cdransf/ai.robots.txt
1
1
Fork 0
mirror of https://github.com/ai-robots-txt/ai.robots.txt.git synced 2025-04-04 19:13:57 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

.htaccess: Make regex in RewriteCond safe

Browse source 
Improve the regular expression by removing unneeded anchors and
escaping special characters (not just space) to prevent false positives
or a misbehaving rewrite rule.
This commit is contained in:
Dennis Camera 2025-02-17 21:00:57 +01:00
parent c0d418cd87
commit a884a2afb9
3 changed files with 12 additions and 11 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
.htaccess
View file

@ -1,3 +1,3 @@
RewriteEngine On RewriteEngine On
RewriteCond %{HTTP_USER_AGENT} ^.*(AI2Bot|Ai2Bot-Dolma|Amazonbot|anthropic-ai|Applebot|Applebot-Extended|Brightbot\ 1.0|Bytespider|CCBot|ChatGPT-User|Claude-Web|ClaudeBot|cohere-ai|cohere-training-data-crawler|Crawlspace|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-OCOB|SemrushBot-SWA|Sidetrade\ indexer\ bot|Timpibot|VelenPublicWebCrawler|Webzio-Extended|YouBot).*$ [NC] RewriteCond %{HTTP_USER_AGENT} (AI2Bot|Ai2Bot\-Dolma|Amazonbot|anthropic\-ai|Applebot|Applebot\-Extended|Brightbot\ 1\.0|Bytespider|CCBot|ChatGPT\-User|Claude\-Web|ClaudeBot|cohere\-ai|cohere\-training\-data\-crawler|Crawlspace|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\-OCOB|SemrushBot\-SWA|Sidetrade\ indexer\ bot|Timpibot|VelenPublicWebCrawler|Webzio\-Extended|YouBot) [NC]
RewriteRule !^/?robots\.txt$ - [F,L] RewriteRule !^/?robots\.txt$ - [F,L]

19
code/robots.py
View file

@ -1,8 +1,9 @@
import json import json
from pathlib import Path import re
import requests import requests
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
from pathlib import Path
def load_robots_json(): def load_robots_json():
@ -99,7 +100,6 @@ def updated_robots_json(soup):
def ingest_darkvisitors(): def ingest_darkvisitors():
old_robots_json = load_robots_json() old_robots_json = load_robots_json()
soup = get_agent_soup() soup = get_agent_soup()
if soup: if soup:
@ -132,16 +132,17 @@ def json_to_table(robots_json):
return table return table
def list_to_pcre(lst):
# Python re is not 100% identical to PCRE which is used by Apache, but it
# should probably be close enough in the real world for re.escape to work.
return f"({"|".join(map(re.escape, lst))})"
def json_to_htaccess(robot_json): def json_to_htaccess(robot_json):
# Creates a .htaccess filter file. It uses a regular expression to filter out # Creates a .htaccess filter file. It uses a regular expression to filter out
# User agents that contain any of the blocked values. # User agents that contain any of the blocked values.
htaccess = "RewriteEngine On\n" htaccess = "RewriteEngine On\n"
htaccess += "RewriteCond %{HTTP_USER_AGENT} ^.*(" htaccess += f"RewriteCond %{{HTTP_USER_AGENT}} {list_to_pcre(robot_json.keys())} [NC]\n"
# 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 !^/?robots\\.txt$ - [F,L]\n" htaccess += "RewriteRule !^/?robots\\.txt$ - [F,L]\n"
return htaccess return htaccess

2
code/test_files/.htaccess
View file

@ -1,3 +1,3 @@
RewriteEngine On 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) [NC]
RewriteRule !^/?robots\.txt$ - [F,L] RewriteRule !^/?robots\.txt$ - [F,L]