修改快代理

deal/matchArticle_deal.py

@@ -75,15 +75,18 @@ class MatchArticlesTask(object):
         async def find_material(task_tuple, mysql_client):
             task_id, title, text = task_tuple
             # 先用视频标题作为query， 后续可逐步优化
-            question_dict = question_fission(title)
-            material_dict = {}
-            for question_key in question_dict:
-                question = question_dict[question_key]
-                material = generate_text(question)
-                cleand_question = question.replace("\n", "").replace("*", "").replace("#", "").replace(":", "").replace('"', "").replace("'", "")
-                material_dict[cleand_question] = material
+            try:
+                question_dict = question_fission(title)
+                material_dict = {}
+                for question_key in question_dict:
+                    question = question_dict[question_key]
+                    material = generate_text(question)
+                    cleand_question = question.replace("\n", "").replace("*", "").replace("#", "").replace(":", "").replace('"', "").replace("'", "")
+                    material_dict[cleand_question] = material
 
-            material_result = json.dumps(material_dict, ensure_ascii=False)
+                material_result = json.dumps(material_dict, ensure_ascii=False)
+            except:
+                material_result=json.dumps({title: text}, ensure_ascii=False)
             update_sql = f"""
             UPDATE {db_config}
             SET materials = %s, status_code = %s
@@ -105,7 +108,10 @@ class MatchArticlesTask(object):
 
         async def ai_generate_text(task_tuple, mysql_client):
             task_id, video_title, materials = task_tuple
-            ai_title, ai_text = summary_articles(materials)
+            try:
+                ai_title, ai_text = summary_articles(materials)
+            except:
+                ai_title, ai_text = video_title, "文章生成失败"
             imgs = get_img_list(video_title)
             update_sql = f"""
             UPDATE {db_config}

spider/baidu_imgs.py

@@ -10,10 +10,11 @@ def tunnel_proxies():
     :return:
     """
     # 隧道域名:端口号
-    tunnel = "q796.kdltps.com:15818"
+    tunnel = "l901.kdltps.com:15818"
+
     # 用户名密码方式
-    username = "t17772369458618"
-    password = "5zqcjkmy"
+    username = "t11983523373311"
+    password = "mtuhdr2z"
     proxies = {
         "http": "http://%(user)s:%(pwd)s@%(proxy)s/" % {"user": username, "pwd": password, "proxy": tunnel},
         "https": "http://%(user)s:%(pwd)s@%(proxy)s/" % {"user": username, "pwd": password, "proxy": tunnel}
@@ -48,7 +49,7 @@ def get_img_list(search_title):
         'sec-fetch-site': 'same-origin',
         'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36'
     }
-    response = requests.request("GET", url, headers=headers, params=params, proxies=tunnel_proxies())
+    response = requests.request("GET", url, headers=headers, params=params)
     res = response.json()
     response = [i['ori'].replace("'", "") for i in res[:15]]
-    return response
+    return response

va_task.py

@@ -85,4 +85,4 @@ if __name__ == '__main__':
     while True:
         asyncio.run(main())
         print("执行完成，等待120s")
-        time.sleep(120)
+        # time.sleep(120)