add video_url

zhufushenghuo/zhufushenghuo_main/run_zfsh_recommend_dev.py

@@ -10,7 +10,7 @@ from common.common import Common
 
 
 def kanyikan_main(log_type, crawler, env):
-    Common.logger(log_type, crawler).info(f'开始抓取:看一看推荐\n')
+    Common.logger(log_type, crawler).info(f'开始抓取祝福生活:\n')
     ZfshRecommend.get_videoList(log_type=log_type,
                                     crawler=crawler,
                                     rule_dict={},

zhufushenghuo/zhufushenghuo_recommend/zfsh_recommend.py

@@ -10,11 +10,52 @@ from common.mq import MQ
 from common.public import download_rule, get_config_from_mysql
 
 proxies = {"http": None, "https": None}
-
+headers = {
+            'Host': 'mini.vvuiiu.cn',
+            'accept': '*/*',
+            'content-type': 'application/json',
+            'accept-language': 'zh-cn',
+            'user-agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 11_3 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Mobile/15E217 MicroMessenger/6.8.0(0x16080000) NetType/WIFI Language/en Branch/Br_trunk MiniProgramEnv/Mac',
+            'referer': 'https://servicewechat.com/wxa903dc775e85eb5b/11/page-frame.html'
+        }
 
 class ZfshRecommend:
     platform = ("祝福生活视频")
 
+    @classmethod
+    def get_video_url(cls, id, uuid1, log_type, crawler, env):
+        try:
+            url = "https://mini.vvuiiu.cn/article/detail"
+
+            payload = json.dumps({
+                "id": id,
+                "uuid": uuid1,
+                "platform": 35,
+                "appid": "wxa903dc775e85eb5b"
+            })
+            r = requests.post(url=url, headers=headers, data=payload, proxies=proxies, verify=False)
+            if "data" not in r.text or r.status_code != 200:
+                Common.logger(log_type, crawler).warning(f"get_videoList:{r.text}\n")
+                Common.logging(log_type, crawler, env, f"get_videoList:{r.text}\n")
+                return
+            elif "data" not in r.json():
+                Common.logger(log_type, crawler).info(f"get_videoList:{r.json()}\n")
+                Common.logging(log_type, crawler, env, f"get_videoList:{r.json()}\n")
+                return
+            elif len(r.json()["data"]) == 0:
+                Common.logger(log_type, crawler).warning(f"get_videoList:{r.json()['data']['list']}\n")
+                Common.logging(log_type, crawler, env, f"get_videoList:{r.json()['data']['list']}\n")
+                return
+            else:
+                # 获取视频url
+                video_url = r.json()["data"].get("video_url")
+                return video_url
+        except Exception as e:
+            Common.logger(log_type, crawler).error(f" 获取视频链接异常:{e}\n")
+            Common.logging(log_type, crawler, env, f"获取视频链接异常:{e}\n")
+
+
+
     @classmethod
     def repeat_video(cls, log_type, crawler, video_id, env):
         sql = f""" select * from crawler_video where platform in ("{crawler}","{cls.platform}") and create_time>='2023-06-26' and out_video_id="{video_id}"; """
@@ -25,7 +66,7 @@ class ZfshRecommend:
     def get_videoList(cls, log_type, crawler, our_uid, rule_dict, env):
         mq = MQ(topic_name="topic_crawler_etl_" + env)
         uuid1 = str(uuid.uuid1())
-        for page in range(1, 100):
+        for page in range(1, 6):
             try:
                 Common.logger(log_type, crawler).info(f"正在抓取第{page}页")
                 Common.logging(log_type, crawler, env, f"正在抓取第{page}页")
@@ -40,14 +81,7 @@ class ZfshRecommend:
                     "platform": 35,
                     "appid": "wxa903dc775e85eb5b"
                 })
-                headers = {
-                    'Host': 'mini.vvuiiu.cn',
-                    'accept': '*/*',
-                    'content-type': 'application/json',
-                    'accept-language': 'zh-cn',
-                    'user-agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 11_3 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Mobile/15E217 MicroMessenger/6.8.0(0x16080000) NetType/WIFI Language/en Branch/Br_trunk MiniProgramEnv/Mac',
-                    'referer': 'https://servicewechat.com/wxa903dc775e85eb5b/11/page-frame.html'
-                }
+
                 r = requests.post(url=url, headers=headers, data=payload, proxies=proxies, verify=False)
 
                 if "data" not in r.text or r.status_code != 200:
@@ -80,6 +114,9 @@ class ZfshRecommend:
                                 .replace("'", "").replace("#", "").replace("Merge", "")
                             publish_time_stamp = int(feeds[i].get("article_id", 0))
                             publish_time_str = time.strftime("%Y/%m/%d %H:%M:%S", time.localtime(publish_time_stamp))
+                            id = feeds[i]["id"]
+                            # 获取视频链接
+                            video_url = cls.get_video_url(id, uuid1, log_type, crawler, env)
                             video_dict = {
                                 "video_title": video_title,
                                 "video_id": feeds[i]["id"],  # 视频id
@@ -88,7 +125,7 @@ class ZfshRecommend:
                                 "is_video": int(feeds[i].get("is_video", 0)),  # 类型
                                 "category_id": int(feeds[i].get("category_id", 0)),  # 视频来源（精彩推荐）
                                 "image_path": feeds[i].get("image_path", ""),  # 视频封面
-                                "video_url": feeds[i].get("video_url", ""),  # 视频链接
+                                "video_url": video_url,  # 视频链接
                                 "click": int(feeds[i].get("click", 0)),  # 点击数
                                 "video_width": int(feeds[i].get("vw", 0)),
                                 "video_height": int(feeds[i].get("vh", 0)),