Update app.py

app.py

@@ -6,6 +6,7 @@ import plotly
 import plotly.express as px
 import json # for graph plotting in website
 # NLTK VADER for sentiment analysis
+from dateutil import parser
 import nltk
 nltk.downloader.download('vader_lexicon')
 from nltk.sentiment.vader import SentimentIntensityAnalyzer
@@ -29,40 +30,41 @@ def get_news(ticker):
     return news_table
 	
 # parse news into dataframe
+
+
 def parse_news(news_table):
     parsed_news = []
-    today_string = datetime.datetime.today().strftime('%Y-%m-%d')
     
     for x in news_table.findAll('tr'):
         try:
-            # read the text from each tr tag into text
-            # get text from a only
-            text = x.a.get_text() 
-            # splite text in the td tag into a list 
-            date_scrape = x.td.text.split()
-            # if the length of 'date_scrape' is 1, load 'time' as the only element
-
+            # Get the headline text
+            text = x.a.get_text()
+            # Get the date and time from the first <td> tag
+            date_scrape = x.td.text.strip().split()
+            
+            # Handle cases where only time is present
             if len(date_scrape) == 1:
+                date = datetime.datetime.today().strftime('%Y-%m-%d')
                 time = date_scrape[0]
-                
-            # else load 'date' as the 1st element and 'time' as the second    
             else:
                 date = date_scrape[0]
                 time = date_scrape[1]
+
+            # Parse the date and time using dateutil.parser
+            datetime_str = f"{date} {time}"
+            datetime_parsed = parser.parse(datetime_str)
+
+            # Append the parsed news to the list
+            parsed_news.append([datetime_parsed, text])
             
-            # Append ticker, date, time and headline as a list to the 'parsed_news' list
-            parsed_news.append([date, time, text]) 
-        except:
-            pass
-        
-        # Set column names
-        columns = ['date', 'time', 'headline']
-        # Convert the parsed_news list into a DataFrame called 'parsed_and_scored_news'
-        parsed_news_df = pd.DataFrame(parsed_news, columns=columns)        
-        # Create a pandas datetime object from the strings in 'date' and 'time' column
-        parsed_news_df['date'] = parsed_news_df['date'].replace("Today", today_string)
-        parsed_news_df['datetime'] = pd.to_datetime(parsed_news_df['date'] + ' ' + parsed_news_df['time'])
-        
+        except Exception as e:
+            print("Error parsing news:", e)
+            continue
+    
+    # Convert the list to a DataFrame
+    columns = ['datetime', 'headline']
+    parsed_news_df = pd.DataFrame(parsed_news, columns=columns)
+    
     return parsed_news_df