Update Rules

This commit is contained in:
SukkaW 2021-11-30 02:56:10 +08:00
parent 58ce1dafd0
commit a0168be5fd
4 changed files with 10769 additions and 4932 deletions

View File

@ -2,6 +2,8 @@ const { simpleGet } = require('./util-http-get');
const { promises: fsPromises } = require('fs');
const { resolve: pathResolve } = require('path');
const rIPv4 = /((25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.){3}(25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)/;
let Piscina;
try {
Piscina = require('piscina');
@ -55,7 +57,7 @@ async function processHosts(hostsUrl, includeAllSubDomain = false) {
if (line.includes('#')) {
return;
}
if (line.startsWith(' ') || line === '' || line.startsWith('\r') || line.startsWith('\n')) {
if (line.startsWith(' ') || line.startsWith('\r') || line.startsWith('\n') || line.trim() === '') {
return;
}
const [, ...domains] = line.split(' ');
@ -103,15 +105,16 @@ async function processFilterRules(filterRulesUrl) {
const filterRules = (await simpleGet.https(filterRulesUrl.hostname, filterRulesUrl.pathname)).split('\n');
filterRules.forEach(line => {
if (
line.startsWith('#')
|| line.startsWith('!')
line.includes('#')
|| line.includes('!')
|| line.startsWith(' ')
|| line === ''
|| line.startsWith('\r')
|| line.startsWith('\n')
|| line.includes('*')
|| line.includes('/')
|| line.includes('$')
|| line.trim() === ''
|| rIPv4.test(line)
) {
return;
}
@ -153,9 +156,8 @@ async function processFilterRules(filterRulesUrl) {
// Parse from remote hosts & domain lists
(await Promise.all([
processHosts('https://pgl.yoyo.org/adservers/serverlist.php?hostformat=hosts&showintro=1&mimetype=plaintext', true),
processHosts('https://raw.githubusercontent.com/hoshsadiq/adblock-nocoin-list/master/hosts.txt'),
processHosts('https://cdn.jsdelivr.net/gh/neoFelhz/neohosts@gh-pages/full/hosts')
processHosts('https://pgl.yoyo.org/adservers/serverlist.php?hostformat=hosts&showintro=0&mimetype=plaintext', true),
processHosts('https://raw.githubusercontent.com/hoshsadiq/adblock-nocoin-list/master/hosts.txt')
])).forEach(hosts => {
hosts.forEach(host => {
if (host) {
@ -198,7 +200,12 @@ async function processFilterRules(filterRulesUrl) {
processFilterRules('https://raw.githubusercontent.com/AdguardTeam/FiltersRegistry/master/filters/filter_11_Mobile/filter.txt'),
processFilterRules('https://raw.githubusercontent.com/AdguardTeam/FiltersRegistry/master/filters/filter_3_Spyware/filter.txt'),
processFilterRules('https://raw.githubusercontent.com/AdguardTeam/FiltersRegistry/master/filters/filter_2_English/filter.txt'),
processFilterRules('https://raw.githubusercontent.com/AdguardTeam/FiltersRegistry/master/filters/filter_224_Chinese/filter.txt')
processFilterRules('https://raw.githubusercontent.com/AdguardTeam/FiltersRegistry/master/filters/filter_224_Chinese/filter.txt'),
processFilterRules('https://filters.adtidy.org/extension/ublock/filters/224.txt'),
processFilterRules('https://easylist.to/easylist/easyprivacy.txt'),
processFilterRules('https://raw.githubusercontent.com/DandelionSprout/adfilt/master/GameConsoleAdblockList.txt'),
processFilterRules('https://raw.githubusercontent.com/Perflyst/PiHoleBlocklist/master/SmartTV-AGH.txt'),
processFilterRules('https://curben.gitlab.io/malware-filter/urlhaus-filter-agh-online.txt')
])).forEach(({ white, black }) => {
white.forEach(i => filterRuleWhitelistDomainSets.add(i));
black.forEach(i => domainSets.add(i));
@ -232,34 +239,31 @@ async function processFilterRules(filterRulesUrl) {
filename: pathResolve(__dirname, 'worker/build-reject-domainset-worker.js')
});
const res2 = await Promise.all([
(await Promise.all([
piscina.run({ keywords: domainKeywordsSet, suffixes: domainSuffixSet, input: domainSets }, { name: 'dedupeKeywords' }),
piscina.run({ whiteList: filterRuleWhitelistDomainSets, input: domainSets }, { name: 'whitelisted' }),
piscina.run({ whiteList: filterRuleWhitelistDomainSets, input: domainSets }, { name: 'whitelisted' })
])).forEach(set => {
set.forEach(i => domainSets.delete(i));
});
const fullSet = new Set([...domainSets]);
(await Promise.all(
Array.from(domainSets).reduce((result, element, index) => {
const chunk = index % 12;
result[chunk] = result[chunk] ?? [];
result[chunk].push(element);
return result;
}, []).map(chunk => piscina.run({ input: chunk, fullSet: domainSets }, { name: 'dedupe' }))
]);
res2.forEach(set => {
}, []).map(chunk => piscina.run({ input: chunk, fullSet }, { name: 'dedupe' }))
)).forEach(set => {
set.forEach(i => domainSets.delete(i));
});
const diffDeduping = beforeDeduping - domainSets.size;
console.log(`Deduped ${beforeDeduping - domainSets.size} rules!`);
console.log(`Deduped ${diffDeduping} rules!`);
return fsPromises.writeFile(pathResolve(__dirname, '../List/domainset/reject.conf'), `${[...domainSets].join('\n')}\n`);
return fsPromises.writeFile(
pathResolve(__dirname, '../List/domainset/reject.conf'),
`${[...domainSets].join('\n')}\n`,
{ encoding: 'utf-8' });
})();
function sliceIntoChunks(arr, chunkSize) {
const res = [];
for (let i = 0; i < arr.length; i += chunkSize) {
const chunk = arr.slice(i, i + chunkSize);
res.push(chunk);
}
return res;
}

File diff suppressed because it is too large Load Diff

View File

@ -3,8 +3,6 @@
# >> General
.kuaizip.com
.mackeeper.com
.2345.com
.2345.cn
.xiniuz.com
.marketo.com
.sharethrough.com
@ -19,8 +17,9 @@ optimus-ads.amap.com
hot.m.shouji.360tpcdn.com
.update.360safe.com
inst.360safe.com
pdown.stat.360safe.com
.down.360.cn
.se.360.cn
.data.360safe.com
# >> Crypto Coin Hive
.coinhive.com
@ -28,12 +27,15 @@ pdown.stat.360safe.com
.coin-hive.com
.authcaptcha.com
.browsermine.com
.flashx.cc
.flashx.pw
.nimiq.agency
.nimiq.network
.nimiq-network.com
.nimiq.com
.hostcontent.live
.cfcdist.loan
.cfcnet.top
# >> Makeding
.4009997658.com
@ -175,11 +177,18 @@ pdown.stat.360safe.com
.zhaozecheng.cn
.zhenxinet.com
.zzd6.com
.dopa.com
.dopa.com.cn
.ok365.com
.114so.cn
.dragonparking.com
# --- AD Block ---
# >> General
.airpush.com
.adbxb.cn
.admedia.com
.addthisedge.com
.addthis.com
@ -217,6 +226,7 @@ stat.loli.net
.bidvertiser.com
.awempire.com
.adtechjp.com
.adtech.de
.adtilt.com
.advertising.com
.adview.cn
@ -251,6 +261,7 @@ stat.loli.net
.coolguang.com
.conviva.com
.criteo.com
.criteo.net
.crwdcntrl.net
.ctrmi.com
.demdex.net
@ -396,7 +407,6 @@ adsapi.manhuaren.com
adsdk.dmzj.com
adshows.21cn.com
adui.tg.meitu.com
.ad.cmvideo.cn
app-ad.variflight.com
applog.mobike.com
appnext.hs.llnwd.net
@ -426,14 +436,26 @@ advertpay-vip-ssl.xunlei.com
.advertising.speed.cdn.vip.xunlei.com
.advertpay.vip.xunlei.com
.youmi.net
.logger.baofeng.com
.houyi.baofeng.net
.moviebox.baofeng.net
.stat.kankan.com
.cm.kankan.com
.videojj.com
.jizzads.com
.mobisage.com
.adsensor.cn
.ymapp.com
.adcolony.com
.adpro.cn
.pro.cn
.adpush.cn
.adsage.com
.adsage.cn
.adsmogo.com
.carbonads.net
.carbonads.com
.openx.net
.domob.cn
.doumob.com
@ -464,6 +486,18 @@ advertpay-vip-ssl.xunlei.com
mlog.hiido.com
ylog.hiido.com
.channeladvisor.com
.adcome.cn
.aduu.cn
.adirects.com
.admarket.mobi
www.kuguopush.com
.keyrun.cn
.linkpage.cn
.ulink.cc
.yoyi.tv
.adimg.deviantart.net
.adcast.deviantart.com
.inside.bitcomet.com
.youxiaoad.com
.iteye.com
@ -499,12 +533,9 @@ supersonicads-a.akamaihd.net
.ad-plus.cn
.hot-mob.com
.hyperpromote.com
.leadboltads.
.propellerads.com
.quantserve.com
.sharethis.com
.turn.com
.ad-stir.com
.adfurikun.jp
.ad-cloud.jp
@ -515,6 +546,11 @@ adcloud.jp
.aaxdetect.com
.districtm.io
.buysellads.net
.servedby-buysellads.com
.viglink.com
.pixels.asia
.snapmobileasia.net
.intellitxt.com
.ad.wx.com
.ad.weixin.qq.com
@ -525,10 +561,15 @@ adcloud.jp
.ad4.udn.com
.ad5.udn.com
events.jianshu.io
.mobileadtrading.com
# >> Tracking
tracking.yorg.app
.tealiumiq.com
stats.wp.com
js.monitor.azure.com
pixel.wp.com
.monitor.azure.com
.cloudflareinsights.com
.histats.com
.appmetrica.yandex.net
@ -556,7 +597,8 @@ beacon.wikia-services.com
.growingio.com
.gtags.net
.statcounter.com
api.segment.io
.segment.io
cdn.segment.com
snap.licdn.com
report.meituan.com
.amplitude.com
@ -568,6 +610,10 @@ analytics.slashdotmedia.com
.ads.pro-market.net
.stat.xtom.com
.analytics.archive.org
.stats.yinyuetai.com
.collect.yinyuetai.com
.sdklog.uu.cc
.tagtic.cn
.adjust.io
.airbrake.io
@ -600,6 +646,12 @@ analytics.slashdotmedia.com
.union.6.cn
api-analytics-cn.huami.com
.stats.mokeedev.com
tongji.tom.com
ads.tvb.com
ad.juksy.com
.actonservice.com
# >> Alexa
data.alexa.com
device-metrics-us.amazon.com
@ -740,7 +792,6 @@ fav.simba.taobao.com
feedback.whalecloud.com
ff.win.taobao.com
fm.p0y.cn
.click.taobao.com
g.tbcdn.cn
gma.alicdn.com
gtms01.alicdn.com
@ -842,7 +893,6 @@ click.qianqian.com
.cpro.baidu.com
.mpro.baidu.com
log.music.baidu.com
.tuisong.baidu.com
.sestat.baidu.com
.shadu.baidu.com
ae.bdstatic.com
@ -893,6 +943,7 @@ videopush.baidu.com
.tuijian.baidu.com
# >> Qihoo 360
.stat.360safe.com
adapi.shouji.360.cn
msg.shouji.360.cn
.lianmeng.360.cn
@ -900,7 +951,7 @@ dev.tg.wan.360.cn
huodong.ios.shouji.360.cn
kuaikan.netmon.360safe.com
leak.360.cn
openbox.mobilem.360.cn
.mobilem.360.cn
.s.360.cn
.jiagu.360.cn
pub.se.360.cn
@ -999,6 +1050,8 @@ ad.yixin.im
iadmat.nosdn.127.net
iadmusicmat.music.126.net
iadmusicmatvideo.music.126.net
.clkservice.youdao.com
.union.youdao.com
impservice.dictapp.youdao.com
impservice.youdao.com
log.yex.youdao.com
@ -1010,6 +1063,8 @@ yt-adp.nosdn.127.net
crash.163.com
crashlytics.163.com
g.163.com
a.youdao.com
adpublish.ydstatic.com
# >> Tencent
.beacon.qq.com
@ -1260,6 +1315,10 @@ adsence.sogou.com
.uranus.sogou.com
.wan.sogou.com
# >> ifeng.com
.ax.ifeng.com
.deliver.ifeng.com
# >> LeTV
api.game.letvstore.com
ark.letv.com
@ -1339,7 +1398,6 @@ log.star.ele.me
.da.hunantv.com
.log.hunantv.com
log.v2.hunantv.com
v2.log.hunantv.com
click.hunantv.com
res.hunantv.com
@ -1438,6 +1496,7 @@ conf.funshion.com
vs.funshion.com
rt.funshion.net
stat.funshion.net
pub.funshion.com
# >> Hupu
adx.hupu.com
@ -1471,7 +1530,7 @@ ysm.yahoo.com
yads.c.yimg.jp
yads.yahoo.co.jp
.flurry.com
flurry.cachefly.net
.flurry.cachefly.net
# >> Disqus
links.services.disqus.com
@ -1480,6 +1539,8 @@ referrer.disqus.com
disqusads.com
# >> 2345
.2345.com
.2345.cn
.50bang.org
# >> XiMaLaYa
@ -1561,6 +1622,11 @@ prt-stsdk.vivo.com.cn
stnetsdk.vivo.com.cn
.stsdk.vivo.com.cn
# >> Gionee
0.0.0.0 ads.gionee.com
0.0.0.0 pdl.gionee.com
0.0.0.0 adres.myaora.net
# >> 勾正数据
.gz-data.com
.gzads.com
@ -1590,7 +1656,6 @@ test.surepush.cn
.ad.gtbrowser.com
# >> Wasu.tv
ads.wasu.tv
adsystem.wasu.tv
adwasu.wasu.tv
@ -1598,3 +1663,8 @@ collector.wasu.cn
delivery-pc.wasu.cn
delivery.wasu.cn
delivery.maihehd.com
# tom.com
adserve2.tom.com
.pub.tom.com
.discovery.tom.com

View File

@ -10,6 +10,10 @@ DOMAIN-KEYWORD,gettate
DOMAIN-KEYWORD,mighbest
DOMAIN-KEYWORD,nimiqpool
DOMAIN-KEYWORD,.freecontent.
DOMAIN-KEYWORD,sunnimiq
DOMAIN-KEYWORD,.nimiq.
DOMAIN-KEYWORD,anybest.
DOMAIN-KEYWORD,dubester.
# --- End of Blacklist Section
@ -33,6 +37,8 @@ DOMAIN-KEYWORD,adsyndication
DOMAIN-KEYWORD,doubleclick.
DOMAIN-KEYWORD,adjust.
DOMAIN-KEYWORD,appsflyer
DOMAIN-KEYWORD,dnserror
DOMAIN-KEYWORD,marketing.net
# Important: Force add the following domains without whitelisting
DOMAIN-SUFFIX,openx.net