爬取网易云音乐榜单第一歌曲的热门评论并制作成词云

热歌榜第一——纸短情长

import requests
from bs4 import BeautifulSoup
import json
from wordcloud import WordCloud
import matplotlib.pyplot as plt
import jieba
from os import path
from PIL import Image
import numpy as np
headers={
    'Host':'music.163.com',
    'Origin':'http://music.163.com',
    'Referer':'http://music.163.com/song?id=516076896',
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.119 Safari/537.36'
}

user_data={
    'params':'YQsn4Tydy/30k45faysdPwSQIjmtwI5UwOn4na6SUEeZbtRL9ZiVe/Fv5XgEl+Lx563KjVjKPVSfjRjCR4q1IDN93ESkTANseOCCTF+Hj+l/+O9ryQQTPoHQnwObboJ0F2vP8zJyRlYZXDpr4gkhz5+W7rg+AzyySE20KU9vHYMGQV2i14AtkBJ+uxzpyIBC',
    'encSecKey':'43a443cd26728f607d458fb69b4503c64ab8907aa7c6c8219bc8b2e8928e554933c9a26c1fda734ed9306754562b8e6a6b6cfc8fa28350734e88df3250519a4f48e6d1da4f5e651ba7b2df7c1c614732d5f3ef382c30d52a9493077c0723cc4c775676e63fee3d4c0cb1bb084ac594f736345add2e77f8eb519aa161b6db064e'
}
url="http://music.163.com/weapi/v1/resource/comments/R_SO_4_516076896?csrf_token="
r=requests.post(url,headers=headers,data=user_data)
data=json.loads(r.text)
print(type(data))
hotcomments=[]
for hotcomment in data['hotComments']:
   item={
       'nickname':hotcomment['user']['nickname'],
       'content':hotcomment['content'],
       'likecount':hotcomment['likedCount']
   }
   hotcomments.append(item)

comments_list=[i['content']for i in hotcomments]
nickname=[i['nickname']for i in hotcomments]
liked_count=[i['likecount']for i in hotcomments]

for i in range(len(nickname)):
    print(nickname[i])
    print(comments_list[i])
    print(liked_count[i])
    print("\n")

img = imread('girl01.jpg')
context="".join(comments_list)
wc=WordCloud(font_path=r'c:\windows\fonts\STXINGKA.TTF').generate(context)
plt.imshow(wc)
plt.axis("off")
plt.show()

男士背景图(省去各位大佬花时间去修图了)
男士背景图(省去各位大佬花时间去修图了)

女孩背景图
女孩背景图

结果显示
未通过jieba分词
未通过jieba分词

jieba分词过后生成的词云
jieba分词过后生成的词云

猜你喜欢

转载自blog.csdn.net/weifuliu/article/details/80466512