Python下载，某音乐网站mp3音乐及歌词下载源码

二爷

发布于 2023-09-02 08:12:55

7572

发布于 2023-09-02 08:12:55

文章被收录于专栏：二爷记

你曾拥有一些英雄的梦想

好像黑夜里面温暖的灯光

怎能没有了希望的力量

只能够挺胸勇往直前

最近循环许巍的那一年，分享到朋友圈，有老板评论好久没听这首歌了，大概率是脱贫了，因为大部分循环听许巍的歌，总会印证那么一句话：贫穷是我们反复相遇。

言归正传，如果想要下载mp3歌曲，这里有一个网站推荐：歌曲宝（https://www.gequbao.com/），解析的各大平台的音乐，大致看了下网易云音乐应该是首选，这里本渣渣用Pyhton简单实现了下载mp3音乐及歌词，附上源码仅供参考和学习。

不知道此类网站能存活多久（找找还是有不少类似的解析平台音乐站点），且用且珍惜，爬取注意频率，不要乱搞！

# !/usr/bin/python
# -*- coding: UTF-8 -*-
#@author:huguo002

import requests
from lxml import etree
import time
import re
import sys

def get_musiclist(name):
    url=f"https://www.gequbao.com/s/{name}"
    headers={
        "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36"
    }
    response=requests.get(url=url,headers=headers,timeout=8)
    print(response.status_code)
    html=response.content.decode("utf-8")
    time.sleep(2)
    tree=etree.HTML(html)
    num=tree.xpath('//small[@class="float-right badge badge-pill badge-warning "]/text()')[0]
    musicnum=num.replace('\n','').replace(' ','')
    print(musicnum)
    musicnames=tree.xpath('//div[@class="row"]/div[@class="col-5 col-content"]/a/text()')
    print(musicnames)
    musicsingers=tree.xpath('//div[@class="row"]/div[@class="text-success col-4 col-content"]/text()')
    print(musicsingers)
    musicurls=tree.xpath('//div[@class="row"]/div[@class="col-3 col-content"]/a/@href')

    print(musicurls)
    musiclists=[]
    i=1
    for musicname,musicsinger,musicurl in zip(musicnames,musicsingers,musicurls):
        musiclist=i,musicname.replace('\n','').replace(' ',''),musicsinger.replace('\n','').replace(' ',''),'https://www.gequbao.com'+ musicurl.replace('\n','').replace(' ','')
        print(musiclist)
        musiclists.append(musiclist)
        i=i+1

    print(musiclists)
    return musiclists


def get_music(musicurl):
    headers = {
        "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36"
    }
    response = requests.get(url=musicurl, headers=headers, timeout=8)
    print(response.status_code)
    html = response.content.decode("utf-8")
    #print(html)
    time.sleep(2)
    music_down_url=re.findall(r"const url = '(.+?)'.replace",html,re.S)[0]
    print(music_down_url)
    tree = etree.HTML(html)
    down_name=tree.xpath('//span[@class="form-control bg-light overflow-hidden"]/text()')[0]
    down_name=down_name.split()[0]
    print(down_name)
    musiclrc_down_url=tree.xpath('//div[@class="input-group-append"]/a[@id="btn-download-lrc"]/@href')[0]
    musiclrc_down_url=f'https://www.gequbao.com{musiclrc_down_url}'
    print(musiclrc_down_url)
    down_music(down_name, music_down_url, musiclrc_down_url)


def down_music(down_name,music_down_url,musiclrc_down_url):
    headers = {
        "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36"
    }
    music_response = requests.get(url=music_down_url, headers=headers, timeout=8)
    print(music_response.status_code)
    time.sleep(2)
    with open(f"{down_name}",'wb') as f:
        f.write(music_response.content)
    print(f"{down_name}歌曲下载完成！")
    music_lrc_name=f'{down_name[:-3]}lrc'
    print(music_lrc_name)
    music_lrc_response = requests.get(url=musiclrc_down_url, headers=headers, timeout=8)
    print(music_lrc_response.status_code)
    time.sleep(2)
    with open(f"{music_lrc_name}",'wb') as f:
        f.write(music_lrc_response.content)
    print(f"{down_name}歌词下载完成！")



def main(name):
    musiclists=get_musiclist(name)
    for musiclist in musiclists:
        musicurl=musiclist[3]
        get_music(musicurl)
        time.sleep(6)
        sys.exit() #终止程序



if __name__=='__main__':
    name = "那一年"
    main(name)

运行：