bioRxiv / robots.txt snapshot
← back to biorxiv.org · fetched 2026-06-26T14:15:22Z (4h ago) · HTTP 200 · 3637 bytes · sha256 1cc8ace946ec6935 · raw
final URL: https://www.biorxiv.org/robots.txt
| 1 | # |
| 2 | # robots.txt |
| 3 | # |
| 4 | # This file is to prevent the crawling and indexing of certain parts |
| 5 | # of your site by web crawlers and spiders run by sites like Yahoo! |
| 6 | # and Google. By telling these "robots" where not to go on your site, |
| 7 | # you save bandwidth and server resources. |
| 8 | # |
| 9 | # This file will be ignored unless it is at the root of your host: |
| 10 | # Used: http://example.com/robots.txt |
| 11 | # Ignored: http://example.com/site/robots.txt |
| 12 | # |
| 13 | # For more information about the robots.txt standard, see: |
| 14 | # http://www.robotstxt.org/robotstxt.html |
| 15 | |
| 16 | User-agent: BLEXBot |
| 17 | Disallow: / |
| 18 | User-agent: Bytespider |
| 19 | Disallow: / |
| 20 | User-agent: Exabot |
| 21 | Disallow: / |
| 22 | User-agent: Scanbot |
| 23 | Disallow: / |
| 24 | User-agent: Semrush |
| 25 | Disallow: / |
| 26 | User-agent: SemrushBot |
| 27 | Disallow: / |
| 28 | User-agent: YoudaoBot |
| 29 | Disallow: / |
| 30 | User-agent: Baiduspider |
| 31 | Disallow: / |
| 32 | User-agent: YandexBot |
| 33 | Disallow: / |
| 34 | User-agent: openai |
| 35 | Disallow: / |
| 36 | User-agent: Petalbot |
| 37 | Disallow: / |
| 38 | User-agent: Bolt |
| 39 | Disallow: / |
| 40 | User-agent: BunnySlippers |
| 41 | Disallow: / |
| 42 | User-agent: ChatGPT-User |
| 43 | Disallow: / |
| 44 | User-agent: GPTBot |
| 45 | Disallow: / |
| 46 | User-agent: Gigabot |
| 47 | Disallow: / |
| 48 | User-agent: HybridBot |
| 49 | Disallow: / |
| 50 | User-agent: JikeSpider |
| 51 | Disallow: / |
| 52 | User-agent: SMTBot |
| 53 | Disallow: / |
| 54 | User-agent: ScreenerBot |
| 55 | Disallow: / |
| 56 | User-agent: SiteLockSpider |
| 57 | Disallow: / |
| 58 | User-agent: SuperBot |
| 59 | Disallow: / |
| 60 | User-agent: SuperHTTP |
| 61 | Disallow: / |
| 62 | User-agent: Amazonbot |
| 63 | Disallow: / |
| 64 | User-agent: AhrefsBot |
| 65 | Disallow: / |
| 66 | User-agent: Applebot |
| 67 | Disallow: / |
| 68 | User-agent: SEMrush |
| 69 | Disallow: / |
| 70 | User-agent: DataForSeoBot |
| 71 | Disallow: / |
| 72 | User-agent: ClaudeBot |
| 73 | Disallow: / |
| 74 | User-agent: DotBot |
| 75 | Disallow: / |
| 76 | User-agent: phxbot |
| 77 | Disallow: / |
| 78 | User-agent: AwarioBot |
| 79 | Disallow: / |
| 80 | User-agent: SeekportBot |
| 81 | Disallow: / |
| 82 | User-agent: MJ12bot |
| 83 | Disallow: / |
| 84 | User-agent: Majestic12 |
| 85 | Disallow: / |
| 86 | User-agent: facebookexternalhit/1.1 |
| 87 | Disallow: / |
| 88 | User-agent: PerplexityBot |
| 89 | Disallow: / |
| 90 | User-agent: Qwantbot |
| 91 | Disallow: / |
| 92 | User-agent: CCBot |
| 93 | Disallow: / |
| 94 | User-agent: python-requests/2.32.3 |
| 95 | Disallow: / |
| 96 | User-agent: wget |
| 97 | Disallow: / |
| 98 | User-agent: curl |
| 99 | Disallow: / |
| 100 | |
| 101 | User-agent: * |
| 102 | Crawl-delay: 7 |
| 103 | # CSS, JS, Images |
| 104 | Allow: /misc/*.css$ |
| 105 | Allow: /misc/*.css? |
| 106 | Allow: /misc/*.js$ |
| 107 | Allow: /misc/*.js? |
| 108 | Allow: /misc/*.gif |
| 109 | Allow: /misc/*.jpg |
| 110 | Allow: /misc/*.jpeg |
| 111 | Allow: /misc/*.png |
| 112 | Allow: /modules/*.css$ |
| 113 | Allow: /modules/*.css? |
| 114 | Allow: /modules/*.js$ |
| 115 | Allow: /modules/*.js? |
| 116 | Allow: /modules/*.gif |
| 117 | Allow: /modules/*.jpg |
| 118 | Allow: /modules/*.jpeg |
| 119 | Allow: /modules/*.png |
| 120 | Allow: /profiles/*.css$ |
| 121 | Allow: /profiles/*.css? |
| 122 | Allow: /profiles/*.js$ |
| 123 | Allow: /profiles/*.js? |
| 124 | Allow: /profiles/*.gif |
| 125 | Allow: /profiles/*.jpg |
| 126 | Allow: /profiles/*.jpeg |
| 127 | Allow: /profiles/*.png |
| 128 | Allow: /themes/*.css$ |
| 129 | Allow: /themes/*.css? |
| 130 | Allow: /themes/*.js$ |
| 131 | Allow: /themes/*.js? |
| 132 | Allow: /themes/*.gif |
| 133 | Allow: /themes/*.jpg |
| 134 | Allow: /themes/*.jpeg |
| 135 | Allow: /themes/*.png |
| 136 | # Directories |
| 137 | Disallow: /includes/ |
| 138 | Disallow: /misc/ |
| 139 | Disallow: /modules/ |
| 140 | Disallow: /profiles/ |
| 141 | Disallow: /scripts/ |
| 142 | Disallow: /themes/ |
| 143 | # Files |
| 144 | Disallow: /CHANGELOG.txt |
| 145 | Disallow: /cron.php |
| 146 | Disallow: /INSTALL.mysql.txt |
| 147 | Disallow: /INSTALL.pgsql.txt |
| 148 | Disallow: /INSTALL.sqlite.txt |
| 149 | Disallow: /install.php |
| 150 | Disallow: /INSTALL.txt |
| 151 | Disallow: /LICENSE.txt |
| 152 | Disallow: /MAINTAINERS.txt |
| 153 | Disallow: /update.php |
| 154 | Disallow: /UPGRADE.txt |
| 155 | Disallow: /xmlrpc.php |
| 156 | # Paths (clean URLs) |
| 157 | Disallow: /admin/ |
| 158 | Disallow: /comment/reply/ |
| 159 | Disallow: /filter/tips/ |
| 160 | Disallow: /node/add/ |
| 161 | Disallow: /search/ |
| 162 | Disallow: /user/register/ |
| 163 | Disallow: /user/password/ |
| 164 | Disallow: /user/login/ |
| 165 | Disallow: /user/logout/ |
| 166 | # Paths (no clean URLs) |
| 167 | Disallow: /?q=admin/ |
| 168 | Disallow: /?q=comment/reply/ |
| 169 | Disallow: /?q=filter/tips/ |
| 170 | Disallow: /?q=node/add/ |
| 171 | Disallow: /?q=search/ |
| 172 | Disallow: /?q=user/password/ |
| 173 | Disallow: /?q=user/register/ |
| 174 | Disallow: /?q=user/login/ |
| 175 | Disallow: /?q=user/logout/ |
| 176 | Disallow: /user |