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()

tshrinivasan

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

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

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

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

#This program helps to remove the given words in a file to all the files inside a directory, recursively.
# Got the sed idea from http://www.linuxask.com/questions/replace-multiple-strings-using-sed


import sys
import glob
import os
import argparse

parser = argparse.ArgumentParser()

tshrinivasan

//var langCode ='ta'; -- TODO Make it language independent.

function doGet() {
  return HtmlService.createTemplateFromFile('Index.html')
                    .evaluate();
}

function doSomething() {
  Logger.log('I was called!');
}

tshrinivasan

import sys

in_file = sys.argv[1]


content = open(in_file).read()
out = open("result.csv","a")

con  = content.split("வாக்காளர்‌ பெயர்‌")

tshrinivasan

# program name : fix_records.py
# author : tshrinivasan@gmail.com
# version : 0.1


import sys
import os
import argparse

parser = argparse.ArgumentParser(description='A program to find and replace bibliographical data')

tshrinivasan

import os
import sys
import glob
#import telegram_send


all_pdf = glob.glob("*.pdf")

all_pdf_count = len(all_pdf)