atlasanalyticslab.github.io/robots.txt at main · AtlasAnalyticsLab/atlasanalyticslab.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
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
---
layout: null
permalink: /robots.txt
---

# ============================================
# Atlas Analytics Lab – robots.txt
# Goals:
#  - Maximize search engine indexing (all agents)
#  - Avoid crawl-delay except where supported
#  - Block known heavy scraper bots
#  - Keep CSS/JS/images crawlable
# ============================================

# --- Major search engines (explicitly allowed) ---
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

User-agent: SeznamBot
Allow: /

# --- Block known heavy scraper / SEO bots ---
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

# --- Optional: block AI training crawlers ---
# User-agent: GPTBot
# Disallow: /
# User-agent: CCBot
# Disallow: /
# User-agent: anthropic-ai
# Disallow: /
# User-agent: Claude-Web
# Disallow: /

# --- Default rule: allow all other crawlers ---
User-agent: *
Allow: /

# Hide build artifacts if they ever appear (normally not deployed)
Disallow: /_site/
Disallow: /bin/

# Sitemap location
Sitemap: {{ site.url }}{{ site.baseurl }}/sitemap.xml