# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"((?:https?(?:%3A%2F%2F|:\/\/))(?:www\.)?(?:\S+)(?:%2F|\/)(?:(?!\.(?:mp4|mkv|wmv|m4v|mov|avi|flv|webm|flac|mka|m4a|aac|ogg))[^\/])*\.(mp4|mkv|wmv|m4v|mov|avi|flv|webm|flac|mka|m4a|aac|ogg))(?!\/|\.[a-z]{1,3})"
test_str = ("http://test.com/test.mkv\n"
"http://test.com/test/test.jpg.mkv\n"
"https://test.com/test.mkv?test=test\n"
"http%3A%2F%2Ftest.com%2Ftest.mkv%3Ftest%3Dtest\n"
"https%3A%2F%2Ftest.com%2Ftest.jpg.mkv%3Ftest%3Dtest.mkv\n"
"http://test.com/t est.mkv__some__random__string__http://test.com/test.mkv\n"
"The last example should match the two URLs but, not the __some__random__string__.\n\n"
"Some examples that should not be matched:\n\n"
"http://test.com/test.mkv.jpg\n"
"http://test.com/test.mkv/test.jpg\n"
"https://test.com/test.mkv.jpg?test=test.mkv\n"
"http%3A%2F%2Ftest.com%2Ftest.mkv.jpg\n"
"https%3A%2F%2Ftest.com%2Ftest.mkv.jpg%3Ftest%3Dtest.mkv\n"
"http://test.com/t est.mkv__some__random__string__http://test.com/test.mkv.jpg\n"
"The last example should match only the first URL, before __some__random__string__")
matches = re.finditer(regex, test_str, re.IGNORECASE | re.MULTILINE)
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