|
|
|
@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
import requests
|
|
|
|
|
|
|
|
from bs4 import BeautifulSoup
|
|
|
|
|
|
|
|
headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36 Edg/128.0.0.0' }
|
|
|
|
|
|
|
|
response = requests.get("https://api.bilibili.com/x/v1/dm/list.so?oid=1512399639", 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
|
|
|
|
|
|
|
|
print(txtsss) ###打印便可看见一条条弹幕的属性和内容了。
|
|
|
|
|
|
|
|
|
