python3写爬取B站视频弹幕功能

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

'<d p=".*">(.*"htmlcode">

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


参考代码如下,将弹幕按照日期保存为单个文件...因为太多了...


import requests
import re
import time
"""
  爬取哔哩哔哩视频弹幕信息
"""
# 2043618 是视频的弹幕标号,这个地址会返回时间列表
# https://www.bilibili.com/video/av1349282
url = 'https://comment.bilibili.com/rolldate,2043618'
# 获取弹幕的id 2043618
video_id = url.split(',')[-1]
print(video_id)
# 获取json文件
html = requests.get(url)
# print(html.json())
# 生成时间戳列表
time_list = [i['timestamp'] for i in html.json()]
# print(time_list)
# 获取弹幕网址格式 'https://comment.bilibili.com/dmroll,时间戳,弹幕号'
# 弹幕内容,由于总弹幕量太大,将每个弹幕文件分别保存
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
  # 匹配弹幕内容
  res = re.findall('<d p=".*">(.*"%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)


最终效果








之后可以 做一些分词生成词云或者进行情感分析,有时间在说吧....
大家可以在下方给小编留言你学习的心得，也感谢你对的支持。