add invalid domain name exclusion logic

This commit is contained in:
gently 2020-02-04 17:01:51 +08:00
parent 48a85cb473
commit d830ab8fca
19 changed files with 82003 additions and 16652 deletions

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@ -222,16 +222,22 @@ class addressMaker{
if(count($tmp_arr1) > 2 && (1 !== $formatObj['full_domain'])){
for($tmp_pos = 3; $tmp_pos <= count($tmp_arr1); $tmp_pos++){
$tmp_arr2 = array_slice($tmp_arr1, -1 * $tmp_pos);
if(in_array(implode('.', $tmp_arr2), $rv)){
if(!in_array(implode('.', $tmp_arr2), $arr_written)){
if(array_key_exists(implode('.', $tmp_arr2), $GLOBALS['arr_whitelist'])){
$tmp_domain = implode('.', $tmp_arr2);
if(array_key_exists($tmp_domain, $GLOBALS['arr_whitelist'])
&& (1 === $GLOBALS['arr_whitelist'][$tmp_domain])){
$written_flag = true;
break;
}
if(in_array($tmp_domain, $rv)){
if(!in_array($tmp_domain, $arr_written)){
if(array_key_exists($tmp_domain, $GLOBALS['arr_whitelist'])){
continue;
}
$arr_written[] = implode('.', $tmp_arr2);
$arr_written[] = $tmp_domain;
$write_len += fwrite(
$fp,
str_replace('{DOMAIN}',
implode('.', $tmp_arr2),
$tmp_domain,
$formatObj['format']
) . "\n"
);

View File

@ -2,6 +2,7 @@
//white_domain_list
//白名单机制...,白名单是
//@date 2018年12月23日
//如果value=1,则其下级域名全部加白例如3级域名则其4级子域名全部加白
return array(
@ -12,7 +13,7 @@ return array(
'googleadapis.l.google.com' => 0, //解决google字体下载异常
'gstaticadssl.l.google.com' => 0, //解决google字体下载异常
'gvt2.com' => 1, //gvt2安卓系统相关
'wangbase.com' => 1, //阮一峰同志的博客图片显示如果value=1并且是根域名则整条加白
'wangbase.com' => 1, //阮一峰同志的博客图片显示
'l.qq.com' => 0, //解决腾讯视频无法播放
'dldir1.qq.com' => 0, //qq下载安装包路径
'cgi.connect.qq.com' => 0, //qq互联

View File

@ -22,6 +22,11 @@ $arr_whitelist = require ROOT_DIR . 'lib/white_domain_list.php';
require ROOT_DIR . 'lib/writerFormat.class.php';
require ROOT_DIR . 'lib/addressMaker.class.php';
//白名单机制增强加入dead hosts
$arr_dead_hosts = file(ROOT_DIR . 'origin-files/base-src-dead-hosts.txt', FILE_SKIP_EMPTY_LINES | FILE_IGNORE_NEW_LINES);
$arr_dead_hosts=array_fill_keys($arr_dead_hosts, 1); //这里设置为1表示命中的子域名同时加白
$arr_whitelist = array_merge($arr_dead_hosts, $arr_whitelist);
$arr_result = array();
$easylist = file_get_contents('./origin-files/base-src-easylist.txt');
$arr_result = array_merge_recursive($arr_result, addressMaker::get_domain_from_easylist($easylist));

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@ -492,6 +492,7 @@
127.0.0.1 ad.madvertise.de
127.0.0.1 ad.mail.ru
127.0.0.1 ad.mail.sohu.com
127.0.0.1 ad.mi.com
127.0.0.1 ad.mnt123.com
127.0.0.1 ad.mo.doubleclick.net
127.0.0.1 ad.molitv.cn
@ -1901,6 +1902,7 @@
127.0.0.1 cdn.fastclick.net
127.0.0.1 cdn.flurry.com
127.0.0.1 cdn.hivps.xyz
127.0.0.1 cdn.hpplay.com.cn
127.0.0.1 cdn.hyperpromote.com
127.0.0.1 cdn.iclicash.com
127.0.0.1 cdn.img.kachapt.cn
@ -2196,6 +2198,7 @@
127.0.0.1 conabi.xjditan.com
127.0.0.1 conde.adsame.com
127.0.0.1 conf.funshion.com
127.0.0.1 conf.hpplay.cn
127.0.0.1 conf.vidown.cn
127.0.0.1 conf.xiniuz.com
127.0.0.1 config-ltvp.inmobi.com
@ -3571,6 +3574,7 @@
127.0.0.1 finead.cn
127.0.0.1 finewe.ljqnbiogjp.com
127.0.0.1 fips.uimserv.net
127.0.0.1 fix.hpplay.cn
127.0.0.1 fjdvzx.cn
127.0.0.1 flash.2144.com
127.0.0.1 flash.cn
@ -7747,6 +7751,7 @@
127.0.0.1 sdk2.youguoquan.com
127.0.0.1 sdkapp.mobile.sina.cn
127.0.0.1 sdkapp.uve.weibo.com
127.0.0.1 sdkauth.hpplay.cn
127.0.0.1 sdkclick.mobile.sina.cn
127.0.0.1 sdkconfig.ad.intl.xiaomi.com
127.0.0.1 sdkconfig.ad.xiaomi.com
@ -8124,6 +8129,7 @@
127.0.0.1 staging.admin.e.mi.com
127.0.0.1 staging2.crazyegg.com
127.0.0.1 stags.bluekai.com
127.0.0.1 starfish.pandora.xiaomi.com
127.0.0.1 startup.oupeng.com
127.0.0.1 stat-y.xywy.com
127.0.0.1 stat-z.xywy.com

31243
origin-files/dead-hosts0.txt Normal file

File diff suppressed because it is too large Load Diff

9399
origin-files/dead-hosts1.txt Normal file

File diff suppressed because it is too large Load Diff

File diff suppressed because one or more lines are too long

View File

@ -1,7 +1,7 @@
[Adblock Plus 2.0]
! Version: 202001300854
! Version: 202002021635
! Title: CJX's Annoyance List
! Last modified: 2020/01/30 08:54 +0800
! Last modified: 2020/02/02 16:35 +0800
! Expires: 4 days (update frequency)
! Homepage: http://abpchina.org/forum/forum.php?mod=viewthread&tid=29667
!
@ -367,6 +367,8 @@
||3158.cn/min/webim.
||3158.cn/static/js/fixbtm/
!------------------------Specific element hiding rules------------------------!
blog.csdn.net##.t0
so.com##.newsfeed-popup
feng.com##.header
sogou.com##.recommend-pop
sm.cn##.oab-ball-wrap
@ -671,7 +673,6 @@ fwxgx.com###jPpo_sc
goodcome.com.tw###jad-float
goodcome.com.tw###jad-right
goodcome.com.tw###jad-top
dianyingbar.com###jihuaslide
douyu.com###js-fix-download
douyu.com###js-live-room-recommend
163.com###js_a_bobo
@ -795,7 +796,6 @@ medsci.cn##.adv1201
8264.com##.advSection__wrapper
eastmoney.com##.advertisement
cngold.org##.ag_fwindow_ywp
dianyingbar.com##.alert_windows
jiankang.com##.all_eye
tmall.com##.app-download-popup
baidu.com##.app-guide
@ -1002,7 +1002,6 @@ m.babytree.com##.recommend-img-box
news.baidu.com##.recommend-mask
longzhu.com##.recommend-pop-up
m.toutiao.com##.recommendation-container + div[class]
dianyingbar.com##.recover
oschina.net##.recruitment
p2peye.com##.red-box
baixing.com##.red-package
@ -1130,6 +1129,7 @@ m.babytree.com##script + a[class]
/v.gif?logtype=
/yesky/js/counter/*
/zcool-analytics.js
||syzjxz2018.cn^
||gog.cn/sys/online_calc.js
||ip.ws.126.net^$domain=~fxingw.com
||dhgxl8qk9zgzr.cloudfront.net/js/log.js

File diff suppressed because one or more lines are too long

View File

@ -1,7 +1,7 @@
[Adblock Plus 1.1]
! Version: 202002011222
! Version: 202002040850
! Title: EasyPrivacy
! Last modified: 01 Feb 2020 12:22 UTC
! Last modified: 04 Feb 2020 08:50 UTC
! Expires: 4 days (update frequency)
! Homepage: https://easylist.to/
! Licence: https://easylist.to/pages/licence.html
@ -106,6 +106,7 @@
-tracking/ga-
-tracking?referrer=
-trackingScript.
-unbxdAnalytics.
-universal-analytics/
-v1/tracking/
-xtcore.js
@ -693,6 +694,7 @@
/analytics/js$script
/analytics/klaviyo_
/analytics/liferay-
/analytics/listeners/*
/analytics/logging
/analytics/mbox.js
/analytics/mbox_
@ -1836,6 +1838,7 @@
/ga-collect?
/ga-custom-tracking.
/ga-custom-vars.
/ga-events.js
/ga-explorations.
/ga-integration-$script
/ga-links.js
@ -4884,6 +4887,7 @@
=getSideStats&
=googleanalytics_
=metrics_profile&
=pageImpression&
=stats&action=
=stats&apiVersion=
=track_view&
@ -6433,6 +6437,7 @@ _mongo_stats/
||iperceptions.com^$third-party
||ipfingerprint.com^$third-party
||ipgeolocation.io^$third-party
||ipgp.net^$third-party
||ipify.org^$third-party
||ipinfo.info^$third-party
||ipinfodb.com^$third-party
@ -11146,6 +11151,7 @@ _mongo_stats/
||tracker.softcube.com^
||tracker.timesgroup.com^
||tracker.twenga.
||tracker.unbxdapi.com^
||tracker.wpserveur.net^
||trackerapi.truste.com^
||trackicollect.ibase.fr^$third-party
@ -15519,7 +15525,6 @@ $csp=worker-src 'none',domain=alltube.pl|alltube.tv|animeteatr.ru|annuaire-bleu.
||hisense.com/ta.js
||ifeng.com/i?p=
||imgstat.baidu.com^
||imp.appledaily.com^
||jcm.jd.com^
||jiayuan.com^*/pv.js
||js.kuwo.cn/stat/
@ -16106,6 +16111,7 @@ $csp=worker-src 'none',domain=alltube.pl|alltube.tv|animeteatr.ru|annuaire-bleu.
@@||amplitude.com/libs/amplitude-$script,third-party
@@||ampproject.org/v0/amp-geo-$script,domain=tasty.co
@@||analytics.edgekey.net/html5/akamaihtml5-min.js$domain=abcnews.go.com|foxbusiness.com|foxnews.com
@@||analytics.edgekey.net/ma_library/html5/html5_malibrary.js$script,domain=mxplayer.in
@@||analytics.edgesuite.net/config/beacon-*.xml$domain=foxnews.com
@@||analytics.edgesuite.net/html5/akamaihtml5-min.js$domain=abcnews.go.com|foxbusiness.com|foxnews.com|resignationbrewery.com|threenow.co.nz
@@||analytics.logsss.com/logsss*.min.js$script,domain=rosegal.com
@ -16114,7 +16120,7 @@ $csp=worker-src 'none',domain=alltube.pl|alltube.tv|animeteatr.ru|annuaire-bleu.
@@||ancestrycdn.com/ui-static/lib/tracking/$domain=ancestry.com
@@||api-track.delhivery.com/track?waybillId=$~third-party,xmlhttprequest
@@||api.academia.edu^*/stats?callback$script,~third-party
@@||api.perfops.net^$script,xmlhttprequest,domain=dnsperf.com
@@||api.perfops.net^$script,xmlhttprequest,domain=cdnperf.com|dnsperf.com
@@||api.segment.io/v1/$xmlhttprequest,domain=instacart.com
@@||api.vidaxl.com^*/trackingservice/customerportal/*?$xmlhttprequest,domain=tracking.vidaxl.com
@@||aramex.co.nz/Umbraco/Api/Tracking/
@ -16190,6 +16196,7 @@ $csp=worker-src 'none',domain=alltube.pl|alltube.tv|animeteatr.ru|annuaire-bleu.
@@||eplayerhtml5.performgroup.com/js/tsEplayerHtml5/js/Eplayer/js/quantcast/$script
@@||events-collector.spot.im/api/$xmlhttprequest
@@||evestment.com/api/analytics/$domain=evestment.com
@@||evil-inc.com/comic/advertising-age/$~third-party,xmlhttprequest
@@||fccbrea.org^*/swfaddress.js
@@||fifa.com^*/webanalytics.js?
@@||firstdirect.com^*/logging-code.js
@ -16316,6 +16323,7 @@ $csp=worker-src 'none',domain=alltube.pl|alltube.tv|animeteatr.ru|annuaire-bleu.
@@||repco.co.nz/_ui/shared/js/analyticsmediator.js
@@||res-x.com^*/Resonance.aspx?
@@||retailmenot.com/__wsm.gif$ping,xmlhttprequest
@@||rum.perfops.net/rum.min.js$script,domain=cdnperf.com
@@||sahibinden.com/assets/analytics*.js$script
@@||sbphototours.com/includes/AWStats.js$~third-party
@@||scorecardresearch.com/beacon.js$domain=agame.com|allmusic.com|amctv.com|apl.tv|babycenter.com|bonappetit.com|calgaryherald.com|canada.com|cbc.ca|dailymail.co.uk|dailymotion.com|deviantart.com|discovery.com|doctoroz.com|edmontonjournal.com|fastcompany.com|financialpost.com|firstwefeast.com|hitfix.com|huffingtonpost.com|investigationdiscovery.com|landandfarm.com|last.fm|leaderpost.com|m.tmz.com|montrealgazette.com|nationalpost.com|newsday.com|ottawacitizen.com|outsideonline.com|radaronline.com|salon.com|sci2.tv|syfy.com|theprovince.com|thestar.com|thestarphoenix.com|thinkatheist.com|tlc.com|tmz.com|v3.co.uk|vancouversun.com|windsorstar.com
@ -16335,6 +16343,7 @@ $csp=worker-src 'none',domain=alltube.pl|alltube.tv|animeteatr.ru|annuaire-bleu.
@@||static.atgsvcs.com/js/atgsvcs.js$domain=officedepot.com|shop.lego.com
@@||static.parsely.com^$script,domain=express.co.uk
@@||staticflickr.com^*/analytics-min.js$domain=flickr.com
@@||supertaxi.com/webclient/scripts/tracking/tracking.js$script,~third-party
@@||t.st/video/js/kGoogleAnalytics.js?$domain=thestreet.com
@@||tagcommander.com^*/tc_$script
@@||tags.news.com.au/prod/heartbeat/
@ -16369,6 +16378,7 @@ $csp=worker-src 'none',domain=alltube.pl|alltube.tv|animeteatr.ru|annuaire-bleu.
@@||wordpress.org/extend/plugins/wp-slimstat/screenshot-$image,~third-party
@@||wordpress.org/wp-slimstat/assets/banner-$image,~third-party
@@||wp.com^*/google-analytics-for-wordpress/$domain=wordpress.org
@@||wplogout.com/wp-content/uploads/*Google$image,~third-party
@@||xfinity.com^*/Comcast.SelfService.Sitecatalyst.js
@@||yandex.ru/metrika/watch.js$domain=engwords.net
@@||yimg.com/ss/rapid3.js$script,domain=techcrunch.com
@ -16501,7 +16511,6 @@ $csp=worker-src 'none',domain=alltube.pl|alltube.tv|animeteatr.ru|annuaire-bleu.
@@||aixifan.com^*/sensorsdata.min.js?$domain=acfun.cn
@@||dynamicyield.com/api/$script,domain=zalora.com.hk|zalora.com.tw
@@||google-analytics.com/analytics.js$domain=news.gamme.com.tw
@@||imp.appledaily.com/js/nxm_tr_v20s.js
@@||tianxun.com^*/js/tracker.js
@@||uwants.com/include/*/swfaddress.js
@@||vanclimg.com/js.ashx?*/google-analytics.js$domain=vancl.com
@ -16517,7 +16526,7 @@ $csp=worker-src 'none',domain=alltube.pl|alltube.tv|animeteatr.ru|annuaire-bleu.
@@||analytics.ooyala.com/static/analytics.js$script,domain=humo.be
@@||centprod.com/nd/assets/js/analytics.js$script,domain=centprod.com
@@||d2zv6vzmaqao5e.cloudfront.net/css/foodticket/*_google_analytics.js
@@||googletagmanager.com/gtm.js?$script,domain=mediamarkt.nl
@@||googletagmanager.com/gtm.js$script,domain=beterbed.nl|mediamarkt.nl
! Finnish
@@||adobedtm.com^*/satelliteLib-$script,domain=gigantti.fi
@@||cnetcontent.com/jsc/h.js$domain=atea.fi

View File

@ -14,7 +14,7 @@
# Localhost (DO NOT REMOVE) End
#*********************************************************
#url=https://github.com/neofelhz/neohosts
#version=20200107044043
#version=20200203044454
#*********************************************************
0.0.0.0 0127.adsame.com

View File

@ -1,5 +1,5 @@
#version=202002011445
#version=202002031001
#url=https://github.com/vokins/yhosts
127.0.0.1 activate.adobe.com
127.0.0.1 ereg.adobe.com
@ -1266,12 +1266,14 @@
127.0.0.1 t.ksrong.com
127.0.0.1 vasapi.rdtuijian.com
127.0.0.1 info.iciba.com
127.0.0.1 ad.mi.com
127.0.0.1 mivideo.g.mi.com
127.0.0.1 bss.pandora.xiaomi.com
127.0.0.1 de.pandora.xiaomi.com
127.0.0.1 dvb.pandora.xiaomi.com
127.0.0.1 jellyfish.pandora.xiaomi.com
127.0.0.1 starfish.pandora.xiaomi.com
127.0.0.1 stat.pandora.xiaomi.com
127.0.0.1 mivideo.g.mi.com
127.0.0.1 stats.mokeedev.com
127.0.0.1 adsfs.oppomobile.com
127.0.0.1 adx.ads.oppomobile.com
@ -1563,6 +1565,12 @@
127.0.0.1 mlog.hiido.com
127.0.0.1 ylog.hiido.com
127.0.0.1 v.smtcdns.net
127.0.0.1 ad.hpplay.cn
127.0.0.1 adeng.hpplay.cn
127.0.0.1 conf.hpplay.cn
127.0.0.1 fix.hpplay.cn
127.0.0.1 sdkauth.hpplay.cn
127.0.0.1 cdn.hpplay.com.cn
127.0.0.1 jrlt.beacon.qq.com
127.0.0.1 log.tbs.qq.com
127.0.0.1 activeqq.3g.qq.com

View File

@ -21,9 +21,15 @@ strict_hosts=(
"https://raw.githubusercontent.com/hoshsadiq/adblock-nocoin-list/master/hosts.txt"
)
dead_hosts=(
"https://raw.githubusercontent.com/notracking/hosts-blocklists-scripts/master/domains.dead.txt"
"https://raw.githubusercontent.com/notracking/hosts-blocklists-scripts/master/hostnames.dead.txt"
)
rm -f ./origin-files/easylist*
rm -f ./origin-files/hosts*
rm -f ./origin-files/strict-hosts*
rm -f ./origin-files/dead-hosts*
for i in "${!easylist[@]}"
do
@ -58,6 +64,17 @@ do
fi
done
for i in "${!dead_hosts[@]}"
do
echo "开始下载 dead-hosts${i}..."
curl -o "./origin-files/dead-hosts${i}.txt" --connect-timeout 60 -s "${dead_hosts[$i]}"
# shellcheck disable=SC2181
if [ $? -ne 0 ];then
echo '下载失败,请重试'
exit 1
fi
done
cd origin-files
@ -71,6 +88,10 @@ cat strict-hosts*.txt | grep -v -E "^((#.*)|(\s*))$" \
| sed s/0.0.0.0/127.0.0.1/g | sed s/::/127.0.0.1/g | sort \
| uniq >base-src-strict-hosts.txt
cat dead-hosts*.txt | grep -v -E "^(#|\!)" \
| sort \
| uniq >base-src-dead-hosts.txt
cat easylist*.txt | grep -E "^\|\|[^\*\^]+?\^" | sort | uniq >base-src-easylist.txt
cat easylist*.txt | grep -E "^\|\|?([^\^=\/:]+)?\*([^\^=\/:]+)?\^" | sort | uniq >wildcard-src-easylist.txt
@ -79,4 +100,5 @@ cat easylist*.txt | grep -E "^@@\|\|?[^\^=\/:]+?\^([^\/=\*]+)?$" | sort | uniq >
cd ../
php make-addr.php
echo
php ./tools/easylist-extend.php anti-ad-easylist.txt