Update tests and convert to stock unittest

For these simple tests Python's built-in unittest framework is more than enough.
No additional dependencies are required.

Added some more test cases with "special" characters to test the escaping code
better.

code/test_files/.htaccess

@@ -1,3 +1,3 @@
 RewriteEngine On
-RewriteCond %{HTTP_USER_AGENT} (AI2Bot|Ai2Bot\-Dolma|Amazonbot|anthropic\-ai|Applebot|Applebot\-Extended|Bytespider|CCBot|ChatGPT\-User|Claude\-Web|ClaudeBot|cohere\-ai|Diffbot|FacebookBot|facebookexternalhit|FriendlyCrawler|Google\-Extended|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|Meta\-ExternalAgent|Meta\-ExternalFetcher|OAI\-SearchBot|omgili|omgilibot|PerplexityBot|PetalBot|Scrapy|Sidetrade\ indexer\ bot|Timpibot|VelenPublicWebCrawler|Webzio\-Extended|YouBot) [NC]
+RewriteCond %{HTTP_USER_AGENT} (AI2Bot|Ai2Bot\-Dolma|Amazonbot|anthropic\-ai|Applebot|Applebot\-Extended|Bytespider|CCBot|ChatGPT\-User|Claude\-Web|ClaudeBot|cohere\-ai|Diffbot|FacebookBot|facebookexternalhit|FriendlyCrawler|Google\-Extended|GoogleOther|GoogleOther\-Image|GoogleOther\-Video|GPTBot|iaskspider/2\.0|ICC\-Crawler|ImagesiftBot|img2dataset|ISSCyberRiskCrawler|Kangaroo\ Bot|Meta\-ExternalAgent|Meta\-ExternalFetcher|OAI\-SearchBot|omgili|omgilibot|PerplexityBot|PetalBot|Scrapy|Sidetrade\ indexer\ bot|Timpibot|VelenPublicWebCrawler|Webzio\-Extended|YouBot|crawler\.with\.dots|star\*\*\*crawler|Is\ this\ a\ crawler\?|a\[mazing\]\{42\}\(robot\)|2\^32\$|curl\|sudo\ bash) [NC]
 RewriteRule !^/?robots\.txt$ - [F,L]

code/test_files/robots.json

@@ -278,5 +278,47 @@
         "function": "Scrapes data for search engine and LLMs.",
         "frequency": "No information.",
         "description": "Retrieves data used for You.com web search engine and LLMs."
+    },
+    "crawler.with.dots": {
+        "operator": "Test suite",
+        "respect": "No",
+        "function": "To ensure the code works correctly.",
+        "frequency": "No information.",
+        "description": "When used in the .htaccess regular expression dots need to be escaped."
+    },
+    "star***crawler": {
+        "operator": "Test suite",
+        "respect": "No",
+        "function": "To ensure the code works correctly.",
+        "frequency": "No information.",
+        "description": "When used in the .htaccess regular expression stars need to be escaped."
+    },
+    "Is this a crawler?": {
+        "operator": "Test suite",
+        "respect": "No",
+        "function": "To ensure the code works correctly.",
+        "frequency": "No information.",
+        "description": "When used in the .htaccess regular expression spaces and question marks need to be escaped."
+    },
+    "a[mazing]{42}(robot)": {
+        "operator": "Test suite",
+        "respect": "No",
+        "function": "To ensure the code works correctly.",
+        "frequency": "No information.",
+        "description": "When used in the .htaccess regular expression parantheses, braces, etc. need to be escaped."
+    },
+    "2^32$": {
+        "operator": "Test suite",
+        "respect": "No",
+        "function": "To ensure the code works correctly.",
+        "frequency": "No information.",
+        "description": "When used in the .htaccess regular expression RE anchor characters need to be escaped."
+    },
+    "curl|sudo bash": {
+        "operator": "Test suite",
+        "respect": "No",
+        "function": "To ensure the code works correctly.",
+        "frequency": "No information.",
+        "description": "When used in the .htaccess regular expression pipes need to be escaped."
     }
-}
+}

code/test_files/robots.txt

@@ -38,4 +38,10 @@ User-agent: Timpibot
 User-agent: VelenPublicWebCrawler
 User-agent: Webzio-Extended
 User-agent: YouBot
+User-agent: crawler.with.dots
+User-agent: star***crawler
+User-agent: Is this a crawler?
+User-agent: a[mazing]{42}(robot)
+User-agent: 2^32$
+User-agent: curl|sudo bash
 Disallow: /

code/test_files/table-of-bot-metrics.md

@@ -1,35 +1,35 @@
 | Name | Operator | Respects `robots.txt` | Data use | Visit regularity | Description |
-|-----|----------|-----------------------|----------|------------------|-------------|
+|------|----------|-----------------------|----------|------------------|-------------|
 | AI2Bot | [Ai2](https://allenai.org/crawler) | Yes | Content is used to train open language models. | No information provided. | Explores 'certain domains' to find web content. |
-| Ai2Bot-Dolma | [Ai2](https://allenai.org/crawler) | Yes | Content is used to train open language models. | No information provided. | Explores 'certain domains' to find web content. |
+| Ai2Bot\-Dolma | [Ai2](https://allenai.org/crawler) | Yes | Content is used to train open language models. | No information provided. | Explores 'certain domains' to find web content. |
 | Amazonbot | Amazon | Yes | Service improvement and enabling answers for Alexa users. | No information provided. | Includes references to crawled website when surfacing answers via Alexa; does not clearly outline other uses. |
-| anthropic-ai | [Anthropic](https://www.anthropic.com) | Unclear at this time. | Scrapes data to train Anthropic's AI products. | No information provided. | Scrapes data to train LLMs and AI products offered by Anthropic. |
+| anthropic\-ai | [Anthropic](https://www.anthropic.com) | Unclear at this time. | Scrapes data to train Anthropic's AI products. | No information provided. | Scrapes data to train LLMs and AI products offered by Anthropic. |
 | Applebot | Unclear at this time. | Unclear at this time. | AI Search Crawlers | Unclear at this time. | Applebot is a web crawler used by Apple to index search results that allow the Siri AI Assistant to answer user questions. Siri's answers normally contain references to the website. More info can be found at https://darkvisitors.com/agents/agents/applebot |
-| Applebot-Extended | [Apple](https://support.apple.com/en-us/119829#datausage) | Yes | Powers features in Siri, Spotlight, Safari, Apple Intelligence, and others. | Unclear at this time. | Apple has a secondary user agent, Applebot-Extended ... [that is] used to train Apple's foundation models powering generative AI features across Apple products, including Apple Intelligence, Services, and Developer Tools. |
+| Applebot\-Extended | [Apple](https://support.apple.com/en-us/119829#datausage) | Yes | Powers features in Siri, Spotlight, Safari, Apple Intelligence, and others. | Unclear at this time. | Apple has a secondary user agent, Applebot-Extended ... [that is] used to train Apple's foundation models powering generative AI features across Apple products, including Apple Intelligence, Services, and Developer Tools. |
 | Bytespider | ByteDance | No | LLM training. | Unclear at this time. | Downloads data to train LLMS, including ChatGPT competitors. |
 | CCBot | [Common Crawl Foundation](https://commoncrawl.org) | [Yes](https://commoncrawl.org/ccbot) | Provides open crawl dataset, used for many purposes, including Machine Learning/AI. | Monthly at present. | Web archive going back to 2008. [Cited in thousands of research papers per year](https://commoncrawl.org/research-papers). |
-| ChatGPT-User | [OpenAI](https://openai.com) | Yes | Takes action based on user prompts. | Only when prompted by a user. | Used by plugins in ChatGPT to answer queries based on user input. |
+| ChatGPT\-User | [OpenAI](https://openai.com) | Yes | Takes action based on user prompts. | Only when prompted by a user. | Used by plugins in ChatGPT to answer queries based on user input. |
-| Claude-Web | [Anthropic](https://www.anthropic.com) | Unclear at this time. | Scrapes data to train Anthropic's AI products. | No information provided. | Scrapes data to train LLMs and AI products offered by Anthropic. |
+| Claude\-Web | [Anthropic](https://www.anthropic.com) | Unclear at this time. | Scrapes data to train Anthropic's AI products. | No information provided. | Scrapes data to train LLMs and AI products offered by Anthropic. |
 | ClaudeBot | [Anthropic](https://www.anthropic.com) | [Yes](https://support.anthropic.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler) | Scrapes data to train Anthropic's AI products. | No information provided. | Scrapes data to train LLMs and AI products offered by Anthropic. |
-| cohere-ai | [Cohere](https://cohere.com) | Unclear at this time. | Retrieves data to provide responses to user-initiated prompts. | Takes action based on user prompts. | Retrieves data based on user prompts. |
+| cohere\-ai | [Cohere](https://cohere.com) | Unclear at this time. | Retrieves data to provide responses to user-initiated prompts. | Takes action based on user prompts. | Retrieves data based on user prompts. |
 | Diffbot | [Diffbot](https://www.diffbot.com/) | At the discretion of Diffbot users. | Aggregates structured web data for monitoring and AI model training. | Unclear at this time. | Diffbot is an application used to parse web pages into structured data; this data is used for monitoring or AI model training. |
 | FacebookBot | Meta/Facebook | [Yes](https://developers.facebook.com/docs/sharing/bot/) | Training language models | Up to 1 page per second | Officially used for training Meta "speech recognition technology," unknown if used to train Meta AI specifically. |
 | facebookexternalhit | Meta/Facebook | [Yes](https://developers.facebook.com/docs/sharing/bot/) | No information. | Unclear at this time. | Unclear at this time. |
 | FriendlyCrawler | Unknown | [Yes](https://imho.alex-kunz.com/2024/01/25/an-update-on-friendly-crawler) | We are using the data from the crawler to build datasets for machine learning experiments. | Unclear at this time. | Unclear who the operator is; but data is used for training/machine learning. |
-| Google-Extended | Google | [Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers) | LLM training. | No information. | Used to train Gemini and Vertex AI generative APIs. Does not impact a site's inclusion or ranking in Google Search. |
+| Google\-Extended | Google | [Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers) | LLM training. | No information. | Used to train Gemini and Vertex AI generative APIs. Does not impact a site's inclusion or ranking in Google Search. |
 | GoogleOther | Google | [Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers) | Scrapes data. | No information. | "Used by various product teams for fetching publicly accessible content from sites. For example, it may be used for one-off crawls for internal research and development." |
-| GoogleOther-Image | Google | [Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers) | Scrapes data. | No information. | "Used by various product teams for fetching publicly accessible content from sites. For example, it may be used for one-off crawls for internal research and development." |
+| GoogleOther\-Image | Google | [Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers) | Scrapes data. | No information. | "Used by various product teams for fetching publicly accessible content from sites. For example, it may be used for one-off crawls for internal research and development." |
-| GoogleOther-Video | Google | [Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers) | Scrapes data. | No information. | "Used by various product teams for fetching publicly accessible content from sites. For example, it may be used for one-off crawls for internal research and development." |
+| GoogleOther\-Video | Google | [Yes](https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers) | Scrapes data. | No information. | "Used by various product teams for fetching publicly accessible content from sites. For example, it may be used for one-off crawls for internal research and development." |
 | GPTBot | [OpenAI](https://openai.com) | Yes | Scrapes data to train OpenAI's products. | No information. | Data is used to train current and future models, removed paywalled data, PII and data that violates the company's policies. |
-| iaskspider/2.0 | iAsk | No | Crawls sites to provide answers to user queries. | Unclear at this time. | Used to provide answers to user queries. |
+| iaskspider/2\.0 | iAsk | No | Crawls sites to provide answers to user queries. | Unclear at this time. | Used to provide answers to user queries. |
-| ICC-Crawler | [NICT](https://nict.go.jp) | Yes | Scrapes data to train and support AI technologies. | No information. | Use the collected data for artificial intelligence technologies; provide data to third parties, including commercial companies; those companies can use the data for their own business. |
+| ICC\-Crawler | [NICT](https://nict.go.jp) | Yes | Scrapes data to train and support AI technologies. | No information. | Use the collected data for artificial intelligence technologies; provide data to third parties, including commercial companies; those companies can use the data for their own business. |
 | ImagesiftBot | [ImageSift](https://imagesift.com) | [Yes](https://imagesift.com/about) | ImageSiftBot is a web crawler that scrapes the internet for publicly available images to support our suite of web intelligence products | No information. | Once images and text are downloaded from a webpage, ImageSift analyzes this data from the page and stores the information in an index. Our web intelligence products use this index to enable search and retrieval of similar images. |
 | img2dataset | [img2dataset](https://github.com/rom1504/img2dataset) | Unclear at this time. | Scrapes images for use in LLMs. | At the discretion of img2dataset users. | Downloads large sets of images into datasets for LLM training or other purposes. |
 | ISSCyberRiskCrawler | [ISS-Corporate](https://iss-cyber.com) | No | Scrapes data to train machine learning models. | No information. | Used to train machine learning based models to quantify cyber risk. |
 | Kangaroo Bot | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Kangaroo Bot is used by the company Kangaroo LLM to download data to train AI models tailored to Australian language and culture. More info can be found at https://darkvisitors.com/agents/agents/kangaroo-bot |
-| Meta-ExternalAgent | [Meta](https://developers.facebook.com/docs/sharing/webmasters/web-crawlers) | Yes. | Used to train models and improve products. | No information. | "The Meta-ExternalAgent crawler crawls the web for use cases such as training AI models or improving products by indexing content directly." |
+| Meta\-ExternalAgent | [Meta](https://developers.facebook.com/docs/sharing/webmasters/web-crawlers) | Yes. | Used to train models and improve products. | No information. | "The Meta-ExternalAgent crawler crawls the web for use cases such as training AI models or improving products by indexing content directly." |
-| Meta-ExternalFetcher | Unclear at this time. | Unclear at this time. | AI Assistants | Unclear at this time. | Meta-ExternalFetcher is dispatched by Meta AI products in response to user prompts, when they need to fetch an individual links. More info can be found at https://darkvisitors.com/agents/agents/meta-externalfetcher |
+| Meta\-ExternalFetcher | Unclear at this time. | Unclear at this time. | AI Assistants | Unclear at this time. | Meta-ExternalFetcher is dispatched by Meta AI products in response to user prompts, when they need to fetch an individual links. More info can be found at https://darkvisitors.com/agents/agents/meta-externalfetcher |
-| OAI-SearchBot | [OpenAI](https://openai.com) | [Yes](https://platform.openai.com/docs/bots) | Search result generation. | No information. | Crawls sites to surface as results in SearchGPT. |
+| OAI\-SearchBot | [OpenAI](https://openai.com) | [Yes](https://platform.openai.com/docs/bots) | Search result generation. | No information. | Crawls sites to surface as results in SearchGPT. |
 | omgili | [Webz.io](https://webz.io/) | [Yes](https://webz.io/blog/web-data/what-is-the-omgili-bot-and-why-is-it-crawling-your-website/) | Data is sold. | No information. | Crawls sites for APIs used by Hootsuite, Sprinklr, NetBase, and other companies. Data also sold for research purposes or LLM training. |
 | omgilibot | [Webz.io](https://webz.io/) | [Yes](https://web.archive.org/web/20170704003301/http://omgili.com/Crawler.html) | Data is sold. | No information. | Legacy user agent initially used for Omgili search engine. Unknown if still used, `omgili` agent still used by Webz.io. |
 | PerplexityBot | [Perplexity](https://www.perplexity.ai/) | [No](https://www.macstories.net/stories/wired-confirms-perplexity-is-bypassing-efforts-by-websites-to-block-its-web-crawler/) | Used to answer queries at the request of users. | Takes action based on user prompts. | Operated by Perplexity to obtain results in response to user queries. |
@@ -38,5 +38,11 @@
 | Sidetrade indexer bot | [Sidetrade](https://www.sidetrade.com) | Unclear at this time. | Extracts data for a variety of uses including training AI. | No information. | AI product training. |
 | Timpibot | [Timpi](https://timpi.io) | Unclear at this time. | Scrapes data for use in training LLMs. | No information. | Makes data available for training AI models. |
 | VelenPublicWebCrawler | [Velen Crawler](https://velen.io) | [Yes](https://velen.io) | Scrapes data for business data sets and machine learning models. | No information. | "Our goal with this crawler is to build business datasets and machine learning models to better understand the web." |
-| Webzio-Extended | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Webzio-Extended is a web crawler used by Webz.io to maintain a repository of web crawl data that it sells to other companies, including those using it to train AI models. More info can be found at https://darkvisitors.com/agents/agents/webzio-extended |
+| Webzio\-Extended | Unclear at this time. | Unclear at this time. | AI Data Scrapers | Unclear at this time. | Webzio-Extended is a web crawler used by Webz.io to maintain a repository of web crawl data that it sells to other companies, including those using it to train AI models. More info can be found at https://darkvisitors.com/agents/agents/webzio-extended |
 | YouBot | [You](https://about.you.com/youchat/) | [Yes](https://about.you.com/youbot/) | Scrapes data for search engine and LLMs. | No information. | Retrieves data used for You.com web search engine and LLMs. |
+| crawler\.with\.dots | Test suite | No | To ensure the code works correctly. | No information. | When used in the .htaccess regular expression dots need to be escaped. |
+| star\*\*\*crawler | Test suite | No | To ensure the code works correctly. | No information. | When used in the .htaccess regular expression stars need to be escaped. |
+| Is this a crawler? | Test suite | No | To ensure the code works correctly. | No information. | When used in the .htaccess regular expression spaces and question marks need to be escaped. |
+| a\[mazing\]\{42\}\(robot\) | Test suite | No | To ensure the code works correctly. | No information. | When used in the .htaccess regular expression parantheses, braces, etc. need to be escaped. |
+| 2^32$ | Test suite | No | To ensure the code works correctly. | No information. | When used in the .htaccess regular expression RE anchor characters need to be escaped. |
+| curl\|sudo bash | Test suite | No | To ensure the code works correctly. | No information. | When used in the .htaccess regular expression pipes need to be escaped. |

code/tests.py

@@ -1,27 +1,58 @@
-"""These tests can be run with pytest.
+#!/usr/bin/env python3
-This requires pytest: pip install pytest
+"""To run these tests just execute this script."""
-cd to the `code` directory and run `pytest`
-"""
 
 import json
-from pathlib import Path
+import unittest
 
 from robots import json_to_txt, json_to_table, json_to_htaccess
 
+class RobotsUnittestExtensions:
+    def loadJson(self, pathname):
+        with open(pathname, "rt") as f:
+            return json.load(f)
 
-def test_robots_txt_creation():
+    def assertEqualsFile(self, f, s):
-    robots_json = json.loads(Path("test_files/robots.json").read_text())
+        with open(f, "rt") as f:
-    robots_txt = json_to_txt(robots_json)
+            f_contents = f.read()
-    assert Path("test_files/robots.txt").read_text() == robots_txt
+
+        return self.assertMultiLineEqual(f_contents, s)
 
 
-def test_table_of_bot_metrices_md():
+class TestRobotsTXTGeneration(unittest.TestCase, RobotsUnittestExtensions):
-    robots_json = json.loads(Path("test_files/robots.json").read_text())
+    maxDiff = 8192
-    robots_table = json_to_table(robots_json)
+
-    assert Path("test_files/table-of-bot-metrics.md").read_text() == robots_table
+    def setUp(self):
+        self.robots_dict = self.loadJson("test_files/robots.json")
+
+    def test_robots_txt_generation(self):
+        robots_txt = json_to_txt(self.robots_dict)
+        self.assertEqualsFile("test_files/robots.txt", robots_txt)
 
 
-def test_htaccess_creation():
+class TestTableMetricsGeneration(unittest.TestCase, RobotsUnittestExtensions):
-    robots_json = json.loads(Path("test_files/robots.json").read_text())
+    maxDiff = 32768
-    robots_htaccess = json_to_htaccess(robots_json)
+
-    assert Path("test_files/.htaccess").read_text() == robots_htaccess
+    def setUp(self):
+        self.robots_dict = self.loadJson("test_files/robots.json")
+
+    def test_table_generation(self):
+        robots_table = json_to_table(self.robots_dict)
+        self.assertEqualsFile("test_files/table-of-bot-metrics.md", robots_table)
+
+
+class TestHtaccessGeneration(unittest.TestCase, RobotsUnittestExtensions):
+    maxDiff = 8192
+
+    def setUp(self):
+        self.robots_dict = self.loadJson("test_files/robots.json")
+
+    def test_htaccess_generation(self):
+        robots_htaccess = json_to_htaccess(self.robots_dict)
+        self.assertEqualsFile("test_files/.htaccess", robots_htaccess)
+
+
+if __name__ == "__main__":
+    import os
+    os.chdir(os.path.dirname(__file__))
+
+    unittest.main(verbosity=2)