| import re | |
| def extract_first_words(character_name, text): | |
| # Regular expression pattern to extract first word after the character's name | |
| pattern = rf"{character_name}: \"(\w+)" | |
| # Find all matches in the text | |
| matches = re.findall(pattern, text) | |
| return matches | |
| def remove_think_tags(text): | |
| # Use regex to remove anything between <think> and </think> tags | |
| cleaned_text = re.sub(r"<think>.*?</think>", "", text, flags=re.DOTALL) | |
| return cleaned_text | |