RuleList/config.yaml at main · OOM-WG/RuleList · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
# 基础配置
work_dir: "./tmp"
output_dir: "./out"

# Mihomo 配置
mihomo:
  api_url: "https://api.github.com/repos/MetaCubeX/mihomo/releases"
  start_with: "mihomo-linux-amd64-alpha"
  end_with: ".gz"

# sing-box 配置（用于生成 .srs 格式规则集）
singbox:
  api_url: "https://api.github.com/repos/SagerNet/sing-box/releases"
  start_with: "sing-box-"
  end_with: "-linux-amd64.tar.gz"

# Git 配置
git:
  user_email: "259484229+oom-wg[bot]@users.noreply.github.com"
  user_name: "oom-wg[bot]"
  release_branch: "release"
  max_history: 7
  timezone: "Asia/Shanghai"

# 任务配置
tasks:
  ad:
    format: "mrs srs"
    src: # 会自动去重
      - "https://github.com/privacy-protection-tools/anti-AD/raw/refs/heads/master/anti-ad-clash.yaml"
      - "https://github.com/Cats-Team/AdRules/raw/refs/heads/main/adrules_domainset.txt"
      - "https://github.com/MetaCubeX/meta-rules-dat/raw/refs/heads/meta/geo/geosite/category-httpdns-cn@ads.list"
      - "https://github.com/ignaciocastro/a-dove-is-dumb/raw/refs/heads/main/pihole.txt"
    custom_script: |
      print(f"  -> 执行自定义 AD 清洗，处理前数量: {len(domains)}")

      # 定义需要移除的后缀，及其对应的替换规则 (None 代表只删不补)
      # 格式: ".后缀": "替换内容"
      rules_map = {
          ".xx.fbcdn.net.iberostar.com": "+.xx.fbcdn.net.iberostar.com",
          ".wns.windows.com":            "+.wns.windows.com",
          ".p2l.info":                   "+.p2l.info",
          ".net.mydays.de":              "+.net.mydays.de",
          ".net.anwalt.de":              "+.net.anwalt.de",
          ".wo.com.cn":                  None,  # 只移除规则(即放行)，不添加泛屏蔽
          ".apps.iocnt.de":              "+.apps.iocnt.de" # 用于配合下面的正则判断
      }
      new_domains = []

      # 单次循环处理所有逻辑 (性能大大提升)
      for d in domains:
          skip = False

          # 1. 特殊正则逻辑: 处理 data-xxx.apps.iocnt.de
          if d.startswith("+.data-") and d.endswith(".apps.iocnt.de"):
              skip = True

          # 2. 批量后缀匹配
          if not skip:
              for suffix in rules_map:
                  if d.endswith(suffix):
                      skip = True
                      break

          # 3. 如果没被标记跳过，则保留
          if not skip:
              new_domains.append(d)
      # 4. 统一补回泛域名规则
      for replacement in rules_map.values():
          if replacement:
              new_domains.append(replacement)
      domains = new_domains
      print(f"  -> 清洗完成，处理后数量: {len(domains)}")

  cn:
    format: "mrs srs"
    src:
      - "https://github.com/MetaCubeX/meta-rules-dat/raw/meta/geo/geosite/cn.list"
      - "https://github.com/MetaCubeX/meta-rules-dat/raw/meta/geo/geosite/steam@cn.list"
      - "https://github.com/MetaCubeX/meta-rules-dat/raw/meta/geo/geosite/microsoft@cn.list"
      - "https://github.com/MetaCubeX/meta-rules-dat/raw/meta/geo/geosite/google@cn.list"
      - "https://github.com/MetaCubeX/meta-rules-dat/raw/meta/geo/geosite/win-update.list"
      - "https://github.com/MetaCubeX/meta-rules-dat/raw/meta/geo/geosite/private.list"
    # 自定义清洗脚本
    # 在这里编写 Python 代码，变量名 'domains' 是一个列表，包含了当前所有的域名行
    custom_script: |
      print(f"  -> 执行自定义清洗，处理前数量: {len(domains)}")
      # 简单的过滤列表 (只删不补的放在这里)
      # 复杂的逻辑或者需要补回的建议用上面的结构，或者保持现在的写法

      # 过滤包含特定字符串的行
      domains = [d for d in domains if "dsp.mp.microsoft.com" not in d]

      # 过滤后缀
      filter_suffixes = (
          ".wns.windows.com",
          ".100.in-addr.arpa",
          ".download.prss.microsoft.com"
      )
      # endswith 实际上支持传入元组 (tuple)，一次匹配多个
      domains = [d for d in domains if not d.endswith(filter_suffixes)]
      # 批量补回
      domains.append("+.do.dsp.mp.microsoft.com")
      domains.append("+.wns.windows.com")
      domains.append("+.100.in-addr.arpa")
      domains.append("+.download.prss.microsoft.com")

      print(f"  -> 清洗完成，处理后数量: {len(domains)}")

  cnIP:
    format: "mrs srs"
    src:
      - "https://github.com/MetaCubeX/meta-rules-dat/raw/meta/geo/geoip/cn.list"
      - "https://github.com/MetaCubeX/meta-rules-dat/raw/meta/geo/geoip/private.list"