Python 爬虫：使用打码平台来识别各种验证码：

本课程使用的是超级鹰打码平台，没有账户的请自行注册！

超级鹰验证码识别-专业的验证码云端识别服务,让验证码识别更快速、更准确、更强大

使用打码平台来攻破验证码难题，是很简单容易的，但是要钱！

案例代码及测试资源：

git clone https://github.com/Python3WebSpider/CaptchaPlatform.git

使用git 将资源拽取下来，然后你会发现多了一个文件夹，文件夹中有一个chaojiying.py 文件，这里面就是基于官方 SDK 改写的代码：

username: 用户名，你注册的超级鹰用户。

password：密码

soft_id: 软件ID。

import requests
from hashlib import md5

class Chaojiying(object):
    
    def __init__(self, username, password, soft_id):
        self.username = username
        self.password = md5(password.encode('utf-8')).hexdigest()
        self.soft_id = soft_id
        self.base_params = {
            'user': self.username,
            'pass2': self.password,
            'softid': self.soft_id,
        }
        self.headers = {
            'User-Agent': 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0)',
        }
    
    def post_pic(self, im, codetype):
        """
        im: 图片字节
        codetype: 题目类型 参考 http://www.chaojiying.com/price.html
        """
        params = {
            'codetype': codetype,
        }
        params.update(self.base_params)
        files = {'userfile': ('ccc.jpg', im)}
        r = requests.post('http://upload.chaojiying.net/Upload/Processing.php', data=params, files=files,
                          headers=self.headers)
        return r.json()
    
    def report_error(self, im_id):
        """
        im_id:报错题目的图片ID
        """
        params = {
            'id': im_id,
        }
        params.update(self.base_params)
        r = requests.post('http://upload.chaojiying.net/Upload/ReportError.php', data=params, headers=self.headers)
        return r.json()

图片验证码：

CAPTCHA_KIND 则为图片的类型，可以在验证码类型与价格表-超级鹰验证码识别看到。

from chaojiying import Chaojiying

USERNAME = '136xxxx108'
PASSWORD = 'xxxxxx'
SOFT_ID = 'xxxxxxxx'
CAPTCHA_KIND = '1006'
FILE_NAME = 'captcha1.png'
client = Chaojiying(USERNAME, PASSWORD, SOFT_ID)
result = client.post_pic(open(FILE_NAME, 'rb').read(), CAPTCHA_KIND)
print(result)

点选验证码：

from chaojiying import Chaojiying

USERNAME = 'xxx'
PASSWORD = ''
SOFT_ID = 'xxxxxx'
CAPTCHA_KIND = '9004'
FILE_NAME = 'captcha2.png'
client = Chaojiying(USERNAME, PASSWORD, SOFT_ID)
result = client.post_pic(open(FILE_NAME, 'rb').read(), CAPTCHA_KIND)
print(result)

得到的响应结果为：

{'err_no': 0, 'err_str': 'OK', 'pic_id': '2256514491185230017', 'pic_str': '118,177|249,173', 'md5': 'e89f632e91cc6b8a85dad2fbbc13c803'}

可以看到图片的坐标信息为： '118,177|249,173' 使用opencv 技术来标记这个点测试一下：

import cv2

image = cv2.imread('captcha2.png')
image = cv2.circle(image, (108, 133), radius=10, color=(0, 0, 255), thickness=-1)
image = cv2.circle(image, (227, 143), radius=10, color=(0, 0, 255), thickness=-1)
cv2.imwrite('captcha2_label.png', image)

滑块验证码：

from chaojiying import Chaojiying

USERNAME = '136xxxx08'
PASSWORD = 'hxxxxx.'
SOFT_ID = '9xxxx'
CAPTCHA_KIND = '9101'
FILE_NAME = 'captcha5.png'
client = Chaojiying(USERNAME, PASSWORD, SOFT_ID)
result = client.post_pic(open(FILE_NAME, 'rb').read(), CAPTCHA_KIND)
print(result)

{'err_no': 0, 'err_str': 'OK', 'pic_id': '1256519431185230022', 'pic_str': '218,96', 'md5': '627d620bccd9a6dd1366329b951f1511'}

使用OpenCV测试验证一下：

import cv2

image = cv2.imread('captcha2.png')
image = cv2.circle(image, (231, 85), radius=10, color=(0, 0, 255), thickness=-1)
cv2.imwrite('captcha3_label.png', image)

可以看到，不是很准确，我们可以向打码平台的工作人员传递一些信息，尽可能的标记的准确一些：

from chaojiying import Chaojiying

import cv2
from PIL import ImageFont, ImageDraw, Image
import numpy as np
import io


def cv2_add_text(image, text, left, top, textColor=(255, 0, 0), text_size=20):
    image = Image.fromarray(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
    draw = ImageDraw.Draw(image)
    font = ImageFont.truetype('simsun.ttc', text_size, encoding="utf-8")
    draw.text((left, top), text, textColor, font=font)
    return cv2.cvtColor(np.asarray(image), cv2.COLOR_RGB2BGR)


USERNAME = '136XXXX08'
PASSWORD = 'hXXXXXXXXXXX..'
SOFT_ID = '9XXXXXXX2'
CAPTCHA_KIND = '9101'
FILE_NAME = 'captcha3.png'
image = cv2.imread(FILE_NAME)
image = cv2_add_text(image, '请点击目标滑块左上角', int(image.shape[1] / 10), int(image.shape[0] / 2), (255, 0, 0), 40)
client = Chaojiying(USERNAME, PASSWORD, SOFT_ID)
result = client.post_pic(io.BytesIO(cv2.imencode(
    '.png', image)[1]).getvalue(), CAPTCHA_KIND)
print(result)