linkify_it_py_url_detection_and_match_extraction.py

1from linkify_it import LinkifyIt
2
3linkify = LinkifyIt()
4
5# Check if a link is valid
6print(linkify.test('google.com'))  # True
7
8# Get matches from text
9text = 'Site google.com, email admin@google.com'
10matches = linkify.match(text)
11
12if matches:
13    for match in matches:
14        print(f"URL: {match.url}")      # Full URL
15        print(f"Schema: {match.schema}") # http:, mailto:, etc.
16        print(f"Index: {match.index}")   # Offset in string
17        print(f"Text: {match.text}")     # Text matched