机器视觉  - tesseract ( 验证码 )

安装

Ubuntu

sudo apt-get install tesseract-ocr

Windows

下载安装包

添加环境变量(Path) ：搜索 环境变量

测试

终端 ：tesseract xx.jpg 文件名

pytesseract 

识别成功率取决你的 tessdata 的质量

自带的质量就很炸, 所以基本上没什么用

安装

sudo pip3 install pytesseract

 

简单使用

import pytesseract# python 标准化图片处理组件from PIL import Image# 创建图片对象img = Image.open('yzm1.jpg')# 图片转字符串r = pytesseract.image_to_string(img)print(r)

 

在线打码平台

tesseract-ocr 识别率有点辛苦, 因此不太实用

使用在线打码会性价比高一点

在线打码, 云打码

网址

官方文档 

import http.client, mimetypes, urllib, json, time, requests######################################################################class YDMHttp:    apiurl = 'http://api.yundama.com/api.php'    username = ''    password = ''    appid = ''    appkey = ''    def __init__(self, username, password, appid, appkey):        self.username = username        self.password = password        self.appid = str(appid)        self.appkey = appkey    def request(self, fields, files=[]):        response = self.post_url(self.apiurl, fields, files)        response = json.loads(response)        return response    def balance(self):        data = {
   'method': 'balance', 'username': self.username, 'password': self.password, 'appid': self.appid,                'appkey': self.appkey}        response = self.request(data)        if (response):            if (response['ret'] and response['ret'] < 0):                return response['ret']            else:                return response['balance']        else:            return -9001    def login(self):        data = {
   'method': 'login', 'username': self.username, 'password': self.password, 'appid': self.appid,                'appkey': self.appkey}        response = self.request(data)        if (response):            if (response['ret'] and response['ret'] < 0):                return response['ret']            else:                return response['uid']        else:            return -9001    def upload(self, filename, codetype, timeout):        data = {
   'method': 'upload', 'username': self.username, 'password': self.password, 'appid': self.appid,                'appkey': self.appkey, 'codetype': str(codetype), 'timeout': str(timeout)}        file = {
   'file': filename}        response = self.request(data, file)        if (response):            if (response['ret'] and response['ret'] < 0):                return response['ret']            else:                return response['cid']        else:            return -9001    def result(self, cid):        data = {
   'method': 'result', 'username': self.username, 'password': self.password, 'appid': self.appid,                'appkey': self.appkey, 'cid': str(cid)}        response = self.request(data)        return response and response['text'] or ''    def decode(self, filename, codetype, timeout):        cid = self.upload(filename, codetype, timeout)        if (cid > 0):            for i in range(0, timeout):                result = self.result(cid)                if (result != ''):                    return cid, result                else:                    time.sleep(1)            return -3003, ''        else:            return cid, ''    def report(self, cid):        data = {
   'method': 'report', 'username': self.username, 'password': self.password, 'appid': self.appid,                'appkey': self.appkey, 'cid': str(cid), 'flag': '0'}        response = self.request(data)        if (response):            return response['ret']        else:            return -9001    def post_url(self, url, fields, files=[]):        for key in files:            files[key] = open(files[key], 'rb');        res = requests.post(url, files=files, data=fields)        return res.text####################################################################### 用户名username = 'username'# 密码password = 'password'# 软件ＩＤ，开发者分成必要参数。登录开发者后台【我的软件】获得！appid = 1# 软件密钥，开发者分成必要参数。登录开发者后台【我的软件】获得！appkey = '22cc5376925e9387a23cf797cb9ba745'# 图片文件filename = 'getimage.jpg'# 验证码类型，# 例：1004表示4位字母数字，不同类型收费不同。请准确填写，否则影响识别率。在此查询所有类型 http://www.yundama.com/price.htmlcodetype = 1004# 超时时间，秒timeout = 60# 检查if (username == 'username'):    print('请设置好相关参数再测试')else:    # 初始化    yundama = YDMHttp(username, password, appid, appkey)    # 登陆云打码    uid = yundama.login();    print('uid: %s' % uid)    # 查询余额    balance = yundama.balance();    print('balance: %s' % balance)    # 开始识别，图片路径，验证码类型ID，超时时间（秒），识别结果    cid, result = yundama.decode(filename, codetype, timeout);    print('cid: %s, result: %s' % (cid, result))######################################################################