nuhmanpk

SIR Electoral Roll PDF Parser (Malayalam → CSV)

A simple Python script to parse SIR (Special Intensive Revision) electoral roll PDFs published by the Election Commission of India, extract voter details from scanned Malayalam documents, and convert them into a clean CSV with Malayalam to English translation.

What is SIR?

Special Intensive Revision (SIR) is a comprehensive verification process of electoral rolls conducted by the Election Commission of India to update, correct, add, or remove voter entries.

Features

• Malayalam OCR using Tesseract
• Parses scanned Election Commission SIR PDFs

nuhmanpk

import streamlit as st
import time

from langchain_community.document_loaders import SeleniumURLLoader
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_core.vectorstores import InMemoryVectorStore
from langchain_ollama import OllamaEmbeddings
from langchain_core.prompts import ChatPromptTemplate
from langchain_ollama.llms import OllamaLLM

nuhmanpk

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({ apiKey: process.env.GEMINI_API_KEY });

let response = await ai.models.generateContent({
  model: "gemini-2.0-flash",
  contents: [
    "Given the sentence 'hello world, this is an example sentence', find the longest word, count the vowels in it, and return the product of the length of the longest word and the number of vowels."
  ],
  config: {

nuhmanpk

import 'dotenv/config';
import { GoogleGenAI, Type } from '@google/genai';

const ai = new GoogleGenAI({ apiKey: process.env.GEMINI_API_KEY });

const getCoordinatesFunction = {
  name: 'get_coordinates',
  description: 'Find latitude and longitude of a city.',
  parameters: {
    type: Type.OBJECT,

nuhmanpk

// 1️⃣ Import the OpenAI SDK
import { OpenAI } from "openai";

// 2️⃣ Initialize the OpenAI client
const openai = new OpenAI();

// 3️⃣ Define our two tools:
//     a. get_coordinates: To find the latitude and longitude for a given city.
//     b. get_weather: To get the current temperature using the coordinates.
const tools = [

nuhmanpk

from pyrogram import Client

# get these values from api.telegram.org
api_id = "API_ID"
api_hash = "API_HASH"


async def main():
    async with Client(":memory:", api_id=int(api_id), api_hash=api_hash) as app:
        # Generate the session string

nuhmanpk

import pyrogram
import pywhatkit

# Replace with your Pyrogram API credentials
API_ID = 'YOUR_API_ID'
API_HASH = 'YOUR_API_HASH'
BOT_TOKEN = 'YOUR_BOT_TOKEN'

# Initialize the Pyrogram client
app = pyrogram.Client('my_bot', api_id=API_ID, api_hash=API_HASH, bot_token=BOT_TOKEN)

nuhmanpk

<lib-ngx-image-zoom 
    [thumbImage]='imageUrl' [fullImage]=imageUrl maxZoomRatio="10" magnification="1"
     enableScrollZoom="true" altText="img-not-found">
</lib-ngx-image-zoom>

nuhmanpk

from userbase import present_in_userbase, add_to_userbase, get_users # userbase.py is Attached below
import time

@bughunter0.on_message(filters.private & filters.command('broadcast') & filters.user(OWNER) & filters.reply)
async def broadcast(client: bughunter0, message: Message):
       broadcast_msg = message.reply_to_message
       txt = await message.reply(text = 'Staring....')        
       user_ids = await get_users()
       success = 0
       deleted = 0

nuhmanpk

import pyrogram
from pyrogram import Client, filters
from pyrogram.types import InlineKeyboardMarkup, InlineKeyboardButton
from pyrogram.types import User, Message
from pyrogram.errors import UserNotParticipant


UPDATE_CHANNEL= "channel name without '@'"
# Follow me on Github - Github.com/nuhmanpk
# Join @BugHunterBots for more