From c3ba631d66887cf5c5c7c871310369e6a705fba0 Mon Sep 17 00:00:00 2001
From: Nicolay <ndmoiseev@edu.hse.ru>
Date: Tue, 25 Mar 2025 19:19:44 +0300
Subject: [PATCH] feat: add s3 saving
---
.env-example | 3 +
.gitignore | 174 +++++++++++++++++++++++++++++++++++++++++++++++++++
s3_saving.py | 80 +++++++++++++++++++++++
3 files changed, 257 insertions(+)
create mode 100644 .env-example
create mode 100644 .gitignore
create mode 100644 s3_saving.py
diff --git a/.env-example b/.env-example
new file mode 100644
index 0000000..676db4c
--- /dev/null
+++ b/.env-example
@@ -0,0 +1,3 @@
+MINIO_ENDPOINT=
+MINIO_ACCESS_KEY=
+MINIO_SECRET_KEY=
\ No newline at end of file
diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..fe2425e
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,174 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+# Usually these files are written by a python script from a template
+# before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+# For a library or package, you might want to ignore these files since the code is
+# intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+# However, in case of collaboration, if having platform-specific dependencies or dependencies
+# having no cross-platform support, pipenv may install dependencies that don't work, or not
+# install all needed dependencies.
+#Pipfile.lock
+
+# UV
+# Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+# This is especially recommended for binary packages to ensure reproducibility, and is more
+# commonly ignored for libraries.
+#uv.lock
+
+# poetry
+# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+# This is especially recommended for binary packages to ensure reproducibility, and is more
+# commonly ignored for libraries.
+# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+# in version control.
+# https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+# and can be added to the global gitignore or merged into this file. For a more nuclear
+# option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
\ No newline at end of file
diff --git a/s3_saving.py b/s3_saving.py
new file mode 100644
index 0000000..cadb354
--- /dev/null
+++ b/s3_saving.py
@@ -0,0 +1,80 @@
+import os
+from io import BytesIO
+
+from PIL import Image
+from dotenv import load_dotenv
+from minio import Minio
+
+import streetview
+from routeparser import get_points_from_coordinates
+
+
+class Config:
+ MINIO_ENDPOINT: str
+ MINIO_ACCESS_KEY: str
+ MINIO_SECRET_KEY: str
+
+
+def load_config(env_path: str = ".env") -> Config:
+ if os.path.exists(env_path):
+ load_dotenv(env_path)
+
+ cfg = Config()
+
+ cfg.MINIO_ENDPOINT = os.getenv("MINIO_ENDPOINT")
+ cfg.MINIO_ACCESS_KEY = os.getenv("MINIO_ACCESS_KEY")
+ cfg.MINIO_SECRET_KEY = os.getenv("MINIO_SECRET_KEY")
+
+ return cfg
+
+
+def download_s3(
+ start_lat: float,
+ start_lon: float,
+ end_lat: float,
+ end_lon: float,
+ minio_client: Minio,
+ bucket_name: str,
+ folder_name: str
+):
+ points = get_points_from_coordinates(start_lat, start_lon, end_lat, end_lon)
+ panoids_buffer = []
+ print(len(points))
+
+ for point in points:
+ panoids = streetview.panoids(lat=point[0], lon=point[1], closest=True)
+
+ if len(panoids) == 0 or panoids[-1]["panoid"] in panoids_buffer:
+ continue
+
+ panorama = streetview.download_panorama_v3(panoids[-1]['panoid'], zoom=2, disp=False)
+ panoids_buffer.append(panoids[-1]['panoid'])
+ image = Image.fromarray(panorama)
+ buf = BytesIO()
+ image.save(buf, format='PNG')
+ buf.seek(0)
+
+ minio_client.put_object(
+ bucket_name,
+ f"{folder_name}/{panoids[-1]['lat']}_{panoids[-1]['lon']}.png",
+ buf,
+ buf.getbuffer().nbytes,
+ content_type="image/png"
+ )
+
+ return len(points)
+
+
+if __name__ == "__main__":
+ config = load_config()
+
+ lat, lon = 55.61727443131236, 37.61265372859094
+ lat2, lon2 = 55.618037091058774, 37.61304548448152
+
+ minio_client = Minio(
+ endpoint=config.MINIO_ENDPOINT,
+ access_key=config.MINIO_ACCESS_KEY,
+ secret_key=config.MINIO_SECRET_KEY
+ )
+
+ download_s3(lat, lon, lat2, lon2, minio_client, "test", "industrial_images")
--
GitLab