python 爬虫带验证的模拟登陆

from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
import pytesseract
from PIL import Image

dcap = dict(DesiredCapabilities.PHANTOMJS)
dcap["phantomjs.page.settings.userAgent"] = (
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36"
)

def login_epubit():
    driver = webdriver.PhantomJS(desired_capabilities=dcap,service_args=['--ignore-ssl-errors=true', '--ssl-protocol=TLSv1'])                                            driver.get('https://www.epubit.com/login')
    driver.set_window_size(1200, 60)
    driver.get_screenshot_as_file("test2.jpg")                                                                                                                           element = driver.find_element_by_xpath('//*[@id="login"]/div/div/div[1]/ul/li/form/div[3]/div/div/div[2]/img')
    print(element.location)
    print(element.size)

    left = element.location['x']
    top = element.location['y']
    right = element.location['x'] + element.size['width']
    bottom = element.location['y'] + element.size['height']

    im = Image.open('test2.jpg')
    im = im.crop((left, top, right, bottom))
    im.save('kapcha.png')


    img = Image.open('kapcha.png')
    code = pytesseract.image_to_string(img)

    print code


if __name__ == '__main__':
    login_epubit()