My first Server written in Python

This is my first successful server program written in Python.  This helps me understand how servers and clients work. Firefox would not hook-up, but Chromium worked just fine. Typed "localhost:1088" in my browser and the sever sent a small html file back.

I added a GUI to my webpage scraper

#!/usr/bin/python
#Appraiser Data scraper example.
#Written by Steve Atchison March 23 2013
import urllib2
from Tkinter import *

def getwebhtml():
    #This gets the html text from the appraiser webpage using the parcel number entered by user: assines it to the_page
    pid = pinnum.get()
    req = urllib2.Request('http://www.snco.us/ap/R_prop/Comp.asp?PRCL_ID='+str(pid)+'&PRCL_CD=01&YEAR=2013')
    response = urllib2.urlopen(req)
    the_page = response.read()

    startchar = the_page.find('PID1=')
    #compareable pin
    comp1=(the_page[int(startchar):int(startchar)+21])
    #saleprice
    saleprice=(the_page[int(startchar+88):int(startchar)+99])  
    #sale date
    saledate=(the_page[int(startchar+63):int(startchar)+67])

    txtbox.insert("1.0",comp1+'\n')
    txtbox.insert("2.0",'Date: '+saledate+'\n')
    txtbox.insert("3.0",'Sale price:'+saleprice+'\n\n')

    startchar = the_page.find('PID2=')
    #compareable pin
    comp1=(the_page[int(startchar):int(startchar)+21])
    #saleprice
    saleprice=(the_page[int(startchar+88):int(startchar)+99])  
    #sale date
    saledate=(the_page[int(startchar+63):int(startchar)+67])
   
    txtbox.insert("1.0",comp1+'\n')
    txtbox.insert("2.0",'Date: '+saledate+'\n')
    txtbox.insert("3.0",'Sale price:'+saleprice+'\n\n')
 
    startchar = the_page.find('PID3=')

    #compareable pin
    comp1=(the_page[int(startchar):int(startchar)+21])
    #saleprice
    saleprice=(the_page[int(startchar+88):int(startchar)+99])  
    #sale date
    saledate=(the_page[int(startchar+63):int(startchar)+67])
   
    txtbox.insert("1.0",comp1+'\n')
    txtbox.insert("2.0",'Date: '+saledate+'\n')
    txtbox.insert("3.0",'Sale price:'+saleprice+'\n\n')

    startchar = the_page.find('PID4=')
    #compareable pin
    comp1=(the_page[int(startchar):int(startchar)+21])
    #saleprice
    saleprice=(the_page[int(startchar+88):int(startchar)+99])  
    #sale date
    saledate=(the_page[int(startchar+63):int(startchar)+67])
   
    txtbox.insert("1.0",comp1+'\n')
    txtbox.insert("2.0",'Date: '+saledate+'\n')
    txtbox.insert("3.0",'Sale price:'+saleprice+'\n\n')

    startchar = the_page.find('PID5=')
    #compareable pin
    comp1=(the_page[int(startchar):int(startchar)+21])
    #saleprice
    saleprice=(the_page[int(startchar+88):int(startchar)+99])  
    #sale date
    saledate=(the_page[int(startchar+63):int(startchar)+67])
   
    txtbox.insert("1.0",comp1+'\n')
    txtbox.insert("2.0",'Date: '+saledate+'\n')
    txtbox.insert("3.0",'Sale price:'+saleprice+'\n\n')

def cleartext():
    txtbox.delete("1.0",  END)
    pinnum.delete(0,END)

root = Tk()
btn = Button(root, text = "Get Comparables", command = getwebhtml)
btn.pack()

btn2=Button(root, text="Clear", command=cleartext)
btn2.pack()

pinnum=Entry(root)
pinnum.pack()

txtbox = Text(root)
txtbox.pack()

root.mainloop()

Eric Python Editor

   I tried a new python editor called Eric, and I like it a lot.  Eric has lots of cool features like code folding, smart indent, and it can export my code to several formats including pdf.

  Unfortunately, my netbook does not have a big enough screen for it, but it is great on a larger display.   I think I have stepped up to the next level of python IDE, but I still like good old idle too.

My new and improved Webpage scraper

#!/usr/bin/python
#Appraiser Data scraper
#Written by Steve Atchison March 23 2013
import urllib2

pid = raw_input('Enter parcel number: ')

#This gets the html text from the appraiser webpage using the parcel number entered by user.
req = urllib2.Request('http://www.snco.us/ap/R_prop/Comp.asp?PRCL_ID='+str(pid)+'&PRCL_CD=01&YEAR=2013')
response = urllib2.urlopen(req)
the_page = response.read()

#erase all data in scrape_data.txt file
f2=open("scrape_data.txt",'w')
f2.close()

def getmoredata(start):
    #This function grabs sales and date from appraiser webpage and saves it to scrape_data.txt
   
    print('--------------------------------')
    #Compare PIN
    thepin=((the_page[int(start+5):int(start)+21]))
    print(thepin)
    #Actual sale price
    saleprice=(the_page[int(start+88):int(start)+99])
    print('Actual sales price = %s') % saleprice  
    #sale date
    saledate=(the_page[int(start+63):int(start)+67])
    print('Sale date = %s') % saledate
   
    f2=open("scrape_data.txt",'a')
    f2.write(thepin +'  ')
    f2.write(saleprice +'  ')
    f2.write(saledate + '\n')
    f2.close()   
   
#Finds the begining point of each parcel number in the html file,
#and then calls the getmoredata function
startchar = the_page.find('PID1=')
getmoredata(startchar)

startchar = the_page.find('PID2=')
getmoredata(startchar)

startchar = the_page.find('PID3=')
getmoredata(startchar)

startchar = the_page.find('PID4=')
getmoredata(startchar)

startchar = the_page.find('PID5=')
getmoredata(startchar)

My web scraper program, Works Great!

#Appraiser Data scraper example.

#Written by Steve Atchisn 3/22/2013

import urllib2

import arcpy

mxd = arcpy.mapping.MapDocument('CURRENT')

df = arcpy.mapping.ListDataFrames(mxd)[0]

def getsalesdate():

    #get parcel number

    parnum1=(the_page[int(startchar+5):int(startchar)+21])

    print(parnum1)

    #Actual sale price

    saleprice=(the_page[int(startchar+88):int(startchar)+99])

    print('Actual sales price = %s') % saleprice                   

    #get sale date 

    saledate=(the_page[int(startchar+63):int(startchar)+67])

    print('Sale date = %s') % saledate

    print('-------------------------------------------------')

   

for row in arcpy.SearchCursor("Owners"):

    parnum = row.getValue('PIN')

    req = urllib2.Request('http://www.snco.us/ap/R_prop/Comp.asp?PRCL_ID='+str(parnum)+'&PRCL_CD=01&YEAR=2013')

    response = urllib2.urlopen(req)

    the_page = response.read()

    startchar = the_page.find('PID1=')

    parnum1 =(the_page[int(startchar+5):int(startchar)+21])

    getsalesdate()

  

    startchar = the_page.find('PID2=')

    parnum2 =(the_page[int(startchar+5):int(startchar)+21])

    getsalesdate()

    startchar = the_page.find('PID3=')

    parnum3=(the_page[int(startchar+5):int(startchar)+21])

    getsalesdate()

    startchar = the_page.find('PID4=')

    parnum4=(the_page[int(startchar+5):int(startchar)+21])

    getsalesdate()

    startchar = the_page.find('PID5=')

    parnum5=(the_page[int(startchar+5):int(startchar)+21])

    getsalesdate()

arcpy.SelectLayerByAttribute_management("Owners","NEW_SELECTION","PIN="+parnum1)

arcpy.SelectLayerByAttribute_management("Owners","ADD_TO_SELECTION","PIN="+parnum2)

arcpy.SelectLayerByAttribute_management("Owners","ADD_TO_SELECTION","PIN="+parnum3)

arcpy.SelectLayerByAttribute_management("Owners","ADD_TO_SELECTION","PIN="+parnum4)

arcpy.SelectLayerByAttribute_management("Owners","ADD_TO_SELECTION","PIN="+parnum5)

df.zoomToSelectedFeatures()

#Select a parcel from the Owner feature class before running this code!!

My first Web scraper written in Python!