/usr/lib/python2.7/dist-packages/stetl/utils/apachelog.py is in python-stetl 1.1+ds-2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 | #!/usr/bin/env python
"""Apache Log Parser
Parser for Apache log files. This is a port to python of Peter Hickman's
Apache::LogEntry Perl module:
<http://cpan.uwinnipeg.ca/~peterhi/Apache-LogRegex>
Takes the Apache logging format defined in your httpd.conf and generates
a regular expression which is used to a line from the log file and
return it as a dictionary with keys corresponding to the fields defined
in the log format.
Example:
import apachelog, sys
# Format copied and pasted from Apache conf - use raw string + single quotes
format = r'%h %l %u %t \"%r\" %>s %b \"%{Referer}i\" \"%{User-Agent}i\"'
p = apachelog.parser(format)
for line in open('/var/apache/access.log'):
try:
data = p.parse(line)
except:
sys.stderr.write("Unable to parse %s" % line)
The return dictionary from the parse method depends on the input format.
For the above example, the returned dictionary would look like;
{
'%>s': '200',
'%b': '2607',
'%h': '212.74.15.68',
'%l': '-',
'%r': 'GET /images/previous.png HTTP/1.1',
'%t': '[23/Jan/2004:11:36:20 +0000]',
'%u': '-',
'%{Referer}i': 'http://peterhi.dyndns.org/bandwidth/index.html',
'%{User-Agent}i': 'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.2) Gecko/20021202'
}
...given an access log entry like (split across lines for formatting);
212.74.15.68 - - [23/Jan/2004:11:36:20 +0000] "GET /images/previous.png HTTP/1.1"
200 2607 "http://peterhi.dyndns.org/bandwidth/index.html"
"Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.2) Gecko/20021202"
You can also re-map the field names by subclassing (or re-pointing) the
alias method.
Generally you should be able to copy and paste the format string from
your Apache configuration, but remember to place it in a raw string
using single-quotes, so that backslashes are handled correctly.
This module provides three of the most common log formats in the
formats dictionary;
# Common Log Format (CLF)
p = apachelog.parser(apachlog.formats['common'])
# Common Log Format with Virtual Host
p = apachelog.parser(apachlog.formats['vhcommon'])
# NCSA extended/combined log format
p = apachelog.parser(apachlog.formats['extended'])
For notes regarding performance while reading lines from a file
in Python, see <http://effbot.org/zone/readline-performance.htm>.
Further performance boost can be gained by using psyco
<http://psyco.sourceforge.net/>
On my system, using a loop like;
for line in open('access.log'):
p.parse(line)
...was able to parse ~60,000 lines / second. Adding psyco to the mix,
up that to ~75,000 lines / second.
The parse_date function is intended as a fast way to convert a log
date into something useful, without incurring a significant date
parsing overhead - good enough for basic stuff but will be a problem
if you need to deal with log from multiple servers in different
timezones.
JvdB:
From https://code.google.com/p/apachelog/
License: Artistic License/GPL
"""
__version__ = "1.1"
__license__ = """Released under the same terms as Perl.
See: http://dev.perl.org/licenses/
"""
__author__ = "Harry Fuecks <hfuecks@gmail.com>"
__contributors__ = [
"Peter Hickman <peterhi@ntlworld.com>",
"Loic Dachary <loic@dachary.org>"
]
import re
import hashlib
class ApacheLogParserError(Exception):
pass
class parser:
default_options = {'methods': ['GET', 'HEAD', 'POST'],
'use_native_types': True,
'request_path_only': True,
'gen_key': False}
def __init__(self, format, key_map=None, options=default_options):
"""
Takes the log format from an Apache configuration file.
Best just copy and paste directly from the .conf file
and pass using a Python raw string e.g.
format = r'%h %l %u %t \"%r\" %>s %b \"%{Referer}i\" \"%{User-Agent}i\"'
p = apachelog.parser(format)
"""
self._names = []
self._regex = None
self._pattern = ''
self._parse_format(format)
self._key_map = key_map
self._options = options
def _parse_format(self, format):
"""
Converts the input format to a regular
expression, as well as extracting fields
Raises an exception if it couldn't compile
the generated regex.
"""
format = format.strip()
format = re.sub('[ \t]+', ' ', format)
subpatterns = []
findquotes = re.compile(r'^\\"')
findreferreragent = re.compile('Referer|User-Agent')
findpercent = re.compile('^%.*t$')
lstripquotes = re.compile(r'^\\"')
rstripquotes = re.compile(r'\\"$')
self._names = []
for element in format.split(' '):
hasquotes = 0
if findquotes.search(element):
hasquotes = 1
if hasquotes:
element = lstripquotes.sub('', element)
element = rstripquotes.sub('', element)
self._names.append(self.alias(element))
subpattern = '(\S*)'
if hasquotes:
if element == '%r' or findreferreragent.search(element):
subpattern = r'\"([^"\\]*(?:\\.[^"\\]*)*)\"'
else:
subpattern = r'\"([^\"]*)\"'
elif findpercent.search(element):
subpattern = r'(\[[^\]]+\])'
elif element == '%U':
subpattern = '(.+?)'
subpatterns.append(subpattern)
self._pattern = '^' + ' '.join(subpatterns) + '$'
try:
self._regex = re.compile(self._pattern)
except Exception, e:
raise ApacheLogParserError(e)
def parse(self, line):
"""
Parses a single line from the log file and returns
a dictionary of it's contents.
Raises and exception if it couldn't parse the line
"""
line = line.strip()
match = self._regex.match(line)
if match:
data = {}
for k, v in zip(self._names, match.groups()):
# JvdB convert to native Python types if needed
if self._options['use_native_types']:
if k in ['%>s', '%b', '%D']:
try:
v = int(v)
except Exception:
v = 0
elif k == '%t':
try:
v = int(parse_date(v)[0])
except Exception:
v = 0
elif v == '-':
v = None
# JvdB: elaborate request '%r' string
if k == '%r':
v_elms = v.split(' ')
# Filter out methods of no interest
if v_elms[0] not in self._options['methods']:
return None
if self._options['request_path_only']:
try:
v = v.split(' ')[1]
except Exception:
v = ''
# JvdB map %-like keys to readable names using key map
if self._key_map:
try:
data[self._key_map[k]] = v
except KeyError:
pass
else:
data[k] = v
# JvdB option to generate unique key, e.g. for database insert
if self._options['gen_key']:
# Generate unique key as md5-string from all values
data['key'] = hashlib.md5(str(data.values())).hexdigest()
return data
raise ApacheLogParserError("Unable to parse: %s with the %s regular expression" % (line, self._pattern))
def alias(self, name):
"""
Override / replace this method if you want to map format
field names to something else. This method is called
when the parser is constructed, not when actually parsing
a log file
Takes and returns a string fieldname
"""
return name
def pattern(self):
"""
Returns the compound regular expression the parser extracted
from the input format (a string)
"""
return self._pattern
def names(self):
"""
Returns the field names the parser extracted from the
input format (a list)
"""
return self._names
months = {
'Jan': '01',
'Feb': '02',
'Mar': '03',
'Apr': '04',
'May': '05',
'Jun': '06',
'Jul': '07',
'Aug': '08',
'Sep': '09',
'Oct': '10',
'Nov': '11',
'Dec': '12'
}
def parse_date(date):
"""
Takes a date in the format: [05/Dec/2006:10:51:44 +0000]
(including square brackets) and returns a two element
tuple containing first a timestamp of the form
YYYYMMDDHH24IISS e.g. 20061205105144 and second the
timezone offset as is e.g.;
parse_date('[05/Dec/2006:10:51:44 +0000]')
>> ('20061205105144', '+0000')
It does not attempt to adjust the timestamp according
to the timezone - this is your problem.
"""
date = date[1:-1]
elems = [
date[7:11],
months[date[3:6]],
date[0:2],
date[12:14],
date[15:17],
date[18:20],
]
return (''.join(elems), date[21:])
"""
Frequenty used log formats stored here
"""
formats = {
# Common Log Format (CLF)
'common': r'%h %l %u %t \"%r\" %>s %b',
# Common Log Format with Virtual Host
'vhcommon': r'%v %h %l %u %t \"%r\" %>s %b',
# NCSA extended/combined log format
'extended': r'%h %l %u %t \"%r\" %>s %b \"%{Referer}i\" \"%{User-agent}i\"',
# JvdB: extended with timing in nanosecs %D as last
'extended_timed': r'%h %l %u %t \"%r\" %>s %b \"%{Referer}i\" \"%{User-agent}i\" %D'
}
if __name__ == '__main__':
import unittest
class TestApacheLogParser(unittest.TestCase):
def setUp(self):
self.format = r'%h %l %u %t \"%r\" %>s ' \
r'%b \"%{Referer}i\" \"%{User-Agent}i\"'
self.fields = '%h %l %u %t %r %>s %b %{Referer}i ' \
'%{User-Agent}i'.split(' ')
self.pattern = '^(\\S*) (\\S*) (\\S*) (\\[[^\\]]+\\]) ' \
'\\\"([^"\\\\]*(?:\\\\.[^"\\\\]*)*)\\\" ' \
'(\\S*) (\\S*) \\\"([^"\\\\]*(?:\\\\.[^"\\\\]*)*)\\\" ' \
'\\\"([^"\\\\]*(?:\\\\.[^"\\\\]*)*)\\\"$'
self.line1 = r'212.74.15.68 - - [23/Jan/2004:11:36:20 +0000] ' \
r'"GET /images/previous.png HTTP/1.1" 200 2607 ' \
r'"http://peterhi.dyndns.org/bandwidth/index.html" ' \
r'"Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.2) ' \
r'Gecko/20021202"'
self.line2 = r'212.74.15.68 - - [23/Jan/2004:11:36:20 +0000] ' \
r'"GET /images/previous.png=\" HTTP/1.1" 200 2607 ' \
r'"http://peterhi.dyndns.org/bandwidth/index.html" ' \
r'"Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.2) ' \
r'Gecko/20021202"'
self.line3 = r'4.224.234.46 - - [20/Jul/2004:13:18:55 -0700] ' \
r'"GET /core/listing/pl_boat_detail.jsp?&units=Feet&checked' \
r'_boats=1176818&slim=broker&&hosturl=giffordmarine&&ywo=' \
r'giffordmarine& HTTP/1.1" 200 2888 "http://search.yahoo.com/' \
r'bin/search?p=\"grady%20white%20306%20bimini\"" ' \
r'"Mozilla/4.0 (compatible; MSIE 6.0; Windows 98; ' \
r'YPC 3.0.3; yplus 4.0.00d)"'
self.p = parser(self.format)
def testpattern(self):
self.assertEqual(self.pattern, self.p.pattern())
def testnames(self):
self.assertEqual(self.fields, self.p.names())
def testline1(self):
data = self.p.parse(self.line1)
self.assertEqual(data['%h'], '212.74.15.68', msg='Line 1 %h')
self.assertEqual(data['%l'], '-', msg='Line 1 %l')
self.assertEqual(data['%u'], '-', msg='Line 1 %u')
self.assertEqual(data['%t'], '[23/Jan/2004:11:36:20 +0000]', msg='Line 1 %t')
self.assertEqual(
data['%r'],
'GET /images/previous.png HTTP/1.1',
msg='Line 1 %r'
)
self.assertEqual(data['%>s'], '200', msg='Line 1 %>s')
self.assertEqual(data['%b'], '2607', msg='Line 1 %b')
self.assertEqual(
data['%{Referer}i'],
'http://peterhi.dyndns.org/bandwidth/index.html',
msg='Line 1 %{Referer}i'
)
self.assertEqual(
data['%{User-Agent}i'],
'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.2) Gecko/20021202',
msg='Line 1 %{User-Agent}i'
)
def testline2(self):
data = self.p.parse(self.line2)
self.assertEqual(data['%h'], '212.74.15.68', msg='Line 2 %h')
self.assertEqual(data['%l'], '-', msg='Line 2 %l')
self.assertEqual(data['%u'], '-', msg='Line 2 %u')
self.assertEqual(
data['%t'],
'[23/Jan/2004:11:36:20 +0000]',
msg='Line 2 %t'
)
self.assertEqual(
data['%r'],
r'GET /images/previous.png=\" HTTP/1.1',
msg='Line 2 %r'
)
self.assertEqual(data['%>s'], '200', msg='Line 2 %>s')
self.assertEqual(data['%b'], '2607', msg='Line 2 %b')
self.assertEqual(
data['%{Referer}i'],
'http://peterhi.dyndns.org/bandwidth/index.html',
msg='Line 2 %{Referer}i'
)
self.assertEqual(
data['%{User-Agent}i'],
'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.2) Gecko/20021202',
msg='Line 2 %{User-Agent}i'
)
def testline3(self):
data = self.p.parse(self.line3)
self.assertEqual(data['%h'], '4.224.234.46', msg='Line 3 %h')
self.assertEqual(data['%l'], '-', msg='Line 3 %l')
self.assertEqual(data['%u'], '-', msg='Line 3 %u')
self.assertEqual(
data['%t'],
'[20/Jul/2004:13:18:55 -0700]',
msg='Line 3 %t'
)
self.assertEqual(
data['%r'],
r'GET /core/listing/pl_boat_detail.jsp?&units=Feet&checked_boats='
r'1176818&slim=broker&&hosturl=giffordmarine&&ywo=giffordmarine& '
r'HTTP/1.1',
msg='Line 3 %r'
)
self.assertEqual(data['%>s'], '200', msg='Line 3 %>s')
self.assertEqual(data['%b'], '2888', msg='Line 3 %b')
self.assertEqual(
data['%{Referer}i'],
r'http://search.yahoo.com/bin/search?p=\"grady%20white%20306'
r'%20bimini\"',
msg='Line 3 %{Referer}i'
)
self.assertEqual(
data['%{User-Agent}i'],
'Mozilla/4.0 (compatible; MSIE 6.0; Windows 98; YPC 3.0.3; '
'yplus 4.0.00d)',
msg='Line 3 %{User-Agent}i'
)
def testjunkline(self):
self.assertRaises(ApacheLogParserError, self.p.parse, 'foobar')
def testhasquotesaltn(self):
p = parser(r'%a \"%b\" %c')
line = r'foo "xyz" bar'
data = p.parse(line)
self.assertEqual(data['%a'], 'foo', '%a')
self.assertEqual(data['%b'], 'xyz', '%c')
self.assertEqual(data['%c'], 'bar', '%c')
def testparsedate(self):
date = '[05/Dec/2006:10:51:44 +0000]'
self.assertEqual(('20061205105144', '+0000'), parse_date(date))
unittest.main()
|