🎈支持新的抖音链接

scraper.py

@@ -10,9 +10,8 @@
 
 import re
 import json
-import time
 import requests
-from retrying import retry
+from tenacity import *
 
 
 class Scraper:
@@ -34,7 +33,7 @@ class Scraper:
             "User-Agent": "Mozilla/5.0  (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) coc_coc_browser/86.0.170 Chrome/80.0.3987.170 Safari/537.36",
         }
 
-    @retry(stop_max_attempt_number=6)
+    @retry(stop=stop_after_attempt(3), wait=wait_random(min=0.2, max=2))
     def douyin(self, original_url):
         """
         利用官方接口解析抖音链接信息
@@ -45,16 +44,34 @@ class Scraper:
         try:
             # 开始时间
             start = time.time()
+            # 判断是否为个人主页链接
+            if 'user' in original_url:
+                return {'status': 'failed', 'reason': '暂不支持个人主页批量解析', 'function': 'Scraper.douyin()',
+                        'value': original_url}
+            else:
                 # 原视频链接
                 r = requests.get(url=original_url, headers=headers, allow_redirects=False)
                 try:
                     # 2021/12/11 发现抖音做了限制，会自动重定向网址，但是可以从回执头中获取
                     long_url = r.headers['Location']
+                    # 判断是否为个人主页链接
+                    if 'user' in long_url:
+                        return {'status': 'failed', 'reason': '暂不支持个人主页批量解析', 'function': 'Scraper.douyin()',
+                                'value': original_url}
                 except:
                     # 报错后判断为长链接，直接截取视频id
                     long_url = original_url
                 # 正则匹配出视频ID
+                try:
+                    # 第一种链接类型
+                    # https://www.douyin.com/video/7086770907674348841
                     key = re.findall('video/(\d+)?', long_url)[0]
+                    print('视频ID为: {}'.format(key))
+                except Exception:
+                    # 第二种链接类型
+                    # https://www.douyin.com/discover?modal_id=7086770907674348841
+                    key = re.findall('modal_id=(\d+)', long_url)[0]
+                    print('视频ID为: {}'.format(key))
                 # 构造抖音API链接
                 api_url = f'https://www.iesdouyin.com/web/api/v2/aweme/iteminfo/?item_ids={key}'
                 print("正在请求抖音API链接: " + '\n' + api_url)
@@ -168,7 +185,8 @@ class Scraper:
                     # 有水印视频链接
                     wm_video_url = str(js['item_list'][0]['video']['play_addr']['url_list'][0])
                     # 无水印视频链接 (在回执JSON中将关键字'playwm'替换为'play'即可获得无水印地址)
-                nwm_video_url = str(js['item_list'][0]['video']['play_addr']['url_list'][0]).replace('playwm', 'play')
+                    nwm_video_url = str(js['item_list'][0]['video']['play_addr']['url_list'][0]).replace('playwm',
+                                                                                                         'play')
                     # 去水印后视频链接(2022年1月1日抖音APi获取到的URL会进行跳转，需要在Location中获取直链)
                     r = requests.get(url=nwm_video_url, headers=headers, allow_redirects=False)
                     video_url = r.headers['Location']
@@ -251,7 +269,7 @@ class Scraper:
             # 返回异常
             return {'status': 'failed', 'reason': e, 'function': 'Scraper.douyin()', 'value': original_url}
 
-    @retry(stop_max_attempt_number=6)
+    @retry(stop=stop_after_attempt(3), wait=wait_random(min=0.2, max=2))
     def tiktok(self, original_url):
         """
         解析TikTok链接