Python 爬取喜马拉雅免费相声音频

qiuyouzhi

1. from requests import get
   
2. from lxml import etree
   
3. import os
   
4. try:
   
5.     os.mkdir("Video")
   
6.     os.chdir("Video")
   
7. except:
   
8.     os.chdir("Video")
   
9. 
   
10. def open_url(url):
    
11.     headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.129 Safari/537.36'}
    
12.     res = get(url, headers=headers)
    
13.     return res
    
14. 
    
15. def get_xs(res):
    
16.     temp = 'https://www.ximalaya.com/xiangsheng'
    
17.     html = etree.HTML(res.text)
    
18.     name = html.xpath("//*[@class='general-album-list']/div[@class='content']/ul/li/div/a/span/text()")
    
19.     href = [temp + each for each in html.xpath("//*[@class='general-album-list']/div[@class='content']/ul/li/div/a[1]/@href")]
    
20.     i = 1
    
21.     result = {}
    
22.     for k in zip(name, href):
    
23.         result[i] = k
    
24.         i += 1
    
25.     return result
    
26. 
    
27. def get_Videourl(nm, hf):
    
28.     res = open_url(hf)
    
29.     vdurl = []
    
30.     temp = 'https://www.ximalaya.com/xiangsheng'
    
31.     html = etree.HTML(res.text)
    
32.     href = html.xpath('//*[@class="sound-list _Qp"]/ul/li/div[2]/a/@href')
    
33.     name = html.xpath('//*[@class="sound-list _Qp"]/ul/li/div[2]/a/span/text()')
    
34.     ids = [each[-9:] for each in html.xpath('//*[@class="sound-list _Qp"]/ul/li/div[2]/a/@href')]
    
35.     # for nm, hf in zip(name, href):
    
36.     #     print(nm, ':', temp + hf)
    
37.     for id in ids:
    
38.         vdurl.append('https://www.ximalaya.com/revision/play/v1/audio?id=%s&ptype=1' % id)
    
39.     return vdurl, name
    
40. 
    
41. def get_Video(vdurl, nm):
    
42.     i = 0
    
43.     for url in vdurl:
    
44.         res = open_url(url).json()
    
45.         for each in res:
    
46.             if type(res[each]) != int:
    
47.                 tempurl = res[each]['src']
    
48.                 video = open_url(tempurl)
    
49.                 filename = f"{nm[i]}.m4a"
    
50.                 print("正在下载：",filename)
    
51.                 print(i)
    
52.                 with open(filename, 'wb') as f:
    
53.                     f.write(video.content)
    
54.         i += 1
    
55. 
    
56. def main():
    
57.     url = 'https://www.ximalaya.com/xiangsheng/xiangsheng/mr132t2722/'
    
58.     res = open_url(url)
    
59.     result = get_xs(res)
    
60.     for i in result:
    
61.         for nm in result[i]:
    
62.             print(i, end = ' ')
    
63.             print(nm)
    
64.             break
    
65. 
    
66.     choice = int(input("请选择您要听的专辑序号："))
    
67.     nm, hf = result[choice]
    
68.     vdurl, nm = get_Videourl(nm, hf)
    
69.     get_Video(vdurl, nm)
    
70. 
    
71. 
    
72. if __name__ == "__main__":
    
73.     main()

复制代码

我待会把思路发出来，顺便说几个缺陷:

1,翻页没有写

2，爬取相声数量太少

这些我都会一一改进，如果有好的建议，请回复我，谢谢

_2_

沙发！
支持楼主！

liuzhengyuan

付费音频的能爬吗

qiuyouzhi

liuzhengyuan 发表于 2020-5-1 16:48
付费音频的能爬吗

前提我得有个VIP的账号

李子豪

支持一波

wuqramy

应该是免费的都能爬吧

qiuyouzhi

wuqramy 发表于 2020-5-4 17:38
应该是免费的都能爬吧

是的