pyritrix3 0.0.1__tar.gz

pyritrix3-0.0.1/.gitignore

@@ -0,0 +1,218 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$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
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.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
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.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/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+# Temporary file for partial code execution
+tempCodeRunnerFile.py
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml

pyritrix3-0.0.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Emilian Zawrotny
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

pyritrix3-0.0.1/PKG-INFO

@@ -0,0 +1,16 @@
+Metadata-Version: 2.5
+Name: pyritrix3
+Version: 0.0.1
+Summary: A simple wrapper around Heritrix3' REST API
+Project-URL: Homepage, https://github.com/obrotowy/pyritrix3
+Project-URL: Issues, https://github.com/obrotowy/pyritrix3/issues
+Author-email: Emilian Zawrotny <emilian@zawrotny.pl>
+License-Expression: MIT
+License-File: LICENSE
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Requires-Python: >=3.9
+Requires-Dist: requests>=2.34.2
+Description-Content-Type: text/markdown
+
+Simple wrapper around [Hetririx3](https://github.com/internetarchive/heritrix3) REST API

pyritrix3-0.0.1/README.md

@@ -0,0 +1 @@
+Simple wrapper around [Hetririx3](https://github.com/internetarchive/heritrix3) REST API

pyritrix3-0.0.1/pyproject.toml

@@ -0,0 +1,24 @@
+[build-system]
+requires = ["hatchling >= 1.26"]
+build-backend = "hatchling.build"
+
+[project]
+name = "pyritrix3"
+version = "0.0.1"
+authors = [
+  { name="Emilian Zawrotny", email="emilian@zawrotny.pl" },
+]
+description = "A simple wrapper around Heritrix3' REST API"
+readme = "README.md"
+requires-python = ">=3.9"
+dependencies = [ "requests>=2.34.2" ]
+classifiers = [
+  "Programming Language :: Python :: 3",
+  "Operating System :: OS Independent",
+]
+license = "MIT"
+license-files = ["LICENSE"]
+
+[project.urls]
+Homepage = "https://github.com/obrotowy/pyritrix3"
+Issues = "https://github.com/obrotowy/pyritrix3/issues"

pyritrix3-0.0.1/requirements.txt

@@ -0,0 +1 @@
+requests

pyritrix3-0.0.1/src/pyritrix3/__init__.py

@@ -0,0 +1 @@
+from .pyritrix import pyritrix

pyritrix3-0.0.1/src/pyritrix3/jobs.py

@@ -0,0 +1,164 @@
+from typing import TYPE_CHECKING, IO
+
+if TYPE_CHECKING:
+    from .pyritrix import pyritrix
+
+
+class JobsEndpoint:
+    def __init__(self, client: pyritrix):
+        self._client = client
+
+    def create(self, createpath: str, profile=None) -> dict:
+        """
+        Creates a new crawl job from the selected profile. 
+        If no profile is supplied, Defaults (XML) is used.
+        Built-in profiles include Defaults (XML) and Defaults (Groovy).
+        Existing job profiles may also be selected by passing the profile job’s short name.
+        Arguments:
+            createpath: the name of the new job
+            profile: optional profile name. Existing profiles use their job short names.
+        """
+        data = {
+            "action": "create",
+            "createpath": createpath,
+            "profile": profile  # It's fine, requests will omit this if profile=None
+        }
+        response = self._client.post("/engine", data=data)
+        assert response.status_code == 200
+        return response.json()
+
+    def add(self, addpath: str) -> dict:
+        """
+        Adds a new job directory to the Heritrix configuration.
+        The directory must contain a cxml configuration file.
+        Arguments:
+            action: must be add
+            addpath: the job directory to add
+        """
+        data = {
+            "action": "add",
+            "addpath": addpath
+        }
+        response = self._client.post("/engine", data=data)
+        return response.json()
+
+    def get(self, jobname: str) -> dict:
+        """
+        Returns status information and statistics about the chosen job.
+        """
+        return self._client.get(f"/engine/job/{jobname}").json()
+
+    def build(self, jobname: str) -> dict:
+        """
+        Builds the job configuration for the chosen job. It reads an XML descriptor file and uses
+        Spring to build the Java objects that are necessary for running the crawl.
+        Before a crawl can be run it must be built.
+        """
+        data = {"action": "build"}
+        response = self._client.post(f"/engine/job/{jobname}", data=data)
+        return response.json()
+
+    def launch(self, jobname: str, checkpoint: str) -> dict:
+        """
+        Launches a crawl job. The job can be launched in the “paused” state or the “unpaused” state.
+        If launched in the “unpaused” state the job will immediately begin crawling.
+        Arguments:
+            checkpoint: optional field. If supplied, Heritrix will attempt to launch from a checkpoint.
+                        Should be the name of a checkpoint (e.g. cp00001-20180102121229) or (since version 3.3)
+                        the special value latest, which will automatically select the most recent checkpoint.
+                        If no checkpoint is specified (or if the latest checkpoint is requested and there
+                        are no valid checkpoints) a new crawl will be launched.
+        """
+        data = {
+            "action": "launch",
+            "checkpoint": checkpoint
+        }
+        response = self._client.post(f"/engine/job/{jobname}", data=data)
+        return response.json()
+
+    def rescan(self) -> dict:
+        """
+        Rescans the main job directory and returns an HTML page containing all the job names.
+        It also returns information about the jobs, such as the location of the job 
+        configuration file and the number of job launches.
+        """
+
+        return self._client.post("/engine", data={"action": "rescan"}).json()
+
+    def pause(self, jobname: str) -> dict:
+        """
+        Pauses an unpaused job. No crawling will occur while a job is paused.
+        """
+        return self._client.post(f"/engine/job/{jobname}", data={"action": "pause"}).json()
+
+    def unpause(self, jobname: str) -> dict:
+        """
+        This API unpauses a paused job. Crawling will resume (or begin, in the case of
+        a job launched in the paused state) if possible.
+        """
+        return self._client.post(f"/engine/job/{jobname}", data={"action": "unpause"}).json()
+
+    def terminate(self, jobname: str) -> dict:
+        """
+        Terminates a runnig job.
+        """
+        return self._client.post(f"/engine/job/{jobname}", data={"action": "terminate"}).json()
+
+    def teardown(self, jobname: str) -> dict:
+        """
+        Removes the Spring code that is used to run the job. Once a job is torn down it must be rebuilt in order to run.
+        """
+        return self._client.post(f"/engine/job/{jobname}", data={"action": "teardown"}).json()
+
+    def copy(self, jobname: str, copyTo: str, asProfile: bool) -> dict:
+        """
+        Copies an existing job configuration to a new job configuration. If the asProfile option is submitted with value on,
+        then the copy is a non-runnable profile. Profiles are listed as options when creating new jobs,
+        and profiles with built-in names override the built-ins.
+        Arguments:
+            copyTo: the name of the new job or profile configuration
+            asProfile: whether to copy the job as a runnable configuration or as a non-runnable profile.
+                       True means the job will be copied as a profile.
+        """
+        data = {
+            "copyTo": copyTo,
+        }
+        if asProfile:
+            data["asProfile"] = "on"
+        return self._client.post(f"/engine/job/{jobname}", data=data).json()
+
+    def delete(self, jobname: str) -> dict:
+        """
+        Deletes an existing job. It will remove everything related to the job (configuration, statistics, logs and results) 
+        including the whole job folder. Everything to keep has to be copied outside of the job folder.
+
+        Deleting a job is only possible if no active application context for the job exists which is
+        the case for new or unbuilt jobs. If a job has been built, it must first be torn down to allow deletion.
+        """
+        return self._client.post(f"/engine/job/{jobname}", data={"action": "delete"}).json()
+
+    def checkpoint(self, jobname: str) -> dict:
+        """
+        This API checkpoints the chosen job. Checkpointing writes the current state of a crawl 
+        to the file system so that the crawl can be recovered if it fails.
+        """
+        return self._client.post(f"/engine/job/{jobname}", data={"action": "checkpoint"}).json()
+
+    def execute_script(self, jobname: str, engine: str, script: str) -> dict:
+        """
+        Executes a script. The script can be written as Beanshell, ECMAScript, Groovy, or AppleScript.
+        Arguments:
+            engine: the script engine to use. One of beanshell, js, groovy or AppleScriptEngine.
+            script: the script code to execute
+        """
+        assert script in ["beanshell", "js", "groovy", "AppleScriptEngine"]
+        data = {
+            "engine": engine,
+            "script": script
+        }
+        return self._client.post(f"/engine/job/{jobname}/script", data=data).json()
+
+    def submit_config_file(self, jobname: str, file: IO):
+        response = self._client.put(
+            f"/engine/job/{jobname}/crawler-beans.cxml", data=file)
+        assert response.status_code == 200

pyritrix3-0.0.1/src/pyritrix3/pyritrix.py

@@ -0,0 +1,34 @@
+import requests
+from requests.auth import HTTPDigestAuth
+from urllib.parse import urljoin
+from .jobs import JobsEndpoint
+
+common_headers = {
+    "Accept": "application/json"
+}
+
+
+class pyritrix():
+    def __init__(self, hostname: str, username: str, password: str, port=8443, verify_certs=True):
+        self.session = requests.Session()
+        self.session.auth = HTTPDigestAuth(username, password)
+        self.verify_certs = verify_certs
+        self.base_url = f"https://{hostname}:{port}/"
+        self.jobs = JobsEndpoint(self)
+
+    def get(self, path: str, **kwargs) -> requests.Response:
+        return self.session.get(
+            urljoin(self.base_url, path), headers=common_headers, verify=self.verify_certs, **kwargs)
+
+    def post(self, path: str, **kwargs) -> requests.Response:
+        return self.session.post(
+            urljoin(self.base_url, path), headers=common_headers, verify=self.verify_certs, **kwargs)
+
+    def post(self, path: str, **kwargs) -> requests.Response:
+        return self.session.put(urljoin(self.base_url, path), headers=common_headers, verify=self.verify_certs, **kwargs)
+
+    def status(self) -> dict:
+        """
+        Returns information about this instance of Heritrix such as version number, memory usage and the list of crawl jobs.
+        """
+        return self.get("/engine").json()