python3 识别图片文字

  1、下载相关组件

    安装:pip install Pillow 或下载:https://pypi.org/project/Pillow/5.2.0/  ,https://pypi.org/project/Pillow/5.2.0/#filesPillow-5.2.0-cp36-cp36m-win_amd64.whl

       下载后:在C:\Python36\Scripts目录下:pip install Pillow-5.2.0-cp36-cp36m-win_amd64.whl

    安装:pip3 install pytesseract   或下载安装:pytesseract-0.2.4.tar.gz 或 https://pypi.org/project/pytesseract/#files

 

    下载:tesseract-ocr-w64-setup-v4.0.0-beta.1.20180608.exe 安装,参见:图片文字OCR识别-tesseract-ocr

  2、实例程序

    

#coding:utf8
import os
from PIL import Image
import pytesseract

file=r"D:\work\python36_crawl\pictureParser\中文.png"
# file=r"D:\work\python36_crawl\pictureParser\英文.png"
if os.path.exists(file):
    image = Image.open(file)
    # 英文
    # vcode = pytesseract.image_to_string(image,"eng")
    vcode = pytesseract.image_to_string(image, "chi_sim")
    print(vcode)

 

 验证码相关链接:https://zhuanlan.zhihu.com/p/30871712

posted on 2018-07-27 11:47  shaomine  阅读(3537)  评论(0编辑  收藏  举报