param20h.github.io/robots.txt at main · param20h/param20h.github.io · 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
# Main Robots.txt for param20h.me
# Allow all search engines

User-agent: *
Allow: /
Allow: /media/
Allow: /*.js
Allow: /*.css

# Sitemap
Sitemap: https://param20h.me/sitemap.xml

# Disallow crawling of specific files and directories
Disallow: /package-lock.json
Disallow: /package.json
Disallow: /.github/
Disallow: /_next/static/
Disallow: /api/
Disallow: /.git/
Disallow: /node_modules/

# Crawl-delay for polite crawling
Crawl-delay: 1

# Specific rules for Google
User-agent: Googlebot
Allow: /
Allow: /media/
Disallow: /api/

# Specific rules for Bing
User-agent: Bingbot
Allow: /
Allow: /media/
Disallow: /api/

# Allow image indexing
User-agent: Googlebot-Image
Allow: /media/

# Allow mobile crawling
User-agent: Googlebot-Mobile
Allow: /