jsonunwrap 0.1.0__tar.gz

jsonunwrap-0.1.0/PKG-INFO

@@ -0,0 +1,28 @@
+Metadata-Version: 2.4
+Name: jsonunwrap
+Version: 0.1.0
+Summary: A small python package that unpacks data from a JSON url and converts it into a csv file.
+Author-email: njuedominic <njuemugodominic@gmail.com>
+Project-URL: Homepage, https://github.com/njuedominic/json-unwrap
+Project-URL: Bug Tracker, https://github.com/njuedominic/json-unwrap/issues
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >3.8
+Description-Content-Type: text/markdown
+Requires-Dist: requests>=2.28.0
+Requires-Dist: pandas>=2.0.0
+
+### JSON Unwrap
+A small python package that unpacks data from a JSON url and converts it into a csv file.
+
+### Current features
+* Convert one JSON url to a csv
+* Automatically creates a data folder if it does not exist
+
+### Roadmap
+* Custom file names for output csv
+* Convert into a dataframe ready for use in a notebook environment
+* Error handling for a failed url
+* Tests
+* Documentation examples

jsonunwrap-0.1.0/README.md

@@ -0,0 +1,13 @@
+### JSON Unwrap
+A small python package that unpacks data from a JSON url and converts it into a csv file.
+
+### Current features
+* Convert one JSON url to a csv
+* Automatically creates a data folder if it does not exist
+
+### Roadmap
+* Custom file names for output csv
+* Convert into a dataframe ready for use in a notebook environment
+* Error handling for a failed url
+* Tests
+* Documentation examples

jsonunwrap-0.1.0/json_unwrap/__init__.py

@@ -0,0 +1,8 @@
+# Import main functions 
+from .core import unwrap_data, fetch_json, json_to_csv
+
+# Define the version of the package
+
+__version__ = '0.1.0'
+
+__all__ = ['unwrap_data', 'fetch_json', 'json_to_csv']

jsonunwrap-0.1.0/json_unwrap/core.py

@@ -0,0 +1,79 @@
+"""
+This module contains the core functionality for the json_unwrap package.
+The main function is `json_to_csv`, which converts a JSON file to a CSV file.
+"""
+import os
+from typing import Any, Dict, List, Union
+import pandas as pd
+import requests
+
+def unwrap_data(data: Union[Dict[str, Any], List[Any]]) -> pd.DataFrame:
+    """
+    Normalizes and deeply flattens semi-structured JSON data into a pandas DataFrame.
+    """
+    # Simply convert a single dictionary into a list containing that dictionary
+    if isinstance(data, dict):
+        main_data = [data]
+    else:
+        main_data = data
+
+    # Perform the initial normalization
+    df = pd.json_normalize(main_data)
+
+    # Automatically iterate through the columns and deeply flatten any nested structures
+    changed = True
+    while changed:
+        changed = False
+        for col in list(df.columns):
+            # Explode lists
+            if any(isinstance(val, list) for val in df[col].dropna()):
+                df = df.explode(col)
+                changed = True
+                break  # Refresh columns list after structural changes
+
+            # Normalize and merge nested dictionaries
+            if any(isinstance(val, dict) for val in df[col].dropna()):
+                nested_df = pd.json_normalize(df[col]).set_index(df.index)
+                df = df.drop(columns=[col]).join(nested_df, rsuffix=f"_{col}")
+                changed = True
+                break
+                
+    return df
+
+ 
+def fetch_json(url: str, **kwargs: Any) -> Union[Dict[str, Any], List[Any]]:
+    """
+    Fetches raw JSON data from a URL.
+    
+    Args:
+        url: The endpoint web target.
+        **kwargs: Additional arguments passed directly to requests.get (e.g., headers, auth).
+    """
+    response = requests.get(url, **kwargs)
+    response.raise_for_status()
+    return response.json()
+
+
+def json_to_csv(url: str, output_path: str) -> pd.DataFrame:
+    """
+    Fetches JSON from a URL, deeply flattens it, and saves it directly to a CSV file.
+    
+    Args:
+        url: The endpoint URL containing the target JSON data.
+        output_path: Target filesystem path where the CSV will be written.
+        
+    Returns:
+        The generated pandas DataFrame.
+    """
+    # Ensure the parent output directory exists safely
+    directory = os.path.dirname(output_path)
+    if directory:
+        os.makedirs(directory, exist_ok=True)
+        
+    raw_data = fetch_json(url)
+    df = unwrap_data(raw_data)
+    
+    df.to_csv(output_path, index=False)
+    return df
+
+

jsonunwrap-0.1.0/jsonunwrap.egg-info/PKG-INFO

@@ -0,0 +1,28 @@
+Metadata-Version: 2.4
+Name: jsonunwrap
+Version: 0.1.0
+Summary: A small python package that unpacks data from a JSON url and converts it into a csv file.
+Author-email: njuedominic <njuemugodominic@gmail.com>
+Project-URL: Homepage, https://github.com/njuedominic/json-unwrap
+Project-URL: Bug Tracker, https://github.com/njuedominic/json-unwrap/issues
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >3.8
+Description-Content-Type: text/markdown
+Requires-Dist: requests>=2.28.0
+Requires-Dist: pandas>=2.0.0
+
+### JSON Unwrap
+A small python package that unpacks data from a JSON url and converts it into a csv file.
+
+### Current features
+* Convert one JSON url to a csv
+* Automatically creates a data folder if it does not exist
+
+### Roadmap
+* Custom file names for output csv
+* Convert into a dataframe ready for use in a notebook environment
+* Error handling for a failed url
+* Tests
+* Documentation examples

jsonunwrap-0.1.0/jsonunwrap.egg-info/SOURCES.txt

@@ -0,0 +1,10 @@
+README.md
+pyproject.toml
+json_unwrap/__init__.py
+json_unwrap/core.py
+jsonunwrap.egg-info/PKG-INFO
+jsonunwrap.egg-info/SOURCES.txt
+jsonunwrap.egg-info/dependency_links.txt
+jsonunwrap.egg-info/requires.txt
+jsonunwrap.egg-info/top_level.txt
+tests/test_core.py

jsonunwrap-0.1.0/jsonunwrap.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

jsonunwrap-0.1.0/jsonunwrap.egg-info/requires.txt

@@ -0,0 +1,2 @@
+requests>=2.28.0
+pandas>=2.0.0

jsonunwrap-0.1.0/jsonunwrap.egg-info/top_level.txt

@@ -0,0 +1 @@
+json_unwrap

jsonunwrap-0.1.0/pyproject.toml

@@ -0,0 +1,28 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "jsonunwrap"
+version = "0.1.0"
+authors = [
+    { name = "njuedominic", email="njuemugodominic@gmail.com"}
+]
+description = "A small python package that unpacks data from a JSON url and converts it into a csv file."
+readme = "README.md"
+requires-python = ">3.8"
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+]
+dependencies = [
+    "requests>=2.28.0",
+    "pandas>=2.0.0",
+]
+[project.urls]
+"Homepage" = "https://github.com/njuedominic/json-unwrap"
+"Bug Tracker" = "https://github.com/njuedominic/json-unwrap/issues"
+
+[tool.setuptools]
+packages = ["json_unwrap"]

jsonunwrap-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

jsonunwrap-0.1.0/tests/test_core.py

@@ -0,0 +1,21 @@
+import pandas as pd
+import pytest
+import json_unwrap as ju
+
+def test_unwrap_data_basic_flattening():
+    """Test that basic nested dictionaries are flattened with dot notation."""
+    sample = {"id": 1, "user": {"name": "Alice", "role": "Admin"}}
+    df = ju.unwrap_data(sample)
+    
+    assert isinstance(df, pd.DataFrame)
+    assert "user.name" in df.columns
+    assert df.loc[0, "user.name"] == "Alice"
+
+def test_unwrap_data_list_explosion():
+    """Test that lists inside dictionaries are properly exploded into rows."""
+    sample = {"id": 101, "hobbies": ["reading", "coding"]}
+    df = ju.unwrap_data(sample)
+    
+    # Should create 2 rows because of the 2 items in the list
+    assert len(df) == 2
+    assert list(df["hobbies"]) == ["reading", "coding"]