不需要动脑子就能爬取bilibili视频弹幕

比眉伴天荒 2022-12-27 01:12 155阅读 0赞

## 爬取bilibili视频弹幕——通用 ##

只需要你动手修改一个参数就可以实现bilibili全网视频弹幕爬取，并且这里还用到了多线程模块  
**demo.py**

import requests
    import pandas as pd
    import re
    import time
    import random
    from concurrent.futures import ThreadPoolExecutor
    import datetime
    from fake_useragent import UserAgent
    user_agent = [
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6",
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6",
        "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1",
        "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
        "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24"
        ]#这里可以优化，使用导入伪造头部信息的模块 from fake_useragent import UserAgent
    start_time = datetime.datetime.now()
    def  Grab_barrage(date):
        # 伪装请求头
        headers = { 
            "sec-fetch-dest": "empty",
            "sec-fetch-mode": "cors",
            "sec-fetch-site": "same-site",
            "origin": "https://www.bilibili.com",
            "referer": "https://www.bilibili.com/video/BV1Z5411Y7or?from=search&seid=8575656932289970537",
            "cookie": "_uuid=0EBFC9C8-19C3-66CC-4C2B-6A5D8003261093748infoc; buvid3=4169BA78-DEBD-44E2-9780-B790212CCE76155837infoc; sid=ae7q4ujj; DedeUserID=501048197; DedeUserID__ckMd5=1d04317f8f8f1021; SESSDATA=e05321c1%2C1607514515%2C52633*61; bili_jct=98edef7bf9e5f2af6fb39b7f5140474a; CURRENT_FNVAL=16; rpdid=|(JJmlY|YukR0J'ulmumY~u~m; LIVE_BUVID=AUTO4315952457375679; CURRENT_QUALITY=80; bp_video_offset_501048197=417696779406748720; bp_t_offset_501048197=417696779406748720; PVID=2",
            "user-agent": random.choice(user_agent),
            #也可以使用 "user-agent": UserAgent().random
        }
        # 构造url访问 需要用到的参数
        params = { 
            'type': 1,
            'oid': '262657924',#这里改成你自己需要爬取视频的cid，通过F12去找到该相关参数 但是我不知道为啥前面的key是 oid
            'date': date#这个时间根据弹幕的历史数量来，起始时间和结束时间都可以自定义
        }
        # 发送请求 获取响应
        response = requests.get(url, params=params, headers=headers)#get请求，params是添加在url后面的附带链接，具体自行百度
        # print(response.encoding) 重新设置编码
        response.encoding = 'utf-8'
        # print(response.text)
        # 正则匹配提取数据
        comment = re.findall('<d p=".*?">(.*?)</d>', response.text)
        # 将每条弹幕数据写入txt
        with open('barrages1.txt', 'a+') as f:
            for con in comment:
                f.write(con + '\n')
        time.sleep(random.randint(1, 3))   # 休眠
        def main():
        # 开多线程爬取 提高爬取效率
        with ThreadPoolExecutor(max_workers=4) as executor:
            executor.map(Grab_barrage, date_list)
        # 计算所用时间
        delta = (datetime.datetime.now() - start_time).total_seconds()
        print(f'用时：{delta}s')
    
    
    if __name__ == '__main__':
        # 目标url
        url = "https://api.bilibili.com/x/v2/dm/history"#弹幕池固定url
        start = '20200601'#自定义
        end = '20201205'#自定义
        # 生成时间序列
        date_list = [x for x in pd.date_range(start, end).strftime('%Y-%m-%d')]
        count = 0
        # 调用主函数
        main()

哔哩哔哩的弹幕都是在弹幕池里的，在这个程序里面只需要找到视频cid即可，cid参数看下图  
[图片链接][Link 1]![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQ0NzYwOTEy_size_16_color_FFFFFF_t_70_pic_center]  
文章算是原创总结，代码非原创，仅做学习用途。烦请各位大佬给我点点赞，鼓励鼓励我！

[Link 1]: https://hbimg.huabanimg.com/5912c874b20295eba84976f1b67c0405561ee9e0d842-mHHOmu
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQ0NzYwOTEy_size_16_color_FFFFFF_t_70_pic_center]: /images/20221120/cf2404c751eb4003bf8d497d10de765b.png