python爬虫练习

抓取

requests.get()
r.text（）

解析
re模块

抓取豆瓣读书《你当像鸟飞往你的山》评论第一页并计算平均评分

import requests
from bs4 import BeautifulSoup
import re
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36(KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'}
r=requests.get('https://book.douban.com/subject/33440205/comments/',headers=headers)
comment=BeautifulSoup(r.text,'lxml')
pattern=comment.find_all('span','short')
for item in pattern:
    print(item.string)
points = re.compile('<span class="user-stars allstar(.*?) rating"')
p = re.findall(points, r.text)
s = 0
count=0
for star in p:
 s += int(star)
 count+=1
average=s/count
print(s,count,average)