爬虫小练习2

“迷你爬虫编程小练习”进阶：抽取豆瓣某本书的前 50 条短评内容并计算评分(star)的平均值。提示：有的评论中并不包含评分。

import re,time
import requests
from bs4 import BeautifulSoup

count = 0
i = 0
s,count_s,count_del = 0,0,0
lst_stars =[]

url = 'https://book.douban.com/subject/1456692/comments/hot?p='

while count<50: # 少于50就循环
    try:
        r = requests.get(url+str(i+1))
    except Exception as err:
        print(err)
        break
    
    soup = BeautifulSoup(r.text,'lxml')
    comments = soup.find_all('span','short')    # 得到评论
    pattern = re.compile('<span class="user-stars allstar(.*?) rating"') # 得到分数
    p = re.findall(pattern,r.text)
    for item in comments: # 打印爬下来的当前页的所有评论
        count += 1  # 每得到一条评论，序号加1
        if count >50:
            count_del += 1  # 如果超过50，count_del加1，打不打印评论
            
        else:
            print(count,item.string) # 打印序号，评论内容
            
    for star in p:
        lst_stars.append(int(star)) # 将当前页得到的分数放入列表lst_stars
        
    time.sleep(5)   #根据robots.txt协议，间隔5秒
    
    i +=1
    for star in lst_stars[:-count_del]:
        s += int(star)
        
if count >=50:
    print(s//(len(lst_stars)-count_del))