Dell Scraper

Due to failings in the past, our inventory system is in need of a revamp as it is missing both systems and information as part of the revamp we decided to scrap everything we new and reinventroy everything. We use a lot of dell systems and I figured that as we had collected the service tags of a number of systems we could get the info about that system from the dell site. I wrote a quick python script to take a list of service tags and output the system info as a csv file in the format “tag, shipdate, SysType, Ram, HDD, Support”.

E.g.

"4GXCB1H","2008-03-29","Latitude D430","2GB","80GB","3Y NBD INTERNATIONAL (NEXT BUSINESS DAY);UPG TO 4Y NBD INTERNATIONAL (NEXT BUSINE"

Place a text file called “taglist.txt” in the same directory as the script with the dell service tags listed 1 per line. When the script is done the data will be in the file called “SystemList.txt”.


4GXCB1H

5GXAB1H

#!/usr/bin/python

#

# Copyright 2009 Ryan McLean <ryanm *at* ninet *.* org>

#

# dellscraper.py

#

# Dell Warranty Scraper

###Imports

from urllib2 import Request, urlopen, URLError

import datetime, re, sys, os, string
def processHTML(rawhtml):

  #Grab Shipdate

  res = re.search('Ship\sDate:</td><td\s.*?>(\d\d/\d\d/\d\d\d\d)</td>', rawhtml, re.IGNORECASE)

  shipdate = res.group(1)
  #Grab System Type

  res = re.search('System\sType:</td><td\s.*?>(.*?)</td></tr>', rawhtml, re.IGNORECASE)

  SysType = res.group(1)
  #Breakdown

  bd1 = re.search('<span>Part Description</span></td></tr><tr><td .*?><img .*? /></td></tr>(.*</table>)', rawhtml, re.IGNORECASE)

  table = bd1.group(1)

  table = re.sub('</table>','',table)

  table = re.sub('<tr>.*?</td><td','<td',table)

  table = re.sub('<td valign="top">|<td valign="top"></td>','',table)

  table = re.sub('<td valign="top">','',table)

  table = re.sub('<.*?>', 'XXX', table)

  table = re.sub('X{2,}', '<x>', table)
  #Get RAM

  res = re.search('<x>MEMORY\s:\s(\d+[M|G]B).*?<x>',table)

  Ram = res.group(1)
  #Get HDD

  res = re.search('<x>.*?(\d+GB).*?<x>',table)

  HDD = res.group(1)
  #Get Support Details

  Support = []

  res = re.search('<x>(\dY[R]?\s.*?)<x>',table)

  if (res):

    Support.append(res.group(1))
  res = ""
  res = re.search('<x>(UPG\sTO\s\dY[R]?\s.*?)<x>',table)

  if (res):

    Support.append(res.group(1))
  res = ""
  res = re.search('<x>(\dY[R]?\sPRO.*?)<x>',table)

  if (res):

    Support.append(res.group(1))
  return shipdate, SysType, Support, Ram, HDD
#fileI/O

def readfile(inFile):

  if os.path.isfile(inFile) == False:

    exit()
  thisfile = open(inFile, 'r')
  tags = []

  taga = tags.append

  for line in thisfile.readlines():

    if line.strip(): # check for empty lines

      if line[-1] == '\n':

        taga(line[0:-1]) # If line ends in line break remove it

      else:

        taga(line)

  thisfile.close()

  return tags
def writefile(outfile, outline):

  thisfile = open(outfile, 'a')

  thisfile.write(outline + "\n")

  thisfile.close()
#format data and write

def fdata(tag, shipdate, SysType, Support, Ram, HDD):

  d,m,y = shipdate.split('/')

  shipdate = y + '-' + m + '-' + d
  ts = ''

  for s in Support:

    ts = ts + ';' + s

  ts = re.sub('^;','',ts)

  Support = ts
  if re.match('\d\d\d\dMB',Ram):

    res = re.search('(\d)\d\d\dMB',Ram)

    Ram = res.group(1) + "GB"
  outstr = '"' + tag + '","' + shipdate + '","' + SysType + '","' + Ram + '","' + HDD + '","' + Support + '"'
  return outstr
###  MAIN ###
url = 'http://support.euro.dell.com/support/topics/topic.aspx/emea/shared/support/my_systems_info/en/details?c=uk&cs=RC1050265&l=en&s=bsd&~ck=anavml&~tab=2&~wsf=tabs&servicetag='
filename = 'taglist.txt'

tags = readfile(filename)
for tag in tags:

  try:

    req = Request(url + tag)

    response = urlopen(req)

    rawhtml = response.read()

  except URLError, e:

    if hasattr(e, 'reason'):

      print 'We failed to reach a server.'

      print 'Reason: ', e.reason

    elif hasattr(e, 'code'):

      print 'The server couldn\'t fulfill the request.'

      print 'Error code: ', e.code

    else:

      shipdate, SysType, Support, Ram, HDD = processHTML(rawhtml)

      outstr = fdata(tag, shipdate, SysType, Support, Ram, HDD)

      writefile("./SystemList.txt", outstr)