Python爬虫下载酷我音乐

介绍

学了点python的皮毛，写了个下载酷我音乐的爬虫，用streamlit生成web程序，边写边看文档，看不懂问chatgpt，报错也问chatgpt，做出来的东西还算能用🥰

感谢酷我音乐提供的优质音乐资源

5月3日更新

可以搜索歌曲、专辑、作者

至多显示前20首歌曲

预览

v1.1

填写音乐url点击确认即可下载音乐😋

v1.2

搜索后打印爬取到的前20首歌曲

向下翻用一个滑块选择序号对应的歌曲，从0开始，点击确定后显示歌曲的音频播放器和一个下载按钮

环境

系统 ：pve lxc Debian 11

Python ： 3.9.2

streamlit ：1.22.0

beautifulsoup4 ： 4.12.2

requests ：2.28.2

代码

替换cookie和csrf，浏览器在酷我搜索界面按f12自行查找。

import requests
import streamlit as st
import os
from bs4 import BeautifulSoup
import re
from urllib.parse import quote
import pandas as pd


#传入mid和name下载歌曲并重命名
def music(name,mid):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.0.0 Safari/537.36 Edg/112.0.1722.64'
    }
    url_base = 'https://www.kuwo.cn/api/v1/www/music/playUrl?mid=%s&type=mp3&httpsStatus=1'
    url = url_base % mid
    response = requests.get(url, headers=headers)
    result = response.json()
    play_url = result['data']['url']
    play = requests.get(play_url, headers=headers)
    with open(f'./file/{name}.mp3', 'wb') as f:
        f.write(play.content)

#通过url获取歌名
def name_music(url):
    detail = requests.get(url)
    # mid = re.search(r'\d+', url).group()
    html = BeautifulSoup(detail.content, 'html.parser')
    name = html.find('span', class_='name').text.strip()
    return name

#搜索返回表格
def search(sth):
    url_base = "https://www.kuwo.cn/api/www/search/searchMusicBykeyWord?key=%s&pn=1&rn=20&httpsStatus=1&reqId=5cf864c0-e8e9-11ed-a0c3-7751e26bbea4"
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.0.0 Safari/537.36 Edg/112.0.1722.68',
        'Referer': 'https://www.kuwo.cn/search/list?key=' + quote(sth),
        'Cookie': '-------------------------f12自己找-----------------------------',
        'csrf': '--------------------------f12自己找-----------------------------'
    }
    url = url_base % sth
    response = requests.get(url, headers=headers)
    search_dick = response.json()
    name_list = []
    album_list = []
    musicrid_list = []
    artist_list = []
    for song in search_dick['data']['list']:
        name = song['name']
        album = song['album']
        artist = song['artist']
        musicrid = song['musicrid']
        artist_list.append(artist)
        name_list.append(name)
        album_list.append(album)
        musicrid_list.append(musicrid)
    mid_list = []
    for musicrid in musicrid_list:
        numbers = str(re.findall(r'\d+', musicrid))[2:-2]
        mid_list.append(numbers)
    df = pd.DataFrame(
        {
            '歌曲': name_list,
            '专辑': album_list,
            '歌手': artist_list,
            'mid': mid_list
        }
    )
    df_view =  pd.DataFrame(
        {
            '歌曲': name_list,
            '专辑': album_list,
            '歌手': artist_list,
        }
    )
    return df,df_view

st.title('酷我音乐下载')
st.write('酷我音乐：https://www.kuwo.cn/')
st.write('只能下载酷我音乐拥有的歌曲')
st.write('只获取搜索列表前20首音乐')
sth = st.text_input('',placeholder='青花瓷')

if not sth:
    st.write('可以搜索：歌曲、专辑、作者等，可同时填入精确搜索')
    st.write('输入完成点击其他地方或回车开始搜索')
else:
    df,df_view = search(sth)
    st.table(df_view)
    num_songs = df.shape[0] - 1
    song_num = st.slider('选择歌曲序号', 0, num_songs)
    st.write(f'选择序号为{song_num}的歌曲')
    if st.button('确定'):
        mid = df['mid'][song_num]
        url = 'https://www.kuwo.cn/play_detail/' + mid
        name = name_music(url)
        music(name,mid)
        with open(f'./file/{name}.mp3', "rb") as file:
            st.audio(file)
            st.download_button(
                label="下载音乐",
                data=file,
                file_name=f'{name}.mp3',
                mime='audio/mp3'
            )
            os.remove(f'./file/{name}.mp3')

windows上运行不能删除服务端下载的音乐

保存至 music.py

运行：streamlit run music.py

后台运行：nohup streamlit run music.py &

查看进程：ps -le | grep streamlit

结束进程：kill pid