python 爬取bilibili 视频弹幕

 1 # -*- coding: utf-8 -*-
 2 # @author: Tele
 3 # @Time  : 2019/04/09 下午 4:50
 4 # 爬取弹幕
 5 import requests
 6 import json
 7 import os
 8 from lxml import etree
 9 
10 
11 def main():
12     headers = {
13         "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36",
14     }
15     # av13197279
16     url = "https://api.bilibili.com/x/web-interface/view?aid=13197279"
17     response = requests.get(url, headers=headers)
18     if response.status_code == 200:
19         cid = json.loads(response.content.decode())["data"]["cid"]
20         print("cid:", cid)
21         cid_url = "https://comment.bilibili.com/{}.xml".format(cid)
22 
23         # 解析弹幕的xml
24         result = requests.get(cid_url, headers=headers)
25         comment_element = etree.HTML(result.content)
26         d_list = comment_element.xpath("//d")
27 
28         if os.path.exists("./comment.txt"):
29             os.remove("./comment.txt")
30         with open("./comment.txt", "w", encoding="utf-8") as file:
31             for d in d_list:
32                 file.write(d.xpath("./text()")[0])
33                 file.write("\n")
34 
35 
36 if __name__ == '__main__':
37     main()