自动识别验证码
（1）光学识别 OCR 其实就是一个软件
- 别对他期望太高，识别率80% 90%
*训练它
代码识别
pip install pytesseract
pip install pillow
转化为灰度图片
img = img.convert('L')
img.show()
二值化处理
threshold = 140
table = []
for i in range(256):
if i < threshold:
table.append(0)
else:
table.append(1)
out = img.point(table, '1')
out.show()
img = img.convert('RGB')
enhancer = ImageEnhance.Color(img)
enhancer = enhancer.enhance(0)
enhancer = ImageEnhance.Brightness(enhancer)
enhancer = enhancer.enhance(2)
enhancer = ImageEnhance.Contrast(enhancer)
enhancer = enhancer.enhance(8)
enhancer = ImageEnhance.Sharpness(enhancer)
img = enhancer.enhance(20)
实例代码如下
import pytesseract
from PIL import Image
from PIL import ImageEnhance
def shibie(imagepath):
img = Image.open(imagepath)
img = img.convert('RGB')
enhancer = ImageEnhance.Color(img)
enhancer = enhancer.enhance(0)
enhancer = ImageEnhance.Brightness(enhancer)
enhancer = enhancer.enhance(2)
enhancer = ImageEnhance.Contrast(enhancer)
enhancer = enhancer.enhance(8)
enhancer = ImageEnhance.Sharpness(enhancer)
img = enhancer.enhance(20)
# 转化为灰度图片
img = img.convert('L')
# img.show()
# 二值化处理
threshold = 140
table = []
for i in range(256):
if i < threshold:
table.append(0)
else:
table.append(1)
out = img.point(table, '1')
# out.show()
img = img.convert('RGB')
return pytesseract.image_to_string(img)
shibie('code.png')
打码平台，专业，识别率高，花钱
云打码平台使用
用户注册（充钱）、开发者注册（创建应用，使用应用识别验证码服务）
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
# 普通账号的用户名
username = ''
# 密码
# 普通账号的密码
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 =
# 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 = ''
# 图片文件
filename = './png/e6ay.png'
# 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.html
codetype = 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))
######################################################################
网友评论