pipetasks 0.1.0__tar.gz

pipetasks-0.1.0/.circleci/config.yml

@@ -0,0 +1,111 @@
+version: 2.1
+orbs:
+  node: circleci/node@4.3
+  gh: circleci/github-cli@1.0
+jobs:
+  build_test:
+    docker:
+      - image: cimg/python:3.11.7
+    steps:
+      - checkout # checkout source code to working directory
+      - run:
+          name: Install uv
+          command: |
+            curl -LsSf https://astral.sh/uv/install.sh | sh
+            echo 'export PATH="$HOME/.local/bin:$PATH"' >> $BASH_ENV
+      - run:
+          name: Install dependencies
+          command: |
+            mkdir test-results
+            uv sync
+      - run:
+          name: Run tests
+          command: |
+            uv run pytest --junitxml=test-results/junit.xml --cov=./ --cov-report=xml
+      - run:
+          name: Run code coverage
+          command: |
+            curl -Os https://uploader.codecov.io/latest/linux/codecov
+            chmod +x codecov
+            ./codecov
+      - store_test_results:
+          path: test-results
+  build_verify:
+    docker:
+      - image: cimg/python:3.11.7
+    steps:
+      - checkout
+      - run:
+          name: Install uv
+          command: |
+            curl -LsSf https://astral.sh/uv/install.sh | sh
+            echo 'export PATH="$HOME/.local/bin:$PATH"' >> $BASH_ENV
+      - run:
+          name: Build package
+          command: uv build
+      - run:
+          name: Verify build artifacts
+          command: |
+            ls dist/
+            test -f dist/*.whl || (echo "Missing wheel" && exit 1)
+            test -f dist/*.tar.gz || (echo "Missing sdist" && exit 1)
+      - persist_to_workspace:
+          root: .
+          paths:
+            - dist/
+  pypi_publish:
+    docker:
+      - image: cimg/python:3.11.7
+    steps:
+      - checkout # checkout source code to working directory
+      - attach_workspace:
+          at: .
+      - run:
+          name: Install uv
+          command: |
+            curl -LsSf https://astral.sh/uv/install.sh | sh
+            echo 'export PATH="$HOME/.local/bin:$PATH"' >> $BASH_ENV
+      - run:
+          name: Build and publish to PyPI
+          command: |
+            uv publish \
+              --username $TWINE_USERNAME \
+              --password $TWINE_PASSWORD
+  gh_release:
+    docker:
+      - image: 'cimg/base:stable'
+    steps:
+      - checkout # checkout source code to working directory
+      - gh/setup
+      - run:
+          name: "Creating a GitHub Release"
+          command: |
+            export GITHUB_HOSTNAME="github.com"
+            VERSION=$(grep '^version' pyproject.toml | head -1 | cut -d'"' -f2)
+            gh release create "$VERSION" \
+              --notes-file "./CHANGELOG.md" \
+              --title "pipetasks v$VERSION" \
+              --repo "$(git config --get remote.origin.url)"
+workflows:
+  build_test_publish:
+    jobs:
+      - build_test
+      - build_verify:
+          requires:
+            - build_test
+          filters:
+            branches:
+              only: [main]
+      - pypi_publish:
+          requires:
+            - build_verify
+          filters:
+            branches:
+              only: [main]
+      - gh_release:
+          requires:
+            - pypi_publish
+          context: [GITHUB_CREDENTIALS]
+          filters:
+            branches:
+              only: [main]

pipetasks-0.1.0/.gitignore

@@ -0,0 +1,32 @@
+# Python-generated files
+__pycache__/
+*.py[oc]
+build/
+dist/
+wheels/
+*.egg-info
+.ruff_cache/
+
+# Virtual environments
+.venv
+
+node_modules
+
+# Output
+.output
+.vercel
+.netlify
+.wrangler
+/.svelte-kit
+/build
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Env
+.env
+.env.*
+frontend/.env
+!.env.example
+!.env.test.example

pipetasks-0.1.0/.pre-commit-config.yaml

@@ -0,0 +1,30 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0
+    hooks:
+    -   id: trailing-whitespace
+    -   id: end-of-file-fixer
+    -   id: check-yaml
+    -   id: check-added-large-files
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.7.0
+    hooks:
+    -   id: ruff
+        args: ["--fix"]
+    -   id: ruff-format
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.13.0
+    hooks:
+    -   id: mypy
+        entry: uv run mypy --config-file=pyproject.toml .
+        language: system
+        pass_filenames: false
+  - repo: local
+    hooks:
+    - id: run-pytest
+      name: Run pytest
+      entry: .venv/bin/pytest
+      args: ["-c", "pyproject.toml", "--maxfail=1", "--disable-warnings"]
+      language: system
+      always_run: true
+      pass_filenames: false

pipetasks-0.1.0/.python-version

@@ -0,0 +1 @@
+3.11.7

pipetasks-0.1.0/.vscode/launch.json

@@ -0,0 +1,23 @@
+{
+    // Use IntelliSense to learn about possible attributes.
+    // Hover to view descriptions of existing attributes.
+    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "Python: Debug tests",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "pytest",
+            "env": {
+                "PYTEST_ADDOPTS": "--no-cov"
+            },
+            "args": [
+                "-v",
+            ],
+            "console": "integratedTerminal",
+            "justMyCode": false,
+            "python": "${workspaceFolder}/.venv/bin/python"
+        }
+    ]
+}

pipetasks-0.1.0/.vscode/settings.json

@@ -0,0 +1,11 @@
+{
+    "python.testing.unittestEnabled": false,
+    "python.testing.pytestEnabled": true,
+    "python.testing.pytestPath": "${workspaceFolder}/.venv/bin/pytest",
+    "python.testing.cwd": "${workspaceFolder}",
+    "python.testing.pytestArgs": [
+        "tests"
+    ],
+    "python-envs.pythonProjects": [],
+    "python.defaultInterpreterPath": "${workspaceFolder}/.venv/bin/python"
+}

pipetasks-0.1.0/CHANGELOG.md

@@ -0,0 +1,12 @@
+# Change Log
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](http://keepachangelog.com/)
+and this project adheres to [Semantic Versioning](http://semver.org/).
+
+## [0.1.0] - 2026-03-24
+
+### Added
+
+- Initial release.

pipetasks-0.1.0/PKG-INFO

@@ -0,0 +1,20 @@
+Metadata-Version: 2.4
+Name: pipetasks
+Version: 0.1.0
+Summary: Utils to build pipelines
+Author-email: Armando Ezequiel Puerta <armando.ezequiel.puerta@gmail.com>
+License: MIT License
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Software Development
+Requires-Python: >=3.11.7
+Requires-Dist: selenium>=4.41.0
+Requires-Dist: webdriver-manager>=4.0.2
+Description-Content-Type: text/markdown
+
+# Pipetasks
+
+Utils to build pipelines

pipetasks-0.1.0/README.md

@@ -0,0 +1,3 @@
+# Pipetasks
+
+Utils to build pipelines

pipetasks-0.1.0/pipetasks/pipeline.py

@@ -0,0 +1,9 @@
+from abc import ABC, abstractmethod
+
+
+class Pipeline(ABC):
+    name: str | None = None
+
+    @abstractmethod
+    def run(self) -> None:
+        pass

pipetasks-0.1.0/pipetasks/scraping/pipeline.py

@@ -0,0 +1,126 @@
+import time
+
+from selenium.common.exceptions import (
+    NoSuchElementException,
+    TimeoutException,
+)
+from selenium.webdriver.chrome.options import Options
+from selenium.webdriver.chrome.service import Service
+from selenium.webdriver.chrome.webdriver import WebDriver as ChromeDriver
+from selenium.webdriver.common.by import By
+from selenium.webdriver.remote.webelement import WebElement
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.support.ui import WebDriverWait
+from webdriver_manager.chrome import ChromeDriverManager
+
+from pipetasks.pipeline import Pipeline
+
+
+class ScrapingPipeline(Pipeline):
+    TIMEOUT = 0.5
+    name = "Scrapper"
+
+    def __init__(  # type: ignore[no-untyped-def]
+        self,
+        headless: bool = True,
+        *args,
+        **kwargs,
+    ):
+        self.driver = self.__init_driver(headless=headless)
+        super().__init__(*args, **kwargs)
+
+    def __init_driver(
+        self,
+        headless: bool = True,
+    ) -> ChromeDriver:
+        chrome_options = Options()
+        if headless:
+            chrome_options.add_argument("--headless=new")
+        chrome_options.add_argument("--disable-gpu")
+        chrome_options.add_argument("--no-sandbox")
+        chrome_options.add_argument("--disable-dev-shm-usage")
+
+        return ChromeDriver(
+            service=Service(ChromeDriverManager().install()),
+            options=chrome_options,
+        )
+
+    def sleep(self, seconds: float | None = None) -> None:
+        secs = seconds if seconds else self.TIMEOUT
+        time.sleep(secs)
+
+    def __timeout(self, seconds: float | None = None) -> float:
+        return seconds if seconds is not None else self.TIMEOUT
+
+    def get(self, dns: str) -> None:
+        self.driver.get(dns)
+        self.sleep()
+
+    def find_element(
+        self,
+        by: str,
+        value: str,
+        on: WebElement | None = None,
+        timeout: float | None = None,
+    ) -> WebElement:
+        if on:
+            return on.find_element(by, value)
+        else:
+            return WebDriverWait(
+                self.driver,
+                self.__timeout(timeout),
+            ).until(EC.presence_of_element_located((by, value)))
+
+    def find_elements(
+        self,
+        by: str,
+        value: str,
+        on: WebElement | None = None,
+        timeout: float | None = None,
+    ) -> list[WebElement]:
+        if on:
+            return on.find_elements(by, value)
+        else:
+            return WebDriverWait(
+                self.driver,
+                self.__timeout(timeout),
+            ).until(EC.presence_of_all_elements_located((by, value)))
+
+    def click(
+        self,
+        by: str,
+        value: str,
+        on: WebElement | None = None,
+        timeout: float | None = None,
+    ) -> None:
+        wait_timeout = self.__timeout(timeout)
+        element = self.find_element(
+            by,
+            value,
+            on=on,
+            timeout=wait_timeout,
+        )
+        WebDriverWait(self.driver, wait_timeout).until(
+            EC.element_to_be_clickable(element)
+        ).click()
+        self.sleep()
+
+    def retry(
+        self,
+        *xpaths: str,
+        timeout: float | None = None,
+    ) -> WebElement:
+        wait_timeout = self.__timeout(timeout)
+        for xpath in xpaths:
+            try:
+                return self.find_element(
+                    By.XPATH,
+                    xpath,
+                    timeout=wait_timeout,
+                )
+            except TimeoutException:
+                continue
+        raise NoSuchElementException("No se encontró el elemento deseado.") from None
+
+    def run(self) -> None:
+        pass

pipetasks-0.1.0/pyproject.toml

@@ -0,0 +1,117 @@
+[project]
+name = "pipetasks"
+version = "0.1.0"
+description = "Utils to build pipelines"
+authors = [
+    {name = "Armando Ezequiel Puerta", email = "armando.ezequiel.puerta@gmail.com"}
+]
+license = {text = "MIT License"}
+readme = "README.md"
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "Programming Language :: Python :: 3",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+    "Topic :: Software Development"]
+requires-python = ">=3.11.7"
+dependencies = [
+    "selenium>=4.41.0",
+    "webdriver-manager>=4.0.2",
+]
+
+[dependency-groups]
+dev = [
+    "mypy>=1.19.1",
+    "pre-commit>=4.5.1",
+    "pytest>=9.0.2",
+    "pytest-cov>=7.1.0",
+    "ruff>=0.15.7",
+]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["pipetasks"]
+
+[tool.pytest.ini_options]
+markers = [
+    "integration: tests using external resources (Chrome, etc)",
+]
+addopts = "-m 'not integration'"
+
+#############################################
+#                 RUFF
+#############################################
+[tool.ruff]
+line-length = 88
+target-version = "py312"
+extend-exclude = []
+
+# Esto activa reglas equivalentes a flake8, isort, pyupgrade,
+# bugs típicos y mejores prácticas.
+lint.select = [
+    "E",   # errores estilo
+    "F",   # errores de flake8
+    "I",   # orden de imports (isort)
+    "B",   # bugbear
+    "UP",  # pyupgrade
+    "C4",  # comprehensions
+    "W",   # warnings
+]
+
+lint.ignore = [
+    "E203",  # compatibilidad con estilo Black
+    "E501",
+]
+
+#############################################
+#                 RUFF ISORT
+#############################################
+[tool.ruff.lint.isort]
+combine-as-imports = true
+known-first-party = ["core"]
+force-single-line = false
+
+#############################################
+#                 RUFF FORMAT
+#############################################
+[tool.ruff.format]
+quote-style = "double"
+indent-style = "space"
+line-ending = "auto"
+
+#############################################
+#                COVERAGE
+#############################################
+[tool.coverage.run]
+branch = true
+source = ["."]
+omit = [
+    "*/__init__.py"
+]
+
+[tool.coverage.report]
+show_missing = true
+skip_covered = false
+
+#############################################
+#                 MYPY
+#############################################
+[tool.mypy]
+python_version = "3.11"
+strict = false
+warn_unused_ignores = true
+warn_redundant_casts = true
+warn_return_any = true
+disallow_any_generics = true
+check_untyped_defs = true
+no_implicit_reexport = true
+disallow_untyped_defs = true
+ignore_missing_imports = true
+
+[[tool.mypy.overrides]]
+module = "tests.*"
+ignore_errors = true

pipetasks-0.1.0/tests/scraping/conftest.py

@@ -0,0 +1,19 @@
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+
+@pytest.fixture
+def mock_driver():
+    return MagicMock()
+
+
+@pytest.fixture
+def scraping_pipeline(mock_driver):
+    with (
+        patch("pipetasks.scraping.pipeline.ChromeDriverManager"),
+        patch("pipetasks.scraping.pipeline.ChromeDriver", return_value=mock_driver),
+    ):
+        from pipetasks.scraping.pipeline import ScrapingPipeline
+
+        yield ScrapingPipeline()