Python3爬取音乐

最新推荐文章于 2024-08-16 11:38:09 发布

HelloWorld. py

最新推荐文章于 2024-08-16 11:38:09 发布

阅读量492

点赞数

分类专栏：就爱敲代码

本文链接：https://blog.csdn.net/AK47red/article/details/103777359

版权

就爱敲代码专栏收录该内容

39 篇文章 1 订阅

订阅专栏

'''
思路： 从缩略图页面开始爬取
1) 先爬取所有缩略图的a标签
2)
3)
'''
import requests
from bs4 import BeautifulSoup
import os
if not os.path.exists("音乐"):
    os.makedirs("音乐")
import lxml
from urllib import request

url = "https://www.i4.cn/ring_22_0_1.html"

if __name__ == '__main__':
    for i in range(1, 5):
        url = "https://www.i4.cn/ring_22_0_%d.html"%i
        req = requests.get(url = url)
        req.encoding = 'utf-8'
        print("响应码: ", req.status_code)
        html = req.text
        bf = BeautifulSoup(html, "lxml")
        ring_list = bf.find_all('div', class_ = "list ring_list")
        for item in ring_list:
            #print(item.get('href'), item.get("title"))
            # name = item.get("title")
            # print(name)
            bf2 = BeautifulSoup(str(item), 'lxml')
            title = bf2.select(".title")
            name = title[0].string + ".mp3"
            url_ = bf2.select(".audio_play")

            url = url_[0].get("data-mp3")
            print(url)
            request.urlretrieve(filename="音乐/%s.jpg" %name, url= url)
            print("%s下载成功" % name + '>' * 10)