From ef50cc4aa0a032cd8013fd5813888419763abcb9 Mon Sep 17 00:00:00 2001
From: pjmw9izve <2308014474@qq.com>
Date: Thu, 12 Sep 2024 22:46:20 +0800
Subject: [PATCH] ADD file via upload

---
 get_danmu.py | 54 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 54 insertions(+)
 create mode 100644 get_danmu.py

diff --git a/get_danmu.py b/get_danmu.py
new file mode 100644
index 0000000..2ac80de
--- /dev/null
+++ b/get_danmu.py
@@ -0,0 +1,54 @@
+import requests
+from bs4 import BeautifulSoup
+import pandas as pd
+import time
+def get_danmu(urls):
+    # 获取BV号
+    bv_id = []
+    for url in urls:
+        parts = url.split('/')
+        for part in parts:
+            if part.startswith('BV'):
+                bv_id.append(part)
+    #获取cid号
+    cids = []
+    for id in bv_id:
+        url = f"https://api.bilibili.com/x/player/pagelist?bvid={id}&jsonp=jsonp"
+        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(url,headers=headers)
+        time.sleep(0.5)
+        if response.status_code == 200:
+            data = response.json()
+            if data['code'] == 0 and data['data']:
+                cid = data['data'][0]['cid']
+                cids.append(cid)
+    print("cid",len(cids))
+    #获取弹幕数据
+    danmu_data = []
+    fail_count = 0
+    for id in cids:
+        url = f"https://api.bilibili.com/x/v1/dm/list.so?oid={id}"
+        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(url,headers=headers)
+        time.sleep(0.5)
+        if response.status_code != 200:
+            fail_count += 1
+        response.encoding = 'utf-8'
+        danmu_data.append(response.text)
+    print("danmu_data_html",len(danmu_data))
+    print("fail_count",fail_count)
+    #返回一个所有弹幕的list
+    all_danmu = []
+    for html in danmu_data:
+        soup = BeautifulSoup(html, 'html.parser')
+        for d in soup.find_all('d'):
+            all_danmu.append(d.get_text())
+
+    print("all_danmu",len(all_danmu))
+    df = pd.DataFrame({'danmu': all_danmu})
+    df.to_excel("all_danmu_data.xlsx", index=False,engine='openpyxl')
+    return all_danmu