Education Board Result Scraper

eduboard.py

import urllib2
from BeautifulSoup import BeautifulSoup

def get_html(exam, year, board, roll):

	"""Get the result page HTML output directly.
	get_html(exam, year, board, roll)"""

	base_url = "http://www.educationboardresults.gov.bd/regular"
	base_index = 'index.php'
	base_result = 'result.php'

	index_response = urllib2.urlopen(base_url + '/' + base_index)
	
	# Getting PHPSESSID session cookie
	session_cookie = index_response.info().headers[3].split()[1][0:36]
	post_data = "sr=3&et=0&exam=%s&year=%s&board=%s&roll=%s&button2=Submit" \
		% (exam, year, board, roll)

	result_request = urllib2.Request(base_url + "/" + base_result, headers = {
		'Cookie': session_cookie
		})

	result_response = urllib2.urlopen(result_request, post_data)
	return result_response.read()

def get_result(exam, year, board, roll):

	"""Get the result as a dictionary.
	get_result(exam, year, board, roll)"""

	html_response = get_html(exam, year, board, roll)
	souped_html = BeautifulSoup(html_response)
	souped_html_td = souped_html.findAll('td')
	td_list = []

	# Forming a new list with only text values
	for each_element in souped_html_td:
		td_list.append(each_element.text)

	# Gathering the grades
	result_list = td_list[td_list.index('Grade')+1:td_list.index('Search Again')]
	
	student_data = {
		'info': {
			'name': td_list[27].lower(),
			'group': td_list[33].lower(),
			'session': td_list[37],
			'registration': td_list[39],
			'student_type': td_list[41].lower(),
			'gpa': td_list[49]
		},		
	}

	full_dict = dict(student_data.items() + dictify(result_list).items())

	return full_dict

def dictify(result_list):

	"""Make a dictionary from the souped result list
	dictify(result_list)"""

	result_dict = {'grades': {}}

	element_counter = 1
	while(element_counter < len(result_list)):
		result_dict['grades'][result_list[element_counter]] = result_list[element_counter+1]
		element_counter = element_counter + 3

	return result_dict