseract.pytesseract.tesseract_cmd='C:\Program Files (x86)\Tesseract-OCR\\tesseract.exe'

#打印識(shí)別的圖像的字符串
print(pytesseract.image_to_string(Image.open('test.png')))

#指定語言識(shí)別圖像字符串,eng為英語
print(pytesseract.image_to_string(Image.open('test-european.jpg'), lang='eng'))

#獲取圖像邊界框
print(pytesseract.image_to_boxes(Image.open('test.png')))

#獲取包含邊界框，置信度，行和頁碼的詳細(xì)數(shù)據(jù)
print(pytesseract.image_to_data(Image.open('test.png')))

#獲取方向和腳本檢測(cè)
print(pytesseract.image_to_osd(Image.open('test.png'))

from PIL import Image
import pytesseract

im = Image.open('66.png')
#二值化圖像傳入圖像和閾值
def erzhihua(image,threshold):
  ''':type image:Image.Image'''
  image=image.convert('L')
  table=[]
  for i in range(256):
    if i < threshold:
      table.append(0)
    else:
      table.append(1)
  return image.point(table,'1')


image=erzhihua(im,127)
image.show()

result=pytesseract.image_to_string(image,lang='eng')
print(result)

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time  : 2018/7/13 8:58
# @Author : Py.qi
# @File  : login.py
# @Software: PyCharm
from selenium import webdriver
from selenium.common.exceptions import TimeoutException,WebDriverException
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.remote.webelement import WebElement
from io import BytesIO
from PIL import Image
import pytesseract
import time

user='zhang'
password='123'
url='http://10.0.0.200'
driver=webdriver.Chrome()
wait=WebDriverWait(driver,10)

#識(shí)別驗(yàn)證碼
def acker(content):
  im_erzhihua=erzhihua(content,127)
  result=pytesseract.image_to_string(im_erzhihua,lang='eng')
  return result

#驗(yàn)證碼二值化
def erzhihua(image,threshold):
  ''':type image:Image.Image'''
  image=image.convert('L')
  table=[]
  for i in range(256):
    if i < threshold:
      table.append(0)
    else:
      table.append(1)
  return image.point(table,'1')

#自動(dòng)登陸
def login():
  try:
    driver.get(url)
    #獲取用戶輸入框
    input=wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#loginname'))) #type:WebElement
    input.clear()
    #發(fā)送用戶名
    input.send_keys(user)
    #獲取密碼框
    inpass=wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#password'))) #type:WebElement
    inpass.clear()
    #發(fā)送密碼
    inpass.send_keys(password)
    #獲取驗(yàn)證輸入框
    yanzheng=wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#code'))) #type:WebElement
    #獲取驗(yàn)證碼在畫布中的位置
    codeimg=wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#codeImg'))) #type:WebElement
    image_location = codeimg.location
    #截取頁面圖像并截取掩碼碼區(qū)域圖像
    image=driver.get_screenshot_as_png()
    im=Image.open(BytesIO(image))
    imag_code=im.crop((image_location['x'],image_location['y'],488,473))
    #輸入驗(yàn)證碼并登陸
    yanzheng.clear()
    yanzheng.send_keys(acker(imag_code))
    time.sleep(2)
    yanzheng.send_keys(Keys.ENTER)
  except TimeoutException as e:
    print('timeout:',e)
  except WebDriverException as e:
    print('webdriver error:',e)

if __name__ == '__main__':
  login()