爬取全民K歌主页上的歌

最新推荐文章于 2023-10-11 09:43:56 发布

马踏飞燕&lin_li

最新推荐文章于 2023-10-11 09:43:56 发布

阅读量563

点赞数

分类专栏：爬虫

本文链接：https://blog.csdn.net/matafeiyanll/article/details/109425115

版权

爬虫专栏收录该内容

2 篇文章 0 订阅

订阅专栏

爬取全民K歌主页上的歌

import urllib.request
import requests
import os
import re

path = "C:\\Users\\HUAWEI\\Desktop\\spider\\kg"
url = "https://kg.qq.com/node/personal?uid=6a9d9a81222830833c"

# path = input("path:")
# url = input("url:")
#伪装浏览器用户


headers = {'User-Agent':'User-Agent:Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)'}
req = urllib.request.Request(url,headers=headers)

#执行请求获取响应信息
res = urllib.request.urlopen(req)

# 从响应对象中读取信息并解码
html = res.read().decode("utf-8")

# print(len(html))
#使用正则解析出歌曲链接
pat = '<a href="(.*?)" .*? target="_blank">(.*?)</a>'
dlist = re.findall(pat,html)

# 遍历输出结果
# for v in dlist:
#     print(v[1]+":"+v[0])

# 匹配歌曲链接
pat_music = 'http://[a-z][a-z].stream.kg.qq.com.*.m4a.*?"'

#获取当前目录下歌曲
for root,dirs,files in os.walk(path):
    print('root:',root)
    print('dirs',dirs)
    print('files',files)
    
for url in dlist:
    music = urllib.request.Request(url[0],headers=headers)
    res = urllib.request.urlopen(music)
    music_html = res.read().decode("utf-8")
    mus = re.findall(pat_music,music_html)
    if mus:
        mus_name = url[1] +".mp3"
        if(mus_name not in files):
            MP3 = requests.get(mus[0])
            if(path[-1]=='\\'):
                path_url =  path+mus_name
            else:
                path_url = path+'\\'+mus_name
            # print(path_url)
        else:
            MP3 = requests.get(mus[0])
            yesorno = input("是否需要覆盖：")
            if(yesorno=='y'):
                path_url = path+'\\'+mus_name
            else:
                mus_name = input("重命名:")
                path_url = path+'\\'+mus_name
        with open(path_url,"wb") as f:
            f.write(MP3.content)
            # if MP3.content:
            #     print(url[1]+":"+url[0])
            # else:
            #     print(url[1]+":"+url[0]+"write error!")