deshortify - npm Package Compare versions

Comparing version 0.4.0 to 0.5.0

CHANGELOG.md

 
+# v0.4.0
+
+* Skip GDPR interstitials
+
 # v0.3.0 (2017-12-06)
@@ -3,0 +7,0 @@

package.json

 {
   "name": "deshortify",
-  "version": "0.4.0",
+  "version": "0.5.0",
   "description": "Turns short URLs into long, meaningful, crap-less URLs.",
@@ -17,8 +17,15 @@ "main": "dist/deshortify.js",
   "scripts": {
-    "lint": "eslint src",
-    "lintfix": "eslint src --fix",
+    "lint": "prettier src/**.js",
+    "lintfix": "prettier src/**.js --write",
     "build": "rollup -c rollup-config.js"
   },
+  "prettier": {
+    "printWidth": 85,
+    "tabWidth": 4,
+    "useTabs": true,
+    "trailingComma": "es5",
+    "arrowParens": "always"
+  },
   "devDependencies": {
-    "eslint": "^4.0.0",
+    "prettier": "^1.17.1",
     "rollup": "^0.52.1",
@@ -25,0 +32,0 @@ "rollup-plugin-buble": "^0.18.0"

src/deshortify.js

@@ -0,12 +1,10 @@
+const http = require("http");
+const https = require("https");
+const parseUrl = require("url").parse;
+const resolveUrl = require("url").resolve;
+const formatUrl = require("url").format;
 
-const http       = require('http');
-const https      = require('https');
-const parseUrl   = require('url').parse;
-const resolveUrl = require('url').resolve;
-const formatUrl  = require('url').format;
-
 export default class Deshortifier {
-// module.exports =  class Deshortifier {
+	// module.exports =  class Deshortifier {
 	constructor(options = {}) {
-
 		this._cache = {};
@@ -16,10 +14,16 @@ this._verbose = !!options.verbose;
 		if (process) {
-			let deshortifyVersion = require('../package.json').version;
-			let nodejsVersion = process.release.name + '/' + process.version;
+			let deshortifyVersion = require("../package.json").version;
+			let nodejsVersion = process.release.name + "/" + process.version;
 			// Nice user agent for most URLs
-			this._userAgent = options.userAgent ||
-				('Deshortify/' + deshortifyVersion + ' ' + nodejsVersion + ' (+https://gitlab.com/IvanSanchez/deshortify)');
+			this._userAgent =
+				options.userAgent ||
+				"Deshortify/" +
+					deshortifyVersion +
+					" " +
+					nodejsVersion +
+					" (+https://gitlab.com/IvanSanchez/deshortify)";
 
 			// User agent for asshole websites which filter requests based on it (I'm looking at you, facebook)
-			this._assholeUserAgent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_2) AppleWebKit/602.3.12 (KHTML, like Gecko) Version/10.0.2 Safari/602.3.12";
+			this._assholeUserAgent =
+				"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_2) AppleWebKit/602.3.12 (KHTML, like Gecko) Version/10.0.2 Safari/602.3.12";
 		} else {
@@ -31,3 +35,2 @@ // User agent when running on browser is the same as the navigator's
 
-
 	// Returns a Promise for the deshortified URL
@@ -38,3 +41,3 @@ deshortify(url) {
 		if (!parsedUrl.protocol) {
-			url = 'http://' + url;
+			url = "http://" + url;
 		}
@@ -46,9 +49,9 @@
 	_deshortify(url, breadcrumbs = []) {
-
-		if (breadcrumbs.indexOf(url) !== -1 || // Circular loop, break it.
+		if (
+			breadcrumbs.indexOf(url) !== -1 || // Circular loop, break it.
 			breadcrumbs.length > 20 || // This looks like an infinite non-circular loop, break it.
-			this._skipUrl(url))	// URL whitelisted from being deshortified because nuisances
-		{
+			this._skipUrl(url) // URL whitelisted from being deshortified because nuisances
+		) {
 			if (this._verbose) {
-				console.log('Skipping: ', url);
+				console.log("Skipping: ", url);
 			}
@@ -61,3 +64,2 @@ return Promise.resolve(this._cleanUp(url));
 		if (url in this._cache) {
-
 			let cachedUrl = this._cache[url];
@@ -67,3 +69,5 @@
 			// return the promise already created.
-			if (cachedUrl instanceof Promise) { return cachedUrl; }
+			if (cachedUrl instanceof Promise) {
+				return cachedUrl;
+			}
 
@@ -75,3 +79,11 @@ if (cachedUrl === url) {
 			if (this._verbose) {
-				console.log('cached follow: ', url, ' → ', cachedUrl, ' (breadcrumbs lenght is ', breadcrumbs.length, ')');
+				console.log(
+					"cached follow: ",
+					url,
+					" → ",
+					cachedUrl,
+					" (breadcrumbs lenght is ",
+					breadcrumbs.length,
+					")"
+				);
 			}
@@ -81,6 +93,5 @@ return this._deshortify(cachedUrl, breadcrumbs);
 
-
 		let parsedUrl = parseUrl(url);
 
-		if (parsedUrl.protocol !== 'http:' && parsedUrl.protocol !== 'https:') {
+		if (parsedUrl.protocol !== "http:" && parsedUrl.protocol !== "https:") {
 			// Neither HTTP or HTTPS, just return whatever (might be ftp, or something more esoteric as irc or gopher)
@@ -91,41 +102,40 @@ return Promise.resolve(url);
 		let userAgent =
-			(parsedUrl.hostname === 'fb.me') ?
-			this._assholeUserAgent :
-			this._userAgent;
+			parsedUrl.hostname === "fb.me"
+				? this._assholeUserAgent
+				: this._userAgent;
 
-
 		// Handle header-based redirects
-		return this._cache[url] = new Promise((resolve)=>{
+		return (this._cache[url] = new Promise((resolve) => {
+			let backend = parsedUrl.protocol === "http:" ? http : https;
 
-			let backend =
-				parsedUrl.protocol === 'http:' ?
-				http:
-				https;
+			let request = backend.request(
+				{
+					method: "HEAD",
+					protocol: parsedUrl.protocol,
+					hostname: parsedUrl.hostname,
+					port: parsedUrl.port,
+					path: parsedUrl.path,
+					headers: {
+						"User-Agent": userAgent,
+					},
+				},
+				(res) => {
+					// 				console.log(res.headers);
 
-			let request = backend.request({
-				method:   'HEAD',
-				protocol: parsedUrl.protocol,
-				hostname: parsedUrl.hostname,
-				port:     parsedUrl.port,
-				path:     parsedUrl.path,
-				headers: {
-					'User-Agent': userAgent
-				}
-			}, (res)=>{
-// 				console.log(res.headers);
+					if ("location" in res.headers) {
+						// w00t! We've got a 30x response and a redirect!
+						let newUrl = resolveUrl(url, res.headers.location);
+						if (this._verbose && url !== newUrl) {
+							console.log("follow: ", url, " → ", newUrl);
+						}
+						this._cache[url] = newUrl;
+						return resolve(this._deshortify(newUrl, breadcrumbs));
+					}
 
-				if ('location' in res.headers) {	// w00t! We've got a 30x response and a redirect!
-					let newUrl = resolveUrl(url, res.headers.location);
-					if (this._verbose && (url !== newUrl)) {
-						console.log('follow: ', url, ' → ', newUrl);
-					}
-					this._cache[url] = newUrl;
-					return resolve(this._deshortify(newUrl, breadcrumbs));
+					// Giving up, looks like this was the final URL.
+					return resolve(this._cleanUp(url));
 				}
+			);
 
-				// Giving up, looks like this was the final URL.
-				return resolve(this._cleanUp(url));
-			});
-
-			request.on('error', ()=>{
+			request.on("error", () => {
 				// Panic and return the original url.
@@ -135,12 +145,8 @@ return resolve(this._cleanUp(url));
 
-			request.end();	// Actually send the request
-
-		});
+			request.end(); // Actually send the request
+		}));
 	}
 
-
 	// Cleans up spammy query parameters and hash bits.
 	_cleanUp(url) {
-		/// TODO
-
 		let parsedUrl = parseUrl(url, true);
@@ -153,21 +159,20 @@ let host = parsedUrl.host;
 		if (params) {
-// 			console.log(url);
-			params.forEach((name)=>{
+			// 			console.log(url);
+			params.forEach((name) => {
 				let val = parsedUrl.query[name];
 
-// 				console.log(host, ' / ', name, ' = ', val);
+				// 				console.log(host, ' / ', name, ' = ', val);
+				// 				console.log('Matches _source: ', name.match(/_source$/));
 
-// 				console.log('Matches _source: ', name.match(/_source$/));
-
 				if (
-					(typeof val !== 'string') || // e.g. http://www.businessinsider.com/...&r=US&IR=T&IR=T
-					(name.match(/_source$/)) ||
-					(name.match(/_medium$/)) ||
-					(name.match(/_term$/)) ||
-					(name.match(/_content$/)) ||
-					(name.match(/_campaign$/)) ||
-					(name.match(/_mchannel/)) ||
-					(name.match(/_kwd$/)) ||
-					(name === 'utm_cid') ||
-					(name === "cm_mmc") ||
+					typeof val !== "string" || // e.g. http://www.businessinsider.com/...&r=US&IR=T&IR=T
+					name.match(/_source$/) ||
+					name.match(/_medium$/) ||
+					name.match(/_term$/) ||
+					name.match(/_content$/) ||
+					name.match(/_campaign$/) ||
+					name.match(/_mchannel/) ||
+					name.match(/_kwd$/) ||
+					name === "utm_cid" ||
+					name === "cm_mmc" ||
 					(name === "tag" && val === "as.rss") ||
@@ -184,14 +189,14 @@ (name === "ref" && val === "rss") ||
 					(name === "spref" && val === "gr") ||
-					(val.match(/^twitter/)) ||
-					(val.match(/\.twitter$/)) ||
-					(val === "share_btn_tw") ||
+					val.match(/^twitter/) ||
+					val.match(/\.twitter$/) ||
+					val === "share_btn_tw" ||
 					(name === "platform" && val === "hootsuite") ||
-					(name === "mbid" && val === "social_retweet") ||	// New Yorker et al
-					(name === "mbid" && val === "social_twitter") ||	// New Yorker et al
+					(name === "mbid" && val === "social_retweet") || // New Yorker et al
+					(name === "mbid" && val === "social_twitter") || // New Yorker et al
 					(host === "www.youtube.com" && name === "feature") ||
 					(host === "www.nytimes.com" && name === "smid") ||
 					(host === "www.nytimes.com" && name === "seid") ||
-					(name === "awesm") ||	// Appears as a logger of awesm shortener, at least in storify
-					(name === "CMP" && val === "twt_gu") ||	// Guardian.co.uk short links
-					(name === "CMP" && val.match(/^soc_/)) ||	// Guardian.co.uk short links
+					name === "awesm" || // Appears as a logger of awesm shortener, at least in storify
+					(name === "CMP" && val === "twt_gu") || // Guardian.co.uk short links
+					(name === "CMP" && val.match(/^soc_/)) || // Guardian.co.uk short links
 					(name === "CMP" && val.match(/^Share_/)) ||
@@ -204,12 +209,14 @@ (name === "ex_cid" && val === "story-twitter") ||
 					(name === "soc_trk" && val === "tw") ||
-					(name === "hootPostID") ||
-					(name === "a" && val === "socialmedia") ||	// Meetup
+					name === "hootPostID" ||
+					(name === "a" && val === "socialmedia") || // Meetup
 					(host.match(/medium.com$/) && name === "source") ||
 					(host.match(/elpais.com$/) && name === "id_externo_rsoc") ||
 					(host.match(/washingtonpost.com$$/) && name === "postshare") ||
-					(host.match(/washingtonpost.com$$/) && name === "ss_tw-bottom") ||
-					(val === "rss-default") ||
-					(name === "__twitter_impression") ||
-					(name === 'src' && val === "syn"))
-				{
+					(host.match(/washingtonpost.com$$/) &&
+						name === "ss_tw-bottom") ||
+					val === "rss-default" ||
+					name === "__twitter_impression" ||
+					(name === "src" && val === "syn") ||
+					name === "fbclid"
+				) {
 					// Noop
@@ -223,3 +230,3 @@ return;
 
-// 		console.log('cleanup: ', JSON.stringify(parsedUrl.query), ' → ', JSON.stringify(cleanedParams) );
+		// 		console.log('cleanup: ', JSON.stringify(parsedUrl.query), ' → ', JSON.stringify(cleanedParams) );
 
@@ -232,6 +239,6 @@ // Replace query params and delete duplicated stuff
 
-// 		console.log(parsedUrl);
+		// 		console.log(parsedUrl);
 		var cleanedUrl = formatUrl(parsedUrl);
-		if (this._verbose && (url !== cleanedUrl)) {
-			console.log('cleanup: ', url, ' → ', cleanedUrl );
+		if (this._verbose && url !== cleanedUrl) {
+			console.log("cleanup: ", url, " → ", cleanedUrl);
 		}
@@ -241,7 +248,5 @@ return cleanedUrl;
 
-
 	// Returns boolean true if the passed URL should be skipped altogether,
 	// false otherwise
 	_skipUrl(url) {
-
 		let parsedUrl = parseUrl(url, true);
@@ -252,30 +257,24 @@
 		return (
-			host === "youtu.be"              ||	// Does not add more info
-			host === "spoti.fi"              ||	// Does not add more info
-			host === "4sq.com"               ||	// Does not add more info
-			host === "flic.kr"               ||	// Does not add more info
-			host === "untp.beer"             ||	// Does not add more info
-			host === "youtube.com"           ||	// Does not add more info
-			host === "www.elmundo.es"        ||	// El Mundo newspaper will only timeout and waste time
-			host === "www.economist.com"     ||	// "You are banned from this site.  Please contact via a different client configuration if you believe that this is a mistake."
-			host === "pbs.twimg.com"         ||	// Might trigger verbose errors if twitter is over capacity
-// 			host === "www.linkedin.com"      ||	// Used to redirect to login
-			host === "session.wikispaces.com" ||	// Infinite redirect loop with different URLs params each time
-
-			host.match(/twitter\.com$/)     ||	// Infinite redirect to login
-			host.match(/blogspot\.[a-z]{2-3}$/)    ||	// Will redirect to a nearby geolocated server
-			host.match(/facebook\.com$/)    ||	// Will redirect to fb.com/unsupportedbrowser due to user-agent
-			host.match(/\.nytimes\.com$/)   ||	// Infinite nocookies loop
-			host.match(/^www\.amazon\.$/)   ||	// 405 MethodNotAllowed
-
-			url.match(/subscribe/)	|| // Potential paywall
-			url.match(/nocookie/)	|| // Potential paywall/login
-			url.match(/gdpr/)	// Potential "GDPR consent" interstitial
+			url.length > 400 || // Just too long, maybe a REPL
+			host === "youtu.be" || // Does not add more info
+			host === "spoti.fi" || // Does not add more info
+			host === "4sq.com" || // Does not add more info
+			host === "flic.kr" || // Does not add more info
+			host === "untp.beer" || // Does not add more info
+			host === "youtube.com" || // Does not add more info
+			host === "www.elmundo.es" || // El Mundo newspaper will only timeout and waste time
+			host === "www.economist.com" || // "You are banned from this site.  Please contact via a different client configuration if you believe that this is a mistake."
+			host === "pbs.twimg.com" || // Might trigger verbose errors if twitter is over capacity
+			// 			host === "www.linkedin.com"      ||	// Used to redirect to login
+			host === "session.wikispaces.com" || // Infinite redirect loop with different URLs params each time
+			host.match(/twitter\.com$/) || // Infinite redirect to login
+			host.match(/blogspot\.[a-z]{2-3}$/) || // Will redirect to a nearby geolocated server
+			host.match(/facebook\.com$/) || // Will redirect to fb.com/unsupportedbrowser due to user-agent
+			host.match(/\.nytimes\.com$/) || // Infinite nocookies loop
+			host.match(/^www\.amazon\.$/) || // 405 MethodNotAllowed
+			url.match(/subscribe/) || // Potential paywall
+			url.match(/nocookie/) || // Potential paywall/login
+			url.match(/gdpr/) // Potential "GDPR consent" interstitial
 		);
-
 	}
-
-
 }
-
-

New alerts

Major refactor

Supply chain risk

Package has recently undergone a major refactor. It may be unstable or indicate significant internal changes. Use caution when updating to versions that include significant changes.

Found 1 instance in 1 package

Network access

Supply chain risk

This module accesses the network.

Found 2 instances in 1 package

Fixed alerts

Network access

Supply chain risk

This module accesses the network.

Found 2 instances in 1 package

Improved metrics

Total package byte prevSize

40097

increased by75.84%

Lines of code

499

increased by92.66%

Worsened metrics

Number of medium supply chain risk alerts

5

increased by150%

No dependency changes