python豆瓣影评url爬取

python
豆瓣电影影评爬取
需要库
lxml，requests
代码如下:

import requests
from lxml import etree
'''定义头部信息'''
head={
   "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36"}
base_url='https://movie.douban.com/review/best/?start='
list1=[]
for i in range(5):
    url=base_url+'{}'.format(20*i)
    r=requests.get(url,headers=head)
    domo=r.content.decode('utf8')
    jiexi=etree.HTML(domo)
    _url=jiexi.xpath('//div[@class="main-bd"]/h2/a/@href')
    list1.append(_url)
for _url in list1:
    for url1 in _url:
        print(url1)

运行结果如下:

https://movie.douban.com/review/13714022/
https://movie.douban.com/review/13715350/
https://movie.douban.com/review