MAQSoftware/robots.txt at master · maqsoftware/MAQSoftware · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
# Robots.txt for MAQ Software
# This file provides crawling instructions for search engine bots

# Allow all crawlers to access the entire site
User-agent: *
Allow: /

# Sitemap location for search engines
Sitemap: https://maqsoftware.com/sitemap.xml

# Specific instructions for major search engines
User-agent: Googlebot
Allow: /
Crawl-delay: 1

User-agent: Bingbot
Allow: /
Crawl-delay: 1

User-agent: Slurp
Allow: /
Crawl-delay: 1

# Block access to administrative and sensitive directories (if they exist)
Disallow: /admin/
Disallow: /private/
Disallow: /.git/
Disallow: /node_modules/
Disallow: /temp/
Disallow: /tmp/
Disallow: /archived/

# Block access to specific file types that shouldn't be indexed
Disallow: /*.log$

# Allow access to important resources for SEO
Allow: /css/
Allow: /js/
Allow: /images/
Allow: /img/
Allow: /fonts/

# Block specific files that shouldn't be indexed but allow important content
Disallow: /package.json
Disallow: /Gruntfile.js
Disallow: /README.md

# Allow important pages that might have extensions
Allow: /privacystatement.html
Allow: /termsofservice.html
Allow: /pbivisualeula.html