File size: 481 Bytes
42da440 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 | 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
|