python学习记录5：爬取网易云音乐爬虫代码

#爬取163音乐

 

import requests
from lxml import etree
url='https://music.163.com/discover/toplist?id=3779629'
domain='http://music.163.com/song/media/outer/url?id='
html_str = requests.get(url).text
#print(type(html_str))
result = etree.HTML(html_str)

#print(type(result))
#song_ids = result.xpath('//a[contains(@href,"/song?")]/@href')
song_ids = result.xpath('//a[contains(@href,"/song?")]/@href')   # 歌曲id
song_names = result.xpath('//a[contains(@href,"/song?")]/text()')       # 歌名
print(song_ids)
i=0
for song_id,song_name in zip(song_ids,song_names):
    #print(song_id)
    #print(song_name)
    sult_id=song_id.strip('/song?id=')
    print(sult_id)
    #resulturl=domain+sult_id
    #print(resulturl)
    if ('$' in sult_id) == False:
#        # print(count_id)
        song_url = domain + sult_id      # 拼接url
        print(song_url)
    i += 1
    mp3 = requests.get(song_url).content
    with open('D:\mypython\爬163音乐\新歌/{}.{}.mp3'.format(i, song_name), 'wb') as file:
        file.write(mp3)
        print('歌曲{}{}.mp3下载成功!'.format(i,song_name))