Merge pull request #68 from MassiminoilTrace/main

Implementing automatic htaccess generation

.htaccess

@@ -0,0 +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|cohere-training-data-crawler|Diffbot|DuckAssistBot|FacebookBot|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|PanguBot|PerplexityBot|PetalBot|Scrapy|SemrushBot|Sidetrade\ indexer\ bot|Timpibot|VelenPublicWebCrawler|Webzio-Extended|YouBot).*$ [NC]
+RewriteRule .* - [F,L]

README.md

@@ -8,9 +8,21 @@ A number of these crawlers have been sourced from [Dark Visitors](https://darkvi
 
 If you'd like to add information about a crawler to the list, please make a pull request with the bot name added to `robots.txt`, `ai.txt`, and any relevant details in `table-of-bot-metrics.md` to help people understand what's crawling.
 
+## Usage
+
+This repository provides the following files:
+- `robots.txt`
+- `.htaccess`
+
+`robots.txt` implements the Robots Exclusion Protocol ([RFC 9309](https://www.rfc-editor.org/rfc/rfc9309.html)).
+
+`.htaccess` may be used to configure web servers such as [Apache httpd](https://httpd.apache.org/) to return an error page when one of the listed AI crawlers sends a request to the web server.
+Note that, as stated in the [httpd documentation](https://httpd.apache.org/docs/current/howto/htaccess.html), more performant methods than an `.htaccess` file exist.
+
+
 ## Contributing
 
-A note about contributing: updates should be added/made to `robots.json`. A GitHub action, courtesy of [Adam](https://github.com/newbold), will then generate the updated `robots.txt` and `table-of-bot-metrics.md`.
+A note about contributing: updates should be added/made to `robots.json`. A GitHub action will then generate the updated `robots.txt`, `table-of-bot-metrics.md`, and `.htaccess`.
 
 ## Subscribe to updates
 

code/robots.py

@@ -132,10 +132,27 @@ def json_to_table(robots_json):
     return table
 
 
+def json_to_htaccess(robot_json):
+    # Creates a .htaccess filter file. It uses a regular expression to filter out
+    # User agents that contain any of the blocked values.
+    htaccess = "RewriteEngine On\n"
+    htaccess += "RewriteCond %{HTTP_USER_AGENT} ^.*("
+
+    # Escape spaces in each User Agent to build the regular expression
+    robots = map(lambda el: el.replace(" ", "\\ "), robot_json.keys())
+    htaccess += "|".join(robots)
+    htaccess += ").*$ [NC]\n"
+    htaccess += "RewriteRule .* - [F,L]"
+    return htaccess
+
+
 def update_file_if_changed(file_name, converter):
     """Update files if newer content is available and log the (in)actions."""
     new_content = converter(load_robots_json())
-    old_content = Path(file_name).read_text(encoding="utf-8")
+    filepath = Path(file_name)
+    # "touch" will create the file if it doesn't exist yet
+    filepath.touch()
+    old_content = filepath.read_text(encoding="utf-8")
     if old_content == new_content:
         print(f"{file_name} is already up to date.")
     else:
@@ -150,6 +167,10 @@ def conversions():
         file_name="./table-of-bot-metrics.md",
         converter=json_to_table,
     )
+    update_file_if_changed(
+        file_name="./.htaccess",
+        converter=json_to_htaccess,
+    )
 
 
 if __name__ == "__main__":

code/test_files/.htaccess

@@ -0,0 +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]
+RewriteRule .* - [F,L]

code/tests.py

@@ -6,7 +6,7 @@ cd to the `code` directory and run `pytest`
 import json
 from pathlib import Path
 
-from robots import json_to_txt, json_to_table
+from robots import json_to_txt, json_to_table, json_to_htaccess
 
 
 def test_robots_txt_creation():
@@ -19,3 +19,9 @@ def test_table_of_bot_metrices_md():
     robots_json = json.loads(Path("test_files/robots.json").read_text())
     robots_table = json_to_table(robots_json)
     assert Path("test_files/table-of-bot-metrics.md").read_text() == robots_table
+
+
+def test_htaccess_creation():
+    robots_json = json.loads(Path("test_files/robots.json").read_text())
+    robots_htaccess = json_to_htaccess(robots_json)
+    assert Path("test_files/.htaccess").read_text() == robots_htaccess