环境
- python3.8
- pycharm2021.2
知识点
- requests >>> pip install requests
- execjs >>> pip install PyExecJS
第一步
打开这个网站 在里面去分析我们需要的数据 每个音乐的名称 id
去网页源代码查找数据,发现并没有,这个网页 并不是一个静态页面
打开开发者工具,找到歌曲的id
找到真正的目标网址https://music.163.com/discover/toplist
【付费VIP完整版】只要看了就能学会的教程,80集Python基础入门视频教学
点这里即可免费在线观看
第二步
通过代码去实现当前这一个步骤
- 通过代码去访问当这个页面 C 拿到网页源代码
- 提取我们真正想要的 音乐的名称 id
- 下载音乐: id获取是为了下载音乐分析里面音乐数据的 加密规则 去下载歌曲
开始代码
先导入所需模块
import requests import re import execjs
请求数据
# 通过代码去访问当这个页面 -- 拿到网页源代码 url = 'https://music.163.com/discover/toplist' # 伪装 headers = { 'cookie': '_ntes_nuid=063717de540d3ec18d9b4a0bdf51e931; WM_TID=sxztjH%2FJbYZBEREFBQZvAgttUnJPrvYf; ntes_kaola_ad=1; NMTID=00OSBNvfChgV2TD7k5IhSzky6R8lXgAAAF0zoWmoA; _ntes_nnid=063717de540d3ec18d9b4a0bdf51e931,1607344992641; _iuqxldmzr_=32; OUTFOX_SEARCH_USER_ID_NCOO=2145381542.3273497; WEVNSM=1.0.0; WNMCID=sazafu.1624080681192.01.0; UM_distinctid=17b784cb58a17-097be09ee87fb9-c343365-1aeaa0-17b784cb58b8bc; __root_domain_v=.163.com; _qddaz=QD.159230735652240; vinfo_n_f_l_n3=11aae7905aa2179b.1.11.1575470964063.1625470009945.1632894007779; usertrack=ezq0J2FlcQWNYypxAx88Ag==; JSESSIONID-WYYY=Yvm62%5Cnd8XNkT2ryCNOJx9urqXsxCDMF6srNnGRegtmuNdB5MrrS9ou%2FWw3JbVf960uHnGW3Bb%2Fbhv2xZm3Vn%2B%2BonZSX38sqKiUMuRd6TDKD39HRzGmrZ%5Cp9IUaNs%5C5nYt9xltJBt5qRgWsl0PZsxDhSu26ugGAozPffXXAjemm0o%2Fv%5C%3A1634111694844; WM_NI=au9XpuutN3GwymEoZsAgWl6%2BH4cTcHgYKos%2BWibR3hSntTQhrpX%2FLoCAycOKLnZteLb1LlluoIk9jlKxaaUThS4tfZr9jWB3LVjXKQUH4%2BMpukbEPcnHaN80J8%2FhoqeeYms%3D; WM_NIKE=9ca17ae2e6ffcda170e2e6ee8de74b85b18eb3b27bae8e8ab2d44e969f9aafae3388af8f98d06da59b968ecf2af0fea7c3b92aa3abf7b9f37fb7ac82d4c67dbbb38b90d97983b9998db5218cecadb5e244a5878590f22195b7aeb3b26491b2bcb5d464b2b098d0cf65819fb784ce4190b29695e848a2ef848def7fad97a5dae96889a8af82d860ac8dfc95e552b2e7a6b8c139908aa6b9ca5b9798fcccd07cb7b5aea6d369ae98afafbb3c8ae8e189ee7ba7bb978ef237e2a3; playerid=29374327', 'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.81 Safari/537.36' } # url: 分析出来的真正数据链接 # headers: 伪装请求头 response = requests.get(url, headers).text # <Response [200]>: 告诉你访问成功了
提取我们真正想要的 音乐的名称 id
zip_data = re.findall('<li><a href="http://www.codebaoku.com/song\?id=(.*?)" rel="external nofollow" rel="external nofollow" >(.*?)</a></li>', response) for music_id, title in zip_data: # url_1 = 'http://music.163.com/song/media/outer/url?id=' + music_id url_1 = 'https://music.163.com/weapi/song/enhance/player/url/v1?csrf_token=' result = ctx.call('start', music_id) data = { 'params': result['encText'], 'encSecKey': result['encSecKey'] } # 发送请求 # 当前的音乐数据 music_url = requests.post(url_1, data=data, headers=headers).json()['data'][0]['url'] music_data = requests.get(music_url, headers).content f.write(music_data) print(title)
完整代码
import requests import re import execjs url = 'https://music.163.com/discover/toplist' # 伪装 headers = { 'cookie': '_ntes_nuid=063717de540d3ec18d9b4a0bdf51e931; WM_TID=sxztjH%2FJbYZBEREFBQZvAgttUnJPrvYf; ntes_kaola_ad=1; NMTID=00OSBNvfChgV2TD7k5IhSzky6R8lXgAAAF0zoWmoA; _ntes_nnid=063717de540d3ec18d9b4a0bdf51e931,1607344992641; _iuqxldmzr_=32; OUTFOX_SEARCH_USER_ID_NCOO=2145381542.3273497; WEVNSM=1.0.0; WNMCID=sazafu.1624080681192.01.0; UM_distinctid=17b784cb58a17-097be09ee87fb9-c343365-1aeaa0-17b784cb58b8bc; __root_domain_v=.163.com; _qddaz=QD.159230735652240; vinfo_n_f_l_n3=11aae7905aa2179b.1.11.1575470964063.1625470009945.1632894007779; usertrack=ezq0J2FlcQWNYypxAx88Ag==; JSESSIONID-WYYY=Yvm62%5Cnd8XNkT2ryCNOJx9urqXsxCDMF6srNnGRegtmuNdB5MrrS9ou%2FWw3JbVf960uHnGW3Bb%2Fbhv2xZm3Vn%2B%2BonZSX38sqKiUMuRd6TDKD39HRzGmrZ%5Cp9IUaNs%5C5nYt9xltJBt5qRgWsl0PZsxDhSu26ugGAozPffXXAjemm0o%2Fv%5C%3A1634111694844; WM_NI=au9XpuutN3GwymEoZsAgWl6%2BH4cTcHgYKos%2BWibR3hSntTQhrpX%2FLoCAycOKLnZteLb1LlluoIk9jlKxaaUThS4tfZr9jWB3LVjXKQUH4%2BMpukbEPcnHaN80J8%2FhoqeeYms%3D; WM_NIKE=9ca17ae2e6ffcda170e2e6ee8de74b85b18eb3b27bae8e8ab2d44e969f9aafae3388af8f98d06da59b968ecf2af0fea7c3b92aa3abf7b9f37fb7ac82d4c67dbbb38b90d97983b9998db5218cecadb5e244a5878590f22195b7aeb3b26491b2bcb5d464b2b098d0cf65819fb784ce4190b29695e848a2ef848def7fad97a5dae96889a8af82d860ac8dfc95e552b2e7a6b8c139908aa6b9ca5b9798fcccd07cb7b5aea6d369ae98afafbb3c8ae8e189ee7ba7bb978ef237e2a3; playerid=29374327', 'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.81 Safari/537.36' } response = requests.get(url, headers).text zip_data = re.findall('<li><a href="http://www.codebaoku.com/song\?id=(.*?)" rel="external nofollow" rel="external nofollow" >(.*?)</a></li>', response) js = open('music163.js', mode='r', encoding='utf-8').read() ctx = execjs.compile(js) for music_id, title in zip_data: url_1 = 'https://music.163.com/weapi/song/enhance/player/url/v1?csrf_token=' result = ctx.call('start', music_id) data = { 'params': result['encText'], 'encSecKey': result['encSecKey'] } music_url = requests.post(url_1, data=data, headers=headers).json()['data'][0]['url'] music_data = requests.get(music_url, headers).content with open('music/' + title + '.mp3', mode='wb') as f: f.write(music_data) print(title)
到此这篇关于Python爬虫实战之网易云音乐加密解析附源码的文章就介绍到这了,更多相关Python 网易云音乐解析内容请搜索服务器之家以前的文章或继续浏览下面的相关文章希望大家以后多多支持服务器之家!
原文链接:https://pythonjx.blog.csdn.net/article/details/120747494