Python3爬虫实战【点触验证码】 — 模拟登陆bilibili

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 = {
            'Connection': 'Keep-Alive',
            '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()

def __init__(self):
    self.url = 'https://passport.bilibili.com/login'
    self.browser = webdriver.Chrome()
    self.browser.maximize_window()
    self.wait = WebDriverWait(self.browser, 20)
    self.username = USERNAME
    self.password = PASSWORD


这里定义了发起请求的url、用户名、密码等全局变量，实例化 Chrome 浏览器、设置浏览器分辨率最大化、用户名、密码、同时也设置等待超时

def open(self):
    """
    打开网页输入用户名密码
    :return: None
    """
    self.browser.get(self.url)
    user = self.wait.until(EC.presence_of_element_located((By.ID, 'login-username')))
    password = self.wait.until(EC.presence_of_element_located((By.ID, 'login-passwd')))
    user.send_keys(self.username)
    password.send_keys(self.password)
    login_btn = self.wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, 'a.btn.btn-login')))
    # 随机暂停几秒
    time.sleep(random.random() * 3)
    # 点击登陆按钮
    login_btn.click()

等待账号输入框和密码输入框对应的 ID 节点加载出来，然后获取对应节点，其中账号输入框 id=“login-username”，密码输框
id=“login-passwd”，通过调用 send_keys() 方法输入账号和密码，接着获取登录按钮 class=“btn
btn-login”，设置暂停时间，最后调用 click() 方法实现登录按钮的点击。

def pick_code(self):
    time.sleep(3)
    pick_img_label = self.browser.find_element_by_css_selector('img.geetest_item_img')  # 获取点触图片标签
    src = pick_img_label.get_attribute('src')  # 获取点触图片链接
    img_content = requests.get(src).content  # 获取图片二进制内容
    f = BytesIO()
    f.write(img_content)
    img0 = Image.open(f)  # 将图片以文件的形式打开，主要是为了获取图片的大小
    scale = [pick_img_label.size['width'] / img0.size[0],
             pick_img_label.size['height'] / img0.size[1]]  # 获取图片与浏览器该标签大小的比例
    cjy = Chaojiying(CHAOJIYING_USERNAME, CHAOJIYING_PASSWORD, CHAOJIYING_SOFT_ID)
    result = cjy.post_pic(img_content, '9005')  # 发送图片并获取结果
    if result['err_no'] == 0:  # 对结果进行分析
        position = result['pic_str'].split('|')  # position = ['110,234','145,247','25,185']
        position = [[int(j) for j in i.split(',')] for i in position]  # position = [[110,234],[145,247],[25,185]]
        for items in position:  # 模拟点击
            ActionChains(self.browser).move_to_element_with_offset(pick_img_label, items[0] * scale[0],
                                                                   items[1] * scale[1]).click().perform()
            time.sleep(1)
        time.sleep(2)
        # 点击登录
        certern_btn = self.browser.find_element_by_css_selector('div.geetest_commit_tip')
        certern_btn.click()
    return cjy, result