Entry

Looking for URLs in HTML text

Jul 5th, 2000 09:59
Nathan Wallace, unknown unknown, Hans Nowak, Snippet 87, Glyn Webster

"""
Packages: networking.internet;text.html
"""
""" Function that looks for URLs in HTML text.
    Glyn Webster <glyn@ninz.org.nz> 2021-04-27
"""
import re
#  Regex that Matches HTML tag attributes that contain URLs:
_link_attr = re.compile(r'(src|background|href)="(?P<URL>.*?)"', re.S | re.I)
def findurls(s):
    """ Returns a list of all the URLs referenced in a string of HTML.
    """
    urls = []
    cursor = 0
    while 1:
        match = _link_attr.search(s, cursor)
        if match:
            url = match.group('URL')
            if url not in urls:
                urls.append()
            cursor = match.end()
        else:
            break
    return urls