Spaces:
Sleeping
Sleeping
| import pandas as pd | |
| import re | |
| pattern = r"^(?P<Date>\d{1,2}/\d{1,2}/\d{2,4}),\s+(?P<Time>[\d:]+(?:\S*\s?[AP]M)?)\s+-\s+(?:(?P<Sender>.*?):\s+)?(?P<Message>.*)$" | |
| lines = [ | |
| "12/12/23, 10:00 - User1: Hello", | |
| "1/1/23, 1:00 - User2: Hi", | |
| "10/10/2023, 10:00 PM - User3: Test", | |
| "12/12/23, 10:00 - System Message" | |
| ] | |
| df = pd.DataFrame({'line': lines}) | |
| extracted = df['line'].str.extract(pattern) | |
| print("Extracted DataFrame:") | |
| print(extracted) | |
| print("\nRegex Match Check:") | |
| for line in lines: | |
| match = re.match(pattern, line) | |
| print(f"'{line}' -> Match: {bool(match)}") | |
| if match: | |
| print(match.groupdict()) | |