huya弹幕提取小尝试

"""爬取实时的虎牙弹幕"""
"""不出现重复弹幕"""
"""不遗漏弹幕"""
from selenium import webdriver
import time

web = webdriver.Chrome()
web.get('https://www.huya.com/52333')
"""第一版"""
# while True:
#     bullets_chat  = web.find_elements_by_xpath('//*[@id="chat-room__list"]/div/div/span[3]')
#     for bullet in bullets_chat:
#         if bullet.text:
#             print(bullet.text)  
#     time.sleep(3)
# 缺点：会出现重复弹幕，为减少重复弹幕增加sleep时间会遗漏弹幕 
"""第二版""" 
# bbb = []
# while True:
    
#     bullets_chat  = web.find_elements_by_class_name('msg')
#     for bullet in bullets_chat:
#         if bullet.text and bullet.text not in bbb: 
#             print(bullet.text)
#             bbb.append(bullet.text)
      
#     time.sleep(0.5)  
# 缺点 1.bbb列表会越来越大，拖慢内存 2.如果两个人发了两个相同弹幕比如哈哈哈，只会出现1个

"""第三版"""
# bbb = []
# while True:
    
#     bullets_chat  = web.find_elements_by_class_name('msg')
#     for bullet in bullets_chat:
#         if bullet.text and bullet.text not in bbb: 
#