# coding=utf-8 # 这是为Google和中文维基(无缝整合)镜像配置的示例配置文件 # # 使用方法: # 1. 复制本文件到 zmirror 根目录(wsgi.py所在目录), 并重命名为 config.py # 2. 修改 my_host_name 为你自己的域名 # # 各项设置选项的详细介绍请看 config_default.py 中对应的部分 # 本配置文件假定你的服务器本身在墙外 # 如果服务器本身在墙内(或者在本地环境下测试, 请修改`Proxy Settings`中的设置 # # 由于google搜索结果经常会出现中文维基, 所以顺便把它也加入了. # google跟中文维基之间使用了本程序的镜像隔离功能, 可以保证中文维基站的正常使用 # # 本配置文件试图还原出一个功能完整的google. # 但是由于程序本身所限, 还是不能[完整]镜像过来整个[google站群] # 在后续版本会不断增加可用的网站 # # 以下google服务完全可用: # google网页搜索/学术/图片/新闻/图书/视频(搜索)/财经/APP搜索/翻译/网页快照/... # google搜索与中文维基百科无缝结合 # 以下服务部分可用: # gg地图(地图可看, 左边栏显示不正常)/G+(不能登录) # 以下服务暂不可用(因为目前无法解决登录的问题): # 所有需要登录的东西, docs之类的 # # Github: https://github.com/aploium/zmirror # ############## Local Domain Settings ############## my_host_name = 'ggb123.cn' my_host_scheme = 'https://' my_host_port = None # None表示使用默认端口, 可以设置成非标准端口, 比如 81 # ############## Target Domain Settings ############## target_domain = 'www.geogebra.org' target_scheme = 'https://' # 这里面大部分域名都是通过 `enable_automatic_domains_whitelist` 自动采集的, 我只是把它们复制黏贴到了这里 # 实际镜像一个新的站时, 手动只需要添加很少的几个域名就可以了. # 自动采集(如果开启的话)会不断告诉你新域名 external_domains = ( "accounts-beta.geogebra.org", "accounts.geogebra.org", "api.geogebra.org", "autotest2.geogebra.org", "beta.geogebra.org", "cdn.geogebra.org", "community.geogebra.org", "data-logger.geogebra.org", "dev.geogebra.org", "download.geogebra.org", #"help.geogebra.org", #"live.geogebra.org", "stage.geogebra.org", "static.geogebra.org", "tube.geogebra.org", "web.geogebra.org", #"wiki.geogebra.org", "static.hotjar.com", "script.hotjar.com", "vars.hotjar.com", "cdnjs.cloudflare.com", "fonts.gstatic.com", "forum.gstatic.com", "geogebra.github.io", #"c60708c831e2.edge.captcha-sdk.awswaf.com", ) # 强制所有Google站点使用HTTPS force_https_domains = 'ALL' # 自动动态添加域名 enable_automatic_domains_whitelist = True domains_whitelist_auto_add_glob_list = ( # "*.awswaf.com", ) # ############## Proxy Settings ############## # 如果你在墙内使用本配置文件, 请指定一个墙外的http代理 is_use_proxy = False # 代理的格式及SOCKS代理, 请看 http://docs.python-requests.org/en/latest/user/advanced/#proxies requests_proxies = dict( http='http://127.0.0.1:8123', https='https://127.0.0.1:8123', ) # ############## Sites Isolation ############## enable_individual_sites_isolation = True # 镜像隔离, 用于支持Google和维基共存 isolated_domains = { #'api.geogebra.org', #'www.google-analytics.com', #'zh.m.wikipedia.org' } # ############## URL Custom Redirect ############## url_custom_redirect_enable = True url_custom_redirect_list = { # 这是一个方便的设置, 如果你访问 /wiki ,程序会自动重定向到后面这个长长的wiki首页 #'/wiki': '/extdomains/https-zh.wikipedia.org/', # 这是gmail #'/gmail': '/extdomains/mail.google.com/mail/u/0/h/girbaeneuj90/', #'/tencent5487524491536532369.txt': '/extdomains/ali.ggb123.cn/tencent5487524491536532369.txt', '/m/dfJGV6Jw': '/extdomains/www.geogebra.org/', '/m/utjBZfbe': '/extdomains/www.geogebra.org/', '/search/%E5%9C%8B%E6%97%97': '/extdomains/www.geogebra.org/', } # If you want more complicated regex redirect, please add then in this dict. # If url FULLY MATCH the first regex, the second regex for re.sub will be applied # Same as above, only the url PATH will be applied (maybe change in later version) # Please see https://docs.python.org/3.5/library/re.html#re.sub for more rules # # Dependency: url_custom_redirect_enable == True url_custom_redirect_regex = ( # v0.18.0+ because the new sites isolation mechanism, these redirect are NO LONGER NEEDED FOR WIKIPEDIA # now, they are for sample only. # # This example fix mobile wikipedia's search bug # will redirect /wiki/Some_wiki_page to /extdomains/https-zh.m.wikipedia.org/wiki/Some_wiki_page # (r'^/wiki/(?P.*)$', '/extdomains/https-zh.m.wikipedia.org/wiki/\g'), # (r'.*recaptcha__zh_cn\.js$', '/extdomains/www.ggb123.cn/recaptcha.ggb123.js'), (r'^/extdomains/accounts\.geogebra\.org/scripts/create\.js.*$', '/extdomains/www.ggb123.cn/create.js'), (r'^/c60708c831e2/jsapi\.js.*$', '/extdomains/www.ggb123.cn/jsapi.js'), (r'^/extdomains/www\.google\.com/recaptcha/api\.js.*$', '/extdomains/accounts.geogebra.org/scripts/gt.js?v=0.2'), (r'^/$', '/extdomains/www.ggb123.cn/geogebra.html'), (r'^/sp-assets/_next/static/chunks/571-69291bd65ab08f61\.js$', '/extdomains/www.ggb123.cn/571-69291bd65ab08f61.js?v=20240705004'), ) # ############## Misc ############## # v0.18.5+ # eg: {'access-control-max-age', 'access-control-allow-origin', 'x-connection-hash'} # must be lower case # 在默认允许的headers以外添加一些允许被传送到用户的http响应头, 一般不需要添加自定义的. 内置的够用了 # 必须全部小写 custom_allowed_remote_headers = {'access-control-allow-origin',} custom_allowed_origin = '*' #custom_text_rewriter_enable = True #url_custom_redirect_enable = False plain_replace_domain_alias = [ ('www.googletagmanager.com', 'www.ggb123.cn'), ('www.google-analytics.com', 'www.ggb123.cn'), ('domain=geogebra.org', 'domain=ggb123.cn'), ] #domains_alias_to_target_domain = ['api.geogebra.org'] enable_connection_keep_alive = True # ############## Output Settings ############## # Verbose level (0~4) 0:important and error 1:info 2:warning 3/4:debug. Default is 3 (for first time runner) # 注意: 在正式部署到服务器后, 请把这个值修改为2, 如果设置为3或4,会产生非常大量的debug输出 verbose_level = 1 custom_inject_content = { "head_first": [ { "content": r"""""", "url_regex": r"^.*user\/create", }, ], "head_last": [ { "content": r"""""", "url_regex": r"^[^\/]+[^.]*$", }, ] } developer_temporary_disable_ssrf_prevention = True local_cache_enable = False #developer_dump_all_traffics = True developer_do_not_verify_ssl=True