Get all CBSE Class 12 Results From http://cbseresults.nic.in/class12/cbse122013.htm

get_results.py

#!/usr/bin/env python
import requests
import os

#Apparently web scraping in now considered *hacking* ... If this is the way India goes, we'll soon be seeing our own 'weev' incident :|
def get_results(i,valid):
	params={'regno':i}
	print(i)
	#Just faking some headers (They're checking the referer... atleast some, albeit weak protection
	headers={'Connection':'keep-alive','Accept-Language':'en-US,en;q=0.5','Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8','DNT':'1','User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.8; rv:21.0) Gecko/20100101 Firefox/21.0','Host': 'cbseresults.nic.in', 'Referer': 'http://cbseresults.nic.in/class12/cbse122013.htm', 'Accept-Encoding': 'gzip, deflate'}
	r = requests.post("http://cbseresults.nic.in/class12/cbse122013.asp",data=params,headers=headers)
	if(r.text.find("Result Not Found")==-1):
		#roll number is valid
		valid.write(i+",")
		#create and write results to rollnumber.html
		a=open(os.path.join(os.getcwd(),i+'.html'),'w')
		a.write(r.text)
		a.close

if __name__=="__main__":
	#Javascript Clientside Validation on the site shows that the first 2 digits should be one of the following... Makes the range to bruteforce much smaller
	first_two=[16, 17, 18, 19,  26, 27, 28, 29,  36, 37, 38, 39,  46, 47, 48, 49,  56, 57, 58, 59,  66, 67, 68, 69,  76, 77, 78, 79,  91, 92, 93, 94, 95,  96, 97, 98, 99]
	#Just a csv to hold valid roll numbers (incase you want to run it again only for valid numbers)
	validroles=open('valid.csv','w')
	#Just iterate through the lists and get results :)
	for i in first_two:
		for k in xrange(10000,99999):
			get_results(str(i)+str(k),validroles)
	validroles.close