opendev/system-config
Code Issues Proposed changes

gitea: crawler UA reject rules

Browse Source 
As described inline, this crawler is causing us problems as it hits
the backends indiscriminately.  Block it via the known UA strings,
which luckily are old so should not cause real client issues.

Change-Id: I0d78a8b625b69f600e00e8b3ea64576e0fdb84d9
This commit is contained in:
Ian Wienand 2020-07-01 12:54:00 +10:00
parent 870f664648
commit 8d0d6155ed
2 changed files with 52 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

45
playbooks/roles/gitea/templates/gitea.vhost.j2
View File

@ -24,6 +24,51 @@ Listen 3081
SSLProxyEngine on
RewriteEngine On
# This interesting list is taken from
#
# https://github.com/mythsman/weiboCrawler/blob/master/opener.py
#
# which appears to be a crawler for a site "weibo" which is crawling
# gitea relentlessly. It seems to rotate though these to avoid
# detection. We are seeing these very specific user-agents appear
# suggesting this code has been repurposed or has otherwise gone mad
# and started going through opendev.org
RewriteCond %{HTTP_USER_AGENT} "=Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50" [OR]
RewriteCond %{HTTP_USER_AGENT} "=Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50" [OR]
RewriteCond %{HTTP_USER_AGENT} "=Mozilla/5.0 (Windows NT 10.0; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0" [OR]
RewriteCond %{HTTP_USER_AGENT} "=Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1" [OR]
RewriteCond %{HTTP_USER_AGENT} "=Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1" [OR]
RewriteCond %{HTTP_USER_AGENT} "=Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11" [OR]
RewriteCond %{HTTP_USER_AGENT} "=Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11" [OR]
RewriteCond %{HTTP_USER_AGENT} "=Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11" [OR]
RewriteCond %{HTTP_USER_AGENT} "=Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)" [OR]
RewriteCond %{HTTP_USER_AGENT} "=Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)" [OR]
RewriteCond %{HTTP_USER_AGENT} "=Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)" [OR]
RewriteCond %{HTTP_USER_AGENT} "=Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)" [OR]
RewriteCond %{HTTP_USER_AGENT} "=Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)" [OR]
RewriteCond %{HTTP_USER_AGENT} "=Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; 360SE)" [OR]
RewriteCond %{HTTP_USER_AGENT} "=Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Avant Browser)" [OR]
RewriteCond %{HTTP_USER_AGENT} "=Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)" [OR]
RewriteCond %{HTTP_USER_AGENT} "=Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5" [OR]
RewriteCond %{HTTP_USER_AGENT} "=Mozilla/5.0 (iPod; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5" [OR]
RewriteCond %{HTTP_USER_AGENT} "=Mozilla/5.0 (iPad; U; CPU OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5" [OR]
RewriteCond %{HTTP_USER_AGENT} "=Mozilla/5.0 (Linux; U; Android 2.3.7; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1" [OR]
RewriteCond %{HTTP_USER_AGENT} "=MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1" [OR]
RewriteCond %{HTTP_USER_AGENT} "=Opera/9.80 (Android 2.3.4; Linux; Opera Mobi/build-1107180945; U; en-GB) Presto/2.8.149 Version/11.10" [OR]
RewriteCond %{HTTP_USER_AGENT} "=Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13" [OR]
RewriteCond %{HTTP_USER_AGENT} "=Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; en) AppleWebKit/534.1+ (KHTML, like Gecko) Version/6.0.0.337 Mobile Safari/534.1+" [OR]
RewriteCond %{HTTP_USER_AGENT} "=Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.0; U; en-US) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/233.70 Safari/534.6 TouchPad/1.0" [OR]
RewriteCond %{HTTP_USER_AGENT} "=Mozilla/5.0 (SymbianOS/9.4; Series60/5.0 NokiaN97-1/20.0.019; Profile/MIDP-2.1 Configuration/CLDC-1.1) AppleWebKit/525 (KHTML, like Gecko) BrowserNG/7.1.18124" [OR]
RewriteCond %{HTTP_USER_AGENT} "=Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)" [OR]
RewriteCond %{HTTP_USER_AGENT} "=UCWEB7.0.2.37/28/999" [OR]
RewriteCond %{HTTP_USER_AGENT} "=NOKIA5700/ UCWEB7.0.2.37/28/999" [OR]
RewriteCond %{HTTP_USER_AGENT} "=Openwave/ UCWEB7.0.2.37/28/999" [OR]
RewriteCond %{HTTP_USER_AGENT} "=Mozilla/4.0 (compatible; MSIE 6.0; ) Opera/UCWEB7.0.2.37/28/999"
RewriteRule . - [R=403,L]
ProxyPass / https://localhost:3000/ retry=0
ProxyPassReverse / https://localhost:3000/

7
testinfra/test_gitea.py
View File

@ -47,3 +47,10 @@ def test_proxy(host):
'--resolve gitea99.opendev.org:3081:127.0.0.1 '
'https://gitea99.opendev.org:3081/')
assert 'Git with a cup of tea' in cmd.stdout
def test_proxy_ua_blacklist(host):
cmd = host.run('curl --insecure -A '
'" Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; TencentTraveler 4.0)" '
'--resolve gitea99.opendev.org:3081:127.0.0.1 '
'https://gitea99.opendev.org:3081/')
assert '403 Forbidden' in cmd.stdout