python2验证码识别

今日就给大家分析一下简单的解决验证码识别的问题，开讲：

首先这是一串验证码链接：

https://credit.wsjd.gov.cn/portal/captcha
然后我们去解析这串链接，再利用pytesseract，PIL这两个库对验证码进行识别，废话不多说，直接开干，代码：

import pytesseract
import urllib2
from PIL import Image
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
headers = {
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
    'Accept-Encoding': 'gzip, deflate, br',
    'Connection': 'keep-alive',
    'Host': 'credit.wsjd.gov.cn',
    'Upgrade-Insecure-Requests': '1',
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36',
}
url = 'https://credit.wsjd.gov.cn/portal/captcha'
request = urllib2.Request(url,headers=headers)
res = urllib2.urlopen(request).read()
try:
    captchaFile = 'yishi/static/images/credit_captcha.png'#这个是创建一个文件来存放解析出来的验证码
    with open(captchaFile, 'wb') as f:
        f.write(res)
　　#对验证码进行识别
    image = Image.open(captchaFile)
    captcha_value = pytesseract.image_to_string(image)
    print '验证码为：'+captcha_value
except IOError,e:
    #验证码失败 重新请求
    print('验证码获取失败')
    print(e)