import re
regex = re.compile(r"<a href=\"http.?:.*(youtube.com|.*be\/|.*embed\/|watch?. v=|(\w{11})).?<\/a>")
test_str = ("the following URL will be found in a <A>:<br>\n"
"<em>\n"
"<a href=\"https://www.youtube.com/watch?t=61&v=JozAmXo2bDE\" rel=\"nofollow\">https://www.youtube.com/watch?t=61&v=JozAmXo2bDE</a>\n"
"<br>\n\n"
"<a href=\"https://soundcloud.com/buzzdeny/sets/deutsch-er-hiphop-rap\" rel=\"nofollow\">https://soundcloud.com/buzzdeny/sets/deutsch-er-hiphop-rap</a>\n\n\n"
"<a href=\"https://www.youtube.com/watch?v=VH2QAMMSL40\" rel=\"nofollow\">https://www.youtube.com/watch?v=VH2QAMMSL40</a>\n\n"
"<br>\n\n"
"<a href=\"http://www.youtube.com/embed/NLqAF9hrVbY\" rel=\"nofollow\">http://www.youtube.com/embed/NLqAF9hrVbY</a>\n\n"
"<br>\n\n"
"<a href=\"http://youtu.be/NLqAF9hrVbY\" rel=\"nofollow\">http://youtu.be/NLqAF9hrVbY</a>\n\n"
"</em>\n"
"<br>\n\n"
"<a href=\"http://www.youtube.com/sandalsResorts#p/c/54B8C800269D7C1B/0/FJUvudQsKCM\" rel=\"nofollow\">http://www.youtube.com/sandalsResorts#p/c/54B8C800269D7C1B/0/FJUvudQsKCM</a>\n\n"
"</p>\n\n"
"<a href=\"/uploads/files/1438381231924-humanistische-friedenspartei.mp3\">Humanistische - Friedenspartei.mp3</a>\n\n"
"<p>nice... <a href=\"/uploads/files/1438418374790-drumloop053_ambnt_160_x_sc5.wav\">DRUMLOOP053_AMBNT_160_X_SC5.wav</a></p>\n\n"
"<a href=\"/uploads/files/1438418374790-drumloop053_ambnt_160_x_sc5.wav\">DRUMLOOP053_AMBNT_160_X_SC5.wav</a>\n\n"
"<p>infos:<br>\n\n"
"<a href=\"https://github.com/ogerly/nodebb-plugin-youtube-lite/blob/master/library.js\" rel=\"nofollow\">https://github.com/ogerly/nodebb-plugin-youtube-lite/blob/master/library.js</a>\n"
"</p>\n"
"<p><a href=\"https://github.com/ogerly/nodebb-plugin-youtube-lite\" rel=\"nofollow\">https://github.com/ogerly/nodebb-plugin-youtube-lite</a></p>\n\n"
" \n"
"</div>")
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