Upload 3 files

addresses 100 generated.csv

@@ -0,0 +1,80 @@
+Address1,City,State,Zipcode
+123 Main St,Chicago,IL,60001
+245 Oak Ave,New York,NY,10001
+356 Pine Rd,Los Angeles,CA,90001
+467 Elm St,Houston,TX,70001
+578 Maple Ave,Philadelphia,PA,19101
+689 Cherry St,Phoenix,AZ,85001
+178 Oak Dr,San Diego,CA,92101
+286 Pine Crt,San Jose,CA,95101
+395 Elm Ln,Austin,TX,78751
+504 Maple Way,Jacksonville,FL,32204
+613 Cherry Pl,Fort Worth,TX,76104
+722 Oak Blvd,Dallas,TX,75201
+831 Pine St,San Antonio,TX,78201
+940 Elm Rd,Indianapolis,IN,46201
+1051 Maple Cir,San Francisco,CA,94101
+1162 Cherry Dr,Columbus,OH,43201
+1273 Oak Way,Charlotte,NC,28201
+1384 Pine Ct,Detroit,MI,48201
+1495 Elm Pl,El Paso,TX,79901
+1606 Maple St,Memphis,TN,38101
+1717 Cherry Ave,Boston,MA,2110
+1828 Oak Pl,Nashville,TN,37201
+1939 Pine Dr,Baltimore,MD,21201
+2050 Elm St,Louisville,KY,40201
+2161 Maple Pl,Portland,OR,97201
+2272 Cherry Way,Oklahoma City,OK,73101
+2383 Oak Rd,Milwaukee,WI,53201
+2494 Pine Cir,Albuquerque,NM,87101
+2605 Elm Dr,Tucson,AZ,85704
+2716 Maple Ave,Fresno,CA,93701
+2827 Cherry Rd,Sacramento,CA,95814
+2938 Oak St,Kansas City,MO,64105
+3049 Pine Ln,Mesa,AZ,85201
+3160 Elm Way,Virginia Beach,VA,23450
+3271 Maple St,Atlanta,GA,30301
+3382 Cherry Cir,Colorado Springs,CO,80903
+3493 Oak Pl,Raleigh,NC,27601
+3604 Pine Dr,Omaha,NE,68101
+3715 Elm Way,Miami,FL,33101
+3826 Maple Ln,Tulsa,OK,74101
+3937 Cherry Ct,Minneapolis,MN,55401
+4048 Oak Rd,Cleveland,OH,44101
+4159 Pine St,Wichita,KS,67201
+4270 Elm St,Arlington,TX,76001
+4381 Maple Pl,New Orleans,LA,70101
+4492 Cherry Ct,Bakersfield,CA,93301
+4603 Oak Ave,Honolulu,HI,96801
+4714 Pine Dr,Tampa,FL,33602
+4825 Elm Way,Anaheim,CA,92801
+4936 Maple St,Aurora,CO,80011
+5047 Cherry Rd,Santa Ana,CA,92703
+5158 Oak Dr,St. Louis,MO,63108
+5269 Pine St,Riverside,CA,92501
+5380 Elm Way,Corpus Christi,TX,78401
+5491 Maple Pl,Lexington,KY,40516
+6602 Cherry Ct,Lincoln,NE,68521
+6713 Oak Rd,Stockton,CA,95201
+6824 Pine Cir,Henderson,NV,89011
+6935 Elm Dr,Cincinnati,OH,45202
+7046 Maple St,Pittsburgh,PA,15203
+7157 Cherry Ave,Saint Paul,MN,55101
+7268 Oak Pl,Toledo,OH,43604
+7379 Pine Dr,Newark,NJ,7101
+7490 Elm Way,Greensboro,NC,27401
+7501 Maple Ln,Plano,TX,75023
+7612 Cherry Ct,Richmond,VA,23219
+7723 Oak Rd,Buffalo,NY,14202
+7834 Pine St,Fort Wayne,IN,46802
+7945 Elm St,Jersey City,NJ,7301
+8056 Maple Pl,Chula Vista,CA,91911
+8167 Cherry Way,Norfolk,VA,23501
+8278 Oak Rd,Orlando,FL,32801
+8389 Pine Cir,Akron,OH,44301
+8500 Elm Dr,Huntington Beach,CA,92648
+8611 Maple St,Durham,NC,27701
+8722 Cherry Rd,Rochester,NY,14601
+8833 Oak St,Garland,TX,75041
+8944 Pine Ln,Eugene,OR,97401
+8055 Elm Way,Chandler,AZ,85225

app.py

@@ -0,0 +1,110 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Tue Oct 24 12:51:42 2023
+
+@author: mritchey
+"""
+import pandas as pd
+import requests
+from urllib.parse import urlparse, quote
+import re
+from bs4 import BeautifulSoup
+from joblib import Parallel, delayed
+import gradio as gr
+from io import StringIO
+
+default_csv = "addresses 100 generated.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 process_csv_text(temp_file):
+    if isinstance(temp_file, str):
+      df = pd.read_csv(StringIO(temp_file))
+    else:
+      df = pd.read_csv(temp_file.name)
+      
+    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]]
+    return df
+
+def process_multiple_address(addresses):
+    results=Parallel(n_jobs=-1, prefer="threads")(delayed(google_address)(i) for i in addresses)
+    return results
+
+def feed_process_multiple(temp_file):
+    df=process_csv_text(temp_file)
+    addresses=df['Address All'].to_list()
+    results=process_multiple_address(addresses)
+    results=pd.concat(results)
+    return results
+
+
+with gr.Blocks() as demo:
+    upload_button = gr.UploadButton(label="Upload Addresses", file_types = ['.csv'], live=True, file_count = "single")    
+    table = gr.Dataframe(headers=['Address Input', 'Title', 'Link', 'Description', 'Address', 'Website',
+       'Square Footage', 'Beds', 'Baths', 'Year Built'], type="pandas", col_count=10)
+    upload_button.upload(fn=feed_process_multiple, inputs=upload_button, 
+                         outputs=table, api_name="Address Scrap")
+  
+   
+demo.launch()
+

requirements.txt

@@ -0,0 +1,5 @@
+beautifulsoup4==4.12.2
+gradio==3.50.2
+joblib==1.1.0
+pandas==1.5.2
+requests==2.27.1