is-crawler 1.0.0__tar.gz

is_crawler-1.0.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

is_crawler-1.0.0/PKG-INFO

@@ -0,0 +1,74 @@
+Metadata-Version: 2.4
+Name: is-crawler
+Version: 1.0.0
+Summary: Tiny, zero-dependency crawler detection via regex.
+Author-email: TN3W <tn3w@protonmail.com>
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/tn3w/is-crawler
+Project-URL: Repository, https://github.com/tn3w/is-crawler.git
+Project-URL: Issues, https://github.com/tn3w/is-crawler/issues
+Keywords: crawler,bot-detection,user-agent,spider,scraper,web-scraping,bot,robot,useragent,detection,security,middleware
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Internet :: WWW/HTTP
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Security
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# is-crawler
+
+Tiny, zero-dependency Python library that detects bots and crawlers from user-agent strings. Fast, lightweight, and ready to drop into any web app or API.
+
+## Install
+
+```bash
+pip install is-crawler
+```
+
+## Usage
+
+```python
+from is_crawler import is_crawler
+
+is_crawler("Googlebot/2.1 (+http://www.google.com/bot.html)")  # True
+is_crawler("Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/120.0.0.0 Safari/537.36")  # False
+```
+
+Works great as middleware, rate-limiter input, or analytics filter:
+
+```python
+from is_crawler import is_crawler
+
+@app.before_request
+def block_bots():
+    if is_crawler(request.headers.get("User-Agent", "")):
+        abort(403)
+```
+
+## How it works
+
+Four fast regex checks, no database or external lookups:
+
+1. **Bot signals** -- common keywords (`bot`, `crawl`, `spider`, `scrape`, ...), URL/email patterns, `headless`
+2. **Missing browser signature** -- real browsers always include engine tokens like `WebKit`, `Gecko`, or `Trident`
+3. **Bare `(compatible; ...)` block** -- classic bot pattern without OS tokens
+4. **Known tools** -- `playwright`, `selenium`, `wget`, `lighthouse`, `sqlmap`, and more
+
+## Need more?
+
+If you need deeper user-agent analysis -- device type, OS, browser version, or full bot fingerprinting -- check out [cr-ua](https://github.com/tn3w/crua).
+
+## License
+
+Apache-2.0

is_crawler-1.0.0/README.md

@@ -0,0 +1,46 @@
+# is-crawler
+
+Tiny, zero-dependency Python library that detects bots and crawlers from user-agent strings. Fast, lightweight, and ready to drop into any web app or API.
+
+## Install
+
+```bash
+pip install is-crawler
+```
+
+## Usage
+
+```python
+from is_crawler import is_crawler
+
+is_crawler("Googlebot/2.1 (+http://www.google.com/bot.html)")  # True
+is_crawler("Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/120.0.0.0 Safari/537.36")  # False
+```
+
+Works great as middleware, rate-limiter input, or analytics filter:
+
+```python
+from is_crawler import is_crawler
+
+@app.before_request
+def block_bots():
+    if is_crawler(request.headers.get("User-Agent", "")):
+        abort(403)
+```
+
+## How it works
+
+Four fast regex checks, no database or external lookups:
+
+1. **Bot signals** -- common keywords (`bot`, `crawl`, `spider`, `scrape`, ...), URL/email patterns, `headless`
+2. **Missing browser signature** -- real browsers always include engine tokens like `WebKit`, `Gecko`, or `Trident`
+3. **Bare `(compatible; ...)` block** -- classic bot pattern without OS tokens
+4. **Known tools** -- `playwright`, `selenium`, `wget`, `lighthouse`, `sqlmap`, and more
+
+## Need more?
+
+If you need deeper user-agent analysis -- device type, OS, browser version, or full bot fingerprinting -- check out [cr-ua](https://github.com/tn3w/crua).
+
+## License
+
+Apache-2.0

is_crawler-1.0.0/is_crawler/__init__.py

@@ -0,0 +1,45 @@
+from functools import lru_cache
+
+try:
+    import re2 as _regex  # type: ignore[reportMissingImports]
+except ImportError:
+    import re as _regex
+
+__version__ = "1.0.0"
+__all__ = ["is_crawler", "__version__"]
+
+_match_bot_signal = _regex.compile(
+    r"(?i)bot\b|crawl|spider|scrape|fetch|scan\b|index"
+    r"|preview|slurp|archiv|headless"
+    r"|\+https?://|@[\w.-]+\.\w{2,}\b"
+).search
+
+_match_browser_sign = _regex.compile(
+    r"(?i)mozilla/|webkit|gecko|trident|presto|khtml"
+    r"|opera[\s/]|links\s|lynx/"
+    r"|\((?:windows|macintosh|x11|linux)"
+).search
+
+_match_bare_compat = _regex.compile(
+    r"(?i)\(compatible;" r"(?![^)]*(?:windows|mac|linux|msie|konqueror))" r"[^)]*\)"
+).search
+
+_match_known_tool = _regex.compile(
+    r"(?i)lighthouse|playwright|selenium|wget[\s/]"
+    r"|nikto|sqlmap|nmap\b|pingdom|httrack"
+    r"|google[\s-](?:favicon|ads|safety|extended)"
+    r"|\bby\s+\S+\.(?:com|org|net)\b"
+    r"|^[\w.-]+\.(?:com|net|org|io|ai)[/\s]"
+    r"|;\s*\w+-agent[);]"
+).search
+
+
+@lru_cache(maxsize=2048)
+def is_crawler(user_agent: str) -> bool:
+    """Return True if the user agent string looks like a crawler."""
+    return bool(
+        _match_bot_signal(user_agent)
+        or not _match_browser_sign(user_agent)
+        or _match_bare_compat(user_agent)
+        or _match_known_tool(user_agent)
+    )

is_crawler-1.0.0/is_crawler.egg-info/PKG-INFO

@@ -0,0 +1,74 @@
+Metadata-Version: 2.4
+Name: is-crawler
+Version: 1.0.0
+Summary: Tiny, zero-dependency crawler detection via regex.
+Author-email: TN3W <tn3w@protonmail.com>
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/tn3w/is-crawler
+Project-URL: Repository, https://github.com/tn3w/is-crawler.git
+Project-URL: Issues, https://github.com/tn3w/is-crawler/issues
+Keywords: crawler,bot-detection,user-agent,spider,scraper,web-scraping,bot,robot,useragent,detection,security,middleware
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Internet :: WWW/HTTP
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Security
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# is-crawler
+
+Tiny, zero-dependency Python library that detects bots and crawlers from user-agent strings. Fast, lightweight, and ready to drop into any web app or API.
+
+## Install
+
+```bash
+pip install is-crawler
+```
+
+## Usage
+
+```python
+from is_crawler import is_crawler
+
+is_crawler("Googlebot/2.1 (+http://www.google.com/bot.html)")  # True
+is_crawler("Mozilla/5.0 (Windows NT 10.0; Win64; x64) Chrome/120.0.0.0 Safari/537.36")  # False
+```
+
+Works great as middleware, rate-limiter input, or analytics filter:
+
+```python
+from is_crawler import is_crawler
+
+@app.before_request
+def block_bots():
+    if is_crawler(request.headers.get("User-Agent", "")):
+        abort(403)
+```
+
+## How it works
+
+Four fast regex checks, no database or external lookups:
+
+1. **Bot signals** -- common keywords (`bot`, `crawl`, `spider`, `scrape`, ...), URL/email patterns, `headless`
+2. **Missing browser signature** -- real browsers always include engine tokens like `WebKit`, `Gecko`, or `Trident`
+3. **Bare `(compatible; ...)` block** -- classic bot pattern without OS tokens
+4. **Known tools** -- `playwright`, `selenium`, `wget`, `lighthouse`, `sqlmap`, and more
+
+## Need more?
+
+If you need deeper user-agent analysis -- device type, OS, browser version, or full bot fingerprinting -- check out [cr-ua](https://github.com/tn3w/crua).
+
+## License
+
+Apache-2.0

is_crawler-1.0.0/is_crawler.egg-info/SOURCES.txt

@@ -0,0 +1,9 @@
+LICENSE
+README.md
+pyproject.toml
+is_crawler/__init__.py
+is_crawler.egg-info/PKG-INFO
+is_crawler.egg-info/SOURCES.txt
+is_crawler.egg-info/dependency_links.txt
+is_crawler.egg-info/top_level.txt
+tests/test_is_crawler.py

is_crawler-1.0.0/is_crawler.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

is_crawler-1.0.0/is_crawler.egg-info/top_level.txt

@@ -0,0 +1 @@
+is_crawler

is_crawler-1.0.0/pyproject.toml

@@ -0,0 +1,39 @@
+[project]
+name = "is-crawler"
+version = "1.0.0"
+description = "Tiny, zero-dependency crawler detection via regex."
+readme = "README.md"
+authors = [
+    {name = "TN3W", email = "tn3w@protonmail.com"}
+]
+license = "Apache-2.0"
+license-files = ["LICENSE"]
+requires-python = ">=3.8"
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "Intended Audience :: Developers",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Internet :: WWW/HTTP",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+    "Topic :: Security",
+]
+keywords = ["crawler", "bot-detection", "user-agent", "spider", "scraper", "web-scraping", "bot", "robot", "useragent", "detection", "security", "middleware"]
+
+[project.urls]
+Homepage = "https://github.com/tn3w/is-crawler"
+Repository = "https://github.com/tn3w/is-crawler.git"
+Issues = "https://github.com/tn3w/is-crawler/issues"
+
+[build-system]
+requires = ["setuptools>=69", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools]
+packages = ["is_crawler"]

is_crawler-1.0.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

is_crawler-1.0.0/tests/test_is_crawler.py

@@ -0,0 +1,143 @@
+from pathlib import Path
+
+import pytest
+
+from is_crawler import __version__, is_crawler
+
+FIXTURES = Path(__file__).parent / "fixtures"
+
+
+def _load_fixture(name):
+    return [l.strip() for l in (FIXTURES / name).read_text().splitlines() if l.strip()]
+
+
+def test_version():
+    assert __version__ == "1.0.0"
+
+
+def test_all_exports():
+    import is_crawler as mod
+
+    assert set(mod.__all__) == {"is_crawler", "__version__"}
+
+
+# --- bot signal regex ---
+
+
+@pytest.mark.parametrize(
+    "ua",
+    [
+        "Googlebot/2.1 (+http://www.google.com/bot.html)",
+        "Mozilla/5.0 (compatible; bingbot/2.0)",
+        "Apache-HttpClient/4.5 (crawling service)",
+        "MySpider/1.0",
+        "web-scraper/0.3",
+        "DataFetcher/1.0",
+        "PortScanner/2.0",
+        "site-indexer v3",
+        "LinkPreview/1.0",
+        "Slurp/3.0",
+        "archive.org_bot/1.0",
+        "HeadlessChrome/90.0",
+        "SomeBot (+https://example.com)",
+        "checker (+http://example.com/info)",
+        "agent@crawler.example.com",
+    ],
+)
+def test_bot_signal_detected(ua):
+    assert is_crawler(ua) is True
+
+
+# --- browser sign keeps it non-crawler (when nothing else triggers) ---
+
+
+@pytest.mark.parametrize(
+    "ua",
+    [
+        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
+        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/17.0 Safari/605.1.15",
+        "Mozilla/5.0 (X11; Linux x86_64; rv:121.0) Gecko/20100101 Firefox/121.0",
+        "Opera/9.80 (Windows NT 6.1) Presto/2.12.388 Version/12.18",
+        "Links (2.28; Linux x86_64; GNU C)",
+        "Lynx/2.8.9rel.1 libwww-FM/2.14",
+    ],
+)
+def test_real_browser_not_crawler(ua):
+    assert is_crawler(ua) is False
+
+
+# --- no browser sign → crawler ---
+
+
+@pytest.mark.parametrize(
+    "ua",
+    [
+        "curl/7.68.0",
+        "python-requests/2.28.0",
+        "Java/1.8.0_292",
+        "",
+    ],
+)
+def test_no_browser_sign_is_crawler(ua):
+    assert is_crawler(ua) is True
+
+
+# --- bare compat (compatible; ...) without OS tokens ---
+
+
+@pytest.mark.parametrize(
+    "ua",
+    [
+        "Mozilla/5.0 (compatible; AhrefsBot/7.0; +http://ahrefs.com/robot/)",
+        "Mozilla/5.0 (compatible; SemrushBot/7; +http://www.semrush.com/bot.html)",
+    ],
+)
+def test_bare_compat_is_crawler(ua):
+    assert is_crawler(ua) is True
+
+
+def test_compat_with_os_not_bare():
+    """(compatible; MSIE 10.0; Windows ...) should NOT trigger bare compat."""
+    ua = "Mozilla/4.0 (compatible; MSIE 10.0; Windows NT 6.1; Trident/6.0)"
+    assert is_crawler(ua) is False
+
+
+# --- known tool regex ---
+
+
+@pytest.mark.parametrize(
+    "ua",
+    [
+        "Mozilla/5.0 (X11; Linux x86_64) Lighthouse",
+        "Mozilla/5.0 (Windows NT 10.0) Playwright/1.40",
+        "Mozilla/5.0 (Windows NT 10.0) Selenium/4.0",
+        "Wget/1.21",
+        "Nikto/2.1.6",
+        "sqlmap/1.7",
+        "Nmap Scripting Engine",
+        "Pingdom.com_bot_version_1.4",
+        "HTTrack/3.49",
+        "Mozilla/5.0 (Windows NT 10.0) Google-Safety/1.0",
+        "Mozilla/5.0 (Windows NT 10.0) Google Favicon",
+        "Mozilla/5.0 (Windows NT 10.0) Google Ads Bot",
+        "Mozilla/5.0 (Windows NT 10.0) Google-Extended",
+        "Mozilla/5.0 (Windows NT 10.0) by example.com crawl",
+        "example.com/crawler",
+        "Mozilla/5.0 (Windows NT 10.0; test-agent) Gecko/20100101",
+    ],
+)
+def test_known_tool_is_crawler(ua):
+    assert is_crawler(ua) is True
+
+
+# --- fixture-based tests ---
+
+
+@pytest.mark.parametrize("ua", _load_fixture("crawler_user_agents.txt"))
+def test_fixture_crawler_detected(ua):
+    assert is_crawler(ua) is True
+
+
+@pytest.mark.parametrize("ua", _load_fixture("browser_user_agents.txt"))
+def test_fixture_browser_not_detected(ua):
+    assert is_crawler(ua) is False