urlscan-python 0.0.1__tar.gz

urlscan_python-0.0.1/.github/workflows/docs.yml

@@ -0,0 +1,32 @@
+name: Publish docs
+
+on:
+  release:
+    types: ["created"]
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0 # fetch all commits/branches (otherwise "mike deploy" fails)
+      - uses: actions/setup-python@v5
+        with:
+          python-version: 3.13
+          cache: "pip"
+      - run: pip install -r requirements.txt
+      - uses: actions/cache@v4
+        with:
+          path: ~/.cache/uv
+          key: uv-3.13-${{ hashFiles('uv.lock') }}
+      - run: uv sync --frozen
+      - name: git config for "mike deploy"
+        run: |
+          git config --global user.name "${{ github.actor }}"
+          git config --global user.email "${{ github.actor }}@users.noreply.github.com"
+      - name: deploy docs by mike
+        run: |
+          VERSION=$(uv run python scripts/convert_to_pep440_version.py "${{ github.event.release.tag_name }}")
+          uv run mike deploy "$VERSION" latest --update-aliases --push
+          uv run mike set-default latest --push

urlscan_python-0.0.1/.github/workflows/publish.yml

@@ -0,0 +1,26 @@
+name: Publish package
+
+on:
+  release:
+    types: ["created"]
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    permissions:
+      id-token: write # IMPORTANT: this permission is mandatory for trusted publishing
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: 3.13
+          cache: "pip"
+      - run: pip install -r requirements.txt
+      - uses: actions/cache@v4
+        with:
+          path: ~/.cache/uv
+          key: uv-3.13-${{ hashFiles('uv.lock') }}
+      - run: uv sync --frozen
+      - run: uv build
+      - name: publish
+        uses: pypa/gh-action-pypi-publish@release/v1

urlscan_python-0.0.1/.github/workflows/test.yml

@@ -0,0 +1,41 @@
+name: Test
+
+on: ["pull_request", "push"]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.10", 3.11, 3.12, 3.13]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: "pip"
+      - run: pip install -r requirements.txt
+      - uses: actions/cache@v4
+        with:
+          path: ~/.cache/uv
+          key: uv-${{ matrix.python-version }}-${{ hashFiles('uv.lock') }}
+      - run: uv sync --frozen
+      - run: uv run pytest
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: 3.13
+          cache: pip
+      - run: pip install -r requirements.txt
+      - uses: actions/cache@v4
+        with:
+          path: ~/.cache/uv
+          key: uv-3.13-${{ hashFiles('uv.lock') }}
+      - run: uv sync --frozen
+      - run: uv run uv-sort --check
+      - run: uv run ruff check --output-format github src/ tests/
+      - run: uv run ruff format --check src/ tests/
+      - run: uv run mypy src/ tests/

urlscan_python-0.0.1/.gitignore

@@ -0,0 +1,179 @@
+# 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
+
+# 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
+
+# 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/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# 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/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# version file
+src/urlscan/_version.py
+
+.python-version

urlscan_python-0.0.1/.lefthookrc

@@ -0,0 +1,5 @@
+#!/bin/bash
+
+if [ -f ./.venv/bin/activate ]; then
+  . ./.venv/bin/activate
+fi

urlscan_python-0.0.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 urlscan.io
+
+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.

urlscan_python-0.0.1/PKG-INFO

@@ -0,0 +1,98 @@
+Metadata-Version: 2.4
+Name: urlscan-python
+Version: 0.0.1
+Summary: The official Python API client for urlscan.io
+Project-URL: Repository, https://github.com/urlscan/urlscan-python/
+Project-URL: Homepage, https://github.com/urlscan/urlscan-python/
+Project-URL: Documentation, https://urlscan.github.io/urlscan-python/
+Project-URL: Issues, https://github.com/urlscan/urlscan-python/issues/
+License-File: LICENSE
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: <4.0,>=3.10
+Requires-Dist: httpx~=0.27
+Description-Content-Type: text/markdown
+
+# urlscan-python
+
+The official Python API client for urlscan.io.
+
+## Requirements
+
+- Python 3.10+
+
+## Installation
+
+```bash
+pip install urlscan-python
+```
+
+## Quickstart
+
+Start by importing `urlscan` module
+
+```py
+>>> import urlscan
+```
+
+Create a client with your API key:
+
+```py
+>>> client = urlscan.Client("<your_api_key>")
+```
+
+Scan a URL:
+
+```py
+>>> res = client.scan("<url>", visibility="public")
+>>> uuid: str = res["uuid"]
+```
+
+Wait for a scan result:
+
+```py
+>>> client.wait_for_result(uuid)
+```
+
+Get a scan result:
+
+```py
+>>> result = client.get_result(uuid)
+```
+
+Bulk scan:
+
+```py
+>>> client.bulk_scan(["<url>", "<url>"], visibility="public")
+```
+
+Alternatively, you can use `_and_get_result(s)` suffixed methods to do scan, wait and get at once.
+
+```py
+>>> client.scan_and_get_result("<url>", visibility="public")
+>>> client.bulk_scan_and_get_results(["<url>", "<url>"], visibility="public")
+```
+
+`urlscan.Client.search()` returns an iterator to iterate search results:
+
+```py
+>>> for result in client.search("page.domain:example.com"):
+>>>     print(result["_id"])
+```
+
+## Examples
+
+See [Examples](https://github.com/urlscan/urlscan-python/tree/main/examples/).
+
+## References
+
+- [Client](https://urlscan.github.io/urlscan-python/references/client/)
+- [Iterator](https://urlscan.github.io/urlscan-python/references/iterator/)
+- [Errors](https://urlscan.github.io/urlscan-python/references/errors/)
+
+## Help Wanted?
+
+Please feel free to to [open an issue](https://github.com/urlscan/urlscan-python/issues/new) if you find a bug or some feature that you want to see implemented.

urlscan_python-0.0.1/README.md

@@ -0,0 +1,80 @@
+# urlscan-python
+
+The official Python API client for urlscan.io.
+
+## Requirements
+
+- Python 3.10+
+
+## Installation
+
+```bash
+pip install urlscan-python
+```
+
+## Quickstart
+
+Start by importing `urlscan` module
+
+```py
+>>> import urlscan
+```
+
+Create a client with your API key:
+
+```py
+>>> client = urlscan.Client("<your_api_key>")
+```
+
+Scan a URL:
+
+```py
+>>> res = client.scan("<url>", visibility="public")
+>>> uuid: str = res["uuid"]
+```
+
+Wait for a scan result:
+
+```py
+>>> client.wait_for_result(uuid)
+```
+
+Get a scan result:
+
+```py
+>>> result = client.get_result(uuid)
+```
+
+Bulk scan:
+
+```py
+>>> client.bulk_scan(["<url>", "<url>"], visibility="public")
+```
+
+Alternatively, you can use `_and_get_result(s)` suffixed methods to do scan, wait and get at once.
+
+```py
+>>> client.scan_and_get_result("<url>", visibility="public")
+>>> client.bulk_scan_and_get_results(["<url>", "<url>"], visibility="public")
+```
+
+`urlscan.Client.search()` returns an iterator to iterate search results:
+
+```py
+>>> for result in client.search("page.domain:example.com"):
+>>>     print(result["_id"])
+```
+
+## Examples
+
+See [Examples](https://github.com/urlscan/urlscan-python/tree/main/examples/).
+
+## References
+
+- [Client](https://urlscan.github.io/urlscan-python/references/client/)
+- [Iterator](https://urlscan.github.io/urlscan-python/references/iterator/)
+- [Errors](https://urlscan.github.io/urlscan-python/references/errors/)
+
+## Help Wanted?
+
+Please feel free to to [open an issue](https://github.com/urlscan/urlscan-python/issues/new) if you find a bug or some feature that you want to see implemented.

urlscan_python-0.0.1/docs/README.md

@@ -0,0 +1 @@
+{% include-markdown "../README.md" %}

urlscan_python-0.0.1/docs/dev.md

@@ -0,0 +1,42 @@
+# Development
+
+This doc explains how to set up dev env if you want to get involved with this project.
+
+## Requirements
+
+- Python 3.10+
+
+## Setup
+
+This project uses [uv](https://github.com/astral-sh/uv) as a project manager and [Lefthook](https://github.com/evilmartians/lefthook) as a Git hooks manager.
+
+```bash
+git clone https://github.com/urlscan/urlscan-python
+cd urlscan-python
+
+# install uv
+pip install -r requirements.txt
+# sync uv
+uv sync
+# install Lefthook
+uv run lefthook install
+```
+
+## Test
+
+This project uses [pytest](https://docs.pytest.org/en/stable/) as a testing framework.
+
+```bash
+uv run pytest
+```
+
+## Docs
+
+This project uses [MkDocs](https://www.mkdocs.org/) as a documentation tool and uses [Mike](https://github.com/jimporter/mike) for versioning.
+
+```bash
+# run the dev server
+uv run mike serve
+# or build the docs
+uv run mke build
+```

urlscan_python-0.0.1/docs/references/client.md

@@ -0,0 +1 @@
+::: urlscan.Client

urlscan_python-0.0.1/docs/references/errors.md

@@ -0,0 +1,3 @@
+::: urlscan.APIError
+
+::: urlscan.RateLimitError

urlscan_python-0.0.1/docs/references/iterator.md

@@ -0,0 +1 @@
+::: urlscan.SearchIterator

urlscan_python-0.0.1/examples/screenshot_to_pil.py

@@ -0,0 +1,45 @@
+# /// script
+# requires-python = ">=3.10"
+# dependencies = [
+#    "pillow",
+#    "python-dotenv",
+#    "typer",
+#    "urlscan-python",
+# ]
+# ///
+
+# this script demonstrates how to get a screenshot & convert it to a PIL image.
+# usage: uv run examples/screenshot_to_pil.py <UUID>
+
+import os
+from typing import Annotated
+
+import typer
+from dotenv import load_dotenv
+from PIL import Image
+
+import urlscan
+
+load_dotenv()
+
+API_KEY = os.getenv("URLSCAN_API_KEY")
+
+
+def main(
+    uuid: Annotated[str, typer.Argument(help="Result UUID")],
+    api_key: Annotated[
+        str | None,
+        typer.Option(help="Your API key, defaults to URLSCAN_API_KEY env"),
+    ] = None,
+) -> None:
+    api_key = api_key or API_KEY
+    assert api_key
+
+    with urlscan.Client(api_key) as client:
+        screenshot = client.get_screenshot(uuid)
+        image = Image.open(screenshot)
+        image.show()
+
+
+if __name__ == "__main__":
+    typer.run(main)

urlscan_python-0.0.1/examples/search_and_download_screenshots.py

@@ -0,0 +1,53 @@
+# /// script
+# requires-python = ">=3.10"
+# dependencies = [
+#    "python-dotenv",
+#    "typer",
+#    "urlscan-python",
+# ]
+# ///
+
+# this script demonstrates how to do search and download screenshots.
+# usage: uv run examples/search_and_download_screenshots.py <QUERY>
+#        (e.g. uv run examples/search_and_download_screenshots.py domain:example.com)
+
+import os
+from pathlib import Path
+from typing import Annotated
+
+import typer
+from dotenv import load_dotenv
+
+import urlscan
+
+load_dotenv()
+
+API_KEY = os.getenv("URLSCAN_API_KEY")
+
+
+def main(
+    query: Annotated[str, typer.Argument(help="Search query")],
+    api_key: Annotated[
+        str | None,
+        typer.Option(help="Your API key. Defaults to URLSCAN_API_KEY env."),
+    ] = None,
+    limit: Annotated[int, typer.Option(help="Limit of search results")] = 10,
+    dest: Annotated[
+        Path, typer.Option(help="Destination directory to download screenshots")
+    ] = Path("/tmp"),
+) -> None:
+    api_key = api_key or API_KEY
+    assert api_key, "API key is required"
+
+    with urlscan.Client(api_key) as client:
+        for result in client.search(query, limit=limit):
+            _id: str = result["_id"]
+            screenshot = client.get_screenshot(_id)
+
+            path = dest / f"{_id}.png"
+            path.write_bytes(screenshot.read())
+            print(f"Downloaded screenshot to {path}")  # noqa: T201
+
+
+if __name__ == "__main__":
+    typer.run(main)

urlscan_python-0.0.1/examples/search_to_dataframe.py

@@ -0,0 +1,58 @@
+# /// script
+# requires-python = ">=3.10"
+# dependencies = [
+#    "itables",
+#    "pandas",
+#    "python-dotenv",
+#    "typer",
+#    "urlscan-python",
+# ]
+# ///
+
+# this script converts search results into a Pandas dataframe & shows it as an HTML table.
+# usage: uv run examples/search_to_dataframe.py <QUERY>
+#        (e.g. uv run examples/search_to_dataframe.py domain:example.com)
+
+import os
+import webbrowser
+from pathlib import Path
+from typing import Annotated
+
+import itables
+import pandas as pd
+import typer
+from dotenv import load_dotenv
+
+import urlscan
+
+load_dotenv()
+
+API_KEY = os.getenv("URLSCAN_API_KEY")
+
+
+def main(
+    query: Annotated[str, typer.Argument(help="Search query")],
+    api_key: Annotated[
+        str | None,
+        typer.Option(help="Your API key, defaults to URLSCAN_API_KEY env"),
+    ] = None,
+    limit: Annotated[int, typer.Option(help="Limit of search results")] = 100,
+    path: Annotated[
+        Path, typer.Option(help="Path to save a dataframe as an HTML file")
+    ] = Path("report.html"),
+) -> None:
+    api_key = api_key or API_KEY
+    assert api_key
+
+    with urlscan.Client(api_key) as client:
+        results = list(client.search(query, limit=limit))
+
+    df = pd.json_normalize(results)
+    html = itables.to_html_datatable(df)
+    path.write_text(html)
+
+    webbrowser.open(path.absolute().as_uri())
+
+
+if __name__ == "__main__":
+    typer.run(main)