commit aea788adf3d45d34ee6bcd5fed3778446c2311a8
Author: bgme <i@bgme.me>
Date: Thu Jan 19 17:14:23 2023 +0800
init
diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..902a101
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,173 @@
+# Created by https://www.toptal.com/developers/gitignore/api/python
+# Edit at https://www.toptal.com/developers/gitignore?templates=python
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+# Usually these files are written by a python script from a template
+# before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+# For a library or package, you might want to ignore these files since the code is
+# intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+# However, in case of collaboration, if having platform-specific dependencies or dependencies
+# having no cross-platform support, pipenv may install dependencies that don't work, or not
+# install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+# This is especially recommended for binary packages to ensure reproducibility, and is more
+# commonly ignored for libraries.
+# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+# in version control.
+# https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+# and can be added to the global gitignore or merged into this file. For a more nuclear
+# option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+
+# End of https://www.toptal.com/developers/gitignore/api/python
+
+/.idea
diff --git a/main.py b/main.py
new file mode 100644
index 0000000..10b35f3
--- /dev/null
+++ b/main.py
@@ -0,0 +1,177 @@
+import base64
+import logging
+import re
+import subprocess
+import sys
+from urllib.request import urlopen
+
+PROXY_DNS_IP = '127.0.0.1'
+PROXY_DNS_PORT = '5353'
+
+DNSMASQ_RULES_FILE = '/tmp/dnsmasq.d/gfwlist'
+
+# https://github.com/gfwlist/gfwlist
+GFWLIST_URL_LIST = [
+ "https://raw.githubusercontent.com/gfwlist/gfwlist/master/gfwlist.txt",
+ "https://pagure.io/gfwlist/raw/master/f/gfwlist.txt",
+ "https://gitlab.com/gfwlist/gfwlist/raw/master/gfwlist.txt",
+ "https://git.tuxfamily.org/gfwlist/gfwlist.git/plain/gfwlist.txt",
+ "http://repo.or.cz/gfwlist.git/blob_plain/HEAD:/gfwlist.txt"
+]
+
+
+def get_gfwlist_text() -> str:
+ for url in GFWLIST_URL_LIST:
+ try:
+ logging.info('request {url}'.format(url=url))
+ with urlopen(url, timeout=15) as responsee:
+ return base64.b64decode(responsee.read()).decode('utf-8')
+ except:
+ pass
+ raise IOError("can't download gfwlist")
+
+
+def is_comment(line: str) -> bool:
+ comment_re = re.compile(r'^!|\[AutoProxy')
+ return bool(comment_re.match(line))
+
+
+def has_ip(line: str) -> bool:
+ # https://stackoverflow.com/questions/5284147/validating-ipv4-addresses-with-regexp
+ # https://stackoverflow.com/questions/53497/regular-expression-that-matches-valid-ipv6-addresses
+ ipv4_re = re.compile(r'((25[0-5]|(2[0-4]|1\d|[1-9]|)\d)\.?\b){4}')
+ ipv6_re = re.compile(
+ r'(([0-9a-fA-F]{1,4}:){7,7}[0-9a-fA-F]{1,4}|([0-9a-fA-F]{1,4}:){1,7}:|([0-9a-fA-F]{1,4}:){1,6}:[0-9a-fA-F]{1,4}|([0-9a-fA-F]{1,4}:){1,5}(:[0-9a-fA-F]{1,4}){1,2}|([0-9a-fA-F]{1,4}:){1,4}(:[0-9a-fA-F]{1,4}){1,3}|([0-9a-fA-F]{1,4}:){1,3}(:[0-9a-fA-F]{1,4}){1,4}|([0-9a-fA-F]{1,4}:){1,2}(:[0-9a-fA-F]{1,4}){1,5}|[0-9a-fA-F]{1,4}:((:[0-9a-fA-F]{1,4}){1,6})|:((:[0-9a-fA-F]{1,4}){1,7}|:)|fe80:(:[0-9a-fA-F]{0,4}){0,4}%[0-9a-zA-Z]{1,}|::(ffff(:0{1,4}){0,1}:){0,1}((25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}(25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])|([0-9a-fA-F]{1,4}:){1,4}:((25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9])\.){3,3}(25[0-5]|(2[0-4]|1{0,1}[0-9]){0,1}[0-9]))')
+ return bool(ipv4_re.findall(line)) or bool(ipv6_re.findall(line))
+
+
+def is_exception(line: str) -> bool:
+ exception_re = re.compile(r'^@@')
+ return bool(exception_re.match(line))
+
+
+def is_regular(line: str) -> bool:
+ regular_re = re.compile(r'^/')
+ return bool(regular_re.match(line))
+
+
+def gfwlist_line_filter(line: str) -> bool:
+ line = line.strip()
+ return (line != '') and (not is_comment(line)) and (not has_ip(line)) \
+ and (not is_exception(line)) and (not is_regular(line))
+
+
+def gfwlist_line_converter(line: str) -> str:
+ raw_line = line
+
+ line = line.strip()
+ line = re.sub(r'/$', '', line)
+
+ def invalid_rule_return():
+ logging.debug('invalid rule: ' + raw_line)
+ return ""
+
+ def convert_asterisk(line: str) -> str:
+ asterisk_re = re.compile(r'^[\w\-_]*\*[\w\-_]*\.')
+ # 替换开头的 *.
+ if re.match(asterisk_re, line):
+ line = asterisk_re.sub("", line)
+ # 移除中间含 * 的规则
+ if '*' in line:
+ return invalid_rule_return()
+ return line
+
+ # ||global.bing.com
+ # ||cdn*.i-scmp.com
+ if line.startswith('||'):
+ line = line.replace('||', "")
+ return convert_asterisk(line)
+
+ # |http://www.dmm.com/netgame
+ # |http://bbs.cantonese.asia/
+ # |http://www.dmm.com/netgame
+ # |http://*.1mobile.tw
+ # |http://*2.bahamut.com.tw
+ if line.startswith('|'):
+ line = line.replace('|', '')
+ line = re.sub(r'^http(s)?://', '', line)
+ # 移除含有 path 的规则
+ if '/' in line:
+ return invalid_rule_return()
+ return convert_asterisk(line)
+
+ # .casinobellini.com
+ # share.dmhy.org
+ # .ddns.net/
+ # bbs.sina.com%2F
+ # .amazon.com/Dalai-Lama
+ # amazon.com/Prisoner-State-Secret-Journal-Premier
+ # .keepandshare.com/visit/visit_page.php?i=688154
+ # .pentoy.hk/%E6%99%82%E4%BA%8B
+ # .ruanyifeng.com/blog*some_ways_to_break_the_great_firewall
+ # prisoner-state-secret-journal-premier
+ # q%3Dfreedom
+ # search*safeweb
+ # q=triangle
+ # ultrareach
+
+ # 移除非域名规则
+ if '.' not in line:
+ return invalid_rule_return()
+
+ # 移除 http 协议头
+ line = re.sub(r'^http(s)?://', '', line)
+
+ # 移除含 path 、含 params 的规则
+ for m in ['/', '?', '=']:
+ if m in line:
+ return invalid_rule_return()
+ # 移除非asci字符
+ if re.match(r'%\w\w', line):
+ return invalid_rule_return()
+
+ line = convert_asterisk(line)
+
+ # 移除域名最开头的 .
+ if line.startswith('.'):
+ line = re.sub(r'^\.', "", line)
+
+ return line
+
+
+def get_gfwlist_hosts() -> set[str]:
+ gfwlist_text = get_gfwlist_text()
+ gfwlist_lines = gfwlist_text.splitlines()
+ return set(
+ filter(
+ lambda line: line != "",
+ map(
+ gfwlist_line_converter,
+ filter(gfwlist_line_filter, gfwlist_lines)
+ )
+ )
+ )
+
+
+def get_dnsmasq_text() -> str:
+ rule_list = list(
+ map(
+ lambda host: "server=/{host}/{dns_ip}#{dns_port}".format(host=host, dns_ip=PROXY_DNS_IP,
+ dns_port=PROXY_DNS_PORT),
+ sorted(list(get_gfwlist_hosts()))
+ )
+ )
+ return '\n'.join(rule_list)
+
+
+def main():
+ dnsmasq_text = get_dnsmasq_text()
+ with open(DNSMASQ_RULES_FILE, 'w') as f:
+ f.write(dnsmasq_text)
+ subprocess.run(["/etc/init.d/dnsmasq", "restart"])
+
+
+if __name__ == '__main__':
+ logging.basicConfig(stream=sys.stderr, level=logging.INFO, format="%(levelname)s:%(message)s")
+
+ main()