|
|
@ -1,20 +1,33 @@ |
|
|
|
# In general, scrapers are welcome if they are collecting data for informational uses |
|
|
|
# (such as search engines) and maintain a reasonable rate of scraping. |
|
|
|
# |
|
|
|
# Scrapers from SEO/marketing-type services will be blocked. Tildes data is not a |
|
|
|
# resource to be mined and sold. |
|
|
|
|
|
|
|
# https://ahrefs.com/robot |
|
|
|
User-agent: AhrefsBot |
|
|
|
Disallow: / |
|
|
|
|
|
|
|
# http://webmeup-crawler.com/ |
|
|
|
User-agent: BLEXBot |
|
|
|
Disallow: / |
|
|
|
|
|
|
|
# https://app.hypefactors.com/media-monitoring/about.html |
|
|
|
User-agent: Buck |
|
|
|
Disallow: / |
|
|
|
|
|
|
|
# https://moz.com/help/moz-procedures/crawlers/dotbot |
|
|
|
User-agent: dotbot |
|
|
|
Disallow: / |
|
|
|
|
|
|
|
# Unknown/suspicious scraper - UA only contains a gmail address |
|
|
|
User-agent: MauiBot |
|
|
|
Disallow: / |
|
|
|
|
|
|
|
# https://megaindex.com/crawler |
|
|
|
User-agent: MegaIndex |
|
|
|
Disallow: / |
|
|
|
|
|
|
|
# https://www.semrush.com/bot/ |
|
|
|
User-agent: SemrushBot |
|
|
|
Disallow: / |