斗鱼网爬虫

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from pandas import DataFrame
import time
browse=webdriver.Chrome()#
def web(www): #定义一个获取网页的函数
browse.get(www)
time.sleep(20)
Tao_price=[]
#//[@id=“js-player-title”]/div/div[2]/div[1]/div[2]/div[1]/h3
a=browse.find_element_by_xpath(’//[@id=“js-player-title”]/div/div[2]/div[1]/div/div[1]/h3’)
Tao_price.append(a.text)
fd=[]

b=browse.find_element_by_xpath('//*[@id="js-player-barrage"]').text
b=b.split()
b=len(b)
fd.append(b)
Tao_price2=[]
#//*[@id="js-player-title"]/div/div[2]/div[1]/div[1]/div/div[2]/span
c=browse.find_element_by_xpath('//*[@id="js-player-title"]/div/div[2]/div[1]/div[1]/div/div[2]/span')
Tao_price2.append(c.text) 
Tao_price3=[]
d=browse.find_element_by_xpath('//*[@id="js-player-asideMain"]/div/div[1]/div[3]/div/div/div/div[1]/ul/li[2]/div/em')
Tao_price3.append(d.text) 


Taobao=DataFrame() 
Taobao['标题']=Tao_price
Taobao['弹幕量']=fd
Taobao['关注人数']=Tao_price2
Taobao['贵宾人数']=Tao_price3
return Taobao

gg=DataFrame()
for i in gg5:
try:

    mm='https://www.douyu.com{}'.format(i)
    # gg.append(mm)
    df_page=web(mm) 

    gg=gg.append(df_page,ignore_index=True)
except:
    pass

browse.get(www)
gg
gg.to_excel(“C:\英雄时刻\Python\新建文件夹 (2)\新建 XLSX 工作表.xlsx”)