tshrinivasan

from tamilstemmer import TamilStemmer

wordlist = [u'மலைகள்',u'பாடுதல்',u'ஓடினான்']
#expected = [u'மலை',u'பாடு', u'ஓடி']

ta_stemmer = TamilStemer()

for word in wordlist:
  ta_stemmer.stemWord(word)

tshrinivasan

import lxml.html.clean as clean

from BeautifulSoup import BeautifulSoup

input_file = 'input.html'
output_file = 'output.html'


orig_content = open(input_file, 'rw').read()

tshrinivasan

# Source http://stackoverflow.com/a/15741856/1301753

import copy
import sys
import math
import pyPdf

def split_pages(src, dst):
    src_f = file(src, 'r+b')
    dst_f = file(dst, 'w+b')

tshrinivasan

<style type="text/css">
body {
   background: white;
   font-size: 12pt;
   }
   
strong,h3,h4{
font-weight: 900;
color:midnightblue;
}

tshrinivasan

import mechanize
import cookielib

# http://stockrt.github.com/p/emulating-a-browser-in-python-with-mechanize/

# Browser
br = mechanize.Browser()

# Cookie Jar
cj = cookielib.LWPCookieJar()