用Python在QQ音乐中爬取周杰伦歌曲的评论，并绘制词云图

由于QQ音乐的反爬虫机制比较强，需要先模拟登录QQ音乐获取cookies，然后再进行爬取评论和生成词云图的操作。

以下是完整代码：

import requests
import json
import time
import os
from wordcloud import WordCloud
import matplotlib.pyplot as plt
from PIL import Image
import numpy as np

# 登录QQ音乐获取cookies
def get_cookies():
    headers = {
        'Referer': 'https://y.qq.com/',
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'
    }
    url = 'https://y.qq.com/'
    response = requests.get(url, headers=headers)
    cookies = response.cookies.get_dict()
    return cookies

# 爬取评论
def get_comments(song_id, page):
    headers = {
        'Referer': 'https://y.qq.com/n/yqq/song/{}.html'.format(song_id),
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3',
        'Cookie': 'pgv_pvid=6021975380; pgv_pvi=3306170880; pt2gguin=o0533414728; RK=J0VJyXs+Ld; ptcz=4e11a4a6e4a6b8d37b42a6b9f9d2b6c8a6b2a6b9f9d2b6c8a6b2a6b9f9d2b6c8; pgv_si=s1046426624; pgv_info=ssid=s7230811040; _qpsvr_localtk=0.7601771490547045; yq_index=0; yq_playschange=0; yq_playdata=; ts_uid=4789989478; player_exist=1; qqmusic_fromtag=66'
    }
    url = 'https://c.y.qq.com/base/fcgi-bin/fcg_global_comment_h5.fcg'
    params = {
        'g_tk': '5381',
        'loginUin': '0',
        'hostUin': '0',
        'format': 'json',
        'inCharset': 'utf8',
        'outCharset': 'utf-8',
        'notice': '0',
        'platform': 'yqq.json',
        'needNewCode': '0',
        'cid': '205360772',
        'reqtype': '2',
        'biztype': '1',
        'topid': song_id,
        'cmd': '8',
        'pagenum': page,
        'pagesize': '25',
        'lasthotcommentid': '',
        'domain': 'qq.com',
        'ct': '24',
        'cv': '10101010'
    }
    response = requests.get(url, headers=headers, params=params)
    json_data = json.loads(response.text)
    comment_list = json_data['comment']['commentlist']
    comments = []
    for comment in comment_list:
        content = comment['rootcommentcontent']
        comments.append(content)
    return comments

# 生成词云图
def generate_wordcloud(text, mask_path):
    # 读取遮罩图片
    mask = np.array(Image.open(mask_path))
    # 设置词云图参数
    wc = WordCloud(background_color="white", max_words=2000, mask=mask, contour_width=1, contour_color='steelblue')
    # 生成词云图
    wc.generate(text)
    # 显示词云图
    plt.imshow(wc, interpolation='bilinear')
    plt.axis("off")
    plt.show()

if __name__ == '__main__':
    # 歌曲id
    song_id = '108119'
    # 存储评论的文件名
    filename = 'comments.txt'
    # 遮罩图片路径
    mask_path = 'jay.jpg'

    # 获取cookies
    cookies = get_cookies()

    # 爬取评论
    comments = []
    for i in range(1, 11):
        comments += get_comments(song_id, i)
        time.sleep(1)
    # 保存评论到文件中
    with open(filename, 'w', encoding='utf-8') as f:
        for comment in comments:
            f.write(comment + '\n')

    # 读取评论文件
    with open(filename, 'r', encoding='utf-8') as f:
        text = f.read()

    # 生成词云图
    generate_wordcloud(text, mask_path)

需要注意的几点：

1. `get_cookies()`函数中的`Cookie`参数需要根据自己的账号进行修改，可以通过浏览器获取；
2. `get_comments()`函数中的`cid`参数是QQ音乐评论的分类id，每个歌曲的分类id不同，需要通过浏览器获取；
3. `generate_wordcloud()`函数中的`mask_path`参数是用于遮罩的图片路径，需要提前准备好；
4. 由于QQ音乐的反爬虫机制比较强，为了避免被封IP，需要在爬取评论时加入适当的延时。