# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = 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 = re.finditer(regex, test_str)
for matchNum, match in enumerate(matches, start=1):
print ("Match {matchNum} was found at {start}-{end}: {match}".format(matchNum = matchNum, start = match.start(), end = match.end(), match = match.group()))
for groupNum in range(0, len(match.groups())):
groupNum = groupNum + 1
print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = match.start(groupNum), end = match.end(groupNum), group = match.group(groupNum)))
# Note: for Python 2.7 compatibility, use ur"" to prefix the regex and u"" to prefix the test string and substitution.
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