Python爬虫之超级鹰验证码应用

import requests
from hashlib import md5
class ChaojiyingClient(object):
    def __init__(self, username, password, soft_id):
        self.username = username
        password = password.encode('utf8')
        self.password = md5(password).hexdigest()
        self.soft_id = soft_id
        self.base_params = {
            'user': self.username,
            'pass2': self.password,
            'softid': self.soft_id,
        }
        self.headers = {
            'Connection': 'Keep-Alive',
            'User-Agent': 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0)',
        }
    def PostPic(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 PostPic_base64(self, base64_str, codetype):
        """
        im: 图片字节
        codetype: 题目类型 参考 http://www.chaojiying.com/price.html
        """
        params = {
            'codetype': codetype,
            'file_base64': base64_str
        }
        params.update(self.base_params)
        r = requests.post('http://upload.chaojiying.net/Upload/Processing.php', data=params, headers=self.headers)
        return r.json()
    def ReportError(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()
if __name__ == '__main__':
    chaojiying = ChaojiyingClient('超级鹰用户名', '超级鹰用户名的密码', '96001')  # 用户中心>>软件ID 生成一个替换 96001
    im = open('a.jpg', 'rb').read()  # 本地图片文件路径 来替换 a.jpg 有时WIN系统须要//
    print(chaojiying.PostPic(im, 1902))  # 1902 验证码类型  官方网站>>价格体系 3.4+版 print 后要加()
    # print chaojiying.PostPic(base64_str, 1902)  #此处为传入 base64代码

from selenium import webdriver
from selenium.webdriver.common.by import By
from PIL import Image
from selenium.webdriver.chrome.options import Options
from chaojiying import chaojiying_Python
chrome_options = Options()
chrome_options.add_argument('window-size=1920x1080')  # 指定浏览器分辨率
chrome_options.add_argument('--disable-gpu')  # 谷歌文档提到需要加上这个属性来规避bug
chrome_options.add_argument('--hide-scrollbars')  # 隐藏滚动条, 应对一些特殊页面
# chrome_options.add_argument('blink-settings=imagesEnabled=false')  # 不加载图片, 提升速度
chrome_options.add_argument('--headless')  # 浏览器不提供可视化页面. linux下如果系统不支持可视化不加这条会启动失败
# chrome = webdriver.Chrome(executable_path='../chromedriver.exe')
chrome = webdriver.Chrome(executable_path='../chromedriver.exe', options=chrome_options)
chrome.implicitly_wait(10)
chrome.maximize_window()
try:
    chrome.get('http://www.aa7a.cn/user.php?')
    username = chrome.find_element(By.ID, 'username')
    password = chrome.find_element(By.ID, 'password')
    captcha = chrome.find_element(By.ID, 'captcha')
    # 保存大图
    chrome.save_screenshot('main.png')
    img = chrome.find_element(By.ID, 'login_img_checkcode')
    img_location = img.location
    img_size = img.size
    # 使用pillow扣除大图中的验证码
    img_tu = (
        int(img_location['x']),
        int(img_location['y']),
        int(img_location['x'] + img_size['width']),
        int(img_location['y'] + img_size['height']),
    )
    # 打开页面大图
    im = Image.open('./main.png')
    # 剪切验证码图片
    fram = im.crop(img_tu)
    # 保存验证码图片
    fram.save('code.png')
    # 打开验证码图片
    code_img = open('code.png', 'rb').read()
    # 调用超级鹰识别
    res = chaojiying_Python.chaojiying.PostPic(code_img, 1902)
    code = res.get('pic_str')
    username.send_keys('username')
    password.send_keys('123')
    captcha.send_keys(code)
    print(code)
except Exception as e:
    print(e)
finally:
    chrome.quit()