🚑: Fix Douyin API and Add Douyin Live API

scraper.py

@@ -2,8 +2,8 @@
 # -*- encoding: utf-8 -*-
 # @Author: https://github.com/Evil0ctal/
 # @Time: 2021/11/06
-# @Update: 2022/12/19
+# @Update: 2022/12/22
-# @Version: 3.1.7
+# @Version: 3.1.8
 # @Function:
 # 核心代码，估值1块(๑•̀ㅂ•́)و✧
 # 用于爬取Douyin/TikTok数据并以字典形式返回。
@@ -211,6 +211,7 @@ class Scraper:
             # 直播页
             elif 'live.douyin' in video_url:
                 # https://live.douyin.com/1000000000000000000
+                video_url = video_url.split('?')[0] if '?' in video_url else video_url
                 key = video_url.replace('https://live.douyin.com/', '')
                 print('获取到的抖音直播ID为: {}'.format(key))
                 return key
@@ -234,14 +235,18 @@ class Scraper:
         print('正在获取抖音视频数据...')
         try:
             # 构造访问链接/Construct the access link
+            """
+            旧API已失效(2022年12月21日)，请大家且用且珍惜。
             api_url = f"https://www.iesdouyin.com/web/api/v2/aweme/iteminfo/?item_ids={video_id}"
+            """
+            api_url = f"https://www.iesdouyin.com/aweme/v1/web/aweme/detail/?aweme_id={video_id}"
             # 访问API/Access API
             print("正在获取视频数据API: {}".format(api_url))
             async with aiohttp.ClientSession() as session:
                 async with session.get(api_url, headers=self.headers, proxy=self.proxies, timeout=10) as response:
                     response = await response.json()
                     # 获取视频数据/Get video data
-                    video_data = response['item_list'][0]
+                    video_data = response['aweme_detail']
                     print('获取视频数据成功！')
                     # print("抖音API返回数据: {}".format(video_data))
                     return video_data
@@ -261,10 +266,9 @@ class Scraper:
             async with aiohttp.ClientSession() as session:
                 async with session.get(api_url, headers=self.douyin_cookies, proxy=self.proxies, timeout=10) as response:
                     response = await response.json()
-                    # 获取返回的json数据/Get the returned json data
-                    data = orjson.loads(response.text)
                     # 获取视频数据/Get video data
-                    video_data = data['data']
+                    video_data = response['data']
+                    print(video_data)
                     print('获取视频数据成功！')
                     # print("抖音API返回数据: {}".format(video_data))
                     return video_data
@@ -382,7 +386,7 @@ class Scraper:
                     'official_api_url':
                         {
                             "User-Agent": self.headers["User-Agent"],
-                            "api_url": f"https://www.iesdouyin.com/web/api/v2/aweme/iteminfo/?item_ids={video_id}"
+                            "api_url": f"https://www.iesdouyin.com/aweme/v1/web/aweme/detail/?aweme_id={video_id}"
                         } if url_platform == 'douyin'
                         else
                         {

web_api.py

@@ -2,8 +2,8 @@
 # -*- encoding: utf-8 -*-
 # @Author: https://github.com/Evil0ctal/
 # @Time: 2021/11/06
-# @Update: 2022/11/09
+# @Update: 2022/12/22
-# @Version: 3.1.0
+# @Version: 3.1.1
 # @Function:
 # 创建一个接受提交参数的FastAPi应用程序。
 # 将scraper.py返回的内容以JSON格式返回。
@@ -369,6 +369,63 @@ async def get_douyin_video_data(request: Request, douyin_video_url: str = None,
             return ORJSONResponse(result)
 
 
+@app.get("/douyin_live_video_data/", response_model=API_Video_Response, tags=["Douyin"])
+@limiter.limit(Rate_Limit)
+async def get_douyin_live_video_data(request: Request, douyin_live_video_url: str = None, web_rid: str = None):
+    if web_rid is None or web_rid == '':
+        # 获取视频ID
+        web_rid = await api.get_douyin_video_id(douyin_live_video_url)
+        if web_rid is None:
+            result = {
+                "status": "failed",
+                "platform": "douyin",
+                "message": "web_rid获取失败/Failed to get web_rid",
+            }
+            return ORJSONResponse(result)
+    if web_rid is not None and web_rid != '':
+        # 开始时间
+        start_time = time.time()
+        print('获取到的web_rid:{}'.format(web_rid))
+        if web_rid is not None:
+            video_data = await api.get_douyin_live_video_data(web_rid=web_rid)
+            if video_data is None:
+                result = {
+                    "status": "failed",
+                    "platform": "douyin",
+                    "endpoint": "/douyin_live_video_data/",
+                    "message": "直播视频API数据获取失败/Failed to get live video API data",
+                }
+                return ORJSONResponse(result)
+            # print('获取到的video_data:{}'.format(video_data))
+            # 记录API调用
+            await api_logs(start_time=start_time,
+                           input_data={'douyin_video_url': douyin_live_video_url, 'web_rid': web_rid},
+                           endpoint='douyin_live_video_data')
+            # 结束时间
+            total_time = float(format(time.time() - start_time, '.4f'))
+            # 返回数据
+            result = {
+                "status": "success",
+                "platform": "douyin",
+                "endpoint": "/douyin_live_video_data/",
+                "message": "获取直播视频数据成功/Got live video data successfully",
+                "total_time": total_time,
+                "aweme_list": [video_data]
+            }
+            return ORJSONResponse(result)
+        else:
+            print('获取抖音video_id失败')
+            result = {
+                "status": "failed",
+                "platform": "douyin",
+                "endpoint": "/douyin_live_video_data/",
+                "message": "获取直播视频ID失败/Failed to get live video ID",
+                "total_time": 0,
+                "aweme_list": []
+            }
+            return ORJSONResponse(result)
+
+
 """ ________________________⬇️TikTok视频解析端点(TikTok video parsing endpoint)⬇️________________________"""