Question

How to extract a substring between two tags using RegEx in Python

Answer 1

import re

def extract_content_between_tags(string, tag_name):
    # Build a regex pattern using the specified tag name
    pattern = rf"<{tag_name}>(.*?)</{tag_name}>"

    # Use re.search to find the content between the tags
    match = re.search(pattern, string)

    if match:
        # Return the content inside the tags
        return match.group(1)

    # Return an empty string if no match is found
    return ""

string = "abcd <tag>efg hijk lmnop</tag> qrst uvwxyz"

# Call the function to extract the substring
content = extract_content_between_tags(string, "tag")

if content:
    print(f"Extracted content: {content}")
else:
    print("No matching tags found.")


 
'''
run:

Extracted content: efg hijk lmnop
  
'''

 

Learn SQL from A to Z at LearnSQL.com