From 982dd3c5982b6c5e5dfb28a9f732a940607def0a Mon Sep 17 00:00:00 2001
From: Jun-te Kim <junte@domna.homes>
Date: Wed, 16 Jul 2025 14:55:16 +0000
Subject: [PATCH] example for khalim

---
 etl/read_stuff_from_s3_example.py | 40 +++++++++++++++++
 poetry.lock                       | 72 ++++++++++++++++++++++++++++++-
 pyproject.toml                    |  1 +
 3 files changed, 112 insertions(+), 1 deletion(-)
 create mode 100644 etl/read_stuff_from_s3_example.py

diff --git a/etl/read_stuff_from_s3_example.py b/etl/read_stuff_from_s3_example.py
new file mode 100644
index 0000000..cb427ba
--- /dev/null
+++ b/etl/read_stuff_from_s3_example.py
@@ -0,0 +1,40 @@
+import boto3
+import os
+
+def split_s3_url(s3_url):
+    if not s3_url.startswith("s3://"):
+        raise ValueError("Invalid S3 URL. Must start with 's3://'")
+
+    path = s3_url[5:]
+    parts = path.split('/', 1)
+
+    if len(parts) != 2:
+        raise ValueError("S3 URL must include a key after the bucket name")
+    return parts[0], parts[1]
+
+def create_temp_file(content_bytes, relative_path):
+    # Save under /tmp/s3/
+    full_path = os.path.join("/tmp/s3", relative_path)
+
+    # Make sure the directory exists
+    os.makedirs(os.path.dirname(full_path), exist_ok=True)
+
+    # Write content to file
+    with open(full_path, 'wb') as temp_file:
+        temp_file.write(content_bytes)
+
+    print(f"Temporary file created at: {full_path}")
+    return full_path
+
+def download_data_from_s3(s3_uri):
+    s3 = boto3.resource('s3')
+    bucket_name, file_name = split_s3_url(s3_uri)
+
+    obj = s3.Object(bucket_name, file_name)
+    data = obj.get()['Body'].read()
+
+    # Save using full S3 key as relative path
+    return create_temp_file(data, file_name)
+
+# Example usage
+download_data_from_s3("s3://retrofit-energy-assessments-dev/JAFFERSONS ENERGY CONSULTANTS/VDE001/12103116/docs & plans/77 Perryn Road, W3 7LT EPR.pdf")
diff --git a/poetry.lock b/poetry.lock
index 62d14e9..0074416 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -84,6 +84,46 @@ charset-normalizer = ["charset-normalizer"]
 html5lib = ["html5lib"]
 lxml = ["lxml"]
 
+[[package]]
+name = "boto3"
+version = "1.39.6"
+description = "The AWS SDK for Python"
+optional = false
+python-versions = ">=3.9"
+groups = ["main"]
+files = [
+    {file = "boto3-1.39.6-py3-none-any.whl", hash = "sha256:db965dc9019df7b1d20e8d8ab7a653956f275865175a8652419ebfd03de03d83"},
+    {file = "boto3-1.39.6.tar.gz", hash = "sha256:e75bfcd444e199767642f28ef8dc4f972846dc3118e48a7e09f9c458dae2021e"},
+]
+
+[package.dependencies]
+botocore = ">=1.39.6,<1.40.0"
+jmespath = ">=0.7.1,<2.0.0"
+s3transfer = ">=0.13.0,<0.14.0"
+
+[package.extras]
+crt = ["botocore[crt] (>=1.21.0,<2.0a0)"]
+
+[[package]]
+name = "botocore"
+version = "1.39.6"
+description = "Low-level, data-driven core of boto 3."
+optional = false
+python-versions = ">=3.9"
+groups = ["main"]
+files = [
+    {file = "botocore-1.39.6-py3-none-any.whl", hash = "sha256:9c002724e9b97cec610dbbb3bb019b3248ff6bf58407835621f0461e740af90b"},
+    {file = "botocore-1.39.6.tar.gz", hash = "sha256:d3a6c207d233ddee3289c1d56646047bef18b21a1faebb3d83a6fca149fd0f59"},
+]
+
+[package.dependencies]
+jmespath = ">=0.7.1,<2.0.0"
+python-dateutil = ">=2.1,<3.0.0"
+urllib3 = {version = ">=1.25.4,<2.2.0 || >2.2.0,<3", markers = "python_version >= \"3.10\""}
+
+[package.extras]
+crt = ["awscrt (==0.23.8)"]
+
 [[package]]
 name = "certifi"
 version = "2025.4.26"
@@ -717,6 +757,18 @@ docs = ["Jinja2 (==2.11.3)", "MarkupSafe (==1.1.1)", "Pygments (==2.8.1)", "alab
 qa = ["flake8 (==5.0.4)", "mypy (==0.971)", "types-setuptools (==67.2.0.1)"]
 testing = ["Django", "attrs", "colorama", "docopt", "pytest (<9.0.0)"]
 
+[[package]]
+name = "jmespath"
+version = "1.0.1"
+description = "JSON Matching Expressions"
+optional = false
+python-versions = ">=3.7"
+groups = ["main"]
+files = [
+    {file = "jmespath-1.0.1-py3-none-any.whl", hash = "sha256:02e2e4cc71b5bcab88332eebf907519190dd9e6e82107fa7f83b1003a6252980"},
+    {file = "jmespath-1.0.1.tar.gz", hash = "sha256:90261b206d6defd58fdd5e85f478bf633a2901798906be2ad389150c5c60edbe"},
+]
+
 [[package]]
 name = "jupyter-client"
 version = "8.6.3"
@@ -1682,6 +1734,24 @@ urllib3 = ">=1.21.1,<3"
 socks = ["PySocks (>=1.5.6,!=1.5.7)"]
 use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"]
 
+[[package]]
+name = "s3transfer"
+version = "0.13.0"
+description = "An Amazon S3 Transfer Manager"
+optional = false
+python-versions = ">=3.9"
+groups = ["main"]
+files = [
+    {file = "s3transfer-0.13.0-py3-none-any.whl", hash = "sha256:0148ef34d6dd964d0d8cf4311b2b21c474693e57c2e069ec708ce043d2b527be"},
+    {file = "s3transfer-0.13.0.tar.gz", hash = "sha256:f5e6db74eb7776a37208001113ea7aa97695368242b364d73e91c981ac522177"},
+]
+
+[package.dependencies]
+botocore = ">=1.37.4,<2.0a.0"
+
+[package.extras]
+crt = ["botocore[crt] (>=1.37.4,<2.0a.0)"]
+
 [[package]]
 name = "six"
 version = "1.17.0"
@@ -1969,4 +2039,4 @@ files = [
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.12"
-content-hash = "1d5c1e0bfc12e88ca9b4c46141c848064a45e9cc4b60990fa3ec7ecb5ef71209"
+content-hash = "7f71e898554f0285d708a349589cc96fe8cfc210e7d39caf66c1dc6faae010da"
diff --git a/pyproject.toml b/pyproject.toml
index 56b1bb8..84c15cd 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -23,6 +23,7 @@ dependencies = [
     "beautifulsoup4 (>=4.13.4,<5.0.0)",
     "tqdm (>=4.67.1,<5.0.0)",
     "hubspot-api-client (>=12.0.0,<13.0.0)",
+    "boto3 (>=1.39.6,<2.0.0)",
 ]
 
 [tool.poetry]