2019-06-27 03:25:07 +00:00
<!DOCTYPE html>
< html lang = "en" >
< head >
< meta charset = "utf-8" >
< meta http-equiv = "X-UA-Compatible" content = "IE=edge" >
< meta name = "generator" content = "Crystal Docs 0.29.0" >
< link href = "../css/style.css" rel = "stylesheet" type = "text/css" >
< script type = "text/javascript" src = "../js/doc.js" > < / script >
< script type = "text/javascript" >
CrystalDoc.base_path = "../";
< / script >
< meta id = "repository-name" content = "github.com/watzon/arachnid" >
< title > Arachnid::Agent - github.com/watzon/arachnid< / title >
< / head >
< body >
< div class = "sidebar" >
< div class = "sidebar-header" >
< div class = "search-box" >
< input type = "search" class = "search-input" placeholder = "Search..." spellcheck = "false" aria-label = "Search" >
< / div >
< div class = "repository-links" >
< a href = "../index.html" > README< / a >
< / div >
< / div >
< div class = "search-results" class = "hidden" >
< ul class = "search-list" > < / ul >
< / div >
< div class = "types-list" >
< ul >
< li class = "parent open current" data-id = "github.com/watzon/arachnid/Arachnid" data-name = "arachnid" >
< a href = "../Arachnid.html" > Arachnid< / a >
< ul >
< li class = "parent open current" data-id = "github.com/watzon/arachnid/Arachnid/Agent" data-name = "arachnid::agent" >
< a href = "../Arachnid/Agent.html" > Agent< / a >
< ul >
< li class = "parent " data-id = "github.com/watzon/arachnid/Arachnid/Agent/Actions" data-name = "arachnid::agent::actions" >
< a href = "../Arachnid/Agent/Actions.html" > Actions< / a >
< ul >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Agent/Actions/Action" data-name = "arachnid::agent::actions::action" >
< a href = "../Arachnid/Agent/Actions/Action.html" > Action< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Agent/Actions/Paused" data-name = "arachnid::agent::actions::paused" >
< a href = "../Arachnid/Agent/Actions/Paused.html" > Paused< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Agent/Actions/RuntimeError" data-name = "arachnid::agent::actions::runtimeerror" >
< a href = "../Arachnid/Agent/Actions/RuntimeError.html" > RuntimeError< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Agent/Actions/SkipLink" data-name = "arachnid::agent::actions::skiplink" >
< a href = "../Arachnid/Agent/Actions/SkipLink.html" > SkipLink< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Agent/Actions/SkipResource" data-name = "arachnid::agent::actions::skipresource" >
< a href = "../Arachnid/Agent/Actions/SkipResource.html" > SkipResource< / a >
< / li >
< / ul >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Agent/Queue" data-name = "arachnid::agent::queue" >
< a href = "../Arachnid/Agent/Queue.html" > Queue< / a >
< / li >
< / ul >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/AuthCredential" data-name = "arachnid::authcredential" >
< a href = "../Arachnid/AuthCredential.html" > AuthCredential< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/AuthStore" data-name = "arachnid::authstore" >
< a href = "../Arachnid/AuthStore.html" > AuthStore< / a >
< / li >
2019-06-30 23:30:15 +00:00
< li class = "parent " data-id = "github.com/watzon/arachnid/Arachnid/Cli" data-name = "arachnid::cli" >
< a href = "../Arachnid/Cli.html" > Cli< / a >
< ul >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Action" data-name = "arachnid::cli::action" >
< a href = "../Arachnid/Cli/Action.html" > Action< / a >
< / li >
< li class = "parent " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library" data-name = "arachnid::cli::command_main_command_of_clim_library" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library.html" > Command_Main_command_of_clim_library< / a >
< ul >
< li class = "parent " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Sitemap" data-name = "arachnid::cli::command_main_command_of_clim_library::command_sitemap" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Sitemap.html" > Command_Sitemap< / a >
< ul >
< li class = "parent " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Sitemap/Options_Sitemap" data-name = "arachnid::cli::command_main_command_of_clim_library::command_sitemap::options_sitemap" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Sitemap/Options_Sitemap.html" > Options_Sitemap< / a >
< ul >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Sitemap/Options_Sitemap/Option_help" data-name = "arachnid::cli::command_main_command_of_clim_library::command_sitemap::options_sitemap::option_help" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Sitemap/Options_Sitemap/Option_help.html" > Option_help< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Sitemap/Options_Sitemap/Option_json" data-name = "arachnid::cli::command_main_command_of_clim_library::command_sitemap::options_sitemap::option_json" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Sitemap/Options_Sitemap/Option_json.html" > Option_json< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Sitemap/Options_Sitemap/Option_output" data-name = "arachnid::cli::command_main_command_of_clim_library::command_sitemap::options_sitemap::option_output" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Sitemap/Options_Sitemap/Option_output.html" > Option_output< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Sitemap/Options_Sitemap/Option_xml" data-name = "arachnid::cli::command_main_command_of_clim_library::command_sitemap::options_sitemap::option_xml" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Sitemap/Options_Sitemap/Option_xml.html" > Option_xml< / a >
< / li >
< / ul >
< / li >
< li class = "parent " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Sitemap/Options_Sitemap" data-name = "arachnid::cli::command_main_command_of_clim_library::command_sitemap::options_sitemap" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Sitemap/Options_Sitemap.html" > Options_Sitemap< / a >
< ul >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Sitemap/Options_Sitemap/Option_help" data-name = "arachnid::cli::command_main_command_of_clim_library::command_sitemap::options_sitemap::option_help" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Sitemap/Options_Sitemap/Option_help.html" > Option_help< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Sitemap/Options_Sitemap/Option_json" data-name = "arachnid::cli::command_main_command_of_clim_library::command_sitemap::options_sitemap::option_json" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Sitemap/Options_Sitemap/Option_json.html" > Option_json< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Sitemap/Options_Sitemap/Option_output" data-name = "arachnid::cli::command_main_command_of_clim_library::command_sitemap::options_sitemap::option_output" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Sitemap/Options_Sitemap/Option_output.html" > Option_output< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Sitemap/Options_Sitemap/Option_xml" data-name = "arachnid::cli::command_main_command_of_clim_library::command_sitemap::options_sitemap::option_xml" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Sitemap/Options_Sitemap/Option_xml.html" > Option_xml< / a >
< / li >
< / ul >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Sitemap/RunProc" data-name = "arachnid::cli::command_main_command_of_clim_library::command_sitemap::runproc" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Sitemap/RunProc.html" > RunProc< / a >
< / li >
< / ul >
< / li >
< li class = "parent " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize" data-name = "arachnid::cli::command_main_command_of_clim_library::command_summarize" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize.html" > Command_Summarize< / a >
< ul >
< li class = "parent " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize" data-name = "arachnid::cli::command_main_command_of_clim_library::command_summarize::options_summarize" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize.html" > Options_Summarize< / a >
< ul >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize/Option_codes" data-name = "arachnid::cli::command_main_command_of_clim_library::command_summarize::options_summarize::option_codes" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize/Option_codes.html" > Option_codes< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize/Option_elinks" data-name = "arachnid::cli::command_main_command_of_clim_library::command_summarize::options_summarize::option_elinks" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize/Option_elinks.html" > Option_elinks< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize/Option_help" data-name = "arachnid::cli::command_main_command_of_clim_library::command_summarize::options_summarize::option_help" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize/Option_help.html" > Option_help< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize/Option_ilinks" data-name = "arachnid::cli::command_main_command_of_clim_library::command_summarize::options_summarize::option_ilinks" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize/Option_ilinks.html" > Option_ilinks< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize/Option_limit" data-name = "arachnid::cli::command_main_command_of_clim_library::command_summarize::options_summarize::option_limit" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize/Option_limit.html" > Option_limit< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize/Option_output" data-name = "arachnid::cli::command_main_command_of_clim_library::command_summarize::options_summarize::option_output" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize/Option_output.html" > Option_output< / a >
< / li >
< / ul >
< / li >
< li class = "parent " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize" data-name = "arachnid::cli::command_main_command_of_clim_library::command_summarize::options_summarize" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize.html" > Options_Summarize< / a >
< ul >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize/Option_codes" data-name = "arachnid::cli::command_main_command_of_clim_library::command_summarize::options_summarize::option_codes" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize/Option_codes.html" > Option_codes< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize/Option_elinks" data-name = "arachnid::cli::command_main_command_of_clim_library::command_summarize::options_summarize::option_elinks" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize/Option_elinks.html" > Option_elinks< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize/Option_help" data-name = "arachnid::cli::command_main_command_of_clim_library::command_summarize::options_summarize::option_help" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize/Option_help.html" > Option_help< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize/Option_ilinks" data-name = "arachnid::cli::command_main_command_of_clim_library::command_summarize::options_summarize::option_ilinks" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize/Option_ilinks.html" > Option_ilinks< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize/Option_limit" data-name = "arachnid::cli::command_main_command_of_clim_library::command_summarize::options_summarize::option_limit" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize/Option_limit.html" > Option_limit< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize/Option_output" data-name = "arachnid::cli::command_main_command_of_clim_library::command_summarize::options_summarize::option_output" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/Options_Summarize/Option_output.html" > Option_output< / a >
< / li >
< / ul >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/RunProc" data-name = "arachnid::cli::command_main_command_of_clim_library::command_summarize::runproc" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Command_Summarize/RunProc.html" > RunProc< / a >
< / li >
< / ul >
< / li >
< li class = "parent " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Options_Main_command_of_clim_library" data-name = "arachnid::cli::command_main_command_of_clim_library::options_main_command_of_clim_library" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Options_Main_command_of_clim_library.html" > Options_Main_command_of_clim_library< / a >
< ul >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Options_Main_command_of_clim_library/Option_help" data-name = "arachnid::cli::command_main_command_of_clim_library::options_main_command_of_clim_library::option_help" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Options_Main_command_of_clim_library/Option_help.html" > Option_help< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Options_Main_command_of_clim_library/Option_version" data-name = "arachnid::cli::command_main_command_of_clim_library::options_main_command_of_clim_library::option_version" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Options_Main_command_of_clim_library/Option_version.html" > Option_version< / a >
< / li >
< / ul >
< / li >
< li class = "parent " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Options_Main_command_of_clim_library" data-name = "arachnid::cli::command_main_command_of_clim_library::options_main_command_of_clim_library" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Options_Main_command_of_clim_library.html" > Options_Main_command_of_clim_library< / a >
< ul >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Options_Main_command_of_clim_library/Option_help" data-name = "arachnid::cli::command_main_command_of_clim_library::options_main_command_of_clim_library::option_help" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Options_Main_command_of_clim_library/Option_help.html" > Option_help< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/Options_Main_command_of_clim_library/Option_version" data-name = "arachnid::cli::command_main_command_of_clim_library::options_main_command_of_clim_library::option_version" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/Options_Main_command_of_clim_library/Option_version.html" > Option_version< / a >
< / li >
< / ul >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Command_Main_command_of_clim_library/RunProc" data-name = "arachnid::cli::command_main_command_of_clim_library::runproc" >
< a href = "../Arachnid/Cli/Command_Main_command_of_clim_library/RunProc.html" > RunProc< / a >
< / li >
< / ul >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Count" data-name = "arachnid::cli::count" >
< a href = "../Arachnid/Cli/Count.html" > Count< / a >
< / li >
< li class = "parent " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Sitemap" data-name = "arachnid::cli::sitemap" >
< a href = "../Arachnid/Cli/Sitemap.html" > Sitemap< / a >
< ul >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Sitemap/LastMod" data-name = "arachnid::cli::sitemap::lastmod" >
< a href = "../Arachnid/Cli/Sitemap/LastMod.html" > LastMod< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Cli/Sitemap/PageMap" data-name = "arachnid::cli::sitemap::pagemap" >
< a href = "../Arachnid/Cli/Sitemap/PageMap.html" > PageMap< / a >
< / li >
< / ul >
< / li >
< / ul >
< / li >
2019-06-27 03:25:07 +00:00
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/CookieJar" data-name = "arachnid::cookiejar" >
< a href = "../Arachnid/CookieJar.html" > CookieJar< / a >
< / li >
< li class = "parent " data-id = "github.com/watzon/arachnid/Arachnid/Document" data-name = "arachnid::document" >
< a href = "../Arachnid/Document.html" > Document< / a >
< ul >
< li class = "parent " data-id = "github.com/watzon/arachnid/Arachnid/Document/HTML" data-name = "arachnid::document::html" >
< a href = "../Arachnid/Document/HTML.html" > HTML< / a >
< ul >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Document/HTML/Tag" data-name = "arachnid::document::html::tag" >
< a href = "../Arachnid/Document/HTML/Tag.html" > Tag< / a >
< / li >
< / ul >
< / li >
< / ul >
< / li >
< li class = "parent " data-id = "github.com/watzon/arachnid/Arachnid/Resource" data-name = "arachnid::resource" >
< a href = "../Arachnid/Resource.html" > Resource< / a >
< ul >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Resource/ContentTypes" data-name = "arachnid::resource::contenttypes" >
< a href = "../Arachnid/Resource/ContentTypes.html" > ContentTypes< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Resource/Cookies" data-name = "arachnid::resource::cookies" >
< a href = "../Arachnid/Resource/Cookies.html" > Cookies< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Resource/HTML" data-name = "arachnid::resource::html" >
< a href = "../Arachnid/Resource/HTML.html" > HTML< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Resource/StatusCodes" data-name = "arachnid::resource::statuscodes" >
< a href = "../Arachnid/Resource/StatusCodes.html" > StatusCodes< / a >
< / li >
< / ul >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/Rules" data-name = "arachnid::rules(t)" >
< a href = "../Arachnid/Rules.html" > Rules< / a >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/Arachnid/SessionCache" data-name = "arachnid::sessioncache" >
< a href = "../Arachnid/SessionCache.html" > SessionCache< / a >
< / li >
< / ul >
< / li >
< li class = " " data-id = "github.com/watzon/arachnid/URI" data-name = "uri" >
< a href = "../URI.html" > URI< / a >
< / li >
< / ul >
< / div >
< / div >
< div class = "main-content" >
< h1 class = "type-name" >
< span class = "kind" > class< / span > Arachnid::Agent
< / h1 >
< ul class = "superclass-hierarchy" > < li class = "superclass" > < a href = "../Arachnid/Agent.html" > Arachnid::Agent< / a > < / li > < li class = "superclass" > Reference< / li > < li class = "superclass" > Object< / li > < / ul >
< h2 > Defined in:< / h2 >
2019-06-30 23:53:02 +00:00
< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/sanitizers.cr#L2" target = "_blank" >
2019-06-27 03:25:07 +00:00
arachnid/agent/sanitizers.cr
< / a >
< br / >
2019-06-30 23:53:02 +00:00
< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L4" target = "_blank" >
2019-06-27 03:25:07 +00:00
arachnid/agent/filters.cr
< / a >
< br / >
2019-06-30 23:53:02 +00:00
< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L4" target = "_blank" >
2019-06-27 03:25:07 +00:00
arachnid/agent/events.cr
< / a >
< br / >
2019-06-30 23:53:02 +00:00
< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/actions.cr#L2" target = "_blank" >
2019-06-27 03:25:07 +00:00
arachnid/agent/actions.cr
< / a >
< br / >
2019-06-30 23:53:02 +00:00
< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/robots.cr#L2" target = "_blank" >
2019-06-27 03:25:07 +00:00
arachnid/agent/robots.cr
< / a >
< br / >
2019-06-30 23:53:02 +00:00
< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L12" target = "_blank" >
2019-06-27 03:25:07 +00:00
arachnid/agent.cr
< / a >
< br / >
2019-06-30 23:53:02 +00:00
< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/queue.cr#L6" target = "_blank" >
2019-06-27 03:25:07 +00:00
arachnid/agent/queue.cr
< / a >
< br / >
< h2 > Constructors< / h2 >
< ul class = "list-summary" >
< li class = "entry-summary" >
< a href = "#new%28host%3AString%3F%3Dnil%2Cread_timeout%3AInt32%3F%3Dnil%2Cconnect_timeout%3AInt32%3F%3Dnil%2Cmax_redirects%3AInt32%3F%3Dnil%2Cdo_not_track%3ABool%3F%3Dnil%2Cdefault_headers%3AHash%28String%2CString%29%3F%3Dnil%2Chost_header%3AString%3F%3Dnil%2Chost_headers%3AHash%28String%7CRegex%2CString%29%3F%3Dnil%2Cuser_agent%3AString%3F%3Dnil%2Creferer%3AString%3F%3Dnil%2Cfetch_delay%3AInt32%7CTime%3A%3ASpan%3F%3Dnil%2Cqueue%3AHash%28String%2CURI%29%3F%3Dnil%2Chistory%3ASet%28URI%29%3F%3Dnil%2Climit%3AInt32%3F%3Dnil%2Cmax_depth%3AInt32%3F%3Dnil%2Crobots%3ABool%3F%3Dnil%2Cfilter_options%3Dnil%29-class-method" class = "signature" > < strong > .new< / strong > (host : String? = < span class = "n" > nil< / span > , read_timeout : Int32? = < span class = "n" > nil< / span > , connect_timeout : Int32? = < span class = "n" > nil< / span > , max_redirects : Int32? = < span class = "n" > nil< / span > , do_not_track : Bool? = < span class = "n" > nil< / span > , default_headers : Hash(String, String)? = < span class = "n" > nil< / span > , host_header : String? = < span class = "n" > nil< / span > , host_headers : Hash(String | Regex, String)? = < span class = "n" > nil< / span > , user_agent : String? = < span class = "n" > nil< / span > , referer : String? = < span class = "n" > nil< / span > , fetch_delay : Int32 | Time::Span? = < span class = "n" > nil< / span > , queue : Hash(String, URI)? = < span class = "n" > nil< / span > , history : Set(URI)? = < span class = "n" > nil< / span > , limit : Int32? = < span class = "n" > nil< / span > , max_depth : Int32? = < span class = "n" > nil< / span > , robots : Bool? = < span class = "n" > nil< / span > , filter_options = < span class = "n" > nil< / span > )< / a >
< div class = "summary" > < p > Creates a new < code > < a href = "../Arachnid/Agent.html" > Agent< / a > < / code > object.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#new%28%2A%2Aoptions%2C%26block%3AAgent-%3E%29-class-method" class = "signature" > < strong > .new< / strong > (**options, & block : Agent -> )< / a >
< div class = "summary" > < p > Create a new scoped < code > < a href = "../Arachnid/Agent.html" > Agent< / a > < / code > in a block.< / p > < / div >
< / li >
< / ul >
< h2 > Class Method Summary< / h2 >
< ul class = "list-summary" >
< li class = "entry-summary" >
< a href = "#host%28url%2C%2A%2Aoptions%2C%26block%3AAgent-%3E%29-class-method" class = "signature" > < strong > .host< / strong > (url, **options, & block : Agent -> )< / a >
< div class = "summary" > < p > Creates a new < code > < a href = "../Arachnid/Agent.html" > Agent< / a > < / code > and spiders the given host.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#site%28url%2C%2A%2Aoptions%2C%26block%3AAgent-%3E%29-class-method" class = "signature" > < strong > .site< / strong > (url, **options, & block : Agent -> )< / a >
< div class = "summary" > < p > Creates a new < code > < a href = "../Arachnid/Agent.html" > Agent< / a > < / code > and spiders the web site located at the given URL.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#start_at%28url%2C%2A%2Aoptions%2C%26block%3AAgent-%3E%29-class-method" class = "signature" > < strong > .start_at< / strong > (url, **options, & block : Agent -> )< / a >
< div class = "summary" > < p > Creates a new < code > < a href = "../Arachnid/Agent.html" > Agent< / a > < / code > and begins spidering at the given URL.< / p > < / div >
< / li >
< / ul >
< h2 > Instance Method Summary< / h2 >
< ul class = "list-summary" >
< li class = "entry-summary" >
< a href = "#all_headers%28%26block%3AHTTP%3A%3AHeaders%29-instance-method" class = "signature" > < strong > #all_headers< / strong > (& block : HTTP::Headers)< / a >
< div class = "summary" > < p > Pass the headers from every response the agent receives to a given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#authorized%3AAuthStore-instance-method" class = "signature" > < strong > #authorized< / strong > : AuthStore< / a >
< div class = "summary" > < p > HTTP Authentication credentials.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#authorized%3D%28authorized%3AAuthStore%29-instance-method" class = "signature" > < strong > #authorized=< / strong > (authorized : AuthStore)< / a >
< div class = "summary" > < p > HTTP Authentication credentials.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#clear-instance-method" class = "signature" > < strong > #clear< / strong > < / a >
< div class = "summary" > < p > Clears the history of the < code > < a href = "../Arachnid/Agent.html" > Agent< / a > < / code > .< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#continue%21%28%26block%29-instance-method" class = "signature" > < strong > #continue!< / strong > (& block)< / a >
< div class = "summary" > < p > Continue spidering< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#cookies%3ACookieJar-instance-method" class = "signature" > < strong > #cookies< / strong > : CookieJar< / a >
< div class = "summary" > < p > Cached cookies.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#cookies%3D%28cookies%3ACookieJar%29-instance-method" class = "signature" > < strong > #cookies=< / strong > (cookies : CookieJar)< / a >
< div class = "summary" > < p > Cached cookies.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#default_headers%3AHash%28String%2CString%29-instance-method" class = "signature" > < strong > #default_headers< / strong > : Hash(String, String)< / a >
< div class = "summary" > < p > HTTP Headers to use for every request.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#default_headers%3D%28default_headers%3AHash%28String%2CString%29%29-instance-method" class = "signature" > < strong > #default_headers=< / strong > (default_headers : Hash(String, String))< / a >
< div class = "summary" > < p > HTTP Headers to use for every request.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#dequeue-instance-method" class = "signature" > < strong > #dequeue< / strong > < / a >
< div class = "summary" > < p > Dequeues a URL that will later be visited.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#enqueue%28url%2Clevel%3D0%2Cforce%3Dfalse%29-instance-method" class = "signature" > < strong > #enqueue< / strong > (url, level = < span class = "n" > 0< / span > , force = < span class = "n" > false< / span > )< / a >
< div class = "summary" > < p > Enqueues a given URL for visiting, only if it passes all of the agent's rules for visiting a given URL.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_atom%28%26block%3AResource-%3E%29-instance-method" class = "signature" > < strong > #every_atom< / strong > (& block : Resource -> )< / a >
< div class = "summary" > < p > Pass every Atom feed that the agent visits to a given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_atom_doc%28%26block%3AXML%3A%3ANode-%3E%29-instance-method" class = "signature" > < strong > #every_atom_doc< / strong > (& block : XML::Node -> )< / a >
< div class = "summary" > < p > Pass every Atom document that the agent parses to a given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_bad_request_page%28%26block%3AResource-%3E%29-instance-method" class = "signature" > < strong > #every_bad_request_page< / strong > (& block : Resource -> )< / a >
< div class = "summary" > < p > Pass every Bad Request resource that the agent visits to a given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_content_type%28content_type%3AString%7CRegex%2C%26block%3AResource-%3E%29-instance-method" class = "signature" > < strong > #every_content_type< / strong > (content_type : String | Regex, & block : Resource -> )< / a >
< div class = "summary" > < p > Passes every resource with a matching content type to the given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_css%28%26block%3AResource-%3E%29-instance-method" class = "signature" > < strong > #every_css< / strong > (& block : Resource -> )< / a >
< div class = "summary" > < p > Pass every CSS resource that the agent visits to a given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_doc%28%26block%3ADocument%3A%3AHTML%7CXML%3A%3ANode-%3E%29-instance-method" class = "signature" > < strong > #every_doc< / strong > (& block : Document::HTML | XML::Node -> )< / a >
< div class = "summary" > < p > Pass every HTML or XML document that the agent parses to a given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_failed_url%28%26block%3AURI-%3E%29-instance-method" class = "signature" > < strong > #every_failed_url< / strong > (& block : URI -> )< / a >
< div class = "summary" > < p > Pass each URL that could not be requested to the given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_forbidden_page%28%26block%3AResource-%3E%29-instance-method" class = "signature" > < strong > #every_forbidden_page< / strong > (& block : Resource -> )< / a >
< div class = "summary" > < p > Pass every Forbidden resource that the agent visits to a given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_html_doc%28%26block%3ADocument%3A%3AHTML%7CXML%3A%3ANode-%3E%29-instance-method" class = "signature" > < strong > #every_html_doc< / strong > (& block : Document::HTML | XML::Node -> )< / a >
< div class = "summary" > < p > Pass every HTML document that the agent parses to a given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_html_page%28%26block%3AResource-%3E%29-instance-method" class = "signature" > < strong > #every_html_page< / strong > (& block : Resource -> )< / a >
< div class = "summary" > < p > Pass every HTML resource that the agent visits to a given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_image%28%26block%3AResource-%3E%29-instance-method" class = "signature" > < strong > #every_image< / strong > (& block : Resource -> )< / a >
< div class = "summary" > < p > Passes every image resource to the given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_internal_server_error_page%28%26block%3AResource-%3E%29-instance-method" class = "signature" > < strong > #every_internal_server_error_page< / strong > (& block : Resource -> )< / a >
< div class = "summary" > < p > Pass every Internal Server Error resource that the agent visits to a given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_javascript%28%26block%3AResource-%3E%29-instance-method" class = "signature" > < strong > #every_javascript< / strong > (& block : Resource -> )< / a >
< div class = "summary" > < p > Pass every JavaScript resource that the agent visits to a given block< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_link%28%26block%3AURI%2CURI-%3E%29-instance-method" class = "signature" > < strong > #every_link< / strong > (& block : URI, URI -> )< / a >
< div class = "summary" > < p > Passes every origin and destination URI of each link to a given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_missing_page%28%26block%3AResource-%3E%29-instance-method" class = "signature" > < strong > #every_missing_page< / strong > (& block : Resource -> )< / a >
< div class = "summary" > < p > Pass every Missing resource that the agent visits to a given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_ms_word%28%26block%3AResource-%3E%29-instance-method" class = "signature" > < strong > #every_ms_word< / strong > (& block : Resource -> )< / a >
< div class = "summary" > < p > Pass every MS Word resource that the agent visits to a given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_ok_page%28%26block%3AResource-%3E%29-instance-method" class = "signature" > < strong > #every_ok_page< / strong > (& block : Resource -> )< / a >
< div class = "summary" > < p > Pass every OK resource that the agent visits to a given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_pdf%28%26block%3AResource-%3E%29-instance-method" class = "signature" > < strong > #every_pdf< / strong > (& block : Resource -> )< / a >
< div class = "summary" > < p > Pass every PDF resource that the agent visits to a given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_redirect_page%28%26block%3AResource-%3E%29-instance-method" class = "signature" > < strong > #every_redirect_page< / strong > (& block : Resource -> )< / a >
< div class = "summary" > < p > Pass every Redirect resource that the agent visits to a given block.< / p > < / div >
< /li>
< li class = "entry-summary" >
< a href = "#every_resource%28%26block%3AResource-%3E%29-instance-method" class = "signature" > < strong > #every_resource< / strong > (& block : Resource -> )< / a >
< div class = "summary" > < p > Pass every resource that the agent visits to a given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_rss%28%26block%3AResource-%3E%29-instance-method" class = "signature" > < strong > #every_rss< / strong > (& block : Resource -> )< / a >
< div class = "summary" > < p > Pass every RSS feed that the agent visits to a given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_rss_doc%28%26block%3AXML%3A%3ANode-%3E%29-instance-method" class = "signature" > < strong > #every_rss_doc< / strong > (& block : XML::Node -> )< / a >
< div class = "summary" > < p > Pass every RSS document that the agent parses to a given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_timedout_page%28%26block%3AResource-%3E%29-instance-method" class = "signature" > < strong > #every_timedout_page< / strong > (& block : Resource -> )< / a >
< div class = "summary" > < p > Pass every Timeout resource that the agent visits to a given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_txt_page%28%26block%3AResource-%3E%29-instance-method" class = "signature" > < strong > #every_txt_page< / strong > (& block : Resource -> )< / a >
< div class = "summary" > < p > Pass every Plain Text resource that the agent visits to a given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_unauthorized_page%28%26block%3AResource-%3E%29-instance-method" class = "signature" > < strong > #every_unauthorized_page< / strong > (& block : Resource -> )< / a >
< div class = "summary" > < p > Pass every Unauthorized resource that the agent visits to a given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_url%28%26block%3AURI-%3E%29-instance-method" class = "signature" > < strong > #every_url< / strong > (& block : URI -> )< / a >
< div class = "summary" > < p > Pass each URL from each resource visited to the given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_url_like%28pattern%2C%26block%3AURI-%3E%29-instance-method" class = "signature" > < strong > #every_url_like< / strong > (pattern, & block : URI -> )< / a >
< div class = "summary" > < p > Pass every URL that the agent visits, and matches a given pattern, to a given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_xml_doc%28%26block%3AXML%3A%3ANode-%3E%29-instance-method" class = "signature" > < strong > #every_xml_doc< / strong > (& block : XML::Node -> )< / a >
< div class = "summary" > < p > Pass every XML document that the agent parses to a given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_xml_page%28%26block%3AResource-%3E%29-instance-method" class = "signature" > < strong > #every_xml_page< / strong > (& block : Resource -> )< / a >
< div class = "summary" > < p > Pass every XML resource that the agent visits to a given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_xsl_doc%28%26block%3AXML%3A%3ANode-%3E%29-instance-method" class = "signature" > < strong > #every_xsl_doc< / strong > (& block : XML::Node -> )< / a >
< div class = "summary" > < p > Pass every XML Stylesheet (XSL) that the agent parses to a given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_xsl_page%28%26block%3AResource-%3E%29-instance-method" class = "signature" > < strong > #every_xsl_page< / strong > (& block : Resource -> )< / a >
< div class = "summary" > < p > Pass every XML Stylesheet (XSL) resource that the agent visits to a given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#every_zip%28%26block%3AResource-%3E%29-instance-method" class = "signature" > < strong > #every_zip< / strong > (& block : Resource -> )< / a >
< div class = "summary" > < p > Pass every ZIP resource that the agent visits to a given block.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#failed%28url%29-instance-method" class = "signature" > < strong > #failed< / strong > (url)< / a >
< div class = "summary" > < p > Adds a given URL to the failures list.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#failed%3F%28url%29-instance-method" class = "signature" > < strong > #failed?< / strong > (url)< / a >
< div class = "summary" > < p > Determines whether a given URL could not be visited.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#failures%3ASet%28URI%29-instance-method" class = "signature" > < strong > #failures< / strong > : Set(URI)< / a >
< div class = "summary" > < p > List of unreachable URIs.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#failures%3D%28new_failures%29-instance-method" class = "signature" > < strong > #failures=< / strong > (new_failures)< / a >
< div class = "summary" > < p > Sets the list of failed URLs.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#fetch_delay%3ATime%3A%3ASpan%7CInt32-instance-method" class = "signature" > < strong > #fetch_delay< / strong > : Time::Span | Int32< / a >
< div class = "summary" > < p > Delay in between fetching resources.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#fetch_delay%3D%28fetch_delay%3ATime%3A%3ASpan%7CInt32%29-instance-method" class = "signature" > < strong > #fetch_delay=< / strong > (fetch_delay : Time::Span | Int32)< / a >
< div class = "summary" > < p > Delay in between fetching resources.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#get_resource%28url%2C%26block%29-instance-method" class = "signature" > < strong > #get_resource< / strong > (url, & block)< / a >
< div class = "summary" > < p > Gets and creates a new < code > < a href = "../Arachnid/Resource.html" > Resource< / a > < / code > object from a given URL, yielding the newly created resource.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#get_resource%28url%29-instance-method" class = "signature" > < strong > #get_resource< / strong > (url)< / a >
< div class = "summary" > < p > Gets and creates a new < code > < a href = "../Arachnid/Resource.html" > Resource< / a > < / code > object from a given URL.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#history%3ASet%28URI%29-instance-method" class = "signature" > < strong > #history< / strong > : Set(URI)< / a >
< div class = "summary" > < p > History containing visited URLs.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#history%3D%28new_history%29-instance-method" class = "signature" > < strong > #history=< / strong > (new_history)< / a >
< div class = "summary" > < p > Sets the history of URLs that were previously visited.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#host%3AString%3F-instance-method" class = "signature" > < strong > #host< / strong > : String?< / a >
< div class = "summary" > < p > Set to limit to a single host.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#host%3D%28host%3AString%3F%29-instance-method" class = "signature" > < strong > #host=< / strong > (host : String?)< / a >
< div class = "summary" > < p > Set to limit to a single host.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#host_header%3AString%3F-instance-method" class = "signature" > < strong > #host_header< / strong > : String?< / a >
< div class = "summary" > < p > HTTP Host Header to use.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#host_header%3D%28host_header%3AString%3F%29-instance-method" class = "signature" > < strong > #host_header=< / strong > (host_header : String?)< / a >
< div class = "summary" > < p > HTTP Host Header to use.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#host_headers%3AHash%28String%7CRegex%2CString%29-instance-method" class = "signature" > < strong > #host_headers< / strong > : Hash(String | Regex, String)< / a >
< div class = "summary" > < p > HTTP Host Headers to use for specific hosts.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#host_headers%3D%28host_headers%3AHash%28String%7CRegex%2CString%29%29-instance-method" class = "signature" > < strong > #host_headers=< / strong > (host_headers : Hash(String | Regex, String))< / a >
< div class = "summary" > < p > HTTP Host Headers to use for specific hosts.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#ignore_exts-instance-method" class = "signature" > < strong > #ignore_exts< / strong > < / a >
< div class = "summary" > < p > Specifies the patterns that match URI path extensions to not visit.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#ignore_exts_like%28%26block%3AString-%3EBool%29-instance-method" class = "signature" > < strong > #ignore_exts_like< / strong > (& block : String -> Bool)< / a >
< div class = "summary" > < p > Adds a given pattern to the < code > < a href = "../Arachnid/Agent.html#ignore_exts-instance-method" > #ignore_exts< / a > < / code > .< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#ignore_exts_like%28pattern%29-instance-method" class = "signature" > < strong > #ignore_exts_like< / strong > (pattern)< / a >
< / li >
< li class = "entry-summary" >
< a href = "#ignore_hosts-instance-method" class = "signature" > < strong > #ignore_hosts< / strong > < / a >
< div class = "summary" > < p > Specifies the patterns that match host-names to not visit.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#ignore_hosts_like%28pattern%29-instance-method" class = "signature" > < strong > #ignore_hosts_like< / strong > (pattern)< / a >
< div class = "summary" > < p > Adds a given pattern to the < code > < a href = "../Arachnid/Agent.html#ignore_hosts-instance-method" > #ignore_hosts< / a > < / code > .< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#ignore_hosts_like%28%26block%29-instance-method" class = "signature" > < strong > #ignore_hosts_like< / strong > (& block)< / a >
< / li >
< li class = "entry-summary" >
< a href = "#ignore_links-instance-method" class = "signature" > < strong > #ignore_links< / strong > < / a >
< div class = "summary" > < p > Specifies the patterns that match links to not visit.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#ignore_links_like%28%26block%3AString-%3EBool%29-instance-method" class = "signature" > < strong > #ignore_links_like< / strong > (& block : String -> Bool)< / a >
< / li >
< li class = "entry-summary" >
< a href = "#ignore_links_like%28pattern%29-instance-method" class = "signature" > < strong > #ignore_links_like< / strong > (pattern)< / a >
< div class = "summary" > < p > Adds a given pattern to the < code > < a href = "../Arachnid/Agent.html#ignore_links-instance-method" > #ignore_links< / a > < / code > .< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#ignore_ports-instance-method" class = "signature" > < strong > #ignore_ports< / strong > < / a >
< div class = "summary" > < p > Specifies the patterns that match ports to not visit.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#ignore_ports_like%28pattern%29-instance-method" class = "signature" > < strong > #ignore_ports_like< / strong > (pattern)< / a >
< div class = "summary" > < p > Adds a given pattern to the < code > < a href = "../Arachnid/Agent.html#ignore_ports-instance-method" > #ignore_ports< / a > < / code > .< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#ignore_ports_like%28%26block%3AInt32-%3EBool%29-instance-method" class = "signature" > < strong > #ignore_ports_like< / strong > (& block : Int32 -> Bool)< / a >
< / li >
< li class = "entry-summary" >
< a href = "#ignore_urls-instance-method" class = "signature" > < strong > #ignore_urls< / strong > < / a >
< div class = "summary" > < p > Specifies the patterns that match URLs to not visit.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#ignore_urls_like%28%26block%3AURI-%3EBool%29-instance-method" class = "signature" > < strong > #ignore_urls_like< / strong > (& block : URI -> Bool)< / a >
< div class = "summary" > < p > Adds a given pattern to the < code > < a href = "../Arachnid/Agent.html#ignore_urls-instance-method" > #ignore_urls< / a > < / code > .< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#ignore_urls_like%28pattern%29-instance-method" class = "signature" > < strong > #ignore_urls_like< / strong > (pattern)< / a >
< / li >
< li class = "entry-summary" >
< a href = "#initialize_robots-instance-method" class = "signature" > < strong > #initialize_robots< / strong > < / a >
< div class = "summary" > < p > Initializes the robots filter.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#levels%3AHash%28URI%2CInt32%29-instance-method" class = "signature" > < strong > #levels< / strong > : Hash(URI, Int32)< / a >
< div class = "summary" > < p > The visited URLs and their depth within a site.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#levels%3D%28levels%3AHash%28URI%2CInt32%29%29-instance-method" class = "signature" > < strong > #levels=< / strong > (levels : Hash(URI, Int32))< / a >
< div class = "summary" > < p > The visited URLs and their depth within a site.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#limit%3AInt32%3F-instance-method" class = "signature" > < strong > #limit< / strong > : Int32?< / a >
< div class = "summary" > < p > Maximum number of resources to visit.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#limit%3D%28limit%3AInt32%3F%29-instance-method" class = "signature" > < strong > #limit=< / strong > (limit : Int32?)< / a >
< div class = "summary" > < p > Maximum number of resources to visit.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#limit_reached%3F-instance-method" class = "signature" > < strong > #limit_reached?< / strong > < / a >
< div class = "summary" > < p > Determines if the maximum limit has been reached.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#max_depth%3AInt32%3F-instance-method" class = "signature" > < strong > #max_depth< / strong > : Int32?< / a >
< div class = "summary" > < p > Maximum depth.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#max_depth%3D%28max_depth%3AInt32%3F%29-instance-method" class = "signature" > < strong > #max_depth=< / strong > (max_depth : Int32?)< / a >
< div class = "summary" > < p > Maximum depth.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#pause%21-instance-method" class = "signature" > < strong > #pause!< / strong > < / a >
< div class = "summary" > < p > Pauses the agent, causing spidering to temporarily stop.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#pause%3D%28state%29-instance-method" class = "signature" > < strong > #pause=< / strong > (state)< / a >
< div class = "summary" > < p > Sets the pause state of the agent.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#paused%3F-instance-method" class = "signature" > < strong > #paused?< / strong > < / a >
< div class = "summary" > < p > Determines whether the agent is paused.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#post_resource%28url%2Cpost_data%3D%26quot%3B%26quot%3B%29-instance-method" class = "signature" > < strong > #post_resource< / strong > (url, post_data = < span class = "s" > " " < / span > )< / a >
< div class = "summary" > < p > Posts supplied form data and creates a new Resource from a given URL.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#post_resource%28url%2Cpost_data%3D%26quot%3B%26quot%3B%2C%26block%29-instance-method" class = "signature" > < strong > #post_resource< / strong > (url, post_data = < span class = "s" > " " < / span > , & block)< / a >
< div class = "summary" > < p > Posts supplied form data and creates a new Resource from a given URL, yielding the newly created resource.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#prepare_request%28url%2C%26block%29-instance-method" class = "signature" > < strong > #prepare_request< / strong > (url, & block)< / a >
< div class = "summary" > < p > Normalizes the request path and grabs a session to handle resource get and post requests.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#queue%3AHash%28String%2CURI%29-instance-method" class = "signature" > < strong > #queue< / strong > : Hash(String, URI)< / a >
< div class = "summary" > < p > Queue of URLs to visit.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#queue%3D%28new_queue%29-instance-method" class = "signature" > < strong > #queue=< / strong > (new_queue)< / a >
< div class = "summary" > < p > Sets the queue of URLs to visit.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#queued%3F%28key%29-instance-method" class = "signature" > < strong > #queued?< / strong > (key)< / a >
< div class = "summary" > < p > Determines whether the given URL has been queued for visiting.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#referer%3AString%3F-instance-method" class = "signature" > < strong > #referer< / strong > : String?< / a >
< div class = "summary" > < p > Referer to use.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#referer%3D%28referer%3AString%3F%29-instance-method" class = "signature" > < strong > #referer=< / strong > (referer : String?)< / a >
< div class = "summary" > < p > Referer to use.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#run-instance-method" class = "signature" > < strong > #run< / strong > < / a >
< div class = "summary" > < p > Start spidering until the queue becomes empty or the agent is paused.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#running%3F%3ABool-instance-method" class = "signature" > < strong > #running?< / strong > : Bool< / a >
< / li >
< li class = "entry-summary" >
< a href = "#sanitize_url%28url%29-instance-method" class = "signature" > < strong > #sanitize_url< / strong > (url)< / a >
< div class = "summary" > < p > Sanitizes a URL based on filtering options< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#schemes%3AArray%28String%29-instance-method" class = "signature" > < strong > #schemes< / strong > : Array(String)< / a >
< div class = "summary" > < p > List of acceptable URL schemes to follow< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#schemes%3D%28new_schemes%29-instance-method" class = "signature" > < strong > #schemes=< / strong > (new_schemes)< / a >
< div class = "summary" > < p > Sets the list of acceptable URL schemes to visit.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#sessions%3ASessionCache-instance-method" class = "signature" > < strong > #sessions< / strong > : SessionCache< / a >
< div class = "summary" > < p > The session cache.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#sessions%3D%28sessions%3ASessionCache%29-instance-method" class = "signature" > < strong > #sessions=< / strong > (sessions : SessionCache)< / a >
< div class = "summary" > < p > The session cache.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#skip_link%21-instance-method" class = "signature" > < strong > #skip_link!< / strong > < / a >
< div class = "summary" > < p > Causes the agent to skip the link being enqueued.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#skip_resource%21-instance-method" class = "signature" > < strong > #skip_resource!< / strong > < / a >
< div class = "summary" > < p > Causes the agent to skip the resource being visited.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#start_at%28url%2Cforce%3Dfalse%29-instance-method" class = "signature" > < strong > #start_at< / strong > (url, force = < span class = "n" > false< / span > )< / a >
< div class = "summary" > < p > Start spidering at a given URL.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#strip_fragments%3D%28strip_fragments%3ABool%29-instance-method" class = "signature" > < strong > #strip_fragments=< / strong > (strip_fragments : Bool)< / a >
< div class = "summary" > < p > Specifies whether the Agent will strip URI fragments< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#strip_fragments%3F%3ABool-instance-method" class = "signature" > < strong > #strip_fragments?< / strong > : Bool< / a >
< div class = "summary" > < p > Specifies whether the Agent will strip URI fragments< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#strip_query%3D%28strip_query%3ABool%29-instance-method" class = "signature" > < strong > #strip_query=< / strong > (strip_query : Bool)< / a >
< div class = "summary" > < p > Specifies whether the Agent will strip URI queries< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#strip_query%3F%3ABool-instance-method" class = "signature" > < strong > #strip_query?< / strong > : Bool< / a >
< div class = "summary" > < p > Specifies whether the Agent will strip URI queries< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#to_h-instance-method" class = "signature" > < strong > #to_h< / strong > < / a >
< div class = "summary" > < p > Converts the agent into a hash.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#urls_like%28pattern%2C%26block%3AURI-%3E%29-instance-method" class = "signature" > < strong > #urls_like< / strong > (pattern, & block : URI -> )< / a >
< div class = "summary" > < p > Ssee < code > < a href = "../Arachnid/Agent.html#every_url_like%28pattern%2C%26block%3AURI-%3E%29-instance-method" > #every_url_like< / a > < / code > < / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#user_agent%3AString-instance-method" class = "signature" > < strong > #user_agent< / strong > : String< / a >
< div class = "summary" > < p > User agent to use.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#user_agent%3D%28user_agent%3AString%29-instance-method" class = "signature" > < strong > #user_agent=< / strong > (user_agent : String)< / a >
< div class = "summary" > < p > User agent to use.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#visit%3F%28url%29-instance-method" class = "signature" > < strong > #visit?< / strong > (url)< / a >
< div class = "summary" > < p > Determines if a given URL should be visited.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#visit_exts-instance-method" class = "signature" > < strong > #visit_exts< / strong > < / a >
< div class = "summary" > < p > Specifies the patterns that match the URI path extensions to visit.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#visit_exts_like%28pattern%29-instance-method" class = "signature" > < strong > #visit_exts_like< / strong > (pattern)< / a >
< / li >
< li class = "entry-summary" >
< a href = "#visit_exts_like%28%26block%3AString-%3EBool%29-instance-method" class = "signature" > < strong > #visit_exts_like< / strong > (& block : String -> Bool)< / a >
< div class = "summary" > < p > Adds a given pattern to the < code > < a href = "../Arachnid/Agent.html#visit_exts-instance-method" > #visit_exts< / a > < / code > .< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#visit_hosts-instance-method" class = "signature" > < strong > #visit_hosts< / strong > < / a >
< div class = "summary" > < p > Specifies the patterns that match host-names to visit.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#visit_hosts_like%28%26block%29-instance-method" class = "signature" > < strong > #visit_hosts_like< / strong > (& block)< / a >
< / li >
< li class = "entry-summary" >
< a href = "#visit_hosts_like%28pattern%29-instance-method" class = "signature" > < strong > #visit_hosts_like< / strong > (pattern)< / a >
< div class = "summary" > < p > Adds a given pattern to the < code > < a href = "../Arachnid/Agent.html#visit_hosts-instance-method" > #visit_hosts< / a > < / code > .< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#visit_links-instance-method" class = "signature" > < strong > #visit_links< / strong > < / a >
< div class = "summary" > < p > Specifies the patterns that match the links to visit.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#visit_links_like%28pattern%29-instance-method" class = "signature" > < strong > #visit_links_like< / strong > (pattern)< / a >
< div class = "summary" > < p > Adds a given pattern to the < code > < a href = "../Arachnid/Agent.html#visit_links-instance-method" > #visit_links< / a > < / code > < / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#visit_links_like%28%26block%3AString-%3EBool%29-instance-method" class = "signature" > < strong > #visit_links_like< / strong > (& block : String -> Bool)< / a >
< / li >
< li class = "entry-summary" >
< a href = "#visit_ports-instance-method" class = "signature" > < strong > #visit_ports< / strong > < / a >
< div class = "summary" > < p > Specifies the patterns that match the ports to visit.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#visit_ports_like%28pattern%29-instance-method" class = "signature" > < strong > #visit_ports_like< / strong > (pattern)< / a >
< div class = "summary" > < p > Adds a given pattern to the < code > < a href = "../Arachnid/Agent.html#visit_ports-instance-method" > #visit_ports< / a > < / code > .< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#visit_ports_like%28%26block%3AInt32-%3EBool%29-instance-method" class = "signature" > < strong > #visit_ports_like< / strong > (& block : Int32 -> Bool)< / a >
< / li >
< li class = "entry-summary" >
< a href = "#visit_resource%28url%29-instance-method" class = "signature" > < strong > #visit_resource< / strong > (url)< / a >
< div class = "summary" > < p > Visits a given URL and enqueues the links recovered from the resource to be visited later.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#visit_urls-instance-method" class = "signature" > < strong > #visit_urls< / strong > < / a >
< div class = "summary" > < p > Specifies the patterns that match the URLs to visit.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#visit_urls_like%28%26block%3AURI-%3EBool%29-instance-method" class = "signature" > < strong > #visit_urls_like< / strong > (& block : URI -> Bool)< / a >
< div class = "summary" > < p > Adds a given pattern to the < code > < a href = "../Arachnid/Agent.html#visit_urls-instance-method" > #visit_urls< / a > < / code > < / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#visit_urls_like%28pattern%29-instance-method" class = "signature" > < strong > #visit_urls_like< / strong > (pattern)< / a >
< / li >
< li class = "entry-summary" >
< a href = "#visited%3F%28url%29-instance-method" class = "signature" > < strong > #visited?< / strong > (url)< / a >
< div class = "summary" > < p > Determines whether a URL was visited or not.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#visited_hosts-instance-method" class = "signature" > < strong > #visited_hosts< / strong > < / a >
< div class = "summary" > < p > Specifies the hosts which have been visited.< / p > < / div >
< / li >
< li class = "entry-summary" >
< a href = "#visited_links-instance-method" class = "signature" > < strong > #visited_links< / strong > < / a >
< div class = "summary" > < p > Specifies the links which have been visited.< / p > < / div >
< / li >
< / ul >
< div class = "methods-inherited" >
< / div >
< h2 > Constructor Detail< / h2 >
< div class = "entry-detail" id = "new(host:String?=nil,read_timeout:Int32?=nil,connect_timeout:Int32?=nil,max_redirects:Int32?=nil,do_not_track:Bool?=nil,default_headers:Hash(String,String)?=nil,host_header:String?=nil,host_headers:Hash(String|Regex,String)?=nil,user_agent:String?=nil,referer:String?=nil,fetch_delay:Int32|Time::Span?=nil,queue:Hash(String,URI)?=nil,history:Set(URI)?=nil,limit:Int32?=nil,max_depth:Int32?=nil,robots:Bool?=nil,filter_options=nil)-class-method" >
< div class = "signature" >
def self.< strong > new< / strong > (host : String? = < span class = "n" > nil< / span > , read_timeout : Int32? = < span class = "n" > nil< / span > , connect_timeout : Int32? = < span class = "n" > nil< / span > , max_redirects : Int32? = < span class = "n" > nil< / span > , do_not_track : Bool? = < span class = "n" > nil< / span > , default_headers : Hash(String, String)? = < span class = "n" > nil< / span > , host_header : String? = < span class = "n" > nil< / span > , host_headers : Hash(String | Regex, String)? = < span class = "n" > nil< / span > , user_agent : String? = < span class = "n" > nil< / span > , referer : String? = < span class = "n" > nil< / span > , fetch_delay : Int32 | Time::Span? = < span class = "n" > nil< / span > , queue : Hash(String, < a href = "../URI.html" > URI< / a > )? = < span class = "n" > nil< / span > , history : Set(< a href = "../URI.html" > URI< / a > )? = < span class = "n" > nil< / span > , limit : Int32? = < span class = "n" > nil< / span > , max_depth : Int32? = < span class = "n" > nil< / span > , robots : Bool? = < span class = "n" > nil< / span > , filter_options = < span class = "n" > nil< / span > )
< a class = "method-permalink" href = "#new%28host%3AString%3F%3Dnil%2Cread_timeout%3AInt32%3F%3Dnil%2Cconnect_timeout%3AInt32%3F%3Dnil%2Cmax_redirects%3AInt32%3F%3Dnil%2Cdo_not_track%3ABool%3F%3Dnil%2Cdefault_headers%3AHash%28String%2CString%29%3F%3Dnil%2Chost_header%3AString%3F%3Dnil%2Chost_headers%3AHash%28String%7CRegex%2CString%29%3F%3Dnil%2Cuser_agent%3AString%3F%3Dnil%2Creferer%3AString%3F%3Dnil%2Cfetch_delay%3AInt32%7CTime%3A%3ASpan%3F%3Dnil%2Cqueue%3AHash%28String%2CURI%29%3F%3Dnil%2Chistory%3ASet%28URI%29%3F%3Dnil%2Climit%3AInt32%3F%3Dnil%2Cmax_depth%3AInt32%3F%3Dnil%2Crobots%3ABool%3F%3Dnil%2Cfilter_options%3Dnil%29-class-method" > #< / a >
< / div >
< div class = "doc" > < p > Creates a new < code > < a href = "../Arachnid/Agent.html" > Agent< / a > < / code > object.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L65" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "new(**options,&block:Agent->)-class-method" >
< div class = "signature" >
def self.< strong > new< / strong > (**options, & block : < a href = "../Arachnid/Agent.html" > Agent< / a > -> )
< a class = "method-permalink" href = "#new%28%2A%2Aoptions%2C%26block%3AAgent-%3E%29-class-method" > #< / a >
< / div >
< div class = "doc" > < p > Create a new scoped < code > < a href = "../Arachnid/Agent.html" > Agent< / a > < / code > in a block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L123" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< h2 > Class Method Detail< / h2 >
< div class = "entry-detail" id = "host(url,**options,&block:Agent->)-class-method" >
< div class = "signature" >
def self.< strong > host< / strong > (url, **options, & block : < a href = "../Arachnid/Agent.html" > Agent< / a > -> )
< a class = "method-permalink" href = "#host%28url%2C%2A%2Aoptions%2C%26block%3AAgent-%3E%29-class-method" > #< / a >
< / div >
< div class = "doc" > < p > Creates a new < code > < a href = "../Arachnid/Agent.html" > Agent< / a > < / code > and spiders the given host.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L148" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "site(url,**options,&block:Agent->)-class-method" >
< div class = "signature" >
def self.< strong > site< / strong > (url, **options, & block : < a href = "../Arachnid/Agent.html" > Agent< / a > -> )
< a class = "method-permalink" href = "#site%28url%2C%2A%2Aoptions%2C%26block%3AAgent-%3E%29-class-method" > #< / a >
< / div >
< div class = "doc" > < p > Creates a new < code > < a href = "../Arachnid/Agent.html" > Agent< / a > < / code > and spiders the web site located
at the given URL.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L137" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "start_at(url,**options,&block:Agent->)-class-method" >
< div class = "signature" >
def self.< strong > start_at< / strong > (url, **options, & block : < a href = "../Arachnid/Agent.html" > Agent< / a > -> )
< a class = "method-permalink" href = "#start_at%28url%2C%2A%2Aoptions%2C%26block%3AAgent-%3E%29-class-method" > #< / a >
< / div >
< div class = "doc" > < p > Creates a new < code > < a href = "../Arachnid/Agent.html" > Agent< / a > < / code > and begins spidering at the given URL.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L130" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< h2 > Instance Method Detail< / h2 >
< div class = "entry-detail" id = "all_headers(&block:HTTP::Headers)-instance-method" >
< div class = "signature" >
def < strong > all_headers< / strong > (& block : HTTP::Headers)
< a class = "method-permalink" href = "#all_headers%28%26block%3AHTTP%3A%3AHeaders%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass the headers from every response the agent receives to a given
block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L43" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "authorized:AuthStore-instance-method" >
< div class = "signature" >
def < strong > authorized< / strong > : < a href = "../Arachnid/AuthStore.html" > AuthStore< / a >
< a class = "method-permalink" href = "#authorized%3AAuthStore-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > HTTP Authentication credentials.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L34" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "authorized=(authorized:AuthStore)-instance-method" >
< div class = "signature" >
def < strong > authorized=< / strong > (authorized : < a href = "../Arachnid/AuthStore.html" > AuthStore< / a > )
< a class = "method-permalink" href = "#authorized%3D%28authorized%3AAuthStore%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > HTTP Authentication credentials.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L38" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "clear-instance-method" >
< div class = "signature" >
def < strong > clear< / strong >
< a class = "method-permalink" href = "#clear-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Clears the history of the < code > < a href = "../Arachnid/Agent.html" > Agent< / a > < / code > .< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L159" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "continue!(&block)-instance-method" >
< div class = "signature" >
def < strong > continue!< / strong > (& block)
< a class = "method-permalink" href = "#continue%21%28%26block%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Continue spidering< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/actions.cr#L22" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "cookies:CookieJar-instance-method" >
< div class = "signature" >
def < strong > cookies< / strong > : < a href = "../Arachnid/CookieJar.html" > CookieJar< / a >
< a class = "method-permalink" href = "#cookies%3ACookieJar-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Cached cookies.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L55" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "cookies=(cookies:CookieJar)-instance-method" >
< div class = "signature" >
def < strong > cookies=< / strong > (cookies : < a href = "../Arachnid/CookieJar.html" > CookieJar< / a > )
< a class = "method-permalink" href = "#cookies%3D%28cookies%3ACookieJar%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Cached cookies.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L59" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "default_headers:Hash(String,String)-instance-method" >
< div class = "signature" >
def < strong > default_headers< / strong > : Hash(String, String)
< a class = "method-permalink" href = "#default_headers%3AHash%28String%2CString%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > HTTP Headers to use for every request.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L31" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "default_headers=(default_headers:Hash(String,String))-instance-method" >
< div class = "signature" >
def < strong > default_headers=< / strong > (default_headers : Hash(String, String))
< a class = "method-permalink" href = "#default_headers%3D%28default_headers%3AHash%28String%2CString%29%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > HTTP Headers to use for every request.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L35" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "dequeue-instance-method" >
< div class = "signature" >
def < strong > dequeue< / strong >
< a class = "method-permalink" href = "#dequeue-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Dequeues a URL that will later be visited.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L509" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "enqueue(url,level=0,force=false)-instance-method" >
< div class = "signature" >
def < strong > enqueue< / strong > (url, level = < span class = "n" > 0< / span > , force = < span class = "n" > false< / span > )
< a class = "method-permalink" href = "#enqueue%28url%2Clevel%3D0%2Cforce%3Dfalse%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Enqueues a given URL for visiting, only if it passes all
of the agent's rules for visiting a given URL.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L279" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_atom(&block:Resource->)-instance-method" >
< div class = "signature" >
def < strong > every_atom< / strong > (& block : < a href = "../Arachnid/Resource.html" > Resource< / a > -> )
< a class = "method-permalink" href = "#every_atom%28%26block%3AResource-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass every Atom feed that the agent visits to a given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L207" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_atom_doc(&block:XML::Node->)-instance-method" >
< div class = "signature" >
def < strong > every_atom_doc< / strong > (& block : XML::Node -> )
< a class = "method-permalink" href = "#every_atom_doc%28%26block%3AXML%3A%3ANode-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass every Atom document that the agent parses to a given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L179" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_bad_request_page(&block:Resource->)-instance-method" >
< div class = "signature" >
def < strong > every_bad_request_page< / strong > (& block : < a href = "../Arachnid/Resource.html" > Resource< / a > -> )
< a class = "method-permalink" href = "#every_bad_request_page%28%26block%3AResource-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass every Bad Request resource that the agent visits to a given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L77" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_content_type(content_type:String|Regex,&block:Resource->)-instance-method" >
< div class = "signature" >
def < strong > every_content_type< / strong > (content_type : String | Regex, & block : < a href = "../Arachnid/Resource.html" > Resource< / a > -> )
< a class = "method-permalink" href = "#every_content_type%28content_type%3AString%7CRegex%2C%26block%3AResource-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Passes every resource with a matching content type to the given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L242" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_css(&block:Resource->)-instance-method" >
< div class = "signature" >
def < strong > every_css< / strong > (& block : < a href = "../Arachnid/Resource.html" > Resource< / a > -> )
< a class = "method-permalink" href = "#every_css%28%26block%3AResource-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass every CSS resource that the agent visits to a given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L193" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_doc(&block:Document::HTML|XML::Node->)-instance-method" >
< div class = "signature" >
def < strong > every_doc< / strong > (& block : < a href = "../Arachnid/Document/HTML.html" > Document::HTML< / a > | XML::Node -> )
< a class = "method-permalink" href = "#every_doc%28%26block%3ADocument%3A%3AHTML%7CXML%3A%3ANode-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass every HTML or XML document that the agent parses to a given
block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L143" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_failed_url(&block:URI->)-instance-method" >
< div class = "signature" >
def < strong > every_failed_url< / strong > (& block : < a href = "../URI.html" > URI< / a > -> )
< a class = "method-permalink" href = "#every_failed_url%28%26block%3AURI-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass each URL that could not be requested to the given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L24" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_forbidden_page(&block:Resource->)-instance-method" >
< div class = "signature" >
def < strong > every_forbidden_page< / strong > (& block : < a href = "../Arachnid/Resource.html" > Resource< / a > -> )
< a class = "method-permalink" href = "#every_forbidden_page%28%26block%3AResource-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass every Forbidden resource that the agent visits to a given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L91" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_html_doc(&block:Document::HTML|XML::Node->)-instance-method" >
< div class = "signature" >
def < strong > every_html_doc< / strong > (& block : < a href = "../Arachnid/Document/HTML.html" > Document::HTML< / a > | XML::Node -> )
< a class = "method-permalink" href = "#every_html_doc%28%26block%3ADocument%3A%3AHTML%7CXML%3A%3ANode-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass every HTML document that the agent parses to a given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L150" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_html_page(&block:Resource->)-instance-method" >
< div class = "signature" >
def < strong > every_html_page< / strong > (& block : < a href = "../Arachnid/Resource.html" > Resource< / a > -> )
< a class = "method-permalink" href = "#every_html_page%28%26block%3AResource-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass every HTML resource that the agent visits to a given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L120" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_image(&block:Resource->)-instance-method" >
< div class = "signature" >
def < strong > every_image< / strong > (& block : < a href = "../Arachnid/Resource.html" > Resource< / a > -> )
< a class = "method-permalink" href = "#every_image%28%26block%3AResource-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Passes every image resource to the given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L235" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_internal_server_error_page(&block:Resource->)-instance-method" >
< div class = "signature" >
def < strong > every_internal_server_error_page< / strong > (& block : < a href = "../Arachnid/Resource.html" > Resource< / a > -> )
< a class = "method-permalink" href = "#every_internal_server_error_page%28%26block%3AResource-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass every Internal Server Error resource that the agent visits to a
given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L106" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_javascript(&block:Resource->)-instance-method" >
< div class = "signature" >
def < strong > every_javascript< / strong > (& block : < a href = "../Arachnid/Resource.html" > Resource< / a > -> )
< a class = "method-permalink" href = "#every_javascript%28%26block%3AResource-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass every JavaScript resource that the agent visits to a given block< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L186" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_link(&block:URI,URI->)-instance-method" >
< div class = "signature" >
def < strong > every_link< / strong > (& block : < a href = "../URI.html" > URI< / a > , < a href = "../URI.html" > URI< / a > -> )
< a class = "method-permalink" href = "#every_link%28%26block%3AURI%2CURI-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Passes every origin and destination URI of each link to a given
block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L250" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_missing_page(&block:Resource->)-instance-method" >
< div class = "signature" >
def < strong > every_missing_page< / strong > (& block : < a href = "../Arachnid/Resource.html" > Resource< / a > -> )
< a class = "method-permalink" href = "#every_missing_page%28%26block%3AResource-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass every Missing resource that the agent visits to a given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L98" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_ms_word(&block:Resource->)-instance-method" >
< div class = "signature" >
def < strong > every_ms_word< / strong > (& block : < a href = "../Arachnid/Resource.html" > Resource< / a > -> )
< a class = "method-permalink" href = "#every_ms_word%28%26block%3AResource-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass every MS Word resource that the agent visits to a given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L214" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_ok_page(&block:Resource->)-instance-method" >
< div class = "signature" >
def < strong > every_ok_page< / strong > (& block : < a href = "../Arachnid/Resource.html" > Resource< / a > -> )
< a class = "method-permalink" href = "#every_ok_page%28%26block%3AResource-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass every OK resource that the agent visits to a given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L56" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_pdf(&block:Resource->)-instance-method" >
< div class = "signature" >
def < strong > every_pdf< / strong > (& block : < a href = "../Arachnid/Resource.html" > Resource< / a > -> )
< a class = "method-permalink" href = "#every_pdf%28%26block%3AResource-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass every PDF resource that the agent visits to a given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L221" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_redirect_page(&block:Resource->)-instance-method" >
< div class = "signature" >
def < strong > every_redirect_page< / strong > (& block : < a href = "../Arachnid/Resource.html" > Resource< / a > -> )
< a class = "method-permalink" href = "#every_redirect_page%28%26block%3AResource-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass every Redirect resource that the agent visits to a given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L63" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_resource(&block:Resource->)-instance-method" >
< div class = "signature" >
def < strong > every_resource< / strong > (& block : < a href = "../Arachnid/Resource.html" > Resource< / a > -> )
< a class = "method-permalink" href = "#every_resource%28%26block%3AResource-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass every resource that the agent visits to a given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L50" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_rss(&block:Resource->)-instance-method" >
< div class = "signature" >
def < strong > every_rss< / strong > (& block : < a href = "../Arachnid/Resource.html" > Resource< / a > -> )
< a class = "method-permalink" href = "#every_rss%28%26block%3AResource-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass every RSS feed that the agent visits to a given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L200" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_rss_doc(&block:XML::Node->)-instance-method" >
< div class = "signature" >
def < strong > every_rss_doc< / strong > (& block : XML::Node -> )
< a class = "method-permalink" href = "#every_rss_doc%28%26block%3AXML%3A%3ANode-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass every RSS document that the agent parses to a given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L172" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_timedout_page(&block:Resource->)-instance-method" >
< div class = "signature" >
def < strong > every_timedout_page< / strong > (& block : < a href = "../Arachnid/Resource.html" > Resource< / a > -> )
< a class = "method-permalink" href = "#every_timedout_page%28%26block%3AResource-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass every Timeout resource that the agent visits to a given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L70" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_txt_page(&block:Resource->)-instance-method" >
< div class = "signature" >
def < strong > every_txt_page< / strong > (& block : < a href = "../Arachnid/Resource.html" > Resource< / a > -> )
< a class = "method-permalink" href = "#every_txt_page%28%26block%3AResource-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass every Plain Text resource that the agent visits to a given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L113" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_unauthorized_page(&block:Resource->)-instance-method" >
< div class = "signature" >
def < strong > every_unauthorized_page< / strong > (& block : < a href = "../Arachnid/Resource.html" > Resource< / a > -> )
< a class = "method-permalink" href = "#every_unauthorized_page%28%26block%3AResource-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass every Unauthorized resource that the agent visits to a given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L84" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_url(&block:URI->)-instance-method" >
< div class = "signature" >
def < strong > every_url< / strong > (& block : < a href = "../URI.html" > URI< / a > -> )
< a class = "method-permalink" href = "#every_url%28%26block%3AURI-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass each URL from each resource visited to the given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L18" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_url_like(pattern,&block:URI->)-instance-method" >
< div class = "signature" >
def < strong > every_url_like< / strong > (pattern, & block : < a href = "../URI.html" > URI< / a > -> )
< a class = "method-permalink" href = "#every_url_like%28pattern%2C%26block%3AURI-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass every URL that the agent visits, and matches a given pattern,
to a given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L31" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_xml_doc(&block:XML::Node->)-instance-method" >
< div class = "signature" >
def < strong > every_xml_doc< / strong > (& block : XML::Node -> )
< a class = "method-permalink" href = "#every_xml_doc%28%26block%3AXML%3A%3ANode-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass every XML document that the agent parses to a given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L157" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_xml_page(&block:Resource->)-instance-method" >
< div class = "signature" >
def < strong > every_xml_page< / strong > (& block : < a href = "../Arachnid/Resource.html" > Resource< / a > -> )
< a class = "method-permalink" href = "#every_xml_page%28%26block%3AResource-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass every XML resource that the agent visits to a given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L127" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_xsl_doc(&block:XML::Node->)-instance-method" >
< div class = "signature" >
def < strong > every_xsl_doc< / strong > (& block : XML::Node -> )
< a class = "method-permalink" href = "#every_xsl_doc%28%26block%3AXML%3A%3ANode-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass every XML Stylesheet (XSL) that the agent parses to a given
block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L165" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_xsl_page(&block:Resource->)-instance-method" >
< div class = "signature" >
def < strong > every_xsl_page< / strong > (& block : < a href = "../Arachnid/Resource.html" > Resource< / a > -> )
< a class = "method-permalink" href = "#every_xsl_page%28%26block%3AResource-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass every XML Stylesheet (XSL) resource that the agent visits to a
given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L135" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "every_zip(&block:Resource->)-instance-method" >
< div class = "signature" >
def < strong > every_zip< / strong > (& block : < a href = "../Arachnid/Resource.html" > Resource< / a > -> )
< a class = "method-permalink" href = "#every_zip%28%26block%3AResource-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pass every ZIP resource that the agent visits to a given block.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L228" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "failed(url)-instance-method" >
< div class = "signature" >
def < strong > failed< / strong > (url)
< a class = "method-permalink" href = "#failed%28url%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Adds a given URL to the failures list.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L534" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "failed?(url)-instance-method" >
< div class = "signature" >
def < strong > failed?< / strong > (url)
< a class = "method-permalink" href = "#failed%3F%28url%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Determines whether a given URL could not be visited.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L255" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "failures:Set(URI)-instance-method" >
< div class = "signature" >
def < strong > failures< / strong > : Set(< a href = "../URI.html" > URI< / a > )
< a class = "method-permalink" href = "#failures%3ASet%28URI%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > List of unreachable URIs.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L46" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "failures=(new_failures)-instance-method" >
< div class = "signature" >
def < strong > failures=< / strong > (new_failures)
< a class = "method-permalink" href = "#failures%3D%28new_failures%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Sets the list of failed URLs.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L244" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "fetch_delay:Time::Span|Int32-instance-method" >
< div class = "signature" >
def < strong > fetch_delay< / strong > : Time::Span | Int32
< a class = "method-permalink" href = "#fetch_delay%3ATime%3A%3ASpan%7CInt32-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Delay in between fetching resources.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L40" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "fetch_delay=(fetch_delay:Time::Span|Int32)-instance-method" >
< div class = "signature" >
def < strong > fetch_delay=< / strong > (fetch_delay : Time::Span | Int32)
< a class = "method-permalink" href = "#fetch_delay%3D%28fetch_delay%3ATime%3A%3ASpan%7CInt32%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Delay in between fetching resources.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L44" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "get_resource(url,&block)-instance-method" >
< div class = "signature" >
def < strong > get_resource< / strong > (url, & block)
< a class = "method-permalink" href = "#get_resource%28url%2C%26block%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Gets and creates a new < code > < a href = "../Arachnid/Resource.html" > Resource< / a > < / code > object from a given URL,
yielding the newly created resource.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L317" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "get_resource(url)-instance-method" >
< div class = "signature" >
def < strong > get_resource< / strong > (url)
< a class = "method-permalink" href = "#get_resource%28url%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Gets and creates a new < code > < a href = "../Arachnid/Resource.html" > Resource< / a > < / code > object from a given URL.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L332" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "history:Set(URI)-instance-method" >
< div class = "signature" >
def < strong > history< / strong > : Set(< a href = "../URI.html" > URI< / a > )
< a class = "method-permalink" href = "#history%3ASet%28URI%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > History containing visited URLs.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L43" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "history=(new_history)-instance-method" >
< div class = "signature" >
def < strong > history=< / strong > (new_history)
< a class = "method-permalink" href = "#history%3D%28new_history%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Sets the history of URLs that were previously visited.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L217" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "host:String?-instance-method" >
< div class = "signature" >
def < strong > host< / strong > : String?
< a class = "method-permalink" href = "#host%3AString%3F-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Set to limit to a single host.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L19" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "host=(host:String?)-instance-method" >
< div class = "signature" >
def < strong > host=< / strong > (host : String?)
< a class = "method-permalink" href = "#host%3D%28host%3AString%3F%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Set to limit to a single host.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L23" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "host_header:String?-instance-method" >
< div class = "signature" >
def < strong > host_header< / strong > : String?
< a class = "method-permalink" href = "#host_header%3AString%3F-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > HTTP Host Header to use.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L25" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "host_header=(host_header:String?)-instance-method" >
< div class = "signature" >
def < strong > host_header=< / strong > (host_header : String?)
< a class = "method-permalink" href = "#host_header%3D%28host_header%3AString%3F%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > HTTP Host Header to use.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L29" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "host_headers:Hash(String|Regex,String)-instance-method" >
< div class = "signature" >
def < strong > host_headers< / strong > : Hash(String | Regex, String)
< a class = "method-permalink" href = "#host_headers%3AHash%28String%7CRegex%2CString%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > HTTP Host Headers to use for specific hosts.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L28" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "host_headers=(host_headers:Hash(String|Regex,String))-instance-method" >
< div class = "signature" >
def < strong > host_headers=< / strong > (host_headers : Hash(String | Regex, String))
< a class = "method-permalink" href = "#host_headers%3D%28host_headers%3AHash%28String%7CRegex%2CString%29%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > HTTP Host Headers to use for specific hosts.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L32" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "ignore_exts-instance-method" >
< div class = "signature" >
def < strong > ignore_exts< / strong >
< a class = "method-permalink" href = "#ignore_exts-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Specifies the patterns that match URI path extensions to not visit.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L164" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "ignore_exts_like(&block:String->Bool)-instance-method" >
< div class = "signature" >
def < strong > ignore_exts_like< / strong > (& block : String -> Bool)
< a class = "method-permalink" href = "#ignore_exts_like%28%26block%3AString-%3EBool%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Adds a given pattern to the < code > < a href = "../Arachnid/Agent.html#ignore_exts-instance-method" > #ignore_exts< / a > < / code > .< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L169" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "ignore_exts_like(pattern)-instance-method" >
< div class = "signature" >
def < strong > ignore_exts_like< / strong > (pattern)
< a class = "method-permalink" href = "#ignore_exts_like%28pattern%29-instance-method" > #< / a >
< / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L174" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "ignore_hosts-instance-method" >
< div class = "signature" >
def < strong > ignore_hosts< / strong >
< a class = "method-permalink" href = "#ignore_hosts-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Specifies the patterns that match host-names to not visit.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L36" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "ignore_hosts_like(pattern)-instance-method" >
< div class = "signature" >
def < strong > ignore_hosts_like< / strong > (pattern)
< a class = "method-permalink" href = "#ignore_hosts_like%28pattern%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Adds a given pattern to the < code > < a href = "../Arachnid/Agent.html#ignore_hosts-instance-method" > #ignore_hosts< / a > < / code > .< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L41" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "ignore_hosts_like(&block)-instance-method" >
< div class = "signature" >
def < strong > ignore_hosts_like< / strong > (& block)
< a class = "method-permalink" href = "#ignore_hosts_like%28%26block%29-instance-method" > #< / a >
< / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L46" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "ignore_links-instance-method" >
< div class = "signature" >
def < strong > ignore_links< / strong >
< a class = "method-permalink" href = "#ignore_links-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Specifies the patterns that match links to not visit.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L100" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "ignore_links_like(&block:String->Bool)-instance-method" >
< div class = "signature" >
def < strong > ignore_links_like< / strong > (& block : String -> Bool)
< a class = "method-permalink" href = "#ignore_links_like%28%26block%3AString-%3EBool%29-instance-method" > #< / a >
< / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L110" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "ignore_links_like(pattern)-instance-method" >
< div class = "signature" >
def < strong > ignore_links_like< / strong > (pattern)
< a class = "method-permalink" href = "#ignore_links_like%28pattern%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Adds a given pattern to the < code > < a href = "../Arachnid/Agent.html#ignore_links-instance-method" > #ignore_links< / a > < / code > .< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L105" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "ignore_ports-instance-method" >
< div class = "signature" >
def < strong > ignore_ports< / strong >
< a class = "method-permalink" href = "#ignore_ports-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Specifies the patterns that match ports to not visit.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L68" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "ignore_ports_like(pattern)-instance-method" >
< div class = "signature" >
def < strong > ignore_ports_like< / strong > (pattern)
< a class = "method-permalink" href = "#ignore_ports_like%28pattern%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Adds a given pattern to the < code > < a href = "../Arachnid/Agent.html#ignore_ports-instance-method" > #ignore_ports< / a > < / code > .< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L73" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "ignore_ports_like(&block:Int32->Bool)-instance-method" >
< div class = "signature" >
def < strong > ignore_ports_like< / strong > (& block : Int32 -> Bool)
< a class = "method-permalink" href = "#ignore_ports_like%28%26block%3AInt32-%3EBool%29-instance-method" > #< / a >
< / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L78" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "ignore_urls-instance-method" >
< div class = "signature" >
def < strong > ignore_urls< / strong >
< a class = "method-permalink" href = "#ignore_urls-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Specifies the patterns that match URLs to not visit.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L132" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "ignore_urls_like(&block:URI->Bool)-instance-method" >
< div class = "signature" >
def < strong > ignore_urls_like< / strong > (& block : < a href = "../URI.html" > URI< / a > -> Bool)
< a class = "method-permalink" href = "#ignore_urls_like%28%26block%3AURI-%3EBool%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Adds a given pattern to the < code > < a href = "../Arachnid/Agent.html#ignore_urls-instance-method" > #ignore_urls< / a > < / code > .< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L137" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "ignore_urls_like(pattern)-instance-method" >
< div class = "signature" >
def < strong > ignore_urls_like< / strong > (pattern)
< a class = "method-permalink" href = "#ignore_urls_like%28pattern%29-instance-method" > #< / a >
< / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L142" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "initialize_robots-instance-method" >
< div class = "signature" >
def < strong > initialize_robots< / strong >
< a class = "method-permalink" href = "#initialize_robots-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Initializes the robots filter.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/robots.cr#L6" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "levels:Hash(URI,Int32)-instance-method" >
< div class = "signature" >
def < strong > levels< / strong > : Hash(< a href = "../URI.html" > URI< / a > , Int32)
< a class = "method-permalink" href = "#levels%3AHash%28URI%2CInt32%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > The visited URLs and their depth within a site.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L64" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "levels=(levels:Hash(URI,Int32))-instance-method" >
< div class = "signature" >
def < strong > levels=< / strong > (levels : Hash(< a href = "../URI.html" > URI< / a > , Int32))
< a class = "method-permalink" href = "#levels%3D%28levels%3AHash%28URI%2CInt32%29%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > The visited URLs and their depth within a site.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L68" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "limit:Int32?-instance-method" >
< div class = "signature" >
def < strong > limit< / strong > : Int32?
< a class = "method-permalink" href = "#limit%3AInt32%3F-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Maximum number of resources to visit.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L58" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "limit=(limit:Int32?)-instance-method" >
< div class = "signature" >
def < strong > limit=< / strong > (limit : Int32?)
< a class = "method-permalink" href = "#limit%3D%28limit%3AInt32%3F%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Maximum number of resources to visit.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L62" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "limit_reached?-instance-method" >
< div class = "signature" >
def < strong > limit_reached?< / strong >
< a class = "method-permalink" href = "#limit_reached%3F-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Determines if the maximum limit has been reached.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L514" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "max_depth:Int32?-instance-method" >
< div class = "signature" >
def < strong > max_depth< / strong > : Int32?
< a class = "method-permalink" href = "#max_depth%3AInt32%3F-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Maximum depth.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L61" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "max_depth=(max_depth:Int32?)-instance-method" >
< div class = "signature" >
def < strong > max_depth=< / strong > (max_depth : Int32?)
< a class = "method-permalink" href = "#max_depth%3D%28max_depth%3AInt32%3F%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Maximum depth.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L65" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "pause!-instance-method" >
< div class = "signature" >
def < strong > pause!< / strong >
< a class = "method-permalink" href = "#pause%21-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Pauses the agent, causing spidering to temporarily stop.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/actions.cr#L33" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "pause=(state)-instance-method" >
< div class = "signature" >
def < strong > pause=< / strong > (state)
< a class = "method-permalink" href = "#pause%3D%28state%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Sets the pause state of the agent.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/actions.cr#L28" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "paused?-instance-method" >
< div class = "signature" >
def < strong > paused?< / strong >
< a class = "method-permalink" href = "#paused%3F-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Determines whether the agent is paused.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/actions.cr#L39" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "post_resource(url,post_data=&quot;&quot;)-instance-method" >
< div class = "signature" >
def < strong > post_resource< / strong > (url, post_data = < span class = "s" > " " < / span > )
< a class = "method-permalink" href = "#post_resource%28url%2Cpost_data%3D%26quot%3B%26quot%3B%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Posts supplied form data and creates a new Resource from a given URL.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L362" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "post_resource(url,post_data=&quot;&quot;,&block)-instance-method" >
< div class = "signature" >
def < strong > post_resource< / strong > (url, post_data = < span class = "s" > " " < / span > , & block)
< a class = "method-permalink" href = "#post_resource%28url%2Cpost_data%3D%26quot%3B%26quot%3B%2C%26block%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Posts supplied form data and creates a new Resource from a given URL,
yielding the newly created resource.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L347" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "prepare_request(url,&block)-instance-method" >
< div class = "signature" >
def < strong > prepare_request< / strong > (url, & block)
< a class = "method-permalink" href = "#prepare_request%28url%2C%26block%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Normalizes the request path and grabs a session to handle
resource get and post requests.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L486" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "queue:Hash(String,URI)-instance-method" >
< div class = "signature" >
def < strong > queue< / strong > : Hash(String, < a href = "../URI.html" > URI< / a > )
< a class = "method-permalink" href = "#queue%3AHash%28String%2CURI%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Queue of URLs to visit.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L49" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "queue=(new_queue)-instance-method" >
< div class = "signature" >
def < strong > queue=< / strong > (new_queue)
< a class = "method-permalink" href = "#queue%3D%28new_queue%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Sets the queue of URLs to visit.
Sets the list of failed URLs.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L262" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "queued?(key)-instance-method" >
< div class = "signature" >
def < strong > queued?< / strong > (key)
< a class = "method-permalink" href = "#queued%3F%28key%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Determines whether the given URL has been queued for visiting.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L273" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "referer:String?-instance-method" >
< div class = "signature" >
def < strong > referer< / strong > : String?
< a class = "method-permalink" href = "#referer%3AString%3F-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Referer to use.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L37" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "referer=(referer:String?)-instance-method" >
< div class = "signature" >
def < strong > referer=< / strong > (referer : String?)
< a class = "method-permalink" href = "#referer%3D%28referer%3AString%3F%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Referer to use.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L41" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "run-instance-method" >
< div class = "signature" >
def < strong > run< / strong >
< a class = "method-permalink" href = "#run-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Start spidering until the queue becomes empty or the
agent is paused.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L199" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "running?:Bool-instance-method" >
< div class = "signature" >
def < strong > running?< / strong > : Bool
< a class = "method-permalink" href = "#running%3F%3ABool-instance-method" > #< / a >
< / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L16" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "sanitize_url(url)-instance-method" >
< div class = "signature" >
def < strong > sanitize_url< / strong > (url)
< a class = "method-permalink" href = "#sanitize_url%28url%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Sanitizes a URL based on filtering options< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/sanitizers.cr#L10" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "schemes:Array(String)-instance-method" >
< div class = "signature" >
def < strong > schemes< / strong > : Array(String)
< a class = "method-permalink" href = "#schemes%3AArray%28String%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > List of acceptable URL schemes to follow< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L8" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "schemes=(new_schemes)-instance-method" >
< div class = "signature" >
def < strong > schemes=< / strong > (new_schemes)
< a class = "method-permalink" href = "#schemes%3D%28new_schemes%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Sets the list of acceptable URL schemes to visit.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L15" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "sessions:SessionCache-instance-method" >
< div class = "signature" >
def < strong > sessions< / strong > : < a href = "../Arachnid/SessionCache.html" > SessionCache< / a >
< a class = "method-permalink" href = "#sessions%3ASessionCache-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > The session cache.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L52" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "sessions=(sessions:SessionCache)-instance-method" >
< div class = "signature" >
def < strong > sessions=< / strong > (sessions : < a href = "../Arachnid/SessionCache.html" > SessionCache< / a > )
< a class = "method-permalink" href = "#sessions%3D%28sessions%3ASessionCache%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > The session cache.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L56" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "skip_link!-instance-method" >
< div class = "signature" >
def < strong > skip_link!< / strong >
< a class = "method-permalink" href = "#skip_link%21-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Causes the agent to skip the link being enqueued.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/actions.cr#L44" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "skip_resource!-instance-method" >
< div class = "signature" >
def < strong > skip_resource!< / strong >
< a class = "method-permalink" href = "#skip_resource%21-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Causes the agent to skip the resource being visited.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/actions.cr#L49" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "start_at(url,force=false)-instance-method" >
< div class = "signature" >
def < strong > start_at< / strong > (url, force = < span class = "n" > false< / span > )
< a class = "method-permalink" href = "#start_at%28url%2Cforce%3Dfalse%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Start spidering at a given URL.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L173" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "strip_fragments=(strip_fragments:Bool)-instance-method" >
< div class = "signature" >
def < strong > strip_fragments=< / strong > (strip_fragments : Bool)
< a class = "method-permalink" href = "#strip_fragments%3D%28strip_fragments%3ABool%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Specifies whether the Agent will strip URI fragments< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/sanitizers.cr#L10" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "strip_fragments?:Bool-instance-method" >
< div class = "signature" >
def < strong > strip_fragments?< / strong > : Bool
< a class = "method-permalink" href = "#strip_fragments%3F%3ABool-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Specifies whether the Agent will strip URI fragments< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/sanitizers.cr#L6" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "strip_query=(strip_query:Bool)-instance-method" >
< div class = "signature" >
def < strong > strip_query=< / strong > (strip_query : Bool)
< a class = "method-permalink" href = "#strip_query%3D%28strip_query%3ABool%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Specifies whether the Agent will strip URI queries< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/sanitizers.cr#L13" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "strip_query?:Bool-instance-method" >
< div class = "signature" >
def < strong > strip_query?< / strong > : Bool
< a class = "method-permalink" href = "#strip_query%3F%3ABool-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Specifies whether the Agent will strip URI queries< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/sanitizers.cr#L9" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "to_h-instance-method" >
< div class = "signature" >
def < strong > to_h< / strong >
< a class = "method-permalink" href = "#to_h-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Converts the agent into a hash.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L451" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "urls_like(pattern,&block:URI->)-instance-method" >
< div class = "signature" >
def < strong > urls_like< / strong > (pattern, & block : < a href = "../URI.html" > URI< / a > -> )
< a class = "method-permalink" href = "#urls_like%28pattern%2C%26block%3AURI-%3E%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Ssee < code > < a href = "../Arachnid/Agent.html#every_url_like%28pattern%2C%26block%3AURI-%3E%29-instance-method" > #every_url_like< / a > < / code > < / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/events.cr#L37" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "user_agent:String-instance-method" >
< div class = "signature" >
def < strong > user_agent< / strong > : String
< a class = "method-permalink" href = "#user_agent%3AString-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > User agent to use.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L22" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "user_agent=(user_agent:String)-instance-method" >
< div class = "signature" >
def < strong > user_agent=< / strong > (user_agent : String)
< a class = "method-permalink" href = "#user_agent%3D%28user_agent%3AString%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > User agent to use.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L26" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "visit?(url)-instance-method" >
< div class = "signature" >
def < strong > visit?< / strong > (url)
< a class = "method-permalink" href = "#visit%3F%28url%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Determines if a given URL should be visited.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L522" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "visit_exts-instance-method" >
< div class = "signature" >
def < strong > visit_exts< / strong >
< a class = "method-permalink" href = "#visit_exts-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Specifies the patterns that match the URI path extensions to visit.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L148" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "visit_exts_like(pattern)-instance-method" >
< div class = "signature" >
def < strong > visit_exts_like< / strong > (pattern)
< a class = "method-permalink" href = "#visit_exts_like%28pattern%29-instance-method" > #< / a >
< / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L158" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "visit_exts_like(&block:String->Bool)-instance-method" >
< div class = "signature" >
def < strong > visit_exts_like< / strong > (& block : String -> Bool)
< a class = "method-permalink" href = "#visit_exts_like%28%26block%3AString-%3EBool%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Adds a given pattern to the < code > < a href = "../Arachnid/Agent.html#visit_exts-instance-method" > #visit_exts< / a > < / code > .< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L153" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "visit_hosts-instance-method" >
< div class = "signature" >
def < strong > visit_hosts< / strong >
< a class = "method-permalink" href = "#visit_hosts-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Specifies the patterns that match host-names to visit.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L20" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "visit_hosts_like(&block)-instance-method" >
< div class = "signature" >
def < strong > visit_hosts_like< / strong > (& block)
< a class = "method-permalink" href = "#visit_hosts_like%28%26block%29-instance-method" > #< / a >
< / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L30" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "visit_hosts_like(pattern)-instance-method" >
< div class = "signature" >
def < strong > visit_hosts_like< / strong > (pattern)
< a class = "method-permalink" href = "#visit_hosts_like%28pattern%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Adds a given pattern to the < code > < a href = "../Arachnid/Agent.html#visit_hosts-instance-method" > #visit_hosts< / a > < / code > .< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L25" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "visit_links-instance-method" >
< div class = "signature" >
def < strong > visit_links< / strong >
< a class = "method-permalink" href = "#visit_links-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Specifies the patterns that match the links to visit.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L84" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "visit_links_like(pattern)-instance-method" >
< div class = "signature" >
def < strong > visit_links_like< / strong > (pattern)
< a class = "method-permalink" href = "#visit_links_like%28pattern%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Adds a given pattern to the < code > < a href = "../Arachnid/Agent.html#visit_links-instance-method" > #visit_links< / a > < / code > < / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L89" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "visit_links_like(&block:String->Bool)-instance-method" >
< div class = "signature" >
def < strong > visit_links_like< / strong > (& block : String -> Bool)
< a class = "method-permalink" href = "#visit_links_like%28%26block%3AString-%3EBool%29-instance-method" > #< / a >
< / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L94" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "visit_ports-instance-method" >
< div class = "signature" >
def < strong > visit_ports< / strong >
< a class = "method-permalink" href = "#visit_ports-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Specifies the patterns that match the ports to visit.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L52" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "visit_ports_like(pattern)-instance-method" >
< div class = "signature" >
def < strong > visit_ports_like< / strong > (pattern)
< a class = "method-permalink" href = "#visit_ports_like%28pattern%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Adds a given pattern to the < code > < a href = "../Arachnid/Agent.html#visit_ports-instance-method" > #visit_ports< / a > < / code > .< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L57" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "visit_ports_like(&block:Int32->Bool)-instance-method" >
< div class = "signature" >
def < strong > visit_ports_like< / strong > (& block : Int32 -> Bool)
< a class = "method-permalink" href = "#visit_ports_like%28%26block%3AInt32-%3EBool%29-instance-method" > #< / a >
< / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L62" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "visit_resource(url)-instance-method" >
< div class = "signature" >
def < strong > visit_resource< / strong > (url)
< a class = "method-permalink" href = "#visit_resource%28url%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Visits a given URL and enqueues the links recovered
from the resource to be visited later.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L415" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "visit_urls-instance-method" >
< div class = "signature" >
def < strong > visit_urls< / strong >
< a class = "method-permalink" href = "#visit_urls-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Specifies the patterns that match the URLs to visit.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L116" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "visit_urls_like(&block:URI->Bool)-instance-method" >
< div class = "signature" >
def < strong > visit_urls_like< / strong > (& block : < a href = "../URI.html" > URI< / a > -> Bool)
< a class = "method-permalink" href = "#visit_urls_like%28%26block%3AURI-%3EBool%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Adds a given pattern to the < code > < a href = "../Arachnid/Agent.html#visit_urls-instance-method" > #visit_urls< / a > < / code > < / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L121" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "visit_urls_like(pattern)-instance-method" >
< div class = "signature" >
def < strong > visit_urls_like< / strong > (pattern)
< a class = "method-permalink" href = "#visit_urls_like%28pattern%29-instance-method" > #< / a >
< / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent/filters.cr#L126" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "visited?(url)-instance-method" >
< div class = "signature" >
def < strong > visited?< / strong > (url)
< a class = "method-permalink" href = "#visited%3F%28url%29-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Determines whether a URL was visited or not.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L238" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "visited_hosts-instance-method" >
< div class = "signature" >
def < strong > visited_hosts< / strong >
< a class = "method-permalink" href = "#visited_hosts-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Specifies the hosts which have been visited.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L233" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< div class = "entry-detail" id = "visited_links-instance-method" >
< div class = "signature" >
def < strong > visited_links< / strong >
< a class = "method-permalink" href = "#visited_links-instance-method" > #< / a >
< / div >
< div class = "doc" > < p > Specifies the links which have been visited.< / p > < / div >
< br / >
< div >
2019-06-30 23:53:02 +00:00
[< a href = "https://github.com/watzon/arachnid/blob/3c12c03fe8e72b5c5150f482d465546989fc805e/src/arachnid/agent.cr#L228" target = "_blank" > View source< / a > ]
2019-06-27 03:25:07 +00:00
< / div >
< / div >
< / div >
< / body >
< / html >