1+ # -*- coding: utf-8 -*-
2+ # @Time : 2017年8月21日 13:26
3+ # @Author : play4fun
4+ # @File : 获取验证码-然后识别.py
5+ # @Software: PyCharm
6+ 7+ """
8+ 获取验证码-然后识别.py:
9+ """
10+ 11+ from io import BytesIO
12+ from PIL import Image
13+ import requests
14+ from tesserocr import PyTessBaseAPI
15+ import tesserocr
16+ import numpy as np
17+ import cv2
18+ 19+ 20+ user_agent = 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.106 Safari/537.36'
21+ headers = {'User-Agent' : user_agent }
22+ 23+ 24+ url = 'http://www.bjsuperpass.com/captcha.svl?d=1503144107405'
25+ rs = requests .get (url , headers = headers , timeout = 10 )
26+ print ('获取公交一卡通网站的验证码' ,rs .status_code )
27+ 28+ print ('用BytesIO导入到Image,Numpy,Opencv' )
29+ s1 = BytesIO (rs .content ) # img = Image.open(BytesIO(resp.read()))
30+ #
31+ img = Image .open (s1 )
32+ img = img .convert ("RGB" )
33+ im = np .array (img )
34+ cv2 .imshow ('src' ,im )
35+ cv2 .waitKey (0 )
36+ cv2 .imwrite ('captcha.jpg' ,im )
37+ 38+ 39+ ocr = PyTessBaseAPI ()
40+ # ocr.Init(".", "eng", tesseract.OEM_DEFAULT)
41+ ocr .SetVariable ("tessedit_char_whitelist" , "0123456789abcdefghijklmnopqrstuvwxyz" )
42+ # ocr.SetPageSegMode(tesseract.PSM_AUTO)
43+ # ocr.SetImage(img)
44+ 45+ print ('验证码是' ,tesserocr .image_to_text (img ))
0 commit comments