My code works for the most part. (The problems are on the html side not the python side) however I feel it could run quicker or more efficiently. Due to the size of the XML document it parses it's always going to take a little while though.
The script parses the XML file and finds the names of several things, estates, symbols and ticktypes. I then create text files storing these items and for estates also use the information in an html file which will be expanded and improved later.
How could I make my code a bit sleeker and more efficient?
from xml.dom import minidom
from os import remove
#THIS IS THE LIVE XML FILE
xmldoc = minidom.parse('xxx.xml')
"""
THIS IS THE TEST XML FILE
xmldoc = minidom.parse('xxx.xml')
"""
#Establishing Lists of Items for use in defined Functions
symlist = xmldoc.getElementsByTagName('Symbol')
EstateList = xmldoc.getElementsByTagName('Estate')
ticklist = xmldoc.getElementsByTagName('Ticktype')
tickset = set(s.firstChild.data for s in ticklist)
#ESTATES
def ESTATES():
with open('estate.txt', 'w') as f:
f.write("There are currently %d Data Estates \n \n" % len(EstateList))
for s in EstateList:
f.write(s.attributes['EstateName'].value + "\n")
#TICK TYPES
def TICKS():
with open('ticktypes.txt', 'w') as e:
e.write("There are currently %d unique Tick Types \n \n" % len(tickset))
for s in tickset:
e.write(s + "\n")
#SYMBOLS
def SYMS():
with open('symbollist.txt', 'w') as g:
g.write("There are currently %d unique Symbols \n \n" % len(symlist))
for s in symlist:
g.write(s.attributes['SymbolName'].value + "\n")
def uniquelines(lineslist):
unique = {}
result = []
for item in lineslist:
if item.strip() in unique: continue
unique[item.strip()] = 1
result.append(item)
return result
with open('Z:\Joe\\temp.txt', 'w') as z:
for element in EstateList:
EstateStr = element.getAttribute('EstateName')
asset = EstateStr.split('.', 3)[2]
z.write(asset + "\n")
with open('Z:\Joe\\temp.txt','r+') as f:
filelines = f.readlines()
with open("Z:\Joe\\assets.txt", "w") as output:
output.write("There are currently %d unique Assets \n \n" %len(uniquelines(filelines)))
output.writelines(uniquelines(filelines))
remove('Z:\Joe\\temp.txt')
ESTATES()
TICKS()
SYMS()
print "There are currently %d Symbols, %d Unique Tick Types, %d Data Estates and %d unique assets" % (len(symlist), len(tickset), len(EstateList), len(uniquelines(filelines)))
print "Compiling data into html pages"
with open("C:\code\jsdd\Dropdown\home.html", "w") as f:
f.write('<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"> \n')
f.write('<html xmlns="http://www.w3.org/1999/xhtml"> \n')
f.write('<head> \n')
f.write('<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" /> \n')
f.write('<title>JavaScript Dropdown</title> \n')
f.write('<link rel="stylesheet" href="design.css" type="text/css" /> \n')
f.write('<script type="text/javascript" src="drop.js"></script> \n')
f.write('</head> \n')
f.write('<body> \n')
f.write('\n')
f.write('<dl class="dropdown"> \n')
f.write('\t <dt id="one-ddheader" onmouseover="ddMenu(\'one\',1)" onmouseout="ddMenu(\'one\',-1)">Data Estates</dt> \n')
f.write('\t <dd id="one-ddcontent" onmouseover="cancelHide(\'one\')" onmouseout="ddMenu(\'one\',-1)"> \n')
f.write('\t \t <ul> \n')
for estate in EstateList:
f.write('\t \t <li><a href="#" class="seperator">' + (estate.attributes['EstateName'].value) + '</a></li> \n')
f.write('\t \t </ul> \n')
f.write('\t </dd> \n')
f.write('\t </dl> \n')
f.write('</dl> \n')
f.write('<div style="clear:both" /> \n')
f.write('</body> \n')
f.write('</html> \n')
I have changed some file names and hidden some as this is for work so don't want to risk breaching confidentiality.
