爬虫-弹幕

参考链接：https://blog.csdn.net/jj8999999/article/details/108845791

import requests
import pandas as pd

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36",
}

datas = []
# 每集90多分钟，所以100够了！
for i in range(100):
    print(f'\r{i}', end='')
    # search bullet
    url = f'https://bullet-ali.hitv.com/bullet/2021/08/17/192249/13137070/{i}.json'
    r = requests.get(url, headers=headers)

    if r.status_code == 200:
        data = r.json()
        data = data['data']['items']
        datas.extend(data)
    else:
        break

df = pd.DataFrame(datas)
df.isnull().sum()
df = df[['ids', 'uid', 'content', 'time', 'v2_up_count']].fillna(0)

df['时间'] = df.time // 60000
# data analysis
df.info()