engg_scrape.py

import requests
from bs4 import BeautifulSoup


if __name__ == "__main__":

	payload = {'reg': 'AA002', 'frm_tokens' :0.6877558 }
	doc =  requests.post("http://karresults.nic.in/cetresult2014.asp", data=payload).text


	file("a.html", "w").write(doc)
	
	soup = BeautifulSoup(doc)
	soup.prettify()

	number = soup.select('td[width=146]')[0]
	print "Number " + number.font.text

	name = soup.select('td[width=224]')[0]
	print "Name" + name.text

	marks_table = soup.select('table[border="1"]')[0]

	#one next_siblingfor whitespace, other for actual sibling
	phys_row = marks_table.tr.next_sibling.next_sibling
	chem_row = phys_row.next_sibling.next_sibling
	maths_row = chem_row.next_sibling.next_sibling

	print "Physics"  + phys_row.td.next_sibling.next_sibling.next_sibling.text
	print "Chem"  + chem_row.td.next_sibling.next_sibling.next_sibling.next_sibling.text
	print "Maths"  + maths_row.td.next_sibling.next_sibling.next_sibling.next_sibling.text


	ranks_table = soup.select('table[border="0"]')[2]
	
	engg_rank = ranks_table.tbody.tr.td.table.tr.next_sibling.next_sibling.td.next_sibling.next_sibling.text
	print "Engg rank: " + engg_rank