From 3a677cc8618f925405f5d95b0a86405c7b6ffbf8 Mon Sep 17 00:00:00 2001
From: Vinicius Aguiar <vncsna@gmail.com>
Date: Fri, 6 Oct 2023 17:08:25 -0300
Subject: [PATCH] feat: migrate website storage blobs (#431)

---
 .../migrations/20231006_migrate_storage.py    | 45 +++++++++++++++++++
 1 file changed, 45 insertions(+)
 create mode 100644 scripts/migrations/20231006_migrate_storage.py

diff --git a/scripts/migrations/20231006_migrate_storage.py b/scripts/migrations/20231006_migrate_storage.py
new file mode 100644
index 00000000..fed2e90a
--- /dev/null
+++ b/scripts/migrations/20231006_migrate_storage.py
@@ -0,0 +1,45 @@
+# -*- coding: utf-8 -*-
+from os import getenv
+from pathlib import Path
+from re import findall
+
+import requests
+from google.cloud import storage
+
+bucket_name = getenv("BUCKET_NAME")
+source_path = Path(getenv("SOURCE_PATH", "."))
+
+url_prefix = "https://basedosdados-static.s3.us-east-2.amazonaws.com/"
+url_prefix_exp = r'(https:\/\/basedosdados-static\.s3\.us-east-2\.amazonaws\.com\/[^"]*)'
+
+
+def run():
+    """
+    Steps to execute:
+    - Set the environment variables
+    - Run the script
+    """
+
+    client = storage.Client()
+    bucket = client.bucket(bucket_name)
+
+    def download_and_upload(url, urlpath: Path, filepath: Path):
+        filepath.parent.mkdir(parents=True, exist_ok=True)
+        if not filepath.exists():
+            response = requests.get(url)
+            if response.status_code == 200:
+                with filepath.open("wb") as f:
+                    f.write(response.content)
+        if not bucket.blob(urlpath).exists():
+            blob = bucket.blob(urlpath)
+            blob.upload_from_filename(filepath)
+
+    for path in source_path.glob("**/*.html"):
+        for url in findall(url_prefix_exp, path.read_text()):
+            urlpath = url.replace(url_prefix, "").lower()
+            filepath = Path(".").resolve() / ".blobs" / urlpath
+            download_and_upload(url, urlpath, filepath)
+
+
+if __name__ == "__main__":
+    run()