小破站视频爬取-仅供学习使用

文静

1. import requests
   
2. import re
   
3. import time
   
4. from lxml import etree
   
5. import json
   
6. from moviepy.editor import *
   
7. 
   
8. url = input（'视频网址：'）
   
9. headers = {
   
10.     'Referer': url,
    
11.     'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:89.0) Gecko/20100101 Firefox/89.0'
    
12. }
    
13. 
    
14. res = requests.get(url,headers=headers)
    
15. html_data = etree.HTML(res.content.decode())
    
16. title = html_data.xpath('//*[@id="viewbox_report"]/h1/span/text()')[0]
    
17. titles = title + "&"
    
18. # print(title)
    
19. 
    
20. response = res.text
    
21. pattern = '<script>window\.__playinfo__=(.*?)</script>'
    
22. list1 = re.findall(pattern,response,re.S)
    
23. list_json = json.loads(list1[0])
    
24. video_url = list_json['data']['dash']['video'][0]['baseUrl']
    
25. audio_url = list_json['data']['dash']['audio'][0]['baseUrl']
    
26. # print(video_url)
    
27. # print(audio_url)
    
28. 
    
29. video_res = requests.get(video_url,headers=headers)
    
30. audio_res = requests.get(audio_url,headers=headers)
    
31. 
    
32. with open('%s.mp4'%titles,'wb') as f:
    
33.     f.write(video_res.content)
    
34. with open('%s.mp3'%titles,'wb') as f:
    
35.     f.write(audio_res.content)
    
36. time.sleep(3)
    
37. # 读取视频文件 和读取音频文件
    
38. videoclip = VideoFileClip("%s.mp4"%titles)
    
39. Audioclip = AudioFileClip("%s.mp3"%titles)
    
40. # 给videoclip视频 添加音频Audioclip
    
41. video_data = videoclip.set_audio(Audioclip)
    
42. # 添加好了后 再输出为一个视频
    
43. video_data.write_videofile('%s.mp4'%(title))

复制代码

helenfalcon

感谢！