import requests
from bs4 import BeautifulSoup
def get_movies():
headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.89 Safari/537.36 SLBrowser/7.0.0.12151 SLBChan/30','Host':' movie.douban.com'}
movie_list=[]
for i in range(0,10):
link='https://movie.douban.com/top250?start=%27+str(i*25)
r=requests.get(link,headers=headers,timeout= 10)
print(str(i+1),'页响应状态码',r.status_code )
soup=BeautifulSoup (r.text,'lxml')
div_dict=soup.find_all('div',class_='hd')
for each in div_dict :
movie=each.a.span.text.strip()
movie_list .appand(movie)
return movie_list
movies=get_movies()
print(movies )
我改完之后就可以看到了
看不出层次, 用代码段功能贴下代码