openulrLog2gource.py

import csv
from time import *

#tr < openurlgource.csv -d '\000' > openurlgourcenonulls.csv ???deletes
#sed 's/\x0/ /g' openurlgource.csv > openurlgourcenonulls.csv

f=open('openurlgourcenonulls.csv', 'rb')

reader = csv.reader(f, delimiter='\t')
writer = csv.writer(open('openurlgource.txt','wb'),delimiter='|')
headerline = reader.next()
'''
for row in reader:
	if row[4].strip() !='':
		t=int(mktime(strptime(row[0]+" "+row[1], "%Y-%m-%d %H:%M:%S")))
		#print row,row[4].rstrip(':'),row[4].replace(':','/'),t
		writer.writerow([t,row[3],'A',row[4].rstrip(':').replace(':','/')])
'''

for row in reader:
	if row[8].strip() !='':
		t=int(mktime(strptime(row[0]+" "+row[1], "%Y-%m-%d %H:%M:%S")))
		# row: 4 - issn, 5 - e-issn, 6 - isbn
		if row[4]!='':
			col='FF0000'
		elif row[5]!='':
			col='00FF00'
		elif row[6]!='':
			col='0000FF'
		else:
			col='666600'
		if row[7]=='article' or row[7]=='journal':
			typ='A'
		elif row[7]=='book' or row[7]=='bookitem':
			typ='M'
		else:
			typ='D'
		agent=row[8].rstrip(':').replace(':','/')
		#if agent=='':
		#	continue
		#print row,row[4].rstrip(':'),row[7].replace(':','/'),t
		writer.writerow([t,row[3],typ,agent,col])