I\'m currently creating a Node.js webscraper/proxy, but I\'m having trouble parsing relative Urls found in the scripting part of the source, I figured REGEX would do the tri
Note for OP, because he requested such a function: Change base_url to your proxy's basE URL in order to achieve the desired results.
Two functions will be shown below (the usage guide is contained within the code). Make sure that you don't skip any part of the explanation of this answer to fully understand the function's behaviour.
rel_to_abs(urL) - This function returns absolute URLs. When an absolute URL with a commonly trusted protocol is passed, it will immediately return this URL. Otherwise, an absolute URL is generated from the base_url and the function argument. Relative URLs are correctly parsed (../ ; ./ ; . ; //).replace_all_rel_by_abs - This function will parse all occurences of URLs which have a significant meaning in HTML, such as CSS url(), links and external resources. See the code for a full list of parsed instances. See this answer for an adjusted implementation to sanitise HTML strings from an external source (to embed in the document).rel_to_abs - Parsing relative URLs
function rel_to_abs(url){
/* Only accept commonly trusted protocols:
* Only data-image URLs are accepted, Exotic flavours (escaped slash,
* html-entitied characters) are not supported to keep the function fast */
if(/^(https?|file|ftps?|mailto|javascript|data:image\/[^;]{2,9};):/i.test(url))
return url; //Url is already absolute
var base_url = location.href.match(/^(.+)\/?(?:#.+)?$/)[0]+"/";
if(url.substring(0,2) == "//")
return location.protocol + url;
else if(url.charAt(0) == "/")
return location.protocol + "//" + location.host + url;
else if(url.substring(0,2) == "./")
url = "." + url;
else if(/^\s*$/.test(url))
return ""; //Empty = Return nothing
else url = "../" + url;
url = base_url + url;
var i=0
while(/\/\.\.\//.test(url = url.replace(/[^\/]+\/+\.\.\//g,"")));
/* Escape certain characters to prevent XSS */
url = url.replace(/\.$/,"").replace(/\/\./g,"").replace(/"/g,"%22")
.replace(/'/g,"%27").replace(//g,"%3E");
return url;
}
Cases / examples:
http://foo.bar. Already an absolute URL, thus returned immediately./doo Relative to the root: Returns the current root + provided relative URL../meh Relative to the current directory.../booh Relative to the parent directory.The function converts relative paths to ../, and performs a search-and-replace (http://domain/sub/anything-but-a-slash/../me to http://domain/sub/me).
replace_all_rel_by_abs - Convert all relevant occurences of URLs, event handlers are not replaced, because it's near-impossible to create a fast-and-secure filter to parse JavaScript.
This script is served with some comments inside. Regular Expressions are dynamically created, because an individual RE can have a size of 3000 characters. can be obfuscated in various ways, hence the size of the RE.
function replace_all_rel_by_abs(html){
/*HTML/XML Attribute may not be prefixed by these characters (common
attribute chars. This list is not complete, but will be sufficient
for this function (see http://www.w3.org/TR/REC-xml/#NT-NameChar). */
var att = "[^-a-z0-9:._]";
var entityEnd = "(?:;|(?!\\d))";
var ents = {" ":"(?:\\s| ?|*32"+entityEnd+"|*20"+entityEnd+")",
"(":"(?:\\(|*40"+entityEnd+"|*28"+entityEnd+")",
")":"(?:\\)|*41"+entityEnd+"|*29"+entityEnd+")",
".":"(?:\\.|*46"+entityEnd+"|*2e"+entityEnd+")"};
/* Placeholders to filter obfuscations */
var charMap = {};
var s = ents[" "]+"*"; //Short-hand for common use
var any = "(?:[^>\"']*(?:\"[^\"]*\"|'[^']*'))*?[^>]*";
/* ^ Important: Must be pre- and postfixed by < and >.
* This RE should match anything within a tag! */
/*
@name ae
@description Converts a given string in a sequence of the original
input and the HTML entity
@param String string String to convert
*/
function ae(string){
var all_chars_lowercase = string.toLowerCase();
if(ents[string]) return ents[string];
var all_chars_uppercase = string.toUpperCase();
var RE_res = "";
for(var i=0; i
*/
function cr(selector, attribute, marker, delimiter, end){
if(typeof selector == "string") selector = new RegExp(selector, "gi");
attribute = att + attribute;
marker = typeof marker == "string" ? marker : "\\s*=\\s*";
delimiter = typeof delimiter == "string" ? delimiter : "";
end = typeof end == "string" ? "?)("+end : ")(";
var re1 = new RegExp('('+attribute+marker+'")([^"'+delimiter+']+'+end+')', 'gi');
var re2 = new RegExp("("+attribute+marker+"')([^'"+delimiter+"]+"+end+")", 'gi');
var re3 = new RegExp('('+attribute+marker+')([^"\'][^\\s>'+delimiter+']*'+end+')', 'gi');
html = html.replace(selector, function(match){
return match.replace(re1, by).replace(re2, by).replace(re3, by);
});
}
/*
@name cri
@description Selects an attribute of a HTML element, and
performs a search-and-replace on certain values
@param String selector HTML element to match
@param String attribute RegExp-escaped; HTML element attribute to match
@param String front RegExp-escaped; attribute value, prefix to match
@param String flags Optional RegExp flags, default "gi"
@param String delimiter Optional RegExp-escaped; non-quote delimiters
@param String end Optional RegExp-escaped; forces the match to end
before an occurence of
*/
function cri(selector, attribute, front, flags, delimiter, end){
if(typeof selector == "string") selector = new RegExp(selector, "gi");
attribute = att + attribute;
flags = typeof flags == "string" ? flags : "gi";
var re1 = new RegExp('('+attribute+'\\s*=\\s*")([^"]*)', 'gi');
var re2 = new RegExp("("+attribute+"\\s*=\\s*')([^']+)", 'gi');
var at1 = new RegExp('('+front+')([^"]+)(")', flags);
var at2 = new RegExp("("+front+")([^']+)(')", flags);
if(typeof delimiter == "string"){
end = typeof end == "string" ? end : "";
var at3 = new RegExp("("+front+")([^\"'][^"+delimiter+"]*" + (end?"?)("+end+")":")()"), flags);
var handleAttr = function(match, g1, g2){return g1+g2.replace(at1, by2).replace(at2, by2).replace(at3, by2)};
} else {
var handleAttr = function(match, g1, g2){return g1+g2.replace(at1, by2).replace(at2, by2)};
}
html = html.replace(selector, function(match){
return match.replace(re1, handleAttr).replace(re2, handleAttr);
});
}
/* */
cri("|'"+ae("refresh")+"'"+any+">|"+ae("refresh")+"(?:"+ae(" ")+any+">|>))", "content", ae("url")+s+ae("=")+s, "i");
cr("<"+any+att+"href\\s*="+any+">", "href"); /* Linked elements */
cr("<"+any+att+"src\\s*="+any+">", "src"); /* Embedded elements */
cr("