import re
regex = re.compile(r"(https?:\/\/[-|\w\.|\/]+)")
test_str = (" <div class=\"col-sm-8\"><p>TLX is a Flat-Face twist lock coupling for the toughest applications in the construction and demolition segment. This super-duty quick connect coupling is designed to work with the highest surge flows and the toughest pressure impulses. TLX is made from high alloy steels with Zinc-Nickel surface treatment for a long life in the harshest conditions. The Series is available in sizes from ½” to 1 ½” to cover most applications.</p><br /><p>- The couplings and nipples are also available in 4 other sizes: ¾” (Series 607) 1” (Series 707) 1 ¼” (Series 807) and 1 ½ ” (Series 907) https://www.cejn.com/globalassets/documents/brochures/tlx-en.pdf</p></div>\n\n"
" <div class=\"col-sm-4\">\n"
" <img src=\"/globalassets/product/cejn/series-507/group/series-507-tlx-group-cejn.jpg?w=275\" rel=\"lightbox\" alt=\"Series 507 - ½”\" class=\"cboxElement\" />\n"
" </div>\n")
matches = regex.finditer(test_str)
for match_num, match in enumerate(matches, start=1):
print(f"Match {match_num} was found at {match.start()}-{match.end()}: {match.group()}")
for group_num, group in enumerate(match.groups(), start=1):
print(f"Group {group_num} found at {match.start(group_num)}-{match.end(group_num)}: {group}")
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Python, please visit: https://docs.python.org/3/library/re.html