From fbdc723e937dd0205a6e02204fbaf90f619dee2b Mon Sep 17 00:00:00 2001
From: QMZ <1164250597@qq.com>
Date: Fri, 13 Sep 2024 22:19:24 +0800
Subject: [PATCH] =?UTF-8?q?=E8=8E=B7=E5=8F=96=E5=8D=95=E4=B8=AA=E8=A7=86?=
 =?UTF-8?q?=E9=A2=91=E7=9A=84=E5=BC=B9=E5=B9=95?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 getdanmu.py | 13 +++++++++++++
 1 file changed, 13 insertions(+)
 create mode 100644 getdanmu.py

diff --git a/getdanmu.py b/getdanmu.py
new file mode 100644
index 0000000..a0d9a03
--- /dev/null
+++ b/getdanmu.py
@@ -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。
+