python爬取b站弹幕_python3 爬取B站视频弹幕

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...

importrequests

importre

importtime

""" 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'] fori inhtml.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

fori intime_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('(.*?)', text)

# 将时间戳转化为日期形式,需要把字符串转为整数timeArray = time.localtime(int(i)) date_time = time.strftime("%Y-%m-%d %H:%M:%S", timeArray) print(date_time) content += date_time + ''fork inres: content += k + ''content += ''file_path = 'txt/{}.txt'.format(time.strftime("%Y_%m_%d", timeArray)) print(file_path)

withopen(file_path, mode='w+', encoding='utf8') asf: f.write(content)