Build a Python QQ Music Scraper: From Song Lists to Word Clouds

Project Goal

The project combines three earlier scraping scripts into a single menu‑driven Python program that can fetch a specified artist's song list, retrieve lyrics and hot comments for a chosen track, and generate a word‑cloud image from the collected comments.

Required Libraries

Core dependencies are requests , openpyxl , html , json , wordcloud , and jieba . For custom word‑cloud backgrounds you also need numpy and Pillow (install via pip install pillow). To create a standalone executable, use pyinstaller -F.

Implementation

A QQ class provides a menu method offering five options: get song info, get lyrics, get comments, generate a word cloud, and exit.

class QQ():
    def menu(self):
        print('欢迎使用QQ音乐爬虫系统，以下是功能菜单，请选择.
')
        while True:
            try:
                print('功能菜单
1.获取指定歌手的歌曲信息
2.获取指定歌曲歌词
3.获取指定歌曲评论
4.生成词云图
5.退出系统
')
                choice = int(input('请输入数字选择对应的功能：'))
                if choice == 1:
                    self.get_info()
                elif choice == 2:
                    self.get_id()
                    self.get_lyric()
                elif choice == 3:
                    self.get_id()
                    self.get_comment()
                elif choice == 4:
                    self.wordcloud()
                elif choice == 5:
                    print('感谢使用！')
                    break
                else:
                    print('输入错误,请重新输入.
')
            except:
                print('输入错误,请重新输入.
')

get_info() creates an Excel workbook, queries QQ Music's search API for a given artist and page count, extracts song name, album, and playback link, and writes the data to the sheet before saving.

def get_info(self):
    wb = openpyxl.Workbook()
    sheet = wb.active
    sheet.title = 'song'
    sheet['A1'] = '歌曲名'
    sheet['B1'] = '所属专辑'
    sheet['C1'] = '播放链接'
    url = 'https://c.y.qq.com/soso/fcgi-bin/client_search_cp'
    name = input('请输入要查询的歌手姓名：')
    page = int(input('请输入需要查询的歌曲页数：'))
    for x in range(page):
        params = {
            'ct':'24','qqmusic_ver':'1298','new_json':'1','remoteplace':'sizer.yqq.song_next',
            'searchid':'64405487069162918','t':'0','aggr':'1','cr':'1','catZhida':'1','lossless':'0',
            'flag_qc':'0','p':str(x+1),'n':'20','w':name,'g_tk':'5381','loginUin':'0','hostUin':'0',
            'format':'json','inCharset':'utf8','outCharset':'utf-8','notice':'0','platform':'yqq.json','needNewCode':'0'
        }
        res = requests.get(url, params=params)
        data = res.json()
        for music in data['data']['song']['list']:
            song_name = music['name']
            album = music['album']['name']
            link = 'https://y.qq.com/n/yqq/song/' + str(music['mid']) + '.html'
            sheet.append([song_name, album, link])
    wb.save(name + '个人单曲排行前' + str(page*20) + '清单.xlsx')
    print('下载成功!
')

get_id() and get_lyric() locate a song's ID via the search API, then request its lyrics, decode HTML entities, and save the result to a .txt file. The request headers must include origin and referer to avoid being blocked.

def get_id(self):
    self.i = input('请输入歌曲名：')
    url_1 = 'https://c.y.qq.com/soso/fcgi-bin/client_search_cp'
    headers = {'user-agent':'Mozilla/5.0 ...'}
    params = {..., 'w':self.i, ...}
    res_music = requests.get(url_1, headers=headers, params=params)
    json_music = res_music.json()
    self.id = json_music['data']['song']['list'][0]['id']

def get_lyric(self):
    url_2 = 'https://c.y.qq.com/lyric/fcgi-bin/fcg_query_lyric_yqq.fcg'
    headers = {'origin':'https://y.qq.com','referer':'https://y.qq.com/n/yqq/song/001qvvgF38HVc4.html','user-agent':'Mozilla/5.0 ...'}
    params = {'nobase64':'1','musicid':self.id,'-':'jsonp1','g_tk':'5381',...}
    res_music = requests.get(url_2, headers=headers, params=params)
    lyric = res_music.json()['lyric']
    lyric_html = html.unescape(lyric)
    with open(self.i + '歌词.txt','a',encoding='utf-8') as f:
        f.writelines(lyric_html)
    print('下载成功!
')

get_comment() iterates over comment pages, extracts each comment's text, and writes them to a .txt file, separating entries with a line of dashes.

def get_comment(self):
    page = input('请输入要下载的评论页数：')
    url_3 = 'https://c.y.qq.com/base/fcgi-bin/fcg_global_comment_h5.fcg'
    headers = {'user-agent':'Mozilla/5.0 ...'}
    f2 = open(self.i + '评论.txt','a',encoding='utf-8')
    for n in range(int(page)):
        params = {...,'topid':self.id,'pagenum':n,...}
        js_2 = requests.get(url_3, headers=headers, params=params).json()
        for i in js_2['comment']['commentlist']:
            comment = i['rootcommentcontent'] + '
——————————————————————————————————
'
            f2.writelines(comment)
    f2.close()
    print('下载成功!
')

wordcloud() reads a text file, uses jieba to segment Chinese words, applies a mask image (e.g., a heart shape), and generates a word‑cloud PNG.

def wordcloud(self):
    self.name = input('请输入要生成词云图的文件名称：')
    def cut(text):
        return " ".join(jieba.cut(text))
    with open(self.name + '.txt',encoding='utf-8') as file:
        text = cut(file.read())
        mask_pic = numpy.array(Image.open('心.png'))
        wc = WordCloud(font_path='C:/Windows/Fonts/simfang.ttf', collocations=False,
                       max_words=100, min_font_size=10, max_font_size=500, mask=mask_pic)
        wc.generate(text)
        wc.to_file(self.name + '云词图.png')
    print('生成成功!
')

Finally, the script is instantiated and the menu launched:

qq = QQ()
qq.menu()

Sample output screenshots are shown below:

When packaging the script into an executable with pyinstaller -F, the word‑cloud step may cause errors; commenting out the word‑cloud related imports and function allows successful packaging, albeit without the visualization feature.