tips_httpd.conf_spiders.md 的修订

Erreur32 修订了这个 Gist 6 months ago. 转到此修订

没有任何变更

Glenn Plas 修订了这个 Gist 14 years ago. 转到此修订

1 file changed, 49 insertions, 16 deletions

httpd.conf_spiders

			@@ -1,13 +1,34 @@
1		-	# To relieve the server
2		-	RewriteEngine On
	1	+	# To relieve servers
3	2
4		-	# a robots.txt file is the only file that will be allowed to be downloaded by those bots now, for all virtual servers.
5		-	RewriteRule ^/robots.txt$ /etc/apache2/robots.txt [L]
	3	+	##Imagine a robots.txt file like this (Google understands this format):
	4	+	#User-agent: *
	5	+	#Disallow: /detailed
	6	+	#Disallow: /?action=detailed
	7	+	#Disallow: /*/detailed
	8	+	#Crawl-delay: 20
	9	+	##
6	10
7	11		# to enable these rules , save them to httpd.conf (debian/ubuntu) and include the following 2 lines in each VirtualHost directive
8	12		# RewriteEngine On
9	13		# RewriteOptions Inherit
10	14
	15	+	# Then this will work in your virtualservers as wel as in the main, except for those you don't set up
	16	+
	17	+	# And you want to enforce those policies, you can do this:
	18	+
	19	+	# put this below in your httpd.conf file
	20	+	RewriteEngine On
	21	+
	22	+	# Set a general robots.txt file (For all virtual hosts here) to a file apache can access
	23	+	RewriteRule ^/robots.txt$ /etc/apache2/robots.txt [L]
	24	+	# a robots.txt file is the now the only file that will be allowed to be downloaded by any bots blocked here below
	25	+
	26	+	# Block fake google when it's not coming from their IP range's (A fake googlebot) [F] => Failure
	27	+	RewriteCond %{HTTP:X-FORWARDED-FOR} !^66\.249\.(6[4-9]\|[78][0-9]\|9[0-5])\.
	28	+	RewriteCond %{HTTP_USER_AGENT} ^Mozilla/5\.0\ $compatible;\ Googlebot/2\.[01];\ \+http://www\.google\.com/bot\.html$$ [NC]
	29	+	RewriteRule .* - [F,L]
	30	+	# End if match
	31	+
11	32		# IF THE UA STARTS WITH THESE
12	33		RewriteCond %{HTTP_USER_AGENT} ^(aesop_com_spiderman\|alexibot\|backweb\|bandit\|batchftp\|bigfoot) [NC,OR]
13	34		RewriteCond %{HTTP_USER_AGENT} ^(black.?hole\|blackwidow\|blowfish\|botalot\|buddy\|builtbottough\|bullseye) [NC,OR]
			@@ -33,25 +54,38 @@ RewriteCond %{HTTP_USER_AGENT} ^(superhttp\|surfbot\|asterias\|suzuran\|szukacz\|take
33	54		RewriteCond %{HTTP_USER_AGENT} ^(telesoft\|the.?intraformant\|thenomad\|tighttwatbot\|titan\|urldispatcher) [NC,OR]
34	55		RewriteCond %{HTTP_USER_AGENT} ^(turingos\|turnitinbot\|urly.?warning\|vacuum\|vci\|voideye\|whacker) [NC,OR]
35	56		RewriteCond %{HTTP_USER_AGENT} ^(libwww-perl\|widow\|wisenutbot\|wwwoffle\|xaldon\|xenu\|zeus\|zyborg\|anonymouse) [NC,OR]
36		-	RewriteCond %{HTTP_USER_AGENT} ^(Sogou\ web\ spider) [NC,OR]
	57	+	RewriteCond %{HTTP_USER_AGENT} ^(Sogou\ web\ spider) [NC]
	58	+	# ISSUE 403 / SERVE ERRORDOCUMENT
	59	+	RewriteRule . - [F,L]
	60	+	# End if match
37	61
38		-	# Block google
	62	+	# Block real Engines , not respecting robots.txt but allowing correct calls to pass (all detail searches basically)
	63	+	# It seemst to take about 2 days of 403 to make it respect the robots.txt file, even though this one got downloaded several times
	64	+	# Google
39	65		RewriteCond %{HTTP_USER_AGENT} ^Mozilla/5\.0\ $compatible;\ Googlebot/2\.[01];\ \+http://www\.google\.com/bot\.html$$ [NC,OR]
40		-	# Block bing
	66	+	# Bing
41	67		RewriteCond %{HTTP_USER_AGENT} ^Mozilla/5\.0\ $compatible;\ bingbot/2\.[01];\ \+http://www\.bing\.com/bingbot\.htm$$ [NC,OR]
42		-	# Block msnbot
	68	+	# msnbot
43	69		RewriteCond %{HTTP_USER_AGENT} ^msnbot-media/1\.[01]\ $\+http://search\.msn\.com/msnbot\.htm$$ [NC,OR]
	70	+	# Slurp
	71	+	RewriteCond %{HTTP_USER_AGENT} ^Mozilla/5\.0\ $compatible;\ Yahoo!\ Slurp;\ http://help\.yahoo\.com/help/us/ysearch/slurp$$ [NC]
	72	+	# block all detail searches, the rest may pass (things like /detailed, /EN/detailed and ?action=detailed
	73	+	RewriteCond %{REQUEST_URI} ^(/detailed\|/[A-Z]{2}/detailed/) [OR]
	74	+	# or with the action=detailed key set
	75	+	RewriteCond %{QUERY_STRING} action=detailed
	76	+	# ISSUE 403 / SERVE ERRORDOCUMENT
	77	+	RewriteRule .* - [F,L]
	78	+	# End if match
44	79
45		-	# Some idiot bot
	80	+	# Defenite blocks
46	81		RewriteCond %{HTTP_USER_AGENT} ^Mozilla/5\.0\ $compatible;\ MJ12bot/v1\.4\.2;\ http://www\.majestic12\.co\.uk/bot\.php\?\+$$ [NC,OR]
47		-
48	82		# Baidus
49	83		RewriteCond %{HTTP_USER_AGENT} ^Mozilla/5\.0\ $compatible;\ Baiduspider/2\.[01];\ \+http://www\.baidu\.com/search/spider\.html$$ [NC,OR]
50	84
51	85		# Deepspider
52	86		RewriteCond %{HTTP_USER_AGENT} ^Mozilla/5\.0\ $compatible;\ OpenindexDeepSpider/Nutch-1\.[0-9]-dev;\ \+http://www\.openindex\.io/en/webmasters/spider\.html$$ [NC,OR]
53	87
54		-	# STARTS WITH WEB
	88	+	# Known user agent strings defenitely belonging to bad spiders
55	89		RewriteCond %{HTTP_USER_AGENT} ^web(zip\|emaile\|enhancer\|fetch\|go.?is\|auto\|bandit\|clip\|copier\|master\|reaper\|sauger\|site.?quester\|whack) [NC,OR]
56	90
57	91		# Yandex (russian google)
			@@ -63,14 +97,12 @@ RewriteCond %{HTTP_USER_AGENT} ^Pingdom\.com_bot_version_1\.4_\(http://www\.ping
63	97		# AhrefsBot
64	98		RewriteCond %{HTTP_USER_AGENT} ^Mozilla/5\.0\ $compatible;\ AhrefsBot/2\.[01];\ \+http://ahrefs\.com/robot/$$ [NC,OR]
65	99
66		-	# Some rogue facebook faker ?
	100	+	# Block a rogue facebook application ?
67	101		#RewriteCond %{HTTP_USER_AGENT} ^facebookexternalhit/1\.1\ $\+http://www\.facebook\.com/externalhit_uatext.php$$ [NC,OR]
68		-
	102	+	#
69	103		# Vagabondo
70	104		RewriteCond %{HTTP_USER_AGENT} ^Mozilla/4\.[01]\ $compatible;\ \ Vagabondo/4\.0;\ webcrawler\ at\ wise-guys\ dot\ nl;\ http://webagent\.wise-guys\.nl/;\ http://www\.wise-guys\.nl/$ [NC,OR]
71	105
72		-	# Slurp
73		-	RewriteCond %{HTTP_USER_AGENT} ^Mozilla/5\.0\ $compatible;\ Yahoo!\ Slurp;\ http://help\.yahoo\.com/help/us/ysearch/slurp$$ [NC,OR]
74	106		# Ezooms
75	107		RewriteCond %{HTTP_USER_AGENT} ^Mozilla/5\.0\ $compatible;\ Ezooms/1\.[01];\ ezooms\.bot@gmail\.com$$ [NC,OR]
76	108
			@@ -81,4 +113,5 @@ RewriteCond %{HTTP_USER_AGENT} ^Synthesio\ Crawler\ release\ MonaLisa\ \(contact
81	113		RewriteCond %{HTTP_USER_AGENT} ^.(craftbot\|download\|extract\|stripper\|sucker\|ninja\|clshttp\|webspider\|leacher\|collector\|grabber\|webpictures).$ [NC]
82	114
83	115		# ISSUE 403 / SERVE ERRORDOCUMENT
84		-	RewriteRule . - [F,L]
	116	+	RewriteRule . - [F,L]
	117	+	# End if match

Glenn Plas 修订了这个 Gist 14 years ago. 转到此修订

1 file changed, 84 insertions

httpd.conf_spiders(文件已创建)

		@@ -0,0 +1,84 @@
1	+	# To relieve the server
2	+	RewriteEngine On
3	+
4	+	# a robots.txt file is the only file that will be allowed to be downloaded by those bots now, for all virtual servers.
5	+	RewriteRule ^/robots.txt$ /etc/apache2/robots.txt [L]
6	+
7	+	# to enable these rules , save them to httpd.conf (debian/ubuntu) and include the following 2 lines in each VirtualHost directive
8	+	# RewriteEngine On
9	+	# RewriteOptions Inherit
10	+
11	+	# IF THE UA STARTS WITH THESE
12	+	RewriteCond %{HTTP_USER_AGENT} ^(aesop_com_spiderman\|alexibot\|backweb\|bandit\|batchftp\|bigfoot) [NC,OR]
13	+	RewriteCond %{HTTP_USER_AGENT} ^(black.?hole\|blackwidow\|blowfish\|botalot\|buddy\|builtbottough\|bullseye) [NC,OR]
14	+	RewriteCond %{HTTP_USER_AGENT} ^(cheesebot\|cherrypicker\|chinaclaw\|collector\|copier\|copyrightcheck) [NC,OR]
15	+	RewriteCond %{HTTP_USER_AGENT} ^(cosmos\|crescent\|curl\|custo\|da\|diibot\|disco\|dittospyder\|dragonfly) [NC,OR]
16	+	RewriteCond %{HTTP_USER_AGENT} ^(drip\|easydl\|ebingbong\|ecatch\|eirgrabber\|emailcollector\|emailsiphon) [NC,OR]
17	+	RewriteCond %{HTTP_USER_AGENT} ^(emailwolf\|erocrawler\|exabot\|eyenetie\|filehound\|flashget\|flunky) [NC,OR]
18	+	RewriteCond %{HTTP_USER_AGENT} ^(frontpage\|getright\|getweb\|go.?zilla\|go-ahead-got-it\|gotit\|grabnet) [NC,OR]
19	+	RewriteCond %{HTTP_USER_AGENT} ^(grafula\|harvest\|hloader\|hmview\|httplib\|httrack\|humanlinks\|ilsebot) [NC,OR]
20	+	RewriteCond %{HTTP_USER_AGENT} ^(infonavirobot\|infotekies\|intelliseek\|interget\|iria\|jennybot\|jetcar) [NC,OR]
21	+	RewriteCond %{HTTP_USER_AGENT} ^(joc\|justview\|jyxobot\|kenjin\|keyword\|larbin\|leechftp\|lexibot\|lftp\|libweb) [NC,OR]
22	+	RewriteCond %{HTTP_USER_AGENT} ^(likse\|linkscan\|linkwalker\|lnspiderguy\|lwp\|magnet\|mag-net\|markwatch) [NC,OR]
23	+	RewriteCond %{HTTP_USER_AGENT} ^(mata.?hari\|memo\|microsoft.?url\|midown.?tool\|miixpc\|mirror\|missigua) [NC,OR]
24	+	RewriteCond %{HTTP_USER_AGENT} ^(mister.?pix\|moget\|mozilla.?newt\|nameprotect\|navroad\|backdoorbot\|nearsite) [NC,OR]
25	+	RewriteCond %{HTTP_USER_AGENT} ^(net.?vampire\|netants\|netcraft\|netmechanic\|netspider\|nextgensearchbot) [NC,OR]
26	+	RewriteCond %{HTTP_USER_AGENT} ^(attach\|nicerspro\|nimblecrawler\|npbot\|octopus\|offline.?explorer) [NC,OR]
27	+	RewriteCond %{HTTP_USER_AGENT} ^(offline.?navigator\|openfind\|outfoxbot\|pagegrabber\|papa\|pavuk) [NC,OR]
28	+	RewriteCond %{HTTP_USER_AGENT} ^(pcbrowser\|php.?version.?tracker\|pockey\|propowerbot\|prowebwalker) [NC,OR]
29	+	RewriteCond %{HTTP_USER_AGENT} ^(psbot\|pump\|queryn\|recorder\|realdownload\|reaper\|reget\|true_robot) [NC,OR]
30	+	RewriteCond %{HTTP_USER_AGENT} ^(repomonkey\|rma\|internetseer\|sitesnagger\|siphon\|slysearch\|smartdownload) [NC,OR]
31	+	RewriteCond %{HTTP_USER_AGENT} ^(snake\|snapbot\|snoopy\|sogou\|spacebison\|spankbot\|spanner\|sqworm\|superbot) [NC,OR]
32	+	RewriteCond %{HTTP_USER_AGENT} ^(superhttp\|surfbot\|asterias\|suzuran\|szukacz\|takeout\|teleport) [NC,OR]
33	+	RewriteCond %{HTTP_USER_AGENT} ^(telesoft\|the.?intraformant\|thenomad\|tighttwatbot\|titan\|urldispatcher) [NC,OR]
34	+	RewriteCond %{HTTP_USER_AGENT} ^(turingos\|turnitinbot\|urly.?warning\|vacuum\|vci\|voideye\|whacker) [NC,OR]
35	+	RewriteCond %{HTTP_USER_AGENT} ^(libwww-perl\|widow\|wisenutbot\|wwwoffle\|xaldon\|xenu\|zeus\|zyborg\|anonymouse) [NC,OR]
36	+	RewriteCond %{HTTP_USER_AGENT} ^(Sogou\ web\ spider) [NC,OR]
37	+
38	+	# Block google
39	+	RewriteCond %{HTTP_USER_AGENT} ^Mozilla/5\.0\ $compatible;\ Googlebot/2\.[01];\ \+http://www\.google\.com/bot\.html$$ [NC,OR]
40	+	# Block bing
41	+	RewriteCond %{HTTP_USER_AGENT} ^Mozilla/5\.0\ $compatible;\ bingbot/2\.[01];\ \+http://www\.bing\.com/bingbot\.htm$$ [NC,OR]
42	+	# Block msnbot
43	+	RewriteCond %{HTTP_USER_AGENT} ^msnbot-media/1\.[01]\ $\+http://search\.msn\.com/msnbot\.htm$$ [NC,OR]
44	+
45	+	# Some idiot bot
46	+	RewriteCond %{HTTP_USER_AGENT} ^Mozilla/5\.0\ $compatible;\ MJ12bot/v1\.4\.2;\ http://www\.majestic12\.co\.uk/bot\.php\?\+$$ [NC,OR]
47	+
48	+	# Baidus
49	+	RewriteCond %{HTTP_USER_AGENT} ^Mozilla/5\.0\ $compatible;\ Baiduspider/2\.[01];\ \+http://www\.baidu\.com/search/spider\.html$$ [NC,OR]
50	+
51	+	# Deepspider
52	+	RewriteCond %{HTTP_USER_AGENT} ^Mozilla/5\.0\ $compatible;\ OpenindexDeepSpider/Nutch-1\.[0-9]-dev;\ \+http://www\.openindex\.io/en/webmasters/spider\.html$$ [NC,OR]
53	+
54	+	# STARTS WITH WEB
55	+	RewriteCond %{HTTP_USER_AGENT} ^web(zip\|emaile\|enhancer\|fetch\|go.?is\|auto\|bandit\|clip\|copier\|master\|reaper\|sauger\|site.?quester\|whack) [NC,OR]
56	+
57	+	# Yandex (russian google)
58	+	RewriteCond %{HTTP_USER_AGENT} ^Mozilla/5\.0\ $compatible;\ YandexBot/3\.[01];\ \+http://yandex\.com/bots$$ [NC,OR]
59	+
60	+	# Pingdom
61	+	RewriteCond %{HTTP_USER_AGENT} ^Pingdom\.com_bot_version_1\.4_$http://www\.pingdom\.com/$ [NC,OR]
62	+
63	+	# AhrefsBot
64	+	RewriteCond %{HTTP_USER_AGENT} ^Mozilla/5\.0\ $compatible;\ AhrefsBot/2\.[01];\ \+http://ahrefs\.com/robot/$$ [NC,OR]
65	+
66	+	# Some rogue facebook faker ?
67	+	#RewriteCond %{HTTP_USER_AGENT} ^facebookexternalhit/1\.1\ $\+http://www\.facebook\.com/externalhit_uatext.php$$ [NC,OR]
68	+
69	+	# Vagabondo
70	+	RewriteCond %{HTTP_USER_AGENT} ^Mozilla/4\.[01]\ $compatible;\ \ Vagabondo/4\.0;\ webcrawler\ at\ wise-guys\ dot\ nl;\ http://webagent\.wise-guys\.nl/;\ http://www\.wise-guys\.nl/$ [NC,OR]
71	+
72	+	# Slurp
73	+	RewriteCond %{HTTP_USER_AGENT} ^Mozilla/5\.0\ $compatible;\ Yahoo!\ Slurp;\ http://help\.yahoo\.com/help/us/ysearch/slurp$$ [NC,OR]
74	+	# Ezooms
75	+	RewriteCond %{HTTP_USER_AGENT} ^Mozilla/5\.0\ $compatible;\ Ezooms/1\.[01];\ ezooms\.bot@gmail\.com$$ [NC,OR]
76	+
77	+	# Monalisa
78	+	RewriteCond %{HTTP_USER_AGENT} ^Synthesio\ Crawler\ release\ MonaLisa\ $contact\ at\ synthesio\ dot\ fr$$ [NC,OR]
79	+
80	+	# ANYWHERE IN UA -- GREEDY REGEX
81	+	RewriteCond %{HTTP_USER_AGENT} ^.(craftbot\|download\|extract\|stripper\|sucker\|ninja\|clshttp\|webspider\|leacher\|collector\|grabber\|webpictures).$ [NC]
82	+
83	+	# ISSUE 403 / SERVE ERRORDOCUMENT
84	+	RewriteRule . - [F,L]