Add more cn domains (#3380)

* weiphone: add weiphone.net

* category-education-cn: add more domains

* category-media-cn: add more domains

* geolocation-cn: add more domains

.gitignore

@@ -4,9 +4,9 @@
 /domain-list-community
 /domain-list-community.exe
 
-# Generated dat file.
+# Generated dat files.
-dlc.dat
+/*.dat
 
 # Exported plaintext lists.
-/*.yml
 /*.txt
+/*.yml

README.md

@@ -86,6 +86,8 @@ Each file in the `data` directory can be used as a rule in this format: `geosite
 
 Run `go run ./ --help` for more usage information.
 
+For anyone who wants to generate custom `.dat` files, you may read [#3370](https://github.com/v2fly/domain-list-community/discussions/3370).
+
 ## Structure of data
 
 All data are under `data` directory. Each file in the directory represents a sub-list of domains, named by the file name. File content is in the following format.
@@ -105,7 +107,7 @@ regexp:^odd[1-7]\.example\.org(\.[a-z]{2})?$
 > Adding new `regexp` and `keyword` rules is discouraged because it is easy to use them incorrectly, and proxy software cannot efficiently match these types of rules.
 
 > [!NOTE]
-> The following types of rules are **NOT** fully compatible with the ones that defined by user in V2Ray config file. Do **Not** copy and paste directly.
+> The following types of rules are **NOT** fully compatible with the ones that defined by user in V2Ray config file. Do **NOT** copy and paste directly.
 
 - Comment begins with `#`. It may begin anywhere in the file. The content in the line after `#` is treated as comment and ignored in production.
 - Subdomain begins with `domain:`, followed by a valid domain name. The prefix `domain:` may be omitted.
@@ -114,7 +116,7 @@ regexp:^odd[1-7]\.example\.org(\.[a-z]{2})?$
 - Regular expression begins with `regexp:`, followed by a valid regular expression (per Golang's standard).
 - Domain rules (including `domain`, `full`, `keyword`, and `regexp`) may have none, one or more attributes. Each attribute begins with `@` and followed by the name of the attribute. Attributes will remain available in final lists and `dlc.dat`.
 - Domain rules may have none, one or more affiliations, which additionally adds the domain rule into the affiliated target list. Each affiliation begins with `&` and followed by the name of the target list (nomatter whether the target has a dedicated file in data path). This is a method for data management, and will not remain in the final lists or `dlc.dat`.
-- Inclusion begins with `include:`, followed by the name of another valid domain list. A simple `include:listb` in file `lista` means adding all domain rules of `listb` into `lista`. Inclusions with attributes stands for selective inclusion. `include:listb @attr1 @-attr2` means only adding those domain rules *with* `@attr1` **and** *without* `@attr2`. This is a special type for data management, and will not remain in the final lists or `dlc.dat`.
+- Inclusion begins with `include:`, followed by the name of another valid domain list. `include:listb` in file `lista` means adding all domain rules of `listb` into `lista`. Inclusions with attributes stand for selective inclusion. `include:listb @attr1 @-attr2` means only adding those domain rules *with* `@attr1` **and** *without* `@attr2`. This is a special type for data management, and will not remain in the final lists or `dlc.dat`.
 
 ## How it works
 

data/annas-archive

@@ -1,5 +1,8 @@
+annas-archive.gd
+annas-archive.gl
 annas-archive.in
 annas-archive.li
 annas-archive.org
+annas-archive.pk
 annas-archive.pm
 annas-archive.se

data/anthropic

@@ -1,8 +1,9 @@
 anthropic.com
+clau.de
 claude.ai
 claude.com
-claudeusercontent.com
 claudemcpclient.com
+claudeusercontent.com
 
 # CDN
 full:servd-anthropic-website.b-cdn.net

data/baidu

@@ -64,6 +64,7 @@ shifen.com
 smartapps.cn
 tieba.com
 tiebaimg.com
+xdrtc.com
 xianfae.com
 xiaodutv.com
 yoojia.com

data/category-acg

@@ -1,4 +1,5 @@
 # Game
+bestdori.com
 colorfulstage.com
 
 # Idol

data/category-ai-!cn

@@ -30,6 +30,7 @@ clipdrop.co
 jasper.ai
 
 chutes.ai
+clawhub.ai
 copilot.microsoft.com
 devin.ai
 diabrowser.com
@@ -37,9 +38,12 @@ diabrowser.engineering
 dify.ai
 duck.ai
 gateway.ai.cloudflare.com
+h2o.ai
 kiro.dev
 lovart.ai
 meta.ai
 mistral.ai
 openart.ai
+openclaw.ai
 openrouter.ai
+spicywriter.com

data/category-dev

@@ -54,6 +54,7 @@ include:stackexchange
 include:strikingly
 include:termux
 include:thelinuxfoundation
+include:tilda
 include:unity
 include:v8
 
@@ -152,4 +153,5 @@ wireshark.org
 x.org
 xposed.info
 yarnpkg.com
+ziglang.org
 zsh.org

data/category-dev-cn

@@ -25,3 +25,4 @@ jinrishici.com
 openvela.com
 pingcode.com
 tipdm.org
+zuidaima.com

data/category-education-cn

@@ -10,6 +10,8 @@ include:shanbay
 include:xueersi
 include:yuanfudao
 
+edu.cn
+
 # 雨课堂
 include:yuketang
 ## 雨豆课堂
@@ -19,8 +21,6 @@ yushiyan.net
 ## 学堂在线
 xuetangx.com
 
-edu.cn
-
 # 国家智慧教育公共服务平台
 cbern.com.cn
 smartedu.cn
@@ -91,6 +91,7 @@ eoffcn.com
 jinrongren.net
 offcn.com
 zggqzp.com
+zgjsks.com
 zgsydw.com
 # 高考100
 gk100.com
@@ -105,6 +106,9 @@ xir.cn
 # 日语测试
 j-test.com
 nattest-china.com
+# 菁优网
+jyeoo.com
+jyeoo.net
 # 课播云校
 keboyunxiao.com
 # 课堂派
@@ -118,6 +122,11 @@ llscdn.com
 llsserver.com
 # 马哥教育
 magedu.com
+# 墨墨背单词
+maimemo.com
+maimemostatus.com
+# 墨墨记忆卡
+markji.com
 # CIS NanoMasters
 neoscholar.com
 neoschool.com
@@ -127,6 +136,8 @@ oldboyedu.com
 pigai.org
 # 公考知识库
 saduck.top
+# 外研在线
+unipus.cn
 # 未来云校
 weilaiyunxiao.com
 # 北京嘉瑞新创教育咨询有限公司

data/category-electronic-cn

@@ -17,11 +17,10 @@ bouffalolab.com
 cxmt.com
 
 # 乐鑫信息科技
+#include:espressif
 esp8266.cn
-esp8266.com
 esp8266.com.cn
 espressif.cn
-espressif.com
 espressif.com.cn
 
 # 华秋电子

data/category-entertainment-cn

@@ -57,10 +57,14 @@ anitabi.cn
 # 暴风影音
 baofeng.com
 baofeng.net
+# 街机地图
+bemanicn.com
 # 布咕阅读
 bgwxc.com
 # B站空降助手
 bsbsb.top
+# CdkeyNoGap
+cdkeynogap.com
 # 动漫之家 #703
 dmzj.com
 muwai.com

data/category-entertainment-ru

@@ -11,6 +11,7 @@ include:okko
 include:wink
 24h.tv
 amediateka.ru
+beeline.tv
 ivi.ru
 premier.one
 smotreshka.tv

data/category-ip-geo-detect

@@ -97,6 +97,7 @@ myexternalip.com
 myip.com
 myip.ms
 myip.ru
+myip.wtf
 myipaddress.com
 myiplookup.com
 mylocation.org
@@ -131,7 +132,10 @@ wtfismyip.com
 
 # Subdomains/internal api used for ip-geo-detect
 full:checkip.amazonaws.com
+full:ipv4-check-perf.radar.cloudflare.com
+full:ipv6-check-perf.radar.cloudflare.com
 geoip.noc.gov.ru
+ip.hetzner.com
 ip.mail.ru
 ip.nic.ru
 ip.tyk.nu

data/category-media-cn

@@ -135,6 +135,10 @@ kksmg.com
 statickksmg.com
 # 晚点
 latepost.com
+# 雷科技
+leikeji.com
+# 雷峰网
+leiphone.com
 # 今日观察网
 miercn.com
 # 快科技
@@ -206,14 +210,21 @@ techweb.com.cn
 thecover.cn
 # 澎湃新闻
 thepaper.cn
+# 潮新闻/浙江日报
+8531.cn
+tidenews.com.cn
 # 人人都是产品经理
 woshipm.com
+# 新华日报
+xhby.net
 # 西陆网
 xilu.com
 # 新快报
 xkb.com.cn
 # 第一财经
 yicai.com
+# 扬子晚报
+yzwb.net
 # ZEALER
 zealer.com
 # 知产力

data/category-speedtest

@@ -3,33 +3,62 @@ include:openspeedtest
 
 cnspeedtest.cn @cn
 fast.com
+fastspeedtest.com
+linkmeter.net
 measurementlab.net
+meter.net
 nperf.com
+openspeedtest.ru
 speed.cloudflare.com
 speed.dler.io
+speed.ee
 speed.hinet.net
 speed.nccu.edu.tw
 speed.neu6.edu.cn @cn
+speed.nju.edu.cn @cn
 speed.nuaa.edu.cn @cn
 speed.qlu.edu.cn @cn
 speed.ujs.edu.cn @cn
-speed6.ujs.edu.cn @cn
 speed2.hinet.net
 speed5.ntu.edu.tw
+speed6.ujs.edu.cn @cn
+speedcheck.org
+speedgeo.net
+speedof.me
+speedtest.cesnet.cz
+speedtest.ch
+speedtest.citylink.pro
 speedtest.cn @cn
+speedtest.co.za
+speedtest.de
+speedtest.dno-it.ru
+speedtest.frontier.com
 speedtest.im
+speedtest.mail.ru
 speedtest.mfcyun.com @cn
+speedtest.net.in
+speedtest.net.ua
+speedtest.net.uk
+speedtest.org
+speedtest.rt.ru
+speedtest.ru
+speedtest.shaw.ca
 speedtest.shu.edu.cn @cn
-speedtest6.shu.edu.cn @cn
+speedtest.su
+speedtest.uz
+speedtest.volia.com
 speedtest.xaut.edu.cn @cn
 speedtest.xfinity.com
-speedtestcustom.com
+speedtest.xyz
-test.ustc.edu.cn @cn
+speedtest24.ru
-test6.ustc.edu.cn @cn
+speedtest6.shu.edu.cn @cn
 test.nju.edu.cn @cn
+test.ustc.edu.cn @cn
 test6.nju.edu.cn @cn
-speed.nju.edu.cn @cn
+test6.ustc.edu.cn @cn
 testmy.net
+testmyspeed.com
+testskorosti.ru
 xnfz.seu.edu.cn @cn
 
 full:hk-global-bgp.hkg.speedtest.yecaoyun.com @!cn

data/category-wiki-cn

@@ -1,3 +1,4 @@
+allhistory.com
 fgo.wiki
 jikipedia.com
 mbalib.com

data/chinamobile

@@ -16,6 +16,9 @@ miguvideo.com
 # 中移金科
 cmft.com.cn
 
+# 中移支付 和包
+cmpay.com
+
 # 中移在线
 cmcc-cs.cn
 online-cmcc.cn

data/chinatelecom

@@ -1,10 +1,11 @@
 include:ctexcel
 
 189.cn
+bestpay.cn
+bestpay.com.cn
 chinatelecom-h.com
 chinatelecom.com.cn
 chinatelecomglobal.com @!cn
+chinatelecomhk.com @!cn
 chntel.com
 vnet.cn
-
-chinatelecomhk.com @!cn

data/chinaunicom

@@ -18,6 +18,7 @@ cuguplus.com @!cn
 cuniq.com @!cn
 cuniq.sg @!cn
 mychinaunicom.com
+unicompayment.com
 wo.cn
 wo.com.cn
 wo116114.com

data/douyin

@@ -65,3 +65,6 @@ supercachenode.com
 ultracachenode.com
 woaihuoshan.com
 wohst8.com
+
+# 抖音支付
+douyinpay.com

data/geolocation-!cn

@@ -326,3 +326,5 @@ include:tsquare
 include:windy
 include:xdty
 include:xingrz
+
+sinyalee.com

data/geolocation-cn

@@ -45,6 +45,8 @@ include:taikang
 
 ## 航财通·校园付
 cc-pay.cn
+## 合利宝
+helipay.com
 ## 徽商期货有限责任公司
 hsqh.net
 ## 上海陆金所
@@ -53,6 +55,8 @@ lufax.com
 lufaxcdn.com
 ## 银豹收银系统
 pospal.cn
+## 上海付费通
+shfft.com
 
 # CDN or SDWAN
 include:category-cdn-cn
@@ -218,27 +222,73 @@ mingxuan.store
 gov.cn
 ## 中国气象局
 cma.cn
+## 政务和公益机构域名注册管理中心
+conac.cn
 ## 中央气象台
 nmc.cn
+## 中国互联网联合辟谣平台
+piyao.org.cn
 
 # Public transportation
-include:airchina # 中国国际航空
+## 中国国际航空
-include:hainanairlines # 海南航空
+include:airchina
+## 海南航空
+include:hainanairlines
+## 长安航空
+airchangan.com
+## 桂林航空
+airguilin.com
+## 中国东方航空
+ceair.com
+## 春秋航空
+ch.com
+china-sss.com
+springairlines.com
+## 华夏航空
+chinaexpressair.com
+## 中国南方航空
+csair.com
+## 中国联合航空
+flycua.com
+## 广西北部湾航空
+gxairlines.com
+## 河北航空
+hbhk.com.cn
+## 首都航空
+jdair.net
+## 吉祥航空
+juneyaoair.com
+## 长龙航空
+loongair.cn
+## 祥鹏航空
+luckyair.net
+## 山东航空
+sda.cn
+## 深圳航空
+shenzhenair.com
+## 四川航空
+sichuanair.com
+## 天津航空
+tianjin-air.com
+## 西藏航空
+tibetairlines.com.cn
+## 乌鲁木齐航空
+urumqi-air.com
+## 厦门航空
+xiamenair.com
+
+## 中国民航局
+caac.gov.cn
+## 信天游（航空电子客票验真）
+travelskymobile.cn
+## 航旅纵横
+umetrip.com
+umetrip.com.cn
+umetrip.net.cn
+ume-trip.cn
+## 飞常准
+variflight.com
 
-# 中国民航局 caac.gov.cn
-ceair.com # 中国东方航空
-chinaexpressair.com # 华夏航空
-csair.com # 中国南方航空
-flycua.com # 中国联合航空
-hbhk.com.cn # 河北航空
-jdair.net # 首都航空
-juneyaoair.com # 吉祥航空
-luckyair.net # 祥鹏航空
-sichuanair.com # 四川航空
-tibetairlines.com.cn # 西藏航空
-travelskymobile.cn # 信天游（航空电子客票验真）
-variflight.com # 飞常准
-xiamenair.com # 厦门航空
 ## Railway
 12306.cn
 95306.cn
@@ -253,11 +303,6 @@ kuajing84.com
 mygolbs.com
 ## 宁停车
 ningtingche.com
-## 航旅纵横
-umetrip.com
-umetrip.com.cn
-umetrip.net.cn
-ume-trip.cn
 
 # Science & Technology & Knowledge & Scholar & Press & E-learning & Education
 include:category-education-cn
@@ -280,10 +325,14 @@ webterren.com
 ## 国学大师网
 guoxuedashi.com
 guoxuemi.com
-## 志愿汇
-zyh365.com
 ## 温州市图书馆
 wzlib.cn
+## 中国大百科全书
+zgbk.com
+## 浙江图书馆
+zjlib.cn
+## 志愿汇
+zyh365.com
 
 # Services & Softwares
 include:category-ai-cn
@@ -421,6 +470,7 @@ xbext.com
 yinxiang.com
 ## 智联招聘
 zhaopin.cn
+zhaopin.com
 
 # Tech companies & Orginations
 include:aisiku # 北京艾斯酷科技有限公司
@@ -642,7 +692,6 @@ ycrx360.com
 52z.com
 53kf.com
 55.com
-56.com
 5577.com
 55bbs.com
 58pic.com
@@ -688,8 +737,6 @@ aiemy.com
 aiketour.com
 aiops.com
 aipai.com
-airchangan.com
-airguilin.com
 aiskycn.com
 aizhan.com
 aldwx.com # 京ICP备17030349号-1
@@ -753,7 +800,6 @@ cecdc.com
 cecport.com
 centanet.com
 cerambath.org
-ch.com
 chachaba.com
 changba.com
 chaojituzi.net
@@ -938,7 +984,6 @@ gupzs.com
 gushiwen.org
 guzhangting.com
 gwdang.com
-gxairlines.com
 gxb.io
 gzcqs.com
 gzwanju.com
@@ -1075,8 +1120,6 @@ lascn.net
 lawxp.com
 leangoo.com
 leanote.com
-leikeji.com
-leiphone.com
 leiting.com
 leju.com
 leturich.org
@@ -1296,7 +1339,6 @@ taoche.com
 te5.com
 tenxcloud.com
 tianjimedia.com
-tianjin-air.com
 tianlailive.com
 tietuku.com
 tiexue.net
@@ -1332,7 +1374,6 @@ ucbug.com
 uggame.com
 uoko.com
 urselect.com
-urumqi-air.com
 useso.com
 uuu9.com
 uzzf.com
@@ -1359,7 +1400,6 @@ weand.com
 weavatar.com
 weicaifu.com
 weilaicaijing.com
-weiphone.net
 weixing.com
 weiyangx.com
 welltrend-edu.com
@@ -1488,7 +1528,6 @@ zastatic.com
 zczj.com
 zdfans.com
 zgjm.org
-zgjsks.com
 zglxw.com
 zgzcw.com
 zhanbuba.com
@@ -1496,7 +1535,6 @@ zhangyoubao.com
 zhanzhang.net
 zhaodanji.com
 zhaokao.net
-zhaopin.com
 zhcw.com
 zhenai.com
 zhibo8.cc
@@ -1507,15 +1545,11 @@ zhongkao.com
 zhuangjiba.com
 zhuanyewanjia.com
 zhuayoukong.com
-zimuzu.io
 zixiaomao.com
 zixuntop.com
 zmengzhu.com
 zpb365.com
-zrblog.net
-zsxq.com
 zuhaowan.com
-zuidaima.com
 zuowen.com
 zuowen8.com
 zuowenwang.net
@@ -1591,3 +1625,6 @@ ao-x.ac.cn
 
 # 万集科技 京ICP备18036282号-2
 wanji.net.cn
+
+# 广州市雅望互联网服务有限公司
+gzyowin.com

data/keep

@@ -1,2 +1,5 @@
+calorietech.com
 gotokeep.com
+keep.com
+keep.com.cn
 keepcdn.com

data/kinopub

@@ -3,6 +3,7 @@ kinopub.online
 kpdl.link
 
 # Mirror sites
+ahc.ovh # sub domains mirror
 gfw.ovh # sub domains mirror
 mos-gorsud.co # kinopub domain to generate a mirror site through gfw.ovh
 

data/netease

@@ -32,6 +32,7 @@ static163.net
 ydstatic.com
 yeah.net
 youdao.com
+yunxindns.com
 yunxinfw.com
 zhuanzfx.com
 

data/nodeseek

@@ -1,5 +1,6 @@
 22112211.xyz
 deepflood.com
+nodeget.com
 nodeimage.com
 nodequality.com
 nodeseek.com

data/nvidia

@@ -59,6 +59,7 @@ tegrazone.com
 tegrazone.jp
 tegrazone.kr
 
+full:nvidia.custhelp.com
 full:nvidia.tt.omtrdc.net
 
 # NVIDIA 文件下载服务器中国镜像

data/oracle

@@ -1,10 +1,14 @@
 # All .oracle domains
 oracle
 
+include:addthis
+include:java
+
 ateam-oracle.com
 bronto.com
 covid19-rx.org
 covid19rx.org
+custhelp.com
 oracle.com
 oraclecloud.com
 oraclefoundation.org
@@ -12,6 +16,3 @@ oracleimg.com
 oracleinfinity.io
 sun.com
 virtualbox.org
-
-include:addthis
-include:java

data/qcloud

@@ -258,13 +258,14 @@ tdnsv14.net
 tdnsv15.net
 
 # myqcloud inside mainland China
-regexp:\.(.+-)?ap-beijing(-.+)?\.myqcloud\.com$             #北京
+# overrided by myqcloud.com
-regexp:\.(.+-)?ap-nanjing(-.+)?\.myqcloud\.com$             #南京
+#regexp:\.(.+-)?ap-beijing(-.+)?\.myqcloud\.com$             #北京
-regexp:\.(.+-)?ap-shanghai(-.+)?\.myqcloud\.com$            #上海
+#regexp:\.(.+-)?ap-nanjing(-.+)?\.myqcloud\.com$             #南京
-regexp:\.(.+-)?ap-guangzhou(-.+)?\.myqcloud\.com$           #广州
+#regexp:\.(.+-)?ap-shanghai(-.+)?\.myqcloud\.com$            #上海
-regexp:\.(.+-)?ap-chengdu(-.+)?\.myqcloud\.com$             #成都
+#regexp:\.(.+-)?ap-guangzhou(-.+)?\.myqcloud\.com$           #广州
-regexp:\.(.+-)?ap-chongqing(-.+)?\.myqcloud\.com$           #重庆
+#regexp:\.(.+-)?ap-chengdu(-.+)?\.myqcloud\.com$             #成都
-regexp:\.(.+-)?ap-shenzhen(-.+)?\.myqcloud\.com$            #深圳
+#regexp:\.(.+-)?ap-chongqing(-.+)?\.myqcloud\.com$           #重庆
+#regexp:\.(.+-)?ap-shenzhen(-.+)?\.myqcloud\.com$            #深圳
 
 # COS 使用到的非中国大陆的地域与可用区，参见 https://cloud.tencent.com/document/product/436/6224
 ap-hongkong.myqcloud.com @!cn       #中国香港
@@ -282,13 +283,14 @@ eu-frankfurt.myqcloud.com @!cn      #法兰克福
 eu-moscow.myqcloud.com @!cn         #莫斯科
 
 # tencentcos inside mainland China
-regexp:\.(.+-)?ap-beijing(-.+)?\.tencentcos\.(cn|com(\.cn)?)$   #北京
+# overrided by tencentcos.cn, tencentcos.com, tencentcos.com.cn
-regexp:\.(.+-)?ap-nanjing(-.+)?\.tencentcos\.(cn|com(\.cn)?)$   #南京
+#regexp:\.(.+-)?ap-beijing(-.+)?\.tencentcos\.(cn|com(\.cn)?)$   #北京
-regexp:\.(.+-)?ap-shanghai(-.+)?\.tencentcos\.(cn|com(\.cn)?)$  #上海
+#regexp:\.(.+-)?ap-nanjing(-.+)?\.tencentcos\.(cn|com(\.cn)?)$   #南京
-regexp:\.(.+-)?ap-guangzhou(-.+)?\.tencentcos\.(cn|com(\.cn)?)$ #广州
+#regexp:\.(.+-)?ap-shanghai(-.+)?\.tencentcos\.(cn|com(\.cn)?)$  #上海
-regexp:\.(.+-)?ap-chengdu(-.+)?\.tencentcos\.(cn|com(\.cn)?)$   #成都
+#regexp:\.(.+-)?ap-guangzhou(-.+)?\.tencentcos\.(cn|com(\.cn)?)$ #广州
-regexp:\.(.+-)?ap-chongqing(-.+)?\.tencentcos\.(cn|com(\.cn)?)$ #重庆
+#regexp:\.(.+-)?ap-chengdu(-.+)?\.tencentcos\.(cn|com(\.cn)?)$   #成都
-regexp:\.(.+-)?ap-shenzhen(-.+)?\.tencentcos\.(cn|com(\.cn)?)$  #深圳
+#regexp:\.(.+-)?ap-chongqing(-.+)?\.tencentcos\.(cn|com(\.cn)?)$ #重庆
+#regexp:\.(.+-)?ap-shenzhen(-.+)?\.tencentcos\.(cn|com(\.cn)?)$  #深圳
 
 # tencentcos outside mainland China
 # regexp:.+\.ap-hongkong\.tencentcos\.(cn|com(\.cn)?)$ @!cn       #中国香港

data/sohu

@@ -9,6 +9,10 @@ itc.cn
 sohu.com
 sohucs.com
 
+# 56网
+56.com
+56img.com
+
 # Ads/tracking
 adnet.sohu.com @ads
 ads.sohu.com @ads

data/tilda

@@ -0,0 +1,5 @@
+tilda.cc
+tilda.ru
+tilda.ws
+tildaapi.com
+tildacdn.com

data/weiphone

@@ -1,3 +1,4 @@
 feng.com
 fengimg.com
+weiphone.net
 wfdata.club

data/wordpress

@@ -1,6 +1,7 @@
 videopress.com
 w.org
 wordpress.com
+wordpress.net
 wordpress.org
 wordpress.tv
 wp-themes.com

main.go

@@ -2,6 +2,7 @@ package main
 
 import (
 	"bufio"
+	"encoding/json"
 	"flag"
 	"fmt"
 	"os"
@@ -19,6 +20,7 @@ var (
 	dataPath    = flag.String("datapath", "./data", "Path to your custom 'data' directory")
 	outputName  = flag.String("outputname", "dlc.dat", "Name of the generated dat file")
 	outputDir   = flag.String("outputdir", "./", "Directory to place all generated files")
+	datProfile  = flag.String("datprofile", "", "Path of config file used to assemble custom dats")
 	exportLists = flag.String("exportlists", "", "Lists to be flattened and exported in plaintext format, separated by ',' comma")
 )
 
@@ -47,7 +49,24 @@ type Processor struct {
 	cirIncMap map[string]bool
 }
 
-func makeProtoList(listName string, entries []*Entry) (*router.GeoSite, error) {
+type GeoSites struct {
+	Sites   []*router.GeoSite
+	SiteIdx map[string]int
+}
+
+type DatTask struct {
+	Name  string   `json:"name"`
+	Mode  string   `json:"mode"`
+	Lists []string `json:"lists"`
+}
+
+const (
+	ModeAll       string = "all"
+	ModeAllowlist string = "allowlist"
+	ModeDenylist  string = "denylist"
+)
+
+func makeProtoList(listName string, entries []*Entry) *router.GeoSite {
 	site := &router.GeoSite{
 		CountryCode: listName,
 		Domain:      make([]*router.Domain, 0, len(entries)),
@@ -73,7 +92,91 @@ func makeProtoList(listName string, entries []*Entry) (*router.GeoSite, error) {
 		}
 		site.Domain = append(site.Domain, pdomain)
 	}
-	return site, nil
+	return site
+}
+
+func loadTasks(path string) ([]DatTask, error) {
+	f, err := os.Open(path)
+	if err != nil {
+		return nil, err
+	}
+	defer f.Close()
+
+	var tasks []DatTask
+	dec := json.NewDecoder(f)
+	if err := dec.Decode(&tasks); err != nil {
+		return nil, fmt.Errorf("failed to decode json: %w", err)
+	}
+	for i, t := range tasks {
+		if t.Name == "" {
+			return nil, fmt.Errorf("task[%d]: name is required", i)
+		}
+		switch t.Mode {
+		case ModeAll, ModeAllowlist, ModeDenylist:
+		default:
+			return nil, fmt.Errorf("task[%d] %q: invalid mode %q", i, t.Name, t.Mode)
+		}
+	}
+	return tasks, nil
+}
+
+func (gs *GeoSites) assembleDat(task DatTask) error {
+	datFileName := strings.ToLower(filepath.Base(task.Name))
+	geoSiteList := new(router.GeoSiteList)
+
+	switch task.Mode {
+	case ModeAll:
+		geoSiteList.Entry = gs.Sites
+	case ModeAllowlist:
+		allowedIdxes := make([]int, 0, len(task.Lists))
+		for _, list := range task.Lists {
+			if idx, ok := gs.SiteIdx[strings.ToUpper(list)]; ok {
+				allowedIdxes = append(allowedIdxes, idx)
+			} else {
+				return fmt.Errorf("list %q not found for allowlist task", list)
+			}
+		}
+		slices.Sort(allowedIdxes)
+		allowedlen := len(allowedIdxes)
+		if allowedlen == 0 {
+			return fmt.Errorf("allowlist needs at least one valid list")
+		}
+		geoSiteList.Entry = make([]*router.GeoSite, allowedlen)
+		for i, idx := range allowedIdxes {
+			geoSiteList.Entry[i] = gs.Sites[idx]
+		}
+	case ModeDenylist:
+		deniedMap := make(map[int]bool, len(task.Lists))
+		for _, list := range task.Lists {
+			if idx, ok := gs.SiteIdx[strings.ToUpper(list)]; ok {
+				deniedMap[idx] = true
+			} else {
+				fmt.Printf("[Warn] list %q not found in denylist task %q", list, task.Name)
+			}
+		}
+		deniedlen := len(deniedMap)
+		if deniedlen == 0 {
+			fmt.Printf("[Warn] nothing to deny in task %q", task.Name)
+			geoSiteList.Entry = gs.Sites
+		} else {
+			geoSiteList.Entry = make([]*router.GeoSite, 0, len(gs.Sites)-deniedlen)
+			for i, site := range gs.Sites {
+				if !deniedMap[i] {
+					geoSiteList.Entry = append(geoSiteList.Entry, site)
+				}
+			}
+		}
+	}
+
+	protoBytes, err := proto.Marshal(geoSiteList)
+	if err != nil {
+		return fmt.Errorf("failed to marshal: %w", err)
+	}
+	if err := os.WriteFile(filepath.Join(*outputDir, datFileName), protoBytes, 0644); err != nil {
+		return fmt.Errorf("failed to write file %q: %w", datFileName, err)
+	}
+	fmt.Printf("dat %q has been generated successfully\n", datFileName)
+	return nil
 }
 
 func writePlainList(listname string, entries []*Entry) error {
@@ -89,46 +192,28 @@ func writePlainList(listname string, entries []*Entry) error {
 	return w.Flush()
 }
 
-func parseEntry(line string) (*Entry, []string, error) {
+func parseEntry(typ, rule string) (*Entry, []string, error) {
-	entry := new(Entry)
+	entry := &Entry{Type: typ}
-	parts := strings.Fields(line)
+	parts := strings.Fields(rule)
 	if len(parts) == 0 {
-		return entry, nil, fmt.Errorf("empty line")
+		return entry, nil, fmt.Errorf("empty domain rule")
 	}
-
+	// Parse value
-	// Parse type and value
+	switch entry.Type {
-	typ, val, isTypeSpecified := strings.Cut(parts[0], ":")
+	case dlc.RuleTypeRegexp:
-	typ = strings.ToLower(typ)
+		if _, err := regexp.Compile(parts[0]); err != nil {
-	if !isTypeSpecified { // Default RuleType
+			return entry, nil, fmt.Errorf("invalid regexp %q: %w", parts[0], err)
-		if !validateDomainChars(typ) {
-			return entry, nil, fmt.Errorf("invalid domain: %q", typ)
 		}
-		entry.Type = dlc.RuleTypeDomain
+		entry.Value = parts[0]
-		entry.Value = typ
+	case dlc.RuleTypeDomain, dlc.RuleTypeFullDomain, dlc.RuleTypeKeyword:
-	} else {
+		entry.Value = strings.ToLower(parts[0])
-		switch typ {
+		if !validateDomainChars(entry.Value) {
-		case dlc.RuleTypeRegexp:
+			return entry, nil, fmt.Errorf("invalid domain: %q", entry.Value)
-			if _, err := regexp.Compile(val); err != nil {
-				return entry, nil, fmt.Errorf("invalid regexp %q: %w", val, err)
-			}
-			entry.Type = dlc.RuleTypeRegexp
-			entry.Value = val
-		case dlc.RuleTypeInclude:
-			entry.Type = dlc.RuleTypeInclude
-			entry.Value = strings.ToUpper(val)
-			if !validateSiteName(entry.Value) {
-				return entry, nil, fmt.Errorf("invalid included list name: %q", entry.Value)
-			}
-		case dlc.RuleTypeDomain, dlc.RuleTypeFullDomain, dlc.RuleTypeKeyword:
-			entry.Type = typ
-			entry.Value = strings.ToLower(val)
-			if !validateDomainChars(entry.Value) {
-				return entry, nil, fmt.Errorf("invalid domain: %q", entry.Value)
-			}
-		default:
-			return entry, nil, fmt.Errorf("invalid type: %q", typ)
 		}
+	default:
+		return entry, nil, fmt.Errorf("unknown rule type: %q", entry.Type)
 	}
+	plen := len(entry.Type) + len(entry.Value) + 1
 
 	// Parse attributes and affiliations
 	var affs []string
@@ -140,6 +225,7 @@ func parseEntry(line string) (*Entry, []string, error) {
 				return entry, affs, fmt.Errorf("invalid attribute: %q", attr)
 			}
 			entry.Attrs = append(entry.Attrs, attr)
+			plen += 2 + len(attr)
 		case '&':
 			aff := strings.ToUpper(part[1:])
 			if !validateSiteName(aff) {
@@ -147,33 +233,70 @@ func parseEntry(line string) (*Entry, []string, error) {
 			}
 			affs = append(affs, aff)
 		default:
-			return entry, affs, fmt.Errorf("invalid attribute/affiliation: %q", part)
+			return entry, affs, fmt.Errorf("unknown field: %q", part)
 		}
 	}
 
-	if entry.Type != dlc.RuleTypeInclude {
+	slices.Sort(entry.Attrs) // Sort attributes
-		slices.Sort(entry.Attrs) // Sort attributes
+	// Formated plain entry: type:domain.tld:@attr1,@attr2
-		// Formated plain entry: type:domain.tld:@attr1,@attr2
+	var plain strings.Builder
-		var plain strings.Builder
+	plain.Grow(plen)
-		plain.Grow(len(entry.Type) + len(entry.Value) + 10)
+	plain.WriteString(entry.Type)
-		plain.WriteString(entry.Type)
+	plain.WriteByte(':')
-		plain.WriteByte(':')
+	plain.WriteString(entry.Value)
-		plain.WriteString(entry.Value)
+	for i, attr := range entry.Attrs {
-		for i, attr := range entry.Attrs {
+		if i == 0 {
-			if i == 0 {
+			plain.WriteByte(':')
-				plain.WriteByte(':')
+		} else {
-			} else {
+			plain.WriteByte(',')
-				plain.WriteByte(',')
-			}
-			plain.WriteByte('@')
-			plain.WriteString(attr)
 		}
-		entry.Plain = plain.String()
+		plain.WriteByte('@')
+		plain.WriteString(attr)
 	}
+	entry.Plain = plain.String()
 	return entry, affs, nil
 }
 
+func parseInclusion(rule string) (*Inclusion, error) {
+	parts := strings.Fields(rule)
+	if len(parts) == 0 {
+		return nil, fmt.Errorf("empty inclusion")
+	}
+	inc := &Inclusion{Source: strings.ToUpper(parts[0])}
+	if !validateSiteName(inc.Source) {
+		return inc, fmt.Errorf("invalid included list name: %q", inc.Source)
+	}
+
+	// Parse attributes
+	for _, part := range parts[1:] {
+		switch part[0] {
+		case '@':
+			attr := strings.ToLower(part[1:])
+			if attr[0] == '-' {
+				battr := attr[1:]
+				if !validateAttrChars(battr) {
+					return inc, fmt.Errorf("invalid ban attribute: %q", battr)
+				}
+				inc.BanAttrs = append(inc.BanAttrs, battr)
+			} else {
+				if !validateAttrChars(attr) {
+					return inc, fmt.Errorf("invalid must attribute: %q", attr)
+				}
+				inc.MustAttrs = append(inc.MustAttrs, attr)
+			}
+		case '&':
+			return inc, fmt.Errorf("affiliation is not allowed for inclusion")
+		default:
+			return inc, fmt.Errorf("unknown field: %q", part)
+		}
+	}
+	return inc, nil
+}
+
 func validateDomainChars(domain string) bool {
+	if domain == "" {
+		return false
+	}
 	for i := range domain {
 		c := domain[i]
 		if (c >= 'a' && c <= 'z') || (c >= '0' && c <= '9') || c == '.' || c == '-' {
@@ -185,9 +308,12 @@ func validateDomainChars(domain string) bool {
 }
 
 func validateAttrChars(attr string) bool {
+	if attr == "" {
+		return false
+	}
 	for i := range attr {
 		c := attr[i]
-		if (c >= 'a' && c <= 'z') || (c >= '0' && c <= '9') || c == '!' || c == '-' {
+		if (c >= 'a' && c <= 'z') || (c >= '0' && c <= '9') || c == '!' {
 			continue
 		}
 		return false
@@ -196,6 +322,9 @@ func validateAttrChars(attr string) bool {
 }
 
 func validateSiteName(name string) bool {
+	if name == "" {
+		return false
+	}
 	for i := range name {
 		c := name[i]
 		if (c >= 'A' && c <= 'Z') || (c >= '0' && c <= '9') || c == '!' || c == '-' {
@@ -232,26 +361,23 @@ func (p *Processor) loadData(listName string, path string) error {
 		if line == "" {
 			continue
 		}
-		entry, affs, err := parseEntry(line)
+		typ, rule, isTypeSpecified := strings.Cut(line, ":")
-		if err != nil {
+		if !isTypeSpecified { // Default RuleType
-			return fmt.Errorf("error in %q at line %d: %w", path, lineIdx, err)
+			typ, rule = dlc.RuleTypeDomain, typ
+		} else {
+			typ = strings.ToLower(typ)
 		}
-
+		if typ == dlc.RuleTypeInclude {
-		if entry.Type == dlc.RuleTypeInclude {
+			inc, err := parseInclusion(rule)
-			inc := &Inclusion{Source: entry.Value}
+			if err != nil {
-			for _, attr := range entry.Attrs {
+				return fmt.Errorf("error in %q at line %d: %w", path, lineIdx, err)
-				if attr[0] == '-' {
-					inc.BanAttrs = append(inc.BanAttrs, attr[1:])
-				} else {
-					inc.MustAttrs = append(inc.MustAttrs, attr)
-				}
-			}
-			for _, aff := range affs {
-				apl := p.getOrCreateParsedList(aff)
-				apl.Inclusions = append(apl.Inclusions, inc)
 			}
 			pl.Inclusions = append(pl.Inclusions, inc)
 		} else {
+			entry, affs, err := parseEntry(typ, rule)
+			if err != nil {
+				return fmt.Errorf("error in %q at line %d: %w", path, lineIdx, err)
+			}
 			for _, aff := range affs {
 				apl := p.getOrCreateParsedList(aff)
 				apl.Entries = append(apl.Entries, entry)
@@ -259,7 +385,7 @@ func (p *Processor) loadData(listName string, path string) error {
 			pl.Entries = append(pl.Entries, entry)
 		}
 	}
-	return nil
+	return scanner.Err()
 }
 
 func isMatchAttrFilters(entry *Entry, incFilter *Inclusion) bool {
@@ -360,6 +486,9 @@ func (p *Processor) resolveList(plname string) error {
 			}
 		}
 	}
+	if len(roughMap) == 0 {
+		return fmt.Errorf("empty list")
+	}
 	p.finalMap[plname] = polishList(roughMap)
 	return nil
 }
@@ -387,13 +516,15 @@ func run() error {
 		return fmt.Errorf("failed to loadData: %w", err)
 	}
 	// Generate finalMap
-	processor.finalMap = make(map[string][]*Entry, len(processor.plMap))
+	sitesCount := len(processor.plMap)
+	processor.finalMap = make(map[string][]*Entry, sitesCount)
 	processor.cirIncMap = make(map[string]bool)
 	for plname := range processor.plMap {
 		if err := processor.resolveList(plname); err != nil {
 			return fmt.Errorf("failed to resolveList %q: %w", plname, err)
 		}
 	}
+	processor.plMap = nil
 
 	// Make sure output directory exists
 	if err := os.MkdirAll(*outputDir, 0755); err != nil {
@@ -403,47 +534,58 @@ func run() error {
 	for rawEpList := range strings.SplitSeq(*exportLists, ",") {
 		if epList := strings.TrimSpace(rawEpList); epList != "" {
 			entries, exist := processor.finalMap[strings.ToUpper(epList)]
-			if !exist || len(entries) == 0 {
+			if !exist {
-				fmt.Printf("list %q does not exist or is empty\n", epList)
+				fmt.Printf("[Warn] list %q does not exist\n", epList)
 				continue
 			}
 			if err := writePlainList(epList, entries); err != nil {
-				fmt.Printf("failed to write list %q: %v\n", epList, err)
+				fmt.Printf("[Error] failed to write list %q: %v\n", epList, err)
 				continue
 			}
-			fmt.Printf("list %q has been generated successfully.\n", epList)
+			fmt.Printf("list %q has been generated successfully\n", epList)
 		}
 	}
 
-	// Generate dat file
+	// Generate proto sites
-	protoList := new(router.GeoSiteList)
+	gs := &GeoSites{
-	for siteName, siteEntries := range processor.finalMap {
+		Sites:   make([]*router.GeoSite, 0, sitesCount),
-		site, err := makeProtoList(siteName, siteEntries)
+		SiteIdx: make(map[string]int, sitesCount),
-		if err != nil {
-			return fmt.Errorf("failed to makeProtoList %q: %w", siteName, err)
-		}
-		protoList.Entry = append(protoList.Entry, site)
 	}
-	// Sort protoList so the marshaled list is reproducible
+	for siteName, siteEntries := range processor.finalMap {
-	slices.SortFunc(protoList.Entry, func(a, b *router.GeoSite) int {
+		gs.Sites = append(gs.Sites, makeProtoList(siteName, siteEntries))
+	}
+	processor = nil
+	// Sort proto sites so the generated file is reproducible
+	slices.SortFunc(gs.Sites, func(a, b *router.GeoSite) int {
 		return strings.Compare(a.CountryCode, b.CountryCode)
 	})
+	for i := range sitesCount {
+		gs.SiteIdx[gs.Sites[i].CountryCode] = i
+	}
 
-	protoBytes, err := proto.Marshal(protoList)
+	// Load tasks and generate dat files
-	if err != nil {
+	var tasks []DatTask
-		return fmt.Errorf("failed to marshal: %w", err)
+	if *datProfile == "" {
+		tasks = []DatTask{{Name: *outputName, Mode: ModeAll}}
+	} else {
+		var err error
+		tasks, err = loadTasks(*datProfile)
+		if err != nil {
+			return fmt.Errorf("failed to loadTasks %q: %v", *datProfile, err)
+		}
 	}
-	if err := os.WriteFile(filepath.Join(*outputDir, *outputName), protoBytes, 0644); err != nil {
+	for _, task := range tasks {
-		return fmt.Errorf("failed to write output: %w", err)
+		if err := gs.assembleDat(task); err != nil {
+			fmt.Printf("[Error] failed to assembleDat %q: %v", task.Name, err)
+		}
 	}
-	fmt.Printf("%q has been generated successfully.\n", *outputName)
 	return nil
 }
 
 func main() {
 	flag.Parse()
 	if err := run(); err != nil {
-		fmt.Printf("Fatal error: %v\n", err)
+		fmt.Printf("[Fatal] critical error: %v\n", err)
 		os.Exit(1)
 	}
 }