import io
import json
import re
import sys
import time
import loguru
# import pymysql.cursors
import requests
from bs4 import BeautifulSoup
from datetime import datetime
from api.index import importJson, getReptileTask, importJsonPath
from utils.Logger import log
from utils.index import convert_to_traditional, create_directory_if_not_exists, delete_directory
# from requests_toolbelt import *
from utils.createBrowserDriver import create
import opencc
from utils.filse import save_json
import os
from config.settings import get_base_file_url
from utils.download_image import download_image
# ---------------   selenium 依赖 start ----------------
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

# ---------------   selenium 依赖 end ----------------
'''
爬取台湾PTT论坛的热门帖子，包括帖子的标题、内容【文本、图片、视频】

爬取流程：创建驱动--》打开浏览器--》打开网页--》爬取分类元素--》循环点击--》爬取热门帖子标题--》循环点击--》爬取帖子详情
'''


def reptile(browser=None, search_word=""):
    url = "https://skynet.ipplus360.com/q.html"
    browser = browser or create(no_headless=False, using_user_data=True)
    # 有头模式执行
    # browser = browser or create()
    # 打开网页
    browser.get(url)
    print("------")
    print(browser.page_source)
    # log.debug("已打开浏览器")
    # classify_item_list = browser.find_elements('xpath', "//div[@class='board-class']")

reptile()