用Python爬取QQ音乐评论并制成词云图的实例

import requests
import json
def get_comment():
  for i in range(1,7000):
    # 打印页码
    print(i)
    # headers头部
    headers = {'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:59.0) Gecko/20100101 Firefox/59.0',
 'Referer': "https://y.qq.com/n/yqq/song/0031TAKo0095np.html"}
    # 请求的url
    url = 'https://c.y.qq.com/base/fcgi-bin/fcg_global_comment_h5.fcg"jsoncallback06927647062927766(")
    html = html.replace(")","")
    # 去掉两边的空格
    html = html.strip()
    # 将处理后的json转为python的json
    data = json.loads(html)
    # 获取json中评论的部分
    list = data['comment']['commentlist']
    # 每次都重新定义一个列表来存储每一页的评论
    content = []
    # 遍历当前页的评论并通过调用write()函数来保存
    for i in list:
      # 偶尔也会有一页的评论获取不到，这时候如果报错了可以直接忽略那一页，继续运行
      try:
        content.append(i['rootcommentcontent'].replace("[em]","").replace("[/em]","").replace("e400",""))
      except KeyError:
        content = []
        break
    write(content)
# 将当前页面的评论传递过来
def write(content):
  # 打开一个文件,将列表的内容一行一行的存储下来
  with open('comments.txt', 'a', encoding = 'UTF-8') as f:
    for i in range(len(content)):
      # 因为转为json后\n不胡自动换行，所以我们这里将\n给手换行
      string = content[i].split("\\n")
      for i in string:
        # 因为出现了很多评论被删除的情况,所有我们把这句给过滤掉
        i = i.replace("该评论已经被删除", "")
        # 打印每条评论
        print (i)
        # 将评论写入文本
        f.writelines(i)
        # 给评论换行
        f.write("\n")
if __name__ == "__main__":
  get_comment()

# -*- coding: utf-8 -*-
import jieba
from wordcloud import WordCloud, STOPWORDS
from os import path
from scipy.misc import imread
# 读取mask/color图片
d = path.dirname(__file__)
color_mask = imread("cyx.png")
#将爬到的评论放在string中
with open('nbzd.txt', 'r', encoding = 'UTF-8') as f:
  string = f.read()
  word = " ".join(jieba.cut(string))
  wordcloud = WordCloud(background_color='white',
             mask=color_mask,
             max_words=100,
             stopwords=STOPWORDS,
             font_path='/home/azhao/桌面/素材/simsun.ttc',
             max_font_size=100,
             random_state=30,
             margin=2).generate_from_text(word)
import matplotlib.pyplot as plt
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis("off")
plt.show()