针对弹幕的爬取我们如果只需要获取看到的网页里面的而数据,使用selenium就能实现,对于直播平台来说,往往有第三方平台api让你获取数据(可以获取发弹幕,发弹幕者的名字礼物等等,这需要客户端向弹幕服务器发送登录请求,心跳信息的发送等等)只获取弹幕信息储存到txt文件中,上代码,上图片
import time
from selenium import webdriver
chrome_options = webdriver.ChromeOptions()
# 使用headless无界面浏览器模式
# chrome_options.add_argument('--headless')
# chrome_options.add_argument('--disable-gpu')
prefs = {"profile.managed_default_content_settings.images": 2}
chrome_options.add_experimental_option("prefs", prefs)
browser = webdriver.Chrome(chrome_options=chrome_options)
url = 'https://www.douyu.com/'
def getDanmu(homeId):
homeHref = url+str(homeId)
browser.get(homeHref)
while 1:
time.sleep(2)
try:
for i in browser.find_elements_by_xpath('.//div[@class=" danmu-6e95c1"]/div/div'):
if len(i.text) > 0:
try:
print(i.text)
except:
pass
saveDanmu(i.text)
else:
continue
except:
time.sleep(2)
for i in browser.find_elements_by_xpath('.//div[@class=" danmu-6e95c1"]/div/div'):
if len(i.text) > 0:
try:
print(i.text)
except:
pass
saveDanmu(i.text)
else:
continue
def saveDanmu(danmu):
with open('danmu.txt', 'a+', encoding='utf-8')as f:
f.write(danmu+'\n')
if __name__ == '__main__':
num = input('请输入需要查询的房间号:')
getDanmu(num)