C-C-L-spider/register.py

#手动指定Chrome浏览器的路径
from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By
import ddddocr
import json
# from selenium.webdriver.chrome.service import Service
import time
import os

def register_file(file_name):#开辟新道路
    if not os.path.exists(file_name):
        os.makedirs(file_name)
    
def register_start():
    options = webdriver.ChromeOptions()
    options.binary_location = "F:/Chrome114/APP/Chrome-bin/chrome.exe"#实际是104，版本问题，需要调用104版chrome【114->104】
    # 防止打印一些无用的日志
    options.add_experimental_option("excludeSwitches", ['enable-automation', 'enable-logging'])

    # 具体操作为在创建Chrome()对象时，添加executable_path参数指定为chromedriver.exe的路径
    
    driver2 = webdriver.Chrome(options=options,executable_path=r'F:/scrapyer/chromedriver2.exe')#校验cookies是否正确
    driver = webdriver.Chrome(options=options,executable_path=r'F:/scrapyer/chromedriver2.exe')#启动驱动

    # 绕过机制检测
    driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
        "source": """
        Object.defineProperty(navigator, 'webdriver', {
        get: () => false
        })
    """
    })

    driver2.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
        "source": """
        Object.defineProperty(navigator, 'webdriver', {
        get: () => false
        })
    """
    })

    # 打开网页,不要使用VPN会被断链
    driver.get('https://www.qb5.ch/')
    '''如果用了VPN：加上
    chrome_options = webdriver.ChromeOptions()
    chrome_options.add_argument('--ignore-certificate-errors') √
    driver = webdriver.Chrome(options=chrome_options)
    '''
    # time.sleep(5)
    '''
    # 登录账号密码，点击登录
        -定位输入框<元素定位>，然后再输入内容
        I. css选择器
        II. xpath节点提取
    出现哎呀出戳了，是因为网站检测到了你在使用selenium --> 绕过机制检测 #解决方案 //19绕过机制检测
    '''
    driver.find_element(By.CSS_SELECTOR,'body > div.header > div.header-right > div > a:nth-child(2)').click()#点击登录按钮
    time.sleep(1)
    driver.find_element(By.CSS_SELECTOR,'#username').send_keys('lchnbnb1')#send_key('发送内容')
    driver.find_element(By.CSS_SELECTOR,'#password').send_keys('admin666')

    #多次尝试后人工筛选的错误补充
    Error_str = ['日','l','引']
    Error_int = ['8','1','3']
    Error_identification = dict(zip(Error_str, Error_int))

    ocr = ddddocr.DdddOcr()#图片识别库
    while True:
        time.sleep(2)
        img = driver.find_element(By.CSS_SELECTOR,'#main > div.login-main > form > fieldset > p:nth-child(3) > img')
        img.screenshot('end\\data\\qb5.png')
        #实例化对象
        #读取图片内容
        f = open('end\\data\\qb5.png','rb')
        img = f.read()
        result = ocr.classification(img)
        time.sleep(1)
        print(result)
        if len(result) != 4:
            time.sleep(2)
            driver.find_element(By.CSS_SELECTOR,'#main > div.login-main > form > fieldset > p:nth-child(3) > img').click()#识别失败刷新验证码按钮
            continue
        num = 0
        for i in result:
            if ord(i) >= 48 and ord(i) <= 57:
                num += 1
            elif i in Error_str:
                num += 1
                result = result.replace(i, Error_identification[i])
                # print(result)
            else:
                time.sleep(2)
                driver.find_element(By.CSS_SELECTOR,'#main > div.login-main > form > fieldset > p:nth-child(3) > img').click()#识别失败刷新验证码按钮
                break
        if num == len(result):
            break
    driver.find_element(By.CSS_SELECTOR,'#main > div.login-main > form > fieldset > p:nth-child(3) > input').send_keys(result)
    time.sleep(1)

    driver.find_element(By.CSS_SELECTOR,'#main > div.login-main > form > fieldset > div > input.btn').click()#点击登录按钮
    time.sleep(2)
    #对cookie操作
    cookie_data = driver.get_cookies()
    time.sleep(1)

    #给其他组员进行爬虫测试的cookie_total
    # cookie_total = ''
    # for cookie_i in cookie_data:
    #     cookie_total = cookie_i['name'] + '=' + cookie_i['value'] + '; ' + cookie_total
    # cookie_total = cookie_total[:-2]
    # print(cookie_total)

    time.sleep(1)

    #selenium的cookies文件处理
    f_path = 'end\\data\\cookie_data.json'

    def save_cookies(cookie_data, encoding="utf-8"):
        with open(f_path, "w", encoding=encoding) as f_w:
            json.dump(cookie_data, f_w)
            
    def load_cookies(encoding="utf-8"):
        if os.path.isfile(f_path):
            with open(f_path, "r", encoding=encoding) as f_r:
                user_status = json.load(f_r)
            return user_status

    def cookies_login(cookies: list):
        print(cookies)
        driver2.delete_all_cookies()
        for new_cookies in cookies:
            print(new_cookies)
            driver2.add_cookie(new_cookies)
        driver2.refresh()
        
    save_cookies(cookie_data)
    cookies = load_cookies()
    time.sleep(1)
    driver2.get('https://www.qb5.ch/')#必须进行get，否则会卡在selenium chrome 的默认跳转页面data;
    cookies_login(cookies)
    time.sleep(1)
    driver2.get('https://www.qb5.ch/')
    driver2.refresh()
    time.sleep(100)
    
if __name__ == '__main__':
    register_start()