Python爬取网易云音乐热歌榜（爬虫）

Python爬取网易云音乐热歌榜歌曲，并下载到本地

找到要下载歌曲排行榜的链接，这里用的是：
https://music.163.com/discover/toplist?id=3778678
然后更改你要保存的目录，目录要先建立好文件夹，例如我的是保存在D盘-360下载-网易云热歌榜文件夹内，就可以完成下载。如果文件夹没有提前建好，会报错[Errno 2] No such file or directory。

from urllib import request
from bs4 import BeautifulSoup
import re
import requests
import time


class Music(object):
    def __init__(self, baseurl, path):
        head = {
            "user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36"
            }
        self.baseurl = baseurl
        self.headers = head
        self.path = path


    def main(self):
        html = self.askurl()
        bs4 = self.analysis(html)
        name1 = self.matching(bs4)
        self.save(name1)


    def askurl(self):
        req = request.Request(url=self.baseurl, headers=self.headers)
        response = request.urlopen(req)
        html = response.read().decode("utf-8")
        return html


    def analysis(self, html):
        soup = BeautifulSoup(html, "html.parser")
        bs4 = soup.find_all("textarea")
        bs4 = str(bs4)
        return bs4


    def matching(self, bs4):
    	rule0 = re.compile(r'"name":"(.*?)","tns":[],"alias":[]')
        name0 = re.findall(rule0, bs4)
        str = ""
        for i in name0:
            str  = str + "," + i
        str = str.replace("\xa0", " ")
        rule1 = re.compile(r'jpg,(.*?),(.*?)","id":(\d*)')
        name1 = re.findall(rule1, str)
        return name1


    def save(self, name1):
        for j in name1:
            print("正在下载：" + j[1] + " - " + j[0] + "...")
            url = "http://music.163.com/song/media/outer/url?id=" + j[2]
            content = requests.get(url=url, headers=self.headers).content
            with open(self.path + j[1] + " - " + j[0] + ".mp3", "wb") as f:
                f.write(content)
            print(j[1] + " - " + j[0] + "下载完毕。\n")
            time.sleep(0.5)
        return


if __name__ == "__main__":
    baseurl = "https://music.163.com/discover/toplist?id=3778678"  # 要爬取的热歌榜链接
    path = "D:/360下载/网易云热歌榜/"  # 保存的文件目录
    demo0 = Music(baseurl, path)
    demo0.main()
    print("下载完毕")

写于8月5号，有想法可以一起探讨。

以上内容就不修改了。

8月18修改内容，加一句
baseurl = baseurl.replace("#/", “”)
就可以用网址：https://music.163.com/#/discover/toplist?id=3778678

def __init__(self, baseurl, path):
        head = {
            "user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36"
            }
        baseurl = baseurl.replace("#/", "")  # 8月18日添加一句
        self.baseurl = baseurl
        self.headers = head
        self.path = path