Fix with accept-encoding header & compressed option

.github/workflows/build.yml

@@ -1,4 +1,4 @@
-name: Build v2ray rules dat files
+name: Build V2Ray rules dat files
 on:
   schedule:
     - cron: "0 22 * * *"
@@ -41,12 +41,12 @@ jobs:
           echo "::add-path::$(dirname $GITHUB_WORKSPACE)/bin"
         shell: bash
 
-      - name: Checkout branch named hidden of this repo
+      - name: Checkout the "hidden" branch
         uses: actions/checkout@v2
         with:
           ref: hidden
 
-      - name: Get GeoLite2 file
+      - name: Get GeoLite2 zip file
         run: |
           curl -L -o GeoLite2-Country-CSV.zip "https://download.maxmind.com/app/geoip_download?edition_id=GeoLite2-Country-CSV&license_key=JvbzLLx7qBZT&suffix=zip"
           unzip GeoLite2-Country-CSV.zip
@@ -63,32 +63,29 @@ jobs:
       - name: Download geosite project
         run: |
           go get -u -v -insecure $GEOSITE_REPO
-          
+
       - name: Automatically generate ookla-speedtest sub-list from source
         run: |
-          curl -L -o servers-source.xml "https://c.speedtest.net/speedtest-servers-static.php"
-          cat servers-source.xml | sed -nEe 's/.+host="(.+):[0-9]+".+/\L\1/p' | sort -u > hosts-with-ip.txt
-          sed -E '/^([0-9]{1,3}\.){3}[0-9]{1,3}$/d' hosts-with-ip.txt > hosts-without-ip.txt
-          cat hosts-without-ip.txt | awk '{printf "full:%s\n", $0}' > $GOPATH/src/$GEOSITE_REPO/data/ookla-speedtest
-          echo "include:ookla-speedtest-ads" >> $GOPATH/src/$GEOSITE_REPO/data/ookla-speedtest
+          curl -L -o servers-source.xml "https://c.speedtest.net/speedtest-servers-static.php" -H "Accept-Encoding: gzip" --compressed
+          perl -ne '/host="(.+):[0-9]+"/ && print "full:$1\n"' servers-source.xml | perl -ne 'print if not /^(full:([0-9]{1,3}\.){3}[0-9]{1,3})$/' | perl -ne 'print lc' | sort --ignore-case -u >> $GOPATH/src/$GEOSITE_REPO/data/ookla-speedtest
 
       - name: Get and add direct domains into temp-direct.txt file
         run: |
-          curl -sSL $CHINA_DOMAINS_URL | awk -F '/' '{print $2}' > temp-direct.txt
+          curl -sSL $CHINA_DOMAINS_URL | perl -ne '/^server=\/([^\/]+)\// && print "$1\n"' > temp-direct.txt
 
       - name: Get and add proxy domains into temp-proxy.txt file
         run: |
-          curl -sSL $GFWLIST_DOMAINS_URL > temp-proxy.txt
-          curl -sSL $GREATFIRE_DOMAINS_URL >> temp-proxy.txt
-          curl -sSL $GOOGLE_DOMAINS_URL | awk -F '/' '{print $2}' >> temp-proxy.txt
-          curl -sSL $APPLE_DOMAINS_URL | awk -F '/' '{print $2}' >> temp-proxy.txt
-          curl -sSL $CDN_DOMAINS_URL | awk '{print $0}' >> temp-proxy.txt
+          curl -sSL $GFWLIST_DOMAINS_URL | perl -ne '/^((?=^.{3,255})[a-zA-Z0-9][-_a-zA-Z0-9]{0,62}(\.[a-zA-Z0-9][-_a-zA-Z0-9]{0,62})+)/ && print "$1\n"' > temp-proxy.txt
+          curl -sSL $GREATFIRE_DOMAINS_URL | perl -ne '/^((?=^.{3,255})[a-zA-Z0-9][-_a-zA-Z0-9]{0,62}(\.[a-zA-Z0-9][-_a-zA-Z0-9]{0,62})+)/ && print "$1\n"' >> temp-proxy.txt
+          curl -sSL $GOOGLE_DOMAINS_URL | perl -ne '/^server=\/([^\/]+)\// && print "$1\n"' >> temp-proxy.txt
+          curl -sSL $APPLE_DOMAINS_URL | perl -ne '/^server=\/([^\/]+)\// && print "$1\n"' >> temp-proxy.txt
+          curl -sSL $CDN_DOMAINS_URL| perl -ne '/^((?=^.{3,255})[a-zA-Z0-9][-_a-zA-Z0-9]{0,62}(\.[a-zA-Z0-9][-_a-zA-Z0-9]{0,62})+)/ && print "$1\n"' >> temp-proxy.txt
           curl -sSL $PROFILES_URL | awk -F ',' '/^DOMAIN(,|\-SUFFIX,).+PROXY/ {print $2}' >> temp-proxy.txt
           curl -sSL $GEQ1AN_RULES_APPLE_URL | awk -F ',' '/^(HOST|DOMAIN)(,|\-SUFFIX,).+Apple/ {print $2}' >> temp-proxy.txt
           curl -sSL $GEQ1AN_RULES_MICROSOFT_URL | awk -F ',' '/^(HOST|DOMAIN)(,|\-SUFFIX,).+Microsoft/ {print $2}' >> temp-proxy.txt
           curl -sSL $GEQ1AN_RULES_GLOBAL_MEDIA_URL | awk -F ',' '/^(HOST|DOMAIN)(,|\-SUFFIX,).+GMedia/ {print $2}' >> temp-proxy.txt
           curl -sSL $GEQ1AN_RULES_OUTSIDE_URL | awk -F ',' '/^(HOST|DOMAIN)(,|\-SUFFIX,).+Outside/ {print $2}' >> temp-proxy.txt
-          
+
       - name: Get and add reject domains into temp-reject.txt file
         run: |
           curl -sSL $PROFILES_URL | awk -F ',' '/^DOMAIN(,|\-SUFFIX,).+REJECT/ {print $2}' > temp-reject.txt
@@ -100,20 +97,14 @@ jobs:
           cat proxy.txt >> temp-proxy.txt
           cat direct.txt >> temp-direct.txt
 
-      - name: Remove repeated domains, sort domains and write domains to appropriate list
+      - name: Sort and generate lists
         run: |
-          cat temp-proxy.txt | sort --ignore-case -u > proxy-sort.txt
-          cat temp-direct.txt | sort --ignore-case -u > direct-sort.txt
-          cat temp-reject.txt | sort --ignore-case -u > reject-sort.txt
-
-      - name: Filter valid domains
-        run: |
-          cat proxy-sort.txt | awk '/^([a-zA-Z0-9[.-.][._.]]+\.)+[a-zA-Z0-9[.-.]]+$/{print $0}' > $GOPATH/src/$GEOSITE_REPO/data/proxylist
-          cat proxy-sort.txt | awk '!/^([a-zA-Z0-9[.-.][._.]]+\.)+[a-zA-Z0-9[.-.]]+$/{print $0}' > proxy-filter.txt
-          cat direct-sort.txt | awk '/^([a-zA-Z0-9[.-.][._.]]+\.)+[a-zA-Z0-9[.-.]]+$/{print $0}' > $GOPATH/src/$GEOSITE_REPO/data/directlist
-          cat direct-sort.txt | awk '!/^([a-zA-Z0-9[.-.][._.]]+\.)+[a-zA-Z0-9[.-.]]+$/{print $0}' > direct-filter.txt
-          cat reject-sort.txt | awk '/^([a-zA-Z0-9[.-.][._.]]+\.)+[a-zA-Z0-9[.-.]]+$/{print $0}' > $GOPATH/src/$GEOSITE_REPO/data/rejectlist
-          cat reject-sort.txt | awk '!/^([a-zA-Z0-9[.-.][._.]]+\.)+[a-zA-Z0-9[.-.]]+$/{print $0}' > reject-filter.txt
+          cat temp-proxy.txt | sort --ignore-case -u | perl -ne '/^((?=^.{3,255})[a-zA-Z0-9][-_a-zA-Z0-9]{0,62}(\.[a-zA-Z0-9][-_a-zA-Z0-9]{0,62})+)/ && print "$1\n"' > $GOPATH/src/$GEOSITE_REPO/data/proxylist
+          cat temp-proxy.txt | sort --ignore-case -u | perl -ne 'print if not /^((?=^.{3,255})[a-zA-Z0-9][-_a-zA-Z0-9]{0,62}(\.[a-zA-Z0-9][-_a-zA-Z0-9]{0,62})+)/' > proxy-excluse-list.txt
+          cat temp-direct.txt | sort --ignore-case -u | perl -ne '/^((?=^.{3,255})[a-zA-Z0-9][-_a-zA-Z0-9]{0,62}(\.[a-zA-Z0-9][-_a-zA-Z0-9]{0,62})+)/ && print "$1\n"' > $GOPATH/src/$GEOSITE_REPO/data/directlist
+          cat temp-direct.txt | sort --ignore-case -u | perl -ne 'print if not /^((?=^.{3,255})[a-zA-Z0-9][-_a-zA-Z0-9]{0,62}(\.[a-zA-Z0-9][-_a-zA-Z0-9]{0,62})+)/' > direct-excluse-list.txt
+          cat temp-reject.txt | sort --ignore-case -u | perl -ne '/^((?=^.{3,255})[a-zA-Z0-9][-_a-zA-Z0-9]{0,62}(\.[a-zA-Z0-9][-_a-zA-Z0-9]{0,62})+)/ && print "$1\n"' > $GOPATH/src/$GEOSITE_REPO/data/rejectlist
+          cat temp-reject.txt | sort --ignore-case -u | perl -ne 'print if not /^((?=^.{3,255})[a-zA-Z0-9][-_a-zA-Z0-9]{0,62}(\.[a-zA-Z0-9][-_a-zA-Z0-9]{0,62})+)/' > reject-excluse-list.txt
 
       - name: Add list into appropriate category file
         run: |
@@ -126,7 +117,7 @@ jobs:
         run: |
           domain-list-community
           mv ./dlc.dat ./publish/geosite.dat
-          mv ./*-filter.txt ./publish/
+          mv ./*-excluse-list.txt ./publish/
           cp -f $GOPATH/src/$GEOSITE_REPO/data/{proxy,direct,reject}list ./publish/
 
       - name: Release dat files

README.md

@@ -1,6 +1,6 @@
 # 简介
 
-**v2ray** 加强版规则文件，可代替 v2ray 官方 `geoip.dat` 和 `geosite.dat` 规则文件。利用 GitHub Actions 北京时间每天早上 6 点自动构建，保证规则最新。
+**V2Ray** 规则文件加强版，可代替 V2Ray 官方 `geoip.dat` 和 `geosite.dat` 规则文件。利用 GitHub Actions 北京时间每天早上 6 点自动构建，保证规则最新。
 
 ## 规则文件生成方式
 
@@ -32,14 +32,14 @@
 **使用方式**：
 
 1. 通过上面下载地址或[点击进入规则文件发布页面](https://github.com/Loyalsoldier/v2ray-rules-dat/releases)，下载 `geoip.dat` 和 `geosite.dat`
-2. 把下载下来的 `geoip.dat` 和 `geosite.dat` 文件放入到 v2ray 软件的规则文件目录，替换掉原来的 `geoip.dat` 和 `geosite.dat`
-3. 修改 v2ray 配置文件，配置参考下面 👇👇👇
+2. 把下载下来的 `geoip.dat` 和 `geosite.dat` 文件放入到 V2Ray 软件的规则文件目录，替换掉原来的 `geoip.dat` 和 `geosite.dat`
+3. 修改 V2Ray 配置文件，配置参考下面 👇👇👇
 
 ## 参考配置
 
 ### geoip.dat
 
-跟 v2ray 官方 `geoip.dat` 配置方式相同。
+跟 V2Ray 官方 `geoip.dat` 配置方式相同。
 
 **Routing 配置方式**：
 
@@ -62,7 +62,7 @@
 
 ### geosite.dat
 
-跟 v2ray 官方 `geosite.dat` 配置方式相同。
+跟 V2Ray 官方 `geosite.dat` 配置方式相同。
 
 **Routing 配置方式**：