import re
regex = re.compile(r"<a[^>]+href=[\"|\'](.*?)[\"|\'][^>]*>((?:.(?!\<\/a\>))*.)<\/a>", flags=re.MULTILINE)
test_str = ("<p>Looking for squeak toys? Check out the <a rel=\"noopener noreferrer\" href=\"https://www.chewy.com/marvel-s-groot-plush-squeaky-dog-toy/dp/247261\" target=\"_blank\" class=\"onecms-affiliate-link\">plush Groot from Marvel's <em>Guardians of the Galaxy</em></a> that's perfect for both play and cuddle time. Cats will surely go wild for the <a rel=\"noopener noreferrer\" href=\"https://www.chewy.com/star-wars-stormtrooper-plush-mice-cat/dp/247537\" target=\"_blank\" class=\"onecms-affiliate-link\">catnip-infused Stormtrooper toys</a>, while dogs that love fetch can <a rel=\"noopener noreferrer\" href=\"https://www.chewy.com/marvel-s-captain-americas-shield/dp/247164\" target=\"_blank\" class=\"onecms-affiliate-link\">chase down Captain America's shield</a>. Those who also want tug toys can grab plush <a rel=\"noopener noreferrer\" href=\"https://www.chewy.com/pixar-aliens-plush-rope-squeaky-dog/dp/247114\" target=\"_blank\" class=\"onecms-affiliate-link\">Pixar's aliens linked on a squeaky rope toy</a>.</p>\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