Merge remote-tracking branch 'origin/main' into linnealovespie/cleanup

.gitignore

@@ -5,3 +5,5 @@ geckodriver-*
 tmp/
 *.org~
 data/
+venv/
+*~

README.md

@@ -24,3 +24,15 @@ Relevant but not 1-1 walkthrough of how to programmatically find building owners
 [Washington State Corporations and Charities Filing Database (CCFS)](https://kingcounty.gov/en/dept/kcit/data-information-services/gis-center/property-research): For looking up a parcel owner name and finding the related business listing and related info.
 
 TODO: Find a good source for eviction filing data. Those with access can refer to the [potential data source list](https://docs.google.com/spreadsheets/d/1Ew0UrZvP-S74velkWSKaiSGBYcxIAoRH6IGpEzNWX6s/edit?gid=0#gid=0) to find new data sources.
+
+## Object Storage
+
+An S3 compatible storage is hosted on [minio.radmin.live](minio.radmin.live)
+
+SDK documentation: https://github.com/minio/minio-py/blob/master/docs/API.md
+
+Use `lib/minio_helper.py` to extend the functionality
+
+Run `test_minio` in `lib/main.py` to test out that it works (TODO: move this to own testing script, perhaps unit tests)
+
+Note: You will need to have access_key and secret_key in your env before running for this to work, contact @linnealovespie or @ammaratef45 to obtain these keys)

lib/.empty

@@ -0,0 +1 @@
+Well, not really empty, but it is for testing, please keep as is!

lib/main.py

@@ -0,0 +1,25 @@
+from minio_helper import MinioHelper
+
+def test_minio():
+    minio_helper = MinioHelper('evictorbook-seattle-data')
+    files_list = minio_helper.list_files()
+    print('listing current files stored in the bucket')
+    for file in files_list:
+        print(file)
+    print('adding a file then listing again')
+    minio_helper.upload('.empty')
+    files_list = minio_helper.list_files()
+    for file in files_list:
+        print(file)
+    print('deleting the file then listing again')
+    minio_helper.delete('.empty')
+    files_list = minio_helper.list_files()
+    for file in files_list:
+        print(file)
+    
+
+def main():
+    test_minio()
+
+if __name__ == '__main__':
+    main()

lib/minio_helper.py

@@ -0,0 +1,30 @@
+from minio import Minio
+import io
+import os
+
+class MinioHelper:
+
+    def __init__(self, bucket_name: str):
+        self.client = Minio(
+            "minio.radmin.live",
+            access_key=os.environ['access_key'],
+            secret_key=os.environ['secret_key']
+        )
+        self.bucket_name = bucket_name
+
+    def list_files(self):
+        return self.client.list_objects(self.bucket_name)
+
+    def upload(self, filepath: str):
+        with open(filepath, "rb") as fh:
+            buf = io.BytesIO(fh.read())
+            self.client.put_object(
+                self.bucket_name,
+                filepath,
+                buf,
+                length=-1,
+                part_size=10*1024*1024
+            )
+
+    def delete(self, filepath: str):
+        self.client.remove_object(self.bucket_name, filepath)

processors/requirements-conda.txt

@@ -0,0 +1,69 @@
+# This file may be used to create an environment using:
+# $ conda create --name <env> --file <this file>
+# platform: linux-64
+# created-by: conda 25.5.1
+_libgcc_mutex=0.1=main
+_openmp_mutex=5.1=1_gnu
+beautifulsoup4=4.13.5=py313h06a4308_0
+blas=1.0=mkl
+bottleneck=1.4.2=py313hf0014fa_0
+brotlicffi=1.0.9.2=py313h6a678d5_1
+bs4=4.13.5=py39hd3eb1b0_0
+bzip2=1.0.8=h5eee18b_6
+ca-certificates=2025.9.9=h06a4308_0
+certifi=2025.8.3=py313h06a4308_0
+cffi=2.0.0=pypi_0
+charset-normalizer=3.3.2=pyhd3eb1b0_0
+defusedxml=0.7.1=pyhd3eb1b0_0
+expat=2.7.1=h6a678d5_0
+idna=3.7=py313h06a4308_0
+intel-openmp=2025.0.0=h06a4308_1171
+ld_impl_linux-64=2.40=h12ee557_0
+libffi=3.4.4=h6a678d5_1
+libgcc-ng=11.2.0=h1234567_1
+libgomp=11.2.0=h1234567_1
+libmpdec=4.0.0=h5eee18b_0
+libstdcxx-ng=11.2.0=h1234567_1
+libuuid=1.41.5=h5eee18b_0
+libxcb=1.17.0=h9b100fa_0
+libzlib=1.3.1=hb25bd0a_0
+mkl=2025.0.0=hacee8c2_941
+mkl-service=2.4.0=py313h5eee18b_3
+mkl_fft=1.3.11=py313hacdc0fc_1
+mkl_random=1.2.8=py313h8928b4f_1
+ncurses=6.5=h7934f7d_0
+numexpr=2.11.0=py313h41d4191_1
+numpy=2.3.3=py313h720eef7_0
+numpy-base=2.3.3=py313h95072fd_0
+odfpy=1.4.1=pyhd8ed1ab_1
+openssl=3.0.17=h5eee18b_0
+pandas=2.3.2=py313h280b501_0
+pip=25.2=pyhc872135_0
+pthread-stubs=0.3=h0ce48e5_1
+pycparser=2.23=py313h06a4308_0
+pysocks=1.7.1=py313h06a4308_0
+python=3.13.7=h7e8bc2b_100_cp313
+python-dateutil=2.9.0post0=py313h06a4308_2
+python-tzdata=2025.2=pyhd3eb1b0_0
+python_abi=3.13=1_cp313
+pytz=2025.2=py313h06a4308_0
+readline=8.3=hc2a1206_0
+requests=2.32.5=py313h06a4308_0
+setuptools=72.1.0=py313h06a4308_0
+six=1.17.0=py313h06a4308_0
+soupsieve=2.5=py313h06a4308_0
+sqlite=3.50.2=hb25bd0a_1
+tbb=2022.0.0=hdb19cb5_0
+tbb-devel=2022.0.0=hdb19cb5_0
+tk=8.6.15=h54e0aa7_0
+typing-extensions=4.15.0=py313h06a4308_0
+typing_extensions=4.15.0=py313h06a4308_0
+tzdata=2025b=h04d1e81_0
+urllib3=2.5.0=py313h06a4308_0
+wheel=0.45.1=py313h06a4308_0
+xorg-libx11=1.8.12=h9b100fa_1
+xorg-libxau=1.0.12=h9b100fa_0
+xorg-libxdmcp=1.1.5=h9b100fa_0
+xorg-xorgproto=2024.1=h5eee18b_1
+xz=5.6.4=h5eee18b_1
+zlib=1.3.1=hb25bd0a_0

requirements.txt

@@ -2,7 +2,6 @@ beautifulsoup4==4.13.5
 Bottleneck==1.4.2
 brotlicffi==1.0.9.2
 certifi==2025.8.3
-cffi==1.17.1
 charset-normalizer==3.3.2
 defusedxml==0.7.1
 idna==3.7
@@ -26,3 +25,8 @@ typing_extensions==4.15.0
 tzdata==2025.2
 urllib3==2.5.0
 wheel==0.45.1
+argon2-cffi==25.1.0
+argon2-cffi-bindings==25.1.0
+cffi==2.0.0
+minio==7.2.16
+pycryptodome==3.23.0