BUG: reading line-format JSON from file url #27135

doc/source/whatsnew/v1.1.0.rst

@@ -988,6 +988,7 @@ I/O
 - Bug in :meth:`~SQLDatabase.execute` was raising a ``ProgrammingError`` for some DB-API drivers when the SQL statement contained the `%` character and no parameters were present (:issue:`34211`)
 - Bug in :meth:`~pandas.io.stata.StataReader` which resulted in categorical variables with difference dtypes when reading data using an iterator. (:issue:`31544`)
 - :meth:`HDFStore.keys` has now an optional `include` parameter that allows the retrieval of all native HDF5 table names (:issue:`29916`)
+- :meth:`read_json` now could read line-delimited JSON from file url. (:issue:`27135`)
 
 Plotting
 ^^^^^^^^

pandas/io/json/_json.py

@@ -1,6 +1,6 @@
 from collections import abc
 import functools
-from io import StringIO
+from io import BytesIO, StringIO
 from itertools import islice
 import os
 from typing import Any, Callable, Optional, Type
@@ -724,6 +724,9 @@ def _get_data_from_filepath(self, filepath_or_buffer):
             self.should_close = True
             self.open_stream = data
 
+        if isinstance(data, BytesIO):
+            data = data.getvalue().decode()
+
         return data
 
     def _combine_lines(self, lines) -> str:

pandas/tests/io/json/data/line_delimited.json

@@ -0,0 +1,3 @@
+    {"a": 1, "b": 2}
+    {"a": 3, "b": 4}
+    {"a": 5, "b": 6}

pandas/tests/io/json/test_readlines.py

@@ -1,4 +1,5 @@
 from io import StringIO
+from pathlib import Path
 
 import pytest
 
@@ -219,3 +220,18 @@ def test_readjson_nrows_requires_lines():
     msg = "nrows can only be passed if lines=True"
     with pytest.raises(ValueError, match=msg):
         pd.read_json(jsonl, lines=False, nrows=2)
+
+
+def test_readjson_lines_chunks_fileurl(datapath):
+    # GH 27135
+    # Test reading line-format JSON from file url
+    df_list_expected = [
+        pd.DataFrame([[1, 2]], columns=["a", "b"], index=[0]),
+        pd.DataFrame([[3, 4]], columns=["a", "b"], index=[1]),
+        pd.DataFrame([[5, 6]], columns=["a", "b"], index=[2]),
+    ]
+    os_path = datapath("io", "json", "data", "line_delimited.json")
+    file_url = Path(os_path).as_uri()
+    url_reader = pd.read_json(file_url, lines=True, chunksize=1)
+    for index, chuck in enumerate(url_reader):
+        tm.assert_frame_equal(chuck, df_list_expected[index])