app.py

import streamlit as st
import requests
import numpy as np
from PIL import Image
import warnings
warnings.filterwarnings("ignore")
import requests
import pandas as pd
import numpy as np
from bs4 import BeautifulSoup
import bs4
from urllib.request import urlopen
import time
import re
import time
import matplotlib.pyplot as plt 
import seaborn as sns 
import matplotlib as mpl
import plotly 
import plotly.express as px
import plotly.graph_objs as go
import plotly.offline as py
from plotly.offline import iplot
from plotly.subplots import make_subplots
import plotly.figure_factory as ff
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.chrome.service import Service

import requests
import platform
import zipfile
import os
import subprocess

import os
import subprocess

import streamlit as st
import numpy as np
import pandas as pd
import time
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.chrome.options import Options
from webdriver_manager.chrome import ChromeDriverManager
from wuzzuf_scraper import Wuzzuf_scrapping
from linkedin_scraper import LINKEDIN_Scrapping
from data_analysis import map_bubble, linkedin_exp, wuzzuf_exp

# Set up Streamlit page configuration
st.set_page_config(page_title="My Web_Scrap Page", page_icon=":tada:", layout="wide")

# ---- HEADER SECTION ----
with st.container():
    left_column, right_column = st.columns(2)
    with left_column:
        st.subheader("Hi! I am Yassmen :wave:")
        st.title("An Electronics and Communication Engineer")
        st.write("In this app we will scrap jobs from LinkedIn and Wuzzuf websites, let's get it started :boom:")
        st.write("[Reach me >](https://www.linkedin.com/in/yassmen-youssef-48439a166/)")
    with right_column:
        st.image("im.gif", use_column_width=True)

# Sidebar selections
webs = ["Wuzzuf", "Linkedin"]
jobs = ["Machine Learning", "AI Engineer", "Data Analysis", "Software Testing"]
nums = np.arange(1, 1000)

site = st.sidebar.selectbox("Select one website", webs)
job = st.sidebar.selectbox("Select one job", jobs)
num_jobs = st.sidebar.selectbox("Select number of jobs you want to scrap", nums)

# Function to get Selenium driver
@st.cache_resource
def get_driver():
    options = Options()
    options.add_argument("--headless")  # Run in headless mode
    options.add_argument("--no-sandbox")  # Bypass OS security model
    options.add_argument("--disable-dev-shm-usage")  # Overcome limited resource problems
    return webdriver.Chrome(service=Service(ChromeDriverManager().install()), options=options)


import streamlit as st
from streamlit_option_menu import option_menu



import streamlit.components.v1 as components

n2 = pd.DataFrame()

if st.sidebar.button('Start Scrapping'):
  if site =="Wuzzuf":

    with st.container():
        st.write("---")
        tab1, tab2 ,tab3= st.tabs([" Data", " Bubble Map","Data Exploration"])
        with tab1 :
          with st.spinner('✨Now loading...' ):
            time.sleep(5)
            driver = get_driver()  # Initialize the driver
            n1 = Wuzzuf_scrapping(job, num_jobs, driver)  # Pass driver to the scraping function
            driver.quit()  # Clean up the driver
            try:
              tab1.dataframe(n1)
            except:
              try:
                tab1.write(n1.astype(str).set_index(n1.index.astype(str)))  # Success
              except:
                tab1.table(n1)
        with tab2:
          map_bubble(n1)
        with tab3:
          #tab3.plotly_chart(wuzzuf_exp(n1))
          wuzzuf_exp(n1)


  elif site =="Linkedin":
    with st.container():
        st.write("---")
        tab1, tab2 ,tab3= st.tabs([" Data", " Bubble Map","Data Exploration"])
        with tab1 :
          with st.spinner('✨Now loading...' ):
            time.sleep(5)
            driver = get_driver()
            n1 = LINKEDIN_Scrapping(job ,num_jobs,driver )
            driver.quit()  # Clean up the driver
            try:
              tab1.dataframe(n1)
            except:
              try:
                tab1.write(n1.astype(str).set_index(n1.index.astype(str)))  # Success
              except:
                tab1.table(n1)
        with tab2:
          map_bubble(n1)
        with tab3:
          linkedin_exp(n1)