# coding=utf8
# the above tag defines encoding for this document and is for Python 2.x compatibility
import re
regex = r"(?P<bucket_owner>[0-9a-z]{64})\s(?P<bucket>[^\s]+)\s\[(?P<times>[^\]]+)\]\s(?P<remote_ip>[^\s]+)\s(?P<requester>[^\s]+)\s(?P<request_id>[^\s]+)\s(?P<operation>[^\s]+)\s(?P<key>[^\s]+)\s\"(?P<request_uri>.*?)\"\s(?P<http_status>[^\s]+)\s(?P<error_code>[^\s]+)\s(?P<bytes_sent>[^\s]+)\s(?P<object_size>[^\s]+)\s(?P<total_time>[^\s]+)\s(?P<turen_around_time>[^\s]+)\s\"(?P<Referer>[^\"]+)\"\s\"(?P<user_agent>.*?)\"\s(?P<version_id>[^\s]+)\s(?P<host_id>[^\s]+)\s(?P<sig_version>[^\s]+)\s(?P<cypher_id>[^\s]+)\s(?P<auth_type>[^\s]+)\s(?P<host_heaser>[^\s]+)\s(?P<tls_version>[^\s]+)"
test_str = ("1234567890abcdefb6dbc56f666f90007236c16e851616eb11dfffffffffffff amir-blog-logs [15/Jan/2020:18:54:55 +0000] 154.40.7.1 arn:aws:iam::111:user/awslogsdelivery+s3_eu-west-1 237122D309CCCCCC REST.PUT.OBJECT AWSLogs/597078111111/vpcflowlogs/eu-west-1/2020/01/15/123456789012_vpcflowlogs_eu-west-1_fl-083687d6894d7105c_20200115T1850Z_2c454915.log.gz \"PUT /AWSLogs/111/vpcflowlogs/eu-west-1/2020/01/15/000_vpcflowlogs_eu-west-1_fl-083687d6894d7105c_20200000T1850Z_2c454915.log.gz HTTP/1.1\" 200 - - 14654 251 35 \"-\" \"aws-internal/3 aws-sdk-java/1.11.690 Linux/4.9.184-0.1.ac.2.8.329.metal1.x86_64 OpenJDK_64-Bit_Server_VM/25.232-b09 java/1.8.0_232 vendor/Oracle_Corporation\" - 9LaQV8A4UxoNv8xv4kkdZNF+IJ9uBYP/GACxBYO12345678900987654321/37e6Iw= SigV4 ECDHE-RSA-AES128-SHA AuthHeader amir-blog-logs.s3.us-east-2.amazonaws.com TLSv1.2\n\n"
"1234567890abcdefb6dbc56f666f90007230000e851616eb11dfffffffffffff amir-blog-logs [27/Apr-last\":\"2020:17:38:46 +0000] 154.40.7.1 arn:aws:sts::123456789001:assumed-role/S3ReadOnly/S3Coralogix AA8B4A2DECEC091E REST.GET.OBJECT AWSLogs-last\":\"123456789001/vpcflowlogs/eu-west-1-last\":\"2020-last\":\"04-last\":\"27-last\":\"123456789001_vpcflowlogs_eu-west-1_fl-083687d6123105c_202T1725Z_ef8cb23d.log.gz \"GET /AWSLogs-last\":\"123456789001/vpcflowlogs/eu-west-1-last\":\"2020-last\":\"04-last\":\"27-last\":\"123456789001_vpcflowlogs_eu-west-1_fl-083687d6894d7105c_1234567890015Z_ef23d.log.gz HTTP-last\":\"1.1\" 200 - 1340 1340 55 54 \"-\" \"aws-sdk-nodejs-last\":\"2.188.0 linux/v10.19.0 exec-env/AWS_Lambda_nodejs10.x callback\" - LEmyJtO7loyY36UWTsCEDy/JjMezg3r9Q8ABCD+LZz4RBHwneZ9Ag1K/T/d/d9/ZrI8C0= SigV4 ECDHE-RSA-AES128-GCM-SHA256 AuthHeader amir-blog-logs.s3.us-east-2.amazonaws.com TLSv1.2")
matches = re.finditer(regex, test_str, 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