lpmagnuson

#EZProxy Starting Point URL Log (SPULog) Example
#LogSPU -strftime log/spu/spu%Y%m.log %h %l %u %t "%r" %s %b "%{ezproxy-groups}i"
111.222.1.2 - - [27/Oct/2014:16:32:27 -0800] "GET http://example.com" 301 0 "-"
111.222.1.3 - uSeR1sEsSiOnId [27/Oct/2014:16:32:31 -0800] "GET http://github.com" 200 0 "Default"
111.222.1.3 - uSeR2sEsSiOnId [27/Oct/2014:16:32:42 -0800] "GET http://gist.github.com" 200 0 "Default"
111.222.1.4 - uSeR3sEsSiOnId [27/Oct/2014:16:32:58 -0800] "GET http://help.github.com" HTTP/1.1" 301 0 "Default"

lpmagnuson

#Example anonymized entries from a full ezproxy log
#LogFormat %h %l %u %t "%r" %s %b "%{user-agent}i"
11.222.333.444 - tHiSiSaSeSsIoNiD [01/Sep/2014:03:26:05 -0800] "GET http://example.com:80/interface/search/ HTTP/1.1" 403 459 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1985.143 Safari/537.36"
11.222.333.444 - tHiSiSaSeSsIoNiD [01/Sep/2014:03:26:05 -0800] "GET http://example.com:80/interface/results?query=dinosaurs HTTP/1.1" 200 664 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1985.143 Safari/537.36"
11.222.333.444 - tHiSiSaSeSsIoNiD [01/Sep/2014:03:26:06 -0800] "GET http://example.com:80/interface/results/article.pdf HTTP/1.1" 200 117956 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1985.143 Safari/537.36"
11.222.333.444 - tHiSiSaSeSsIoNiD [01/Sep/2014:03:26:07 -0800] "GET http://example.com:80/interface/results/article.pdf?page=2 HTTP/1.1" 200 664 "Mozilla/5.0 (Windows NT 6.1; W

lpmagnuson

#!/usr/bin/env python

import csv
from pymarc import MARCReader
from os import listdir
from re import search

# change this line to match your folder structure
SRC_DIR = '/path/to/mrc/records'