#!/usr/bin/python # encoding: utf-8 import os import re import gzip import sys from datetime import datetime, timedelta try: dir_logs = sys.argv[1] except IndexError: dir_logs = "/var/log" try: scope_begin = datetime.strptime(sys.argv[2], "%Y-%m-%d %H:%M:%S") except IndexError: scope_begin = datetime.now().replace(hour=0, minute=0, second=0, microsecond=0) try: duration = int(sys.argv[3]) except IndexError: duration = 5 scope_end = scope_begin + timedelta(minutes=duration) sys.stderr.write("Otsin logikirjeid vahemikus %s kuni %s kaustast %s\n" % (scope_begin, scope_end, dir_logs)) RE_LOG_ENTRY = "(?P.+?) - (?P.+?) \[(?P.+?)\] \"(?P[A-Z]+) (?P.+) HTTP/1.[01]\" (?P\d+) (?P\d+) \"(?P.+?)\" \"(?P.+?)\"" # os.walk käib rekursiivselt kataloogipuu läbi for root, dirs, files in os.walk(dir_logs): # iga kausta kohta (root) on kättesaadav alamkataloogide nimekiri (dirs) # ning failide nimekiri (files) for filename in files: if filename.startswith("access.log"): path = os.path.join(root, filename) file_end = datetime.fromtimestamp( os.stat(path).st_mtime) if scope_begin > file_end: sys.stderr.write("Jätan vahele %s faili kuna logifaili lõpp oli %s\n" % (path, file_end)) continue file_start = None with gzip.open(path) if path.endswith(".gz") else open(path) as fh: for line in fh: m = re.match(RE_LOG_ENTRY, line) if not m: continue dt = datetime.strptime(m.group("timestamp")[:-6], "%d/%b/%Y:%H:%M:%S") if not file_start: # loeme esimest rida sellest failist file_start = dt if scope_end < file_start: sys.stderr.write("Jätan vahele %s faili kuna logifaili algus oli %s\n" % (path, file_start)) # Hüppa ridade lugemise tsükklist välja, järgmise faili juurde break else: sys.stderr.write("Otsin logikirjeid failist %s\n" % path) if dt > scope_end: break if dt > scope_begin: print line.strip()