问我写了一个爬虫 想爬取腾讯视频的弹幕 但是总是获取不完整 求助？

如问题描述：开始是视频显示有60000多条弹幕，但是我只能爬取到25000条。

顺便 想问一下，js包里面的内容都代表什么呢？

视频网址https://v.qq.com/x/cover/pkd7mm8nlor7sqv/m0020d4bocq.html

其中一个js包中的一个内容：{"commentid"::"6129416678651013752","content":"今天我们","upcount":5,"isfriend":0,"isop":0,"isself":0,"timepoint":155,"headurl":"","opername":"","bb_bcolor":"","bb_head":"","bb_level":"","bb_id":"","rich_type":0,"uservip_degree":0,"content_style":""}

因为我看到第一个弹幕的时间戳是15所以设置的stamp=15，然后+=30

下面附代码，求助！

from urllib.parse import urlencode

import requests

import re

import csv

import time

import random

def search(base_url, time_stamp):

try:

headers = {

'user-agent': 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.104 Safari/537.36 Core/1.53.4295.400 QQBrowser/9.7.12661.400',

'accept': '*/*',

'accept - encoding': 'gzip, deflate, sdch, br',

'accept - language': 'zh-CN,zh;q=0.8',

'cache - control': 'max - age = 0',

'cookie':'cuid=9102028816; pgv_pvi=8393473024; RK=ITK8C31Rc1; tvfe_boss_uuid=047a68f022a12505; pac_uid=1_1179630150; ptui_loginuin=1179630150; ptisp=cnc; ptcz=4c8a92ec5e84326bd8926bc75a1413db138bc560b11fd2026cbb4652c51a10d9; uin=o1179630150; skey=@G4DR3fRZB; appid=3000501; login_time_init=1553069185; _video_qq_version=1.1; _video_qq_appid=3000501; _video_qq_login_time_init=1553069185; main_login=qq; vuserid=624788404; vusession=70de633e23002eb00000000012d275a5949283c2bd4e; next_refresh_time=4405; _video_qq_main_login=qq; _video_qq_vuserid=624788404; _video_qq_vusession=70de633e23002eb00000000012d275a5949283c2bd4e; _video_qq_next_refresh_time=4405; login_time_last=2019-3-20 16:42:40; o_cookie=1179630150; pgv_info=ssid=s3395872160; pgv_pvid=3092479592'

}

data = {

'timestamp': time_stamp,

'target_id': '1379190863',

}

# 使用urlencode()函数将参数表示为链接形式，进行拼接

url = base_url + urlencode(data)

response = requests.get(url, headers=headers)

if response.status_code == 200:

return response.text

except Exception:

return None

def get_30s_danmu(text):

id = re.findall(r'"commentid":"(.*?)",', text)

T = re.findall(r'"timepoint":(.*?),', text)

comments = re.findall(r'"content":"(.*?)",', text)

like = re.findall(r'"upcount":(.*?),"', text)

for (i, j, k, l) in zip(id, T, like, comments): # 生成可迭代对象

a=int(int(j)/60)

b=int(j)%60

c=":"

d=str(a)

e=str(b)

seq=(d,e)

j=c.join(seq)

with open('douluo_test1_danmu.csv', 'a+', newline='', encoding='utf-8-sig') as f: # newline=''可以避免存入空行；设置编码；追加写入

writer = csv.writer(f)

writer.writerow(['\''+str(i), str(j), str(k), l])

def main():

time_stamp = 15

num = 1

while True:

print('第{}次爬取'.format(num))

print('*'*50)

base_url = 'https://mfm.video.qq.com/danmu?'

text = search(base_url, time_stamp)

print('*'*50)

get_30s_danmu(text)

time_stamp += 30

num += 1

if __name__ == '__main__':

main()