config.py

@@ -225,9 +225,9 @@ TWITTER_CONFIG = {
     "user_search_url": "https://api.twitter.com/2/users/by/username/{0}",
     "contents_search_url": "https://api.twitter.com/2/users/{0}/tweets?max_results=100&tweet.fields=text,created_at&exclude=replies,retweets",
     "monitor_accounts": [
-        {"name": "FoxNews", "id": ""},
-        {"name": "WhiteHouse", "id": "1879644163769335808"},
-        {"name": "sama", "id": ""},
-        {"name": "PressSec", "id": ""},
+        "FoxNews",
+        "WhiteHouse",
+        "sama",
+        "PressSec",
     ],
 }

core/twitter/twitter_retriever.py

@@ -12,11 +12,6 @@ import pandas as pd
 logger = logging.logger
 
 class TwitterRetriever:
-    """
-    免费版本的账号，每个月只能获取100条推文，
-    需要使用付费版本的账号，基础版每个月可以获取15000条推文,200美元/月
-    高级版每个月可以获取1000000条推文,5000美元/月
-    """
     def __init__(self):
         self.keys = TWITTER_CONFIG["keys"]
         self.headers = {
@@ -58,19 +53,17 @@ class TwitterRetriever:
             return None
     
     def monitor_accounts(self):
-        for account_dict in self.monitor_account_list:
-            user_name = account_dict["name"]
-            user_id = account_dict["id"]
-            logger.info(f"Monitoring account: {user_name}")
+        for account in self.monitor_account_list:
+            logger.info(f"Monitoring account: {account}")
             logger.info(f"Sleeping for {self.sleep_time} seconds")
-            # time.sleep(self.sleep_time)
+            time.sleep(self.sleep_time)
             result_list = []
-            if user_id is None or user_id == "":
-                user = self.search_user(user_name)
-                if user is None:
-                    continue
-                user_id = str(user["data"]["id"])
-            contents = self.search_contents(user_name, user_id)
+            user = self.search_user(account)
+            if user is None:
+                continue
+            username = user["data"]["username"]
+            user_id = str(user["data"]["id"])
+            contents = self.search_contents(username, user_id)
             if contents is None:
                 continue
             twitter_contents = contents["data"]
@@ -82,7 +75,7 @@ class TwitterRetriever:
                 text = content["text"]
                 result = {
                     "user_id": user_id,
-                    "user_name": user_name,
+                    "user_name": username,
                     "timestamp": timestamp_ms,
                     "date_time": beijing_time_str,
                     "text": text
@@ -93,7 +86,7 @@ class TwitterRetriever:
                 self.db_twitter_content.insert_data_to_mysql(result_df)
                 logger.info(f"Inserted {len(result_df)} rows into twitter_content")
             else:
-                logger.warning(f"No data inserted for account: {user_name}")
+                logger.warning(f"No data inserted for account: {account}")
     
     def transform_datetime(self, datetime_text: str):
         utc_time = datetime.strptime(datetime_text, "%Y-%m-%dT%H:%M:%S.%fZ").replace(tzinfo=pytz.UTC)