telegram group links saving

 from selenium import webdriver

from selenium.webdriver.chrome.service import Service

from selenium.webdriver.common.by import By

from selenium.webdriver.support.ui import WebDriverWait

from selenium.webdriver.support import expected_conditions as EC

from selenium.webdriver.common.keys import Keys

from selenium.webdriver.common.action_chains import ActionChains

import pickle

import time

import re

import csv

import os

# Specify the path to the ChromeDriver executable

chrome_driver_path = '/Users/jitendersingh/Documents/chromedriver' # Change this to the actual path

service = Service(chrome_driver_path)

driver = webdriver.Chrome(service=service)

wait = WebDriverWait(driver, 120)

actions = ActionChains(driver)

# Regular expression pattern to match URLs

url_pattern = r'https://terab\S+'

# Open the login page

driver.get('https://web.telegram.org/k/#-1784024652')

wait.until(EC.presence_of_element_located((By.XPATH, '/html/body/div[1]/div[1]/div[1]/div/div/div[1]/div[1]/button/div')))

driver.get('https://web.telegram.org/k/#-1784024652')

group_element = wait.until(EC.presence_of_element_located((By.XPATH, '/html/body/div[1]/div[1]/div[2]/div/div/div[2]/div[1]/div[1]/div/div/div[1]/div/span')))

group_element.click()

print("group clicked")

time.sleep(2)

group_element = wait.until(EC.presence_of_element_located((By.XPATH, '/html/body/div[1]/div[1]/div[2]/div/div/div[2]/div[1]/div[1]/div/div/div[1]/div/span')))

group_element.click()

print("group clicked")

time.sleep(2)

imgsection = wait.until(EC.presence_of_element_located((By.XPATH, '/html/body/div[1]/div[1]/div[3]/div/div/div[2]/div/div/div[3]/div[2]/div[2]/div/div/div[2]/div[1]/img')))

imgsection.click()

print("imgsection clicked")

time.sleep(2)

img = wait.until(EC.presence_of_element_located((By.XPATH, '/html/body/div[1]/div[1]/div[5]/div')))

img.click()

print("img clicked")

time.sleep(2)

# Function to extract links from text

def extract_links_from_text(text):

import re

url_pattern = r'https://terab\S+'

links = re.findall(url_pattern, text)

return links

# Initialize WebDriver and navigate to the page

# ...

csv_filename = '/Users/jitendersingh/Documents/onlylinks.csv' # Replace with the actual CSV file path

max_iterations = 500 # Set the maximum number of iterations

# Loop to extract links from each element

for iteration in range(max_iterations):

# Send the right arrow key

actions.send_keys(Keys.ARROW_RIGHT).perform()

# Wait for a brief moment to allow content to load

time.sleep(1)

wait.until(EC.presence_of_element_located((By.XPATH, '/html/body/div[1]/div[1]/div[5]/div')))

# Find the element containing the text

element = driver.find_element(By.XPATH, '/html/body/div[1]/div[1]/div[5]/div')

# Get the text from the element

text = element.text

# Extract links from the text

links = extract_links_from_text(text)

# Append the links to the CSV file

with open(csv_filename, 'a') as csv_file:

for link in links:

csv_file.write(link + '\n')

time.sleep(1)

# Check if there is any more content to navigate

# Close the driver

driver.quit()