You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

55 lines
1.8 KiB

import requests
from bs4 import BeautifulSoup
2 months ago
#从BV号获取CID
def get_cid_from_bv(bv_ids):
cids=[]
for bv_id in bv_ids:
# 视频详情 API 地址
video_url = f'https://api.bilibili.com/x/web-interface/view?bvid={bv_id}'
# 发送请求
response = requests.get(video_url, headers=headers)
response.raise_for_status()
data = response.json()
# 提取 cid
if data.get('code') == 0:
cid = data.get('data', {}).get('cid')
cids.append(cid)
return cids
def get_danmu(id):
global videosnumber
video_url = f'https://api.bilibili.com/x/v1/dm/list.so?oid={id}'
response = requests.get(video_url, headers=headers) #要爬取的网址
response.encoding='utf-8' #编码方式
html = response.text
soup = BeautifulSoup(html) #使用beautifulsoup库快速查找我们想要的信息
all_txt = soup.findAll("d") #寻找到所有包含d的行
txt=[all_txts.attrs ["p"]for all_txts in all_txt] #寻找到所有包含d的行中属性为p的值这里边包含了弹幕的虚拟id等
txtss=[all_txts.string for all_txts in all_txt] #寻找到所有包含d的行中的字符串数据即弹幕内容
txtsss=[txts.replace(' ','') for txts in txtss] #将字符串中的空格消除掉
videosnumber = videosnumber +1
bulletnumber = len(txtsss)
print( f"这是第{videosnumber}视频, 获取到{bulletnumber}弹幕")
time.sleep(1)#休眠防被封
return(txtsss)
def main(kword,mubiao):
bvs=[]
alltxt=[]
for i in range(100):
cids = []
cids = get_cid_from_bv(bvs)
for id in cids:
if(videosnumber>=mubiao): break
txt = get_danmu(id)
alltxt=alltxt + txt
if(videosnumber>=mubiao): break
return(alltxt)
flag = 50 #你要爬的视频数量
altxt=main(keword,flag)