import pandas as pd 
from palmerpenguins import load_penguins 

penguins = load_penguins()
penguins['ID'] = penguins.reset_index().index + 1
penguins.head()

import pandas as pd 
from palmerpenguins import load_penguins 

penguins = load_penguins()
penguins['ID'] = penguins.reset_index().index + 1
penguins.head()

import seaborn as sns
import pandas as pd

iris_df = sns.load_dataset("iris")
iris_df.head()

import pandas as pd

data = [
    {"year": 2020, "month": 1, "week": 2, "company" : "A회사", "revenue_pct" : 49},
    {"year": 2020, "month": 1, "week": 2, "company" : "B회사", "revenue_pct" : 51},
    {"year": 2021, "month": 1, "week": 2, "company" : "A회사", "revenue_pct" : 37},
    {"year": 2021, "month": 1, "week": 2, "company" : "B회사", "revenue_pct" : 63},
    {"year": 2022, "month": 12, "week": 1, "company" : "A회사", "revenue_pct" : 70},
    {"year": 2022, "month": 12, "week": 1, "company" : "B회사", "revenue_pct" : 30},
]

df = pd.DataFrame(data)
df

df["date"] = pd.to_datetime(df["year"].astype(str) + df["week"].astype(str) + '1', format="%Y%W%w")
df

df["date"] = pd.to_datetime(df["year"].astype(str) + "-" + df["month"].astype(str))
df["date"] = df["date"] + pd.to_timedelta(df["week"] * 7 - 6, unit="D")
df

# .streamlit/secrets.toml
[public_data_api]
seoul_api_key = 'your_api_key'

[gcp_service_account]
type = "service_account"
project_id = "your_project_id"
private_key_id = "your_private_key_id"
private_key = "your_private_key"
client_email = "your_client_email"
client_id = "your_client_id"
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_x509_cert_url = "your_client_x509_cert_url"

import streamlit as st
from google.oauth2 import service_account

SERVICE_KEY = st.secrets.public_data_api.seoul_api_key

# Create API client.
credentials = service_account.Credentials.from_service_account_info(
    # Very Important Point
    st.secrets["gcp_service_account"]
)

# -*- coding:utf-8 -*-
import requests
import pandas as pd

# Google Cloud
from google.cloud import bigquery
import pandas_gbq

# API Key Settings
from utils import credentials, SERVICE_KEY
client = bigquery.Client(credentials=credentials)

def aptCrawling(SERVICE_KEY):
    data = None
    for j in range(1,2):
        url = f'http://openapi.seoul.go.kr:8088/{SERVICE_KEY}/json/tbLnOpendataRtmsV/{1+((j-1)*1000)}/{j*1000}'
        print(url)
        req = requests.get(url)
        content = req.json()
        con = content['tbLnOpendataRtmsV']['row']
        result = pd.DataFrame(con)
        data = pd.concat([data, result])
    data = data.reset_index(drop=True)
    data['DEAL_YMD'] = pd.to_datetime(data['DEAL_YMD'], format=("%Y%m%d"))

    return data

def save2BQ(data):
    table_name = "seoul.realestate"
    project_id = "streamlit-dashboard-369600"

    # Save the DataFrame to BigQuery
    pandas_gbq.to_gbq(data,
                      table_name,
                      project_id=project_id, if_exists='replace')

if __name__ == "__main__":
    data = aptCrawling(SERVICE_KEY)
    save2BQ(data)

$ python aptCrawling.py
http://openapi.seoul.go.kr:8088/your_api_key/json/tbLnOpendataRtmsV/1/1000
100%|████████████████████████████████████████████████████████████| 1/1 [00:00<?, ?it/s]

$ virtualenv venv
created virtual environment CPython3.9.13.final.0-64 in 606ms
  creator CPython3Windows(dest=C:\Users\YONSAI\Desktop\streamlit-korean-fonts\venv, clear=False, no_vcs_ignore=False, global=False)
  seeder FromAppData(download=False, pip=bundle, setuptools=bundle, wheel=bundle, via=copy, app_data_dir=C:\Users\YONSAI\AppData\Local\pypa\virtualenv)
    added seed packages: pip==23.1.2, setuptools==67.6.1, wheel==0.40.0
  activators BashActivator,BatchActivator,FishActivator,NushellActivator,PowerShellActivator,PythonActivator
$ source venv/Scripts/activate
(venv)
$