修改【main.py】，增加【saveData.py】，将数据存储模块与调度模块分离

 from spiderContent import start as spiderContentStart
 from spiderComments import start as spiderCommentsStart
-import os
-from sqlalchemy import create_engine
-import pandas as pd
-
-engine = create_engine('mysql+pymysql://XiaoXueQi:XiaoXueQi@10.92.35.13/Weibo_PublicOpinion_AnalysisSystem?charset=utf8mb4')
-
-def save_to_sql():
-    try:
-        artileOldPd = pd.read_sql('select * from article',engine)
-        articleNewPd = pd.read_csv('articleData.csv')
-        commentOldPd = pd.read_sql('select * from comments',engine)
-        commentNewPd = pd.read_csv('articleComments.csv')
-
-        concatArticlePd = pd.concat([articleNewPd,artileOldPd],join='inner')
-        concatCommentsPd = pd.concat([commentNewPd,commentOldPd],join='inner')
-
-        concatArticlePd.drop_duplicates(subset='id',keep='last',inplace=True)
-        concatCommentsPd.drop_duplicates(subset='content',keep='last',inplace=True)
-
-        concatArticlePd.to_sql('article', con=engine, if_exists='replace', index=False)
-        concatCommentsPd.to_sql('comments', con=engine, if_exists='replace', index=False)
-    except:
-        articleNewPd = pd.read_csv('articleData.csv')
-        commentNewPd = pd.read_csv('articleComments.csv')
-        articleNewPd.to_sql('article',con=engine,if_exists='replace',index=False)
-        commentNewPd.to_sql('comments',con=engine,if_exists='replace',index=False)
-
-    os.remove('./articleData.csv')
-    os.remove('./articleComments.csv')
+from saveData import save_to_sql as saveData
 
 def main():
     print('正在爬取文章数据')
@@ -36,8 +8,7 @@ def main():
     print('正在爬取文章评论数据')
     spiderCommentsStart()
     print('正在存储数据')
-    save_to_sql()
-
+    saveData()
 
 if __name__ == '__main__':
     main()
\ No newline at end of file

+import os
+from sqlalchemy import create_engine
+import pandas as pd
+
+engine = create_engine('mysql+pymysql://XiaoXueQi:XiaoXueQi@10.92.35.13/Weibo_PublicOpinion_AnalysisSystem?charset=utf8mb4')
+
+def save_to_sql():
+    try:
+        artileOldPd = pd.read_sql('select * from article',engine)
+        articleNewPd = pd.read_csv('articleData.csv')
+        commentOldPd = pd.read_sql('select * from comments',engine)
+        commentNewPd = pd.read_csv('articleComments.csv')
+
+        concatArticlePd = pd.concat([articleNewPd,artileOldPd],join='inner')
+        concatCommentsPd = pd.concat([commentNewPd,commentOldPd],join='inner')
+
+        concatArticlePd.drop_duplicates(subset='id',keep='last',inplace=True)
+        concatCommentsPd.drop_duplicates(subset='content',keep='last',inplace=True)
+
+        concatArticlePd.to_sql('article', con=engine, if_exists='replace', index=False)
+        concatCommentsPd.to_sql('comments', con=engine, if_exists='replace', index=False)
+    except:
+        articleNewPd = pd.read_csv('articleData.csv')
+        commentNewPd = pd.read_csv('articleComments.csv')
+        articleNewPd.to_sql('article',con=engine,if_exists='replace',index=False)
+        commentNewPd.to_sql('comments',con=engine,if_exists='replace',index=False)
+
+    os.remove('./articleData.csv')
+    os.remove('./articleComments.csv')
+
+if __name__ == '__main__':
+    save_to_sql()
\ No newline at end of file