Initial parser release

.github/workflows/tests.yaml

@@ -0,0 +1,27 @@
+name: Tests
+"on":
+  push:
+    branches:
+      - "*"
+jobs:
+  tests:
+    runs-on: ubuntu-22.04
+    strategy:
+      max-parallel: 2
+      matrix:
+        python-version: ["3.8", "3.9", "3.10", "3.11"]
+    steps:
+      - uses: actions/checkout@v4
+      - name: "Setup Python ${{ matrix.python-version }}"
+        uses: actions/setup-python@v5
+        with:
+          python-version: "${{ matrix.python-version }}"
+          cache: pip
+          cache-dependency-path: "**/requirements.txt"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements.txt
+      - name: Run Tests
+        run: |
+          pytest .

.gitignore

@@ -0,0 +1,164 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+.vscode/
+.DS_Store
+.ruff_cache/

README.md

@@ -0,0 +1,96 @@
+# SR Invoice Parser
+
+[![build-status-image]][build-status]
+
+SR Invoice Parser is a small library that is parsing invoices and extracting relevant information.
+It is designed to work with invoices from the Tax Administration of the Republic of Serbia (Poreska uprava Republike Srbije).
+
+- https://purs.gov.rs/
+- https://suf.purs.gov.rs/
+
+QR code gives a URL to the invoice web page, and this parser extracts the relevant information from the web page, like a crawler.
+
+## Installation
+
+To install SR Invoice Parser, follow these steps:
+
+    pip install sr-invoice-parser
+
+## Usage
+
+The `InvoiceParser` class is the entry point for using the parser.
+
+### Methods
+
+- `get_data()` - Extracts all the data from the invoice and returns it as a dictionary
+- `get_company_name()` - Extracts the company name.
+- `get_company_tin()` - Extracts the company's tax identification number/PFR.
+- `get_total_amount()` - Extracts the total amount of the invoice.
+- `get_dt()` - Extracts the date and time of the invoice and converts it to UTC as a datetime object.
+- `get_invoice_number()` - Extracts the invoice number.
+- `get_invoice_text()` - Extracts the full text of the invoice with QR code base64.
+- `get_items()` - Extracts items details from the invoice. This is array of dictionaries with keys: `name`, `quantity`, `price`, `total_price`.
+
+Here's a basic example of how to use it:
+
+```python
+from sr_invoice_parser import InvoiceParser
+
+parser = InvoiceParser(url="https://suf.purs.gov.rs/v/?vl=...")
+# or
+parser = InvoiceParser(html_text="<HTML source code of invoice web page>")
+
+parser.data()
+
+parser.get_company_name()
+parser.get_company_tin()
+parser.get_total_amount()
+parser.get_dt()
+parser.get_invoice_number()
+parser.get_invoice_text()
+parser.get_items()
+
+```
+
+## Example response data
+
+```python
+{
+    "company_name": "Company Name",
+    "company_tin": "123456789",
+    "invoice_number": "QWERTYU1-QWERTYU1-12345",
+    "invoice_datetime": datetime.datetime(2021, 1, 1, 0, 0, tzinfo=datetime.timezone.utc),
+    "invoice_total_amount": 123.45,
+    "invoice_text": "============ ФИСКАЛНИ РАЧУН ============.....",
+    "invoice_items": [
+        {
+            "name": "Item 1",
+            "quantity": 1,
+            "price": 123.45,
+            "total_price": 123.45
+        }
+    ]
+}
+```
+
+Check the [test_parser.py](/tests/test_parser.py) file for more examples.
+
+## Handling Exceptions
+
+The module has custom exceptions for handling various error scenarios:
+
+- `ParserParseException` - Raised when any error occurs during parsing the HTML content.
+- `ParserRequestException` - Raised for errors related to fetching HTML content.
+
+## Contributing
+
+Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
+
+If you have any questions, please contact us via email: [[email protected]](mailto:[email protected]?subject=[GitHub]%20sr-invoice-parser%20Question)
+
+## License
+
+This project is licensed under the [MIT License](/LICENSE).
+
+[build-status-image]: https://github.com/Innovigo/sr-invoice-parser/actions/workflows/tests.yaml/badge.svg
+[build-status]: https://github.com/Innovigo/sr-invoice-parser/actions/workflows/tests.yaml

pyproject.toml

@@ -0,0 +1,31 @@
+[build-system]
+requires = ["flit_core>=3.9.0"]
+build-backend = "flit_core.buildapi"
+
+[project]
+name = "sr-invoice-parser"
+dynamic = ["version", "description"]
+authors = [
+  { name="Innovigo", email="[email protected]" },
+]
+readme = "README.md"
+license = {text = "MIT"}
+
+requires-python = ">=3.8"
+dependencies = [
+  "pytz>=2021.1",
+  "requests>=2.21.0",
+  "parsel>=1.7.0",
+  "srtools>=0.1.13",
+]
+classifiers = [
+    "Intended Audience :: Developers",
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+]
+
+[project.urls]
+Home = "https://github.com/Innovigo/sr-invoice-parser"
+Source = "https://github.com/Innovigo/sr-invoice-parser"
+Issues = "https://github.com/Innovigo/sr-invoice-parser/issues"

requirements.txt

@@ -0,0 +1,7 @@
+pytz>=2021.1
+requests>=2.21.0
+parsel>=1.7.0
+srtools>=0.1.13
+flit-core>=3.9.0
+ruff
+pytest

sr_invoice_parser/__init__.py

@@ -0,0 +1,14 @@
+"""SR Invoice Parser is a small library(crawler) that is parsing invoices and extracting relevant information from URL. For Serbian market."""
+
+__title__ = "sr_invoice_parser"
+__author__ = "Innovigo"
+__website__ = "https://wwwinnovigo.co/"
+__email__ = "[email protected]"
+__version__ = "0.0.1"
+
+VERSION = __version__
+
+from .exceptions import ParserParseException, ParserRequestException  # noqa: E402
+from .parser import InvoiceParser  # noqa: E402
+
+__all__ = ["InvoiceParser", "ParserRequestException", "ParserParseException"]

sr_invoice_parser/decorators.py

@@ -0,0 +1,19 @@
+import functools
+
+from .exceptions import ParserParseException
+
+
+def handle_exception():
+    def wrapper(function):
+        @functools.wraps(function)
+        def inner(*args, **kwargs):
+            try:
+                return function(*args, **kwargs)
+            except Exception as e:
+                raise ParserParseException(
+                    f"Failed to parse the HTML content in '{function.__name__}': {e}"
+                )
+
+        return inner
+
+    return wrapper

sr_invoice_parser/exceptions.py

@@ -0,0 +1,6 @@
+class ParserRequestException(Exception):
+    pass
+
+
+class ParserParseException(Exception):
+    pass