## ----setup, include = FALSE--------------------------------------------------- knitr::opts_chunk$set( collapse = TRUE, comment = "#>" ) library(rurl) ## ----------------------------------------------------------------------------- safe_parse_url("https://sub.example.co.uk/path?q=1") ## ----------------------------------------------------------------------------- get_scheme("https://sub.example.com") get_host("https://sub.example.com") get_path("https://sub.example.com/path/to/page") ## ----------------------------------------------------------------------------- get_domain("https://a.b.example.co.uk") ## ----------------------------------------------------------------------------- get_tld("https://foo.blogspot.com") ## ----------------------------------------------------------------------------- urls <- c("example.com", "http://example.com", NA) get_clean_url(urls) ## ----------------------------------------------------------------------------- get_host( "http://www.three.two.one.example.com", subdomain_levels_to_keep = 0 ) # www_handling default is "none" # Expected: "www.example.com" get_host( "http://three.two.one.example.com", www_handling = "strip", subdomain_levels_to_keep = 0 ) # Expected: "example.com" get_host("http://www.three.two.one.example.com", subdomain_levels_to_keep = 1) # Expected: "www.one.example.com" get_host( "http://three.two.one.example.com", www_handling = "strip", subdomain_levels_to_keep = 1 ) # Expected: "one.example.com" get_host( "http://www.three.two.one.example.com", www_handling = "keep", subdomain_levels_to_keep = 2 ) # Expected: "www.two.one.example.com" ## ----------------------------------------------------------------------------- get_clean_url( "http://www.deep.sub.example.com/some/path", subdomain_levels_to_keep = 0, www_handling = "keep" ) # Expected: "http://www.example.com/some/path" get_clean_url( "http://deep.sub.example.com/some/path", subdomain_levels_to_keep = 1 ) # Expected: "http://sub.example.com/some/path"