当前位置:首页 >> 脚本专栏

python图片验证码识别最新模块muggle_ocr的示例代码

一.官方文档

https://pypi.org/project/muggle-ocr/

二模块安装

pip install muggle-ocr
# 因模块过新,阿里/清华等第三方源可能尚未更新镜像,因此手动指定使用境外源,为了提高依赖的安装速度,可预先自行安装依赖:tensorflow/numpy/opencv-python/pillow/pyyaml

三.使用代码

# 导入包
import muggle_ocr

# 初始化;model_type 包含了 ModelType.OCR/ModelType.Captcha 两种
sdk = muggle_ocr.SDK(model_type=muggle_ocr.ModelType.OCR)
# ModelType.OCR 可识别光学印刷文本 这里个人觉得应该是官方文档写错了 官方文档是ModelType.Captcha 可识别光学印刷文本
with open(r"test1.png", "rb") as f:
 b = f.read()
text = sdk.predict(image_bytes=b)
print(text)

# ModelType.Captcha 可识别4-6位验证码
sdk = muggle_ocr.SDK(model_type=muggle_ocr.ModelType.Captcha)
with open(r"test1.png", "rb") as f:
 b = f.read()
text = sdk.predict(image_bytes=b)
print(text)

PS:下面看下 Python 实现全自动登录(真正的全自动,自动识别验证码)

你没有看错,全自动验证~~~

黑科技?还是黑代码?
我感觉这个看在你用啥,对不对?反正我用来(* * * * ) 你懂得

好了,先说一下用到的东西

  • selenium (本意是用来全自动测试)
  • Phantomjs (一种没有界面的浏览器)
  • ** 验证码识别器(一块钱可用100次的这种)

关门放代码

from selenium import webdriver
from PIL import Image
if __name__ == '__main__':
 wbe = webdriver.PhantomJS()
 wbe.get("https://www.某个网站的登录页面.com/login/index.html")//你可以拿知乎,百度,等等测试
 element = wbe.find_element_by_xpath('//*[@id="entry_name"]/p[3]/img')//验证码所在的xpath路径
 left = element.location['x']
 top = element.location['y']
 right = element.location['x'] + element.size['width']
 bottom = element.location['y'] + element.size['height']
 im = Image.open(r'登录页.png')//全页面截屏
 im = im.crop((left, top, right, bottom))
 im.save('验证码.png')
#!/usr/bin/env python
# coding:utf-8
import requests
from hashlib import md5
class RClient(object):
 def __init__(self, username, password, soft_id, soft_key):
  self.username = username
  self.password = md5(password).hexdigest()
  self.soft_id = soft_id
  self.soft_key = soft_key
  self.base_params = {
   'username': self.username,
   'password': self.password,
   'softid': self.soft_id,
   'softkey': self.soft_key,
  }
  self.headers = {
   'Connection': 'Keep-Alive',
   'Expect': '100-continue',
   'User-Agent': 'ben',
  }
 def rk_create(self, im, im_type, timeout=60):
  """
  im: 图片字节
  im_type: 题目类型
  """
  params = {
   'typeid': im_type,
   'timeout': timeout,
  }
  params.update(self.base_params)
  files = {'image': ('a.png', im)}
  r = requests.post('http://api.ruokuai.com/create.json', data=params, files=files, headers=self.headers)
  return r.json()
 def rk_report_error(self, im_id):
  """
  im_id:报错题目的ID
  """
  params = {
   'id': im_id,
  }
  params.update(self.base_params)
  r = requests.post('http://api.ruokuai.com/reporterror.json', data=params, headers=self.headers)
  return r.json()
def get_code():
 rc = RClient('用户名', '密码', '94522', '62c235939b7240879453f31603733fd6')//想拿下测试的留言我,教你拿到测试账号
 im = open('a.png', 'rb').read()
 print rc.rk_create(im, 3040)

完整代码

#!/usr/bin/env python
# coding:utf-8
from selenium import webdriver
from PIL import Image
import requests
from hashlib import md5
import time
class RClient(object):
 def __init__(self, username, password, soft_id, soft_key):
  self.username = username
  self.password = md5(password.encode("utf-8")).hexdigest()
  self.soft_id = soft_id
  self.soft_key = soft_key
  self.base_params = {
   'username': self.username,
   'password': self.password,
   'softid': self.soft_id,
   'softkey': self.soft_key,
  }
  self.headers = {
   'Connection': 'Keep-Alive',
   'Expect': '100-continue',
   'User-Agent': 'ben',
  }
 def rk_create(self, im, im_type, timeout=60):
  """
  im: 图片字节
  im_type: 题目类型
  """
  params = {
   'typeid': im_type,
   'timeout': timeout,
  }
  params.update(self.base_params)
  files = {'image': ('a.png', im)}
  r = requests.post('http://api.ruokuai.com/create.json', data=params, files=files, headers=self.headers)
  return r.json()
 def rk_report_error(self, im_id):
  """
  im_id:报错题目的ID
  """
  params = {
   'id': im_id,
  }
  params.update(self.base_params)
  r = requests.post('http://api.ruokuai.com/reporterror.json', data=params, headers=self.headers)
  return r.json()
def get_code(im_file):
 rc = RClient('账号', '密码', '94522', '62c235939b7240879453f31603733fd6')
 im_source = open(im_file, "rb").read()
 print(rc.rk_create(im_source, 3040))
if __name__ == '__main__':
 wbe = webdriver.PhantomJS()
 wbe.get("https://www.dajiang365.com/login/index.html")
 time.sleep(2)
 wbe.save_screenshot("das.png")
 element = wbe.find_element_by_xpath('//*[@id="entry_name"]/p[3]/img')
 left = element.location['x']
 top = element.location['y']
 right = element.location['x'] + element.size['width']
 bottom = element.location['y'] + element.size['height']
 im = Image.open(r'das.png')
 im = im.crop((left, top, right, bottom))
 im.save('a.png')
 time.sleep(2)
 get_code("a.png")

总结