From 7a177b38c9a2f0fab00df8db2873222519d3936f Mon Sep 17 00:00:00 2001
From: moshferatu <gitea@steveharris.sh>
Date: Sun, 2 Jul 2023 05:14:43 -0700
Subject: [PATCH] Initial commit of script to automate the download of SPX
 options quotes

---
 Dockerfile             |  5 +++++
 download_spx_quotes.py | 48 ++++++++++++++++++++++++++++++++++++++++++
 requirements.txt       |  4 ++++
 3 files changed, 57 insertions(+)
 create mode 100644 Dockerfile
 create mode 100644 download_spx_quotes.py
 create mode 100644 requirements.txt

diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..836cbc5
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,5 @@
+FROM python:3.10
+COPY download_spx_quotes.py .
+COPY requirements.txt .
+RUN pip install -r requirements.txt
+CMD ["python", "./download_spx_quotes.py"]
\ No newline at end of file
diff --git a/download_spx_quotes.py b/download_spx_quotes.py
new file mode 100644
index 0000000..d6ebc92
--- /dev/null
+++ b/download_spx_quotes.py
@@ -0,0 +1,48 @@
+import os
+import pandas as pd
+import paramiko
+import schedule
+import time
+import zipfile
+
+quotes_directory = os.environ['DOWNLOAD_DIRECTORY']
+download_directory = quotes_directory + 'Zip Archive/'
+
+def process_file(file: str):
+    quote_data = pd.read_csv(file)
+    current_date = quote_data.iloc[0]['quote_datetime'][:10]
+    zero_dte_quotes = quote_data[(quote_data['expiration'] == current_date) & (quote_data['root'] == 'SPXW')]
+    if not zero_dte_quotes.empty:
+        zero_dte_quotes.to_csv(os.path.join(quotes_directory, current_date[:4], current_date + '.csv'), index=False)
+
+def download_quotes():
+    client = paramiko.SSHClient()
+    client.set_missing_host_key_policy(paramiko.AutoAddPolicy())
+    client.connect(
+        hostname='sftp.datashop.livevol.com', 
+        username=os.environ['USER'], 
+        password=os.environ['PASSWORD']
+    )
+    sftp = client.open_sftp()
+    sftp.chdir('./subscriptions/' + os.environ['ORDER'] + '/' + os.environ['ITEM'])
+    files = sftp.listdir()
+    for file in files:
+        local_file = download_directory + file
+        if not os.path.exists(local_file):
+            print('Downloading', file)
+            sftp.get(file, local_file)
+            with zipfile.ZipFile(local_file, 'r') as zip_file:
+                print('Extracting', file)
+                zip_file.extractall(download_directory)
+                extracted_file = local_file.replace('.zip', '.csv')
+                print('Processing', extracted_file)
+                process_file(extracted_file)
+                print('Deleting', extracted_file)
+                os.remove(extracted_file)
+    client.close()
+
+if __name__ == '__main__':
+    schedule.every().day.at('04:00', 'America/Los_Angeles').do(download_quotes)
+    while True:
+        schedule.run_pending()
+        time.sleep(1)
\ No newline at end of file
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..64f7c4b
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,4 @@
+pandas
+paramiko
+pytz
+schedule
\ No newline at end of file