pip3 install request -i http://pypi.douban.com/simple
          

            
'
            
              (.*?)
            
            '
          

            
with open('content.txt', mode='w+', encoding='utf8') as f:  f.write(content)
          

            
import requests
import re
import time
"""
  爬取嗶哩嗶哩視頻彈幕信息
"""
# 2043618 是視頻的彈幕標號,這個地址會返回時間列表
# https://www.bilibili.com/video/av1349282
url = 'https://comment.bilibili.com/rolldate,2043618'
# 獲取彈幕的id 2043618
video_id = url.split(',')[-1]
print(video_id)
# 獲取json文件
html = requests.get(url)
# print(html.json())
# 生成時間戳列表
time_list = [i['timestamp'] for i in html.json()]
# print(time_list)
# 獲取彈幕網址格式 'https://comment.bilibili.com/dmroll,時間戳,彈幕號'
# 彈幕內容,由于總彈幕量太大,將每個彈幕文件分別保存
for i in time_list:
  content = ''
  j = 'https://comment.bilibili.com/dmroll,{0},{1}'.format(i, video_id)
  print(j)
  text = requests.get(j).text
  # 匹配彈幕內容
  res = re.findall('
            
              (.*?)
            
            ', text)
  # 將時間戳轉化為日期形式,需要把字符串轉為整數
  timeArray = time.localtime(int(i))
  date_time = time.strftime("%Y-%m-%d %H:%M:%S", timeArray)
  print(date_time)
  content += date_time + '\n'
  for k in res:
    content += k + '\n'
  content += '\n'
  file_path = 'txt/{}.txt'.format(time.strftime("%Y_%m_%d", timeArray))
  print(file_path)
  with open(file_path, mode='w+', encoding='utf8') as f:
    f.write(content)