Public Bucket Read Test

Author: alimcmaster1

pandas/io/s3.py

@@ -16,8 +16,8 @@ def _strip_schema(url):
     return result.netloc + result.path
 
 
-def get_fs():
-    return s3fs.S3FileSystem(anon=False)
+def get_fs(anon: bool = False):
+    return s3fs.S3FileSystem(anon=anon)
 
 
 def get_file_and_filesystem(
@@ -38,7 +38,7 @@ def get_file_and_filesystem(
         # aren't valid for that bucket.
         # A NoCredentialsError is raised if you don't have creds
         # for that bucket.
-        fs = get_fs()
+        fs = get_fs(anon=True)
         file = fs.open(_strip_schema(filepath_or_buffer), mode)
     return file, fs
 

pandas/tests/io/test_s3.py

@@ -2,7 +2,10 @@
 
 import pytest
 
+import pandas.util._test_decorators as td
+
 from pandas import read_csv
+import pandas._testing as tm
 
 from pandas.io.common import is_s3_url
 
@@ -23,3 +26,10 @@ def test_streaming_s3_objects():
     for el in data:
         body = StreamingBody(BytesIO(el), content_length=len(el))
         read_csv(body)
+
+
+@tm.network
+@td.skip_if_no("s3fs")
+def test_read_without_creds_from_pub_bucket():
+    result = read_csv("s3://gdelt-open-data/events/1981.csv", nrows=3)
+    assert len(result) == 3