Python爬虫案例--音乐网站mp3文件的提取

# 爬取tuke88的配乐mp3文件 

2 

3 import os

4 import random

5 import time

6 import requests

7 import lxml.etree

8 

9 page_n = int(input("请输入你想爬取的网页数量")) 

10 

11 for i in range(page_n): 

12 url = f'http://www.tuke88.com/peiyue/zonghe_0_{i}.html' 

13 response = requests.get(url) 

14 html_parser = lxml.etree.HTMLParser() 

15 html = lxml.etree.fromstring(response.text, parser=html_parser) 
 titles = html.xpath("//div[@class='lmt']//div[@class='audiolist']//a[@class='title']/text()") 

16


mp3_urls = html.xpath("//div[@class='lmt']//div[@class='audiolist']//source/@src") 

17
18
if not os.path.exists("pymp3"): 

19 os.mkdir('pymp3') 

20 for title, mp3_url in zip(titles, mp3_urls): 

21 mp3_stream = requests.get(mp3_url, stream=True) 

22 with open(os.path.join('pymp3', title + '.mp3'), 'wb+') as writer: 

23 writer.write(mp3_stream.raw.read()) 

24 print(f"【INFO】{title}.mp3下载成功") 

25 time.sleep(random.uniform(0.1, 0.4))