python 爬取bilibili 视频弹幕

 # -*- coding: utf-8 -*-
 # @author: Tele
 # @Time  : 2019/04/09 下午 4:50
 # 爬取弹幕
 import requests
 import json
 import os
 from lxml import etree

 def main():
     headers = {
         "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",
     }
     # av13197279
     url = "https://api.bilibili.com/x/web-interface/view?aid=13197279"
     response = requests.get(url, headers=headers)
     if response.status_code == 200:
         cid = json.loads(response.content.decode())["data"]["cid"]
         print("cid:", cid)
         cid_url = "https://comment.bilibili.com/{}.xml".format(cid)

         # 解析弹幕的xml
         result = requests.get(cid_url, headers=headers)
         comment_element = etree.HTML(result.content)
         d_list = comment_element.xpath("//d")

         if os.path.exists("./comment.txt"):
             os.remove("./comment.txt")
         with open("./comment.txt", "w", encoding="utf-8") as file:
             for d in d_list:
                 file.write(d.xpath("./text()")[0])
                 file.write("\n")

 if __name__ == '__main__':
     main()