import time
import json
import re
from selenium import webdriver
from selenium.webdriver.chrome.service import Service  # 新版本将executable_path被重构，放在Service函数里
from selenium.webdriver.common.by import By  # 隐式等待，定位元素的By类
from selenium.webdriver.support import expected_conditions as EC  # 预期条件，监控相关
from selenium.webdriver.support.wait import WebDriverWait  # 等待；页面可能是动态的，Ajax加载的不完全
from selenium.webdriver.chrome.options import Options   # 浏览器参数设置：如导入Options模块，用于加载headers

# 必须要https://严格格式构建的html地址
url = 'http://42.194.197.95:8001/webdriver_ajax'


# 设置请求头参数
headers = {
    'Accept': 'application/json, text/plain, */*',
    'Accept-Language': 'zh-CN,zh;q=0.9',
    'Cache-Control': 'no-cache',
    'Connection': 'keep-alive',
    # 'Cookie': 'session=.eJyrViotTi1SsqpWyiyOT0zJzcxTsjLQUcrJTwexSopKU3WUcvOTMnNSlayUDM3gQEkHrDE-M0XJyhjCzkvMBSmKKTU3NbKIKTUzMjZXqq0FAN1MHbY.ZPMkQg.MeUf3o_GgoHaGX1K_kSP_CEN0ng; auth=508OGQJI368827WWN1693662187',
    'Pragma': 'no-cache',
    'User-Agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Mobile Safari/537.36',
}


# 创建Options对象并添加请求头参数
def add_header():
    _options = Options()
    for k, v in headers.items():
        _options.add_argument(f'{k}={v}')
    return _options


# 禁止图片和css加载
def disable_img_css(__options):
    prefs = {"profile.managed_default_content_settings.images": 2,
             'permissions.default.stylesheet': 2}
    __options.add_experimental_option("prefs", prefs)


# 实现元素条件等待的方法
def wait_element(_driver, element_id, wait_time=10):
    try:
        # 隐式等待
        # brower：需要隐式等待的浏览器
        # wait_time：最长等待实际
        # 1：每隔1秒判断一下对应的元素是否成功加载
        # 创建WebDriverWait对象,每1秒检查一次,最长等待10秒
        wait = WebDriverWait(_driver, wait_time, 1)

        # 定义要等待的元素条件,传入定位方式和元素id
        element = (By.ID, element_id)

        # 等待直到元素条件出现,否则超时抛出TimeoutException
        wait.until(EC.presence_of_element_located(element))

    except Exception as e:
        raise Exception(e)


# 创建服务对象
s = Service("chromedriver.exe")
# 或 browser = webdriver.chrome.service.Service("chromedriver.exe")

# 获取配置好的参数选项
options = add_header()
disable_img_css(options)
# 创建WebDriver对象并传入参数选项
driver = webdriver.Chrome(service=s, options=options)  # 定义driver方法

# js脚本加载
with open("stealth.min.js") as f:
    js = f.read()
# 执行js脚本
driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
  "source": js
})


try:
    driver.get(url)  # 获取html网页
    driver.add_cookie({"name": "session",
                       "value": ".eJyrViotTi1SsqpWyiyOT0zJzcxTsjLQUcrJTwexSopKU3WUcvOTMnNSlayUDM3gQEkHrDE-M0XJyhjCzkvMBSmKKTU3NbKIKTUzMjZXqq0FAN1MHbY.ZPMkQg.MeUf3o_GgoHaGX1K_kSP_CEN0ng"
                       })
    # 添加后，浏览器进行http请求时，会自动携带上cookies -> Headers
    driver.get(url)  # 再次访问

    # 保存网址完整html，方便查阅
    html = driver.page_source

    pattern = r'"movies":\[.*?\]'
    match = re.search(pattern, html)
    if match:
        json_str = match.group()
        print(json_str)
finally:
    time.sleep(5)
    driver.close()






"""国外网址，使用js避免特征被捕获


import time
from selenium.webdriver import Chrome
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.chrome.service import Service

url = "http://42.194.197.95:8001/brower"

chrome_options = Options()
# 无头浏览器配置
chrome_options.add_argument("--headless")
# 添加请求头
chrome_options.add_argument("user-agent=Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Mobile Safari/537.36")

# 配置浏览器启动工具
s = Service("chromedriver.exe")
driver = Chrome(service=s, options=chrome_options)

# js脚本加载
with open("stealth.min.js") as f:
    js = f.read()

# 在打印具体的网页前，执行隐藏浏览器特征的JavaScript
# 执行js脚本
driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
  "source": js
})

# 访问url
#driver.get(url)
driver.get('https://bot.sannysoft.com/')
time.sleep(5)
driver.save_screenshot('workaround.png')

# 保存网址完整html，方便查阅
source = driver.page_source
with open('result.html', 'w') as f:
    f.write(source)




"""