使用pytesserac和Pillow实现验证码识别

可以使用pytesseract模块和PIL模块解决不太复杂的验证码问题

image.png

简单网页验证码解决思路：
截屏整个页面
获得验证码坐标数据
根据坐标数据抠图
使用pytesseract模块进行验证

import time

import re
from PIL import Image
from selenium import webdriver
import pytesseract

def test1():
    browser = webdriver.Chrome()
    browser.get('http://localhost:8188/jpress/user/register')
    browser.maximize_window()

    #获取验证码图片
    t = time.time()
    picture_name1 = str(t)+'.png'
    browser.save_screenshot(picture_name1)

    ce = browser.find_element_by_id("captchaimg")
    print(ce.location)
    left = ce.location['x']
    top = ce.location['y']
    right = ce.size['width'] + left
    height = ce.size['height'] + top

    #普通屏幕：
    #im = Image.open(picture_name1)
    #crop抠图
    #img = im.crop((left,top,right,height))

    #如果是retina屏幕需要这样：
    dpr = browser.execute_script('return window.devicePixelRatio')
    print(dpr)
    im = Image.open(picture_name1)
    img = im.crop((left * dpr, top * dpr, right * dpr, height * dpr))

    t = time.time()
    picture_name2 = str(t)+'.png'

    img.save(picture_name2)
    browser.close()

def test2():
    image1 = Image.open('test.jpg')
    str = pytesseract.image_to_string(image1)
    result = re.sub(u"([^\u4e00-\u9fa5\u0030-\u0039\u0041-\u005a\u0061-\u007a])", "", str)  # 去除识别出来的特殊字符
    #result_four = result[0:4]  # 只获取前4个字符
    print(result)