extracting_data_from_a_telegram_channel.ipynb.txt

from telethon import TelegramClient

import pandas as pd

import asyncio

import configparser


# Reading Configs
config = configparser.ConfigParser()
config.read("config.ini")

# Setting configuration values
api_id = config['Telegram']['api_id']
api_hash = config['Telegram']['api_hash']

api_hash = str(api_hash)

phone = config['Telegram']['phone']
username = config['Telegram']['username']
# Create the client and connect
client = await TelegramClient('username22', api_id, api_hash).start()
print("Client Created")
# Ensure you're authorized
v= await client.is_user_authorized()
if not v:
    client.send_code_request(phone)
    try:
        client.sign_in(phone, input('Enter the code: '))
    except SessionPasswordNeededError:
        client.sign_in(password=input('Password: '))
#below code gives the list of participants
channel_username='t.me/mytestgroupA'

participants = await client.get_participants(channel_username)

firstname =[]

lastname = []

username = []

if len(participants):
    
    for x in participants:
        
        firstname.append(x.first_name)
        
        lastname.append(x.last_name)
        
        username.append(x.username)
        
data ={'first_name' :firstname, 'last_name':lastname, 'user_name':username}

df_user = pd.DataFrame(data)

display(df_user)
#for displaying latest 50 messages
n=50

chats = await client.get_messages(channel_username, n) # n = Number of messages to be extracted

message_id = []

message = []

sender = []

reply_to = []

time = []

if len(chats):
    
    for chat in chats:
        
        message_id.append(chat.id)
        
        message.append(chat.message)
        
        sender.append(chat.from_id)
        
        reply_to.append(chat.reply_to_msg_id)
        
        time.append(chat.date)
        
data ={'message_id':message_id, 'message': message, 'sender_ID':sender, 'reply_to_msg_id':reply_to, 'time':time}

df = pd.DataFrame(data)

display(df)
#for displaying messages with specific keywords
messages = df.sort_index(ascending= False)

messages =[]

time = []

async for message in client.iter_messages(channel_username, search='netflix'):
    
    messages.append(message.message)
    
    time.append(message.date)
    
data ={'time':time, 'message':messages}


df = pd.DataFrame(data)

display(df)
#for storing data in a json file
import json
all_user_details = []
for x in participants:
    all_user_details.append(
        {"id": x.id, "first_name": x.first_name, "last_name": x.last_name,
         "user": x.username, "phone": x.phone, "is_bot": x.bot})

with open('user_data.json', 'w') as outfile:
    json.dump(all_user_details, outfile)
#for sending a message
message='-----this message was sent using telethon-----'
await client.send_message('t.me/mytestgroupA', message=message)