File size: 668 Bytes
42da440 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 | import re
def extract_steps(text, steps=[2, 4, 5]):
"""
Extracts the specified steps from the text.
Args:
text (str): The input text containing various steps.
steps (list of int): The step numbers to extract.
Returns:
str: A new string with each specified step's content on its own line.
"""
step_pattern = "|".join([f"Step {step}\." for step in steps])
matches = re.findall(
f"({step_pattern})\s*(.*?)\s*(?=(Step \d\.|$))", text, re.DOTALL
)
# Extract and join the matched content, skipping the "Step n." part
extracted_text = "\n".join(match[1].strip() for match in matches)
return extracted_text
|