Add ZillowGrabber

This commit is contained in:
tsb1995 2020-02-26 16:15:16 -08:00
parent e9649d9a8b
commit 84a701501d
6 changed files with 176 additions and 0 deletions

BIN
HousingData.xls Normal file

Binary file not shown.

139
ZillowGrabber.py Normal file
View File

@ -0,0 +1,139 @@
import numpy as np
import pandas as pd
import zillow
import configparser
from oauth2client.service_account import ServiceAccountCredentials
import os.path
from googleapiclient.discovery import build
from google_auth_oauthlib.flow import InstalledAppFlow
from google.auth.transport.requests import Request
import pickle
import datetime
# Open our config file
config = configparser.ConfigParser()
config.read('zillowkey.conf')
# Grab our key
key = config['DEFAULT']['zillowkey']
# Setup zillow api
api = zillow.ValuationApi()
# Load in our data and cut out irrelevant information
addresses = pd.read_excel('HousingData.xls')
address_df = addresses.loc[addresses['County'].isin(['Orange', 'Los Angeles', 'San Bernardino', 'Riverside'])]
address_df = addresses.loc[addresses['Status'].isin(['Postponed', 'Auction'])]
address_df = address_df.drop(['Original Principal Balance'], axis=1).dropna(subset=['Property Address', 'Zip'])
df = address_df.copy()
# Setup lists to be added to our dataframe from zillow api
zestimate = []
zillow_year_build = []
zillow_lot_size_sqft = []
zillow_bathrooms = []
zillow_bedrooms = []
# Go through each address, grab info, add it to our lists
for index, row in address_df.iterrows():
address = address_df['Property Address'][index].rstrip('\n')
postal_code = str(int(address_df['Zip'][index]))
try:
data = api.GetDeepSearchResults(key, address, postal_code)
datadict = data.get_dict()
zestimate.append(datadict['zestimate']['amount'])
zillow_year_build.append(datadict['extended_data']['year_built'])
zillow_lot_size_sqft.append(datadict['extended_data']['lot_size_sqft'])
zillow_bathrooms.append(datadict['extended_data']['bathrooms'])
zillow_bedrooms.append(datadict['extended_data']['bedrooms'])
except:
zestimate.append(None)
zillow_year_build.append(None)
zillow_lot_size_sqft.append(None)
zillow_bathrooms.append(None)
zillow_bedrooms.append(None)
# Create new columns in our dataframe from our lists
df['zestimate'] = zestimate
df['zillow_year_build'] = zillow_year_build
df['zillow_lot_size_sqft'] = zillow_lot_size_sqft
df['zillow_bathrooms'] = zillow_bathrooms
df['zillow_bedrooms'] = zillow_bedrooms
df.drop(columns=['State'], inplace=True)
df = df.fillna('None')
# If modifying these scopes, delete the file token.pickle.
SCOPES = ['https://www.googleapis.com/auth/spreadsheets']
# The ID and range of a sample spreadsheet.
sheet_name = "TEST"
range_ = "Sheet1!A:A"
# Name for sheet
d = datetime.datetime.today()
sheet_name = 'Housing ' + d.strftime('%d-%m-%Y')
def main():
creds = None
# The file token.pickle stores the user's access and refresh tokens, and is
# created automatically when the authorization flow completes for the first
# time.
if os.path.exists('token.pickle'):
with open('token.pickle', 'rb') as token:
creds = pickle.load(token)
# If there are no (valid) credentials available, let the user log in.
if not creds or not creds.valid:
if creds and creds.expired and creds.refresh_token:
creds.refresh(Request())
else:
flow = InstalledAppFlow.from_client_secrets_file(
'credentials.json', SCOPES)
creds = flow.run_local_server(port=0)
# Save the credentials for the next run
with open('token.pickle', 'wb') as token:
pickle.dump(creds, token)
service = build('sheets', 'v4', credentials=creds)
# Call the Sheets API
sheet = service.spreadsheets()
# Create new Sheet
spreadsheet = {
'properties': {
'title': sheet_name
}
}
spreadsheet = service.spreadsheets().create(body=spreadsheet,
fields='spreadsheetId').execute()
spreadsheet_id = spreadsheet.get('spreadsheetId')
print('Spreadsheet ID: {0}'.format(spreadsheet.get('spreadsheetId')))
# Fill in header
list = [df.columns.tolist()]
resource = {
"majorDimension": "ROWS",
"values": list
}
request = service.spreadsheets().values().append(spreadsheetId=spreadsheet_id, range=range_, body=resource,
valueInputOption="USER_ENTERED")
response = request.execute()
# Fill in body
list = df.values.tolist()
resource = {
"majorDimension": "ROWS",
"values": list
}
request = service.spreadsheets().values().append(spreadsheetId=spreadsheet_id, range=range_, body=resource,
valueInputOption="USER_ENTERED")
response = request.execute()
main()

33
ZillowGrabber.spec Normal file
View File

@ -0,0 +1,33 @@
# -*- mode: python ; coding: utf-8 -*-
block_cipher = None
a = Analysis(['ZillowGrabber.py'],
pathex=['C:\\Users\\TSB\\Desktop\\Zillow'],
binaries=[],
datas=[],
hiddenimports=[],
hookspath=[],
runtime_hooks=[],
excludes=[],
win_no_prefer_redirects=False,
win_private_assemblies=False,
cipher=block_cipher,
noarchive=False)
pyz = PYZ(a.pure, a.zipped_data,
cipher=block_cipher)
exe = EXE(pyz,
a.scripts,
a.binaries,
a.zipfiles,
a.datas,
[],
name='ZillowGrabber',
debug=False,
bootloader_ignore_signals=False,
strip=False,
upx=True,
upx_exclude=[],
runtime_tmpdir=None,
console=True )

Binary file not shown.

1
credentials.json Normal file
View File

@ -0,0 +1 @@
{"installed":{"client_id":"495919805073-o2o41tu9c9pv9mpo4ugjdcca6h5jg5u7.apps.googleusercontent.com","project_id":"zillowfun-1581659411719","auth_uri":"https://accounts.google.com/o/oauth2/auth","token_uri":"https://oauth2.googleapis.com/token","auth_provider_x509_cert_url":"https://www.googleapis.com/oauth2/v1/certs","client_secret":"HL2xQvsWITylqar1GsC8noW1","redirect_uris":["urn:ietf:wg:oauth:2.0:oob","http://localhost"]}}

3
zillowkey.conf Normal file
View File

@ -0,0 +1,3 @@
[DEFAULT]
zillowkey = X1-ZWz1bxj5x02juz_2rqd6