Record 1st trending tweet count in every minute

TwiiterTrend.py

import json
import os
from datetime import datetime
from time import sleep
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.ui import WebDriverWait
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.common.by import By


import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt


print('Starting...')

# CHROME_PATH = '/usr/bin/google-chrome'
CHROMEDRIVER_PATH = './chromedriver'
WINDOW_SIZE = "1920,1080"
chrome_options = Options()
chrome_options.headless = True
# chrome_options.add_argument("--headless")
# chrome_options.add_argument("--window-size=%s" % WINDOW_SIZE)
# chrome_options.add_argument('--user-data-dir=./User_Data')
# chrome_options.add_argument("--no-sandbox")
# chrome_options.add_argument("--disable-dev-shm-usage")
# chrome_options.add_argument("--disable-gpu")
# chrome_options.add_argument("--remote-debugging-port=9222")
# chrome_options.add_experimental_option("excludeSwitches",["ignore-certificate-errors"])

print('initiated...')

preferences = {
	# "profile.default_content_settings.popups": 0,
	"download.default_directory": os.getcwd() + os.path.sep,
	# "directory_upgrade": True
}

chrome_options.add_experimental_option('prefs', preferences)

# chrome_options.binary_location = CHROME_PATH

driver = webdriver.Chrome(executable_path=CHROMEDRIVER_PATH, options=chrome_options)
driver.maximize_window()


url = 'https://trendlistz.com/india'


def fetch_and_save_data_to_csv():
	try:

		
		driver.get(url)

		card_selector = '//li[@class="trend-item"]'
		card_elements = driver.find_elements_by_xpath(card_selector)

		first_card_element = card_elements[0]


		first_card_element_splited = first_card_element.text.split('\n')

		print(first_card_element_splited)

		_, tag, trending_since, tweet_count  = first_card_element_splited


		trending_since_formated = trending_since.split('Trending since ')[1][:-1]
		tweet_count_formated = tweet_count.split(' TWEETS')[0]


		if 'K' in tweet_count_formated:
			tweet_count_formated = str( int(tweet_count_formated[:-1]) * 1000)
		else:	
			print('skipping due to insufficient data')
			return

		time = datetime.now()

		with open('tweet_trend.csv','a') as file:
			file.write(str(time) + '|' + tag + '|' + trending_since_formated + '|' + tweet_count_formated + '\n')


	except Exception as e:
		print(e)	




def draw_graph():
	df = pd.read_csv('tweet_trend.csv',header=None,names=['Time','Hashtag','Duration','Tweet Count'],sep='|')
	df['Time'] = pd.to_datetime(df['Time'])

	plt.figure(figsize=(16, 9), dpi=100)

	sns.lineplot(x='Time', y='Tweet Count', data=df)
	plt.savefig('tweet_trend.png',dpi=100)
	# plt.clf()
	plt.close()












while True:
	fetch_and_save_data_to_csv()
	draw_graph()
	print('Data Updated...')
	sleep(60)