maybankpdf2json 0.1.0__tar.gz

maybankpdf2json-0.1.0/PKG-INFO

@@ -0,0 +1,72 @@
+Metadata-Version: 2.4
+Name: maybankpdf2json
+Version: 0.1.0
+Summary: A package for extracting data from Maybank account statements in PDF format.
+Home-page: https://github.com/nordinz7/maybankpdf2json
+Author: Nordin
+Author-email: Nordin <vipnordin@gmail.com>
+Project-URL: Homepage, https://github.com/nordinz7/maybankpdf2json
+Keywords: maybank,pdf,JSON,account statements,Email delivery statement,Malayan Banking
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown
+Requires-Dist: pdfplumber>=0.7.4
+Dynamic: author
+Dynamic: home-page
+Dynamic: requires-python
+
+# Maybank Account Statement Extractor
+
+This package provides functionality to extract and process data from Maybank account statement PDFs. It allows users to read PDF files, filter relevant data, and map it into a structured format for further analysis or reporting.
+
+## Features
+
+- Extract data from PDF statements.
+- Filter and map extracted data into a structured format.
+- Utility functions for data manipulation and validation.
+
+## Installation
+
+To install the package, clone the repository and run the following command:
+
+```
+pip install .
+```
+
+## Usage
+
+Here is a basic example of how to use the package:
+
+```python
+from maybank_acc_extractor.extractor import read_pdfs, get_filtered_data, get_mapped_data
+
+# Read PDF files from a specified directory
+pdf_data = read_pdfs('path/to/pdf/folder', 'your_password')
+
+# Filter the data
+filtered_data = get_filtered_data(pdf_data)
+
+# Map the filtered data to a structured format
+mapped_data = get_mapped_data(filtered_data)
+
+# Output the mapped data
+print(mapped_data)
+```
+
+## Testing
+
+To run the tests, navigate to the project directory and execute:
+
+```
+pytest tests/
+```
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit a pull request or open an issue for any enhancements or bug fixes.
+
+## License
+
+This project is licensed under the MIT License. See the LICENSE file for more details.

maybankpdf2json-0.1.0/README.md

@@ -0,0 +1,53 @@
+# Maybank Account Statement Extractor
+
+This package provides functionality to extract and process data from Maybank account statement PDFs. It allows users to read PDF files, filter relevant data, and map it into a structured format for further analysis or reporting.
+
+## Features
+
+- Extract data from PDF statements.
+- Filter and map extracted data into a structured format.
+- Utility functions for data manipulation and validation.
+
+## Installation
+
+To install the package, clone the repository and run the following command:
+
+```
+pip install .
+```
+
+## Usage
+
+Here is a basic example of how to use the package:
+
+```python
+from maybank_acc_extractor.extractor import read_pdfs, get_filtered_data, get_mapped_data
+
+# Read PDF files from a specified directory
+pdf_data = read_pdfs('path/to/pdf/folder', 'your_password')
+
+# Filter the data
+filtered_data = get_filtered_data(pdf_data)
+
+# Map the filtered data to a structured format
+mapped_data = get_mapped_data(filtered_data)
+
+# Output the mapped data
+print(mapped_data)
+```
+
+## Testing
+
+To run the tests, navigate to the project directory and execute:
+
+```
+pytest tests/
+```
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit a pull request or open an issue for any enhancements or bug fixes.
+
+## License
+
+This project is licensed under the MIT License. See the LICENSE file for more details.

maybankpdf2json-0.1.0/maybankpdf2json/__init__.py

@@ -0,0 +1,3 @@
+# This file marks the directory as a Python package.
+# You can add package-level imports or initialization code here if needed.
+from .extractor import MaybankPDFExtractor

maybankpdf2json-0.1.0/maybankpdf2json/extractor.py

@@ -0,0 +1,68 @@
+from typing import List, Dict, Union, BinaryIO
+import pdfplumber
+
+START_ENTRY = "BEGINNING BALANCE"
+END_ENTRY = "TOTAL DEBIT"
+EXCLUDE_ITEMS = ["TOTAL CREDIT", "TOTAL DEBIT", "ENDING BALANCE"]
+
+class MaybankAccExtractor:
+    def __init__(self, buffers: Union[List[BinaryIO], BinaryIO], pwd: str = None):
+        if isinstance(buffers, list):
+            self.buffers = buffers
+        else:
+            self.buffers = [buffers]
+        self.pwd = pwd
+
+    def read_pdfs(self) -> List[List[str]]:
+        pdf_files = []
+        for buffer in self.buffers:
+            try:
+                pdf_files.append(self.read_single_pdf_file(buffer, self.pwd))
+            except Exception:
+                pdf_files.append(self.read_single_pdf_file(buffer, None))
+        return pdf_files
+
+    def read_single_pdf_file(self, buffer: BinaryIO, pwd: str) -> List[str]:
+        buffer.seek(0)
+        with pdfplumber.open(buffer, password=pwd) as pdf:
+            return [
+                txt
+                for page in pdf.pages
+                for txt in page.extract_text().split("\n")
+            ]
+
+    def get_filtered_data(self, arr: List[str]) -> List[str]:
+        indexes = [0, len(arr)]
+        for i, x in enumerate(arr):
+            if x.startswith(START_ENTRY):
+                indexes[0] = i
+            elif x.startswith(END_ENTRY):
+                indexes[1] = i + 1
+                break
+        filtered = arr[indexes[0]: indexes[1]]
+        narr = [v for v in filtered if not any(v.startswith(item) for item in EXCLUDE_ITEMS)]
+        return narr
+
+    def get_mapped_data(self, arr: List[str]) -> List[Dict[str, str]]:
+        narr = []
+        for current in arr:
+            splitted = current.split()
+            if len(splitted) < 3:
+                continue
+            obj = {
+                "date": splitted[0],
+                "desc": " ".join(splitted[1:-2]),
+                "trans": float(splitted[-2]),
+                "bal": float(splitted[-1])
+            }
+            narr.append(obj)
+        return narr
+
+    def extract_data(self) -> List[Dict[str, str]]:
+        pdf_data = self.read_pdfs()
+        all_mapped_data = []
+        for pdf in pdf_data:
+            filtered_data = self.get_filtered_data(pdf)
+            mapped_data = self.get_mapped_data(filtered_data)
+            all_mapped_data.extend(mapped_data)
+        return all_mapped_data

maybankpdf2json-0.1.0/maybankpdf2json/utils.py

@@ -0,0 +1,32 @@
+def parse_acc_value(value: str) -> float:
+    value = value.replace(",", "")
+    if value.endswith("-"):
+        return -float(value[:-1])
+    elif value.endswith("+"):
+        return float(value[:-1])
+    else:
+        return float(value)
+
+
+def is_valid_date(date_str: str) -> bool:
+    try:
+        datetime.strptime(date_str, "%d/%m/%y")
+        return True
+    except ValueError:
+        return False
+
+
+def output_extracted_data(value, options):
+    type = options["format"]
+    is_json = type == "json"
+    newline = None if is_json else ""
+    date = datetime.strptime(value[2]["date"], "%d/%m/%y")
+    file_date = date.strftime("%Y%m %B ") if not options["merge"] else "-COMBINED"
+
+    with open(f"{OUTPUT_FILENAME}{file_date}.{type}", "w", newline=newline) as o_file:
+        if is_json:
+            json.dump(value, o_file, indent=4)
+        else:
+            writer = csv.DictWriter(o_file, ["date", "desc", "trans", "bal"])
+            writer.writeheader()
+            writer.writerows(value)

maybankpdf2json-0.1.0/maybankpdf2json.egg-info/PKG-INFO

@@ -0,0 +1,72 @@
+Metadata-Version: 2.4
+Name: maybankpdf2json
+Version: 0.1.0
+Summary: A package for extracting data from Maybank account statements in PDF format.
+Home-page: https://github.com/nordinz7/maybankpdf2json
+Author: Nordin
+Author-email: Nordin <vipnordin@gmail.com>
+Project-URL: Homepage, https://github.com/nordinz7/maybankpdf2json
+Keywords: maybank,pdf,JSON,account statements,Email delivery statement,Malayan Banking
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown
+Requires-Dist: pdfplumber>=0.7.4
+Dynamic: author
+Dynamic: home-page
+Dynamic: requires-python
+
+# Maybank Account Statement Extractor
+
+This package provides functionality to extract and process data from Maybank account statement PDFs. It allows users to read PDF files, filter relevant data, and map it into a structured format for further analysis or reporting.
+
+## Features
+
+- Extract data from PDF statements.
+- Filter and map extracted data into a structured format.
+- Utility functions for data manipulation and validation.
+
+## Installation
+
+To install the package, clone the repository and run the following command:
+
+```
+pip install .
+```
+
+## Usage
+
+Here is a basic example of how to use the package:
+
+```python
+from maybank_acc_extractor.extractor import read_pdfs, get_filtered_data, get_mapped_data
+
+# Read PDF files from a specified directory
+pdf_data = read_pdfs('path/to/pdf/folder', 'your_password')
+
+# Filter the data
+filtered_data = get_filtered_data(pdf_data)
+
+# Map the filtered data to a structured format
+mapped_data = get_mapped_data(filtered_data)
+
+# Output the mapped data
+print(mapped_data)
+```
+
+## Testing
+
+To run the tests, navigate to the project directory and execute:
+
+```
+pytest tests/
+```
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit a pull request or open an issue for any enhancements or bug fixes.
+
+## License
+
+This project is licensed under the MIT License. See the LICENSE file for more details.

maybankpdf2json-0.1.0/maybankpdf2json.egg-info/SOURCES.txt

@@ -0,0 +1,12 @@
+README.md
+pyproject.toml
+setup.py
+maybankpdf2json/__init__.py
+maybankpdf2json/extractor.py
+maybankpdf2json/utils.py
+maybankpdf2json.egg-info/PKG-INFO
+maybankpdf2json.egg-info/SOURCES.txt
+maybankpdf2json.egg-info/dependency_links.txt
+maybankpdf2json.egg-info/requires.txt
+maybankpdf2json.egg-info/top_level.txt
+tests/test_extractor.py

maybankpdf2json-0.1.0/maybankpdf2json.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

maybankpdf2json-0.1.0/maybankpdf2json.egg-info/requires.txt

@@ -0,0 +1 @@
+pdfplumber>=0.7.4

maybankpdf2json-0.1.0/maybankpdf2json.egg-info/top_level.txt

@@ -0,0 +1 @@
+maybankpdf2json

maybankpdf2json-0.1.0/pyproject.toml

@@ -0,0 +1,30 @@
+[build-system]
+requires = ["setuptools", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "maybankpdf2json"
+description = "A package for extracting data from Maybank account statements in PDF format."
+authors = [{ name = "Nordin", email = "vipnordin@gmail.com" }]
+license = { file = "LICENSE" }
+readme = "README.md"
+urls = { "Homepage" = "https://github.com/nordinz7/maybankpdf2json" }
+keywords = [
+    "maybank",
+    "pdf",
+    "JSON",
+    "account statements",
+    "Email delivery statement",
+    "Malayan Banking",
+]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+]
+dependencies = ["pdfplumber>=0.7.4"]
+dynamic = ["version"]
+requires-python = ">=3.6"
+
+[tool.setuptools]
+packages = ["maybankpdf2json"]

maybankpdf2json-0.1.0/setup.cfg

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

maybankpdf2json-0.1.0/setup.py

@@ -0,0 +1,22 @@
+from setuptools import setup, find_packages
+
+setup(
+    name="maybankpdf2json",
+    version="0.1.0",
+    author="Nordin",
+    author_email="vipnordin@gmail.com",
+    description="A package for extracting JSON data from Maybank account statements(PDF format).",
+    long_description=open("README.md").read(),
+    long_description_content_type="text/markdown",
+    url="https://github.com/nordinz7/maybankpdf2json",
+    packages=find_packages(),
+    install_requires=[
+        "pdfplumber",
+    ],
+    classifiers=[
+        "Programming Language :: Python :: 3",
+        "License :: OSI Approved :: MIT License",
+        "Operating System :: OS Independent",
+    ],
+    python_requires='>=3.6',
+)

maybankpdf2json-0.1.0/tests/test_extractor.py

@@ -0,0 +1,35 @@
+import unittest
+from maybank_acc_extractor.extractor import read_pdfs, get_filtered_data, get_mapped_data
+
+class TestExtractor(unittest.TestCase):
+
+    def setUp(self):
+        self.test_pdf_path = "path/to/test/pdf"  # Update with actual test PDF path
+        self.test_password = "test_password"  # Update with actual test password
+        self.test_data = [
+            "BEGINNING BALANCE 1000.00",
+            "01/01/22 Transaction Description 100.00 1100.00",
+            "02/01/22 Transaction Description -50.00 1050.00",
+            "TOTAL DEBIT 50.00"
+        ]
+
+    def test_read_pdfs(self):
+        pdf_data = read_pdfs(self.test_pdf_path, self.test_password)
+        self.assertIsInstance(pdf_data, list)
+
+    def test_get_filtered_data(self):
+        filtered_data = get_filtered_data(self.test_data)
+        self.assertGreater(len(filtered_data), 0)
+
+    def test_get_mapped_data(self):
+        filtered_data = get_filtered_data(self.test_data)
+        mapped_data = get_mapped_data(filtered_data)
+        self.assertIsInstance(mapped_data, list)
+        self.assertGreater(len(mapped_data), 0)
+        self.assertIn("date", mapped_data[0])
+        self.assertIn("desc", mapped_data[0])
+        self.assertIn("trans", mapped_data[0])
+        self.assertIn("bal", mapped_data[0])
+
+if __name__ == "__main__":
+    unittest.main()