jpcorpreg 1.7.0__tar.gz

jpcorpreg-1.7.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

jpcorpreg-1.7.0/MANIFEST.in

@@ -0,0 +1,3 @@
+include LICENSE
+include README.md
+recursive-include jpcorpreg/config *.json

jpcorpreg-1.7.0/PKG-INFO

@@ -0,0 +1,60 @@
+Metadata-Version: 2.4
+Name: jpcorpreg
+Version: 1.7.0
+Summary: jpcorpreg is a Python library that downloads corporate registry which is published in the Corporate Number Publication Site as a data frame.
+Author: new-village
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/new-village/jpcorpreg
+Project-URL: Repository, https://github.com/new-village/jpcorpreg
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests
+Requires-Dist: bs4
+Requires-Dist: pandas
+Dynamic: license-file
+
+# jpcorpreg  
+[![Test](https://github.com/new-village/jpcorpreg/actions/workflows/test.yaml/badge.svg)](https://github.com/new-village/jpcorpreg/actions/workflows/test.yaml)
+![PyPI - Version](https://img.shields.io/pypi/v/jpcorpreg)
+  
+**jpcorpreg** is a Python library that downloads corporate registry which is published in the [Corporate Number Publication Site](https://www.houjin-bangou.nta.go.jp/en/) as a data frame.
+   
+  
+## Installation  
+----------------------
+jpcorpreg is available on pip installation.
+```sh
+$ python -m pip install jpcorpreg
+```
+  
+### GitHub Install
+Installing the latest version from GitHub:  
+```sh
+$ git clone https://github.com/new-village/jpcorpreg
+$ cd jpcorpreg
+$ pip install -e .
+```
+    
+## Usage
+This section demonstrates how to use this library to load and process data from the National Tax Agency's [Corporate Number Publication Site](https://www.houjin-bangou.nta.go.jp/).
+
+### Direct Data Loading
+To download data for a specific prefecture, use the `load` function. By passing the prefecture name as an argument, you can obtain a DataFrame containing data for that prefecture.  
+```python
+>>> import jpcorpreg
+>>> df = jpcorpreg.load("Shimane")
+```
+
+To execute the `load` function without argument, data for all prefectures across Japan will be downloaded. 
+```python
+>>> import jpcorpreg
+>>> df = jpcorpreg.load()
+```
+
+### CSV Data Loading
+If you already have a downloaded CSV file, use the `read_csv` function. By passing the file path as an argument, you can obtain a DataFrame with headers from the CSV data.
+```python
+>>> import jpcorpreg
+>>> df = jpcorpreg.read_csv("path/to/data.csv")
+```

jpcorpreg-1.7.0/README.md

@@ -0,0 +1,44 @@
+# jpcorpreg  
+[![Test](https://github.com/new-village/jpcorpreg/actions/workflows/test.yaml/badge.svg)](https://github.com/new-village/jpcorpreg/actions/workflows/test.yaml)
+![PyPI - Version](https://img.shields.io/pypi/v/jpcorpreg)
+  
+**jpcorpreg** is a Python library that downloads corporate registry which is published in the [Corporate Number Publication Site](https://www.houjin-bangou.nta.go.jp/en/) as a data frame.
+   
+  
+## Installation  
+----------------------
+jpcorpreg is available on pip installation.
+```sh
+$ python -m pip install jpcorpreg
+```
+  
+### GitHub Install
+Installing the latest version from GitHub:  
+```sh
+$ git clone https://github.com/new-village/jpcorpreg
+$ cd jpcorpreg
+$ pip install -e .
+```
+    
+## Usage
+This section demonstrates how to use this library to load and process data from the National Tax Agency's [Corporate Number Publication Site](https://www.houjin-bangou.nta.go.jp/).
+
+### Direct Data Loading
+To download data for a specific prefecture, use the `load` function. By passing the prefecture name as an argument, you can obtain a DataFrame containing data for that prefecture.  
+```python
+>>> import jpcorpreg
+>>> df = jpcorpreg.load("Shimane")
+```
+
+To execute the `load` function without argument, data for all prefectures across Japan will be downloaded. 
+```python
+>>> import jpcorpreg
+>>> df = jpcorpreg.load()
+```
+
+### CSV Data Loading
+If you already have a downloaded CSV file, use the `read_csv` function. By passing the file path as an argument, you can obtain a DataFrame with headers from the CSV data.
+```python
+>>> import jpcorpreg
+>>> df = jpcorpreg.read_csv("path/to/data.csv")
+```

jpcorpreg-1.7.0/jpcorpreg/__init__.py

@@ -0,0 +1,6 @@
+"""
+Corporate Number Parser Library
+~~~~~~~~~~~~~~~~~~~~~
+jpcorpreg is a simple scraping library for Corporate Number Publication Site
+"""
+from jpcorpreg.load import load, read_csv

jpcorpreg-1.7.0/jpcorpreg/config/header.json

@@ -0,0 +1,32 @@
+[
+    "sequence_number",
+    "corporate_number",
+    "process",
+    "correct",
+    "update_date",
+    "change_date",
+    "name",
+    "name_image_id",
+    "kind",
+    "prefecture_name",
+    "city_name",
+    "street_number",
+    "address_image_id",
+    "prefecture_code",
+    "city_code",
+    "post_code",
+    "address_outside",
+    "address_outside_image_id",
+    "close_date",
+    "close_cause",
+    "successor_corporate_number",
+    "change_cause",
+    "assignment_date",
+    "latest",
+    "en_name",
+    "en_prefecture_name",
+    "en_city_name",
+    "en_address_outside",
+    "furigana",
+    "hihyoji"
+]

jpcorpreg-1.7.0/jpcorpreg/load.py

@@ -0,0 +1,216 @@
+'''load.py
+'''
+import io
+import re
+import zipfile
+
+import requests
+import pandas as pd
+from io import StringIO
+from bs4 import BeautifulSoup
+
+from jpcorpreg.utility import load_config
+
+# Dictionary mapping Japanese prefecture names to English
+PREF_MAP = {
+    "全国": "All",
+    "北海道": "Hokkaido",
+    "青森県": "Aomori",
+    "岩手県": "Iwate",
+    "宮城県": "Miyagi",
+    "秋田県": "Akita",
+    "山形県": "Yamagata",
+    "福島県": "Fukushima",
+    "茨城県": "Ibaraki",
+    "栃木県": "Tochigi",
+    "群馬県": "Gunma",
+    "埼玉県": "Saitama",
+    "千葉県": "Chiba",
+    "東京都": "Tokyo",
+    "神奈川県": "Kanagawa",
+    "新潟県": "Niigata",
+    "富山県": "Toyama",
+    "石川県": "Ishikawa",
+    "福井県": "Fukui",
+    "山梨県": "Yamanashi",
+    "長野県": "Nagano",
+    "岐阜県": "Gifu",
+    "静岡県": "Shizuoka",
+    "愛知県": "Aichi",
+    "三重県": "Mie",
+    "滋賀県": "Shiga",
+    "京都府": "Kyoto",
+    "大阪府": "Osaka",
+    "兵庫県": "Hyogo",
+    "奈良県": "Nara",
+    "和歌山県": "Wakayama",
+    "鳥取県": "Tottori",
+    "島根県": "Shimane",
+    "岡山県": "Okayama",
+    "広島県": "Hiroshima",
+    "山口県": "Yamaguchi",
+    "徳島県": "Tokushima",
+    "香川県": "Kagawa",
+    "愛媛県": "Ehime",
+    "高知県": "Kochi",
+    "福岡県": "Fukuoka",
+    "佐賀県": "Saga",
+    "長崎県": "Nagasaki",
+    "熊本県": "Kumamoto",
+    "大分県": "Oita",
+    "宮崎県": "Miyazaki",
+    "鹿児島県": "Kagoshima",
+    "沖縄県": "Okinawa",
+    "国外": "Other"
+}
+
+def load(prefecture="All") -> pd.DataFrame:
+    """Loads data for a specified prefecture.
+
+    Args:
+        prefecture (str): The name of the prefecture to load data for. Defaults to "All".
+
+    Returns:
+        DataFrame: A DataFrame containing the loaded data.
+    """
+    loader = ZipLoader()
+    return loader.zip_load(prefecture)
+
+def read_csv(file_path: str) -> pd.DataFrame:
+    """Reads a CSV file from a specified path.
+
+    Args:
+        file_path (str): The path to the CSV file.
+
+    Returns:
+        DataFrame: A DataFrame containing the CSV data.
+    """
+    header = load_config("header")
+    return pd.read_csv(file_path, encoding='utf-8', header=None, names=header, dtype='object')
+
+class ZipLoader():
+    """Handles the loading and processing of zip files from a specified URL."""
+    def __init__(self):
+        self.url = "https://www.houjin-bangou.nta.go.jp/download/zenken/"
+
+        try:
+            response = requests.get(self.url, timeout=(3.0, 60.0))
+            soup = BeautifulSoup(response.text, "html.parser")
+        except requests.exceptions.RequestException as exp:
+            raise SystemExit(f"Request to {self.url} has been failure") from exp
+        
+        key = "jp.go.nta.houjin_bangou.framework.web.common.CNSFWTokenProcessor.request.token"
+        self.payload = {key: self._load_token(soup, key), "event": "download"}
+        self.pref_list = self._fetch_file_ids(soup)
+
+    def zip_load(self, prefecture) -> pd.DataFrame:
+        """Loads and processes a zip file from the server using a file ID.
+
+        Args:
+            file_id (str): The file ID to request the zip file.
+
+        Returns:
+            DataFrame: A DataFrame containing the data from the zip file.
+        """
+        try:
+            file_id = self.pref_list[prefecture.capitalize()]
+        except KeyError as exp:
+            raise SystemExit(f"Unexpected Key Value: {prefecture}") from exp
+
+        contents = self._download_zip(file_id)
+        csv_string = self._uncompress_file(contents)
+        return self._convert_csv_2_df(csv_string)
+
+    def _load_token(self, soup, key) -> str:
+        """Loads a security token from the server for requests.
+
+        Args:
+            url (str): The URL to load the token from.
+            key (str): The key name of the token to retrieve.
+
+        Returns:
+            str: The token as a string.
+
+        Raises:
+            SystemExit: If the request fails.
+        """
+        return soup.find("input", {"name": key, "type": "hidden"})["value"]
+
+    def _download_zip(self, file_id) -> bytes:
+        """Downloads a zip file from the server using the specified file ID.
+
+        Args:
+            file_id (str): The file ID to use for the download.
+
+        Returns:
+            bytes: The content of the zip file as bytes.
+
+        Raises:
+            SystemExit: If the request fails or the server responds with an error.
+        """
+        try:
+            self.payload["selDlFileNo"] = file_id
+            res = requests.post(self.url, params=self.payload, timeout=(3.0, 120.0))
+        except requests.exceptions.RequestException as exp:
+            print('Request is failure: Name, server or service not known')
+            raise SystemExit("RequestsExceptions") from exp
+
+        if res.status_code not in [200]:
+            raise SystemExit('Request to ' + self.url + ' has been failed: ' + str(res.status_code))
+        return res.content
+
+    def _uncompress_file(self, content) -> StringIO:
+        """Uncompresses the zip file content and extracts the CSV file.
+
+        Args:
+            content (bytes): The content of the zip file as bytes.
+
+        Returns:
+            StringIO: The CSV file content as a StringIO object.
+
+        Raises:
+            zipfile.BadZipFile: If the content is not a valid zip file.
+        """
+        try:
+            zip_object = zipfile.ZipFile(io.BytesIO(content))
+        except zipfile.BadZipFile:
+            print("Failed to unzip content. The content may not be a valid zip file.")
+            raise
+
+        for file_name in zip_object.namelist():
+            if not re.search(r'.*\.asc', file_name):
+                txt = zip_object.open(file_name).read()
+                return StringIO(txt.decode('utf-8'))
+
+    def _convert_csv_2_df(self, csv_string) -> pd.DataFrame:
+        """Converts a CSV string to a DataFrame using predefined headers.
+
+        Args:
+            csv_string (str): The CSV file content as a string.
+
+        Returns:
+            DataFrame: A DataFrame created from the CSV string.
+        """
+        header = load_config("header")
+        return pd.read_csv(csv_string, encoding='utf-8', header=None, names=header, dtype='object')
+
+    def _fetch_file_ids(self, soup) -> dict:
+        """
+        Extracts file IDs from the parsed HTML of a webpage.
+        
+        Args:
+        soup (BeautifulSoup): The BeautifulSoup object containing the parsed HTML.
+        
+        Returns:
+        dict: A dictionary mapping region names to their corresponding file IDs.
+        """
+
+        unicode_table = soup.find('div', class_='inBox21').find_all('div', class_='tbl02')[1]
+        rows = unicode_table.find_all('dl')
+        region_file_ids = {}
+        for row in rows:
+            region_name_jp = row.find('dt', class_='mb05').text.strip()
+            region_name = PREF_MAP.get(region_name_jp, region_name_jp)  # Convert Japanese to English if possible
+            file_id = re.search(r'\d{5}', row.find('a').get('onclick')).group()  # Extract file ID using regex
+            region_file_ids[region_name] = file_id
+        return region_file_ids

jpcorpreg-1.7.0/jpcorpreg/utility.py

@@ -0,0 +1,21 @@
+""" Utility
+It is utility functions class.
+"""
+import json
+import os
+
+import jpcorpreg
+
+
+def load_config(data_type:str) -> str:
+    """ The function loads configuration file from config directory
+    :param data_type: Category is identifier of data types such as ENTRY, ODDS, RACE and RESULT.
+    """
+    try:
+        dir_location = os.path.dirname(jpcorpreg.__file__) + '/config/'
+        with open(dir_location + data_type + '.json', 'r', encoding='UTF-8') as file:
+            return json.load(file)
+    except json.JSONDecodeError as exc:
+        raise SystemExit(f'Config file decode error: {exc}') from exc
+    except FileNotFoundError as exc:
+        raise SystemExit(f'Config file not found: {exc}') from exc

jpcorpreg-1.7.0/jpcorpreg.egg-info/PKG-INFO

@@ -0,0 +1,60 @@
+Metadata-Version: 2.4
+Name: jpcorpreg
+Version: 1.7.0
+Summary: jpcorpreg is a Python library that downloads corporate registry which is published in the Corporate Number Publication Site as a data frame.
+Author: new-village
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/new-village/jpcorpreg
+Project-URL: Repository, https://github.com/new-village/jpcorpreg
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests
+Requires-Dist: bs4
+Requires-Dist: pandas
+Dynamic: license-file
+
+# jpcorpreg  
+[![Test](https://github.com/new-village/jpcorpreg/actions/workflows/test.yaml/badge.svg)](https://github.com/new-village/jpcorpreg/actions/workflows/test.yaml)
+![PyPI - Version](https://img.shields.io/pypi/v/jpcorpreg)
+  
+**jpcorpreg** is a Python library that downloads corporate registry which is published in the [Corporate Number Publication Site](https://www.houjin-bangou.nta.go.jp/en/) as a data frame.
+   
+  
+## Installation  
+----------------------
+jpcorpreg is available on pip installation.
+```sh
+$ python -m pip install jpcorpreg
+```
+  
+### GitHub Install
+Installing the latest version from GitHub:  
+```sh
+$ git clone https://github.com/new-village/jpcorpreg
+$ cd jpcorpreg
+$ pip install -e .
+```
+    
+## Usage
+This section demonstrates how to use this library to load and process data from the National Tax Agency's [Corporate Number Publication Site](https://www.houjin-bangou.nta.go.jp/).
+
+### Direct Data Loading
+To download data for a specific prefecture, use the `load` function. By passing the prefecture name as an argument, you can obtain a DataFrame containing data for that prefecture.  
+```python
+>>> import jpcorpreg
+>>> df = jpcorpreg.load("Shimane")
+```
+
+To execute the `load` function without argument, data for all prefectures across Japan will be downloaded. 
+```python
+>>> import jpcorpreg
+>>> df = jpcorpreg.load()
+```
+
+### CSV Data Loading
+If you already have a downloaded CSV file, use the `read_csv` function. By passing the file path as an argument, you can obtain a DataFrame with headers from the CSV data.
+```python
+>>> import jpcorpreg
+>>> df = jpcorpreg.read_csv("path/to/data.csv")
+```

jpcorpreg-1.7.0/jpcorpreg.egg-info/SOURCES.txt

@@ -0,0 +1,14 @@
+LICENSE
+MANIFEST.in
+README.md
+pyproject.toml
+jpcorpreg/__init__.py
+jpcorpreg/load.py
+jpcorpreg/utility.py
+jpcorpreg.egg-info/PKG-INFO
+jpcorpreg.egg-info/SOURCES.txt
+jpcorpreg.egg-info/dependency_links.txt
+jpcorpreg.egg-info/requires.txt
+jpcorpreg.egg-info/top_level.txt
+jpcorpreg/config/header.json
+test/test_load.py

jpcorpreg-1.7.0/jpcorpreg.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

jpcorpreg-1.7.0/jpcorpreg.egg-info/requires.txt

@@ -0,0 +1,3 @@
+requests
+bs4
+pandas

jpcorpreg-1.7.0/jpcorpreg.egg-info/top_level.txt

@@ -0,0 +1 @@
+jpcorpreg

jpcorpreg-1.7.0/pyproject.toml

@@ -0,0 +1,31 @@
+[build-system]
+requires = ["setuptools>=68", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "jpcorpreg"
+version = "1.7.0"
+description = "jpcorpreg is a Python library that downloads corporate registry which is published in the Corporate Number Publication Site as a data frame."
+readme = "README.md"
+authors = [{ name = "new-village" }]
+license = { text = "Apache-2.0" }
+requires-python = ">=3.8"
+dependencies = [
+  "requests",
+  "bs4",
+  "pandas",
+]
+
+[project.urls]
+Homepage = "https://github.com/new-village/jpcorpreg"
+Repository = "https://github.com/new-village/jpcorpreg"
+
+[tool.setuptools]
+include-package-data = true
+
+[tool.setuptools.packages.find]
+include = ["jpcorpreg"]
+where = ["."]
+
+[tool.setuptools.package-data]
+jpcorpreg = ["config/*.json"]

jpcorpreg-1.7.0/setup.cfg

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

jpcorpreg-1.7.0/test/test_load.py

@@ -0,0 +1,35 @@
+""" test_load.py
+"""
+import unittest
+import json
+import pandas as pd
+import jpcorpreg
+
+class TestLoadFunctions(unittest.TestCase):
+    def setUp(self):
+        """Load expected columns from configuration file before each test."""
+        with open('jpcorpreg/config/header.json', 'r') as file:
+            self.expected_columns = json.load(file)
+
+    def test_load(self):
+        """Test the load function with 'Shimane' prefecture."""
+        result = jpcorpreg.load(prefecture='Shimane')
+
+        # Validate results
+        self.assertIsInstance(result, pd.DataFrame)
+        self.assertEqual(list(result.columns), self.expected_columns)
+        self.assertGreater(len(result), 20000)
+
+    def test_read_csv(self):
+        """Test the read_csv function with a specific CSV file."""
+        result = jpcorpreg.read_csv('./test/data/31_tottori_test_20240329.csv')
+
+        # Validate results
+        self.assertIsInstance(result, pd.DataFrame)
+        self.assertEqual(list(result.columns), self.expected_columns)
+        self.assertEqual(len(result), 5)
+        self.assertEqual(result.iloc[0]['corporate_number'], '1000013050238')
+        self.assertEqual(result.iloc[1]['name'], '島田商事株式会社')
+
+if __name__ == '__main__':
+    unittest.main()