NeuralCrawl

Weather / robots.txt snapshot

← back to weather.com · fetched 2026-11-06T08:00:37Z (1d ago) · HTTP 200 · 3532 bytes · sha256 3cb9ab77300b08a6 · raw

final URL: https://weather.com/robots.txt

1#
2# /robots.txt
3#
4
5#
6# Last updated by nick.hester 10/26/2026
7#
8
9#
10# AI / AEO bot policy (CW-9994)
11# We explicitly allow AI bots that fetch pages on behalf of a user's direct
12# request (answer engines like ChatGPT-User, Brightbot) so our content can
13# be cited in AI-generated answers. Bulk AI-training/indexing crawlers
14# remain blocked below under "Block Bots" (e.g. YouBot, Google-CloudVertexBot).
15#
16
17# Explicit Allows
18
19User-agent: ChatGPT-User
20Allow: /
21
22User-agent: AmazonAdBot
23Allow: /
24
25User-agent: Brightbot 1.0
26Allow: /
27
28User-agent: CriteoBot/0.1
29Allow: /
30
31# Disallowed for PhantomJS
32
33User-agent: *
34Crawl-delay: 10
35# Directories
36Disallow: /includes/
37Disallow: /life/
38Disallow: /misc/
39Disallow: /modules/
40Disallow: /profiles/
41Disallow: /scripts/
42Disallow: /themes/
43Disallow: /api/payload
44Allow: /api/payload/v1/sitemaps
45Disallow: /taxonomy/
46# Files
47Disallow: /appspromo
48Disallow: /CHANGELOG.txt
49Disallow: /cron.php
50Disallow: /INSTALL.mysql.txt
51Disallow: /INSTALL.pgsql.txt
52Disallow: /INSTALL.sqlite.txt
53Disallow: /install.php
54Disallow: /INSTALL.txt
55Disallow: /LICENSE.txt
56Disallow: /MAINTAINERS.txt
57Disallow: /update.php
58Disallow: /UPGRADE.txt
59Disallow: /xmlrpc.php
60# Paths (clean URLs)
61Disallow: /migration/
62Disallow: /admin/
63Disallow: /comment/reply/
64Disallow: /filter/tips/
65Disallow: /node/add/
66Disallow: /search/
67Disallow: /user/register/
68Disallow: /user/password/
69Disallow: /user/login/
70Disallow: /user/logout/
71# Paths (no clean URLs)
72Disallow: /*?apiKey=
73Disallow: /*&apiKey=
74Disallow: /?q=admin/
75Disallow: /?q=comment/reply/
76Disallow: /?q=filter/tips/
77Disallow: /?q=node/add/
78Disallow: /?q=search/
79Disallow: /?q=user/password/
80Disallow: /?q=user/register/
81Disallow: /?q=user/login/
82Disallow: /?q=user/logout/
83
84Disallow: /sponsored
85Disallow: /ugc
86Disallow: /sponsored-content
87
88Disallow: /api/v1/p/redux-dal
89# International weather language URL paths (404s)
90Disallow: /tiempo/
91Disallow: /clima/
92Disallow: /temps/
93Disallow: /vreme/
94Disallow: /idojaras/
95Disallow: /pogoda/
96Disallow: /wetter/
97Disallow: /vejret/
98Disallow: /pocasi/
99Disallow: /cuaca/
100Disallow: /weer/
101# Duplicate forecast URLs that canonicalize to the param-less page (CW-12397)
102Disallow: /*?t=
103Disallow: /*&t=
104Disallow: /*?metric=
105Disallow: /*&metric=
106
107#
108# Block Bots
109#
110
111User-agent: Amazonbot
112Disallow: /
113
114User-agent: AwarioRssBot
115User-agent: AwarioSmartBot
116Disallow: /
117
118User-agent: Bytespider
119Disallow: /
120
121User-agent: CCBot
122Disallow: /
123
124User-agent: DataForSeoBot
125Disallow: /
126
127User-agent: Diffbot
128Disallow: /
129
130User-agent: FacebookBot
131Disallow: /
132
133User-agent: FriendlyCrawler
134Disallow: /
135
136User-agent: Google-CloudVertexBot
137Disallow: /
138
139User-agent: GoogleOther
140Disallow: /
141
142User-agent: ImagesiftBot
143Disallow: /
144
145User-agent: magpie-crawler
146Disallow: /
147
148User-agent: NewsNow
149Disallow: /
150
151User-agent: news-please
152Disallow: /
153
154User-agent: omgili
155Disallow: /
156
157User-agent: omgilibot
158Disallow: /
159
160User-agent: peer39_crawler
161User-agent: peer39_crawler/1.0
162Disallow: /
163
164User-agent: Quora-Bot
165Disallow: /
166
167User-agent: Scrapy
168Disallow: /
169
170User-agent: TurnitinBot
171Disallow: /
172
173User-agent: YouBot
174Disallow: /
175
176#
177# Sitemaps
178#
179
180Sitemap: https://weather.com/en-US/sitemaps/bios-sitemap.xml
181Sitemap: https://weather.com/en-US/sitemaps/collections-manual.xml
182Sitemap: https://weather.com/api/payload/v1/sitemaps/en-US/news.xml
183Sitemap: https://weather.com/de-DE/sitemaps/sitemap.xml
184Sitemap: https://weather.com/es-US/sitemaps/sitemap.xml
185Sitemap: https://weather.com/api/payload/v1/sitemaps/en-US/sitemap.xml
186Sitemap: https://weather.com/api/location/sitemaps/en-US/sitemap.xml