Modernise project

.github/dependabot.yml

@@ -5,7 +5,7 @@ updates:
     schedule:
       interval: "daily"
 
-  - package-ecosystem: "pip"
+  - package-ecosystem: "uv"
     directory: "/"
     schedule:
       interval: "daily"

.github/workflows/ci-build.yml

@@ -11,16 +11,29 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python: ['3.8', '3.9', '3.10', '3.11']
+        python: ['3.10', '3.11', '3.12', '3.13', '3.14']
 
     steps:
       - name: Checkout code
         uses: actions/checkout@v5
 
-      - name: Setup Python
-        uses: actions/setup-python@v6
-        with:
-          python-version: ${{ matrix.python }}
+      - name: Install the latest version of uv
+        uses: astral-sh/setup-uv@681c641aba71e4a1c380be3ab5e12ad51f415867 # v7.1.6
+
+      - name: Install python
+        run: uv python install ${{ matrix.python-version }}
+
+      - name: Install dependencies
+        run: uv sync --frozen
+
+      - name: Check formatting
+        run: make check-format
+
+      - name: Check linting
+        run: make check-fix
 
       - name: Run tests
-        run: python setup.py test
+        run: make test
+
+      - name: Build package
+        run: uv build

.gitignore

@@ -1,3 +1,5 @@
 *.pyc
 /dist/
 /*.egg-info
+.venv
+build/

.python-version

@@ -0,0 +1 @@
+3.14

Makefile

@@ -0,0 +1,18 @@
+RUN := uv run
+
+test:
+	@$(RUN) pytest
+
+fix:
+	@$(RUN) ruff check --fix
+
+check-fix:
+	@$(RUN) ruff check
+
+format:
+	@$(RUN) ruff format
+
+check-format:
+	@$(RUN) ruff format --check
+
+.PHONY: test fix check-fix format check-format

README.md

@@ -15,10 +15,10 @@ pip: (requires git installed)
 pip: (without git)
 
     pip install https://github.com/pdftables/python-pdftables-api/archive/master.tar.gz
-
-Locally:
 
-    python setup.py install
+For local development:
+
+    uv sync
 
 ### Upgrading
 
@@ -48,7 +48,12 @@ To specify Excel (single sheet) or Excel (multiple sheets) use `c.xlsx_single` o
 
 ## Test
 
-    python -m unittest test.test_pdftables_api
+Tests run with pytest: `make test`
+
+## Linting and formatting
+
+* Format with `make format`
+* Apply Ruff fixes with `make fix`
 
 ## Configuring a timeout
 

pdftables_api/__init__.py

@@ -12,10 +12,22 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from .pdftables_api import (Client,
-                            APIException,
-                            FORMAT_CSV,
-                            FORMAT_XLSX,
-                            FORMAT_XLSX_MULTIPLE,
-                            FORMAT_XLSX_SINGLE,
-                            FORMAT_XML)
+from .pdftables_api import (
+    FORMAT_CSV,
+    FORMAT_XLSX,
+    FORMAT_XLSX_MULTIPLE,
+    FORMAT_XLSX_SINGLE,
+    FORMAT_XML,
+    APIException,
+    Client,
+)
+
+__all__ = [
+    "FORMAT_CSV",
+    "FORMAT_XLSX",
+    "FORMAT_XLSX_MULTIPLE",
+    "FORMAT_XLSX_SINGLE",
+    "FORMAT_XML",
+    "APIException",
+    "Client",
+]

pdftables_api/pdftables_api.py

@@ -13,38 +13,37 @@
 # limitations under the License.
 
 import os
-
-import requests
-
 from shutil import copyfileobj
 
+import requests
 
-FORMAT_CSV = 'csv'
-FORMAT_HTML = 'html'
-FORMAT_XLSX_MULTIPLE = 'xlsx-multiple'
-FORMAT_XLSX_SINGLE = 'xlsx-single'
+FORMAT_CSV = "csv"
+FORMAT_HTML = "html"
+FORMAT_XLSX_MULTIPLE = "xlsx-multiple"
+FORMAT_XLSX_SINGLE = "xlsx-single"
 FORMAT_XLSX = FORMAT_XLSX_MULTIPLE
-FORMAT_XML = 'xml'
+FORMAT_XML = "xml"
 
-_API_URL = 'https://pdftables.com/api'
+_API_URL = "https://pdftables.com/api"
 _DEFAULT_TIMEOUT = (10, 300)  # seconds (connect and read)
 _FORMATS_EXT = {
-    FORMAT_CSV: '.csv',
-    FORMAT_HTML: '.html',
-    FORMAT_XLSX: '.xlsx',
-    FORMAT_XLSX_MULTIPLE: '.xlsx',
-    FORMAT_XLSX_SINGLE: '.xlsx',
-    FORMAT_XML: '.xml',
+    FORMAT_CSV: ".csv",
+    FORMAT_HTML: ".html",
+    FORMAT_XLSX: ".xlsx",
+    FORMAT_XLSX_MULTIPLE: ".xlsx",
+    FORMAT_XLSX_SINGLE: ".xlsx",
+    FORMAT_XML: ".xml",
 }
 _EXT_FORMATS = {
-    '.csv': FORMAT_CSV,
-    '.html': FORMAT_HTML,
-    '.xlsx': FORMAT_XLSX,
-    '.xml': FORMAT_XML,
+    ".csv": FORMAT_CSV,
+    ".html": FORMAT_HTML,
+    ".xlsx": FORMAT_XLSX,
+    ".xml": FORMAT_XML,
 }
 _STRING_FORMATS = {FORMAT_CSV, FORMAT_HTML, FORMAT_XML}
 
-class Client(object):
+
+class Client:
     def __init__(self, api_key, api_url=_API_URL, timeout=_DEFAULT_TIMEOUT):
         self.api_key = api_key
         self.api_url = api_url
@@ -98,60 +97,61 @@ def html(self, pdf_path, html_path=None):
         """
         return self.convert(pdf_path, html_path, out_format=FORMAT_HTML)
 
-    def convert(self, pdf_path, out_path=None, out_format=None, query_params=None, **requests_params):
+    def convert(
+        self,
+        pdf_path,
+        out_path=None,
+        out_format=None,
+        query_params=None,
+        **requests_params,
+    ):
         """
         Convert PDF given by `pdf_path` into `format` at `out_path`.
 
         If `out_path` is None, returns a string containing the contents, or a
         bytes for binary output types (e.g, XLSX)
         """
         (out_path, out_format) = Client.ensure_format_ext(out_path, out_format)
-        with open(pdf_path, 'rb') as pdf_fo:
-            response = self.request(pdf_fo, out_format, query_params,
-                                    **requests_params)
+        with open(pdf_path, "rb") as pdf_fo:
+            response = self.request(pdf_fo, out_format, query_params, **requests_params)
 
             if out_path is None:
                 use_text = out_format in _STRING_FORMATS
                 return response.text if use_text else response.content
 
-            with open(out_path, 'wb') as out_fo:
+            with open(out_path, "wb") as out_fo:
                 converted_fo = response.raw
                 # Ensure that gzip content is decoded.
                 converted_fo.decode_content = True
                 copyfileobj(converted_fo, out_fo)
 
-    def dump(self, pdf_fo, out_format=None, query_params=None,
-             **requests_params):
+    def dump(self, pdf_fo, out_format=None, query_params=None, **requests_params):
         """
         Convert PDF file object given by `pdf_fo` into an output stream iterator.
         """
-        response = self.request(pdf_fo, out_format, query_params,
-                                **requests_params)
+        response = self.request(pdf_fo, out_format, query_params, **requests_params)
 
         return response.iter_content(chunk_size=4096)
 
-    def request(self, pdf_fo, out_format=None, query_params=None,
-                **requests_params):
+    def request(self, pdf_fo, out_format=None, query_params=None, **requests_params):
         """
         Convert PDF given by `pdf_path`, returning requests.Response object.
         """
         if self.api_key == "":
             raise APIException("Invalid API key")
 
-        if 'timeout' not in requests_params:
-            requests_params.update({'timeout': self.timeout})
+        if "timeout" not in requests_params:
+            requests_params.update({"timeout": self.timeout})
 
         (_, out_format) = Client.ensure_format_ext(None, out_format)
         url = self.api_url
-        files = {'f': ('file.pdf', pdf_fo)}
+        files = {"f": ("file.pdf", pdf_fo)}
         params = query_params if query_params else {}
-        params.update({'key': self.api_key, 'format': out_format})
+        params.update({"key": self.api_key, "format": out_format})
 
-        response = requests.post(url,
-                                 files=files,
-                                 stream=True,
-                                 params=params,
-                                 **requests_params)
+        response = requests.post(
+            url, files=files, stream=True, params=params, **requests_params
+        )
 
         if response.status_code == 400:
             raise APIException("Unknown file format")
@@ -172,9 +172,9 @@ def remaining(self, query_params=None, **requests_params):
         if self.api_key == "":
             raise APIException("Invalid API key")
 
-        url = self.api_url+'/remaining'
+        url = self.api_url + "/remaining"
         params = query_params if query_params else {}
-        params.update({'key': self.api_key})
+        params.update({"key": self.api_key})
 
         response = requests.get(url, params=params, **requests_params)
 
@@ -190,29 +190,28 @@ def ensure_format_ext(out_path, out_format):
         Ensure the appropriate file extension and format is given. If not
         provided, try to guess either.
         """
-        if out_format != None and out_format not in _FORMATS_EXT.keys():
-            raise ValueError('Invalid output format')
+        if out_format is not None and out_format not in _FORMATS_EXT.keys():
+            raise ValueError("Invalid output format")
 
         default_format = FORMAT_XLSX_MULTIPLE
 
         # Check if stdout is desired
-        if out_path == None:
-            if out_format == None:
+        if out_path is None:
+            if out_format is None:
                 out_format = default_format
             return (None, out_format)
 
         _, ext = os.path.splitext(out_path)
 
         # Guess output format by file extension
-        if out_format == None:
+        if out_format is None:
             if ext in _FORMATS_EXT.values():
                 out_format = _EXT_FORMATS[ext]
             else:
                 out_format = default_format
 
         # Ensure correct file extension by output format
-        if (ext not in _FORMATS_EXT.values() or
-            ext != _FORMATS_EXT[out_format]):
+        if ext not in _FORMATS_EXT.values() or ext != _FORMATS_EXT[out_format]:
             out_path = out_path + _FORMATS_EXT[out_format]
 
         return (out_path, out_format)

pyproject.toml

@@ -0,0 +1,52 @@
+[build-system]
+requires = ["setuptools>=42", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "pdftables-api"
+version = "2.0.0"
+requires-python = ">=3.10"
+description = "PDFTables.com Python API library."
+readme = "README.md"
+license = { text = "Apache License 2.0" }
+keywords = ["pdf", "tables", "excel", "csv", "xml", "api"]
+authors = [ { name = "The Sensible Code Company", email = "[email protected]" } ]
+urls = { "Homepage" = "https://github.com/sensiblecode/python-pdftables-api" }
+dependencies = ["requests"]
+classifiers = [
+  "Development Status :: 5 - Production/Stable",
+  "Intended Audience :: Developers",
+  "License :: OSI Approved :: Apache Software License",
+  "Programming Language :: Python",
+  "Programming Language :: Python :: 3",
+  "Topic :: Software Development :: Libraries",
+  "Topic :: System :: Networking",
+]
+
+[dependency-groups]
+dev = [
+    "pytest",
+    "requests-mock",
+    "ruff",
+]
+
+[tool.pytest.ini_options]
+testpaths = ["test"]
+python_files = ["test_*.py"]
+
+[tool.ruff]
+line-length = 88
+
+[tool.ruff.lint]
+# "A": flake8-builtins
+# "I": isort
+# "UP": pyupgrade
+# "W": pycodestyle
+extend-select = ["A", "I", "UP", "W"]
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["pdftables_api"]
+
+[tool.uv]
+required-version = ">=0.9"