Introduction to Python Programming

Assignment 1

Sample output when called from DOS shell.

Disclaimer: Normally, I would have used regular expressions (re module) with this type of application. The instructor agreed, however he noted that regular expressions is not part of standard Python and he wanted to first emphasize standard Python string methods. He later introduced the module, Elementtree, which is one of numerous packages dedicated to XML processing.

#!/usr/bin/env python

"""

Assignment 1:

Parse xml file. Look for product name and unit price,

build a dictionary and then print all records.

This program assumes product name and unit price tags are not multiline

and that product name precedes the unit price.

DOS Shell Usage:

assignment1.py <inputfile>

"""

import sys

import string

# extract the tag item at foundIndex

def getItem(line,foundIndex):

substring = line[foundIndex:]

foundIndex = string.find(substring,">")

substring = substring[foundIndex+1:]

foundIndex = string.find(substring,"<")

substring = substring[:foundIndex]

return substring

def main():

# process file input argument

args = sys.argv[1:]

if len(args) > 0:

xmlpath = args[0]

else:

print "*** Error: Missing input file argument ***"

sys.stdout.write(__doc__)

sys.exit(1)

try:

xmlin = open(xmlpath,'r')

except:

print "Error: Unable to open", xmlpath

sys.exit(1)

# read all file input lines into a list

# initialize dictionary and tag items

xmlLines = xmlin.readlines()

productprice = {}

productname = unitprice = ''

# search for tag items line by line and build dictionary

# assume productname occurs before unit price and tag items are not mult-line

for line in xmlLines:

if (productname == ''):

foundIndex = string.find(line,"productname")

if foundIndex > -1:

productname = getItem(line,foundIndex)

else:

foundIndex = string.find(line,"unitprice")

if foundIndex > -1:

unitprice = getItem(line,foundIndex)

productprice[productname] = unitprice

productname = unitprice = ''

# print the record

print "Product Name".ljust(40),"Unit Price".ljust(10)

keys = productprice.keys()

# keys.sort()

for product in keys:

print product.ljust(40),productprice[product].ljust(10)

xmlin.close()

# accomodate Windows

# print "\nHit <Enter> to exit program.\n"

# raw_input()

if __name__ == '__main__':

main()