import re
regex = re.compile(r"\s([a-zA-Z]+://)*(\b([a-zA-Z][\w-]*\.){1,3}[a-zA-Z0-9]+|(\b((2[0-4]\d|25[0-5]|1\d\d|0\d\d|0\d|\d\d|\d)\.){3}(2[0-4]\d|25[0-5]|1\d\d|0\d\d|0\d|\d\d|\d)\b))(:\d+)*([\\\!\"\#\$\%\&\'\(\)\*\+\-\/\:\;\<\=\>\?\@\[\]\^\`\{\|\}\~\.\w])*(\,.+\.[a-z]+)*")
test_str = ("they all call home to 194.68.59.34:2018, 192[.]168[.]1[.]1\n\n"
"hxxp://securedownload2.duckdns.org:7373/docs/ @JAMESWT_MHT\n"
"abc://www.hhghg.ghgh.jkjkjk.jkjkj.jkjk\n"
"#LokiBot @ hxxp://xupfile.duckdns.org:1133/$59,200.exe \n"
"https://www.reverse.it/sam\\ple/529b10d3faaa143c074d0f25ee75c8e9bad7f5982ead482d6c0c19a39d207b68?environmentId=100 …\n"
"255.2.3.4\n"
"194.68.59.34:2018,\n"
"www.virustotal.com\n"
"C2: hta.duckdns.org:7373/excel/fre.php\n"
"http://www.virustotal.com/en/file/a94f7db23f64985f22a4250886db0d67e3cc1fbf59ef3d1bf9ffd28d3357d3f7/analysis/1511168707/ …\n"
"dasdasd hxxp://172.106.75.131/temp/amazingdoz.exe\n"
"dasdasd hxxp://172.1d06.75.131/temp/amazingdoz.exe\n"
"https://www.virustotal.com/#/url/2512afa822b8cadbe9e2fa0ecda5ad55d6024b0694fecf265282a63ef88058cf/detection …\n"
"hxxp://www.dk-fyn.dk/ebgate/ri.php\n"
"hxxp://www.fourthtour.it/rus/tour/php.scr\n"
"hxxp://www.foxydance.cz/repository/ri.php\n"
"hxxp://www.sabineclaire.com/girasoli/ri.php,1212 sdfsdfsdsdfsdf\n"
"https://www.reverse.it/sample/b57bd0dec0873bea8e47a16e1da41aafa817ae11d536c90cb7aec6d6686b686e?environmentId=100 …\n"
"hxxp://www.sabineclaire.com/girasoli/ri.php\n"
"sdf.bom\n"
"fasdkj adsflk jasldk fjalskd fjslaskjdf lkaj dsfl\n"
"So, I've got a matching set of Trojan.Nymeria samples\n"
"https://www.virustotal.com/en/file/0e6ac6a1db6fdeb8d85edfdd9f33761b2877ae46399f30dee7335e1783ef53c9/analysis/ … …\n"
"https://www.virustotal.com/en/file/9178e59b6e2227cccf137f5b3c259035d3750f2dfc3314f9e326fb0995a2862c/analysis/ … …\n"
"https://www.virustotal.com/en/file/0eae5dd0655ca17db3c6b6c7fb921405d82533bb619b12de010b449de1322efd/analysis/ … …\n"
"https://www.virustotal.com/en/file/394af1f36a36b631cfa48158314dc378c8dba5307f79d86d7262aaa86a694089/analysis/ … …\n"
"they all call home to 194.68.59.34:2018")
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