python使用Tesseract库实现识别验证

一、Tesseract简介

#根据下载安装文件的路径配置环境变量
set TESSDATA_PREFIX F:\Tesseract-OCR\

import pytesseract
from PIL import Image
#1.引入Tesseract程序
pytesseract.pytesseract.tesseract_cmd = r'F:\Tesseract-OCR\tesseract.exe'
#2.使用Image模块下的Open()函数打开图片
image = Image.open('6.jpg',mode='r')
print(image)
#3.识别图片文字
code= pytesseract.image_to_string(image)
print(code)

import requests
import time
import pytesseract
from PIL import Image
from bs4 import BeautifulSoup

def captcha(data):
  with open('captcha.jpg','wb') as fp:
    fp.write(data)
  time.sleep(1)
  image = Image.open("captcha.jpg")
  text = pytesseract.image_to_string(image)
  print "机器识别后的验证码为：" + text
  command = raw_input("请输入Y表示同意使用，按其他键自行重新输入：")
  if (command == "Y" or command == "y"):
    return text
  else:
    return raw_input('输入验证码：')

def zhihuLogin(username,password):

  # 构建一个保存Cookie值的session对象
  sessiona = requests.Session()
  headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:47.0) Gecko/20100101 Firefox/47.0'}

  # 先获取页面信息，找到需要POST的数据（并且已记录当前页面的Cookie）
  html = sessiona.get('https://HdhCmsTestzhihu测试数据/#signin', headers=headers).content

  # 找到 name 属性值为 _xsrf 的input标签，取出value里的值
  _xsrf = BeautifulSoup(html ,'lxml').find('input', attrs={'name':'_xsrf'}).get('value')

  # 取出验证码，r后面的值是Unix时间戳,time.time()
  captcha_url = 'https://HdhCmsTestzhihu测试数据/captcha.gif?r=%d&type=login' % (time.time() * 1000)
  response = sessiona.get(captcha_url, headers = headers)


  data = {
    "_xsrf":_xsrf,
    "email":username,
    "password":password,
    "remember_me":True,
    "captcha": captcha(response.content)
  }

  response = sessiona.post('https://HdhCmsTestzhihu测试数据/login/email', data = data, headers=headers)
  print response.text

  response = sessiona.get('https://HdhCmsTestzhihu测试数据/people/maozhaojun/activities', headers=headers)
  print response.text


if __name__ == "__main__":
  #username = raw_input("username")
  #password = raw_input("password")
  zhihuLogin('xxxx@qq测试数据','ALAxxxxIME')