Loggly CLI interface - standalone (Just Python). Pages results automatically so you can easily grab >2000 rows.

loggly.py

#!/usr/bin/env python

"""
Loggly CLI interface - standalone (Just Python). Deals with paging results automatically so you can easily grab >2000 rows.

Run `loggly.py --help` to see usage information.

TODO: 
* Support XML format results (ie. combining multiple pages of results together)
* Facet support

Rob Coup - @amatix - [email protected]

-------

Copyright (c) 2012, Robert Coup
All rights reserved.

Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:

1. Redistributions of source code must retain the above copyright notice, this
   list of conditions and the following disclaimer.
2. Redistributions in binary form must reproduce the above copyright notice,
   this list of conditions and the following disclaimer in the documentation
   and/or other materials provided with the distribution.

THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

The views and conclusions contained in the software and documentation are those
of the authors and should not be interpreted as representing official policies,
either expressed or implied, of the FreeBSD Project.
"""

from optparse import OptionParser
import urllib
import urllib2
import os
import json
import sys
import time


def main():
    parser = OptionParser("Usage: %prog [options] SEARCH_QUERY")

    parser.add_option("--username", help="Loggly username. Or specify via LOGGLY_USERNAME environment variable")
    parser.add_option("--password", help="Loggly password. Or specify via LOGGLY_PASSWORD")
    parser.add_option("--subdomain", help="Loggly subdomain (eg. foo). Or specify via LOGGLY_SUBDOMAIN")

    parser.add_option("--from", help="Start time for the search.", default="NOW-24HOURS", dest="start")
    parser.add_option("--to", help="End time for the search.", default="NOW", dest="end")
    parser.add_option("--format", help="Output format, either 'json', 'xml', 'csv', or 'text'.", choices=('text', 'json', 'csv', 'xml'), default="text")
    parser.add_option("--order", help="Direction of results returned, either 'asc' or 'desc'.", choices=('asc', 'desc'), default="asc")

    # search API
    parser.add_option("--rows", help="Number of rows returned by search. 0 will get all matching rows via paging.", type="int", default=0)

    options, args = parser.parse_args()

    if len(args) != 1:
        parser.error("Need to specify SEARCH_QUERY as one argument")

    if not options.username and 'LOGGLY_USERNAME' in os.environ:
        options.username = os.environ['LOGGLY_USERNAME']
    if not options.password and 'LOGGLY_PASSWORD' in os.environ:
        options.password = os.environ['LOGGLY_PASSWORD']
    if not options.subdomain and 'LOGGLY_SUBDOMAIN' in os.environ:
        options.subdomain = os.environ['LOGGLY_SUBDOMAIN']

    if not options.username:
        parser.error("Need to specify either LOGGLY_USERNAME or --username")
    if not options.password:
        parser.error("Need to specify either LOGGLY_PASSWORD or --password")
    if not options.subdomain:
        parser.error("Need to specify either LOGGLY_SUBDOMAIN or --subdomain")

    url = "https://%s.loggly.com/api/search/" % options.subdomain

    password_mgr = urllib2.HTTPPasswordMgrWithDefaultRealm()
    password_mgr.add_password(None, url, options.username, options.password)
    handler = urllib2.HTTPBasicAuthHandler(password_mgr)
    opener = urllib2.build_opener(handler)

    if options.rows > 2000 or options.rows <= 0:
        target_rows = None if options.rows <= 0 else options.rows
        rows = 2000
        paging = True
    else:
        rows = options.rows
        paging = False

    params = {
        'q': args[0],
        'from': options.start,
        'until': options.end,
        'format': options.format,
        'order': options.order,
        'rows': rows,
        'start': 0,
    }

    results = None
    while True:
        req_url = url + '?' + urllib.urlencode(params)
        print >>sys.stderr, req_url
        try:
            resp = opener.open(req_url)
        except Exception, e:
            print >>sys.stderr, "\t%s -- retrying" % repr(e)
            time.sleep(3)
            resp = opener.open(req_url)

        result_count = 0
        if options.format in ('csv', 'text'):
            # can stream the output
            for line in resp:
                if len(line) > 1:
                    result_count += 1
                    print line,
        elif options.format == 'json':
            # merge JSON result pages in.
            r_this = json.load(resp)
            result_count += len(r_this['data'])
            if results is None:
                results = r_this
            else:
                results['data'] += r_this['data']
        elif options.format == 'xml':
            # TODO: merge XML result pages together
            print resp.read()
            raise NotImplementedError("TODO: implement XML-format result paging")

        if paging:
            if target_rows:
                got = params['start'] + result_count
                if got >= target_rows:
                    # got the target number of rows
                    break
                params['rows'] += min(2000, target_rows - got)
            elif result_count == 0:
                # no more results
                break
            params['start'] += 2000
        else:
            # no paging, just get required
            break

    if options.format == 'json':
        json.dump(results, sys.stdout, indent=2)
        sys.stdout.write("\n")
    elif options.format == 'xml':
        # TODO: output combined XML results
        raise NotImplementedError("TODO: implement XML-format result paging")

if __name__ == "__main__":
    main()

The script doesn't work anymore with API v2 from Loggly.

Updated version for API v2, which now sadly only returns 5000 lines maximum:

https://gist.github.com/dconlon/50d2175b0844bc7908e3fa09e24d7f2f

paginated version

https://gist.github.com/danield137/2ec43619e1bae893c86d26dad0152871