爬取豆瓣网影评数据并进行简单分析与展示

 1 from urllib import request
 2 from bs4 import BeautifulSoup
 3 import matplotlib as mpl
 4 import matplotlib.pyplot as plt
 5 import pandas as pd
 6 import numpy as np
 7 import requests
 8 import re
 9 
10 """
11 生成分页网址
12 n:需要生成的页数
13 """
14 def get_urls(n):
15     urls=[]
16     for i in range(0,n):
17         u=‘https://movie.douban.com/subject/30166972/comments?start=‘+str(i*20)+‘&limit=20&sort=new_score&status=P‘
18         urls.append(u)
19     return urls
20 #get_urls(5)
21 
22 """
23 【从分页采集数据】
24 u:输入分页网址
25 """
26 def get_informations(u):
27     headers = {
28         ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36‘}
29     r = requests.get(u, headers=headers)
30     soup = BeautifulSoup(r.text, ‘lxml‘)
31     ims = soup.find_all(‘div‘, class_=‘comment-item‘)
32 
33     # print(ims)
34     data = []
35 
36     for i in ims:
37         dic = {}
38         dic[‘用户名‘] = i.find(‘span‘, class_=‘comment-info‘).find(‘a‘, class_="").text
39         mystar = i.find(‘span‘, class_=‘comment-info‘).find(‘span‘).next_sibling.next_sibling
40         mystar = str(mystar)
41         t = re.findall(r‘\d+‘, mystar)
42         dic[‘所评星级‘] = str(t[0])
43         dic[‘评论‘] = i.find(‘span‘, class_=‘short‘).text
44         dic[‘评论获赞数‘] = i.find(‘span‘, class_=‘votes‘).text
45         dic[‘评论时间‘] = i.find(‘span‘, class_=‘comment-time‘).text.strip()
46         data.append(dic)
47     return data
48 #get_informations(‘https://movie.douban.com/subject/30166972/comments?start=0&limit=20&sort=new_score&status=P‘)
49 
50 """
51 【从每一页采取所有数据】
52 n:需要采集的页数
53 """
54 def get_alldata(n):
55     alldata = []
56     for u in get_urls(n):
57         alldata.extend(get_informations(u))
58     """
59     清洗数据
60     转换数据类型以及星级去除%
61     .loc就是索引，逗号前面是行索引，逗号后面是列索引
62     """
63     df.loc[:, ‘所评星级‘] = df[‘所评星级‘].astype(‘float‘)
64     df.loc[:, ‘评论获赞数‘] = df[‘评论获赞数‘].astype(‘int‘)
65 
66     return pd.DataFrame(alldata)
67 
68 """
69 内容1、爬取豆瓣网某一部电影的评论信息
70 """
71 #保存数据到《少年的你》影评.csv
72 df = get_alldata(5)
73 df.to_csv(‘《少年的你》影评.csv‘,index=False,encoding=‘utf-8‘)
74 print(df)
75 
76 """pandas绘图：直方图，bins是像素"""
77 df[‘星级‘].hist(bins=20)

#str.strip()
s1=‘\nabcdefg\n‘
print(s1.strip())

 1 字符窜：DataFrame数据框里边的name列为字符窜形式
 2 
 3 清除字符窜左侧是空值：
 4 
 5 newname=df[‘name‘].str.lstrip()
 6 
 7 
 8 删除右侧：
 9 newname=df[‘name‘].str.rstrip()
10 
11 
12 删除全部：
13 newname=df[‘name‘].str.strip()

next_sibling
“”“
<p class=‘comment-time‘>ads<\p>
<p class=‘comment-time‘>bdg<\p>
<p class=‘comment-time‘>fgh<\p >
可以通过next_sibling
”“”
Tsecond =  i.find(‘p‘,class_=‘comment-time‘).next_sibling.next_sibling

TsecondText =  i.find(‘p‘,class_=‘comment-time‘).next_sibling.next_sibling.text

import matplotlib as mpl
import matplotlib.pyplot as plt

mpl.rcParams[‘font.sans-serif‘] = [‘KaiTi‘]
mpl.rcParams[‘font.serif‘] = [‘KaiTi‘]