获取弹幕

getdanmu.py

@@ -1,13 +1,54 @@
 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'   }
+#从BV号获取CID
-response = requests.get("https://api.bilibili.com/x/v1/dm/list.so?oid=1512399639", headers=headers) #要爬取的网址
+def get_cid_from_bv(bv_ids):
-response.encoding='utf-8' #编码方式
+    cids=[]
-html = response.text
+    for bv_id in bv_ids:
-soup = BeautifulSoup(html) #使用beautifulsoup库快速查找我们想要的信息
+        # 视频详情 API 地址
-all_txt = soup.findAll("d") #寻找到所有包含d的行
+        video_url = f'https://api.bilibili.com/x/web-interface/view?bvid={bv_id}'
-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
+        # 发送请求
-txtsss=[txts.replace(' ','') for txts in txtss] #将字符串中的空格消除掉
+        response = requests.get(video_url, headers=headers)
-print(txtsss) ###打印便可看见一条条弹幕的属性和内容了。
+        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)
+