Created
November 29, 2012 14:41
-
-
Save meineerde/4169512 to your computer and use it in GitHub Desktop.
Python Regex to Parse HAProxy's HTTP Logs
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Are quotes escaped? | |
escaped_quotes = True | |
haproxy_re = (r'haproxy\[(?P<pid>\d+)\]: ' | |
r'(?P<client_ip>(\d{1,3}\.){3}\d{1,3}):(?P<client_port>\d{1,5}) ' | |
r'\[(?P<date>\d{2}/\w{3}/\d{4}(:\d{2}){3}\.\d{3})\] ' | |
r'(?P<listener_name>\S+) (?P<server_name>\S+) ' | |
r'(?P<Tq>(-1|\d+))/(?P<Tw>(-1|\d+))/(?P<Tc>(-1|\d+))/(?P<Tr>(-1|\d+))/' | |
r'(?P<Tt>\+?\d+) ' | |
r'(?P<HTTP_return_code>\d{3}) (?P<bytes_read>\d+) ' | |
r'(?P<captured_request_cookie>\S+) (?P<captured_response_cookie>\S+) ' | |
r'(?P<termination_state>[\w-]{4}) (?P<actconn>\d+)/(?P<feconn>\d+)/' | |
r'(?P<beconn>\d+)/(?P<srv_conn>\d+)/(?P<retries>\d+) ' | |
r'(?P<server_queue>\d+)/(?P<listener_queue>\d+) ' | |
r'(\{(?P<captured_request_headers>.*?)\} )?' | |
r'(\{(?P<captured_response_headers>.*?)\} )?') | |
if escape_quotes: | |
haproxy_re += r'\\"(?P<HTTP_request>.+)\\"' | |
else: | |
haproxy_re += r'"(?P<HTTP_request>.+)"' | |
haproxy_re = re.compile(haproxy_re) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
line 18 needs to be escaped_quotes rather than escape_quotes