爬bilibili弹幕

import re, requests
from lxml import etree

class Blbl(object):
   def __init__(self, url):
       self.url = url
       self.headers = {
           'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36'
       }

   def get_html(self,url):
       try:
           return requests.get(url, headers=self.headers)
       except:
           print("获取失败")

   def get_xml(self, cid):
       url = "https://comment.bilibili.com/{}.xml"
       response = self.get_html(url.format(cid))
       html = etree.HTML(response.content)
       danmu_list = html.xpath('//d/text()')
       with open('danmu.text', 'w', encoding='utf-8') as f:
           for danmu in danmu_list:
               f.write(danmu + '\n')

   def run(self):
       response = self.get_html(self.url)
       # print(html)
       pattern = re.compile(r'cid=(\d+)\&')
       cid = pattern.findall(response.text)[0]
       self.get_xml(cid)

if __name__ == '__main__':
   url = 'https://www.bilibili.com/video/av16757535'
   bili = Blbl(url)
   bili.run()