Processing HTML with Scala as if XML

HTML.scala

import java.net.URL
import scala.xml.XML
import org.xml.sax.InputSource
import scala.xml.parsing.NoBindingFactoryAdapter
import org.ccil.cowan.tagsoup.jaxp.SAXFactoryImpl
import java.net.HttpURLConnection
import scala.xml.Node

object HTML {
  lazy val adapter = new NoBindingFactoryAdapter
  lazy val parser = (new SAXFactoryImpl).newSAXParser

  def load(url: URL, headers: Map[String, String] = Map.empty): Node = {
    val conn = url.openConnection().asInstanceOf[HttpURLConnection]
    for ((k, v) <- headers)
      conn.setRequestProperty(k, v)
    val source = new InputSource(conn.getInputStream)
    adapter.loadXML(source, parser)
  }
}

HtmlDemo.scala

import java.net.URL

val site = new URL("http://michel-daviot.blogspot.fr/")
  
val content = HTML.load(site)

for (
  a <- content \\ "a";
  href = a.attribute("href");
  if href.isDefined
) println(href.get)

pom.xml

<dependency>
  <groupId>org.ccil.cowan.tagsoup</groupId>
  <artifactId>tagsoup</artifactId>
  <version>1.2.1</version>
</dependency>

SetProxy.scala

object SetProxy {
  def apply(proxyConfig: (String, Int)) {
    val (host, port) = proxyConfig
    for (protocol <- Seq("http", "https")) {
      System.setProperty(s"$protocol.proxyPort", port.toString)
      System.setProperty(s"$protocol.proxyHost", host)
    }
  }
}

XMLLoad.scala

import java.net.URL
import scala.xml.XML

val site = new URL("http://michel-daviot.blogspot.fr/")
XML.load(site)
//Exception in thread "main" org.xml.sax.SAXParseException; lineNumber: 7; columnNumber: 265; 
//The entity name must immediately follow the '&' in the entity reference.