能够提取综合排序前300个视频的弹幕

2 months ago · 69679670f7
parent 7de7dcaa79
commit 69679670f7
1 changed files with 93 additions and 0 deletions
--- a/python3.py
+++ b/python3.py
@ -0,0 +1,93 @@
+import requests
+import re
+
+def GetResponse(url, data):
+    """
+    发送请求
+    - url: 请求网址
+    - data: 请求参数
+    """
+    # 模拟游览器
+    headers = {
+        # Cookie 用户信息，常用于检测是否有登陆账号
+        "Cookie": "b_nut=1655303638; CURRENT_BLACKGAP=0; i-wanna-go-back=-1; buvid_fp_plain=undefined; buvid3=136172B5-8F7E-42EF-90C5-2D4A04147EE8167644infoc; LIVE_BUVID=AUTO3016558277732131; is-2022-channel=1; DedeUserID=17012171; DedeUserID__ckMd5=f518907167c48789; buvid4=88DCF3D1-502C-06D9-BF49-B7E4F0A0519315466-022061522-P1wwgn5lZ%2FpHMTaSvipifA%3D%3D; rpdid=|(JlRYJ~Ykl)0J'u~|JulJkJm; b_ut=5; FEED_LIVE_VERSION=V_HEADER_LIVE_NO_POP; _uuid=10525FA4C-8522-AFCC-210B4-19DE77B6FC8C66067infoc; enable_web_push=DISABLE; header_theme_version=CLOSE; CURRENT_FNVAL=16; fingerprint=913be879852fe07606cd36fdc205d010; home_feed_column=5; PVID=2; buvid_fp=913be879852fe07606cd36fdc205d010; bili_ticket=eyJhbGciOiJIUzI1NiIsImtpZCI6InMwMyIsInR5cCI6IkpXVCJ9.eyJleHAiOjE3MjY1ODE3NTksImlhdCI6MTcyNjMyMjQ5OSwicGx0IjotMX0.gM_SG7dtVNHO6JWzjJQb9TKfMdYUCQCc5kwBCvwvLTg; bili_ticket_expires=1726581699; CURRENT_QUALITY=120; SESSDATA=453edc86%2C1742051724%2C4ecfc%2A92CjBdMxud0tS4fWj_7UbpyntEQgA3SRR47yjry_nQGUMYCBxWrcLTlEr08nFsh9Jb83oSVkJZQXlsMXN0MkQxRU9lQzZ2NjhmS1BGVHBETjVsUHVTX2lSeG9xMWpYUE1BM3hVcTljZWpUcnUzNmdlU29JMTh4a1otc3VUYUlPUmNPOFFteWctWm1nIIEC; bili_jct=1b519a4b9101a167c49d8dad05dbdb80; b_lsid=AB4510676_191FF788B10; sid=8axcda7r; bmg_af_switch=1; bmg_src_def_domain=i0.hdslb.com; browser_resolution=1707-837; bp_t_offset_17012171=978105529521930240",
+        # User-Agent 用户代理，表示游览器基本身份信息/设备信息
+        "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"
+    }
+    
+    # 发送请求
+    response = requests.get(url = url, params = data, headers = headers)
+    
+    # 返回内容
+    return response
+
+def GetBvids():
+    """获取综合排序前300个视频的bvid"""
+    pages = 10
+    bvids = []
+    for page in range(1, pages + 1):
+        if len(bvids) >= 300:
+            break
+        
+        # 该页请求网址
+        url = f"https://api.bilibili.com/x/web-interface/wbi/search/type?category_id=&search_type=video&ad_resource=5654&__refresh__=true&_extra=&context=&page={page}&page_size=42&pubtime_begin_s=0&pubtime_end_s=0&from_source=&from_spmid=333.337&platform=pc&highlight=1&single_column=0&keyword=2024%E5%B7%B4%E9%BB%8E%E5%A5%A5%E8%BF%90%E4%BC%9A&qv_id=v6jFbUhcT7bjHVQXrLt535Vt7pgQ0qf1&source_tag=3&gaia_vtoken=&dynamic_offset=24&web_location=1430654&w_rid=532d2b5246861f41eb2ab975ff882c0d&wts=1726475442"
+        
+        # 发送请求 + 获取数据
+        Jsondata = GetResponse(url = url, data = None).json()  
+        
+        # 解析数据，提取视频信息
+        result = Jsondata['data']['result']
+        
+        #for 循环遍历，提取列表里面元素
+        for index in result:
+            bvids.append(index['bvid'])
+            if len(bvids) >= 300:
+                break
+    return bvids
+
+def GetCids(bvids):
+    """通过bvid获取综合排序前300个视频的cid"""
+    cids = []
+    for bvid in bvids:
+        url = f"https://www.bilibili.com/video/{bvid}"
+        response = GetResponse(url = url, data = None)
+        
+        #通过正则表达式匹配出cid
+        cid_pattern = re.compile(r'"cid":(\d+)')
+        cid = cid_pattern.search(response.text).group(1)
+        
+        cids.append(cid)
+    return cids
+
+def GetDanmus(cids):
+    """通过cid获取综合排序前300个视频的弹幕"""
+    DanmuDict = {}
+    for cid in cids:
+        url = f"https://api.bilibili.com/x/v1/dm/list.so?oid={cid}"
+        response = GetResponse(url = url, data = None)
+        
+        #转码以正常读取中文信息
+        response.encoding = 'utf-8'
+        
+        danmus = re.findall('<d p=".*?">(.*?)</d>', response.text)
+        
+        #统计每条弹幕的数量
+        for danmu in danmus:
+            if danmu in DanmuDict:
+                DanmuDict[danmu] += 1
+            else:
+                DanmuDict[danmu] = 1
+    return DanmuDict
+    
+def GetInfo():
+    """获取视频数据"""
+    bvids = GetBvids()
+    print(bvids)
+    cids = GetCids(bvids)
+    print(cids)
+    Danmus = GetDanmus(cids)
+    print(Danmus)
+    
+
+if __name__  == '__main__':
+    GetInfo()