#
# robots.txt
#
# This file is to prevent the crawling and indexing of certain parts
# of your site by web crawlers and spiders run by sites like Yahoo!
# and Google. By telling these "robots" where not to go on your site,
# you save bandwidth and server resources.
#
# This file will be ignored unless it is at the root of your host:
# Used:    http://example.com/robots.txt
# Ignored: http://example.com/site/robots.txt
#
# For more information about the robots.txt standard, see:
# http://www.robotstxt.org/robotstxt.html


User-agent: *
Disallow: /*utm_source*
Disallow: /*fireglass*
Disallow: /*kui*
Disallow: /*session_id*
Disallow: /*sid*
Disallow: /*itok*
Disallow: /*scope*
Disallow: /*delta*
Disallow: /*123*
Disallow: /*tags*
Disallow: /sites/default/files/documents/lca-documents/*
Disallow: /*careers/job-openings?page*
Disallow: /*careers/job-opportunities?page*
Disallow: /*careers/lca-postings?page*
Disallow: /jobs/*/*
Disallow: /sites/default/files/js/js*
Disallow: /taxonomy/*
Disallow: /sites/default/files/Investors-day-December-2022.zip
Disallow: /sites/default/files/documents/Details_of_Reclassified_P_L_Data_Quarter-wiseFY22.xlsx

# Files
Disallow: /CHANGELOG.txt
Disallow: /cron.php
Disallow: /INSTALL.mysql.txt
Disallow: /INSTALL.pgsql.txt
Disallow: /INSTALL.sqlite.txt
Disallow: /install.php
Disallow: /INSTALL.txt
Disallow: /LICENSE.txt
Disallow: /MAINTAINERS.txt
Disallow: /update.php
Disallow: /UPGRADE.txt
Disallow: /xmlrpc.php
Disallow: /file*

# Paths (clean URLs)
Disallow: /admin/
Disallow: /comment/reply/
Disallow: /filter/tips/
Disallow: /logout/
Disallow: /node/add/
Disallow: */node/*
Disallow: /search/
Disallow: /user*

# Paths (no clean URLs)
Disallow: /*?q=*
Disallow: /?q=admin/
Disallow: /?q=comment/reply/
Disallow: /?q=filter/tips/
Disallow: /?q=logout/
Disallow: /?q=node/add/
Disallow: /?q=search/
Disallow: /?q=user/password/
Disallow: /?q=user/register/
Disallow: /?q=user/login/
Disallow: /?q=user/logout/

#boost
Disallow: /boost_stats.php

#Thankyou 
Disallow: */thank-you
Disallow: */thankyou

# 404
Disallow: /404
Disallow: /subscribe*
Disallow: /nodequeue/*

Allow: /*.jpeg
Allow: /*.jpg
Allow: /*.gif
Allow: /*.png
Allow: /*.svg
Allow: /*.webp
Allow: /*.pdf
Allow: /*.js
Allow: /*.css

# SemRush
User-agent: SemrushBot
Disallow: *careers*
Disallow: *jobs*
Disallow: /*?*=*

User-agent: SiteAuditBot
Disallow: *careers*
Disallow: *jobs*
Disallow: /*?*=*

sitemap: https://www.hcltech.com/sitemap.xml