# 导入requests和bs4两个库
import requests, bs4
# 准备基础数据,url和请求头
url = 'https://movie.douban.com/top250'
header = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.81 Safari/537.36'
}
# 封装请求方法
def getmoive(url):
r = requests.get(url, headers=header, timeout=10)
moive_lists = []
soup = bs4.BeautifulSoup(r.text,'lxml')
div_lists = soup.select('#content > div > div.article > ol > li > div > div.info > div.hd > a > span:nth-child(1)')
for i in div_lists:
moive = i.text.strip()
moive_lists.append(moive)
return moive_lists
# 执行和打印结果
moives = getmoive(url)
print(moives)
关于bs4的使用可以参考简书的这篇文章: