# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"<p>(\s*)(<a(.*)>)?(\s*)(https?:\/\/)?(w{3}\.)?(youtube\.com|youtu\.be)\/(watch\?v=|embed\/)?([A-Za-z0-9-_]{11})(\S*)(\s*)(<\/a>)?(\s*)<\/p>"
test_str = ("No protocol:\n\n"
"<p>youtube.com/watch?v=dQw4w9WgXcQ</p>\n"
"<p>www.youtube.com/watch?v=dQw4w9WgXcQ</p>\n\n"
"HTTP or HTTPS:\n\n"
"<p>http://youtube.com/watch?v=dQw4w9WgXcQ</p>\n"
"<p>http://www.youtube.com/watch?v=dQw4w9WgXcQ</p>\n"
"<p>https://youtube.com/watch?v=dQw4w9WgXcQ</p>\n"
"<p>https://www.youtube.com/watch?v=dQw4w9WgXcQ</p>\n\n"
"With or without “www”\n\n"
"<p>https://youtube.com/watch?v=dQw4w9WgXcQ</p>\n"
"<p>https://www.youtube.com/watch?v=dQw4w9WgXcQ</p>\n\n"
"Youtu.be short links\n"
"<p>youtu.be/LQaehcfXvK0</p>\n"
"<p>https://youtu.be/LQaehcfXvK0</p>\n\n"
"Embed Urls:\n"
"<p>http://www.youtube.com/embed/dQw4w9WgXcQ</p>\n\n"
"URLs with extra parameters:\n"
"<p>https://www.youtube.com/watch?v=LQaehcfXvK0&feature=youtu.be</p>\n"
"<p>https://www.youtube.com/watch?v=dQw4w9WgXcQ&list=RDdQw4w9WgXcQ&start_radio=1&t=1</p>\n\n"
"This URL won’t actually work on YouTube, but it works here, which is somewhat odd? And yet doesn't seem harmful.\n"
"<p>youtu.be/embed/dQw4w9WgXcQ</p>\n\n"
"Paragraph tags on separate lines with arbitrary whitespace:\n\n"
"<p>\n"
" www.youtube.com/embed/u8pCsfT1gDU\n"
"</p>\n\n"
"<p>\n"
" https://youtube.com/watch?v=dQw4w9WgXcQ\n"
"</p>\n"
"<p>\n"
" http://www.youtube.com/embed/dQw4w9WgXcQ\n"
"</p>\n\n"
" <p>\n"
" youtube.com/watch?v=dQw4w9WgXcQ\n\n"
"</p>\n\n"
"Paragraph tags with any other text in them, besides the URL:\n\n"
"<p>This shouldn’t work: https://youtube.com/watch?v=dQw4w9WgXcQ</p>\n"
"<p>https://youtube.com/watch?v=dQw4w9WgXcQ nor this</p>\n"
"<p>\n"
"https://youtube.com/watch?v=dQw4w9WgXcQ also not this\n\n"
"</p>\n\n\n"
"Paragraph tags with links added by markdown-it:\n\n"
"<p><a href=\"https://www.youtube.com/watch?v=dQw4w9WgXcQ\">https://www.youtube.com/watch?v=dQw4w9WgXcQ</a></p>\n\n"
"<p>\n"
" <a href=\"https://www.youtube.com/watch?v=dQw4w9WgXcQ?something\" class=\"something\" id=\"whatever\">\n"
" youtube.com/watch?v=dQw4w9WgXcQ?foo=bar&whatever\n\n"
" </a>\n"
"</p>\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