app.py

import streamlit as st
import pandas as pd
import numpy as np
import requests
from urllib.parse import urlparse, quote
import re
from bs4 import BeautifulSoup
import time
from joblib import Parallel, delayed


@st.cache_data
def convert_df(df):
    return df.to_csv()

def extract_website_domain(url):
    parsed_url = urlparse(url)
    return parsed_url.netloc


def google_address(address):
        
    address_number = re.findall(r'\b\d+\b', address)[0]
    address_zip =re.search(r'(\d{5})$', address).group()[:2]
    
    search_query = quote(address)
    url=f'https://www.google.com/search?q={search_query}'
    response = requests.get(url)
    soup = BeautifulSoup(response.content, "html.parser")
    
    texts_links = []
    for link in soup.find_all("a"):
        t,l=link.get_text(), link.get("href")
        if (l[:11]=='/url?q=http') and (len(t)>20 ):
            texts_links.append((t,l))
    
    
    text = soup.get_text()
    
    texts_links_des=[]
    for i,t_l in enumerate(texts_links):
        start=text.find(texts_links[i][0][:50])
        try:
            end=text.find(texts_links[i+1][0][:50])
        except:
            end=text.find('Related searches')
            
        description=text[start:end]
        texts_links_des.append((t_l[0],t_l[1],description))
    
    df=pd.DataFrame(texts_links_des,columns=['Title','Link','Description'])
    df['Description']=df['Description'].bfill()
    df['Address']=df['Title'].str.extract(r'(.+? \d{5})')
    df['Link']=[i[7:i.find('&sa=')] for i in df['Link']]
    df['Website'] = df['Link'].apply(extract_website_domain)
    
    df['Square Footage']=df['Description'].str.extract(r"((\d+) Square Feet|(\d+) sq. ft.|(\d+) sqft|(\d+) Sq. Ft.|(\d+) sq|(\d+(?:,\d+)?) Sq\. Ft\.|(\d+(?:,\d+)?) sq)")[0]
    df['Square Footage']=df['Square Footage'].replace({',':''},regex=True).str.replace(r'\D', '')
    
    df['Beds']=df['Description'].replace({'-':' ','total':''},regex=True).str.extract(r"(\d+) bed")
    
    
    df['Baths']=df['Description'].replace({'-':' ','total':''},regex=True).str.extract(r"((\d+) bath|(\d+(?:\.\d+)?) bath)")[0]
    df['Baths']=df['Baths'].str.extract(r'([\d.]+)').astype(float)
    
    df['Year Built']=df['Description'].str.extract(r"built in (\d{4})")
    
    df_final=df[df['Address'].notnull()]
    df_final=df_final[(df_final['Address'].str.contains(str(address_number))) & (df_final['Address'].str.contains(str(address_zip)))]

    df_final.insert(0,'Address Input',address)
    return df_final
    
def catch_errors(addresses):
    try: 
        return google_address(addresses,trial=True)
    except:
        return pd.DataFrame({'Address Input':[addresses]})


def process_multiple_address(addresses):
    results=Parallel(n_jobs=32, prefer="threads")(delayed(catch_errors)(i) for i in addresses)
    return results
    
  



st.set_page_config(layout="wide")
# col1, col2 = st.columns((2))
address_file = st.sidebar.radio('Choose',('Single Address', 'File'))

address = st.sidebar.text_input("Address", "190 Pebble Creek Dr Etna, OH 43062")
uploaded_file = st.sidebar.file_uploader("Choose a file")
# uploaded_file='C:/Users/mritchey/Documents/addresses 100 generated.xlsx'
return_sq = st.sidebar.radio('Return Only Results with Square Footage',('No', 'Yes'))


if address_file == 'File' and not None:
    try:
        df = pd.read_csv(uploaded_file)
    except:
        df = pd.read_excel(uploaded_file)
     
    address_cols=list(df.columns[:4])
    df[address_cols[-1]]=df[address_cols[-1]].astype(str).str[:5].astype(int).astype(str)
    df[address_cols[-1]]=df[address_cols[-1]].apply(lambda x: x.zfill(5))
    
    df['Address All']=df[address_cols[0]]+', '+df[address_cols[1]]+', '+df[address_cols[2]]+' '+df[address_cols[3]]
    
    results= process_multiple_address(df['Address All'].values)
    results=pd.concat(results).reset_index(drop=1)
    results.index=results.index+1

else:    
    results=google_address(address).reset_index(drop=1)
    results.index=results.index+1

    
    
results=results[['Address Input', 'Address', 'Website','Square Footage', 'Beds', 'Baths', 'Year Built',
 'Link', 'Description', 
      ]]

if return_sq=='Yes':
    results=results.query("`Square Footage`==`Square Footage`").reset_index(drop=1)
    results.index=results.index+1
    
st.dataframe(
    results,
    column_config={
   
        "Link": st.column_config.LinkColumn("Link"),
    },
    hide_index=True,
)

csv2 = convert_df(results)
st.download_button(
    label="Download data as CSV",
    data=csv2,
    file_name=f'{address}.csv',
    mime='text/csv')


st.markdown(""" <style>
#MainMenu {visibility: hidden;}
footer {visibility: hidden;}
</style> """, unsafe_allow_html=True)