python网易云音乐爬虫原理_Python爬虫实战：网易云音乐爬取

前言

本文的文字及图片来源于网络,仅供学习、交流使用,不具有任何商业用途,如有问题请及时联系我们以作处理。

本次目标

爬取网易云音乐

https://music.163.com/

环境

python 3.6

pycharm

爬虫代码

导入工具

import requests

import re

请求网站、解析网站数据

def get_music_url(music_id, music_title):

url = 'https://api.zhuolin.wang/api.php'

headers = {

'Accept': '*/*',

'Accept-Encoding': 'gzip, deflate, br',

'Accept-Language': 'zh-CN,zh;q=0.9',

'Cache-Control': 'no-cache',

'Connection': 'keep-alive',

'Cookie': 'UM_distinctid=175aca5b31d39e-06d658eceb014a-3962420d-1fa400-175aca5b31e92e',

'Host': 'api.zhuolin.wang',

'Pragma': 'no-cache',

'Referer': 'https://music.zhuolin.wang/',

'Sec-Fetch-Dest': 'script',

'Sec-Fetch-Mode': 'no-cors',

'Sec-Fetch-Site': 'same-site',

'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36',

}

params = {

'callback': 'jQuery111305698848623906863_1604919341715',

'types': 'url',

'id': '{}'.format(music_id),

'source': 'netease',

'_': '1604919341751',

}

response = requests.get(url=url, params=params, headers=headers)

html_data = response.text

if music_url == '':

print('无音频下载链接')

def music_id():

url = 'https://music.163.com/discover/toplist'

headers = {

'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36'

}

response = requests.get(url=url, headers=headers)

lis = re.findall('

(.*?)', response.text, re.S)[0:100]

for i in lis:

music_id = i[0].split('id=')[-1]

title = i[1]

pattern = re.compile(r"[\/\\\:\*\?\"\<\>\|]") # '/ \ : * ? " < > |'

music_title = re.sub(pattern, "_", title) # 替换为下划线

get_music_url(music_id, music_title)

保存数据

else:

path = '保存地址\\' + music_title + '.mp3'

response = requests.get(url=music_url)

with open(path, mode='wb') as f:

f.write(response.content)

print(music_title, music_url)

运行代码，结果如下图