Python爬蟲之超級鷹驗證碼應用

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: 圖片位元組
        codetype: 題目型別 參考 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: 圖片位元組
        codetype: 題目型別 參考 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:報錯題目的圖片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('超級鷹使用者名稱', '超級鷹使用者名稱的密碼', '96001')  # 使用者中心>>軟體ID 生成一個替換 96001
    im = open('a.jpg', 'rb').read()  # 本地圖片檔案路徑 來替換 a.jpg 有時WIN系統須要//
    print(chaojiying.PostPic(im, 1902))  # 1902 驗證碼型別  官方網站>>價格體系 3.4+版 print 後要加()
    # print chaojiying.PostPic(base64_str, 1902)  #此處為傳入 base64程式碼

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')  # 指定瀏覽器解析度
chrome_options.add_argument('--disable-gpu')  # 谷歌檔案提到需要加上這個屬性來規避bug
chrome_options.add_argument('--hide-scrollbars')  # 隱藏卷軸, 應對一些特殊頁面
# chrome_options.add_argument('blink-settings=imagesEnabled=false')  # 不載入圖片, 提升速度
chrome_options.add_argument('--headless')  # 瀏覽器不提供視覺化頁面. linux下如果系統不支援視覺化不加這條會啟動失敗
# 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')
    # 儲存大圖
    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扣除大圖中的驗證碼
    img_tu = (
        int(img_location['x']),
        int(img_location['y']),
        int(img_location['x'] + img_size['width']),
        int(img_location['y'] + img_size['height']),
    )
    # 開啟頁面大圖
    im = Image.open('./main.png')
    # 剪下驗證碼圖片
    fram = im.crop(img_tu)
    # 儲存驗證碼圖片
    fram.save('code.png')
    # 開啟驗證碼圖片
    code_img = open('code.png', 'rb').read()
    # 呼叫超級鷹識別
    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()