本文共 5104 字，大约阅读时间需要 17 分钟。

今天来更新第二章

• 首先分析一下网页代码

ctrl + u 快捷键

• 第二步来解析下我们看到的数据
  
• 第三步找到我们需要提取的数据
• 
• 第四步提取链接地址
  
  第五步提取name值
  
  思路的清晰了我们来整合一下

import osimport requestsfrom  bs4 import BeautifulSoup# #歌单地址# url = 'https://music.163.com/#/discover/toplist?id=3778678'# #外链地址# baser_url = 'http://music.163.com/song/media/outer/url'#请求头url = 'https://music.163.com/discover/toplist?id=3778678'headers = {
       'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.72 Safari/537.36'}respoen = requests.get(url=url,headers=headers).texts = BeautifulSoup(respoen, 'lxml')main = s.find('ul', class_='f-hide')#print(main)for music in main.find_all('a'):    print('{} : {}'.format(music.text, music['href']))    #这里我们确认没有问题数据的在这里面我们继续往下写

import osimport requestsfrom  bs4 import BeautifulSoup# #歌单地址# url = 'https://music.163.com/#/discover/toplist?id=3778678'# #外链地址# baser_url = 'http://music.163.com/song/media/outer/url'#请求头url = 'https://music.163.com/discover/toplist?id=3778678'headers = {
       'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.72 Safari/537.36'}respoen = requests.get(url=url,headers=headers).texts = BeautifulSoup(respoen, 'lxml')main = s.find('ul', class_='f-hide')#print(main)for music in main.find_all('a'):    #print(music)    #print('{} : {}'.format(music.text, music['href']))    #MP3地址    musicUrl = 'http://music.163.com/song/media/outer/url' + music['href'][5:] + '.mp3'    print(musicUrl)

import osimport requestsfrom  bs4 import BeautifulSoup# #歌单地址# url = 'https://music.163.com/#/discover/toplist?id=3778678'# #外链地址# baser_url = 'http://music.163.com/song/media/outer/url'#请求头url = 'https://music.163.com/discover/toplist?id=3778678'headers = {
       'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.72 Safari/537.36'}respoen = requests.get(url=url,headers=headers).texts = BeautifulSoup(respoen, 'lxml')main = s.find('ul', class_='f-hide')#print(main)lists = []for music in main.find_all('a'):    list = []    #print(music)    #print('{} : {}'.format(music.text, music['href']))    #MP3地址    musicUrl = 'http://music.163.com/song/media/outer/url' + music['href'][5:] + '.mp3'    #print(musicUrl)    # 歌曲名    musicName = music.text    #print(musicName)    # 单首歌曲的名字和地址放在list列表中    list.append(musicName)    list.append(musicUrl)    lists.append(list)    #循环从列表里面拿数据    for i in lists:        url = i[1]        # print(url)        name = i[0]        #print(name)        try:            print(f'歌曲{name}在在下载', end='\t\t')            # MP3数据流            res = requests.get(url, headers=headers)            # print(res)            MP3 = res.content            # print(MP3)            with open('./music/' + name + '.mp3', 'wb') as file:                file.write(MP3)                print(name, '下载成功')        except:            print('下载失败')

4.我们来封装一下代码保持可读性

import osimport requestsfrom  bs4 import BeautifulSoup# #歌单地址# url = 'https://music.163.com/#/discover/toplist?id=3778678'# #外链地址# baser_url = 'http://music.163.com/song/media/outer/url'#请求头headers = {
       'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.72 Safari/537.36'}# 新建一个文件夹保存所有MP3if not os.path.exists('./music/'):    # 如果没有当前文件夹则创建一个    os.mkdir('./music/')#定义解析函数def down(url):    respoen = requests.get(url=url,headers=headers).text    s = BeautifulSoup(respoen, 'lxml')    main = s.find('ul', class_='f-hide')    # print(main)    lists = []    for music in main.find_all('a'):        list = []        # print('{} : {}'.format(music.text, music['href']))        musicUrl = 'http://music.163.com/song/media/outer/url' + music['href'][5:] + '.mp3'        # MP3 = requests.get(musicUrl).content        #print(MP3)        #歌曲名        musicName = music.text        #print(musicName)        # 单首歌曲的名字和地址放在list列表中        list.append(musicName)        list.append(musicUrl)        lists.append(list)    for i in lists:        url = i[1]        #print(url)        name = i[0]        #print(name)        try:            print(f'歌曲{name}正在下载',end='\t\t')            #MP3数据流            res = requests.get(url,headers=headers)            #print(res)            MP3 = res.content            #print(MP3)            with open('./music/' + name + '.mp3', 'wb') as file:                file.write(MP3)                print(name,'下载成功')        except:            print('下载失败')if __name__ == '__main__':    #歌单地址    url = 'https://music.163.com/discover/toplist?id=3778678'    down(url)    #这里数据有点多可能会很慢因为这里是一个单线程写的    #感兴趣的话可以查看我写的那篇多线程的文章

总结

• 打开网易云音乐，随便找到一首歌，播放，复制网址的ID
• 例如：杨钰莹的心雨，网址是：
• 很明显，ID是317151
  https://music.163.com/#/song?id=317151
  那么，这首歌的真实地址就是：
  http://music.163.com/song/media/outer/url?id=317151.mp3
• 这个地址不会失效的；
  这就得到一个下载公式：
  http://music.163.com/song/media/outer/url?id=ID数字.mp3

把上面红色部分ID数字换成网易云播放页面的id即可。

• 潘美辰：我曾用心爱着你
• http://music.163.com/#/song?id=281951
• mp3下载、外链地址：
• http://music.163.com/song/media/outer/url?id=281951.mp3
  因为网址带特色字符所以我们是获取的不数据的我们把特色字符#去掉就可以了

转载地址：http://toywi.baihongyu.com/