import json
import lxml
import os
import urllib
from selenium.webdriver import ChromeOptions
from bs4 import BeautifulSoup
from selenium import webdriver
import time
from selenium.webdriver.chrome.service import Service
# 获取抖音直播封面图片、链接、标题、主播名
if (os.path.isfile("test.txt")):

    # os.remove() function to remove the file
    os.remove("test.txt")

    # Printing the confirmation message of deletion
    print("File Deleted successfully")
else:
    print("File does not exist")

url = 'https://www.douyin.com/follow'

print('正在打开浏览器')
options = ChromeOptions()
options.add_experimental_option("debuggerAddress", "127.0.0.1:9014")
browser = webdriver.Chrome(executable_path=r"C:\Google\Chrome\Application\chromedriver.exe",
chrome_options=options)
browser.get(url)


time.sleep(3)

html =browser.page_source
soup = BeautifulSoup(html, 'lxml')  # 生成BeautifulSoup对象

#hrefs =soup.find_all("a", class_="Jt6LO5RK o3pEYU7M")
for each in soup.findAll("a", class_="Jt6LO5RK o3pEYU7M"):  # get all elements with 'a' tag
    href = each.get('href')
    href2 = href.replace('https://live.douyin.com/', 'https://live.douyin.com/webcast/room/web/enter/?aid=6383&app_name=douyin_web&live_id=1&web_rid=')
    print(each)
    print(href2)

    browser.get(href2)
    # time.sleep(1)
    pre = browser.page_source
    soup = BeautifulSoup(pre, 'lxml')  # 生成BeautifulSoup对象
    first_p_text = soup.find('pre').text

    #jsontxt = urllib.parse.unquote(first_p_text)
    res = json.loads(first_p_text)
    #     print(res)
    try:
        rtmp = res['data']['data'][0]['stream_url']['flv_pull_url']['FULL_HD1']
        print(rtmp)
    except Exception as e:
        print('Exception：', e)
        try:
            rtmp = res['data']['data'][0]['stream_url']['hls_pull_url']
        except Exception as e:
            print('Exception：', e)
            rtmp = "0"
            print(rtmp)

    Data = str(rtmp) + '\n'
    with open("test.txt", "a") as f:
        f.write(Data)
# 用字典保存直播间信息
browser.close()
    #     print(item['href'])